diff --git a/.github/dependabot.yml b/.github/dependabot.yml new file mode 100644 index 000000000..623d48cfa --- /dev/null +++ b/.github/dependabot.yml @@ -0,0 +1,12 @@ +version: 2 +updates: + - package-ecosystem: github-actions + directory: "/" + schedule: + interval: monthly + groups: + github-actions: + patterns: + - "*" + cooldown: + default-days: 7 diff --git a/.github/pull_request_template.md b/.github/pull_request_template.md new file mode 100644 index 000000000..34c3228c8 --- /dev/null +++ b/.github/pull_request_template.md @@ -0,0 +1,3 @@ +Resolves #NNNN. + +- [ ] I have read the [contributing guide](https://dateparser.readthedocs.io/en/latest/contributing.html) and [set up pre-commit](https://pre-commit.com/#quick-start). diff --git a/.github/workflows/cifuzz.yml b/.github/workflows/cifuzz.yml index 111913019..eec6e7f84 100644 --- a/.github/workflows/cifuzz.yml +++ b/.github/workflows/cifuzz.yml @@ -9,26 +9,26 @@ jobs: steps: - name: Build Fuzzers id: build - uses: google/oss-fuzz/infra/cifuzz/actions/build_fuzzers@master + uses: google/oss-fuzz/infra/cifuzz/actions/build_fuzzers@2820b2b71f58013e7f2ef2f87089433a075561d8 # master with: oss-fuzz-project-name: 'dateparser' language: python - name: Run Fuzzers - uses: google/oss-fuzz/infra/cifuzz/actions/run_fuzzers@master + uses: google/oss-fuzz/infra/cifuzz/actions/run_fuzzers@2820b2b71f58013e7f2ef2f87089433a075561d8 # master with: oss-fuzz-project-name: 'dateparser' language: python fuzz-seconds: 600 output-sarif: true - name: Upload Crash - uses: actions/upload-artifact@v4 + uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1 if: failure() && steps.build.outcome == 'success' with: name: artifacts path: ./out/artifacts - name: Upload Sarif if: always() && steps.build.outcome == 'success' - uses: github/codeql-action/upload-sarif@v2 + uses: github/codeql-action/upload-sarif@2892aa5e19bbd11bc0cff5427e3b750a04d9e3c2 # v4.38.2 with: # Path to SARIF file relative to the root of the repository sarif_file: cifuzz-sarif/results.sarif diff --git a/.github/workflows/cldr.yml b/.github/workflows/cldr.yml new file mode 100644 index 000000000..b0a1cdeb4 --- /dev/null +++ b/.github/workflows/cldr.yml @@ -0,0 +1,54 @@ +name: CLDR +on: + # CLDR releases come every few months, so a monthly check is timely enough. + schedule: + - cron: "43 5 1 * *" + workflow_dispatch: + +permissions: + contents: read + +jobs: + check: + name: Check for a newer CLDR release + if: github.ref == 'refs/heads/master' + runs-on: ubuntu-latest + timeout-minutes: 5 + permissions: + contents: read + issues: write + steps: + - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1 + with: + persist-credentials: false + - name: File an issue if the bundled CLDR data is out of date + env: + GH_TOKEN: ${{ github.token }} + GH_REPO: ${{ github.repository }} + LABEL: cldr-update + run: | + set -euo pipefail + current="$(grep -oP 'cldr_version = "\K[^"]+' dateparser_scripts/utils.py)" + # The latest release excludes alphas and betas. + latest="$(gh api repos/unicode-org/cldr-json/releases/latest --jq .tag_name)" + echo "Bundled: $current, latest: $latest." + if [ "$current" = "$latest" ]; then + exit 0 + fi + gh label create "$LABEL" --force --color 5319e7 \ + --description "Filed by the CLDR workflow" + existing="$(gh issue list --state open --label "$LABEL" --limit 1 \ + --json number --jq '.[0].number // empty')" + if [ -n "$existing" ]; then + echo "Already tracked in #$existing." + exit 0 + fi + gh issue create --title "Update the CLDR data to $latest" \ + --label "$LABEL" --label "Type: Maintenance" --body-file - < (now - new Date(date)) / 86400000; + + // Rate and abuse limits reset on the order of a minute, so waiting + // is enough; other errors are not worth retrying. + const retriable = new Set([403, 429, 500, 502, 503, 504]); + const sleep = ms => new Promise(resolve => setTimeout(resolve, ms)); + async function withRetries(description, call) { + for (let attempt = 1; ; attempt++) { + try { + return await call(); + } catch (error) { + if (!retriable.has(error.status) || attempt > RETRIES) throw error; + const reset = Number(error.response?.headers?.['x-ratelimit-reset']) * 1000 - Date.now(); + const after = Number(error.response?.headers?.['retry-after']) * 1000; + const wait = Math.min(Math.max(after || reset || RETRY_WAIT_MS, RETRY_WAIT_MS), 15 * RETRY_WAIT_MS); + core.info(`${description} failed with ${error.status}, retrying in ${Math.round(wait / 1000)}s (attempt ${attempt}/${RETRIES}).`); + await sleep(wait); + } + } + } + // Accounts excluded from search, deleted users and the like leave a + // signal unmeasurable rather than negative. + const orNull = promise => promise.catch(error => { + if ([404, 410, 422].includes(error.status)) return null; + throw error; + }); + + async function score(pr) { + const author = pr.user.login; + + // author_association only reports membership of the organisation + // that owns this repository, and only when it is public, so trust + // in the author is established here instead. + const trustedOrg = (await Promise.all(TRUSTED_ORGS.map(org => + orNull(withRetries(`Checking public membership of ${org}`, () => + github.rest.orgs.checkPublicMembershipForUser({ org, username: author }), + )).then(response => response && org), + ))).find(Boolean); + if (trustedOrg) { + core.info(`Skipping PR #${pr.number} by ${author} (public member of ${trustedOrg}).`); + return; + } + // Repeating a qualifier narrows the search instead of widening it, + // hence the explicit disjunction. + const trustedMerges = await orNull(withRetries('Counting merged PRs in trusted organisations', () => + github.rest.search.issuesAndPullRequests({ + q: `author:${author} type:pr is:merged` + + ` (${TRUSTED_ORGS.map(org => `org:${org}`).join(' OR ')})`, + advanced_search: 'true', per_page: 1, + }).then(response => response.data.total_count), + )); + if (trustedMerges >= MIN_TRUSTED_MERGES) { + core.info(`Skipping PR #${pr.number} by ${author}` + + ` (${trustedMerges} PR(s) merged into ${TRUSTED_ORGS.join(', ')}).`); + return; + } + + // Signal 1: pull requests closed unmerged elsewhere, recently. + const search = await orNull(withRetries('Searching for PRs by the author', () => + github.rest.search.issuesAndPullRequests({ + q: `author:${author} type:pr`, advanced_search: 'true', + sort: 'created', order: 'desc', per_page: 100, + }).then(response => response.data), + )); + let rejections = null; + if (search) { + rejections = search.items.filter(item => { + const itemOwner = item.repository_url.split('/repos/')[1].split('/')[0].toLowerCase(); + return itemOwner !== author.toLowerCase() + && item.state === 'closed' && !item.pull_request?.merged_at + && daysAgo(item.created_at) <= REJECTION_WINDOW_DAYS; + }).map(item => item.html_url); + } + + // Signal 2: how their recent comments across GitHub read. + const events = []; + for (let page = 1; page <= EVENT_PAGES; page++) { + const batch = await orNull(withRetries(`Reading public events page ${page}`, () => + github.rest.activity.listPublicEventsForUser({ + username: author, per_page: 100, page, + }).then(response => response.data), + )); + if (!batch?.length) break; + events.push(...batch); + if (batch.length < 100) break; + } + const comments = events + .filter(event => ['IssueCommentEvent', 'PullRequestReviewCommentEvent'].includes(event.type)) + .map(event => event.payload?.comment?.body) + .filter(Boolean); + + // Signal 3: how many unrelated projects they open pull requests + // against in a single week. Breadth rather than volume: a focused + // contributor sends many pull requests to few repositories, while + // an unattended agent sprays a few across many. Taken from the + // event feed, which unlike search covers authors that search + // refuses to return. + const weeks = {}; + for (const event of events) { + if (event.type !== 'PullRequestEvent' || event.payload?.action !== 'opened') continue; + const name = event.repo?.name; + if (!name || name.toLowerCase().startsWith(`${author.toLowerCase()}/`)) continue; + const week = Math.floor(new Date(event.created_at) / (7 * 86400000)); + (weeks[week] ??= new Set()).add(name); + } + const breadth = events.length + ? Math.max(0, ...Object.values(weeks).map(repos => repos.size)) + : null; + const STRUCTURE = [/^\s*#{2,3}\s/m, /^\s*[-*]\s.+\n\s*[-*]\s/m, /\*\*[^*]+\*\*/, /```/]; + const ACKNOWLEDGEMENT = [ + /thanks for (the )?(review|feedback|pointing|catching|flagging|clarif)/i, + /you'?re (absolutely )?right/i, /great catch/i, /that makes sense/i, + /i'?ll (continue|investigate|update|submit|look into|make sure)/i, + /let me know (if|whether)/i, /happy to (update|adjust|revise|change)/i, + /i understand that/i, /thanks for your time/i, /just following up/i, + /hope (this|that) helps/i, /please let me know/i, /i'?ve (updated|addressed|fixed)/i, + ]; + let voice = null; + if (comments.length >= MIN_COMMENTS) { + const chars = comments.reduce((total, body) => total + body.length, 0); + const rate = patterns => comments.filter(body => patterns.some(re => re.test(body))).length / comments.length; + voice = { + comments: comments.length, + structure: rate(STRUCTURE), + acknowledgement: rate(ACKNOWLEDGEMENT), + emDashPerKChar: 1000 * comments.reduce((total, body) => total + (body.match(/—/g) || []).length, 0) / chars, + }; + } + + const reasons = []; + if (rejections && rejections.length >= MIN_REJECTIONS) { + reasons.push(`${rejections.length} PR(s) of theirs closed unmerged elsewhere in the last` + + ` ${REJECTION_WINDOW_DAYS} days: ${rejections.slice(0, 10).join(' ')}`); + } + if (voice && (voice.structure > VOICE.structure + || voice.emDashPerKChar > VOICE.emDashPerKChar + || voice.acknowledgement > VOICE.acknowledgement)) { + reasons.push(`comment style over ${voice.comments} recent comments:` + + ` ${(100 * voice.structure).toFixed(0)}% structured,` + + ` ${(100 * voice.acknowledgement).toFixed(0)}% stock acknowledgements,` + + ` ${voice.emDashPerKChar.toFixed(2)} em dashes per 1000 characters`); + } + if (breadth !== null && breadth > MAX_REPOS_PER_WEEK) { + reasons.push(`opened pull requests against ${breadth} unrelated repositories within a week`); + } + if (AGENT_BRANCH.test(pr.head?.ref || '')) { + reasons.push(`branch name carries an agent prefix: ${pr.head.ref}`); + } + + await core.summary + .addHeading(`PR #${pr.number} by ${author}`, 3) + .addList([ + rejections === null + ? 'recent rejections elsewhere: unmeasurable, the author cannot be searched' + : `recent rejections elsewhere: ${rejections.length}`, + voice === null + ? `comment style: unmeasurable, fewer than ${MIN_COMMENTS} recent comments found` + : `comment style: ${(100 * voice.structure).toFixed(0)}% structured,` + + ` ${(100 * voice.acknowledgement).toFixed(0)}% stock acknowledgements,` + + ` ${voice.emDashPerKChar.toFixed(2)} em dashes per 1000 characters` + + ` over ${voice.comments} comments`, + breadth === null + ? 'repositories per week: unmeasurable, no public events found' + : `repositories per week, at most: ${breadth}`, + `branch: ${pr.head?.ref ?? 'unknown'}`, + `verdict: ${reasons.length ? `closed as ${LABEL}` : 'left open'}`, + ]) + .addRaw(reasons.length ? `\n${reasons.map(reason => `- ${reason}`).join('\n')}\n` : '') + .write(); + + if (!reasons.length) { + core.info(`Leaving PR #${pr.number} open.`); + return; + } + await withRetries('Adding the label', () => + github.rest.issues.addLabels({ owner, repo, issue_number: pr.number, labels: [LABEL] }), + ); + await withRetries('Closing the PR', () => + github.rest.pulls.update({ owner, repo, pull_number: pr.number, state: 'closed' }), + ); + core.info(`Closed PR #${pr.number} as ${LABEL}: ${reasons.join(' | ')}`); + } + + // A maintainer who has commented on, reviewed or reopened a pull + // request has already made the call. + async function attended(pr) { + const timeline = await withRetries(`Reading the timeline of PR #${pr.number}`, () => + github.paginate(github.rest.issues.listEventsForTimeline, { + owner, repo, issue_number: pr.number, per_page: 100, + }), + ); + return timeline.some(event => event.event === 'reopened' + || (['commented', 'reviewed'].includes(event.event) + && event.user?.login !== pr.user.login && event.user?.type !== 'Bot')); + } + + const opened = context.payload.pull_request; + const prs = opened ? [opened] : (await withRetries('Listing open PRs', () => + github.paginate(github.rest.pulls.list, { + owner, repo, state: 'open', sort: 'created', direction: 'desc', per_page: 100, + }), + )).filter(pr => daysAgo(pr.created_at) <= RECHECK_WINDOW_DAYS); + core.info(`Scoring ${prs.length} PR(s).`); + for (const pr of prs) { + if (pr.user.type === 'Bot' + || ['MEMBER', 'OWNER', 'COLLABORATOR'].includes(pr.author_association)) { + core.info(`Skipping PR #${pr.number} by ${pr.user.login} (${pr.user.type}, ${pr.author_association}).`); + continue; + } + if (!opened && await attended(pr)) { + core.info(`Skipping PR #${pr.number} by ${pr.user.login} (a maintainer has already looked at it).`); + continue; + } + await score(pr); + } diff --git a/.github/workflows/codspeed.yml b/.github/workflows/codspeed.yml new file mode 100644 index 000000000..4acf16db6 --- /dev/null +++ b/.github/workflows/codspeed.yml @@ -0,0 +1,58 @@ +name: CodSpeed +on: + push: + branches: + - master + pull_request: + branches: + - master + paths: + - dateparser/** + - dateparser_data/** + - tests/benchmarks/** + - pytest.ini + - tox.ini + - pyproject.toml + - .github/workflows/codspeed.yml + # Lets CodSpeed trigger a run to collect the initial baseline. + workflow_dispatch: + +# Superseded runs of the same pull request are cancelled. Outside pull requests +# the group is unique per run, so a master baseline is never cancelled. +concurrency: + group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.run_id }} + cancel-in-progress: true + +permissions: + contents: read + +jobs: + benchmarks: + name: Run benchmarks + runs-on: ubuntu-latest + # A reintroduced #1335-style regression makes the benchmarks orders of + # magnitude slower, so cap the job instead of letting it run for hours. + timeout-minutes: 30 + permissions: + contents: read + id-token: write + steps: + - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1 + with: + persist-credentials: false + - name: Set up Python + uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7.0.0 + with: + python-version: "3.13" + - name: Install dependencies + run: | + python -m pip install --upgrade pip + pip install tox + tox -e benchmark --notest + - name: Run benchmarks + uses: CodSpeedHQ/action@373d6868929f444bc08d901fd0eb0ad52a8875ea # v5.2.1 + with: + mode: simulation + # The step above already built the environment, so the measured command + # only runs pytest instead of packaging and installing again. + run: tox -e benchmark --skip-pkg-install diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml index b17e70667..afe5591d4 100644 --- a/.github/workflows/main.yml +++ b/.github/workflows/main.yml @@ -6,6 +6,15 @@ on: pull_request: branches: - master + # Called by the Nightly workflow, which re-runs these same legs daily. The + # schedule lives there and not here because GitHub disables a workflow that + # has a schedule after 60 days without repository activity, and a disabled + # workflow answers none of its triggers, which would take pull request runs + # down with it. + workflow_call: +permissions: + contents: read + jobs: build: name: Build @@ -16,10 +25,13 @@ jobs: include: - python-version: "3.14" toxenv: pre-commit + - python-version: "3.10" + toxenv: mypy - python-version: "3.10" toxenv: min - python-version: "3.10" toxenv: min-all + - python-version: "3.10" - python-version: "3.11" - python-version: "3.12" - python-version: "3.14" @@ -30,10 +42,18 @@ jobs: toxenv: docs - python-version: "3.14" toxenv: twinecheck + - python-version: "3.13" + toxenv: py + timezone: "Pacific/Auckland" + - python-version: "3.13" + toxenv: py + timezone: "Pacific/Fiji" steps: - - uses: actions/checkout@v3 + - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1 + with: + persist-credentials: false - name: 'Set up Python ${{ matrix.python-version }}' - uses: actions/setup-python@v5 + uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7.0.0 with: python-version: ${{ matrix.python-version }} - name: Install language-pack-fr @@ -43,8 +63,14 @@ jobs: python -m pip install --upgrade pip pip install tox - name: Run tests - run: tox -e ${{ matrix.toxenv || 'py' }} + run: | + TZ=${{ matrix.timezone || 'UTC' }} echo "Running tests with timezone: $TZ" + TZ=${{ matrix.timezone || 'UTC' }} tox -e ${{ matrix.toxenv || 'py' }} - name: Upload coverage.xml to codecov - uses: codecov/codecov-action@v5 + # A nightly run, scheduled or dispatched, re-tests a commit that already + # has a coverage report, so uploading again only repeats the Codecov + # notification for that SHA. + if: github.event_name == 'push' || github.event_name == 'pull_request' + uses: codecov/codecov-action@303a32d7a59b442fa8d48b6a1cc6825c09c847a5 # v7.1.1 with: token: ${{ secrets.CODECOV_TOKEN }} diff --git a/.github/workflows/nightly.yml b/.github/workflows/nightly.yml new file mode 100644 index 000000000..8ed49ce86 --- /dev/null +++ b/.github/workflows/nightly.yml @@ -0,0 +1,78 @@ +name: Nightly +on: + # Dependency, time zone database and calendar drift arrives with no commit + # behind it, and tests that only fail on the 31st of a month need a run on + # every date; a fixed weekday lands on a 31st about once a year. Off the hour, + # which GitHub names as a high-load window, and early in the UTC day so that + # the Pacific/Auckland and Pacific/Fiji legs stay on the same calendar date as + # the rest of the matrix. + schedule: + - cron: "17 4 * * *" + # Runs the same legs on demand, which is also the only way to exercise the + # reporting below before it is needed. GitHub disables this workflow after 60 + # days without repository activity; re-enable it from the Actions tab or with + # `gh workflow enable nightly.yml`, since a disabled workflow answers no + # triggers at all. + workflow_dispatch: + +# The called matrix only checks out and tests; the report job below asks for +# the one extra scope it needs. +permissions: + contents: read + +jobs: + build: + uses: ./.github/workflows/main.yml + + report: + name: Report failure + needs: build + # A push or pull request failure is already in front of whoever caused it. + # A failure with no commit behind it has nowhere to land but a single + # notification email to whoever last edited the schedule. A cancelled build + # counts, since a leg that hangs until GitHub kills it is a failure too. + # Master only, so that a dispatch on a work branch can neither file a + # report nor mask the real one. + if: >- + (needs.build.result == 'failure' || needs.build.result == 'cancelled') + && github.ref == 'refs/heads/master' + runs-on: ubuntu-latest + permissions: + issues: write + steps: + - name: File a tracking issue unless one is already open + env: + GH_TOKEN: ${{ github.token }} + GH_REPO: ${{ github.repository }} + TITLE: The nightly build is failing + LABEL: nightly-failure + RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }} + SHA: ${{ github.sha }} + run: | + set -euo pipefail + # One issue per outage: a daily comment stream would only be one more + # signal to ignore. The label, not the title, identifies the tracking + # issue, so retitling it to record the cause does not defeat the + # check; --force makes creating the label idempotent. A transient + # listing failure must not stop the report, since a duplicate issue + # is cheaper than silence. + gh label create "$LABEL" --force --color d93f0b \ + --description "Filed by the Nightly workflow" + existing="$(gh issue list --state open --label "$LABEL" --limit 1 \ + --json number --jq '.[0].number // empty' || true)" + if [ -n "$existing" ]; then + echo "Already tracked in #$existing." + exit 0 + fi + gh issue create --title "$TITLE" --label "$LABEL" \ + --label "Type: Maintenance" --body-file - < -
- - Dateparser - -
- +
+ + +.. image:: artwork/dateparser-logo.png + :alt: Dateparser + :width: 500 + :target: https://github.com/scrapinghub/dateparser + -

Python parser for human readable dates

+**Python parser for human readable dates** + + +.. raw:: html + +
+ + +.. docs-include-marker + + +.. raw:: html

@@ -41,7 +53,7 @@ Key Features ------------- +============ - Support for almost every existing date format: absolute dates, relative dates (``"two weeks ago"`` or ``"tomorrow"``), timestamps, @@ -52,24 +64,23 @@ Key Features - Customizable behavior through `settings `__. - Support for `non-Gregorian calendar - systems `__. + systems <#supported-calendars>`__. - Support for dates with timezones abbreviations or UTC offsets (``"August 14, 2015 EST"``, ``"21 July 2013 10:15 pm +0500"``...) -- `Search - dates `__ +- `Search dates <#search-for-dates-in-longer-chunks-of-text>`__ in longer texts. - Time span detection for expressions like "past month", "last week". Online demo ------------ +=========== Do you want to try it out without installing any dependency? Now you can test -it quickly by visiting `this online demo `__! +it quickly by visiting `this online demo `__! How To Use ----------- +========== The most straightforward way to parse dates with **dateparser** is to use the ``dateparser.parse()`` function, that wraps around most of the @@ -94,8 +105,7 @@ functionality of the module. >>> dateparser.parse('January 12, 2012 10:00 PM EST') datetime.datetime(2012, 1, 12, 22, 0, tzinfo=) -As you can see, **dateparser** works with different date formats, but it -can also be used directly with strings in different languages: +**dateparser** also works with strings in different languages: .. code:: python @@ -117,6 +127,184 @@ can also be used directly with strings in different languages: >>> dateparser.parse('2小时前') # Chinese (2 hours ago), current time: 22:30 datetime.datetime(2018, 5, 31, 20, 30) +You can specify the language(s), if known, using the ``languages`` argument. +In this case, given languages are used and language detection is skipped: + +.. code:: python + + >>> dateparser.parse('2015, Ago 15, 1:08 pm', languages=['pt', 'es']) + datetime.datetime(2015, 8, 15, 13, 8) + +If you know the possible formats of the dates, you can use the +``date_formats`` argument: + +.. code:: python + + >>> dateparser.parse('22 Décembre 2010', date_formats=['%d %B %Y']) + datetime.datetime(2010, 12, 22, 0, 0) + +Relative Dates +-------------- + +.. code:: python + + >>> from dateparser import parse + >>> parse('1 hour ago') + datetime.datetime(2015, 5, 31, 23, 0) + >>> parse('Il ya 2 heures') # French (2 hours ago) + datetime.datetime(2015, 5, 31, 22, 0) + >>> parse('1 anno 2 mesi') # Italian (1 year 2 months) + datetime.datetime(2014, 4, 1, 0, 0) + >>> parse('yaklaşık 23 saat önce') # Turkish (23 hours ago) + datetime.datetime(2015, 5, 31, 1, 0) + >>> parse('Hace una semana') # Spanish (a week ago) + datetime.datetime(2015, 5, 25, 0, 0) + >>> parse('2小时前') # Chinese (2 hours ago) + datetime.datetime(2015, 5, 31, 22, 0) + +.. note:: Testing above code might return different values depending on your environment's current date and time. + +.. note:: For the ``Finnish`` language, please specify ``settings={'SKIP_TOKENS': []}`` to correctly parse relative dates. + +Date Order +---------- + +.. code:: python + + >>> # parsing ambiguous date + >>> parse('02-03-2016') # assumes english language, uses MDY date order + datetime.datetime(2016, 2, 3, 0, 0) + >>> parse('le 02-03-2016') # detects french, uses DMY date order + datetime.datetime(2016, 3, 2, 0, 0) + +.. note:: Ordering is not locale-based — do not expect ``DMY`` order for UK/Australia English. + You can specify date order explicitly: + + .. code:: python + + >>> parse('18-12-15 06:00', settings={'DATE_ORDER': 'DMY'}) + datetime.datetime(2015, 12, 18, 6, 0) + +For more on date order, see the `settings documentation `__. + +Timezone and UTC Offset +----------------------- + +By default, `dateparser` returns a timezone-aware ``datetime`` if a timezone is +present in the date string. Otherwise it returns a naive ``datetime`` object. + +.. code:: python + + >>> parse('January 12, 2012 10:00 PM EST') + datetime.datetime(2012, 1, 12, 22, 0, tzinfo=) + + >>> parse('January 12, 2012 10:00 PM -0500') + datetime.datetime(2012, 1, 12, 22, 0, tzinfo=) + + >>> parse('2 hours ago EST') + datetime.datetime(2017, 3, 10, 15, 55, 39, 579667, tzinfo=) + +If the date has no timezone name/abbreviation or offset, you can specify it +using the ``TIMEZONE`` setting: + +.. code:: python + + >>> parse('January 12, 2012 10:00 PM', settings={'TIMEZONE': 'US/Eastern'}) + datetime.datetime(2012, 1, 12, 22, 0) + + >>> parse('January 12, 2012 10:00 PM', settings={'TIMEZONE': 'US/Eastern', 'RETURN_AS_TIMEZONE_AWARE': True}) + datetime.datetime(2012, 1, 12, 22, 0, tzinfo=) + + >>> parse('10:00 am', settings={'TIMEZONE': 'EST', 'TO_TIMEZONE': 'EDT'}) + datetime.datetime(2016, 9, 25, 11, 0) + + >>> parse('10:00 am EST', settings={'TO_TIMEZONE': 'EDT'}) + datetime.datetime(2017, 3, 12, 11, 0, tzinfo=) + +For more on timezones, see the `settings documentation `__. + +Incomplete Dates +---------------- + +.. code:: python + + >>> from dateparser import parse + >>> parse('December 2015') # default behavior + datetime.datetime(2015, 12, 16, 0, 0) + >>> parse('December 2015', settings={'PREFER_DAY_OF_MONTH': 'last'}) + datetime.datetime(2015, 12, 31, 0, 0) + >>> parse('December 2015', settings={'PREFER_DAY_OF_MONTH': 'first'}) + datetime.datetime(2015, 12, 1, 0, 0) + + >>> parse('March') + datetime.datetime(2015, 3, 16, 0, 0) + >>> parse('March', settings={'PREFER_DATES_FROM': 'future'}) + datetime.datetime(2016, 3, 16, 0, 0) + + >>> import dateparser + >>> dateparser.parse("2015") # default behavior + datetime.datetime(2015, 3, 27, 0, 0) + >>> dateparser.parse("2015", settings={"PREFER_MONTH_OF_YEAR": "last"}) + datetime.datetime(2015, 12, 27, 0, 0) + >>> dateparser.parse("2015", settings={"PREFER_MONTH_OF_YEAR": "current"}) + datetime.datetime(2015, 3, 27, 0, 0) + +You can also ignore incomplete dates by setting the ``STRICT_PARSING`` flag: + +.. code:: python + + >>> parse('December 2015', settings={'STRICT_PARSING': True}) + None + +For more on handling incomplete dates, see the `settings documentation `__. + +Search for Dates in Longer Chunks of Text +----------------------------------------- + +.. warning:: Support for date searching is limited and needs improvement. + Contributions are welcome — see `contributing `__. + +You can extract dates from longer strings of text. Results are returned as a +list of ``(substring, datetime)`` tuples: + +.. code:: python + + >>> from dateparser.search import search_dates + >>> search_dates('Today is 25 of October 2017, so the 27th is in 2 days.') + [('25 of October 2017', datetime.datetime(2017, 10, 25, 0, 0)), ('the 27th is in 2 days', datetime.datetime(2017, 10, 27, 0, 0))] + +Pass ``languages`` when you know them: language detection is slow and +error-prone on short text. If no date is found, ``None`` is returned: + +.. code:: python + + >>> search_dates('Lancé le 4 octobre 1957.', languages=['fr']) + [('le 4 octobre 1957', datetime.datetime(1957, 10, 4, 0, 0))] + >>> search_dates('Rien à voir.', languages=['fr']) + None + +See the `API reference +`__ +for other parameters, such as ``strategy``. + +Time Span Detection +------------------- + +The ``search_dates`` function can also detect time spans such as "past month" +or "last week". When ``RETURN_TIME_SPAN`` is enabled it returns start and end +dates for the detected period. + +For example, assuming the current date and time is `December 7, 2024, 15:30`: + +.. code:: python + + >>> search_dates("Messages from the past month", settings={'RETURN_TIME_SPAN': True}) + [('past month (start)', datetime.datetime(2024, 11, 7, 15, 30)), + ('past month (end)', datetime.datetime(2024, 12, 7, 15, 30))] + +Settings +-------- + You can control multiple behaviors by using the ``settings`` parameter: .. code:: python @@ -133,12 +321,11 @@ You can control multiple behaviors by using the ``settings`` parameter: >>> dateparser.parse('tomorrow', settings={'RELATIVE_BASE': datetime.datetime(1992, 1, 1)}) datetime.datetime(1992, 1, 2, 0, 0) -To see more examples on how to use the ``settings``, check the `settings -section `__ -in the docs. +To see all available settings, check the `settings +documentation `__. False positives -^^^^^^^^^^^^^^^ +--------------- **dateparser** will do its best to return a date, dealing with multiple formats and different locales. For that reason it is important that the input is a valid date, otherwise it could return false positives. @@ -155,7 +342,7 @@ are executed, you can do so through the `settings PARSERS `_. Installation ------------- +============ Dateparser supports Python 3.10+. You can install it by doing: @@ -163,21 +350,83 @@ Dateparser supports Python 3.10+. You can install it by doing: $ pip install dateparser -If you want to use the jalali or hijri calendar, you need to install the +If you want to use a non-Gregorian calendar, you need to install the ``calendars`` extra: :: $ pip install dateparser[calendars] +Supported Calendars +=================== + +Apart from the Gregorian calendar, `dateparser` supports the `Persian Jalali +calendar`, the `Hijri/Islamic calendar`, the `French Republican calendar` and +the `Minguo calendar`. To use the first three, install the ``calendars`` extra +(see `Installation`_). + +Example using the `Persian Jalali calendar +`_: + +.. code:: python + + >>> from dateparser.calendars.jalali import JalaliCalendar + >>> JalaliCalendar('جمعه سی ام اسفند ۱۳۸۷').get_date() + DateData(date_obj=datetime.datetime(2009, 3, 20, 0, 0), period='day', locale=None, parts=('year', 'month', 'day')) + +Example using the `Hijri/Islamic calendar +`_: + +.. code:: python + + >>> from dateparser.calendars.hijri import HijriCalendar + >>> HijriCalendar('17-01-1437 هـ 08:30 مساءً').get_date() + DateData(date_obj=datetime.datetime(2015, 10, 30, 20, 30), period='day', locale=None, parts=('year', 'month', 'day', 'time')) + +Example using the `French Republican calendar +`_: + +.. code:: python + + >>> from dateparser.calendars.french_republican import FrenchRepublicanCalendar + >>> FrenchRepublicanCalendar('18 brumaire an VIII').get_date() + DateData(date_obj=datetime.datetime(1799, 11, 9, 0, 0), period='day', locale=None) + +Example using the `Minguo calendar +`_: + +.. code:: python + + >>> from dateparser.calendars.minguo import MinguoCalendar + >>> MinguoCalendar('民國101年5月25日 08:36').get_date() + DateData(date_obj=datetime.datetime(2012, 5, 25, 8, 36), period='day', locale=None) + +Dependencies +============ + +`dateparser` relies on the following libraries: + +* dateutil_'s module ``relativedelta`` for its freshness parser. +* convertdate_ to convert *Jalali* and *French Republican* dates to + *Gregorian*. +* hijridate_ to convert *Hijri* dates to *Gregorian*. +* tzlocal_ to reliably get local timezone. +* ruamel.yaml_ (optional) for operations on language files. + +.. _dateutil: https://pypi.python.org/pypi/python-dateutil +.. _convertdate: https://pypi.python.org/pypi/convertdate +.. _hijridate: https://pypi.python.org/pypi/hijridate +.. _tzlocal: https://pypi.python.org/pypi/tzlocal +.. _ruamel.yaml: https://pypi.python.org/pypi/ruamel.yaml + Common use cases ----------------- +================ **dateparser** can be used for a wide variety of purposes, but it stands out when it comes to: Consuming data from different sources: -^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +-------------------------------------- - **Scraping**: extract dates from different places with several different formats and languages @@ -188,7 +437,7 @@ Consuming data from different sources: different files (PDF, CSV, etc.) to other formats (database, etc). Offering natural interaction with users: -^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +---------------------------------------- - **Tooling and CLI**: allow users to write “3 days ago” to retrieve information. @@ -197,7 +446,7 @@ Offering natural interaction with users: - **Bots**: allow users to interact with a bot easily You may also like... --------------------- +==================== - `price-parser `__ - A small library for extracting price and currency from raw text @@ -209,6 +458,6 @@ You may also like... scraping framework License -------- +======= `BSD3-Clause `__ diff --git a/SECURITY.md b/SECURITY.md new file mode 100644 index 000000000..ce5a8b780 --- /dev/null +++ b/SECURITY.md @@ -0,0 +1,13 @@ +# Security Policy + +## Supported Versions + +| Version | Supported | +| --------- | ------------------ | +| 1.4.x | :white_check_mark: | +| < 1.4.x | :x: | + +## Reporting a Vulnerability + +Please report the vulnerability using +https://github.com/scrapinghub/dateparser/security/advisories/new. diff --git a/artwork/dateparser-logo.png b/artwork/dateparser-logo.png index ac052cf57..9ee7c6924 100644 Binary files a/artwork/dateparser-logo.png and b/artwork/dateparser-logo.png differ diff --git a/artwork/dateparser.xcf b/artwork/dateparser.xcf index f5e0a074f..504ebb462 100644 Binary files a/artwork/dateparser.xcf and b/artwork/dateparser.xcf differ diff --git a/conftest.py b/conftest.py deleted file mode 100644 index 21040d96d..000000000 --- a/conftest.py +++ /dev/null @@ -1,9 +0,0 @@ -def pytest_collection_modifyitems(session, config, items): - # Avoid executing tests when executing `--flake8` flag (pytest-flake8) - try: - from pytest_flake8 import Flake8Item - - if config.getoption("--flake8"): - items[:] = [item for item in items if isinstance(item, Flake8Item)] - except ImportError: - pass diff --git a/dateparser/__init__.py b/dateparser/__init__.py index 3629ac057..808a28d8f 100644 --- a/dateparser/__init__.py +++ b/dateparser/__init__.py @@ -1,21 +1,27 @@ -__version__ = "1.2.2" +__version__ = "1.4.3" -from .conf import apply_settings -from .date import DateDataParser +from collections.abc import Callable, Iterable +from datetime import datetime +from typing import Any + +from ._parts_of_day import PartOfDay as PartOfDay +from ._parts_of_day import PartsOfDay as PartsOfDay +from .conf import Settings, apply_settings +from .date import DateDataParser as DateDataParser _default_parser = DateDataParser() @apply_settings def parse( - date_string, - date_formats=None, - languages=None, - locales=None, - region=None, - settings=None, - detect_languages_function=None, -): + date_string: str, + date_formats: Iterable[str] | None = None, + languages: Iterable[str] | None = None, + locales: Iterable[str] | None = None, + region: str | None = None, + settings: Settings | dict[str, Any] | None = None, + detect_languages_function: Callable[..., list[str]] | None = None, +) -> datetime | None: """Parse date and time from given date string. :param date_string: @@ -59,6 +65,7 @@ def parse( ``ValueError``: Unknown Language, ``TypeError``: Languages argument must be a list, ``SettingValidationError``: A provided setting is not valid. """ + assert isinstance(settings, Settings) parser = _default_parser if ( @@ -77,6 +84,5 @@ def parse( ) data = parser.get_date_data(date_string, date_formats) - - if data: - return data["date_obj"] + date_obj: datetime | None = data["date_obj"] + return date_obj diff --git a/dateparser/_parts_of_day.py b/dateparser/_parts_of_day.py new file mode 100644 index 000000000..8f72d1d20 --- /dev/null +++ b/dateparser/_parts_of_day.py @@ -0,0 +1,101 @@ +from dataclasses import dataclass, fields +from datetime import time +from enum import Enum + +import regex as re + + +class PartOfDay(str, Enum): + """Part of the day that a date string refers to, e.g. ``"tonight"``. + + See :attr:`DateData.part_of_day `. + + .. versionadded:: VERSION + """ + + EARLY_MORNING = "early_morning" + """Between midnight and dawn, e.g. ``"in the small hours"`` or Spanish + ``"de madrugada"``.""" + + MORNING = "morning" + AFTERNOON = "afternoon" + EVENING = "evening" + NIGHT = "night" + + +@dataclass(frozen=True) +class PartsOfDay: + """Time of the day to use for each :class:`PartOfDay`, for the + ``PARTS_OF_DAY`` :ref:`setting `. + + .. versionadded:: VERSION + """ + + early_morning: time = time(3) + morning: time = time(9) + afternoon: time = time(15) + evening: time = time(18) + night: time = time(20) + + def __post_init__(self) -> None: + for field in fields(self): + value = getattr(self, field.name) + if not isinstance(value, time): + raise TypeError( + f"{type(self).__name__}.{field.name} must be a datetime.time, " + f"not {type(value).__name__}" + ) + + +_PART_OF_DAY_PATTERN = re.compile( + r"(?(?\d{1,2})(?P:\d{2})?\s*$" +) + + +def _meridiem(part: PartOfDay, hour: int) -> str: + if part in (PartOfDay.EARLY_MORNING, PartOfDay.MORNING): + return "am" + if part is PartOfDay.NIGHT and not 6 <= hour <= 11: + return "am" + return "pm" + + +def _replace_part_of_day( + translated: str, parts_of_day: PartsOfDay +) -> tuple[str, PartOfDay | None, bool]: + """Return *translated* with its part-of-day token replaced by a time, the + matching :class:`PartOfDay` (or ``None``), and whether that time came from + *parts_of_day*. + + A number right before the part of the day is an hour, e.g. ``"8 in the + evening"``, unless a month without a day precedes it, e.g. ``"January 8 in + the evening"``. A part of the day on its own is left in place, so that + parsing fails.""" + match = _PART_OF_DAY_PATTERN.search(translated) + if not match: + return translated, None, False + part = PartOfDay(match[1]) + before, after = translated[: match.start()], translated[match.end() :] + number = _TRAILING_NUMBER_PATTERN.search(before) + if number and not number["month"]: + hour = int(number["hour"]) + if hour > 12: + return translated, None, False + time_string = f"{hour}{number['minutes'] or ':00'} {_meridiem(part, hour)}" + return f"{before[: number.start()]}{time_string} {after}", part, False + rest = f"{before} {after}" + if not rest.strip(): + return translated, None, False + if _TIME_PATTERN.search(rest): + return rest, part, False + part_time: time = getattr(parts_of_day, part.value) + return f"{rest} {part_time:%H:%M:%S}", part, True diff --git a/dateparser/calendars/__init__.py b/dateparser/calendars/__init__.py index eabb6f5f1..14e9e35d2 100644 --- a/dateparser/calendars/__init__.py +++ b/dateparser/calendars/__init__.py @@ -1,10 +1,18 @@ -from datetime import datetime +from collections.abc import Callable +from datetime import datetime, tzinfo +from typing import Any, ClassVar, Protocol -from dateparser.conf import settings +from dateparser.conf import Settings, settings from dateparser.date import DateData from dateparser.parser import _parser +class _CalendarParser(Protocol): + def parse( + self, datestring: str, settings: Settings + ) -> tuple[datetime, str | None, tuple[str, ...]]: ... + + class CalendarBase: """Base setup class for non-Gregorian calendar system. @@ -13,57 +21,57 @@ class CalendarBase: :type source: str """ - parser = NotImplemented + parser: _CalendarParser = NotImplemented - def __init__(self, source): + def __init__(self, source: str) -> None: self.source = source - def get_date(self): + def get_date(self) -> DateData | None: try: - date_obj, period = self.parser.parse(self.source, settings) - return DateData(date_obj=date_obj, period=period) + date_obj, period, parts = self.parser.parse(self.source, settings) + return DateData(date_obj=date_obj, period=period, parts=parts) except ValueError: - pass + return None class non_gregorian_parser(_parser): - calendar_converter = NotImplemented - default_year = NotImplemented - default_month = NotImplemented - default_day = NotImplemented - non_gregorian_date_cls = NotImplemented + calendar_converter: Any = NotImplemented + default_year: int = NotImplemented + default_month: int = NotImplemented + default_day: int = NotImplemented + non_gregorian_date_cls: Callable[[int, int, int], Any] = NotImplemented - _digits = None - _months = None - _weekdays = None - _number_letters = None + _digits: ClassVar[dict[str, int] | None] = None + _months: ClassVar[dict[str, tuple[int, int, list[str]]] | None] = None + _weekdays: ClassVar[dict[str, list[str]] | None] = None + _number_letters: ClassVar[dict[int, list[str]] | None] = None @classmethod - def _replace_time_conventions(cls, source): + def _replace_time_conventions(cls, source: str) -> str: return source @classmethod - def _replace_digits(cls, source): + def _replace_digits(cls, source: str) -> str: return source @classmethod - def _replace_months(cls, source): + def _replace_months(cls, source: str) -> str: return source @classmethod - def _replace_weekdays(cls, source): + def _replace_weekdays(cls, source: str) -> str: return source @classmethod - def _replace_time(cls, source): + def _replace_time(cls, source: str) -> str: return source @classmethod - def _replace_days(cls, source): + def _replace_days(cls, source: str) -> str: return source @classmethod - def to_latin(cls, source): + def to_latin(cls, source: str) -> str: result = source result = cls._replace_months(result) result = cls._replace_weekdays(result) @@ -72,14 +80,12 @@ def to_latin(cls, source): result = cls._replace_time(result) result = cls._replace_time_conventions(result) - result = result.strip() - - return result + return result.strip() - def handle_two_digit_year(self, year): + def handle_two_digit_year(self, year: int) -> int: raise ValueError - def _get_datetime_obj(self, **params): + def _get_datetime_obj(self, **params: Any) -> datetime: day = params["day"] year = params["year"] month = params["month"] @@ -91,16 +97,16 @@ def _get_datetime_obj(self, **params): year=year, month=month, day=day ) c_params = params.copy() - c_params.update(dict(year=year, month=month, day=day)) + c_params.update({"year": year, "month": month, "day": day}) return datetime(**c_params) - def _get_datetime_obj_params(self): + def _get_datetime_obj_params(self) -> dict[str, int]: if not self.now: self._set_relative_base() now_year, now_month, now_day = self.calendar_converter.from_gregorian( self.now.year, self.now.month, self.now.day ) - params = { + return { "day": self.day or now_day, "month": self.month or now_month, "year": self.year or now_year, @@ -109,9 +115,8 @@ def _get_datetime_obj_params(self): "second": 0, "microsecond": 0, } - return params - def _get_date_obj(self, token, directive): + def _get_date_obj(self, token: str, directive: str) -> Any: year, month, day = self.default_year, self.default_month, self.default_day token_len = len(token) is_digit = token.isdigit() @@ -139,6 +144,12 @@ def _get_date_obj(self, token, directive): return self.non_gregorian_date_cls(year, month, day) @classmethod - def parse(cls, datestring, settings): + def parse( + cls, + datestring: str, + settings: Settings, + tz: tzinfo | None = None, + date_order: str | None = None, + ) -> tuple[datetime, str | None, tuple[str, ...]]: datestring = cls.to_latin(datestring) - return super().parse(datestring, settings) + return super().parse(datestring, settings, tz, date_order) diff --git a/dateparser/calendars/french_republican.py b/dateparser/calendars/french_republican.py new file mode 100644 index 000000000..285f97fc0 --- /dev/null +++ b/dateparser/calendars/french_republican.py @@ -0,0 +1,103 @@ +import re +import unicodedata +from datetime import datetime, timezone +from typing import TYPE_CHECKING + +from convertdate import french_republican + +from dateparser.calendars import CalendarBase + +if TYPE_CHECKING: + from dateparser.conf import Settings + +_MONTHS = { + name: index + for index, names in enumerate( + ( + ("vendemiaire",), + ("brumaire",), + ("frimaire",), + ("nivose",), + ("pluviose",), + ("ventose",), + ("germinal",), + ("floreal",), + ("prairial",), + ("messidor",), + ("thermidor",), + ("fructidor",), + ("sansculottides", "sans-culottides", "jours complementaires"), + ), + start=1, + ) + for name in names +} +_RE_DATE = re.compile( + rf"(?:(?:(?P\d{{1,2}})(?:er)?\s+)?(?P{'|'.join(_MONTHS)})\s+)?" + r"an\.?\s+(?:(?P\d{1,3})|(?P" + r"C{0,3}(?:XC|XL|L?X{0,3})(?:IX|IV|V?I{0,3})))\.?(?:er|e|eme|me)?\.?", + flags=re.IGNORECASE, +) +_ROMAN_NUMERAL_VALUES = {"C": 100, "L": 50, "X": 10, "V": 5, "I": 1} + + +def _roman_to_int(numeral: str) -> int: + values = [_ROMAN_NUMERAL_VALUES[char] for char in numeral.upper()] + return sum( + -value if value < next_value else value + for value, next_value in zip(values, [*values[1:], 0], strict=True) + ) + + +def _month_length(year: int, month: int) -> int: + if month < 13: + return 30 + return 6 if french_republican.leap(year) else 5 + + +class _french_republican_parser: + @classmethod + def parse( + cls, datestring: str, settings: "Settings" + ) -> tuple[datetime, str | None, tuple[str, ...]]: + normalized = "".join( + char + for char in unicodedata.normalize("NFKD", datestring.strip()) + if not unicodedata.combining(char) + ) + match = _RE_DATE.fullmatch(normalized) + if not match or not (match["year"] or match["roman"]): + raise ValueError(datestring) + year = int(match["year"]) if match["year"] else _roman_to_int(match["roman"]) + if not year: + raise ValueError(datestring) + now = settings.RELATIVE_BASE or datetime.now(tz=timezone.utc).replace( + tzinfo=None + ) + _, now_month, now_day = french_republican.from_gregorian( + now.year, now.month, now.day + ) + if match["month"]: + month = _MONTHS[match["month"].lower()] + else: + month = {"first": 1, "last": 13}.get( + settings.PREFER_MONTH_OF_YEAR, now_month + ) + if match["day"]: + day = int(match["day"]) + else: + day = min( + {"first": 1, "last": 30}.get(settings.PREFER_DAY_OF_MONTH, now_day), + _month_length(year, month), + ) + date = datetime(*french_republican.to_gregorian(year, month, day)) + period = "day" if match["day"] else "month" if match["month"] else "year" + parts = ("year", "month", "day")[: ("year", "month", "day").index(period) + 1] + return date, period, parts + + +class FrenchRepublicanCalendar(CalendarBase): + """Calendar class for the `French Republican calendar + `_.""" + + parser = _french_republican_parser diff --git a/dateparser/calendars/hijri_parser.py b/dateparser/calendars/hijri_parser.py index 716d88d4e..6de34e5a6 100644 --- a/dateparser/calendars/hijri_parser.py +++ b/dateparser/calendars/hijri_parser.py @@ -1,3 +1,5 @@ +from typing import ClassVar + from hijridate import Gregorian, Hijri from dateparser.calendars import non_gregorian_parser @@ -5,33 +7,27 @@ class hijri: @classmethod - def to_gregorian(cls, year=None, month=None, day=None): + def to_gregorian(cls, year: int, month: int, day: int) -> tuple[int, int, int]: g = Hijri(year=year, month=month, day=day, validate=False).to_gregorian() return g.datetuple() @classmethod - def from_gregorian(cls, year=None, month=None, day=None): + def from_gregorian(cls, year: int, month: int, day: int) -> tuple[int, int, int]: h = Gregorian(year, month, day).to_hijri() return h.datetuple() @classmethod - def month_length(cls, year, month): + def month_length(cls, year: int, month: int) -> int: h = Hijri(year=year, month=month, day=1) return h.month_length() class HijriDate: - def __init__(self, year, month, day): + def __init__(self, year: int, month: int, day: int) -> None: self.year = year self.month = month self.day = day - def weekday(self): - for week in hijri.monthcalendar(self.year, self.month): - for idx, day in enumerate(week): - if day == self.day: - return idx - class hijri_parser(non_gregorian_parser): calendar_converter = hijri @@ -40,21 +36,20 @@ class hijri_parser(non_gregorian_parser): default_day = 1 non_gregorian_date_cls = HijriDate - _time_conventions = { + _time_conventions: ClassVar[dict[str, list[str]]] = { "am": ["صباحاً"], "pm": ["مساءً"], } @classmethod - def _replace_time_conventions(cls, source): + def _replace_time_conventions(cls, source: str) -> str: result = source for latin, arabics in cls._time_conventions.items(): for arabic in arabics: result = result.replace(arabic, latin) return result - def handle_two_digit_year(self, year): + def handle_two_digit_year(self, year: int) -> int: if year >= 90: return year + 1300 - else: - return year + 1400 + return year + 1400 diff --git a/dateparser/calendars/jalali_parser.py b/dateparser/calendars/jalali_parser.py index ef437d5fb..3386398fb 100644 --- a/dateparser/calendars/jalali_parser.py +++ b/dateparser/calendars/jalali_parser.py @@ -1,6 +1,6 @@ import re -from collections import OrderedDict from functools import reduce +from typing import ClassVar from convertdate import persian @@ -8,16 +8,17 @@ class PersianDate: - def __init__(self, year, month, day): + def __init__(self, year: int, month: int, day: int) -> None: self.year = year self.month = month self.day = day - def weekday(self): + def weekday(self) -> int | None: for week in persian.monthcalendar(self.year, self.month): for idx, day in enumerate(week): if day == self.day: return idx + return None class jalali_parser(non_gregorian_parser): @@ -27,7 +28,7 @@ class jalali_parser(non_gregorian_parser): default_day = 1 non_gregorian_date_cls = PersianDate - _digits = { + _digits: ClassVar[dict[str, int]] = { "۰": 0, "۱": 1, "۲": 2, @@ -40,37 +41,33 @@ class jalali_parser(non_gregorian_parser): "۹": 9, } - _months = OrderedDict( - [ - # pinglish : (persian literals, month index, number of days) - ("Farvardin", (1, 31, ["فروردین"])), - ("Ordibehesht", (2, 31, ["اردیبهشت"])), - ("Khordad", (3, 31, ["خرداد"])), - ("Tir", (4, 31, ["تیر"])), - ("Mordad", (5, 31, ["امرداد", "مرداد"])), - ("Shahrivar", (6, 31, ["شهریور", "شهريور"])), - ("Mehr", (7, 30, ["مهر"])), - ("Aban", (8, 30, ["آبان"])), - ("Azar", (9, 30, ["آذر"])), - ("Dey", (10, 30, ["دی"])), - ("Bahman", (11, 30, ["بهمن", "بهن"])), - ("Esfand", (12, 29, ["اسفند"])), - ] - ) - - _weekdays = OrderedDict( - [ - ("Sunday", ["یکشنبه"]), - ("Monday", ["دوشنبه"]), - ("Tuesday", ["سهشنبه", "سه شنبه"]), - ("Wednesday", ["چهارشنبه", "چهار شنبه"]), - ("Thursday", ["پنجشنبه", "پنج شنبه"]), - ("Friday", ["جمعه"]), - ("Saturday", ["روز شنبه", "شنبه"]), - ] - ) - - _number_letters = { + _months: ClassVar[dict[str, tuple[int, int, list[str]]]] = { + # pinglish : (persian literals, month index, number of days) + "Farvardin": (1, 31, ["فروردین"]), + "Ordibehesht": (2, 31, ["اردیبهشت"]), + "Khordad": (3, 31, ["خرداد"]), + "Tir": (4, 31, ["تیر"]), + "Mordad": (5, 31, ["امرداد", "مرداد"]), + "Shahrivar": (6, 31, ["شهریور", "شهريور"]), + "Mehr": (7, 30, ["مهر"]), + "Aban": (8, 30, ["آبان"]), + "Azar": (9, 30, ["آذر"]), + "Dey": (10, 30, ["دی"]), + "Bahman": (11, 30, ["بهمن", "بهن"]), + "Esfand": (12, 29, ["اسفند"]), + } + + _weekdays: ClassVar[dict[str, list[str]]] = { + "Sunday": ["یکشنبه"], + "Monday": ["دوشنبه"], + "Tuesday": ["سهشنبه", "سه شنبه"], + "Wednesday": ["چهارشنبه", "چهار شنبه"], + "Thursday": ["پنجشنبه", "پنج شنبه"], + "Friday": ["جمعه"], + "Saturday": ["روز شنبه", "شنبه"], + } + + _number_letters: ClassVar[dict[int, list[str]]] = { 0: ["صفر"], 1: ["یک", "اول"], 2: ["دو"], @@ -106,14 +103,14 @@ class jalali_parser(non_gregorian_parser): } @classmethod - def _replace_digits(cls, source): + def _replace_digits(cls, source: str) -> str: result = source for pers_digit, number in cls._digits.items(): result = result.replace(pers_digit, str(number)) return result @classmethod - def _replace_months(cls, source): + def _replace_months(cls, source: str) -> str: result = source for pers, latin in reduce( lambda a, b: a + b, @@ -126,7 +123,7 @@ def _replace_months(cls, source): return result @classmethod - def _replace_weekdays(cls, source): + def _replace_weekdays(cls, source: str) -> str: result = source for pers, latin in reduce( lambda a, b: a + b, @@ -139,8 +136,8 @@ def _replace_weekdays(cls, source): return result @classmethod - def _replace_time(cls, source): - def only_numbers(match_obj): + def _replace_time(cls, source: str) -> str: + def only_numbers(match_obj: re.Match[str]) -> str: matched_string = match_obj.group() return re.sub(r"\D", " ", matched_string) @@ -151,17 +148,16 @@ def only_numbers(match_obj): result = re.sub(minute_pattern, only_numbers, result) result = re.sub(second_pattern, only_numbers, result) result = re.sub(r"\s+و\s+", ":", result) - result = result.replace("ساعت", "") - return result + return result.replace("ساعت", "") @classmethod - def _replace_days(cls, source): + def _replace_days(cls, source: str) -> str: result = re.sub( r"ام|م|ین", "", source ) # removes persian variant of th/first/second/third day_pairs = list(cls._number_letters.items()) - def comp_key(tup): + def comp_key(tup: tuple[int, list[str]]) -> int: return tup[0] day_pairs.sort(key=comp_key, reverse=True) @@ -177,8 +173,7 @@ def comp_key(tup): result = result.replace(persian_number, str(number)) return result - def handle_two_digit_year(self, year): + def handle_two_digit_year(self, year: int) -> int: if year > 60: return year + 1300 - else: - return year + 1400 + return year + 1400 diff --git a/dateparser/calendars/minguo.py b/dateparser/calendars/minguo.py new file mode 100644 index 000000000..31c4b8e48 --- /dev/null +++ b/dateparser/calendars/minguo.py @@ -0,0 +1,57 @@ +import calendar +from datetime import date, datetime, tzinfo +from typing import Any + +from dateparser.calendars import CalendarBase, non_gregorian_parser +from dateparser.conf import Settings + +_YEAR_OFFSET = 1911 + + +class _minguo: + @classmethod + def to_gregorian(cls, year: int, month: int, day: int) -> tuple[int, int, int]: + return year + _YEAR_OFFSET, month, day + + @classmethod + def from_gregorian(cls, year: int, month: int, day: int) -> tuple[int, int, int]: + return year - _YEAR_OFFSET, month, day + + @classmethod + def month_length(cls, year: int, month: int) -> int: + return calendar.monthrange(year + _YEAR_OFFSET, month)[1] + + +class _minguo_parser(non_gregorian_parser): + calendar_converter = _minguo + default_year = 101 + default_month = 1 + default_day = 1 + non_gregorian_date_cls = date + + def _get_date_obj(self, token: str, directive: str) -> Any: + if directive == "%Y": + if not (token.isdigit() and len(token) <= 3 and int(token)): + raise ValueError + return date(int(token), self.default_month, self.default_day) + return super()._get_date_obj(token, directive) + + @classmethod + def parse( + cls, + datestring: str, + settings: Settings, + tz: tzinfo | None = None, + date_order: str | None = None, + ) -> tuple[datetime, str | None, tuple[str, ...]]: + return super(non_gregorian_parser, cls).parse( + datestring, settings, tz, date_order or "YMD" + ) + + +class MinguoCalendar(CalendarBase): + """Calendar class for the `Minguo calendar + `_, used in + Taiwan.""" + + parser = _minguo_parser diff --git a/dateparser/conf.py b/dateparser/conf.py index 73eab5f63..4c0a04889 100644 --- a/dateparser/conf.py +++ b/dateparser/conf.py @@ -1,12 +1,19 @@ import hashlib +from collections.abc import Callable, Iterable, Mapping from datetime import datetime from functools import wraps +from types import MappingProxyType +from typing import Any, Literal, ParamSpec, TypeVar +from dateparser._parts_of_day import PartsOfDay from dateparser.data.languages_info import language_order from .parser import date_order_chart from .utils import registry +_P = ParamSpec("_P") +_R = TypeVar("_R") + @registry class Settings: @@ -15,6 +22,7 @@ class Settings: * `DATE_ORDER` * `PREFER_LOCALE_DATE_ORDER` + * `STRICT_DATE_ORDER` * `TIMEZONE` * `TO_TIMEZONE` * `RETURN_AS_TIMEZONE_AWARE` @@ -24,57 +32,96 @@ class Settings: * `RELATIVE_BASE` * `STRICT_PARSING` * `REQUIRE_PARTS` + * `IGNORE_SURROUNDING_TEXT` * `SKIP_TOKENS` * `NORMALIZE` * `RETURN_TIME_AS_PERIOD` * `RETURN_TIME_SPAN` * `DEFAULT_START_OF_WEEK` * `DEFAULT_DAYS_IN_MONTH` + * `PARTS_OF_DAY` * `PARSERS` * `DEFAULT_LANGUAGES` + * `USE_GIVEN_LANGUAGE_ORDER` * `LANGUAGE_DETECTION_CONFIDENCE_THRESHOLD` * `CACHE_SIZE_LIMIT` """ - _default = True - _pyfile_data = None - _mod_settings = dict() - - def __init__(self, settings=None): + _default: bool = True + _pyfile_data: dict[str, Any] | None = None + _mod_settings: Mapping[str, Any] = MappingProxyType({}) + + registry_key: str + DATE_ORDER: str + PREFER_LOCALE_DATE_ORDER: bool + STRICT_DATE_ORDER: str + TIMEZONE: str + TO_TIMEZONE: str | Literal[False] + RETURN_AS_TIMEZONE_AWARE: bool | Literal["default"] + PREFER_MONTH_OF_YEAR: str + PREFER_DAY_OF_MONTH: str + PREFER_DATES_FROM: str + RELATIVE_BASE: datetime | Literal[False] + STRICT_PARSING: bool + REQUIRE_PARTS: list[str] + IGNORE_SURROUNDING_TEXT: bool + SKIP_TOKENS: list[str] + NORMALIZE: bool + RETURN_TIME_AS_PERIOD: bool + RETURN_TIME_SPAN: bool + DEFAULT_START_OF_WEEK: str + DEFAULT_DAYS_IN_MONTH: int + PARTS_OF_DAY: PartsOfDay + PARSERS: list[str] + DEFAULT_LANGUAGES: list[str] + USE_GIVEN_LANGUAGE_ORDER: bool + LANGUAGE_DETECTION_CONFIDENCE_THRESHOLD: float + CACHE_SIZE_LIMIT: int + + def __init__(self, settings: Mapping[str, Any] | None = None) -> None: if settings: self._updateall(settings.items()) else: self._updateall(self._get_settings_from_pyfile().items()) @classmethod - def get_key(cls, settings=None): + def get_key(cls, settings: Mapping[str, Any] | None = None) -> str: if not settings: return "default" - keys = sorted(["%s-%s" % (key, str(settings[key])) for key in settings]) - return hashlib.md5("".join(keys).encode("utf-8")).hexdigest() + keys = sorted([f"{key}-{settings[key]}" for key in settings]) + return hashlib.md5( + "".join(keys).encode("utf-8"), usedforsecurity=False + ).hexdigest() @classmethod - def _get_settings_from_pyfile(cls): + def _get_settings_from_pyfile(cls) -> dict[str, Any]: if not cls._pyfile_data: - from dateparser_data import settings + from dateparser_data import settings # noqa: PLC0415 cls._pyfile_data = settings.settings return cls._pyfile_data - def _updateall(self, iterable): + def _updateall(self, iterable: Iterable[tuple[str, Any]]) -> None: for key, value in iterable: setattr(self, key, value) - def replace(self, mod_settings=None, **kwds): + def replace( + self, mod_settings: Mapping[str, Any] | None = None, **kwds: Any + ) -> "Settings": for k, v in kwds.items(): if v is None: - raise TypeError('Invalid {{"{}": {}}}'.format(k, v)) + raise TypeError(f'Invalid {{"{k}": {v}}}') - for x in self._get_settings_from_pyfile().keys(): + for x in self._get_settings_from_pyfile(): kwds.setdefault(x, getattr(self, x)) kwds["_default"] = False + # Keep track of the settings that the caller set, or replacing another + # one, like RELATIVE_BASE, makes an explicit DATE_ORDER give way to the + # order of the locale. + if mod_settings is None: + mod_settings = self._mod_settings if mod_settings: kwds["_mod_settings"] = mod_settings @@ -84,10 +131,10 @@ def replace(self, mod_settings=None, **kwds): settings = Settings() -def apply_settings(f): +def apply_settings(f: Callable[_P, _R]) -> Callable[_P, _R]: @wraps(f) - def wrapper(*args, **kwargs): - mod_settings = kwargs.get("settings") + def wrapper(*args: _P.args, **kwargs: _P.kwargs) -> _R: + mod_settings: Any = kwargs.get("settings") kwargs["settings"] = mod_settings or settings if isinstance(kwargs["settings"], dict): @@ -109,15 +156,14 @@ class SettingValidationError(ValueError): pass -def _check_repeated_values(setting_name, setting_value): +def _check_repeated_values(setting_name: str, setting_value: list[Any]) -> None: if len(setting_value) != len(set(setting_value)): raise SettingValidationError( - 'There are repeated values in the "{}" setting'.format(setting_name) + f'There are repeated values in the "{setting_name}" setting' ) - return -def _check_require_part(setting_name, setting_value): +def _check_require_part(setting_name: str, setting_value: list[str]) -> None: """Returns `True` if the provided list of parts contains valid values""" invalid_values = set(setting_value) - {"day", "month", "year"} if invalid_values: @@ -129,7 +175,7 @@ def _check_require_part(setting_name, setting_value): _check_repeated_values(setting_name, setting_value) -def _check_parsers(setting_name, setting_value): +def _check_parsers(setting_name: str, setting_value: list[str]) -> None: """Returns `True` if the provided list of parsers contains valid values""" existing_parsers = [ "timestamp", @@ -149,7 +195,7 @@ def _check_parsers(setting_name, setting_value): _check_repeated_values(setting_name, setting_value) -def _check_default_languages(setting_name, setting_value): +def _check_default_languages(setting_name: str, setting_value: list[str]) -> None: unsupported_languages = set(setting_value) - set(language_order) if unsupported_languages: raise SettingValidationError( @@ -160,24 +206,21 @@ def _check_default_languages(setting_name, setting_value): _check_repeated_values(setting_name, setting_value) -def _check_between_0_and_1(setting_name, setting_value): +def _check_between_0_and_1(setting_name: str, setting_value: float) -> None: is_valid = 0 <= setting_value <= 1 if not is_valid: raise SettingValidationError( - "{} is not a valid value for {}. It can take values between 0 and " - "1.".format( - setting_value, - setting_name, - ) + f"{setting_value} is not a valid value for {setting_name}. It can take " + "values between 0 and 1." ) -def check_settings(settings): +def check_settings(settings: Settings) -> None: """ Check if provided settings are valid, if not it raises `SettingValidationError`. Only checks for the modified settings. """ - settings_values = { + settings_values: dict[str, dict[str, Any]] = { "DATE_ORDER": { "values": tuple(date_order_chart.keys()), "type": str, @@ -206,6 +249,7 @@ def check_settings(settings): "type": datetime }, "STRICT_PARSING": {"type": bool}, + "IGNORE_SURROUNDING_TEXT": {"type": bool}, "REQUIRE_PARTS": { # "values" covered by the 'extra_check' "type": list, @@ -224,7 +268,9 @@ def check_settings(settings): }, "FUZZY": {"type": bool}, "PREFER_LOCALE_DATE_ORDER": {"type": bool}, + "STRICT_DATE_ORDER": {"values": ("none", "year", "all"), "type": str}, "DEFAULT_LANGUAGES": {"type": list, "extra_check": _check_default_languages}, + "USE_GIVEN_LANGUAGE_ORDER": {"type": bool}, "LANGUAGE_DETECTION_CONFIDENCE_THRESHOLD": { "type": float, "extra_check": _check_between_0_and_1, @@ -240,6 +286,7 @@ def check_settings(settings): "DEFAULT_DAYS_IN_MONTH": { "type": int, }, + "PARTS_OF_DAY": {"type": PartsOfDay}, } modified_settings = settings._mod_settings # check only modified settings @@ -247,7 +294,7 @@ def check_settings(settings): # check settings keys: for setting in modified_settings: if setting not in settings_values: - raise SettingValidationError('"{}" is not a valid setting'.format(setting)) + raise SettingValidationError(f'"{setting}" is not a valid setting') for setting_name, setting_value in modified_settings.items(): setting_type = type(setting_value) @@ -276,3 +323,12 @@ def check_settings(settings): extra_check = setting_props.get("extra_check") if extra_check: extra_check(setting_name, setting_value) + + # STRICT_DATE_ORDER enforces the DATE_ORDER that the caller sets. The default + # one is only a preference, so without it there is nothing to enforce. + strict_date_order = modified_settings.get("STRICT_DATE_ORDER", "none") + if strict_date_order != "none" and "DATE_ORDER" not in modified_settings: + raise SettingValidationError( + f'"STRICT_DATE_ORDER": "{strict_date_order}" requires the "DATE_ORDER" ' + "setting" + ) diff --git a/dateparser/custom_language_detection/fasttext.py b/dateparser/custom_language_detection/fasttext.py index 713b014c3..8977a2c47 100644 --- a/dateparser/custom_language_detection/fasttext.py +++ b/dateparser/custom_language_detection/fasttext.py @@ -1,43 +1,36 @@ -import os - -import fasttext - -from dateparser_cli.exceptions import FastTextModelNotFoundException -from dateparser_cli.fasttext_manager import fasttext_downloader -from dateparser_cli.utils import create_data_model_home, dateparser_model_home - -_supported_models = ["large.bin", "small.bin"] -_DEFAULT_MODEL = "small" - - -class _FastTextCache: - model = None - - -def _load_fasttext_model(): - if _FastTextCache.model: - return _FastTextCache.model - create_data_model_home() - downloaded_models = [ - file for file in os.listdir(dateparser_model_home) if file in _supported_models - ] - if not downloaded_models: - fasttext_downloader(_DEFAULT_MODEL) - return _load_fasttext_model() - model_path = os.path.join(dateparser_model_home, downloaded_models[0]) - if not os.path.isfile(model_path): - raise FastTextModelNotFoundException("Fasttext model file not found") - _FastTextCache.model = fasttext.load_model(model_path) - return _FastTextCache.model - - -def detect_languages(text, confidence_threshold): - _language_parser = _load_fasttext_model() - text = text.replace("\n", " ").replace("\r", "") - language_codes = [] - parser_data = _language_parser.predict(text) - for idx, language_probability in enumerate(parser_data[1]): - if language_probability > confidence_threshold: - language_code = parser_data[0][idx].replace("__label__", "") - language_codes.append(language_code) - return language_codes +""" +Deprecated fastText language detection module. + +This module is deprecated as the fastText library is archived and unmaintained. +Please use langdetect instead. +""" + +import warnings +from typing import NoReturn + +warnings.warn( + "fastText support is deprecated and will be removed in a future version. " + "The fastText library is archived and unmaintained. " + "Please migrate to langdetect: from dateparser.custom_language_detection.langdetect import detect_languages", + DeprecationWarning, + stacklevel=2, +) + + +def detect_languages(text: str, confidence_threshold: float) -> NoReturn: + """ + Deprecated function. FastText support has been removed. + + Args: + text: The text to detect languages from (unused) + confidence_threshold: Minimum confidence threshold (unused) + + Raises: + ImportError: Always, as fastText is no longer supported. + """ + raise ImportError( + "fastText is no longer supported as the library is archived and unmaintained. " + "Please use langdetect instead:\n" + " pip install dateparser[langdetect]\n" + " from dateparser.custom_language_detection.langdetect import detect_languages" + ) diff --git a/dateparser/custom_language_detection/langdetect.py b/dateparser/custom_language_detection/langdetect.py index d105631e7..895f35c55 100644 --- a/dateparser/custom_language_detection/langdetect.py +++ b/dateparser/custom_language_detection/langdetect.py @@ -1,3 +1,5 @@ +from typing import Any + import langdetect # The below _Factory is set to prevent setting global state of the library @@ -6,30 +8,32 @@ class _Factory: - data = None + data: Any = None -def _init_factory(): +def _init_factory() -> None: if _Factory.data is None: _Factory.data = langdetect.detector_factory.DetectorFactory() _Factory.data.load_profile(langdetect.detector_factory.PROFILES_DIRECTORY) _Factory.data.seed = 0 -def _get_language_probablities(text): +def _get_language_probablities(text: str) -> Any: _init_factory() detector = _Factory.data.create() detector.append(text) return detector.get_probabilities() -def detect_languages(text, confidence_threshold): - language_codes = [] +def detect_languages(text: str, confidence_threshold: float) -> list[str]: + language_codes: list[str] = [] try: parser_data = _get_language_probablities(text) - for language_candidate in parser_data: - if language_candidate.prob > confidence_threshold: - language_codes.append(language_candidate.lang) + language_codes.extend( + language_candidate.lang + for language_candidate in parser_data + if language_candidate.prob > confidence_threshold + ) except langdetect.lang_detect_exception.LangDetectException: # This exception can be produced with empty strings or inputs without letters like `10-10-2021`. # As this could be really common, we ignore them. diff --git a/dateparser/custom_language_detection/language_mapping.py b/dateparser/custom_language_detection/language_mapping.py index a76030828..5e797d7cc 100644 --- a/dateparser/custom_language_detection/language_mapping.py +++ b/dateparser/custom_language_detection/language_mapping.py @@ -1,7 +1,9 @@ +from collections.abc import Iterable + from dateparser.data.languages_info import language_map -def map_languages(language_codes): +def map_languages(language_codes: Iterable[str]) -> list[str]: """ Returns the candidates from the supported languages codes. :param language_codes: diff --git a/dateparser/data/__init__.py b/dateparser/data/__init__.py index 0bd6b7d25..d09e0eb7a 100644 --- a/dateparser/data/__init__.py +++ b/dateparser/data/__init__.py @@ -1,2 +1,3 @@ from dateparser.data import date_translation_data -from .languages_info import language_order, language_locale_dict + +from .languages_info import language_locale_dict, language_order diff --git a/dateparser/data/date_translation_data/af.py b/dateparser/data/date_translation_data/af.py index a636d4ea8..85e5c0258 100644 --- a/dateparser/data/date_translation_data/af.py +++ b/dateparser/data/date_translation_data/af.py @@ -109,8 +109,8 @@ ], "second": [ "s", - "sek", - "sekonde" + "sekonde", + "sek" ], "relative-type": { "0 day ago": [ @@ -123,101 +123,118 @@ "hierdie minuut" ], "0 month ago": [ + "hierdie md", "vandeesmaand" ], "0 second ago": [ "nou" ], "0 week ago": [ + "hierdie w", + "hierdie week", "vandeesweek" ], "0 year ago": [ + "hierdie j", "hierdie jaar" ], "1 day ago": [ "gister" ], "1 month ago": [ - "verlede maand" + "verlede maand", + "verlede md" ], "1 week ago": [ + "verlede w", "verlede week" ], "1 year ago": [ + "verlede j", "verlede jaar" ], "in 1 day": [ "môre" ], "in 1 month": [ - "volgende maand" + "volgende maand", + "volgende md" ], "in 1 week": [ + "volgende w", "volgende week" ], "in 1 year": [ + "volgende j", "volgende jaar" ] }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) dae gelede", - "(\\d+[.,]?\\d*) dag gelede" + "(\\d++[.,]?\\d*+) dae gelede", + "(\\d++[.,]?\\d*+) dag gelede" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) uur gelede" + "(\\d++[.,]?\\d*+) u gelede", + "(\\d++[.,]?\\d*+) uur gelede" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) min gelede", - "(\\d+[.,]?\\d*) minute gelede", - "(\\d+[.,]?\\d*) minuut gelede" + "(\\d++[.,]?\\d*+) min gelede", + "(\\d++[.,]?\\d*+) minute gelede", + "(\\d++[.,]?\\d*+) minuut gelede" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) maand gelede", - "(\\d+[.,]?\\d*) maande gelede", - "(\\d+[.,]?\\d*) md gelede" + "(\\d++[.,]?\\d*+) maand gelede", + "(\\d++[.,]?\\d*+) maande gelede", + "(\\d++[.,]?\\d*+) md gelede" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) sek gelede", - "(\\d+[.,]?\\d*) sekonde gelede", - "(\\d+[.,]?\\d*) sekondes gelede" + "(\\d++[.,]?\\d*+) s gelede", + "(\\d++[.,]?\\d*+) sekonde gelede", + "(\\d++[.,]?\\d*+) sekondes gelede", + "(\\d++[.,]?\\d*+) sek gelede" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) w gelede", - "(\\d+[.,]?\\d*) week gelede", - "(\\d+[.,]?\\d*) weke gelede" + "(\\d++[.,]?\\d*+) w gelede", + "(\\d++[.,]?\\d*+) week gelede", + "(\\d++[.,]?\\d*+) weke gelede" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) jaar gelede" + "(\\d++[.,]?\\d*+) j gelede", + "(\\d++[.,]?\\d*+) jaar gelede" ], "in \\1 day": [ - "oor (\\d+[.,]?\\d*) dae", - "oor (\\d+[.,]?\\d*) dag", - "oor (\\d+[.,]?\\d*) minuut" + "oor (\\d++[.,]?\\d*+) dae", + "oor (\\d++[.,]?\\d*+) dag" ], "in \\1 hour": [ - "oor (\\d+[.,]?\\d*) uur" + "oor (\\d++[.,]?\\d*+) u", + "oor (\\d++[.,]?\\d*+) uur" ], "in \\1 minute": [ - "oor (\\d+[.,]?\\d*) min", - "oor (\\d+[.,]?\\d*) minuut" + "oor (\\d++[.,]?\\d*+) min", + "oor (\\d++[.,]?\\d*+) minute", + "oor (\\d++[.,]?\\d*+) minuut" ], "in \\1 month": [ - "oor (\\d+[.,]?\\d*) md", - "oor (\\d+[.,]?\\d*) minuut" + "oor (\\d++[.,]?\\d*+) maand", + "oor (\\d++[.,]?\\d*+) maande", + "oor (\\d++[.,]?\\d*+) md" ], "in \\1 second": [ - "oor (\\d+[.,]?\\d*) sek", - "oor (\\d+[.,]?\\d*) sekonde", - "oor (\\d+[.,]?\\d*) sekondes" + "oor (\\d++[.,]?\\d*+) s", + "oor (\\d++[.,]?\\d*+) sekonde", + "oor (\\d++[.,]?\\d*+) sekondes", + "oor (\\d++[.,]?\\d*+) sek" ], "in \\1 week": [ - "oor (\\d+[.,]?\\d*) w", - "oor (\\d+[.,]?\\d*) week", - "oor (\\d+[.,]?\\d*) weke" + "oor (\\d++[.,]?\\d*+) w", + "oor (\\d++[.,]?\\d*+) week", + "oor (\\d++[.,]?\\d*+) weke" ], "in \\1 year": [ - "oor (\\d+[.,]?\\d*) jaar" + "oor (\\d++[.,]?\\d*+) j", + "oor (\\d++[.,]?\\d*+) jaar" ] }, "locale_specific": { diff --git a/dateparser/data/date_translation_data/agq.py b/dateparser/data/date_translation_data/agq.py index 06861dc06..ad62e132c 100644 --- a/dateparser/data/date_translation_data/agq.py +++ b/dateparser/data/date_translation_data/agq.py @@ -96,6 +96,7 @@ "utsuʔ" ], "hour": [ + "hr", "tàm" ], "minute": [ diff --git a/dateparser/data/date_translation_data/ak.py b/dateparser/data/date_translation_data/ak.py index 22cba0a41..3ca6fe2de 100644 --- a/dateparser/data/date_translation_data/ak.py +++ b/dateparser/data/date_translation_data/ak.py @@ -96,7 +96,8 @@ "da" ], "hour": [ - "dɔnhwer" + "dɔnhwer", + "hr" ], "minute": [ "sema" diff --git a/dateparser/data/date_translation_data/am.py b/dateparser/data/date_translation_data/am.py index 5a0abd00b..0d4a3f8ec 100644 --- a/dateparser/data/date_translation_data/am.py +++ b/dateparser/data/date_translation_data/am.py @@ -2,10 +2,14 @@ "name": "am", "date_order": "DMY", "january": [ + "ጃን", + "ጃንዋሪ", "ጃንዩ", "ጃንዩወሪ" ], "february": [ + "ፌብ", + "ፌብሩዋሪ", "ፌብሩ", "ፌብሩወሪ" ], @@ -86,7 +90,8 @@ "ቀን" ], "hour": [ - "ሰዓት" + "ሰዓት", + "ሰዓቶች" ], "minute": [ "ደቂቃ" @@ -146,62 +151,62 @@ }, "relative-type-regex": { "\\1 day ago": [ - "ከ (\\d+[.,]?\\d*) ቀን በፊት", - "ከ(\\d+[.,]?\\d*) ቀናት በፊት", - "ከ(\\d+[.,]?\\d*) ቀን በፊት", - "ከ(\\d+[.,]?\\d*) ቀኖች በፊት" + "ከ (\\d++[.,]?\\d*+) ቀን በፊት", + "ከ(\\d++[.,]?\\d*+) ቀናት በፊት", + "ከ(\\d++[.,]?\\d*+) ቀን በፊት", + "ከ(\\d++[.,]?\\d*+) ቀኖች በፊት" ], "\\1 hour ago": [ - "ከ(\\d+[.,]?\\d*) ሰዓት በፊት", - "ከ(\\d+[.,]?\\d*) ሰዓቶች በፊት" + "ከ(\\d++[.,]?\\d*+) ሰዓት በፊት", + "ከ(\\d++[.,]?\\d*+) ሰዓቶች በፊት" ], "\\1 minute ago": [ - "ከ(\\d+[.,]?\\d*) ደቂቃ በፊት", - "ከ(\\d+[.,]?\\d*) ደቂቃዎች በፊት" + "ከ(\\d++[.,]?\\d*+) ደቂቃ በፊት", + "ከ(\\d++[.,]?\\d*+) ደቂቃዎች በፊት" ], "\\1 month ago": [ - "ከ(\\d+[.,]?\\d*) ወራት በፊት", - "ከ(\\d+[.,]?\\d*) ወር በፊት" + "ከ(\\d++[.,]?\\d*+) ወራት በፊት", + "ከ(\\d++[.,]?\\d*+) ወር በፊት" ], "\\1 second ago": [ - "ከ(\\d+[.,]?\\d*) ሰከንድ በፊት", - "ከ(\\d+[.,]?\\d*) ሰከንዶች በፊት" + "ከ(\\d++[.,]?\\d*+) ሰከንድ በፊት", + "ከ(\\d++[.,]?\\d*+) ሰከንዶች በፊት" ], "\\1 week ago": [ - "ከ(\\d+[.,]?\\d*) ሳምንታት በፊት", - "ከ(\\d+[.,]?\\d*) ሳምንት በፊት" + "ከ(\\d++[.,]?\\d*+) ሳምንታት በፊት", + "ከ(\\d++[.,]?\\d*+) ሳምንት በፊት" ], "\\1 year ago": [ - "ከ(\\d+[.,]?\\d*) ዓመታት በፊት", - "ከ(\\d+[.,]?\\d*) ዓመት በፊት" + "ከ(\\d++[.,]?\\d*+) ዓመታት በፊት", + "ከ(\\d++[.,]?\\d*+) ዓመት በፊት" ], "in \\1 day": [ - "በ(\\d+[.,]?\\d*) ቀናት ውስጥ", - "በ(\\d+[.,]?\\d*) ቀን ውስጥ", - "በ(\\d+[.,]?\\d*) ቀኖች ውስጥ" + "በ(\\d++[.,]?\\d*+) ቀናት ውስጥ", + "በ(\\d++[.,]?\\d*+) ቀን ውስጥ", + "በ(\\d++[.,]?\\d*+) ቀኖች ውስጥ" ], "in \\1 hour": [ - "በ(\\d+[.,]?\\d*) ሰዓት ውስጥ", - "በ(\\d+[.,]?\\d*) ሰዓቶች ውስጥ" + "በ(\\d++[.,]?\\d*+) ሰዓት ውስጥ", + "በ(\\d++[.,]?\\d*+) ሰዓቶች ውስጥ" ], "in \\1 minute": [ - "በ(\\d+[.,]?\\d*) ደቂቃ ውስጥ", - "በ(\\d+[.,]?\\d*) ደቂቃዎች ውስጥ" + "በ(\\d++[.,]?\\d*+) ደቂቃ ውስጥ", + "በ(\\d++[.,]?\\d*+) ደቂቃዎች ውስጥ" ], "in \\1 month": [ - "በ(\\d+[.,]?\\d*) ወራት ውስጥ", - "በ(\\d+[.,]?\\d*) ወር ውስጥ" + "በ(\\d++[.,]?\\d*+) ወራት ውስጥ", + "በ(\\d++[.,]?\\d*+) ወር ውስጥ" ], "in \\1 second": [ - "በ(\\d+[.,]?\\d*) ሰከንድ ውስጥ", - "በ(\\d+[.,]?\\d*) ሰከንዶች ውስጥ" + "በ(\\d++[.,]?\\d*+) ሰከንድ ውስጥ", + "በ(\\d++[.,]?\\d*+) ሰከንዶች ውስጥ" ], "in \\1 week": [ - "በ(\\d+[.,]?\\d*) ሳምንታት ውስጥ", - "በ(\\d+[.,]?\\d*) ሳምንት ውስጥ" + "በ(\\d++[.,]?\\d*+) ሳምንታት ውስጥ", + "በ(\\d++[.,]?\\d*+) ሳምንት ውስጥ" ], "in \\1 year": [ - "በ(\\d+[.,]?\\d*) ዓመታት ውስጥ" + "በ(\\d++[.,]?\\d*+) ዓመታት ውስጥ" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/ar.py b/dateparser/data/date_translation_data/ar.py index db378974b..640a965e7 100644 --- a/dateparser/data/date_translation_data/ar.py +++ b/dateparser/data/date_translation_data/ar.py @@ -17,10 +17,14 @@ "مايو" ], "june": [ - "يونيو" + "يونيو", + "يونيه", + "يونية" ], "july": [ - "يوليو" + "يوليو", + "يوليه", + "يولية" ], "august": [ "أغسطس" @@ -51,7 +55,8 @@ "الخميس" ], "friday": [ - "الجمعة" + "الجمعة", + "الجمعه" ], "saturday": [ "السبت" @@ -71,7 +76,8 @@ "year": [ "السنة", "عام", - "سنة" + "سنة", + "السنه" ], "month": [ "الشهر", @@ -87,6 +93,7 @@ ], "hour": [ "الساعات", + "ساعات", "ساعة", "ساعات" ], @@ -97,7 +104,8 @@ ], "second": [ "الثواني", - "ثانية" + "ثانية", + "ثانيه" ], "relative-type": { "0 day ago": [ @@ -159,46 +167,46 @@ }, "relative-type-regex": { "\\1 day ago": [ - "قبل (\\d+[.,]?\\d*) يوم" + "قبل (\\d++[.,]?\\d*+) يوم" ], "\\1 hour ago": [ - "قبل (\\d+[.,]?\\d*) ساعة" + "قبل (\\d++[.,]?\\d*+) ساعة" ], "\\1 minute ago": [ - "قبل (\\d+[.,]?\\d*) دقيقة" + "قبل (\\d++[.,]?\\d*+) دقيقة" ], "\\1 month ago": [ - "قبل (\\d+[.,]?\\d*) شهر" + "قبل (\\d++[.,]?\\d*+) شهر" ], "\\1 second ago": [ - "قبل (\\d+[.,]?\\d*) ثانية" + "قبل (\\d++[.,]?\\d*+) ثانية" ], "\\1 week ago": [ - "قبل (\\d+[.,]?\\d*) أسبوع" + "قبل (\\d++[.,]?\\d*+) أسبوع" ], "\\1 year ago": [ - "قبل (\\d+[.,]?\\d*) سنة" + "قبل (\\d++[.,]?\\d*+) سنة" ], "in \\1 day": [ - "خلال (\\d+[.,]?\\d*) يوم" + "خلال (\\d++[.,]?\\d*+) يوم" ], "in \\1 hour": [ - "خلال (\\d+[.,]?\\d*) ساعة" + "خلال (\\d++[.,]?\\d*+) ساعة" ], "in \\1 minute": [ - "خلال (\\d+[.,]?\\d*) دقيقة" + "خلال (\\d++[.,]?\\d*+) دقيقة" ], "in \\1 month": [ - "خلال (\\d+[.,]?\\d*) شهر" + "خلال (\\d++[.,]?\\d*+) شهر" ], "in \\1 second": [ - "خلال (\\d+[.,]?\\d*) ثانية" + "خلال (\\d++[.,]?\\d*+) ثانية" ], "in \\1 week": [ - "خلال (\\d+[.,]?\\d*) أسبوع" + "خلال (\\d++[.,]?\\d*+) أسبوع" ], "in \\1 year": [ - "خلال (\\d+[.,]?\\d*) سنة" + "خلال (\\d++[.,]?\\d*+) سنة" ] }, "locale_specific": { @@ -570,5 +578,28 @@ ], "in": [ "خلال" + ], + "simplifications": [ + { + "(?<=(قبل|منذ)\\s+)أسبوع\\b": "1 أسبوع" + }, + { + "(?<=(قبل|منذ)\\s+)شهر\\b": "1 شهر" + }, + { + "(?<=(قبل|منذ)\\s+)سنة\\b": "1 سنة" + }, + { + "(?<=(قبل|منذ)\\s+)يوم\\b": "1 يوم" + }, + { + "(?<=(قبل|منذ)\\s+)ساعة\\b": "1 ساعة" + }, + { + "(?<=(قبل|منذ)\\s+)دقيقة\\b": "1 دقيقة" + }, + { + "(?<=(قبل|منذ)\\s+)ثانية\\b": "1 ثانية" + } ] } diff --git a/dateparser/data/date_translation_data/as.py b/dateparser/data/date_translation_data/as.py index f97def63b..7da14320b 100644 --- a/dateparser/data/date_translation_data/as.py +++ b/dateparser/data/date_translation_data/as.py @@ -1,6 +1,6 @@ info = { "name": "as", - "date_order": "YMD", + "date_order": "DMY", "january": [ "জানু", "জানুৱাৰী" @@ -16,6 +16,7 @@ "এপ্ৰিল" ], "may": [ + "মে'", "মে" ], "june": [ @@ -29,6 +30,7 @@ "আগষ্ট" ], "september": [ + "ছেপ্তে", "ছেপ্তেম্বৰ", "সেপ্ট" ], @@ -37,10 +39,12 @@ "অক্টোবৰ" ], "november": [ - "নভে", - "নৱেম্বৰ" + "নৱে", + "নৱেম্বৰ", + "নভে" ], "december": [ + "ডিচে", "ডিচেম্বৰ", "ডিসে" ], @@ -57,6 +61,8 @@ "বুধবাৰ" ], "thursday": [ + "বৃহ", + "বৃহস্পতিবাৰ", "বৃহষ্পতি", "বৃহষ্পতিবাৰ" ], @@ -69,13 +75,16 @@ "শনিবাৰ" ], "sunday": [ + "দেও", "দেওবাৰ", "ৰবি" ], "am": [ + "পূৰ্বাহ্ন", "পূৰ্বাহ্ণ" ], "pm": [ + "অপৰাহ্ন", "অপৰাহ্ণ" ], "year": [ @@ -104,48 +113,106 @@ "আজি" ], "0 hour ago": [ + "এইটো ঘণ্টাত", "this hour" ], "0 minute ago": [ + "এইটো মিনিটত", "this minute" ], "0 month ago": [ + "এই মা", + "এই মাহ", "this month" ], "0 second ago": [ + "এতিয়া", "now" ], "0 week ago": [ + "এই সপ্তাহ", "this week" ], "0 year ago": [ + "এই বছৰ", "this year" ], "1 day ago": [ "কালি" ], "1 month ago": [ + "যোৱা মা", + "যোৱা মাহ", "last month" ], "1 week ago": [ + "যোৱা সপ্তাহ", "last week" ], "1 year ago": [ + "যোৱা বছৰ", "last year" ], "in 1 day": [ "কাইলৈ" ], "in 1 month": [ + "অহা মাহ", "next month" ], "in 1 week": [ + "অহা সপ্তাহ", "next week" ], "in 1 year": [ + "অহা বছৰ", "next year" ] }, + "relative-type-regex": { + "\\1 day ago": [ + "(\\d++[.,]?\\d*+) দিন পূৰ্বে" + ], + "\\1 hour ago": [ + "(\\d++[.,]?\\d*+) ঘণ্টা পূৰ্বে" + ], + "\\1 minute ago": [ + "(\\d++[.,]?\\d*+) মিনিট পূৰ্বে" + ], + "\\1 month ago": [ + "(\\d++[.,]?\\d*+) মাহ পূৰ্বে" + ], + "\\1 second ago": [ + "(\\d++[.,]?\\d*+) ছেকেণ্ড পূৰ্বে" + ], + "\\1 week ago": [ + "(\\d++[.,]?\\d*+) সপ্তাহ পূৰ্বে" + ], + "\\1 year ago": [ + "(\\d++[.,]?\\d*+) বছৰৰ পূৰ্বে" + ], + "in \\1 day": [ + "(\\d++[.,]?\\d*+) দিনত" + ], + "in \\1 hour": [ + "(\\d++[.,]?\\d*+) ঘণ্টাত" + ], + "in \\1 minute": [ + "(\\d++[.,]?\\d*+) মিনিটত" + ], + "in \\1 month": [ + "(\\d++[.,]?\\d*+) মাহত" + ], + "in \\1 second": [ + "(\\d++[.,]?\\d*+) ছেকেণ্ডত" + ], + "in \\1 week": [ + "(\\d++[.,]?\\d*+) সপ্তাহত" + ], + "in \\1 year": [ + "(\\d++[.,]?\\d*+) বছৰত" + ] + }, "locale_specific": {}, "skip": [ " ", diff --git a/dateparser/data/date_translation_data/asa.py b/dateparser/data/date_translation_data/asa.py index fdbbc3350..ebcaa1e2f 100644 --- a/dateparser/data/date_translation_data/asa.py +++ b/dateparser/data/date_translation_data/asa.py @@ -95,6 +95,7 @@ "thiku" ], "hour": [ + "hr", "thaa" ], "minute": [ diff --git a/dateparser/data/date_translation_data/ast.py b/dateparser/data/date_translation_data/ast.py index cf32fb3bc..222cef83d 100644 --- a/dateparser/data/date_translation_data/ast.py +++ b/dateparser/data/date_translation_data/ast.py @@ -114,7 +114,8 @@ ], "hour": [ "h", - "hora" + "hora", + "hores" ], "minute": [ "m", @@ -188,78 +189,78 @@ }, "relative-type-regex": { "\\1 day ago": [ - "hai (\\d+[.,]?\\d*) d", - "hai (\\d+[.,]?\\d*) día", - "hai (\\d+[.,]?\\d*) díes" + "hai (\\d++[.,]?\\d*+) d", + "hai (\\d++[.,]?\\d*+) día", + "hai (\\d++[.,]?\\d*+) díes" ], "\\1 hour ago": [ - "hai (\\d+[.,]?\\d*) h", - "hai (\\d+[.,]?\\d*) hora", - "hai (\\d+[.,]?\\d*) hores" + "hai (\\d++[.,]?\\d*+) h", + "hai (\\d++[.,]?\\d*+) hora", + "hai (\\d++[.,]?\\d*+) hores" ], "\\1 minute ago": [ - "hai (\\d+[.,]?\\d*) min", - "hai (\\d+[.,]?\\d*) minutos", - "hai (\\d+[.,]?\\d*) minutu" + "hai (\\d++[.,]?\\d*+) min", + "hai (\\d++[.,]?\\d*+) minutos", + "hai (\\d++[.,]?\\d*+) minutu" ], "\\1 month ago": [ - "hai (\\d+[.,]?\\d*) m", - "hai (\\d+[.,]?\\d*) mes", - "hai (\\d+[.,]?\\d*) meses" + "hai (\\d++[.,]?\\d*+) m", + "hai (\\d++[.,]?\\d*+) mes", + "hai (\\d++[.,]?\\d*+) meses" ], "\\1 second ago": [ - "hai (\\d+[.,]?\\d*) s", - "hai (\\d+[.,]?\\d*) seg", - "hai (\\d+[.,]?\\d*) segundos", - "hai (\\d+[.,]?\\d*) segundu" + "hai (\\d++[.,]?\\d*+) s", + "hai (\\d++[.,]?\\d*+) seg", + "hai (\\d++[.,]?\\d*+) segundos", + "hai (\\d++[.,]?\\d*+) segundu" ], "\\1 week ago": [ - "hai (\\d+[.,]?\\d*) se", - "hai (\\d+[.,]?\\d*) selm", - "hai (\\d+[.,]?\\d*) selmana", - "hai (\\d+[.,]?\\d*) selmanes" + "hai (\\d++[.,]?\\d*+) se", + "hai (\\d++[.,]?\\d*+) selm", + "hai (\\d++[.,]?\\d*+) selmana", + "hai (\\d++[.,]?\\d*+) selmanes" ], "\\1 year ago": [ - "hai (\\d+[.,]?\\d*) a", - "hai (\\d+[.,]?\\d*) años", - "hai (\\d+[.,]?\\d*) añu" + "hai (\\d++[.,]?\\d*+) a", + "hai (\\d++[.,]?\\d*+) años", + "hai (\\d++[.,]?\\d*+) añu" ], "in \\1 day": [ - "en (\\d+[.,]?\\d*) d", - "en (\\d+[.,]?\\d*) día", - "en (\\d+[.,]?\\d*) díes" + "en (\\d++[.,]?\\d*+) d", + "en (\\d++[.,]?\\d*+) día", + "en (\\d++[.,]?\\d*+) díes" ], "in \\1 hour": [ - "en (\\d+[.,]?\\d*) h", - "en (\\d+[.,]?\\d*) hora", - "en (\\d+[.,]?\\d*) hores" + "en (\\d++[.,]?\\d*+) h", + "en (\\d++[.,]?\\d*+) hora", + "en (\\d++[.,]?\\d*+) hores" ], "in \\1 minute": [ - "en (\\d+[.,]?\\d*) min", - "en (\\d+[.,]?\\d*) minutos", - "en (\\d+[.,]?\\d*) minutu" + "en (\\d++[.,]?\\d*+) min", + "en (\\d++[.,]?\\d*+) minutos", + "en (\\d++[.,]?\\d*+) minutu" ], "in \\1 month": [ - "en (\\d+[.,]?\\d*) m", - "en (\\d+[.,]?\\d*) mes", - "en (\\d+[.,]?\\d*) meses" + "en (\\d++[.,]?\\d*+) m", + "en (\\d++[.,]?\\d*+) mes", + "en (\\d++[.,]?\\d*+) meses" ], "in \\1 second": [ - "en (\\d+[.,]?\\d*) s", - "en (\\d+[.,]?\\d*) seg", - "en (\\d+[.,]?\\d*) segundos", - "en (\\d+[.,]?\\d*) segundu" + "en (\\d++[.,]?\\d*+) s", + "en (\\d++[.,]?\\d*+) seg", + "en (\\d++[.,]?\\d*+) segundos", + "en (\\d++[.,]?\\d*+) segundu" ], "in \\1 week": [ - "en (\\d+[.,]?\\d*) se", - "en (\\d+[.,]?\\d*) selm", - "en (\\d+[.,]?\\d*) selmana", - "en (\\d+[.,]?\\d*) selmanes" + "en (\\d++[.,]?\\d*+) se", + "en (\\d++[.,]?\\d*+) selm", + "en (\\d++[.,]?\\d*+) selmana", + "en (\\d++[.,]?\\d*+) selmanes" ], "in \\1 year": [ - "en (\\d+[.,]?\\d*) a", - "en (\\d+[.,]?\\d*) años", - "en (\\d+[.,]?\\d*) añu" + "en (\\d++[.,]?\\d*+) a", + "en (\\d++[.,]?\\d*+) años", + "en (\\d++[.,]?\\d*+) añu" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/az-Cyrl.py b/dateparser/data/date_translation_data/az-Cyrl.py index 728d4c804..ce452d54b 100644 --- a/dateparser/data/date_translation_data/az-Cyrl.py +++ b/dateparser/data/date_translation_data/az-Cyrl.py @@ -95,7 +95,8 @@ "day" ], "hour": [ - "hour" + "hour", + "hr" ], "minute": [ "minute" diff --git a/dateparser/data/date_translation_data/az-Latn.py b/dateparser/data/date_translation_data/az-Latn.py index 1709c642d..df79ae0a8 100644 --- a/dateparser/data/date_translation_data/az-Latn.py +++ b/dateparser/data/date_translation_data/az-Latn.py @@ -157,46 +157,46 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) gün öncə" + "(\\d++[.,]?\\d*+) gün öncə" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) saat öncə" + "(\\d++[.,]?\\d*+) saat öncə" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) dəqiqə öncə" + "(\\d++[.,]?\\d*+) dəqiqə öncə" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) ay öncə" + "(\\d++[.,]?\\d*+) ay öncə" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) saniyə öncə" + "(\\d++[.,]?\\d*+) saniyə öncə" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) həftə öncə" + "(\\d++[.,]?\\d*+) həftə öncə" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) il öncə" + "(\\d++[.,]?\\d*+) il öncə" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) gün ərzində" + "(\\d++[.,]?\\d*+) gün ərzində" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) saat ərzində" + "(\\d++[.,]?\\d*+) saat ərzində" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) dəqiqə ərzində" + "(\\d++[.,]?\\d*+) dəqiqə ərzində" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) ay ərzində" + "(\\d++[.,]?\\d*+) ay ərzində" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) saniyə ərzində" + "(\\d++[.,]?\\d*+) saniyə ərzində" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) həftə ərzində" + "(\\d++[.,]?\\d*+) həftə ərzində" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) il ərzində" + "(\\d++[.,]?\\d*+) il ərzində" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/az.py b/dateparser/data/date_translation_data/az.py index 037511509..e4033ab9f 100644 --- a/dateparser/data/date_translation_data/az.py +++ b/dateparser/data/date_translation_data/az.py @@ -157,46 +157,46 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) gün öncə" + "(\\d++[.,]?\\d*+) gün öncə" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) saat öncə" + "(\\d++[.,]?\\d*+) saat öncə" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) dəqiqə öncə" + "(\\d++[.,]?\\d*+) dəqiqə öncə" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) ay öncə" + "(\\d++[.,]?\\d*+) ay öncə" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) saniyə öncə" + "(\\d++[.,]?\\d*+) saniyə öncə" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) həftə öncə" + "(\\d++[.,]?\\d*+) həftə öncə" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) il öncə" + "(\\d++[.,]?\\d*+) il öncə" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) gün ərzində" + "(\\d++[.,]?\\d*+) gün ərzində" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) saat ərzində" + "(\\d++[.,]?\\d*+) saat ərzində" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) dəqiqə ərzində" + "(\\d++[.,]?\\d*+) dəqiqə ərzində" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) ay ərzində" + "(\\d++[.,]?\\d*+) ay ərzində" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) saniyə ərzində" + "(\\d++[.,]?\\d*+) saniyə ərzində" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) həftə ərzində" + "(\\d++[.,]?\\d*+) həftə ərzində" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) il ərzində" + "(\\d++[.,]?\\d*+) il ərzində" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/bas.py b/dateparser/data/date_translation_data/bas.py index d66975bbf..6bafffb58 100644 --- a/dateparser/data/date_translation_data/bas.py +++ b/dateparser/data/date_translation_data/bas.py @@ -96,6 +96,7 @@ "kɛl" ], "hour": [ + "hr", "ŋgɛŋ" ], "minute": [ diff --git a/dateparser/data/date_translation_data/be.py b/dateparser/data/date_translation_data/be.py index ea3e99dd3..54a135698 100644 --- a/dateparser/data/date_translation_data/be.py +++ b/dateparser/data/date_translation_data/be.py @@ -143,6 +143,7 @@ "гадз", "гадзіна", "гадзіны", + "гадзіны", "гадзіну", "гадзін" ], @@ -174,12 +175,14 @@ "у гэту хвіліну" ], "0 month ago": [ + "у гэтым мес", "у гэтым месяцы" ], "0 second ago": [ "цяпер" ], "0 week ago": [ + "на гэтым тыд", "на гэтым тыдні" ], "0 year ago": [ @@ -190,24 +193,30 @@ "ўчора" ], "1 month ago": [ + "у мін мес", "у мінулым месяцы" ], "1 week ago": [ + "на мін тыд", "на мінулым тыдні" ], "1 year ago": [ + "у мін годзе", "у мінулым годзе" ], "in 1 day": [ "заўтра" ], "in 1 month": [ + "у наст мес", "у наступным месяцы" ], "in 1 week": [ + "на наст тыд", "на наступным тыдні" ], "in 1 year": [ + "у наст годзе", "у наступным годзе" ], "2 day ago": [ @@ -216,74 +225,74 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) д таму", - "(\\d+[.,]?\\d*) дзень таму", - "(\\d+[.,]?\\d*) дня таму" + "(\\d++[.,]?\\d*+) дзень таму", + "(\\d++[.,]?\\d*+) дня таму", + "(\\d++[.,]?\\d*+) д таму" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) гадз таму", - "(\\d+[.,]?\\d*) гадзіну таму", - "(\\d+[.,]?\\d*) гадзіны таму" + "(\\d++[.,]?\\d*+) гадз таму", + "(\\d++[.,]?\\d*+) гадзіну таму", + "(\\d++[.,]?\\d*+) гадзіны таму" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) хв таму", - "(\\d+[.,]?\\d*) хвіліну таму", - "(\\d+[.,]?\\d*) хвіліны таму" + "(\\d++[.,]?\\d*+) хв таму", + "(\\d++[.,]?\\d*+) хвіліну таму", + "(\\d++[.,]?\\d*+) хвіліны таму" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) мес таму", - "(\\d+[.,]?\\d*) месяц таму", - "(\\d+[.,]?\\d*) месяца таму" + "(\\d++[.,]?\\d*+) мес таму", + "(\\d++[.,]?\\d*+) месяц таму", + "(\\d++[.,]?\\d*+) месяца таму" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) с таму", - "(\\d+[.,]?\\d*) секунду таму", - "(\\d+[.,]?\\d*) секунды таму" + "(\\d++[.,]?\\d*+) с таму", + "(\\d++[.,]?\\d*+) секунду таму", + "(\\d++[.,]?\\d*+) секунды таму" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) тыд таму", - "(\\d+[.,]?\\d*) тыдзень таму", - "(\\d+[.,]?\\d*) тыдня таму" + "(\\d++[.,]?\\d*+) тыд таму", + "(\\d++[.,]?\\d*+) тыдзень таму", + "(\\d++[.,]?\\d*+) тыдня таму" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) г таму", - "(\\d+[.,]?\\d*) год таму", - "(\\d+[.,]?\\d*) года таму" + "(\\d++[.,]?\\d*+) г таму", + "(\\d++[.,]?\\d*+) год таму", + "(\\d++[.,]?\\d*+) года таму" ], "in \\1 day": [ - "праз (\\d+[.,]?\\d*) д", - "праз (\\d+[.,]?\\d*) дзень", - "праз (\\d+[.,]?\\d*) дня" + "праз (\\d++[.,]?\\d*+) дзень", + "праз (\\d++[.,]?\\d*+) дня", + "праз (\\d++[.,]?\\d*+) д" ], "in \\1 hour": [ - "праз (\\d+[.,]?\\d*) гадз", - "праз (\\d+[.,]?\\d*) гадзіну", - "праз (\\d+[.,]?\\d*) гадзіны" + "праз (\\d++[.,]?\\d*+) гадз", + "праз (\\d++[.,]?\\d*+) гадзіну", + "праз (\\d++[.,]?\\d*+) гадзіны" ], "in \\1 minute": [ - "праз (\\d+[.,]?\\d*) хв", - "праз (\\d+[.,]?\\d*) хвіліну", - "праз (\\d+[.,]?\\d*) хвіліны" + "праз (\\d++[.,]?\\d*+) хв", + "праз (\\d++[.,]?\\d*+) хвіліну", + "праз (\\d++[.,]?\\d*+) хвіліны" ], "in \\1 month": [ - "праз (\\d+[.,]?\\d*) мес", - "праз (\\d+[.,]?\\d*) месяц", - "праз (\\d+[.,]?\\d*) месяца" + "праз (\\d++[.,]?\\d*+) мес", + "праз (\\d++[.,]?\\d*+) месяц", + "праз (\\d++[.,]?\\d*+) месяца" ], "in \\1 second": [ - "праз (\\d+[.,]?\\d*) с", - "праз (\\d+[.,]?\\d*) секунду", - "праз (\\d+[.,]?\\d*) секунды" + "праз (\\d++[.,]?\\d*+) с", + "праз (\\d++[.,]?\\d*+) секунду", + "праз (\\d++[.,]?\\d*+) секунды" ], "in \\1 week": [ - "праз (\\d+[.,]?\\d*) тыд", - "праз (\\d+[.,]?\\d*) тыдзень", - "праз (\\d+[.,]?\\d*) тыдня" + "праз (\\d++[.,]?\\d*+) тыд", + "праз (\\d++[.,]?\\d*+) тыдзень", + "праз (\\d++[.,]?\\d*+) тыдня" ], "in \\1 year": [ - "праз (\\d+[.,]?\\d*) г", - "праз (\\d+[.,]?\\d*) год", - "праз (\\d+[.,]?\\d*) года" + "праз (\\d++[.,]?\\d*+) г", + "праз (\\d++[.,]?\\d*+) год", + "праз (\\d++[.,]?\\d*+) года" ] }, "locale_specific": {}, @@ -334,7 +343,19 @@ "некалькі хвілін": "2 хвіліны" }, { - "(\\d+[.,]?\\d*)\\s*гадзін\\s(\\d+[.,]?\\d*)\\s*хвілін": "\\1:\\2" + "(\\d++[.,]?\\d*+)\\s*гадзін\\s(\\d++[.,]?\\d*+)\\s*хвілін": "\\1:\\2" + }, + { + "(?<=[^\\d]\\s+|^)тыдзень(?=\\s+таму)": "1 тыдзень" + }, + { + "(?<=[^\\d]\\s+|^)месяц(?=\\s+таму)": "1 месяц" + }, + { + "(?<=[^\\d]\\s+|^)год(?=\\s+таму)": "1 год" + }, + { + "(?<=[^\\d]\\s+|^)дзень(?=\\s+таму)": "1 дзень" } ] } diff --git a/dateparser/data/date_translation_data/bem.py b/dateparser/data/date_translation_data/bem.py index 6b8d2b6bd..8edb5aef6 100644 --- a/dateparser/data/date_translation_data/bem.py +++ b/dateparser/data/date_translation_data/bem.py @@ -88,6 +88,7 @@ "ubushiku" ], "hour": [ + "hr", "insa" ], "minute": [ diff --git a/dateparser/data/date_translation_data/bez.py b/dateparser/data/date_translation_data/bez.py index 476edab59..be114631b 100644 --- a/dateparser/data/date_translation_data/bez.py +++ b/dateparser/data/date_translation_data/bez.py @@ -96,6 +96,7 @@ "sihu" ], "hour": [ + "hr", "saa" ], "minute": [ diff --git a/dateparser/data/date_translation_data/bg.py b/dateparser/data/date_translation_data/bg.py index 972971b60..a03a92fe7 100644 --- a/dateparser/data/date_translation_data/bg.py +++ b/dateparser/data/date_translation_data/bg.py @@ -93,15 +93,17 @@ ], "year": [ "г", + "год", "година", "год", "години" ], "month": [ - "м", + "мес", "месец", "мес", - "месеци" + "месеци", + "м" ], "week": [ "седм", @@ -119,6 +121,7 @@ "hour": [ "ч", "час", + "часове", "часа" ], "minute": [ @@ -127,7 +130,7 @@ "минути" ], "second": [ - "с", + "сек", "секунда", "сек", "секунди" @@ -170,9 +173,9 @@ ], "1 week ago": [ "мин седм", - "миналата седмица", "предходната седмица", - "преди седмица" + "преди седмица", + "миналата седмица" ], "1 year ago": [ "мин г", @@ -219,86 +222,86 @@ }, "relative-type-regex": { "\\1 day ago": [ - "пр (\\d+[.,]?\\d*) д", - "преди (\\d+[.,]?\\d*) ден", - "преди (\\d+[.,]?\\d*) дни" + "пр (\\d++[.,]?\\d*+) д", + "преди (\\d++[.,]?\\d*+) ден", + "преди (\\d++[.,]?\\d*+) дни" ], "\\1 hour ago": [ - "пр (\\d+[.,]?\\d*) ч", - "преди (\\d+[.,]?\\d*) ч", - "преди (\\d+[.,]?\\d*) час", - "преди (\\d+[.,]?\\d*) часа" + "пр (\\d++[.,]?\\d*+) ч", + "преди (\\d++[.,]?\\d*+) ч", + "преди (\\d++[.,]?\\d*+) час", + "преди (\\d++[.,]?\\d*+) часа" ], "\\1 minute ago": [ - "пр (\\d+[.,]?\\d*) мин", - "преди (\\d+[.,]?\\d*) мин", - "преди (\\d+[.,]?\\d*) минута", - "преди (\\d+[.,]?\\d*) минути" + "пр (\\d++[.,]?\\d*+) мин", + "преди (\\d++[.,]?\\d*+) мин", + "преди (\\d++[.,]?\\d*+) минута", + "преди (\\d++[.,]?\\d*+) минути" ], "\\1 month ago": [ - "пр (\\d+[.,]?\\d*) м", - "преди (\\d+[.,]?\\d*) м", - "преди (\\d+[.,]?\\d*) месец", - "преди (\\d+[.,]?\\d*) месеца" + "пр (\\d++[.,]?\\d*+) м", + "преди (\\d++[.,]?\\d*+) м", + "преди (\\d++[.,]?\\d*+) месец", + "преди (\\d++[.,]?\\d*+) месеца" ], "\\1 second ago": [ - "пр (\\d+[.,]?\\d*) сек", - "преди (\\d+[.,]?\\d*) сек", - "преди (\\d+[.,]?\\d*) секунда", - "преди (\\d+[.,]?\\d*) секунди" + "пр (\\d++[.,]?\\d*+) сек", + "преди (\\d++[.,]?\\d*+) сек", + "преди (\\d++[.,]?\\d*+) секунда", + "преди (\\d++[.,]?\\d*+) секунди" ], "\\1 week ago": [ - "пр (\\d+[.,]?\\d*) седм", - "преди (\\d+[.,]?\\d*) седм", - "преди (\\d+[.,]?\\d*) седмица", - "преди (\\d+[.,]?\\d*) седмици" + "пр (\\d++[.,]?\\d*+) седм", + "преди (\\d++[.,]?\\d*+) седм", + "преди (\\d++[.,]?\\d*+) седмица", + "преди (\\d++[.,]?\\d*+) седмици" ], "\\1 year ago": [ - "пр (\\d+[.,]?\\d*) г", - "преди (\\d+[.,]?\\d*) г", - "преди (\\d+[.,]?\\d*) година", - "преди (\\d+[.,]?\\d*) години" + "пр (\\d++[.,]?\\d*+) г", + "преди (\\d++[.,]?\\d*+) г", + "преди (\\d++[.,]?\\d*+) година", + "преди (\\d++[.,]?\\d*+) години" ], "in \\1 day": [ - "сл (\\d+[.,]?\\d*) д", - "след (\\d+[.,]?\\d*) ден", - "след (\\d+[.,]?\\d*) дни" + "сл (\\d++[.,]?\\d*+) д", + "след (\\d++[.,]?\\d*+) ден", + "след (\\d++[.,]?\\d*+) дни" ], "in \\1 hour": [ - "сл (\\d+[.,]?\\d*) ч", - "след (\\d+[.,]?\\d*) ч", - "след (\\d+[.,]?\\d*) час", - "след (\\d+[.,]?\\d*) часа" + "сл (\\d++[.,]?\\d*+) ч", + "след (\\d++[.,]?\\d*+) ч", + "след (\\d++[.,]?\\d*+) час", + "след (\\d++[.,]?\\d*+) часа" ], "in \\1 minute": [ - "сл (\\d+[.,]?\\d*) мин", - "след (\\d+[.,]?\\d*) мин", - "след (\\d+[.,]?\\d*) минута", - "след (\\d+[.,]?\\d*) минути" + "сл (\\d++[.,]?\\d*+) мин", + "след (\\d++[.,]?\\d*+) мин", + "след (\\d++[.,]?\\d*+) минута", + "след (\\d++[.,]?\\d*+) минути" ], "in \\1 month": [ - "сл (\\d+[.,]?\\d*) м", - "след (\\d+[.,]?\\d*) м", - "след (\\d+[.,]?\\d*) месец", - "след (\\d+[.,]?\\d*) месеца" + "сл (\\d++[.,]?\\d*+) м", + "след (\\d++[.,]?\\d*+) м", + "след (\\d++[.,]?\\d*+) месец", + "след (\\d++[.,]?\\d*+) месеца" ], "in \\1 second": [ - "сл (\\d+[.,]?\\d*) сек", - "след (\\d+[.,]?\\d*) сек", - "след (\\d+[.,]?\\d*) секунда", - "след (\\d+[.,]?\\d*) секунди" + "сл (\\d++[.,]?\\d*+) сек", + "след (\\d++[.,]?\\d*+) сек", + "след (\\d++[.,]?\\d*+) секунда", + "след (\\d++[.,]?\\d*+) секунди" ], "in \\1 week": [ - "сл (\\d+[.,]?\\d*) седм", - "след (\\d+[.,]?\\d*) седм", - "след (\\d+[.,]?\\d*) седмица", - "след (\\d+[.,]?\\d*) седмици" + "сл (\\d++[.,]?\\d*+) седм", + "след (\\d++[.,]?\\d*+) седм", + "след (\\d++[.,]?\\d*+) седмица", + "след (\\d++[.,]?\\d*+) седмици" ], "in \\1 year": [ - "сл (\\d+[.,]?\\d*) г", - "след (\\d+[.,]?\\d*) г", - "след (\\d+[.,]?\\d*) година", - "след (\\d+[.,]?\\d*) години" + "сл (\\d++[.,]?\\d*+) г", + "след (\\d++[.,]?\\d*+) г", + "след (\\d++[.,]?\\d*+) година", + "след (\\d++[.,]?\\d*+) години" ] }, "locale_specific": {}, @@ -340,6 +343,9 @@ }, { "три": "3" + }, + { + "(?<=преди\\s+)месец\\b": "1 месец" } ] } diff --git a/dateparser/data/date_translation_data/bm.py b/dateparser/data/date_translation_data/bm.py index 6cadd73c7..396377dbc 100644 --- a/dateparser/data/date_translation_data/bm.py +++ b/dateparser/data/date_translation_data/bm.py @@ -94,6 +94,7 @@ "don" ], "hour": [ + "hr", "lɛrɛ" ], "minute": [ diff --git a/dateparser/data/date_translation_data/bn.py b/dateparser/data/date_translation_data/bn.py index 409f0d587..f2c2c1054 100644 --- a/dateparser/data/date_translation_data/bn.py +++ b/dateparser/data/date_translation_data/bn.py @@ -15,6 +15,7 @@ "মার্চ" ], "april": [ + "এপ্রি", "এপ্রিল" ], "may": [ @@ -24,21 +25,27 @@ "জুন" ], "july": [ + "জুল", "জুলাই" ], "august": [ + "আগ", "আগস্ট" ], "september": [ + "সেপ", "সেপ্টেম্বর" ], "october": [ + "অক্টো", "অক্টোবর" ], "november": [ + "নভে", "নভেম্বর" ], "december": [ + "ডিসে", "ডিসেম্বর" ], "monday": [ @@ -54,9 +61,9 @@ "বুধবার" ], "thursday": [ - "বৃহষ্পতিবার", "বৃহস্পতি", - "বৃহস্পতিবার" + "বৃহস্পতিবার", + "বৃহষ্পতিবার" ], "friday": [ "শুক্র", @@ -91,6 +98,7 @@ "দিন" ], "hour": [ + "ঘণ্টা", "ঘন্টা" ], "minute": [ @@ -154,53 +162,65 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) দিন আগে" + "(\\d++[.,]?\\d*+) দিন আগে" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) ঘন্টা আগে" + "(\\d++[.,]?\\d*+) ঘন্টা আগে" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) মিনিট আগে", - "(\\d+[.,]?\\d*) মিনিট পূর্বে" + "(\\d++[.,]?\\d*+) মিনিট আগে", + "(\\d++[.,]?\\d*+) মিনিট পূর্বে" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) মাস আগে" + "(\\d++[.,]?\\d*+) মাস আগে" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) সেকেন্ড আগে", - "(\\d+[.,]?\\d*) সেকেন্ড পূর্বে" + "(\\d++[.,]?\\d*+) সেকেন্ড আগে", + "(\\d++[.,]?\\d*+) সেকেন্ড পূর্বে" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) সপ্তাহ আগে" + "(\\d++[.,]?\\d*+) সপ্তাহ আগে" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) বছর পূর্বে" + "(\\d++[.,]?\\d*+) বছর পূর্বে" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) দিনের মধ্যে" + "(\\d++[.,]?\\d*+) দিনের মধ্যে" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) ঘন্টায়" + "(\\d++[.,]?\\d*+) ঘন্টায়" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) মিনিটে" + "(\\d++[.,]?\\d*+) মিনিটে" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) মাসে" + "(\\d++[.,]?\\d*+) মাসে" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) সেকেন্ডে" + "(\\d++[.,]?\\d*+) সেকেন্ডে" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) সপ্তাহে" + "(\\d++[.,]?\\d*+) সপ্তাহে" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) বছরে" + "(\\d++[.,]?\\d*+) বছরে" ] }, "locale_specific": { "bn-IN": { - "name": "bn-IN" + "name": "bn-IN", + "september": [ + "সেপ্টেঃ" + ], + "october": [ + "অক্টোঃ" + ], + "november": [ + "নভেঃ" + ], + "december": [ + "ডিসেঃ" + ] } }, "skip": [ diff --git a/dateparser/data/date_translation_data/bo.py b/dateparser/data/date_translation_data/bo.py index b805577b6..1b5d9b9a2 100644 --- a/dateparser/data/date_translation_data/bo.py +++ b/dateparser/data/date_translation_data/bo.py @@ -108,6 +108,7 @@ "ཉིན།" ], "hour": [ + "hr", "ཆུ་ཚོད་" ], "minute": [ diff --git a/dateparser/data/date_translation_data/br.py b/dateparser/data/date_translation_data/br.py index 38c5ae437..dcd406e25 100644 --- a/dateparser/data/date_translation_data/br.py +++ b/dateparser/data/date_translation_data/br.py @@ -1,6 +1,6 @@ info = { "name": "br", - "date_order": "YMD", + "date_order": "DMY", "january": [ "gen", "genver" @@ -42,9 +42,9 @@ "du" ], "december": [ - "ker", "kerzu", - "kzu" + "kzu", + "ker" ], "monday": [ "lun" @@ -78,13 +78,16 @@ "gm" ], "year": [ + "b", "bl", "bloaz" ], "month": [ + "m", "miz" ], "week": [ + "sizh", "sizhun" ], "day": [ @@ -93,7 +96,8 @@ ], "hour": [ "e", - "eur" + "eur", + "eurioù" ], "minute": [ "min", @@ -108,12 +112,15 @@ "hiziv" ], "0 hour ago": [ + "d'an eur-mañ", "this hour" ], "0 minute ago": [ + "ar munut-mañ", "this minute" ], "0 month ago": [ + "ar m-mañ", "ar miz-mañ" ], "0 second ago": [ @@ -121,6 +128,7 @@ "bremañ" ], "0 week ago": [ + "ar sizh-mañ", "ar sizhun-mañ" ], "0 year ago": [ @@ -130,9 +138,11 @@ "dec'h" ], "1 month ago": [ + "ar m diaraok", "ar miz diaraok" ], "1 week ago": [ + "ar sizh diaraok", "ar sizhun diaraok" ], "1 year ago": [ @@ -142,9 +152,11 @@ "warc'hoazh" ], "in 1 month": [ + "ar m a zeu", "ar miz a zeu" ], "in 1 week": [ + "ar sizh a zeu", "ar sizhun a zeu" ], "in 1 year": [ @@ -154,58 +166,60 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) d zo", - "(\\d+[.,]?\\d*) deiz zo" + "(\\d++[.,]?\\d*+) d zo", + "(\\d++[.,]?\\d*+) deiz zo" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) e zo", - "(\\d+[.,]?\\d*) eur zo" + "(\\d++[.,]?\\d*+) e zo", + "(\\d++[.,]?\\d*+) eur zo" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) min zo", - "(\\d+[.,]?\\d*) munut zo" + "(\\d++[.,]?\\d*+) min zo", + "(\\d++[.,]?\\d*+) munut zo" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) miz zo" + "(\\d++[.,]?\\d*+) miz zo" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) eilenn zo", - "(\\d+[.,]?\\d*) s zo" + "(\\d++[.,]?\\d*+) eilenn zo", + "(\\d++[.,]?\\d*+) s zo" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) sizhun zo" + "(\\d++[.,]?\\d*+) sizh zo", + "(\\d++[.,]?\\d*+) sizhun zo" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) bl zo", - "(\\d+[.,]?\\d*) bloaz zo", - "(\\d+[.,]?\\d*) vloaz zo" + "(\\d++[.,]?\\d*+) bl zo", + "(\\d++[.,]?\\d*+) bloaz zo", + "(\\d++[.,]?\\d*+) vloaz zo" ], "in \\1 day": [ - "a-benn (\\d+[.,]?\\d*) d", - "a-benn (\\d+[.,]?\\d*) deiz" + "a-benn (\\d++[.,]?\\d*+) d", + "a-benn (\\d++[.,]?\\d*+) deiz" ], "in \\1 hour": [ - "a-benn (\\d+[.,]?\\d*) e", - "a-benn (\\d+[.,]?\\d*) eur" + "a-benn (\\d++[.,]?\\d*+) e", + "a-benn (\\d++[.,]?\\d*+) eur" ], "in \\1 minute": [ - "a-benn (\\d+[.,]?\\d*) min", - "a-benn (\\d+[.,]?\\d*) munut" + "a-benn (\\d++[.,]?\\d*+) min", + "a-benn (\\d++[.,]?\\d*+) munut" ], "in \\1 month": [ - "a-benn (\\d+[.,]?\\d*) miz" + "a-benn (\\d++[.,]?\\d*+) miz" ], "in \\1 second": [ - "a-benn (\\d+[.,]?\\d*) eilenn", - "a-benn (\\d+[.,]?\\d*) s" + "a-benn (\\d++[.,]?\\d*+) eilenn", + "a-benn (\\d++[.,]?\\d*+) s" ], "in \\1 week": [ - "a-benn (\\d+[.,]?\\d*) sizhun" + "a-benn (\\d++[.,]?\\d*+) sizh", + "a-benn (\\d++[.,]?\\d*+) sizhun" ], "in \\1 year": [ - "a-benn (\\d+[.,]?\\d*) bl", - "a-benn (\\d+[.,]?\\d*) bloaz", - "a-benn (\\d+[.,]?\\d*) vloaz" + "a-benn (\\d++[.,]?\\d*+) bl", + "a-benn (\\d++[.,]?\\d*+) bloaz", + "a-benn (\\d++[.,]?\\d*+) vloaz" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/brx.py b/dateparser/data/date_translation_data/brx.py index 0630614b9..4020e6d23 100644 --- a/dateparser/data/date_translation_data/brx.py +++ b/dateparser/data/date_translation_data/brx.py @@ -1,16 +1,22 @@ info = { "name": "brx", - "date_order": "MDY", + "date_order": "DMY", "january": [ + "जान", "जानुवारी" ], "february": [ + "फेब", + "फेब्रूवारी", "फेब्रुवारी" ], "march": [ + "मार्च", "मार्स" ], "april": [ + "एप्रि", + "एप्रिल", "एफ्रिल" ], "may": [ @@ -20,21 +26,33 @@ "जुन" ], "july": [ + "जुल", + "जुलाई", "जुलाइ" ], "august": [ + "आग", + "आगष्ट", "आगस्थ" ], "september": [ + "सेप", + "सेप्थेम्बर", "सेबथेज्ब़र" ], "october": [ + "अक्ट'", + "अक्ट'बर", "अखथबर" ], "november": [ + "नवे", + "नवेम्बर", "नबेज्ब़र" ], "december": [ + "डिसे", + "डिसेम्बर", "दिसेज्ब़र" ], "monday": [ @@ -46,18 +64,25 @@ "मंगलबार" ], "wednesday": [ + "बुध", + "बुधबार", "बुद", "बुदबार" ], "thursday": [ + "बिस्थि", + "बिस्थिबार", "बिसथि", "बिसथिबार" ], "friday": [ "सुखुर", - "सुखुरबार" + "सुखुरबार", + "सुुखुरबार" ], "saturday": [ + "सनि", + "सनिबार", "सुनि", "सुनिबार" ], @@ -78,18 +103,23 @@ "दान" ], "week": [ + "सप्थाह", "सबथा/हबथा" ], "day": [ "सान" ], "hour": [ + "hr", + "घन्टा", "रिंगा" ], "minute": [ + "मिनित", "मिनिथ" ], "second": [ + "सेकेण्ड", "सेखेन्द" ], "relative-type": { @@ -97,48 +127,104 @@ "दिनै" ], "0 hour ago": [ + "बे घन्टा", "this hour" ], "0 minute ago": [ + "बे मिनिट", "this minute" ], "0 month ago": [ + "बे दान", "this month" ], "0 second ago": [ + "दा", "now" ], "0 week ago": [ + "बे सप्थाह", "this week" ], "0 year ago": [ + "बे बोसोर", "this year" ], "1 day ago": [ "मैया" ], "1 month ago": [ + "थांनाय दान", "last month" ], "1 week ago": [ + "थांनाय सप्थाह", "last week" ], "1 year ago": [ + "थांनाय बोसोर", "last year" ], "in 1 day": [ "गाबोन" ], "in 1 month": [ + "फैगौ दान", "next month" ], "in 1 week": [ + "फैगौ सप्थाह", "next week" ], "in 1 year": [ + "फैगौ बोसोर", "next year" ] }, + "relative-type-regex": { + "\\1 day ago": [ + "(\\d++[.,]?\\d*+) सान सिगां" + ], + "\\1 hour ago": [ + "(\\d++[.,]?\\d*+) घन्टा सिगां" + ], + "\\1 minute ago": [ + "(\\d++[.,]?\\d*+) मिनिट सिगां" + ], + "\\1 month ago": [ + "(\\d++[.,]?\\d*+) दान सिगां" + ], + "\\1 second ago": [ + "(\\d++[.,]?\\d*+) सेकेण्ड सिगां" + ], + "\\1 week ago": [ + "(\\d++[.,]?\\d*+) सप्थाह सिगां" + ], + "\\1 year ago": [ + "(\\d++[.,]?\\d*+) बोसोर सिगां" + ], + "in \\1 day": [ + "(\\d++[.,]?\\d*+) सानाव" + ], + "in \\1 hour": [ + "(\\d++[.,]?\\d*+) घन्टायाव" + ], + "in \\1 minute": [ + "(\\d++[.,]?\\d*+) मिनिटआव" + ], + "in \\1 month": [ + "(\\d++[.,]?\\d*+) दानाव" + ], + "in \\1 second": [ + "(\\d++[.,]?\\d*+) सेकेण्डआव" + ], + "in \\1 week": [ + "(\\d++[.,]?\\d*+) सप्थाहयाव" + ], + "in \\1 year": [ + "(\\d++[.,]?\\d*+) बोसोरआव" + ] + }, "locale_specific": {}, "skip": [ " ", diff --git a/dateparser/data/date_translation_data/bs-Cyrl.py b/dateparser/data/date_translation_data/bs-Cyrl.py index c07a696f8..3d61d3321 100644 --- a/dateparser/data/date_translation_data/bs-Cyrl.py +++ b/dateparser/data/date_translation_data/bs-Cyrl.py @@ -29,6 +29,8 @@ "јули" ], "august": [ + "ауг", + "аугуст", "авг", "август" ], @@ -50,6 +52,8 @@ ], "monday": [ "пон", + "понедјељак", + "понедјељак", "понедељак" ], "tuesday": [ @@ -74,138 +78,264 @@ ], "sunday": [ "нед", + "недјеља", + "недјеља", "недеља" ], "am": [ - "пре подне" + "пре подне", + "прије подне", + "пријеподне" ], "pm": [ - "поподне" + "поподне", + "послије подне", + "послијеподне" ], "year": [ - "година" + "год", + "година", + "г", + "год", + "годинa" ], "month": [ + "мјес", + "мјесец", + "мј", + "мјесец", + "мјесеци", + "мјесеца", "месец" ], "week": [ + "седм", + "седмица", + "сед", + "седмица", + "седмице", "недеља" ], "day": [ "дан" ], "hour": [ + "сат", + "сати", + "сат", "час" ], "minute": [ - "минут" + "мин", + "минут", + "мин", + "минута" ], "second": [ - "секунд" + "сек", + "секунд", + "с", + "сек", + "секунда" ], "relative-type": { "0 day ago": [ "данас" ], "0 hour ago": [ + "овог сата", + "овај сат", "this hour" ], "0 minute ago": [ + "овог минута", + "ова минута", "this minute" ], "0 month ago": [ + "ов мјес", + "овог мјес", + "овог мјесеца", + "овај мјесец", "овог месеца" ], "0 second ago": [ + "сада", + "сада", "now" ], "0 week ago": [ + "ове седм", + "ове седмице", + "ове седмице", "ове недеље" ], "0 year ago": [ + "ове год", "ове године" ], "1 day ago": [ "јуче" ], "1 month ago": [ + "прош мјес", + "прош мјесеца", + "прошлог мјесеца", + "прошли мјесец", "прошлог месеца" ], "1 week ago": [ + "прош седм", + "прошле седмице", + "прошле седмице", "прошле недеље" ], "1 year ago": [ + "прош године", "прошле године" ], "in 1 day": [ "сутра" ], "in 1 month": [ + "сљ мјес", + "сљед мјесеца", + "сљедећег мјесеца", + "сљедећи мјесец", "следећег месеца" ], "in 1 week": [ + "сљ седм", + "сљедеће седмице", + "сљедеће седмице", "следеће недеље" ], "in 1 year": [ + "сљед године", + "сљедеће године", + "сљедеће године", "следеће године" ] }, "relative-type-regex": { "\\1 day ago": [ - "пре (\\d+[.,]?\\d*) дан", - "пре (\\d+[.,]?\\d*) дана" + "прије (\\d++[.,]?\\d*+) дан", + "прије (\\d++[.,]?\\d*+) дана", + "прије (\\d++[.,]?\\d*+) дан", + "прије (\\d++[.,]?\\d*+) дана", + "пре (\\d++[.,]?\\d*+) дан", + "пре (\\d++[.,]?\\d*+) дана" ], "\\1 hour ago": [ - "пре (\\d+[.,]?\\d*) сат", - "пре (\\d+[.,]?\\d*) сати" + "прије (\\d++[.,]?\\d*+) сат", + "прије (\\d++[.,]?\\d*+) сати", + "прије (\\d++[.,]?\\d*+) сат", + "прије (\\d++[.,]?\\d*+) сати", + "пре (\\d++[.,]?\\d*+) сат", + "пре (\\d++[.,]?\\d*+) сати" ], "\\1 minute ago": [ - "пре (\\d+[.,]?\\d*) минут", - "пре (\\d+[.,]?\\d*) минута" + "прије (\\d++[.,]?\\d*+) мин", + "прије (\\d++[.,]?\\d*+) минут", + "прије (\\d++[.,]?\\d*+) минута", + "прије (\\d++[.,]?\\d*+) мин", + "прије (\\d++[.,]?\\d*+) минута", + "прије (\\d++[.,]?\\d*+) минуту", + "пре (\\d++[.,]?\\d*+) минут", + "пре (\\d++[.,]?\\d*+) минута" ], "\\1 month ago": [ - "пре (\\d+[.,]?\\d*) месец", - "пре (\\d+[.,]?\\d*) месеци" + "прије (\\d++[.,]?\\d*+) мјес", + "прије (\\d++[.,]?\\d*+) мјесец", + "прије (\\d++[.,]?\\d*+) мјесеци", + "прије (\\d++[.,]?\\d*+) мј", + "прије (\\d++[.,]?\\d*+) мјесец", + "прије (\\d++[.,]?\\d*+) мјесеца", + "прије (\\d++[.,]?\\d*+) мјесеци", + "пре (\\d++[.,]?\\d*+) месец", + "пре (\\d++[.,]?\\d*+) месеци" ], "\\1 second ago": [ - "пре (\\d+[.,]?\\d*) секунд", - "пре (\\d+[.,]?\\d*) секунди" + "прије (\\d++[.,]?\\d*+) сек", + "прије (\\d++[.,]?\\d*+) секунд", + "прије (\\d++[.,]?\\d*+) секунди", + "прије (\\d++[.,]?\\d*+) сек", + "прије (\\d++[.,]?\\d*+) секунда", + "прије (\\d++[.,]?\\d*+) секунду", + "пре (\\d++[.,]?\\d*+) секунд", + "пре (\\d++[.,]?\\d*+) секунди" ], "\\1 week ago": [ - "пре (\\d+[.,]?\\d*) недеља", - "пре (\\d+[.,]?\\d*) недељу" + "прије (\\d++[.,]?\\d*+) седм", + "прије (\\d++[.,]?\\d*+) седмица", + "прије (\\d++[.,]?\\d*+) седмицу", + "прије (\\d++[.,]?\\d*+) сед", + "прије (\\d++[.,]?\\d*+) седмица", + "прије (\\d++[.,]?\\d*+) седмице", + "прије (\\d++[.,]?\\d*+) седмицу", + "пре (\\d++[.,]?\\d*+) недеља", + "пре (\\d++[.,]?\\d*+) недељу" ], "\\1 year ago": [ - "пре (\\d+[.,]?\\d*) година", - "пре (\\d+[.,]?\\d*) годину" + "прије (\\d++[.,]?\\d*+) година", + "прије (\\d++[.,]?\\d*+) годину", + "прије (\\d++[.,]?\\d*+) г", + "прије (\\d++[.,]?\\d*+) год", + "прије (\\d++[.,]?\\d*+) година", + "прије (\\d++[.,]?\\d*+) годину", + "пре (\\d++[.,]?\\d*+) година", + "пре (\\d++[.,]?\\d*+) годину" ], "in \\1 day": [ - "за (\\d+[.,]?\\d*) дан", - "за (\\d+[.,]?\\d*) дана" + "за (\\d++[.,]?\\d*+) дан", + "за (\\d++[.,]?\\d*+) дана" ], "in \\1 hour": [ - "за (\\d+[.,]?\\d*) сат", - "за (\\d+[.,]?\\d*) сати" + "за (\\d++[.,]?\\d*+) сат", + "за (\\d++[.,]?\\d*+) сати" ], "in \\1 minute": [ - "за (\\d+[.,]?\\d*) минут", - "за (\\d+[.,]?\\d*) минута" + "за (\\d++[.,]?\\d*+) минут", + "за (\\d++[.,]?\\d*+) минута", + "за (\\d++[.,]?\\d*+) мин", + "за (\\d++[.,]?\\d*+) минута", + "за (\\d++[.,]?\\d*+) минуту" ], "in \\1 month": [ - "за (\\d+[.,]?\\d*) месец", - "за (\\d+[.,]?\\d*) месеци" + "за (\\d++[.,]?\\d*+) мјес", + "за (\\d++[.,]?\\d*+) мјесец", + "за (\\d++[.,]?\\d*+) мјесеци", + "за (\\d++[.,]?\\d*+) мј", + "за (\\d++[.,]?\\d*+) мјесец", + "за (\\d++[.,]?\\d*+) мјесеца", + "за (\\d++[.,]?\\d*+) мјесеци", + "за (\\d++[.,]?\\d*+) месец", + "за (\\d++[.,]?\\d*+) месеци" ], "in \\1 second": [ - "за (\\d+[.,]?\\d*) секунд", - "за (\\d+[.,]?\\d*) секунди" + "за (\\d++[.,]?\\d*+) сек", + "за (\\d++[.,]?\\d*+) секунд", + "за (\\d++[.,]?\\d*+) секунди", + "за (\\d++[.,]?\\d*+) сек", + "за (\\d++[.,]?\\d*+) секунда", + "за (\\d++[.,]?\\d*+) секунду" ], "in \\1 week": [ - "за (\\d+[.,]?\\d*) недеља", - "за (\\d+[.,]?\\d*) недељу" + "за (\\d++[.,]?\\d*+) седм", + "за (\\d++[.,]?\\d*+) седмица", + "за (\\d++[.,]?\\d*+) седмицу", + "за (\\d++[.,]?\\d*+) сед", + "за (\\d++[.,]?\\d*+) седмица", + "за (\\d++[.,]?\\d*+) седмицу", + "за (\\d++[.,]?\\d*+) седмице", + "за (\\d++[.,]?\\d*+) недеља", + "за (\\d++[.,]?\\d*+) недељу" ], "in \\1 year": [ - "за (\\d+[.,]?\\d*) година", - "за (\\d+[.,]?\\d*) годину" + "за (\\d++[.,]?\\d*+) година", + "за (\\d++[.,]?\\d*+) годину", + "за (\\d++[.,]?\\d*+) г", + "за (\\d++[.,]?\\d*+) год" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/bs-Latn.py b/dateparser/data/date_translation_data/bs-Latn.py index b0cbe0c99..8ffbf8705 100644 --- a/dateparser/data/date_translation_data/bs-Latn.py +++ b/dateparser/data/date_translation_data/bs-Latn.py @@ -29,6 +29,8 @@ "juli" ], "august": [ + "aug", + "august", "avg", "avgust" ], @@ -77,9 +79,11 @@ "nedjelja" ], "am": [ + "am", "prijepodne" ], "pm": [ + "pm", "popodne" ], "year": [ @@ -100,7 +104,8 @@ ], "hour": [ "h", - "sat" + "sat", + "sati" ], "minute": [ "min", @@ -160,74 +165,74 @@ }, "relative-type-regex": { "\\1 day ago": [ - "prije (\\d+[.,]?\\d*) d", - "prije (\\d+[.,]?\\d*) dan", - "prije (\\d+[.,]?\\d*) dana" + "prije (\\d++[.,]?\\d*+) d", + "prije (\\d++[.,]?\\d*+) dan", + "prije (\\d++[.,]?\\d*+) dana" ], "\\1 hour ago": [ - "prije (\\d+[.,]?\\d*) sat", - "prije (\\d+[.,]?\\d*) sati" + "prije (\\d++[.,]?\\d*+) sat", + "prije (\\d++[.,]?\\d*+) sati" ], "\\1 minute ago": [ - "prije (\\d+[.,]?\\d*) min", - "prije (\\d+[.,]?\\d*) minuta", - "prije (\\d+[.,]?\\d*) minutu" + "prije (\\d++[.,]?\\d*+) min", + "prije (\\d++[.,]?\\d*+) minuta", + "prije (\\d++[.,]?\\d*+) minutu" ], "\\1 month ago": [ - "prije (\\d+[.,]?\\d*) mj", - "prije (\\d+[.,]?\\d*) mjesec", - "prije (\\d+[.,]?\\d*) mjeseci" + "prije (\\d++[.,]?\\d*+) mj", + "prije (\\d++[.,]?\\d*+) mjesec", + "prije (\\d++[.,]?\\d*+) mjeseci" ], "\\1 second ago": [ - "prije (\\d+[.,]?\\d*) sek", - "prije (\\d+[.,]?\\d*) sekundi", - "prije (\\d+[.,]?\\d*) sekundu" + "prije (\\d++[.,]?\\d*+) sek", + "prije (\\d++[.,]?\\d*+) sekundi", + "prije (\\d++[.,]?\\d*+) sekundu" ], "\\1 week ago": [ - "prije (\\d+[.,]?\\d*) sed", - "prije (\\d+[.,]?\\d*) sedmica", - "prije (\\d+[.,]?\\d*) sedmicu" + "prije (\\d++[.,]?\\d*+) sed", + "prije (\\d++[.,]?\\d*+) sedmica", + "prije (\\d++[.,]?\\d*+) sedmicu" ], "\\1 year ago": [ - "prije (\\d+[.,]?\\d*) g", - "prije (\\d+[.,]?\\d*) god", - "prije (\\d+[.,]?\\d*) godina", - "prije (\\d+[.,]?\\d*) godinu" + "prije (\\d++[.,]?\\d*+) g", + "prije (\\d++[.,]?\\d*+) god", + "prije (\\d++[.,]?\\d*+) godina", + "prije (\\d++[.,]?\\d*+) godinu" ], "in \\1 day": [ - "za (\\d+[.,]?\\d*) d", - "za (\\d+[.,]?\\d*) dan", - "za (\\d+[.,]?\\d*) dana" + "za (\\d++[.,]?\\d*+) d", + "za (\\d++[.,]?\\d*+) dan", + "za (\\d++[.,]?\\d*+) dana" ], "in \\1 hour": [ - "za (\\d+[.,]?\\d*) sat", - "za (\\d+[.,]?\\d*) sati" + "za (\\d++[.,]?\\d*+) sat", + "za (\\d++[.,]?\\d*+) sati" ], "in \\1 minute": [ - "za (\\d+[.,]?\\d*) min", - "za (\\d+[.,]?\\d*) minuta", - "za (\\d+[.,]?\\d*) minutu" + "za (\\d++[.,]?\\d*+) min", + "za (\\d++[.,]?\\d*+) minuta", + "za (\\d++[.,]?\\d*+) minutu" ], "in \\1 month": [ - "za (\\d+[.,]?\\d*) mj", - "za (\\d+[.,]?\\d*) mjesec", - "za (\\d+[.,]?\\d*) mjeseci" + "za (\\d++[.,]?\\d*+) mj", + "za (\\d++[.,]?\\d*+) mjesec", + "za (\\d++[.,]?\\d*+) mjeseci" ], "in \\1 second": [ - "za (\\d+[.,]?\\d*) sek", - "za (\\d+[.,]?\\d*) sekundi", - "za (\\d+[.,]?\\d*) sekundu" + "za (\\d++[.,]?\\d*+) sek", + "za (\\d++[.,]?\\d*+) sekundi", + "za (\\d++[.,]?\\d*+) sekundu" ], "in \\1 week": [ - "za (\\d+[.,]?\\d*) sed", - "za (\\d+[.,]?\\d*) sedmica", - "za (\\d+[.,]?\\d*) sedmicu" + "za (\\d++[.,]?\\d*+) sed", + "za (\\d++[.,]?\\d*+) sedmica", + "za (\\d++[.,]?\\d*+) sedmicu" ], "in \\1 year": [ - "za (\\d+[.,]?\\d*) g", - "za (\\d+[.,]?\\d*) god", - "za (\\d+[.,]?\\d*) godina", - "za (\\d+[.,]?\\d*) godinu" + "za (\\d++[.,]?\\d*+) g", + "za (\\d++[.,]?\\d*+) god", + "za (\\d++[.,]?\\d*+) godina", + "za (\\d++[.,]?\\d*+) godinu" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/bs.py b/dateparser/data/date_translation_data/bs.py index 7c0ba09a7..805b60d17 100644 --- a/dateparser/data/date_translation_data/bs.py +++ b/dateparser/data/date_translation_data/bs.py @@ -29,6 +29,8 @@ "juli" ], "august": [ + "aug", + "august", "avg", "avgust" ], @@ -77,9 +79,11 @@ "nedjelja" ], "am": [ + "am", "prijepodne" ], "pm": [ + "pm", "popodne" ], "year": [ @@ -100,7 +104,8 @@ ], "hour": [ "h", - "sat" + "sat", + "sati" ], "minute": [ "min", @@ -160,74 +165,74 @@ }, "relative-type-regex": { "\\1 day ago": [ - "prije (\\d+[.,]?\\d*) d", - "prije (\\d+[.,]?\\d*) dan", - "prije (\\d+[.,]?\\d*) dana" + "prije (\\d++[.,]?\\d*+) d", + "prije (\\d++[.,]?\\d*+) dan", + "prije (\\d++[.,]?\\d*+) dana" ], "\\1 hour ago": [ - "prije (\\d+[.,]?\\d*) sat", - "prije (\\d+[.,]?\\d*) sati" + "prije (\\d++[.,]?\\d*+) sat", + "prije (\\d++[.,]?\\d*+) sati" ], "\\1 minute ago": [ - "prije (\\d+[.,]?\\d*) min", - "prije (\\d+[.,]?\\d*) minuta", - "prije (\\d+[.,]?\\d*) minutu" + "prije (\\d++[.,]?\\d*+) min", + "prije (\\d++[.,]?\\d*+) minuta", + "prije (\\d++[.,]?\\d*+) minutu" ], "\\1 month ago": [ - "prije (\\d+[.,]?\\d*) mj", - "prije (\\d+[.,]?\\d*) mjesec", - "prije (\\d+[.,]?\\d*) mjeseci" + "prije (\\d++[.,]?\\d*+) mj", + "prije (\\d++[.,]?\\d*+) mjesec", + "prije (\\d++[.,]?\\d*+) mjeseci" ], "\\1 second ago": [ - "prije (\\d+[.,]?\\d*) sek", - "prije (\\d+[.,]?\\d*) sekundi", - "prije (\\d+[.,]?\\d*) sekundu" + "prije (\\d++[.,]?\\d*+) sek", + "prije (\\d++[.,]?\\d*+) sekundi", + "prije (\\d++[.,]?\\d*+) sekundu" ], "\\1 week ago": [ - "prije (\\d+[.,]?\\d*) sed", - "prije (\\d+[.,]?\\d*) sedmica", - "prije (\\d+[.,]?\\d*) sedmicu" + "prije (\\d++[.,]?\\d*+) sed", + "prije (\\d++[.,]?\\d*+) sedmica", + "prije (\\d++[.,]?\\d*+) sedmicu" ], "\\1 year ago": [ - "prije (\\d+[.,]?\\d*) g", - "prije (\\d+[.,]?\\d*) god", - "prije (\\d+[.,]?\\d*) godina", - "prije (\\d+[.,]?\\d*) godinu" + "prije (\\d++[.,]?\\d*+) g", + "prije (\\d++[.,]?\\d*+) god", + "prije (\\d++[.,]?\\d*+) godina", + "prije (\\d++[.,]?\\d*+) godinu" ], "in \\1 day": [ - "za (\\d+[.,]?\\d*) d", - "za (\\d+[.,]?\\d*) dan", - "za (\\d+[.,]?\\d*) dana" + "za (\\d++[.,]?\\d*+) d", + "za (\\d++[.,]?\\d*+) dan", + "za (\\d++[.,]?\\d*+) dana" ], "in \\1 hour": [ - "za (\\d+[.,]?\\d*) sat", - "za (\\d+[.,]?\\d*) sati" + "za (\\d++[.,]?\\d*+) sat", + "za (\\d++[.,]?\\d*+) sati" ], "in \\1 minute": [ - "za (\\d+[.,]?\\d*) min", - "za (\\d+[.,]?\\d*) minuta", - "za (\\d+[.,]?\\d*) minutu" + "za (\\d++[.,]?\\d*+) min", + "za (\\d++[.,]?\\d*+) minuta", + "za (\\d++[.,]?\\d*+) minutu" ], "in \\1 month": [ - "za (\\d+[.,]?\\d*) mj", - "za (\\d+[.,]?\\d*) mjesec", - "za (\\d+[.,]?\\d*) mjeseci" + "za (\\d++[.,]?\\d*+) mj", + "za (\\d++[.,]?\\d*+) mjesec", + "za (\\d++[.,]?\\d*+) mjeseci" ], "in \\1 second": [ - "za (\\d+[.,]?\\d*) sek", - "za (\\d+[.,]?\\d*) sekundi", - "za (\\d+[.,]?\\d*) sekundu" + "za (\\d++[.,]?\\d*+) sek", + "za (\\d++[.,]?\\d*+) sekundi", + "za (\\d++[.,]?\\d*+) sekundu" ], "in \\1 week": [ - "za (\\d+[.,]?\\d*) sed", - "za (\\d+[.,]?\\d*) sedmica", - "za (\\d+[.,]?\\d*) sedmicu" + "za (\\d++[.,]?\\d*+) sed", + "za (\\d++[.,]?\\d*+) sedmica", + "za (\\d++[.,]?\\d*+) sedmicu" ], "in \\1 year": [ - "za (\\d+[.,]?\\d*) g", - "za (\\d+[.,]?\\d*) god", - "za (\\d+[.,]?\\d*) godina", - "za (\\d+[.,]?\\d*) godinu" + "za (\\d++[.,]?\\d*+) g", + "za (\\d++[.,]?\\d*+) god", + "za (\\d++[.,]?\\d*+) godina", + "za (\\d++[.,]?\\d*+) godinu" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/ca.py b/dateparser/data/date_translation_data/ca.py index 4d0a2f2cd..8b60dcf78 100644 --- a/dateparser/data/date_translation_data/ca.py +++ b/dateparser/data/date_translation_data/ca.py @@ -116,7 +116,8 @@ ], "hour": [ "h", - "hora" + "hora", + "hores" ], "minute": [ "min", @@ -175,10 +176,10 @@ "in 1 week": [ "la setm que ve", "la setmana que ve", - "setm vinent", "la setmana vinent", "la pròxima setmana", - "la propera setmana" + "la propera setmana", + "setm vinent" ], "in 1 year": [ "l'any que ve" @@ -201,69 +202,69 @@ }, "relative-type-regex": { "\\1 day ago": [ - "fa (\\d+[.,]?\\d*) dia", - "fa (\\d+[.,]?\\d*) dies" + "fa (\\d++[.,]?\\d*+) dia", + "fa (\\d++[.,]?\\d*+) dies" ], "\\1 hour ago": [ - "fa (\\d+[.,]?\\d*) h", - "fa (\\d+[.,]?\\d*) hora", - "fa (\\d+[.,]?\\d*) hores" + "fa (\\d++[.,]?\\d*+) h", + "fa (\\d++[.,]?\\d*+) hora", + "fa (\\d++[.,]?\\d*+) hores" ], "\\1 minute ago": [ - "fa (\\d+[.,]?\\d*) min", - "fa (\\d+[.,]?\\d*) minut", - "fa (\\d+[.,]?\\d*) minuts" + "fa (\\d++[.,]?\\d*+) min", + "fa (\\d++[.,]?\\d*+) minut", + "fa (\\d++[.,]?\\d*+) minuts" ], "\\1 month ago": [ - "fa (\\d+[.,]?\\d*) mes", - "fa (\\d+[.,]?\\d*) mesos" + "fa (\\d++[.,]?\\d*+) mes", + "fa (\\d++[.,]?\\d*+) mesos" ], "\\1 second ago": [ - "fa (\\d+[.,]?\\d*) s", - "fa (\\d+[.,]?\\d*) segon", - "fa (\\d+[.,]?\\d*) segons" + "fa (\\d++[.,]?\\d*+) s", + "fa (\\d++[.,]?\\d*+) segon", + "fa (\\d++[.,]?\\d*+) segons" ], "\\1 week ago": [ - "fa (\\d+[.,]?\\d*) setm", - "fa (\\d+[.,]?\\d*) setmana", - "fa (\\d+[.,]?\\d*) setmanes" + "fa (\\d++[.,]?\\d*+) setm", + "fa (\\d++[.,]?\\d*+) setmana", + "fa (\\d++[.,]?\\d*+) setmanes" ], "\\1 year ago": [ - "fa (\\d+[.,]?\\d*) any", - "fa (\\d+[.,]?\\d*) anys" + "fa (\\d++[.,]?\\d*+) any", + "fa (\\d++[.,]?\\d*+) anys" ], "in \\1 day": [ - "d'aquí a (\\d+[.,]?\\d*) dia", - "d'aquí a (\\d+[.,]?\\d*) dies" + "d'aquí a (\\d++[.,]?\\d*+) dia", + "d'aquí a (\\d++[.,]?\\d*+) dies" ], "in \\1 hour": [ - "d'aquí a (\\d+[.,]?\\d*) h", - "d'aquí a (\\d+[.,]?\\d*) hora", - "d'aquí a (\\d+[.,]?\\d*) hores", - "d‘aquí a (\\d+[.,]?\\d*) h" + "d'aquí a (\\d++[.,]?\\d*+) h", + "d'aquí a (\\d++[.,]?\\d*+) hora", + "d'aquí a (\\d++[.,]?\\d*+) hores", + "d‘aquí a (\\d++[.,]?\\d*+) h" ], "in \\1 minute": [ - "d'aquí a (\\d+[.,]?\\d*) min", - "d'aquí a (\\d+[.,]?\\d*) minut", - "d'aquí a (\\d+[.,]?\\d*) minuts" + "d'aquí a (\\d++[.,]?\\d*+) min", + "d'aquí a (\\d++[.,]?\\d*+) minut", + "d'aquí a (\\d++[.,]?\\d*+) minuts" ], "in \\1 month": [ - "d'aquí a (\\d+[.,]?\\d*) mes", - "d'aquí a (\\d+[.,]?\\d*) mesos" + "d'aquí a (\\d++[.,]?\\d*+) mes", + "d'aquí a (\\d++[.,]?\\d*+) mesos" ], "in \\1 second": [ - "d'aquí a (\\d+[.,]?\\d*) s", - "d'aquí a (\\d+[.,]?\\d*) segon", - "d'aquí a (\\d+[.,]?\\d*) segons" + "d'aquí a (\\d++[.,]?\\d*+) s", + "d'aquí a (\\d++[.,]?\\d*+) segon", + "d'aquí a (\\d++[.,]?\\d*+) segons" ], "in \\1 week": [ - "d'aquí a (\\d+[.,]?\\d*) setm", - "d'aquí a (\\d+[.,]?\\d*) setmana", - "d'aquí a (\\d+[.,]?\\d*) setmanes" + "d'aquí a (\\d++[.,]?\\d*+) setm", + "d'aquí a (\\d++[.,]?\\d*+) setmana", + "d'aquí a (\\d++[.,]?\\d*+) setmanes" ], "in \\1 year": [ - "d'aquí a (\\d+[.,]?\\d*) any", - "d'aquí a (\\d+[.,]?\\d*) anys" + "d'aquí a (\\d++[.,]?\\d*+) any", + "d'aquí a (\\d++[.,]?\\d*+) anys" ] }, "locale_specific": { diff --git a/dateparser/data/date_translation_data/ce.py b/dateparser/data/date_translation_data/ce.py index 494d945cd..d07bb0ee0 100644 --- a/dateparser/data/date_translation_data/ce.py +++ b/dateparser/data/date_translation_data/ce.py @@ -49,24 +49,38 @@ "декабрь" ], "monday": [ + "ор", + "оршот", "оршотан де" ], "tuesday": [ + "ши", + "шинара", "шинарин де" ], "wednesday": [ + "кха", + "кхаара", "кхаарин де" ], "thursday": [ + "еа", + "еара", "еарин де" ], "friday": [ + "пӏе", + "пӏераска", "пӏераскан де" ], "saturday": [ + "шуо", + "шуот", "шот де" ], "sunday": [ + "кӏи", + "кӏира", "кӏиранан де" ], "am": [ @@ -92,7 +106,8 @@ ], "hour": [ "сахь", - "сахьт" + "сахьт", + "сахьташ" ], "minute": [ "мин", @@ -107,15 +122,18 @@ "тахана" ], "0 hour ago": [ + "хӏокху сахьтехь", "this hour" ], "0 minute ago": [ + "хӏокху минотехь", "this minute" ], "0 month ago": [ "карарчу баттахь" ], "0 second ago": [ + "хӏинца", "now" ], "0 week ago": [ @@ -151,60 +169,60 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) д хьалха", - "(\\d+[.,]?\\d*) де хьалха" + "(\\d++[.,]?\\d*+) д хьалха", + "(\\d++[.,]?\\d*+) де хьалха" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) сахь хьалха", - "(\\d+[.,]?\\d*) сахьт хьалха" + "(\\d++[.,]?\\d*+) сахь хьалха", + "(\\d++[.,]?\\d*+) сахьт хьалха" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) мин хьалха", - "(\\d+[.,]?\\d*) минот хьалха" + "(\\d++[.,]?\\d*+) мин хьалха", + "(\\d++[.,]?\\d*+) минот хьалха" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) б хьалха", - "(\\d+[.,]?\\d*) бутт хьалха" + "(\\d++[.,]?\\d*+) б хьалха", + "(\\d++[.,]?\\d*+) бутт хьалха" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) сек хьалха", - "(\\d+[.,]?\\d*) секунд хьалха" + "(\\d++[.,]?\\d*+) сек хьалха", + "(\\d++[.,]?\\d*+) секунд хьалха" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) кӏир хьалха", - "(\\d+[.,]?\\d*) кӏира хьалха" + "(\\d++[.,]?\\d*+) кӏир хьалха", + "(\\d++[.,]?\\d*+) кӏира хьалха" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) ш хьалха", - "(\\d+[.,]?\\d*) шо хьалха" + "(\\d++[.,]?\\d*+) ш хьалха", + "(\\d++[.,]?\\d*+) шо хьалха" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) д даьлча", - "(\\d+[.,]?\\d*) де даьлча" + "(\\d++[.,]?\\d*+) д даьлча", + "(\\d++[.,]?\\d*+) де даьлча" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) сахь даьлча", - "(\\d+[.,]?\\d*) сахьт даьлча" + "(\\d++[.,]?\\d*+) сахь даьлча", + "(\\d++[.,]?\\d*+) сахьт даьлча" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) мин яьлча", - "(\\d+[.,]?\\d*) минот яьлча" + "(\\d++[.,]?\\d*+) мин яьлча", + "(\\d++[.,]?\\d*+) минот яьлча" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) б баьлча", - "(\\d+[.,]?\\d*) бутт баьлча" + "(\\d++[.,]?\\d*+) б баьлча", + "(\\d++[.,]?\\d*+) бутт баьлча" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) сек яьлча", - "(\\d+[.,]?\\d*) секунд яьлча" + "(\\d++[.,]?\\d*+) сек яьлча", + "(\\d++[.,]?\\d*+) секунд яьлча" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) кӏир даьлча", - "(\\d+[.,]?\\d*) кӏира даьлча" + "(\\d++[.,]?\\d*+) кӏир даьлча", + "(\\d++[.,]?\\d*+) кӏира даьлча" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) ш даьлча", - "(\\d+[.,]?\\d*) шо даьлча" + "(\\d++[.,]?\\d*+) ш даьлча", + "(\\d++[.,]?\\d*+) шо даьлча" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/cgg.py b/dateparser/data/date_translation_data/cgg.py index 494a6e8d1..2dfd7ffe6 100644 --- a/dateparser/data/date_translation_data/cgg.py +++ b/dateparser/data/date_translation_data/cgg.py @@ -96,6 +96,7 @@ "eizooba" ], "hour": [ + "hr", "shaaha" ], "minute": [ diff --git a/dateparser/data/date_translation_data/chr.py b/dateparser/data/date_translation_data/chr.py index baf375fb6..587eee9ab 100644 --- a/dateparser/data/date_translation_data/chr.py +++ b/dateparser/data/date_translation_data/chr.py @@ -81,6 +81,7 @@ "ꮜꮎꮄ" ], "pm": [ + "ꮢꭿᏹꭲ", "ꮢꭿᏹꭲꮧꮲ" ], "year": [ @@ -99,6 +100,7 @@ "ꭲꭶ" ], "hour": [ + "ꭲᏻꮯꮆꮣ", "ꮡꮯ", "ꮡꮯꮆꮣ" ], @@ -107,6 +109,7 @@ "ꭲꮿꮤꮼꮝꮤꮕ" ], "second": [ + "ꭰꮞ", "ꭰꮞꮲ" ], "relative-type": { @@ -120,6 +123,7 @@ "ꭿꭰ ꭲꮿꮤꮼꮝꮤꮕ" ], "0 month ago": [ + "ꭿꭰ ꭷꮈ", "ꭿꭰ ꭷꮈꭲ" ], "0 second ago": [ @@ -135,6 +139,7 @@ "ꮢꭿ" ], "1 month ago": [ + "ꭷꮈ ꮵꭸꮢ", "ꭷꮈꭲ ꮵꭸꮢ" ], "1 week ago": [ @@ -147,6 +152,8 @@ "ꮜꮎꮄꭲ" ], "in 1 month": [ + "ꭿꭰ ꭷꮈ", + "ꮤꮅꮑ ꭷꮈ", "ꮤꮅꮑ ꭷꮈꭲ" ], "in 1 week": [ @@ -158,68 +165,80 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) ꭲꭶ ꮵꭸꮢ", - "(\\d+[.,]?\\d*) ꭿꮈꮝꭹ ꮷꮢꭿꮫ ꮵꭸꮢ" + "(\\d++[.,]?\\d*+) ꭲꭶ ꮵꭸꮢ", + "(\\d++[.,]?\\d*+) ꭿꮈꮝꭹ ꮷꮢꭿꮫ ꮵꭸꮢ" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) ꭲᏻꮯꮆꮣ ꮵꭸꮢ", - "(\\d+[.,]?\\d*) ꮡꮯꮆꮣ ꮵꭸꮢ", - "ꮎꮏ (\\d+[.,]?\\d*) ꮡꮯ ꮵꭸꮢ" + "(\\d++[.,]?\\d*+) ꭲᏻꮯꮆꮣ ꮵꭸꮢ", + "(\\d++[.,]?\\d*+) ꮡꮯ ꮵꭸꮢ", + "(\\d++[.,]?\\d*+) ꮡꮯꮆꮣ ꮵꭸꮢ", + "ꮎꮏ (\\d++[.,]?\\d*+) ꮡꮯ ꮵꭸꮢ" ], "\\1 minute ago": [ - "ꮎꮏ (\\d+[.,]?\\d*) ꭲꮿꮤ ꮵꭸꮢ", - "ꮎꮏ (\\d+[.,]?\\d*) ꭲꮿꮤꮼꮝꮤꮕ ꮵꭸꮢ" + "(\\d++[.,]?\\d*+) ꭲꮿꮤ ꮵꭸꮢ", + "(\\d++[.,]?\\d*+) ꭲꮿꮤꮼꮝꮤꮕ ꮵꭸꮢ", + "ꮎꮏ (\\d++[.,]?\\d*+) ꭲꮿꮤ ꮵꭸꮢ", + "ꮎꮏ (\\d++[.,]?\\d*+) ꭲꮿꮤꮼꮝꮤꮕ ꮵꭸꮢ" ], "\\1 month ago": [ - "ꮎꮏ (\\d+[.,]?\\d*) ꭷꮈ ꮵꭸꮢ", - "ꮎꮏ (\\d+[.,]?\\d*) ꭷꮈꭲ ꮵꭸꮢ", - "ꮎꮏ (\\d+[.,]?\\d*) ꮧꭷꮈꭲ ꮵꭸꮢ" + "(\\d++[.,]?\\d*+) ꭷꮈ ꮵꭸꮢ", + "(\\d++[.,]?\\d*+) ꭷꮈꭲ ꮵꭸꮢ", + "(\\d++[.,]?\\d*+) ꮧꭷꮈꭲ ꮵꭸꮢ", + "ꮎꮏ (\\d++[.,]?\\d*+) ꭷꮈ ꮵꭸꮢ", + "ꮎꮏ (\\d++[.,]?\\d*+) ꭷꮈꭲ ꮵꭸꮢ", + "ꮎꮏ (\\d++[.,]?\\d*+) ꮧꭷꮈꭲ ꮵꭸꮢ" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) ꭰꮞꮲ ꮵꭸꮢ", - "(\\d+[.,]?\\d*) ꮣꮣꮎꮹꮝꭼ ꮵꭸꮢ" + "(\\d++[.,]?\\d*+) ꭰꮞ ꮵꭸꮢ", + "(\\d++[.,]?\\d*+) ꭰꮞꮲ ꮵꭸꮢ", + "(\\d++[.,]?\\d*+) ꮣꮣꮎꮹꮝꭼ ꮵꭸꮢ" ], "\\1 week ago": [ - "ꮎꮏ (\\d+[.,]?\\d*) ꭲᏻꮎꮩꮣꮖꮝꮧ ꮵꭸꮢ", - "ꮎꮏ (\\d+[.,]?\\d*) ꮢꮎ ꮵꭸꮢ", - "ꮎꮏ (\\d+[.,]?\\d*) ꮢꮎꮩꮣꮖꮝꮧ ꮵꭸꮢ" + "(\\d++[.,]?\\d*+) ꭲᏻꮎꮩꮣꮖꮝꮧ ꮵꭸꮢ", + "(\\d++[.,]?\\d*+) ꮢꮎ ꮵꭸꮢ", + "(\\d++[.,]?\\d*+) ꮢꮎꮩꮣꮖꮝꮧ ꮵꭸꮢ", + "ꮎꮏ (\\d++[.,]?\\d*+) ꭲᏻꮎꮩꮣꮖꮝꮧ ꮵꭸꮢ", + "ꮎꮏ (\\d++[.,]?\\d*+) ꮢꮎ ꮵꭸꮢ", + "ꮎꮏ (\\d++[.,]?\\d*+) ꮢꮎꮩꮣꮖꮝꮧ ꮵꭸꮢ" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) ꭲꮷꮥꮨᏼꮜꮧꮢꭲ ꮵꭸꮢ", - "(\\d+[.,]?\\d*) ꭴꮥꮨᏼꮜꮧꮢꭲ ꮵꭸꮢ", - "ꮎꮏ (\\d+[.,]?\\d*) ꭴꮥ ꮵꭸꮢ" + "(\\d++[.,]?\\d*+) ꭲꮷꮥꮨᏼꮜꮧꮢꭲ ꮵꭸꮢ", + "(\\d++[.,]?\\d*+) ꭴꮥ ꮵꭸꮢ", + "(\\d++[.,]?\\d*+) ꭴꮥꮨᏼꮜꮧꮢꭲ ꮵꭸꮢ", + "ꮎꮏ (\\d++[.,]?\\d*+) ꭴꮥ ꮵꭸꮢ" ], "in \\1 day": [ - "ꮎꮏ (\\d+[.,]?\\d*) ꭲꭶ", - "ꮎꮏ (\\d+[.,]?\\d*) ꭿꮈꮝꭹ ꮷꮢꭿꮫ" + "ꮎꮏ (\\d++[.,]?\\d*+) ꭲꭶ", + "ꮎꮏ (\\d++[.,]?\\d*+) ꭿꮈꮝꭹ ꮷꮢꭿꮫ" ], "in \\1 hour": [ - "ꮎꮏ (\\d+[.,]?\\d*) ꭲᏻꮯꮆꮣ", - "ꮎꮏ (\\d+[.,]?\\d*) ꮡꮯ", - "ꮎꮏ (\\d+[.,]?\\d*) ꮡꮯꮆꮣ" + "ꮎꮏ (\\d++[.,]?\\d*+) ꭲᏻꮯꮆꮣ", + "ꮎꮏ (\\d++[.,]?\\d*+) ꮡꮯ", + "ꮎꮏ (\\d++[.,]?\\d*+) ꮡꮯꮆꮣ" ], "in \\1 minute": [ - "ꮎꮏ (\\d+[.,]?\\d*) ꭲꮿꮤ", - "ꮎꮏ (\\d+[.,]?\\d*) ꭲꮿꮤꮼꮝꮤꮕ" + "ꮎꮏ (\\d++[.,]?\\d*+) ꭲꮿꮤ", + "ꮎꮏ (\\d++[.,]?\\d*+) ꭲꮿꮤꮼꮝꮤꮕ" ], "in \\1 month": [ - "ꮎꮏ (\\d+[.,]?\\d*) ꭷꮈ", - "ꮎꮏ (\\d+[.,]?\\d*) ꭷꮈꭲ", - "ꮎꮏ (\\d+[.,]?\\d*) ꮧꭷꮈꭲ" + "ꮎꮏ (\\d++[.,]?\\d*+) ꭷꮈ", + "ꮎꮏ (\\d++[.,]?\\d*+) ꭷꮈꭲ", + "ꮎꮏ (\\d++[.,]?\\d*+) ꮧꭷꮈꭲ" ], "in \\1 second": [ - "ꮎꮏ (\\d+[.,]?\\d*) ꭰꮞꮲ", - "ꮎꮏ (\\d+[.,]?\\d*) ꮣꮣꮎꮹꮝꭼ ꮵꭸꮢ" + "ꮎꮏ (\\d++[.,]?\\d*+) ꭰꮞ", + "ꮎꮏ (\\d++[.,]?\\d*+) ꭰꮞꮲ", + "ꮎꮏ (\\d++[.,]?\\d*+) ꮣꮣꮎꮹꮝꭼ ꮵꭸꮢ" ], "in \\1 week": [ - "ꮎꮏ (\\d+[.,]?\\d*) ꭲᏻꮎꮩꮣꮖꮝꮧ", - "ꮎꮏ (\\d+[.,]?\\d*) ꮢꮎ", - "ꮎꮏ (\\d+[.,]?\\d*) ꮢꮎꮩꮣꮖꮝꮧ" + "ꮎꮏ (\\d++[.,]?\\d*+) ꭲᏻꮎꮩꮣꮖꮝꮧ", + "ꮎꮏ (\\d++[.,]?\\d*+) ꮢꮎ", + "ꮎꮏ (\\d++[.,]?\\d*+) ꮢꮎꮩꮣꮖꮝꮧ" ], "in \\1 year": [ - "ꮎꮏ (\\d+[.,]?\\d*) ꭲꮷꮥꮨᏼꮜꮧꮢꭲ", - "ꮎꮏ (\\d+[.,]?\\d*) ꭴꮥ", - "ꮎꮏ (\\d+[.,]?\\d*) ꭴꮥꮨᏼꮜꮧꮢꭲ" + "ꮎꮏ (\\d++[.,]?\\d*+) ꭲꮷꮥꮨᏼꮜꮧꮢꭲ", + "ꮎꮏ (\\d++[.,]?\\d*+) ꭴꮥ", + "ꮎꮏ (\\d++[.,]?\\d*+) ꭴꮥꮨᏼꮜꮧꮢꭲ" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/ckb.py b/dateparser/data/date_translation_data/ckb.py index 0de4a7c70..f2818fdf4 100644 --- a/dateparser/data/date_translation_data/ckb.py +++ b/dateparser/data/date_translation_data/ckb.py @@ -77,7 +77,8 @@ "day" ], "hour": [ - "hour" + "hour", + "hr" ], "minute": [ "minute" diff --git a/dateparser/data/date_translation_data/cs.py b/dateparser/data/date_translation_data/cs.py index 93a93367b..2fa63b701 100644 --- a/dateparser/data/date_translation_data/cs.py +++ b/dateparser/data/date_translation_data/cs.py @@ -4,46 +4,54 @@ "january": [ "led", "leden", - "ledna" + "ledna", + "lednu" ], "february": [ "úno", "únor", "února", - "únr" + "únr", + "únoru" ], "march": [ "bře", "březen", - "března" + "března", + "březnu" ], "april": [ "dub", "duben", - "dubna" + "dubna", + "dubnu" ], "may": [ "kvě", "květen", - "května" + "května", + "květnu" ], "june": [ "červen", "června", "čvn", - "Čer" + "Čer", + "červnu" ], "july": [ "července", "červenec", "čvc", "Črc", + "červenci", "črv" ], "august": [ "srp", "srpen", - "srpna" + "srpna", + "srpnu" ], "september": [ "zář", @@ -52,7 +60,8 @@ "october": [ "říj", "říjen", - "října" + "října", + "říjnu" ], "november": [ "lis", @@ -62,7 +71,8 @@ "december": [ "pro", "prosince", - "prosinec" + "prosinec", + "prosinci" ], "monday": [ "po", @@ -78,7 +88,8 @@ "st", "středa", "Stř", - "Středu" + "Středu", + "Středy" ], "thursday": [ "čt", @@ -88,13 +99,15 @@ "friday": [ "pá", "pátek", - "Pát" + "Pát", + "Pátku" ], "saturday": [ "so", "sobota", "Sob", - "Sobotu" + "Sobotu", + "Soboty" ], "sunday": [ "ne", @@ -112,14 +125,19 @@ "r", "rok", "roků", - "roky" + "roky", + "let", + "léta", + "lety" ], "month": [ "měs", "měsíc", "měsíců", "měsíce", - "měsícem" + "měsícem", + "měsícemi", + "měsícema" ], "week": [ "týd", @@ -131,32 +149,45 @@ "day": [ "den", "dnů", - "dny" + "dny", + "dnem", + "dní" ], "hour": [ "h", "hodina", + "hodiny", "hodin", "hodiny", "hodinou", "hodinu", - "hodinami" + "hodinami", + "hodinama" ], "minute": [ "min", "minuta", "minut", + "minutu", + "minutou", "minutami", - "minuty" + "minuty", + "minutama" ], "second": [ "s", "sekunda", "sekundy", "sekund", + "sekundu", + "sekundou", + "sekundami", "vteřina", + "vteřinu", + "vteřinou", "vteřin", - "vteřiny" + "vteřiny", + "vteřinami" ], "relative-type": { "0 day ago": [ @@ -169,10 +200,15 @@ "tuto minutu" ], "0 month ago": [ + "tento měs", "tento měsíc" ], "0 second ago": [ - "nyní" + "nyní", + "teď hned", + "teď", + "okamžitě", + "právě teď" ], "0 week ago": [ "tento týd", @@ -185,6 +221,7 @@ "včera" ], "1 month ago": [ + "minulý měs", "minulý měsíc" ], "1 week ago": [ @@ -195,9 +232,12 @@ "minulý rok" ], "in 1 day": [ - "zítra" + "zítra", + "zítřek", + "zítřka" ], "in 1 month": [ + "příští měs", "příští měsíc" ], "in 1 week": [ @@ -209,84 +249,122 @@ ], "2 day ago": [ "předevčírem" + ], + "3 day ago": [ + "předpředevčírem" + ], + "in 2 day": [ + "pozítří" + ], + "in 3 day": [ + "popozítří" ] }, "relative-type-regex": { "\\1 day ago": [ - "před (\\d+[.,]?\\d*) dnem", - "před (\\d+[.,]?\\d*) dny" + "před (\\d++[.,]?\\d*+) dnem", + "před (\\d++[.,]?\\d*+) dny" ], "\\1 hour ago": [ - "před (\\d+[.,]?\\d*) h", - "před (\\d+[.,]?\\d*) hodinami", - "před (\\d+[.,]?\\d*) hodinou" + "před (\\d++[.,]?\\d*+) h", + "před (\\d++[.,]?\\d*+) hodinami", + "před (\\d++[.,]?\\d*+) hodinou" ], "\\1 minute ago": [ - "před (\\d+[.,]?\\d*) min", - "před (\\d+[.,]?\\d*) minutami", - "před (\\d+[.,]?\\d*) minutou" + "před (\\d++[.,]?\\d*+) min", + "před (\\d++[.,]?\\d*+) minutami", + "před (\\d++[.,]?\\d*+) minutou" ], "\\1 month ago": [ - "před (\\d+[.,]?\\d*) měs", - "před (\\d+[.,]?\\d*) měsícem", - "před (\\d+[.,]?\\d*) měsíci" + "před (\\d++[.,]?\\d*+) měs", + "před (\\d++[.,]?\\d*+) měsícem", + "před (\\d++[.,]?\\d*+) měsíci" ], "\\1 second ago": [ - "před (\\d+[.,]?\\d*) s", - "před (\\d+[.,]?\\d*) sekundami", - "před (\\d+[.,]?\\d*) sekundou" + "před (\\d++[.,]?\\d*+) s", + "před (\\d++[.,]?\\d*+) sekundami", + "před (\\d++[.,]?\\d*+) sekundou" ], "\\1 week ago": [ - "před (\\d+[.,]?\\d*) týd", - "před (\\d+[.,]?\\d*) týdnem", - "před (\\d+[.,]?\\d*) týdny" + "před (\\d++[.,]?\\d*+) týd", + "před (\\d++[.,]?\\d*+) týdnem", + "před (\\d++[.,]?\\d*+) týdny" ], "\\1 year ago": [ - "před (\\d+[.,]?\\d*) l", - "před (\\d+[.,]?\\d*) lety", - "před (\\d+[.,]?\\d*) r", - "před (\\d+[.,]?\\d*) rokem" + "před (\\d++[.,]?\\d*+) l", + "před (\\d++[.,]?\\d*+) lety", + "před (\\d++[.,]?\\d*+) r", + "před (\\d++[.,]?\\d*+) rokem" ], "in \\1 day": [ - "za (\\d+[.,]?\\d*) den", - "za (\\d+[.,]?\\d*) dní" + "za (\\d++[.,]?\\d*+) den", + "za (\\d++[.,]?\\d*+) dní" ], "in \\1 hour": [ - "za (\\d+[.,]?\\d*) h", - "za (\\d+[.,]?\\d*) hodin", - "za (\\d+[.,]?\\d*) hodinu" + "za (\\d++[.,]?\\d*+) h", + "za (\\d++[.,]?\\d*+) hodin", + "za (\\d++[.,]?\\d*+) hodinu" ], "in \\1 minute": [ - "za (\\d+[.,]?\\d*) min", - "za (\\d+[.,]?\\d*) minut", - "za (\\d+[.,]?\\d*) minutu" + "za (\\d++[.,]?\\d*+) min", + "za (\\d++[.,]?\\d*+) minut", + "za (\\d++[.,]?\\d*+) minutu" ], "in \\1 month": [ - "za (\\d+[.,]?\\d*) měs", - "za (\\d+[.,]?\\d*) měsíc", - "za (\\d+[.,]?\\d*) měsíců" + "za (\\d++[.,]?\\d*+) měs", + "za (\\d++[.,]?\\d*+) měsíc", + "za (\\d++[.,]?\\d*+) měsíců" ], "in \\1 second": [ - "za (\\d+[.,]?\\d*) s", - "za (\\d+[.,]?\\d*) sekund", - "za (\\d+[.,]?\\d*) sekundu" + "za (\\d++[.,]?\\d*+) s", + "za (\\d++[.,]?\\d*+) sekund", + "za (\\d++[.,]?\\d*+) sekundu" ], "in \\1 week": [ - "za (\\d+[.,]?\\d*) týd", - "za (\\d+[.,]?\\d*) týden", - "za (\\d+[.,]?\\d*) týdnů" + "za (\\d++[.,]?\\d*+) týd", + "za (\\d++[.,]?\\d*+) týden", + "za (\\d++[.,]?\\d*+) týdnů" ], "in \\1 year": [ - "za (\\d+[.,]?\\d*) l", - "za (\\d+[.,]?\\d*) let", - "za (\\d+[.,]?\\d*) r", - "za (\\d+[.,]?\\d*) rok" + "za (\\d++[.,]?\\d*+) l", + "za (\\d++[.,]?\\d*+) let", + "za (\\d++[.,]?\\d*+) r", + "za (\\d++[.,]?\\d*+) rok" + ], + "\\1 decade ago": [ + "před (\\d++[.,]?\\d*+) desetiletími", + "před (\\d++[.,]?\\d*+) dekádami", + "před (\\d++[.,]?\\d*+) dekádou", + "před (\\d++[.,]?\\d*+) desetiletím" + ], + "in \\1 decade": [ + "za (\\d++[.,]?\\d*+) desetiletí", + "za (\\d++[.,]?\\d*+) dekád", + "za (\\d++[.,]?\\d*+) dekády", + "za (\\d++[.,]?\\d*+) dekádu" + ], + "\\1 century ago": [ + "před (\\d++[.,]?\\d*+) staletími", + "před (\\d++[.,]?\\d*+) stoletími", + "před (\\d++[.,]?\\d*+) stoletím" + ], + "in \\1 century": [ + "za (\\d++[.,]?\\d*+) staletí", + "za (\\d++[.,]?\\d*+) století" ] }, "locale_specific": {}, "skip": [ "přibližně", "v", + "ve", + "přibližně", + "asi", + "zhruba", + "cca", + "kolem", + "okolo", + "někdy", " ", "'", ",", @@ -305,12 +383,299 @@ "před" ], "in": [ - "ve", - "v" + "za" ], "simplifications": [ { - "teď": "0 sekunda" + "(o )?půlnoc(i|í)?": "0:00" + }, + { + "ráno": "AM" + }, + { + "dopoledne": "AM" + }, + { + "odpoledne": "PM" + }, + { + "(pod)?večer": "PM" + }, + { + "budoucí(ho)?": "příští" + }, + { + "nadcházející(ho)?": "příští" + }, + { + "tenhle": "tento" + }, + { + "tohle": "tento" + }, + { + "letos": "tento rok" + }, + { + "vloni": "minulý rok" + }, + { + "loni": "minulý rok" + }, + { + "jed(en|na|no|ním|ným|nou|noho|né|ný)": "1" + }, + { + "dv(a|ě|ou|ěma)": "2" + }, + { + "tř(i|ech|em|emi)": "3" + }, + { + "čty(r|ř)(i|ech|em|mi)": "4" + }, + { + "pět(i)?": "5" + }, + { + "šest(i)?": "6" + }, + { + "sed(u)?m(i)?": "7" + }, + { + "osm(i)?": "8" + }, + { + "devět|devíti": "9" + }, + { + "deset(i)?": "10" + }, + { + "jedenáct(i)?": "11" + }, + { + "dvanáct(i)?": "12" + }, + { + "čtrnáct(i)?": "14" + }, + { + "dvacet(i)?": "20" + }, + { + "třicet(i)?": "30" + }, + { + "první(ho|mu|m)?": "1." + }, + { + "druh(ý|á|é|ého|ému|ým|ou|ýho)": "2." + }, + { + "třet(í|ího|ímu|ím)": "3." + }, + { + "čtvrt(ý|á|é|ého|ému|ým|ou|ýho)": "4." + }, + { + "pát(ý|á|é|ého|ému|ým|ou|ýho)": "5." + }, + { + "šest(ý|á|é|ého|ému|ým|ou|ýho)": "6." + }, + { + "sedm(ý|á|é|ého|ému|ým|ou|ýho)": "7." + }, + { + "osm(ý|á|é|ého|ému|ým|ou|ýho)": "8." + }, + { + "devát(ý|á|é|ého|ému|ým|ou|ýho)": "9." + }, + { + "desát(ý|á|é|ého|ému|ým|ou|ýho)": "10." + }, + { + "jedenáct(ý|á|ého|ému|ým|ou|ýho|é)": "11." + }, + { + "dvanáct(ý|á|ého|ému|ým|ou|ýho|é)": "12." + }, + { + "čtrnáct(ý|á|ého|ému|ým|ou|ýho|é)": "14." + }, + { + "dvacát(ý|á|ého|ému|ým|ou|ýho|é)": "20." + }, + { + "třicát(ý|á|ého|ému|ým|ou|ýho|é)": "30." + }, + { + "(?<=(za|před)\\s)hodin(u|ou)\\b": "1 hodinu" + }, + { + "(?<=(za|před)\\s)minut(u|ou)\\b": "1 minutu" + }, + { + "(?<=(za|před)\\s)(?:vteřin(u|ou)|sekund(u|ou))\\b": "1 sekundu" + }, + { + "(?<=(za|před)\\s)týdn(em)\\b": "1 týden" + }, + { + "(?<=(za|před)\\s)měsíc(em)\\b": "1 měsíc" + }, + { + "(?<=(za|před)\\s)rok(em)\\b": "1 rok" + }, + { + "(?<=(za|před)\\s)(?:denem|dnem|den)\\b": "1 den" + }, + { + "(?<=před\\s)týden\\b": "1 týden" + }, + { + "(?<=před\\s)měsíc\\b": "1 měsíc" + }, + { + "(?<=před\\s)rok\\b": "1 rok" + }, + { + "(?<=za\\s)týden\\b": "1 týden" + }, + { + "(?<=za\\s)měsíc\\b": "1 měsíc" + }, + { + "(?<=za\\s)rok\\b": "1 rok" + }, + { + "čtvrt\\s*hodin(y|u)": "15 minut" + }, + { + "čtvrt\\s*hodinou": "15 minutami" + }, + { + "půl\\s*hodin(y|u)": "30 minut" + }, + { + "půl\\s*hodinou": "30 minutami" + }, + { + "tři\\s*čtvrtě\\s*hodin(y|u)": "45 minut" + }, + { + "tři\\s*čtvrtě\\s*hodinou": "45 minutami" + }, + { + "čtvrt na 1\\.?": "12:15" + }, + { + "čtvrt na 2\\.?": "1:15" + }, + { + "čtvrt na 3\\.?": "2:15" + }, + { + "čtvrt na 4\\.?": "3:15" + }, + { + "čtvrt na 5\\.?": "4:15" + }, + { + "čtvrt na 6\\.?": "5:15" + }, + { + "čtvrt na 7\\.?": "6:15" + }, + { + "čtvrt na 8\\.?": "7:15" + }, + { + "čtvrt na 9\\.?": "8:15" + }, + { + "čtvrt na 10\\.?": "9:15" + }, + { + "čtvrt na 11\\.?": "10:15" + }, + { + "čtvrt na 12\\.?": "11:15" + }, + { + "půl 1\\.?": "12:30" + }, + { + "půl 2\\.?": "1:30" + }, + { + "půl 3\\.?": "2:30" + }, + { + "půl 4\\.?": "3:30" + }, + { + "půl 5\\.?": "4:30" + }, + { + "půl 6\\.?": "5:30" + }, + { + "půl 7\\.?": "6:30" + }, + { + "půl 8\\.?": "7:30" + }, + { + "půl 9\\.?": "8:30" + }, + { + "půl 10\\.?": "9:30" + }, + { + "půl 11\\.?": "10:30" + }, + { + "půl 12\\.?": "11:30" + }, + { + "tři\\s*čtvrtě na 1\\.?": "12:45" + }, + { + "tři\\s*čtvrtě na 2\\.?": "1:45" + }, + { + "tři\\s*čtvrtě na 3\\.?": "2:45" + }, + { + "tři\\s*čtvrtě na 4\\.?": "3:45" + }, + { + "tři\\s*čtvrtě na 5\\.?": "4:45" + }, + { + "tři\\s*čtvrtě na 6\\.?": "5:45" + }, + { + "tři\\s*čtvrtě na 7\\.?": "6:45" + }, + { + "tři\\s*čtvrtě na 8\\.?": "7:45" + }, + { + "tři\\s*čtvrtě na 9\\.?": "8:45" + }, + { + "tři\\s*čtvrtě na 10\\.?": "9:45" + }, + { + "tři\\s*čtvrtě na 11\\.?": "10:45" + }, + { + "tři\\s*čtvrtě na 12\\.?": "11:45" } ] } diff --git a/dateparser/data/date_translation_data/cy.py b/dateparser/data/date_translation_data/cy.py index da5e8a8d5..190f2fcec 100644 --- a/dateparser/data/date_translation_data/cy.py +++ b/dateparser/data/date_translation_data/cy.py @@ -78,9 +78,11 @@ "sul" ], "am": [ + "am", "yb" ], "pm": [ + "pm", "yh" ], "year": [ @@ -94,10 +96,12 @@ "wythnos" ], "day": [ + "diwrnod", "dydd" ], "hour": [ - "awr" + "awr", + "oriau" ], "minute": [ "mun", @@ -123,6 +127,7 @@ "nawr" ], "0 week ago": [ + "yr ws hon", "yr wythnos hon" ], "0 year ago": [ @@ -135,6 +140,7 @@ "mis diwethaf" ], "1 week ago": [ + "ws ddiwethaf", "wythnos ddiwethaf" ], "1 year ago": [ @@ -147,56 +153,63 @@ "mis nesaf" ], "in 1 week": [ + "ws nesaf", "wythnos nesaf" ], "in 1 year": [ + "bl nesaf", "blwyddyn nesaf" ] }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) diwrnod yn ôl" + "(\\d++[.,]?\\d*+) diwrnod yn ôl" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) awr yn ôl" + "(\\d++[.,]?\\d*+) awr yn ôl" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) mun yn ôl", - "(\\d+[.,]?\\d*) munud yn ôl" + "(\\d++[.,]?\\d*+) mun yn ôl", + "(\\d++[.,]?\\d*+) munud yn ôl" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) mis yn ôl" + "(\\d++[.,]?\\d*+) mis yn ôl" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) eiliad yn ôl" + "(\\d++[.,]?\\d*+) eil yn ôl", + "(\\d++[.,]?\\d*+) eiliad yn ôl" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) wythnos yn ôl" + "(\\d++[.,]?\\d*+) ws yn ôl", + "(\\d++[.,]?\\d*+) wythnos yn ôl" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) o flynyddoedd yn ôl" + "(\\d++[.,]?\\d*+) bl yn ôl", + "(\\d++[.,]?\\d*+) o flynyddoedd yn ôl" ], "in \\1 day": [ - "ymhen (\\d+[.,]?\\d*) diwrnod" + "ymhen (\\d++[.,]?\\d*+) diwrnod" ], "in \\1 hour": [ - "ymhen (\\d+[.,]?\\d*) awr" + "ymhen (\\d++[.,]?\\d*+) awr" ], "in \\1 minute": [ - "ymhen (\\d+[.,]?\\d*) mun", - "ymhen (\\d+[.,]?\\d*) munud" + "ymhen (\\d++[.,]?\\d*+) mun", + "ymhen (\\d++[.,]?\\d*+) munud" ], "in \\1 month": [ - "ymhen (\\d+[.,]?\\d*) mis" + "ymhen (\\d++[.,]?\\d*+) mis" ], "in \\1 second": [ - "ymhen (\\d+[.,]?\\d*) eiliad" + "ymhen (\\d++[.,]?\\d*+) eil", + "ymhen (\\d++[.,]?\\d*+) eiliad" ], "in \\1 week": [ - "ymhen (\\d+[.,]?\\d*) wythnos" + "ymhen (\\d++[.,]?\\d*+) ws", + "ymhen (\\d++[.,]?\\d*+) wythnos" ], "in \\1 year": [ - "ymhen (\\d+[.,]?\\d*) mlynedd" + "ymhen (\\d++[.,]?\\d*+) mlynedd" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/da.py b/dateparser/data/date_translation_data/da.py index 9350b648a..13e0c68dc 100644 --- a/dateparser/data/date_translation_data/da.py +++ b/dateparser/data/date_translation_data/da.py @@ -53,16 +53,18 @@ "mandag" ], "tuesday": [ - "tir", - "tirsdag" + "tirs", + "tirsdag", + "tir" ], "wednesday": [ "ons", "onsdag" ], "thursday": [ - "tor", - "torsdag" + "tors", + "torsdag", + "tor" ], "friday": [ "fre", @@ -101,6 +103,7 @@ "hour": [ "t", "time", + "timer", "timer" ], "minute": [ @@ -119,9 +122,11 @@ "i dag" ], "0 hour ago": [ + "denne time", "i den kommende time" ], "0 minute ago": [ + "dette minut", "i det kommende minut" ], "0 month ago": [ @@ -166,72 +171,83 @@ }, "relative-type-regex": { "\\1 day ago": [ - "for (\\d+[.,]?\\d*) dag siden", - "for (\\d+[.,]?\\d*) dage siden" + "for (\\d++[.,]?\\d*+) dag siden", + "for (\\d++[.,]?\\d*+) dage siden", + "(\\d++[.,]?\\d*+) dag siden", + "(\\d++[.,]?\\d*+) dage siden" ], "\\1 hour ago": [ - "for (\\d+[.,]?\\d*) time siden", - "for (\\d+[.,]?\\d*) timer siden", - "for (\\d+[.,]?\\d*)\\s*h", - "for (\\d+[.,]?\\d*) timer" + "for (\\d++[.,]?\\d*+) time siden", + "for (\\d++[.,]?\\d*+) timer siden", + "(\\d++[.,]?\\d*+) time siden", + "(\\d++[.,]?\\d*+) timer siden", + "for (\\d++[.,]?\\d*+)\\s*h", + "for (\\d++[.,]?\\d*+) timer" ], "\\1 minute ago": [ - "for (\\d+[.,]?\\d*) min siden", - "for (\\d+[.,]?\\d*) minut siden", - "for (\\d+[.,]?\\d*) minutter siden", - "for (\\d+[.,]?\\d*)\\s*m", - "for (\\d+[.,]?\\d*) minutter" + "for (\\d++[.,]?\\d*+) minut siden", + "for (\\d++[.,]?\\d*+) minutter siden", + "(\\d++[.,]?\\d*+) min siden", + "for (\\d++[.,]?\\d*+)\\s*m", + "for (\\d++[.,]?\\d*+) minutter", + "for (\\d++[.,]?\\d*+) min siden" ], "\\1 month ago": [ - "for (\\d+[.,]?\\d*) md siden", - "for (\\d+[.,]?\\d*) mdr siden", - "for (\\d+[.,]?\\d*) måned siden", - "for (\\d+[.,]?\\d*) måneder siden" + "for (\\d++[.,]?\\d*+) måned siden", + "for (\\d++[.,]?\\d*+) måneder siden", + "(\\d++[.,]?\\d*+) md siden", + "(\\d++[.,]?\\d*+) mdr siden", + "for (\\d++[.,]?\\d*+) md siden", + "for (\\d++[.,]?\\d*+) mdr siden" ], "\\1 second ago": [ - "for (\\d+[.,]?\\d*) sek siden", - "for (\\d+[.,]?\\d*) sekund siden", - "for (\\d+[.,]?\\d*) sekunder siden", - "for (\\d+[.,]?\\d*)\\s*s", - "for (\\d+[.,]?\\d*) sekunder" + "for (\\d++[.,]?\\d*+) sekund siden", + "for (\\d++[.,]?\\d*+) sekunder siden", + "(\\d++[.,]?\\d*+) sek siden", + "for (\\d++[.,]?\\d*+)\\s*s", + "for (\\d++[.,]?\\d*+) sekunder", + "for (\\d++[.,]?\\d*+) sek siden" ], "\\1 week ago": [ - "for (\\d+[.,]?\\d*) uge siden", - "for (\\d+[.,]?\\d*) uger siden" + "for (\\d++[.,]?\\d*+) uge siden", + "for (\\d++[.,]?\\d*+) uger siden", + "(\\d++[.,]?\\d*+) uge siden", + "(\\d++[.,]?\\d*+) uger siden" ], "\\1 year ago": [ - "for (\\d+[.,]?\\d*) år siden" + "for (\\d++[.,]?\\d*+) år siden", + "(\\d++[.,]?\\d*+) år siden" ], "in \\1 day": [ - "om (\\d+[.,]?\\d*) dag", - "om (\\d+[.,]?\\d*) dage" + "om (\\d++[.,]?\\d*+) dag", + "om (\\d++[.,]?\\d*+) dage" ], "in \\1 hour": [ - "om (\\d+[.,]?\\d*) time", - "om (\\d+[.,]?\\d*) timer" + "om (\\d++[.,]?\\d*+) time", + "om (\\d++[.,]?\\d*+) timer" ], "in \\1 minute": [ - "om (\\d+[.,]?\\d*) min", - "om (\\d+[.,]?\\d*) minut", - "om (\\d+[.,]?\\d*) minutter" + "om (\\d++[.,]?\\d*+) min", + "om (\\d++[.,]?\\d*+) minut", + "om (\\d++[.,]?\\d*+) minutter" ], "in \\1 month": [ - "om (\\d+[.,]?\\d*) md", - "om (\\d+[.,]?\\d*) mdr", - "om (\\d+[.,]?\\d*) måned", - "om (\\d+[.,]?\\d*) måneder" + "om (\\d++[.,]?\\d*+) md", + "om (\\d++[.,]?\\d*+) mdr", + "om (\\d++[.,]?\\d*+) måned", + "om (\\d++[.,]?\\d*+) måneder" ], "in \\1 second": [ - "om (\\d+[.,]?\\d*) sek", - "om (\\d+[.,]?\\d*) sekund", - "om (\\d+[.,]?\\d*) sekunder" + "om (\\d++[.,]?\\d*+) sek", + "om (\\d++[.,]?\\d*+) sekund", + "om (\\d++[.,]?\\d*+) sekunder" ], "in \\1 week": [ - "om (\\d+[.,]?\\d*) uge", - "om (\\d+[.,]?\\d*) uger" + "om (\\d++[.,]?\\d*+) uge", + "om (\\d++[.,]?\\d*+) uger" ], "in \\1 year": [ - "om (\\d+[.,]?\\d*) år" + "om (\\d++[.,]?\\d*+) år" ] }, "locale_specific": { @@ -242,6 +258,7 @@ "skip": [ "cirka", "d.", + "den", "kl", "kl.", " ", @@ -272,13 +289,13 @@ "et": "1" }, { - "(\\d+[.,]?\\d*)\\s*hr(s?)": "\\1 time\\2" + "(\\d++[.,]?\\d*+)\\s*hr(s?)": "\\1 time\\2" }, { - "(\\d+[.,]?\\d*)\\s*min(s?)": "\\1 minut\\2" + "(\\d++[.,]?\\d*+)\\s*min(s?)": "\\1 minut\\2" }, { - "(\\d+[.,]?\\d*)\\s*sec(s?)": "\\1 sekund\\2" + "(\\d++[.,]?\\d*+)\\s*sec(s?)": "\\1 sekund\\2" }, { "middag": "12:00" @@ -287,7 +304,7 @@ "midnat": "00:00" }, { - "(\\d+[.,]?\\d*)h(\\d+[.,]?\\d*)m?": "\\1:\\2" + "(\\d++[.,]?\\d*+)h(\\d++[.,]?\\d*+)m?": "\\1:\\2" }, { "mindre end 1 minut siden": "45 seconds" diff --git a/dateparser/data/date_translation_data/dav.py b/dateparser/data/date_translation_data/dav.py index 17b9f90e6..0cc577ad4 100644 --- a/dateparser/data/date_translation_data/dav.py +++ b/dateparser/data/date_translation_data/dav.py @@ -96,6 +96,7 @@ "ituku" ], "hour": [ + "hr", "saa" ], "minute": [ diff --git a/dateparser/data/date_translation_data/de.py b/dateparser/data/date_translation_data/de.py index dcf9a0b11..c1a576b94 100644 --- a/dateparser/data/date_translation_data/de.py +++ b/dateparser/data/date_translation_data/de.py @@ -37,6 +37,7 @@ ], "september": [ "sep", + "sept", "september", "Sept" ], @@ -88,9 +89,11 @@ "Son" ], "am": [ + "am", "vorm" ], "pm": [ + "pm", "nachm" ], "year": [ @@ -118,6 +121,7 @@ "hour": [ "std", "stunde", + "stunden", "Stunden" ], "minute": [ @@ -185,75 +189,75 @@ }, "relative-type-regex": { "\\1 day ago": [ - "vor (\\d+[.,]?\\d*) tag", - "vor (\\d+[.,]?\\d*) tagen" + "vor (\\d++[.,]?\\d*+) tag", + "vor (\\d++[.,]?\\d*+) tagen" ], "\\1 hour ago": [ - "vor (\\d+[.,]?\\d*) std", - "vor (\\d+[.,]?\\d*) stunde", - "vor (\\d+[.,]?\\d*) stunden", - "vor (\\d+[.,]?\\d*)\\s*h" + "vor (\\d++[.,]?\\d*+) std", + "vor (\\d++[.,]?\\d*+) stunde", + "vor (\\d++[.,]?\\d*+) stunden", + "vor (\\d++[.,]?\\d*+)\\s*h" ], "\\1 minute ago": [ - "vor (\\d+[.,]?\\d*) m", - "vor (\\d+[.,]?\\d*) min", - "vor (\\d+[.,]?\\d*) minute", - "vor (\\d+[.,]?\\d*) minuten", - "vor (\\d+[.,]?\\d*)\\s*m" + "vor (\\d++[.,]?\\d*+) m", + "vor (\\d++[.,]?\\d*+) min", + "vor (\\d++[.,]?\\d*+) minute", + "vor (\\d++[.,]?\\d*+) minuten", + "vor (\\d++[.,]?\\d*+)\\s*m" ], "\\1 month ago": [ - "vor (\\d+[.,]?\\d*) monat", - "vor (\\d+[.,]?\\d*) monaten" + "vor (\\d++[.,]?\\d*+) monat", + "vor (\\d++[.,]?\\d*+) monaten" ], "\\1 second ago": [ - "vor (\\d+[.,]?\\d*) s", - "vor (\\d+[.,]?\\d*) sek", - "vor (\\d+[.,]?\\d*) sekunde", - "vor (\\d+[.,]?\\d*) sekunden", - "vor (\\d+[.,]?\\d*)\\s*s" + "vor (\\d++[.,]?\\d*+) s", + "vor (\\d++[.,]?\\d*+) sek", + "vor (\\d++[.,]?\\d*+) sekunde", + "vor (\\d++[.,]?\\d*+) sekunden", + "vor (\\d++[.,]?\\d*+)\\s*s" ], "\\1 week ago": [ - "vor (\\d+[.,]?\\d*) wo", - "vor (\\d+[.,]?\\d*) woche", - "vor (\\d+[.,]?\\d*) wochen" + "vor (\\d++[.,]?\\d*+) wo", + "vor (\\d++[.,]?\\d*+) woche", + "vor (\\d++[.,]?\\d*+) wochen" ], "\\1 year ago": [ - "vor (\\d+[.,]?\\d*) jahr", - "vor (\\d+[.,]?\\d*) jahren" + "vor (\\d++[.,]?\\d*+) jahr", + "vor (\\d++[.,]?\\d*+) jahren" ], "in \\1 day": [ - "in (\\d+[.,]?\\d*) tag", - "in (\\d+[.,]?\\d*) tagen" + "in (\\d++[.,]?\\d*+) tag", + "in (\\d++[.,]?\\d*+) tagen" ], "in \\1 hour": [ - "in (\\d+[.,]?\\d*) std", - "in (\\d+[.,]?\\d*) stunde", - "in (\\d+[.,]?\\d*) stunden" + "in (\\d++[.,]?\\d*+) std", + "in (\\d++[.,]?\\d*+) stunde", + "in (\\d++[.,]?\\d*+) stunden" ], "in \\1 minute": [ - "in (\\d+[.,]?\\d*) m", - "in (\\d+[.,]?\\d*) min", - "in (\\d+[.,]?\\d*) minute", - "in (\\d+[.,]?\\d*) minuten" + "in (\\d++[.,]?\\d*+) m", + "in (\\d++[.,]?\\d*+) min", + "in (\\d++[.,]?\\d*+) minute", + "in (\\d++[.,]?\\d*+) minuten" ], "in \\1 month": [ - "in (\\d+[.,]?\\d*) monat", - "in (\\d+[.,]?\\d*) monaten" + "in (\\d++[.,]?\\d*+) monat", + "in (\\d++[.,]?\\d*+) monaten" ], "in \\1 second": [ - "in (\\d+[.,]?\\d*) s", - "in (\\d+[.,]?\\d*) sek", - "in (\\d+[.,]?\\d*) sekunde", - "in (\\d+[.,]?\\d*) sekunden" + "in (\\d++[.,]?\\d*+) s", + "in (\\d++[.,]?\\d*+) sek", + "in (\\d++[.,]?\\d*+) sekunde", + "in (\\d++[.,]?\\d*+) sekunden" ], "in \\1 week": [ - "in (\\d+[.,]?\\d*) wo", - "in (\\d+[.,]?\\d*) woche", - "in (\\d+[.,]?\\d*) wochen" + "in (\\d++[.,]?\\d*+) wo", + "in (\\d++[.,]?\\d*+) woche", + "in (\\d++[.,]?\\d*+) wochen" ], "in \\1 year": [ - "in (\\d+[.,]?\\d*) jahr", - "in (\\d+[.,]?\\d*) jahren" + "in (\\d++[.,]?\\d*+) jahr", + "in (\\d++[.,]?\\d*+) jahren" ] }, "locale_specific": { diff --git a/dateparser/data/date_translation_data/dje.py b/dateparser/data/date_translation_data/dje.py index d3e90c103..1ee9e9a6e 100644 --- a/dateparser/data/date_translation_data/dje.py +++ b/dateparser/data/date_translation_data/dje.py @@ -94,7 +94,8 @@ "zaari" ], "hour": [ - "guuru" + "guuru", + "hr" ], "minute": [ "miniti" diff --git a/dateparser/data/date_translation_data/dsb.py b/dateparser/data/date_translation_data/dsb.py index 086d4ed96..33de25c4a 100644 --- a/dateparser/data/date_translation_data/dsb.py +++ b/dateparser/data/date_translation_data/dsb.py @@ -89,9 +89,11 @@ "njeźela" ], "am": [ + "dop", "dopołdnja" ], "pm": [ + "wótp", "wótpołdnja" ], "year": [ @@ -113,7 +115,8 @@ "hour": [ "g", "góź", - "góźina" + "góźina", + "góźiny" ], "minute": [ "m", @@ -127,129 +130,155 @@ ], "relative-type": { "0 day ago": [ - "źinsa" + "źins", + "źinsa", + "źis" ], "0 hour ago": [ + "w toś tej góźinje", "this hour" ], "0 minute ago": [ + "w toś tej minuśe", "this minute" ], "0 month ago": [ - "ten mjasec" + "te mjasec", + "ten mjasec", + "tot mjasec" ], "0 second ago": [ - "now" + "něnto" ], "0 week ago": [ - "ten tyźeń" + "te tyźeń", + "ten tyźeń", + "tot tyźeń" ], "0 year ago": [ - "lětosa" + "lět", + "lětosa", + "lěts" ], "1 day ago": [ - "cora" + "cora", + "cr", + "cra" ], "1 month ago": [ + "zajź mjasec", + "zajźony mjasec", "slědny mjasec" ], "1 week ago": [ + "zajź tyźeń", + "zajźony tyźeń", "slědny tyźeń" ], "1 year ago": [ + "ło", + "łon", "łoni" ], "in 1 day": [ + "wit", + "witś", "witśe" ], "in 1 month": [ + "pśid mjasec", + "pśiduc mjasec", "pśiducy mjasec" ], "in 1 week": [ + "pśid tyźeń", + "pśiduc tyźeń", "pśiducy tyźeń" ], "in 1 year": [ + "zno", + "znow", "znowa" ] }, "relative-type-regex": { "\\1 day ago": [ - "pśed (\\d+[.,]?\\d*) d", - "pśed (\\d+[.,]?\\d*) dnj", - "pśed (\\d+[.,]?\\d*) dnjami", - "pśed (\\d+[.,]?\\d*) dnjom" + "pśed (\\d++[.,]?\\d*+) d", + "pśed (\\d++[.,]?\\d*+) dnj", + "pśed (\\d++[.,]?\\d*+) dnjami", + "pśed (\\d++[.,]?\\d*+) dnjom" ], "\\1 hour ago": [ - "pśed (\\d+[.,]?\\d*) g", - "pśed (\\d+[.,]?\\d*) góź", - "pśed (\\d+[.,]?\\d*) góźinami", - "pśed (\\d+[.,]?\\d*) góźinu" + "pśed (\\d++[.,]?\\d*+) g", + "pśed (\\d++[.,]?\\d*+) góź", + "pśed (\\d++[.,]?\\d*+) góźinami", + "pśed (\\d++[.,]?\\d*+) góźinu" ], "\\1 minute ago": [ - "pśed (\\d+[.,]?\\d*) m", - "pśed (\\d+[.,]?\\d*) min", - "pśed (\\d+[.,]?\\d*) minutami", - "pśed (\\d+[.,]?\\d*) minutu" + "pśed (\\d++[.,]?\\d*+) m", + "pśed (\\d++[.,]?\\d*+) min", + "pśed (\\d++[.,]?\\d*+) minutami", + "pśed (\\d++[.,]?\\d*+) minutu" ], "\\1 month ago": [ - "pśed (\\d+[.,]?\\d*) mjas", - "pśed (\\d+[.,]?\\d*) mjasecami", - "pśed (\\d+[.,]?\\d*) mjasecom" + "pśed (\\d++[.,]?\\d*+) mjas", + "pśed (\\d++[.,]?\\d*+) mjasecami", + "pśed (\\d++[.,]?\\d*+) mjasecom" ], "\\1 second ago": [ - "pśed (\\d+[.,]?\\d*) s", - "pśed (\\d+[.,]?\\d*) sek", - "pśed (\\d+[.,]?\\d*) sekundami", - "pśed (\\d+[.,]?\\d*) sekundu" + "pśed (\\d++[.,]?\\d*+) s", + "pśed (\\d++[.,]?\\d*+) sek", + "pśed (\\d++[.,]?\\d*+) sekundami", + "pśed (\\d++[.,]?\\d*+) sekundu" ], "\\1 week ago": [ - "pśed (\\d+[.,]?\\d*) tyź", - "pśed (\\d+[.,]?\\d*) tyźenjami", - "pśed (\\d+[.,]?\\d*) tyźenjom" + "pśed (\\d++[.,]?\\d*+) tyź", + "pśed (\\d++[.,]?\\d*+) tyźenjami", + "pśed (\\d++[.,]?\\d*+) tyźenjom" ], "\\1 year ago": [ - "pśed (\\d+[.,]?\\d*) l", - "pśed (\\d+[.,]?\\d*) lětami", - "pśed (\\d+[.,]?\\d*) lětom" + "pśed (\\d++[.,]?\\d*+) l", + "pśed (\\d++[.,]?\\d*+) lětami", + "pśed (\\d++[.,]?\\d*+) lětom" ], "in \\1 day": [ - "za (\\d+[.,]?\\d*) dnj", - "za (\\d+[.,]?\\d*) dnjow", - "za (\\d+[.,]?\\d*) ź", - "za (\\d+[.,]?\\d*) źeń" + "za (\\d++[.,]?\\d*+) dnj", + "za (\\d++[.,]?\\d*+) dnjow", + "za (\\d++[.,]?\\d*+) ź", + "za (\\d++[.,]?\\d*+) źeń" ], "in \\1 hour": [ - "za (\\d+[.,]?\\d*) g", - "za (\\d+[.,]?\\d*) góź", - "za (\\d+[.,]?\\d*) góźin", - "za (\\d+[.,]?\\d*) góźinu" + "za (\\d++[.,]?\\d*+) g", + "za (\\d++[.,]?\\d*+) góź", + "za (\\d++[.,]?\\d*+) góźin", + "za (\\d++[.,]?\\d*+) góźinu" ], "in \\1 minute": [ - "za (\\d+[.,]?\\d*) m", - "za (\\d+[.,]?\\d*) min", - "za (\\d+[.,]?\\d*) minutow", - "za (\\d+[.,]?\\d*) minutu" + "za (\\d++[.,]?\\d*+) m", + "za (\\d++[.,]?\\d*+) min", + "za (\\d++[.,]?\\d*+) minutow", + "za (\\d++[.,]?\\d*+) minutu" ], "in \\1 month": [ - "za (\\d+[.,]?\\d*) mjas", - "za (\\d+[.,]?\\d*) mjasec", - "za (\\d+[.,]?\\d*) mjasecow" + "za (\\d++[.,]?\\d*+) mjas", + "za (\\d++[.,]?\\d*+) mjasec", + "za (\\d++[.,]?\\d*+) mjasecow" ], "in \\1 second": [ - "za (\\d+[.,]?\\d*) s", - "za (\\d+[.,]?\\d*) sek", - "za (\\d+[.,]?\\d*) sekundow", - "za (\\d+[.,]?\\d*) sekundu" + "za (\\d++[.,]?\\d*+) s", + "za (\\d++[.,]?\\d*+) sek", + "za (\\d++[.,]?\\d*+) sekundow", + "za (\\d++[.,]?\\d*+) sekundu" ], "in \\1 week": [ - "za (\\d+[.,]?\\d*) tyź", - "za (\\d+[.,]?\\d*) tyźenjow", - "za (\\d+[.,]?\\d*) tyźeń" + "za (\\d++[.,]?\\d*+) tyź", + "za (\\d++[.,]?\\d*+) tyźenjow", + "za (\\d++[.,]?\\d*+) tyźeń" ], "in \\1 year": [ - "za (\\d+[.,]?\\d*) l", - "za (\\d+[.,]?\\d*) lět", - "za (\\d+[.,]?\\d*) lěto" + "za (\\d++[.,]?\\d*+) l", + "za (\\d++[.,]?\\d*+) lět", + "za (\\d++[.,]?\\d*+) lěto" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/dua.py b/dateparser/data/date_translation_data/dua.py index 886f5a30a..3e79492f9 100644 --- a/dateparser/data/date_translation_data/dua.py +++ b/dateparser/data/date_translation_data/dua.py @@ -96,6 +96,7 @@ "búnyá" ], "hour": [ + "hr", "ŋgandɛ" ], "minute": [ diff --git a/dateparser/data/date_translation_data/dyo.py b/dateparser/data/date_translation_data/dyo.py index 486d1077b..1e947e76b 100644 --- a/dateparser/data/date_translation_data/dyo.py +++ b/dateparser/data/date_translation_data/dyo.py @@ -95,7 +95,8 @@ "funak" ], "hour": [ - "hour" + "hour", + "hr" ], "minute": [ "minute" diff --git a/dateparser/data/date_translation_data/dz.py b/dateparser/data/date_translation_data/dz.py index d1d9013dd..0d75f6002 100644 --- a/dateparser/data/date_translation_data/dz.py +++ b/dateparser/data/date_translation_data/dz.py @@ -108,6 +108,7 @@ "ཚེས་" ], "hour": [ + "hr", "ཆུ་ཚོད" ], "minute": [ @@ -165,46 +166,46 @@ }, "relative-type-regex": { "\\1 day ago": [ - "ཉིནམ་ (\\d+[.,]?\\d*) ཧེ་མ་" + "ཉིནམ་ (\\d++[.,]?\\d*+) ཧེ་མ་" ], "\\1 hour ago": [ - "ཆུ་ཚོད་ (\\d+[.,]?\\d*) ཧེ་མ་" + "ཆུ་ཚོད་ (\\d++[.,]?\\d*+) ཧེ་མ་" ], "\\1 minute ago": [ - "སྐར་མ་ (\\d+[.,]?\\d*) ཧེ་མ་" + "སྐར་མ་ (\\d++[.,]?\\d*+) ཧེ་མ་" ], "\\1 month ago": [ - "ཟླཝ་ (\\d+[.,]?\\d*) ཧེ་མ་" + "ཟླཝ་ (\\d++[.,]?\\d*+) ཧེ་མ་" ], "\\1 second ago": [ - "སྐར་ཆ་ (\\d+[.,]?\\d*) ཧེ་མ་" + "སྐར་ཆ་ (\\d++[.,]?\\d*+) ཧེ་མ་" ], "\\1 week ago": [ - "བངུན་ཕྲག་ (\\d+[.,]?\\d*) ཧེ་མ་" + "བངུན་ཕྲག་ (\\d++[.,]?\\d*+) ཧེ་མ་" ], "\\1 year ago": [ - "ལོ་འཁོར་ (\\d+[.,]?\\d*) ཧེ་མ་" + "ལོ་འཁོར་ (\\d++[.,]?\\d*+) ཧེ་མ་" ], "in \\1 day": [ - "ཉིནམ་ (\\d+[.,]?\\d*) ནང་" + "ཉིནམ་ (\\d++[.,]?\\d*+) ནང་" ], "in \\1 hour": [ - "ཆུ་ཚོད་ (\\d+[.,]?\\d*) ནང་" + "ཆུ་ཚོད་ (\\d++[.,]?\\d*+) ནང་" ], "in \\1 minute": [ - "སྐར་མ་ (\\d+[.,]?\\d*) ནང་" + "སྐར་མ་ (\\d++[.,]?\\d*+) ནང་" ], "in \\1 month": [ - "ཟླཝ་ (\\d+[.,]?\\d*) ནང་" + "ཟླཝ་ (\\d++[.,]?\\d*+) ནང་" ], "in \\1 second": [ - "སྐར་ཆ་ (\\d+[.,]?\\d*) ནང་" + "སྐར་ཆ་ (\\d++[.,]?\\d*+) ནང་" ], "in \\1 week": [ - "བངུན་ཕྲག་ (\\d+[.,]?\\d*) ནང་" + "བངུན་ཕྲག་ (\\d++[.,]?\\d*+) ནང་" ], "in \\1 year": [ - "ལོ་འཁོར་ (\\d+[.,]?\\d*) ནང་" + "ལོ་འཁོར་ (\\d++[.,]?\\d*+) ནང་" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/ebu.py b/dateparser/data/date_translation_data/ebu.py index efe459c33..199d014b4 100644 --- a/dateparser/data/date_translation_data/ebu.py +++ b/dateparser/data/date_translation_data/ebu.py @@ -96,6 +96,7 @@ "mũthenya" ], "hour": [ + "hr", "ithaa" ], "minute": [ diff --git a/dateparser/data/date_translation_data/ee.py b/dateparser/data/date_translation_data/ee.py index b6068c50d..bc2d95c06 100644 --- a/dateparser/data/date_translation_data/ee.py +++ b/dateparser/data/date_translation_data/ee.py @@ -96,7 +96,8 @@ "ŋkeke" ], "hour": [ - "gaƒoƒo" + "gaƒoƒo", + "gaƒoƒowo" ], "minute": [ "aɖabaƒoƒo" @@ -153,62 +154,62 @@ }, "relative-type-regex": { "\\1 day ago": [ - "ŋkeke (\\d+[.,]?\\d*) si va yi", - "ŋkeke (\\d+[.,]?\\d*) si wo va yi" + "ŋkeke (\\d++[.,]?\\d*+) si va yi", + "ŋkeke (\\d++[.,]?\\d*+) si wo va yi" ], "\\1 hour ago": [ - "gaƒoƒo (\\d+[.,]?\\d*) si va yi", - "gaƒoƒo (\\d+[.,]?\\d*) si wo va yi" + "gaƒoƒo (\\d++[.,]?\\d*+) si va yi", + "gaƒoƒo (\\d++[.,]?\\d*+) si wo va yi" ], "\\1 minute ago": [ - "aɖabaƒoƒo (\\d+[.,]?\\d*) si va yi", - "aɖabaƒoƒo (\\d+[.,]?\\d*) si wo va yi" + "aɖabaƒoƒo (\\d++[.,]?\\d*+) si va yi", + "aɖabaƒoƒo (\\d++[.,]?\\d*+) si wo va yi" ], "\\1 month ago": [ - "ɣleti (\\d+[.,]?\\d*) si va yi", - "ɣleti (\\d+[.,]?\\d*) si wo va yi" + "ɣleti (\\d++[.,]?\\d*+) si va yi", + "ɣleti (\\d++[.,]?\\d*+) si wo va yi" ], "\\1 second ago": [ - "sekend (\\d+[.,]?\\d*) si va yi", - "sekend (\\d+[.,]?\\d*) si wo va yi" + "sekend (\\d++[.,]?\\d*+) si va yi", + "sekend (\\d++[.,]?\\d*+) si wo va yi" ], "\\1 week ago": [ - "kɔsiɖa (\\d+[.,]?\\d*) si va yi", - "kɔsiɖa (\\d+[.,]?\\d*) si wo va yi" + "kɔsiɖa (\\d++[.,]?\\d*+) si va yi", + "kɔsiɖa (\\d++[.,]?\\d*+) si wo va yi" ], "\\1 year ago": [ - "le ƒe (\\d+[.,]?\\d*) si va yi me", - "ƒe (\\d+[.,]?\\d*) si va yi", - "ƒe (\\d+[.,]?\\d*) si va yi me", - "ƒe (\\d+[.,]?\\d*) si wo va yi" + "le ƒe (\\d++[.,]?\\d*+) si va yi me", + "ƒe (\\d++[.,]?\\d*+) si va yi", + "ƒe (\\d++[.,]?\\d*+) si va yi me", + "ƒe (\\d++[.,]?\\d*+) si wo va yi" ], "in \\1 day": [ - "le ŋkeke (\\d+[.,]?\\d*) me", - "le ŋkeke (\\d+[.,]?\\d*) wo me" + "le ŋkeke (\\d++[.,]?\\d*+) me", + "le ŋkeke (\\d++[.,]?\\d*+) wo me" ], "in \\1 hour": [ - "le gaƒoƒo (\\d+[.,]?\\d*) me", - "le gaƒoƒo (\\d+[.,]?\\d*) wo me" + "le gaƒoƒo (\\d++[.,]?\\d*+) me", + "le gaƒoƒo (\\d++[.,]?\\d*+) wo me" ], "in \\1 minute": [ - "le aɖabaƒoƒo (\\d+[.,]?\\d*) me", - "le aɖabaƒoƒo (\\d+[.,]?\\d*) wo me" + "le aɖabaƒoƒo (\\d++[.,]?\\d*+) me", + "le aɖabaƒoƒo (\\d++[.,]?\\d*+) wo me" ], "in \\1 month": [ - "le ɣleti (\\d+[.,]?\\d*) me", - "le ɣleti (\\d+[.,]?\\d*) wo me" + "le ɣleti (\\d++[.,]?\\d*+) me", + "le ɣleti (\\d++[.,]?\\d*+) wo me" ], "in \\1 second": [ - "le sekend (\\d+[.,]?\\d*) me", - "le sekend (\\d+[.,]?\\d*) wo me" + "le sekend (\\d++[.,]?\\d*+) me", + "le sekend (\\d++[.,]?\\d*+) wo me" ], "in \\1 week": [ - "le kɔsiɖa (\\d+[.,]?\\d*) me", - "le kɔsiɖa (\\d+[.,]?\\d*) wo me" + "le kɔsiɖa (\\d++[.,]?\\d*+) me", + "le kɔsiɖa (\\d++[.,]?\\d*+) wo me" ], "in \\1 year": [ - "le ƒe (\\d+[.,]?\\d*) me", - "le ƒe (\\d+[.,]?\\d*) si gbɔna me" + "le ƒe (\\d++[.,]?\\d*+) me", + "le ƒe (\\d++[.,]?\\d*+) si gbɔna me" ] }, "locale_specific": { diff --git a/dateparser/data/date_translation_data/el.py b/dateparser/data/date_translation_data/el.py index 12c793285..69ac05b0e 100644 --- a/dateparser/data/date_translation_data/el.py +++ b/dateparser/data/date_translation_data/el.py @@ -114,12 +114,14 @@ "εβδομάδα" ], "day": [ + "ημ", "ημέρα" ], "hour": [ "ώ", - "ώρ", - "ώρα" + "ώρα", + "ώρες", + "ώρ" ], "minute": [ "λ", @@ -136,18 +138,24 @@ "σήμερα" ], "0 hour ago": [ + "τρέχουσα ώρα", "αυτήν την ώρα" ], "0 minute ago": [ + "τρέχον λεπτό", "αυτό το λεπτό" ], "0 month ago": [ + "τρέχ μήνας", "τρέχων μήνας" ], "0 second ago": [ "τώρα" ], "0 week ago": [ + "τρέχ εβδ", + "τρέχ εβδομάδα", + "τρέχουσα εβδομάδα", "αυτήν την εβδομάδα" ], "0 year ago": [ @@ -157,9 +165,12 @@ "χθες" ], "1 month ago": [ + "προηγ μήνας", "προηγούμενος μήνας" ], "1 week ago": [ + "προηγ εβδ", + "προηγ εβδομάδα", "προηγούμενη εβδομάδα" ], "1 year ago": [ @@ -169,9 +180,12 @@ "αύριο" ], "in 1 month": [ + "επόμ μήνας", "επόμενος μήνας" ], "in 1 week": [ + "επόμ εβδ", + "επόμ εβδομάδα", "επόμενη εβδομάδα" ], "in 1 year": [ @@ -180,81 +194,83 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) ημ πριν", - "πριν από (\\d+[.,]?\\d*) ημέρα", - "πριν από (\\d+[.,]?\\d*) ημέρες" + "(\\d++[.,]?\\d*+) ημ πριν", + "πριν από (\\d++[.,]?\\d*+) ημ", + "πριν από (\\d++[.,]?\\d*+) ημέρα", + "πριν από (\\d++[.,]?\\d*+) ημέρες" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) ώ πριν", - "πριν από (\\d+[.,]?\\d*) ώρ", - "πριν από (\\d+[.,]?\\d*) ώρα", - "πριν από (\\d+[.,]?\\d*) ώρες" + "(\\d++[.,]?\\d*+) ώ πριν", + "πριν από (\\d++[.,]?\\d*+) ώ", + "πριν από (\\d++[.,]?\\d*+) ώρα", + "πριν από (\\d++[.,]?\\d*+) ώρες", + "πριν από (\\d++[.,]?\\d*+) ώρ" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) λ πριν", - "πριν από (\\d+[.,]?\\d*) λεπ", - "πριν από (\\d+[.,]?\\d*) λεπτά", - "πριν από (\\d+[.,]?\\d*) λεπτό" + "(\\d++[.,]?\\d*+) λ πριν", + "πριν από (\\d++[.,]?\\d*+) λεπ", + "πριν από (\\d++[.,]?\\d*+) λεπτά", + "πριν από (\\d++[.,]?\\d*+) λεπτό" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) μ πριν", - "πριν από (\\d+[.,]?\\d*) μήνα", - "πριν από (\\d+[.,]?\\d*) μήνες" + "(\\d++[.,]?\\d*+) μ πριν", + "πριν από (\\d++[.,]?\\d*+) μήνα", + "πριν από (\\d++[.,]?\\d*+) μήνες" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) δ πριν", - "πριν από (\\d+[.,]?\\d*) δευτ", - "πριν από (\\d+[.,]?\\d*) δευτερόλεπτα", - "πριν από (\\d+[.,]?\\d*) δευτερόλεπτο" + "(\\d++[.,]?\\d*+) δ πριν", + "πριν από (\\d++[.,]?\\d*+) δευτ", + "πριν από (\\d++[.,]?\\d*+) δευτερόλεπτα", + "πριν από (\\d++[.,]?\\d*+) δευτερόλεπτο" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) εβδ πριν", - "πριν από (\\d+[.,]?\\d*) εβδ", - "πριν από (\\d+[.,]?\\d*) εβδομάδα", - "πριν από (\\d+[.,]?\\d*) εβδομάδες" + "(\\d++[.,]?\\d*+) εβδ πριν", + "πριν από (\\d++[.,]?\\d*+) εβδ", + "πριν από (\\d++[.,]?\\d*+) εβδομάδα", + "πριν από (\\d++[.,]?\\d*+) εβδομάδες" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) έτη πριν", - "(\\d+[.,]?\\d*) έτος πριν", - "πριν από (\\d+[.,]?\\d*) έτη", - "πριν από (\\d+[.,]?\\d*) έτος" + "(\\d++[.,]?\\d*+) έτη πριν", + "(\\d++[.,]?\\d*+) έτος πριν", + "πριν από (\\d++[.,]?\\d*+) έτη", + "πριν από (\\d++[.,]?\\d*+) έτος" ], "in \\1 day": [ - "σε (\\d+[.,]?\\d*) ημ", - "σε (\\d+[.,]?\\d*) ημέρα", - "σε (\\d+[.,]?\\d*) ημέρες" + "σε (\\d++[.,]?\\d*+) ημ", + "σε (\\d++[.,]?\\d*+) ημέρα", + "σε (\\d++[.,]?\\d*+) ημέρες" ], "in \\1 hour": [ - "σε (\\d+[.,]?\\d*) ώ", - "σε (\\d+[.,]?\\d*) ώρ", - "σε (\\d+[.,]?\\d*) ώρα", - "σε (\\d+[.,]?\\d*) ώρες" + "σε (\\d++[.,]?\\d*+) ώ", + "σε (\\d++[.,]?\\d*+) ώρα", + "σε (\\d++[.,]?\\d*+) ώρες", + "σε (\\d++[.,]?\\d*+) ώρ" ], "in \\1 minute": [ - "σε (\\d+[.,]?\\d*) λ", - "σε (\\d+[.,]?\\d*) λεπ", - "σε (\\d+[.,]?\\d*) λεπτά", - "σε (\\d+[.,]?\\d*) λεπτό" + "σε (\\d++[.,]?\\d*+) λ", + "σε (\\d++[.,]?\\d*+) λεπ", + "σε (\\d++[.,]?\\d*+) λεπτά", + "σε (\\d++[.,]?\\d*+) λεπτό" ], "in \\1 month": [ - "σε (\\d+[.,]?\\d*) μ", - "σε (\\d+[.,]?\\d*) μήνα", - "σε (\\d+[.,]?\\d*) μήνες" + "σε (\\d++[.,]?\\d*+) μ", + "σε (\\d++[.,]?\\d*+) μήνα", + "σε (\\d++[.,]?\\d*+) μήνες" ], "in \\1 second": [ - "σε (\\d+[.,]?\\d*) δ", - "σε (\\d+[.,]?\\d*) δευτ", - "σε (\\d+[.,]?\\d*) δευτερόλεπτα", - "σε (\\d+[.,]?\\d*) δευτερόλεπτο" + "σε (\\d++[.,]?\\d*+) δ", + "σε (\\d++[.,]?\\d*+) δευτ", + "σε (\\d++[.,]?\\d*+) δευτερόλεπτα", + "σε (\\d++[.,]?\\d*+) δευτερόλεπτο" ], "in \\1 week": [ - "σε (\\d+[.,]?\\d*) εβδ", - "σε (\\d+[.,]?\\d*) εβδομάδα", - "σε (\\d+[.,]?\\d*) εβδομάδες" + "σε (\\d++[.,]?\\d*+) εβδ", + "σε (\\d++[.,]?\\d*+) εβδομάδα", + "σε (\\d++[.,]?\\d*+) εβδομάδες" ], "in \\1 year": [ - "σε (\\d+[.,]?\\d*) έτη", - "σε (\\d+[.,]?\\d*) έτος" + "σε (\\d++[.,]?\\d*+) έτη", + "σε (\\d++[.,]?\\d*+) έτος" ] }, "locale_specific": { diff --git a/dateparser/data/date_translation_data/en.py b/dateparser/data/date_translation_data/en.py index ffa7a6de4..017edb218 100644 --- a/dateparser/data/date_translation_data/en.py +++ b/dateparser/data/date_translation_data/en.py @@ -114,6 +114,7 @@ ], "hour": [ "hour", + "hours", "hr", "h", "hours", @@ -205,441 +206,720 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) day ago", - "(\\d+[.,]?\\d*) days ago" + "(\\d++[.,]?\\d*+) day ago", + "(\\d++[.,]?\\d*+) days ago", + "(\\d++[.,]?\\d*+)d ago" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) hour ago", - "(\\d+[.,]?\\d*) hours ago", - "(\\d+[.,]?\\d*) hr ago" + "(\\d++[.,]?\\d*+) hour ago", + "(\\d++[.,]?\\d*+) hours ago", + "(\\d++[.,]?\\d*+) hr ago", + "(\\d++[.,]?\\d*+)h ago" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) min ago", - "(\\d+[.,]?\\d*) minute ago", - "(\\d+[.,]?\\d*) minutes ago" + "(\\d++[.,]?\\d*+) min ago", + "(\\d++[.,]?\\d*+) minute ago", + "(\\d++[.,]?\\d*+) minutes ago", + "(\\d++[.,]?\\d*+)m ago" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) mo ago", - "(\\d+[.,]?\\d*) month ago", - "(\\d+[.,]?\\d*) months ago" + "(\\d++[.,]?\\d*+) mo ago", + "(\\d++[.,]?\\d*+) month ago", + "(\\d++[.,]?\\d*+) months ago", + "(\\d++[.,]?\\d*+)mo ago" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) sec ago", - "(\\d+[.,]?\\d*) second ago", - "(\\d+[.,]?\\d*) seconds ago" + "(\\d++[.,]?\\d*+) sec ago", + "(\\d++[.,]?\\d*+) second ago", + "(\\d++[.,]?\\d*+) seconds ago", + "(\\d++[.,]?\\d*+)s ago" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) week ago", - "(\\d+[.,]?\\d*) weeks ago", - "(\\d+[.,]?\\d*) wk ago" + "(\\d++[.,]?\\d*+) week ago", + "(\\d++[.,]?\\d*+) weeks ago", + "(\\d++[.,]?\\d*+) wk ago", + "(\\d++[.,]?\\d*+)w ago" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) year ago", - "(\\d+[.,]?\\d*) years ago", - "(\\d+[.,]?\\d*) yr ago" + "(\\d++[.,]?\\d*+) year ago", + "(\\d++[.,]?\\d*+) years ago", + "(\\d++[.,]?\\d*+) yr ago", + "(\\d++[.,]?\\d*+)y ago" ], "in \\1 day": [ - "in (\\d+[.,]?\\d*) day", - "in (\\d+[.,]?\\d*) days" + "in (\\d++[.,]?\\d*+) day", + "in (\\d++[.,]?\\d*+) days", + "in (\\d++[.,]?\\d*+)d" ], "in \\1 hour": [ - "in (\\d+[.,]?\\d*) hour", - "in (\\d+[.,]?\\d*) hours", - "in (\\d+[.,]?\\d*) hr" + "in (\\d++[.,]?\\d*+) hour", + "in (\\d++[.,]?\\d*+) hours", + "in (\\d++[.,]?\\d*+) hr", + "in (\\d++[.,]?\\d*+)h" ], "in \\1 minute": [ - "in (\\d+[.,]?\\d*) min", - "in (\\d+[.,]?\\d*) minute", - "in (\\d+[.,]?\\d*) minutes" + "in (\\d++[.,]?\\d*+) min", + "in (\\d++[.,]?\\d*+) minute", + "in (\\d++[.,]?\\d*+) minutes", + "in (\\d++[.,]?\\d*+)m" ], "in \\1 month": [ - "in (\\d+[.,]?\\d*) mo", - "in (\\d+[.,]?\\d*) month", - "in (\\d+[.,]?\\d*) months" + "in (\\d++[.,]?\\d*+) mo", + "in (\\d++[.,]?\\d*+) month", + "in (\\d++[.,]?\\d*+) months", + "in (\\d++[.,]?\\d*+)mo" ], "in \\1 second": [ - "in (\\d+[.,]?\\d*) sec", - "in (\\d+[.,]?\\d*) second", - "in (\\d+[.,]?\\d*) seconds" + "in (\\d++[.,]?\\d*+) sec", + "in (\\d++[.,]?\\d*+) second", + "in (\\d++[.,]?\\d*+) seconds", + "in (\\d++[.,]?\\d*+)s" ], "in \\1 week": [ - "in (\\d+[.,]?\\d*) week", - "in (\\d+[.,]?\\d*) weeks", - "in (\\d+[.,]?\\d*) weeks time", - "in (\\d+[.,]?\\d*) weeks' time", - "in (\\d+[.,]?\\d*) wk" + "in (\\d++[.,]?\\d*+) week", + "in (\\d++[.,]?\\d*+) weeks", + "in (\\d++[.,]?\\d*+) wk", + "in (\\d++[.,]?\\d*+)w", + "in (\\d++[.,]?\\d*+) weeks time", + "in (\\d++[.,]?\\d*+) weeks' time" ], "in \\1 year": [ - "in (\\d+[.,]?\\d*) year", - "in (\\d+[.,]?\\d*) years", - "in (\\d+[.,]?\\d*) yr" + "in (\\d++[.,]?\\d*+) year", + "in (\\d++[.,]?\\d*+) years", + "in (\\d++[.,]?\\d*+) yr", + "in (\\d++[.,]?\\d*+)y" ], "in \\1 decade": [ - "in (\\d+[.,]?\\d*) decades?" + "in (\\d++[.,]?\\d*+) decades?" ], "\\1 decade ago": [ - "(\\d+[.,]?\\d*) decades? ago" + "(\\d++[.,]?\\d*+) decades? ago" ] }, "locale_specific": { "en-001": { "name": "en-001", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-150": { "name": "en-150", + "date_order": "DMY", + "september": [ + "sept" + ] + }, + "en-AE": { + "name": "en-AE", "date_order": "DMY" }, "en-AG": { "name": "en-AG", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-AI": { "name": "en-AI", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-AS": { "name": "en-AS" }, "en-AT": { "name": "en-AT", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-AU": { "name": "en-AU", "date_order": "DMY", - "hour": [ - "h" - ] + "september": [ + "sept" + ], + "relative-type-regex": { + "\\1 hour ago": [ + "(\\d++[.,]?\\d*+) hrs ago" + ], + "\\1 minute ago": [ + "(\\d++[.,]?\\d*+) mins ago" + ], + "\\1 second ago": [ + "(\\d++[.,]?\\d*+) secs ago" + ], + "\\1 week ago": [ + "(\\d++[.,]?\\d*+) wks ago" + ], + "\\1 year ago": [ + "(\\d++[.,]?\\d*+) yrs ago" + ], + "in \\1 hour": [ + "in (\\d++[.,]?\\d*+) hrs" + ], + "in \\1 minute": [ + "in (\\d++[.,]?\\d*+) mins" + ], + "in \\1 second": [ + "in (\\d++[.,]?\\d*+) secs" + ], + "in \\1 week": [ + "in (\\d++[.,]?\\d*+) wks" + ], + "in \\1 year": [ + "in (\\d++[.,]?\\d*+) yrs" + ] + } }, "en-BB": { "name": "en-BB", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-BE": { "name": "en-BE", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-BI": { "name": "en-BI" }, "en-BM": { "name": "en-BM", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-BS": { "name": "en-BS", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-BW": { "name": "en-BW", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-BZ": { "name": "en-BZ", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-CA": { "name": "en-CA", "date_order": "YMD", "relative-type-regex": { "\\1 hour ago": [ - "(\\d+[.,]?\\d*) hrs ago" + "(\\d++[.,]?\\d*+) hrs ago" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) mins ago" + "(\\d++[.,]?\\d*+) mins ago" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) mos ago" + "(\\d++[.,]?\\d*+) mos ago" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) secs ago" + "(\\d++[.,]?\\d*+) secs ago" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) wks ago" + "(\\d++[.,]?\\d*+) wks ago" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) yrs ago" + "(\\d++[.,]?\\d*+) yrs ago" ], "in \\1 hour": [ - "in (\\d+[.,]?\\d*) hrs" + "in (\\d++[.,]?\\d*+) hrs" ], "in \\1 minute": [ - "in (\\d+[.,]?\\d*) mins" + "in (\\d++[.,]?\\d*+) mins" ], "in \\1 month": [ - "in (\\d+[.,]?\\d*) mos" + "in (\\d++[.,]?\\d*+) mos" ], "in \\1 second": [ - "in (\\d+[.,]?\\d*) secs" + "in (\\d++[.,]?\\d*+) secs" ], "in \\1 week": [ - "in (\\d+[.,]?\\d*) wks" + "in (\\d++[.,]?\\d*+) wks" ], "in \\1 year": [ - "in (\\d+[.,]?\\d*) yrs" + "in (\\d++[.,]?\\d*+) yrs" ] } }, "en-CC": { "name": "en-CC", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-CH": { "name": "en-CH", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-CK": { "name": "en-CK", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-CM": { "name": "en-CM", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-CX": { "name": "en-CX", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-CY": { "name": "en-CY", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-DE": { "name": "en-DE", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-DG": { "name": "en-DG", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-DK": { "name": "en-DK", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-DM": { "name": "en-DM", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-ER": { "name": "en-ER", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-FI": { "name": "en-FI", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-FJ": { "name": "en-FJ", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-FK": { "name": "en-FK", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-FM": { "name": "en-FM", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-GB": { "name": "en-GB", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-GD": { "name": "en-GD", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-GG": { "name": "en-GG", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-GH": { "name": "en-GH", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-GI": { "name": "en-GI", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-GM": { "name": "en-GM", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-GU": { "name": "en-GU" }, "en-GY": { "name": "en-GY", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-HK": { "name": "en-HK", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] + }, + "en-ID": { + "name": "en-ID", + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-IE": { "name": "en-IE", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-IL": { "name": "en-IL", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-IM": { "name": "en-IM", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-IN": { "name": "en-IN", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-IO": { "name": "en-IO", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-JE": { "name": "en-JE", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-JM": { "name": "en-JM", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-KE": { "name": "en-KE", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-KI": { "name": "en-KI", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-KN": { "name": "en-KN", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-KY": { "name": "en-KY", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-LC": { "name": "en-LC", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-LR": { "name": "en-LR", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-LS": { "name": "en-LS", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-MG": { "name": "en-MG", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-MH": { "name": "en-MH" }, "en-MO": { "name": "en-MO", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-MP": { "name": "en-MP" }, "en-MS": { "name": "en-MS", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-MT": { "name": "en-MT", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-MU": { "name": "en-MU", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] + }, + "en-MV": { + "name": "en-MV", + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-MW": { "name": "en-MW", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-MY": { "name": "en-MY", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-NA": { "name": "en-NA", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-NF": { "name": "en-NF", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-NG": { "name": "en-NG", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-NL": { "name": "en-NL", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-NR": { "name": "en-NR", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-NU": { "name": "en-NU", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-NZ": { "name": "en-NZ", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-PG": { "name": "en-PG", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-PH": { - "name": "en-PH", - "date_order": "DMY" + "name": "en-PH" }, "en-PK": { "name": "en-PK", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-PN": { "name": "en-PN", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-PR": { "name": "en-PR" }, "en-PW": { "name": "en-PW", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-RW": { "name": "en-RW", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-SB": { "name": "en-SB", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-SC": { "name": "en-SC", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-SD": { "name": "en-SD", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-SE": { "name": "en-SE", - "date_order": "YMD" + "date_order": "YMD", + "september": [ + "sept" + ] }, "en-SG": { "name": "en-SG", "date_order": "DMY", + "september": [ + "sept" + ], "month": [ "mth" ], @@ -656,98 +936,162 @@ }, "relative-type-regex": { "\\1 month ago": [ - "(\\d+[.,]?\\d*) mth ago" + "(\\d++[.,]?\\d*+) mth ago" ], "in \\1 month": [ - "in (\\d+[.,]?\\d*) mth" + "in (\\d++[.,]?\\d*+) mth" ] } }, "en-SH": { "name": "en-SH", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-SI": { "name": "en-SI", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-SL": { "name": "en-SL", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-SS": { "name": "en-SS", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-SX": { "name": "en-SX", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-SZ": { "name": "en-SZ", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-TC": { "name": "en-TC", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-TK": { "name": "en-TK", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-TO": { "name": "en-TO", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-TT": { "name": "en-TT", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-TV": { "name": "en-TV", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-TZ": { "name": "en-TZ", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-UG": { "name": "en-UG", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-UM": { "name": "en-UM" }, "en-VC": { "name": "en-VC", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-VG": { "name": "en-VG", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-VI": { "name": "en-VI" }, "en-VU": { "name": "en-VU", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-WS": { "name": "en-WS", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-ZA": { "name": "en-ZA", - "date_order": "YMD" + "date_order": "YMD", + "september": [ + "sept" + ] }, "en-ZM": { "name": "en-ZM", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-ZW": { "name": "en-ZW", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] + }, + "en-US": { + "name": "en-US", + "date_order": "MDY" } }, "skip": [ @@ -756,6 +1100,7 @@ "and", "at", "by", + "from", "just", "m", "nd", @@ -786,6 +1131,23 @@ "decade", "decades" ], + "early_morning": [ + "early morning", + "small hours", + "wee hours" + ], + "morning": [ + "morning" + ], + "afternoon": [ + "afternoon" + ], + "evening": [ + "evening" + ], + "night": [ + "night" + ], "ago": [ "ago", "before" @@ -796,6 +1158,9 @@ "after" ], "simplifications": [ + { + "(\\d++[.,]?\\d*+)\\s*mons?\\b": "\\1 month" + }, { "an": "1" }, @@ -809,16 +1174,31 @@ "(?:12\\s+)?midnight": "00:00" }, { - "(\\d+[.,]?\\d*)h(\\d+[.,]?\\d*)": "\\1:\\2" + "tonight": "today night" }, { - "(?<=from\\s+)now": "in" + "last night": "yesterday night" + }, + { + "this ((?:early )?morning|afternoon|evening|night)": "today \\1" + }, + { + "in the ((?:early )?morning|afternoon|evening|night|small hours|wee hours)": "\\1" + }, + { + "(\\d++[.,]?\\d*+)h(\\d++[.,]?\\d*+)": "\\1:\\2" + }, + { + "from\\s+now": "in" }, { "less than 1 minute ago": "45 second ago" }, { - "(\\d+[.,]?\\d*) (decade|year|month|week|day|hour|minute|second)s? later": "in \\1 \\2" + "(\\d+(?:st|nd|rd|th)) day": "\\1" + }, + { + "(\\d++[.,]?\\d*+|one|two|three|four|five|six|seven|eight|nine|ten|eleven|twelve) (decade|year|month|week|day|hour|minute|second)s? later": "in \\1 \\2" }, { "one": "1" diff --git a/dateparser/data/date_translation_data/eo.py b/dateparser/data/date_translation_data/eo.py index 8e172aeb2..252d94593 100644 --- a/dateparser/data/date_translation_data/eo.py +++ b/dateparser/data/date_translation_data/eo.py @@ -96,7 +96,8 @@ "day" ], "hour": [ - "hour" + "hour", + "hr" ], "minute": [ "minute" diff --git a/dateparser/data/date_translation_data/es.py b/dateparser/data/date_translation_data/es.py index ea36dbf81..fb11efdc5 100644 --- a/dateparser/data/date_translation_data/es.py +++ b/dateparser/data/date_translation_data/es.py @@ -115,6 +115,7 @@ "hour": [ "h", "hora", + "horas", "horas" ], "minute": [ @@ -144,6 +145,7 @@ "ahora" ], "0 week ago": [ + "esta sem", "esta semana" ], "0 year ago": [ @@ -156,7 +158,8 @@ "el mes pasado" ], "1 week ago": [ - "la semana pasada" + "la semana pasada", + "sem ant" ], "1 year ago": [ "el año pasado" @@ -168,7 +171,8 @@ "el próximo mes" ], "in 1 week": [ - "la próxima semana" + "la próxima semana", + "próx sem" ], "in 1 year": [ "el próximo año" @@ -179,142 +183,197 @@ }, "relative-type-regex": { "\\1 day ago": [ - "hace (\\d+[.,]?\\d*) día", - "hace (\\d+[.,]?\\d*) días" + "hace (\\d++[.,]?\\d*+) d", + "hace (\\d++[.,]?\\d*+) día", + "hace (\\d++[.,]?\\d*+) días" ], "\\1 hour ago": [ - "hace (\\d+[.,]?\\d*) h", - "hace (\\d+[.,]?\\d*) hora", - "hace (\\d+[.,]?\\d*) horas" + "hace (\\d++[.,]?\\d*+) h", + "hace (\\d++[.,]?\\d*+) hora", + "hace (\\d++[.,]?\\d*+) horas" ], "\\1 minute ago": [ - "hace (\\d+[.,]?\\d*) min", - "hace (\\d+[.,]?\\d*) minuto", - "hace (\\d+[.,]?\\d*) minutos" + "hace (\\d++[.,]?\\d*+) min", + "hace (\\d++[.,]?\\d*+) minuto", + "hace (\\d++[.,]?\\d*+) minutos" ], "\\1 month ago": [ - "hace (\\d+[.,]?\\d*) m", - "hace (\\d+[.,]?\\d*) mes", - "hace (\\d+[.,]?\\d*) meses" + "hace (\\d++[.,]?\\d*+) m", + "hace (\\d++[.,]?\\d*+) mes", + "hace (\\d++[.,]?\\d*+) meses" ], "\\1 second ago": [ - "hace (\\d+[.,]?\\d*) s", - "hace (\\d+[.,]?\\d*) segundo", - "hace (\\d+[.,]?\\d*) segundos" + "hace (\\d++[.,]?\\d*+) s", + "hace (\\d++[.,]?\\d*+) segundo", + "hace (\\d++[.,]?\\d*+) segundos" ], "\\1 week ago": [ - "hace (\\d+[.,]?\\d*) sem", - "hace (\\d+[.,]?\\d*) semana", - "hace (\\d+[.,]?\\d*) semanas" + "hace (\\d++[.,]?\\d*+) sem", + "hace (\\d++[.,]?\\d*+) semana", + "hace (\\d++[.,]?\\d*+) semanas" ], "\\1 year ago": [ - "hace (\\d+[.,]?\\d*) a", - "hace (\\d+[.,]?\\d*) año", - "hace (\\d+[.,]?\\d*) años" + "hace (\\d++[.,]?\\d*+) a", + "hace (\\d++[.,]?\\d*+) año", + "hace (\\d++[.,]?\\d*+) años" ], "in \\1 day": [ - "dentro de (\\d+[.,]?\\d*) día", - "dentro de (\\d+[.,]?\\d*) días" + "dentro de (\\d++[.,]?\\d*+) d", + "dentro de (\\d++[.,]?\\d*+) día", + "dentro de (\\d++[.,]?\\d*+) días" ], "in \\1 hour": [ - "dentro de (\\d+[.,]?\\d*) h", - "dentro de (\\d+[.,]?\\d*) hora", - "dentro de (\\d+[.,]?\\d*) horas" + "dentro de (\\d++[.,]?\\d*+) h", + "dentro de (\\d++[.,]?\\d*+) hora", + "dentro de (\\d++[.,]?\\d*+) horas" ], "in \\1 minute": [ - "dentro de (\\d+[.,]?\\d*) min", - "dentro de (\\d+[.,]?\\d*) minuto", - "dentro de (\\d+[.,]?\\d*) minutos" + "dentro de (\\d++[.,]?\\d*+) min", + "dentro de (\\d++[.,]?\\d*+) minuto", + "dentro de (\\d++[.,]?\\d*+) minutos" ], "in \\1 month": [ - "dentro de (\\d+[.,]?\\d*) m", - "dentro de (\\d+[.,]?\\d*) mes", - "dentro de (\\d+[.,]?\\d*) meses" + "dentro de (\\d++[.,]?\\d*+) m", + "dentro de (\\d++[.,]?\\d*+) mes", + "dentro de (\\d++[.,]?\\d*+) meses" ], "in \\1 second": [ - "dentro de (\\d+[.,]?\\d*) s", - "dentro de (\\d+[.,]?\\d*) segundo", - "dentro de (\\d+[.,]?\\d*) segundos" + "dentro de (\\d++[.,]?\\d*+) s", + "dentro de (\\d++[.,]?\\d*+) segundo", + "dentro de (\\d++[.,]?\\d*+) segundos" ], "in \\1 week": [ - "dentro de (\\d+[.,]?\\d*) sem", - "dentro de (\\d+[.,]?\\d*) semana", - "dentro de (\\d+[.,]?\\d*) semanas" + "dentro de (\\d++[.,]?\\d*+) sem", + "dentro de (\\d++[.,]?\\d*+) semana", + "dentro de (\\d++[.,]?\\d*+) semanas" ], "in \\1 year": [ - "dentro de (\\d+[.,]?\\d*) a", - "dentro de (\\d+[.,]?\\d*) año", - "dentro de (\\d+[.,]?\\d*) años" + "dentro de (\\d++[.,]?\\d*+) a", + "dentro de (\\d++[.,]?\\d*+) año", + "dentro de (\\d++[.,]?\\d*+) años" ] }, "locale_specific": { "es-419": { "name": "es-419", + "relative-type": { + "1 week ago": [ + "sem pas" + ] + }, "september": [ "sep" ] }, "es-AR": { "name": "es-AR", - "september": [ - "sep" + "hour": [ + "hs" ], "second": [ "seg" ], + "relative-type": { + "1 week ago": [ + "sem pas" + ] + }, "relative-type-regex": { "\\1 second ago": [ - "hace (\\d+[.,]?\\d*) seg" + "hace (\\d++[.,]?\\d*+) seg" ], "in \\1 second": [ - "dentro de (\\d+[.,]?\\d*) seg" + "dentro de (\\d++[.,]?\\d*+) seg" ] - } + }, + "september": [ + "sep" + ] }, "es-BO": { "name": "es-BO", + "relative-type": { + "1 week ago": [ + "sem pas" + ] + }, "september": [ "sep" ] }, "es-BR": { "name": "es-BR", + "relative-type": { + "1 week ago": [ + "sem pas" + ] + }, "september": [ "sep" ] }, "es-BZ": { "name": "es-BZ", + "relative-type": { + "1 week ago": [ + "sem pas" + ] + }, "september": [ "sep" ] }, "es-CL": { "name": "es-CL", + "relative-type": { + "1 week ago": [ + "sem pas" + ] + }, "september": [ "sep" ] }, "es-CO": { "name": "es-CO", + "relative-type": { + "1 week ago": [ + "sem pas" + ] + }, "september": [ "sep" ] }, "es-CR": { "name": "es-CR", + "relative-type": { + "1 week ago": [ + "sem pas" + ] + }, "september": [ "sep" ] }, "es-CU": { "name": "es-CU", + "relative-type": { + "1 week ago": [ + "sem pas" + ] + }, "september": [ "sep" ] }, "es-DO": { "name": "es-DO", + "relative-type": { + "1 week ago": [ + "sem pas" + ] + }, "september": [ "sep" ] @@ -324,6 +383,11 @@ }, "es-EC": { "name": "es-EC", + "relative-type": { + "1 week ago": [ + "sem pas" + ] + }, "september": [ "sep" ] @@ -333,12 +397,22 @@ }, "es-GT": { "name": "es-GT", + "relative-type": { + "1 week ago": [ + "sem pas" + ] + }, "september": [ "sep" ] }, "es-HN": { "name": "es-HN", + "relative-type": { + "1 week ago": [ + "sem pas" + ] + }, "september": [ "sep" ] @@ -352,6 +426,9 @@ "sep" ], "relative-type": { + "1 week ago": [ + "sem pas" + ], "in 1 month": [ "el mes próximo" ], @@ -364,34 +441,39 @@ }, "relative-type-regex": { "in \\1 day": [ - "en (\\d+[.,]?\\d*) día", - "en (\\d+[.,]?\\d*) días" + "en (\\d++[.,]?\\d*+) día", + "en (\\d++[.,]?\\d*+) días" ], "in \\1 hour": [ - "en (\\d+[.,]?\\d*) h", - "en (\\d+[.,]?\\d*) n" - ], - "in \\1 minute": [ - "en (\\d+[.,]?\\d*) min" + "en (\\d++[.,]?\\d*+) h", + "en (\\d++[.,]?\\d*+) n" ], "in \\1 month": [ - "en (\\d+[.,]?\\d*) m", - "en (\\d+[.,]?\\d*) mes", - "en (\\d+[.,]?\\d*) meses" + "en (\\d++[.,]?\\d*+) m", + "en (\\d++[.,]?\\d*+) mes", + "en (\\d++[.,]?\\d*+) meses" ], "in \\1 second": [ - "en (\\d+[.,]?\\d*) s" + "en (\\d++[.,]?\\d*+) s" ], "in \\1 week": [ - "en (\\d+[.,]?\\d*) sem" + "en (\\d++[.,]?\\d*+) sem" ], "in \\1 year": [ - "en (\\d+[.,]?\\d*) a" + "en (\\d++[.,]?\\d*+) a" + ], + "in \\1 minute": [ + "en (\\d++[.,]?\\d*+) min" ] } }, "es-NI": { "name": "es-NI", + "relative-type": { + "1 week ago": [ + "sem pas" + ] + }, "september": [ "sep" ] @@ -399,6 +481,11 @@ "es-PA": { "name": "es-PA", "date_order": "MDY", + "relative-type": { + "1 week ago": [ + "sem pas" + ] + }, "september": [ "sep" ] @@ -408,7 +495,12 @@ "september": [ "set", "setiembre" - ] + ], + "relative-type": { + "1 week ago": [ + "sem pas" + ] + } }, "es-PH": { "name": "es-PH" @@ -416,6 +508,11 @@ "es-PR": { "name": "es-PR", "date_order": "MDY", + "relative-type": { + "1 week ago": [ + "sem pas" + ] + }, "september": [ "sep" ] @@ -425,23 +522,41 @@ "second": [ "seg" ], + "relative-type": { + "1 week ago": [ + "sem pas" + ] + }, "relative-type-regex": { "\\1 second ago": [ - "hace (\\d+[.,]?\\d*) seg" + "hace (\\d++[.,]?\\d*+) seg" ], "in \\1 second": [ - "dentro de (\\d+[.,]?\\d*) seg" + "dentro de (\\d++[.,]?\\d*+) seg" ] } }, "es-SV": { "name": "es-SV", + "relative-type": { + "1 week ago": [ + "sem pas" + ] + }, "september": [ "sep" ] }, "es-US": { "name": "es-US", + "relative-type": { + "1 week ago": [ + "sem pasada" + ], + "in 1 week": [ + "próxima sem" + ] + }, "september": [ "sep" ] @@ -451,10 +566,20 @@ "september": [ "set", "setiembre" - ] + ], + "relative-type": { + "1 week ago": [ + "sem pas" + ] + } }, "es-VE": { - "name": "es-VE" + "name": "es-VE", + "relative-type": { + "1 week ago": [ + "sem pas" + ] + } } }, "skip": [ @@ -482,6 +607,10 @@ "del" ], "sentence_splitter_group": 2, + "early_morning": [ + "de madrugada", + "madrugada" + ], "ago": [ "hace" ], @@ -489,6 +618,12 @@ "en" ], "simplifications": [ + { + "esta madrugada": "hoy madrugada" + }, + { + "(?:de|por|en) la madrugada": "madrugada" + }, { "una": "1" }, diff --git a/dateparser/data/date_translation_data/et.py b/dateparser/data/date_translation_data/et.py index d17276fb5..4c77e3e1c 100644 --- a/dateparser/data/date_translation_data/et.py +++ b/dateparser/data/date_translation_data/et.py @@ -97,7 +97,8 @@ ], "hour": [ "t", - "tund" + "tund", + "tunnid" ], "minute": [ "min", @@ -119,100 +120,118 @@ "praegusel minutil" ], "0 month ago": [ - "käesolev kuu" + "käesolev kuu", + "see k", + "see kuu" ], "0 second ago": [ "nüüd" ], "0 week ago": [ - "käesolev nädal" + "käesolev nädal", + "see n", + "see näd" ], "0 year ago": [ - "käesolev aasta" + "käesolev a", + "käesolev aasta", + "see a" ], "1 day ago": [ "eile" ], "1 month ago": [ + "eelm k", + "eelm kuu", "eelmine kuu" ], "1 week ago": [ + "eelm n", + "eelm näd", "eelmine nädal" ], "1 year ago": [ + "eelm a", + "eelmine a", "eelmine aasta" ], "in 1 day": [ "homme" ], "in 1 month": [ + "järgm k", + "järgm kuu", "järgmine kuu" ], "in 1 week": [ + "järgm n", + "järgm näd", "järgmine nädal" ], "in 1 year": [ + "järgm a", + "järgmine a", "järgmine aasta" ] }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) p eest", - "(\\d+[.,]?\\d*) päeva eest" + "(\\d++[.,]?\\d*+) p eest", + "(\\d++[.,]?\\d*+) päeva eest" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) t eest", - "(\\d+[.,]?\\d*) tunni eest" + "(\\d++[.,]?\\d*+) t eest", + "(\\d++[.,]?\\d*+) tunni eest" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) min eest", - "(\\d+[.,]?\\d*) minuti eest" + "(\\d++[.,]?\\d*+) min eest", + "(\\d++[.,]?\\d*+) minuti eest" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) k eest", - "(\\d+[.,]?\\d*) kuu eest" + "(\\d++[.,]?\\d*+) k eest", + "(\\d++[.,]?\\d*+) kuu eest" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) s eest", - "(\\d+[.,]?\\d*) sek eest", - "(\\d+[.,]?\\d*) sekundi eest" + "(\\d++[.,]?\\d*+) s eest", + "(\\d++[.,]?\\d*+) sek eest", + "(\\d++[.,]?\\d*+) sekundi eest" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) näd eest", - "(\\d+[.,]?\\d*) nädala eest" + "(\\d++[.,]?\\d*+) näd eest", + "(\\d++[.,]?\\d*+) nädala eest" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) a eest", - "(\\d+[.,]?\\d*) aasta eest" + "(\\d++[.,]?\\d*+) a eest", + "(\\d++[.,]?\\d*+) aasta eest" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) p pärast", - "(\\d+[.,]?\\d*) päeva pärast" + "(\\d++[.,]?\\d*+) p pärast", + "(\\d++[.,]?\\d*+) päeva pärast" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) t pärast", - "(\\d+[.,]?\\d*) tunni pärast" + "(\\d++[.,]?\\d*+) t pärast", + "(\\d++[.,]?\\d*+) tunni pärast" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) min pärast", - "(\\d+[.,]?\\d*) minuti pärast" + "(\\d++[.,]?\\d*+) min pärast", + "(\\d++[.,]?\\d*+) minuti pärast" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) k pärast", - "(\\d+[.,]?\\d*) kuu pärast" + "(\\d++[.,]?\\d*+) k pärast", + "(\\d++[.,]?\\d*+) kuu pärast" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) s pärast", - "(\\d+[.,]?\\d*) sek pärast", - "(\\d+[.,]?\\d*) sekundi pärast" + "(\\d++[.,]?\\d*+) s pärast", + "(\\d++[.,]?\\d*+) sek pärast", + "(\\d++[.,]?\\d*+) sekundi pärast" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) näd pärast", - "(\\d+[.,]?\\d*) nädala pärast" + "(\\d++[.,]?\\d*+) näd pärast", + "(\\d++[.,]?\\d*+) nädala pärast" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) a pärast", - "(\\d+[.,]?\\d*) aasta pärast" + "(\\d++[.,]?\\d*+) a pärast", + "(\\d++[.,]?\\d*+) aasta pärast" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/eu.py b/dateparser/data/date_translation_data/eu.py index 2e8a6c436..c40a94484 100644 --- a/dateparser/data/date_translation_data/eu.py +++ b/dateparser/data/date_translation_data/eu.py @@ -100,7 +100,8 @@ ], "hour": [ "h", - "ordua" + "ordua", + "orduak" ], "minute": [ "min", @@ -121,12 +122,14 @@ "minutu honetan" ], "0 month ago": [ + "hilabete honetan", "hilabete hau" ], "0 second ago": [ "orain" ], "0 week ago": [ + "aste honetan", "aste hau" ], "0 year ago": [ @@ -136,69 +139,75 @@ "atzo" ], "1 month ago": [ + "aurreko hilabetean", "aurreko hilabetea" ], "1 week ago": [ + "aurreko astean", "aurreko astea" ], "1 year ago": [ - "aurreko urtea" + "aurreko urtea", + "iaz" ], "in 1 day": [ "bihar" ], "in 1 month": [ + "hurrengo hilabetean", "hurrengo hilabetea" ], "in 1 week": [ + "hurrengo astean", "hurrengo astea" ], "in 1 year": [ - "hurrengo urtea" + "hurrengo urtea", + "hurrengo urtean" ] }, "relative-type-regex": { "\\1 day ago": [ - "duela (\\d+[.,]?\\d*) egun" + "duela (\\d++[.,]?\\d*+) egun" ], "\\1 hour ago": [ - "duela (\\d+[.,]?\\d*) ordu" + "duela (\\d++[.,]?\\d*+) ordu" ], "\\1 minute ago": [ - "duela (\\d+[.,]?\\d*) minutu" + "duela (\\d++[.,]?\\d*+) minutu" ], "\\1 month ago": [ - "duela (\\d+[.,]?\\d*) hilabete" + "duela (\\d++[.,]?\\d*+) hilabete" ], "\\1 second ago": [ - "duela (\\d+[.,]?\\d*) segundo" + "duela (\\d++[.,]?\\d*+) segundo" ], "\\1 week ago": [ - "duela (\\d+[.,]?\\d*) aste" + "duela (\\d++[.,]?\\d*+) aste" ], "\\1 year ago": [ - "duela (\\d+[.,]?\\d*) urte" + "duela (\\d++[.,]?\\d*+) urte" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) egun barru" + "(\\d++[.,]?\\d*+) egun barru" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) ordu barru" + "(\\d++[.,]?\\d*+) ordu barru" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) minutu barru" + "(\\d++[.,]?\\d*+) minutu barru" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) hilabete barru" + "(\\d++[.,]?\\d*+) hilabete barru" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) segundo barru" + "(\\d++[.,]?\\d*+) segundo barru" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) aste barru" + "(\\d++[.,]?\\d*+) aste barru" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) urte barru" + "(\\d++[.,]?\\d*+) urte barru" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/ewo.py b/dateparser/data/date_translation_data/ewo.py index 62c3afc0c..39c599a6e 100644 --- a/dateparser/data/date_translation_data/ewo.py +++ b/dateparser/data/date_translation_data/ewo.py @@ -96,7 +96,8 @@ "amǒs" ], "hour": [ - "awola" + "awola", + "hr" ], "minute": [ "enútɛn" diff --git a/dateparser/data/date_translation_data/fa.py b/dateparser/data/date_translation_data/fa.py index 8fa28ceaf..bc4a50c98 100644 --- a/dateparser/data/date_translation_data/fa.py +++ b/dateparser/data/date_translation_data/fa.py @@ -136,8 +136,8 @@ "دیروز" ], "1 month ago": [ - "ماه پیش", - "ماه گذشته" + "ماه گذشته", + "ماه پیش" ], "1 week ago": [ "هفتهٔ گذشته" @@ -160,46 +160,47 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) روز پیش" + "(\\d++[.,]?\\d*+) روز پیش" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) ساعت پیش" + "(\\d++[.,]?\\d*+) ساعت پیش" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) دقیقه پیش" + "(\\d++[.,]?\\d*+) دقیقه پیش" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) ماه پیش" + "(\\d++[.,]?\\d*+) ماه پیش" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) ثانیه پیش" + "(\\d++[.,]?\\d*+) ثانیه پیش" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) هفته پیش" + "(\\d++[.,]?\\d*+) هفته پیش" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) سال پیش" + "(\\d++[.,]?\\d*+) سال پیش" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) روز بعد" + "(\\d++[.,]?\\d*+) روز بعد", + "(\\d++[.,]?\\d*+) روز دیگر" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) ساعت بعد" + "(\\d++[.,]?\\d*+) ساعت بعد" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) دقیقه بعد" + "(\\d++[.,]?\\d*+) دقیقه بعد" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) ماه بعد" + "(\\d++[.,]?\\d*+) ماه بعد" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) ثانیه بعد" + "(\\d++[.,]?\\d*+) ثانیه بعد" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) هفته بعد" + "(\\d++[.,]?\\d*+) هفته بعد" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) سال بعد" + "(\\d++[.,]?\\d*+) سال بعد" ] }, "locale_specific": { diff --git a/dateparser/data/date_translation_data/ff.py b/dateparser/data/date_translation_data/ff.py index 3e684a39e..02712b9d7 100644 --- a/dateparser/data/date_translation_data/ff.py +++ b/dateparser/data/date_translation_data/ff.py @@ -96,6 +96,7 @@ "ñalnde" ], "hour": [ + "hr", "waktu" ], "minute": [ diff --git a/dateparser/data/date_translation_data/fi.py b/dateparser/data/date_translation_data/fi.py index 3b8f7646e..0ad5f611b 100644 --- a/dateparser/data/date_translation_data/fi.py +++ b/dateparser/data/date_translation_data/fi.py @@ -158,6 +158,7 @@ ], "hour": [ "t", + "tunnit", "tunti", "tuntia", "tunnin" @@ -250,72 +251,73 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) pv sitten", - "(\\d+[.,]?\\d*) päivä sitten", - "(\\d+[.,]?\\d*) päivää sitten" + "(\\d++[.,]?\\d*+) pv sitten", + "(\\d++[.,]?\\d*+) päivä sitten", + "(\\d++[.,]?\\d*+) päivää sitten" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) t sitten", - "(\\d+[.,]?\\d*) tunti sitten", - "(\\d+[.,]?\\d*) tuntia sitten" + "(\\d++[.,]?\\d*+) t sitten", + "(\\d++[.,]?\\d*+) tunti sitten", + "(\\d++[.,]?\\d*+) tuntia sitten" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) min sitten", - "(\\d+[.,]?\\d*) minuutti sitten", - "(\\d+[.,]?\\d*) minuuttia sitten" + "(\\d++[.,]?\\d*+) min sitten", + "(\\d++[.,]?\\d*+) minuutti sitten", + "(\\d++[.,]?\\d*+) minuuttia sitten" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) kk sitten", - "(\\d+[.,]?\\d*) kuukausi sitten", - "(\\d+[.,]?\\d*) kuukautta sitten" + "(\\d++[.,]?\\d*+) kk sitten", + "(\\d++[.,]?\\d*+) kuukausi sitten", + "(\\d++[.,]?\\d*+) kuukautta sitten" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) s sitten", - "(\\d+[.,]?\\d*) sekunti sitten", - "(\\d+[.,]?\\d*) sekuntia sitten" + "(\\d++[.,]?\\d*+) s sitten", + "(\\d++[.,]?\\d*+) sekunti sitten", + "(\\d++[.,]?\\d*+) sekuntia sitten" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) viikko sitten", - "(\\d+[.,]?\\d*) viikkoa sitten", - "(\\d+[.,]?\\d*) vk sitten" + "(\\d++[.,]?\\d*+) viikko sitten", + "(\\d++[.,]?\\d*+) viikkoa sitten", + "(\\d++[.,]?\\d*+) vk sitten" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) v sitten", - "(\\d+[.,]?\\d*) vuosi sitten", - "(\\d+[.,]?\\d*) vuotta sitten" + "(\\d++[.,]?\\d*+) v sitten", + "(\\d++[.,]?\\d*+) vuosi sitten", + "(\\d++[.,]?\\d*+) vuotta sitten" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) pv päästä", - "(\\d+[.,]?\\d*) päivän päästä" + "(\\d++[.,]?\\d*+) pv päästä", + "(\\d++[.,]?\\d*+) päivän päästä" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) t päästä", - "(\\d+[.,]?\\d*) tunnin päästä" + "(\\d++[.,]?\\d*+) t päästä", + "(\\d++[.,]?\\d*+) tunnin päästä" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) min päästä", - "(\\d+[.,]?\\d*) minuutin päästä" + "(\\d++[.,]?\\d*+) min päästä", + "(\\d++[.,]?\\d*+) minuutin päästä" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) kk päästä", - "(\\d+[.,]?\\d*) kuukauden päästä" + "(\\d++[.,]?\\d*+) kk päästä", + "(\\d++[.,]?\\d*+) kuukauden päästä" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) s päästä", - "(\\d+[.,]?\\d*) sekunnin päästä" + "(\\d++[.,]?\\d*+) s päästä", + "(\\d++[.,]?\\d*+) sekunnin päästä" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) viikon päästä", - "(\\d+[.,]?\\d*) vk päästä" + "(\\d++[.,]?\\d*+) viikon päästä", + "(\\d++[.,]?\\d*+) vk päästä" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) v päästä", - "(\\d+[.,]?\\d*) vuoden päästä" + "(\\d++[.,]?\\d*+) v päästä", + "(\\d++[.,]?\\d*+) vuoden päästä" ] }, "locale_specific": {}, "skip": [ ":n", + "klo", " ", "'", ",", @@ -339,7 +341,22 @@ ], "simplifications": [ { - "(\\d+[.,]?\\d*) (sekunnin|sekuntin|minuutin|tunnin|päivän|viikon|kuukauden|vuoden) (päästä|kuluttua)": "\\3 \\1 \\2" + "(\\d++[.,]?\\d*+) (sekunnin|sekuntin|minuutin|tunnin|päivän|viikon|kuukauden|vuoden) (päästä|kuluttua)": "\\3 \\1 \\2" + }, + { + "(?<=[^\\d]\\s+|^)viikko(?=\\s+sitten)": "1 viikko" + }, + { + "(?<=[^\\d]\\s+|^)kuukausi(?=\\s+sitten)": "1 kuukausi" + }, + { + "(?<=[^\\d]\\s+|^)vuosi(?=\\s+sitten)": "1 vuosi" + }, + { + "(?<=[^\\d]\\s+|^)päivä(?=\\s+sitten)": "1 päivä" + }, + { + "(?<=[^\\d]\\s+|^)tunti(?=\\s+sitten)": "1 tunti" } ] } diff --git a/dateparser/data/date_translation_data/fil.py b/dateparser/data/date_translation_data/fil.py index e2e598803..465e829c6 100644 --- a/dateparser/data/date_translation_data/fil.py +++ b/dateparser/data/date_translation_data/fil.py @@ -96,6 +96,7 @@ "araw" ], "hour": [ + "mga oras", "oras" ], "minute": [ @@ -157,52 +158,52 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) araw ang nakalipas" + "(\\d++[.,]?\\d*+) araw ang nakalipas" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) oras ang nakalipas", - "(\\d+[.,]?\\d*) oras nakalipas" + "(\\d++[.,]?\\d*+) oras ang nakalipas", + "(\\d++[.,]?\\d*+) oras nakalipas" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) min ang nakalipas", - "(\\d+[.,]?\\d*) minuto ang nakalipas" + "(\\d++[.,]?\\d*+) min ang nakalipas", + "(\\d++[.,]?\\d*+) minuto ang nakalipas" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) buwan ang nakalipas" + "(\\d++[.,]?\\d*+) buwan ang nakalipas" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) seg ang nakalipas", - "(\\d+[.,]?\\d*) seg nakalipas", - "(\\d+[.,]?\\d*) segundo ang nakalipas" + "(\\d++[.,]?\\d*+) seg ang nakalipas", + "(\\d++[.,]?\\d*+) segundo ang nakalipas", + "(\\d++[.,]?\\d*+) seg nakalipas" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) linggo ang nakalipas" + "(\\d++[.,]?\\d*+) linggo ang nakalipas" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) taon ang nakalipas" + "(\\d++[.,]?\\d*+) taon ang nakalipas" ], "in \\1 day": [ - "sa (\\d+[.,]?\\d*) araw" + "sa (\\d++[.,]?\\d*+) araw" ], "in \\1 hour": [ - "sa (\\d+[.,]?\\d*) oras" + "sa (\\d++[.,]?\\d*+) oras" ], "in \\1 minute": [ - "sa (\\d+[.,]?\\d*) min", - "sa (\\d+[.,]?\\d*) minuto" + "sa (\\d++[.,]?\\d*+) min", + "sa (\\d++[.,]?\\d*+) minuto" ], "in \\1 month": [ - "sa (\\d+[.,]?\\d*) buwan" + "sa (\\d++[.,]?\\d*+) buwan" ], "in \\1 second": [ - "sa (\\d+[.,]?\\d*) seg", - "sa (\\d+[.,]?\\d*) segundo" + "sa (\\d++[.,]?\\d*+) seg", + "sa (\\d++[.,]?\\d*+) segundo" ], "in \\1 week": [ - "sa (\\d+[.,]?\\d*) linggo" + "sa (\\d++[.,]?\\d*+) linggo" ], "in \\1 year": [ - "sa (\\d+[.,]?\\d*) taon" + "sa (\\d++[.,]?\\d*+) taon" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/fo.py b/dateparser/data/date_translation_data/fo.py index d1ffe66a2..c3a4ed4e3 100644 --- a/dateparser/data/date_translation_data/fo.py +++ b/dateparser/data/date_translation_data/fo.py @@ -101,6 +101,7 @@ ], "hour": [ "t", + "tímar", "tími" ], "minute": [ @@ -124,12 +125,15 @@ "hendan minuttin" ], "0 month ago": [ + "henda mnð", "henda mánaðin" ], "0 second ago": [ "nú" ], "0 week ago": [ + "hesu v", + "hesu vi", "hesu viku" ], "0 year ago": [ @@ -139,9 +143,12 @@ "í gjár" ], "1 month ago": [ + "seinasta mnð", "seinasta mánað" ], "1 week ago": [ + "seinastu v", + "seinastu vi", "seinastu viku" ], "1 year ago": [ @@ -151,9 +158,12 @@ "í morgin" ], "in 1 month": [ + "næsta mnð", "næsta mánað" ], "in 1 week": [ + "næstu v", + "næstu vi", "næstu viku" ], "in 1 year": [ @@ -162,76 +172,76 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) d síðan", - "(\\d+[.,]?\\d*) da síðan", - "(\\d+[.,]?\\d*) dagar síðan", - "(\\d+[.,]?\\d*) dagur síðan" + "(\\d++[.,]?\\d*+) d síðan", + "(\\d++[.,]?\\d*+) da síðan", + "(\\d++[.,]?\\d*+) dagar síðan", + "(\\d++[.,]?\\d*+) dagur síðan" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) t síðan", - "(\\d+[.,]?\\d*) tímar síðan", - "(\\d+[.,]?\\d*) tími síðan" + "(\\d++[.,]?\\d*+) t síðan", + "(\\d++[.,]?\\d*+) tímar síðan", + "(\\d++[.,]?\\d*+) tími síðan" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) m síðan", - "(\\d+[.,]?\\d*) min síðan", - "(\\d+[.,]?\\d*) minutt síðan", - "(\\d+[.,]?\\d*) minuttir síðan" + "(\\d++[.,]?\\d*+) m síðan", + "(\\d++[.,]?\\d*+) min síðan", + "(\\d++[.,]?\\d*+) minutt síðan", + "(\\d++[.,]?\\d*+) minuttir síðan" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) mnð síðan", - "(\\d+[.,]?\\d*) mánað síðan", - "(\\d+[.,]?\\d*) mánaðir síðan" + "(\\d++[.,]?\\d*+) mnð síðan", + "(\\d++[.,]?\\d*+) mánað síðan", + "(\\d++[.,]?\\d*+) mánaðir síðan" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) s síðan", - "(\\d+[.,]?\\d*) sek síðan", - "(\\d+[.,]?\\d*) sekund síðan" + "(\\d++[.,]?\\d*+) s síðan", + "(\\d++[.,]?\\d*+) sek síðan", + "(\\d++[.,]?\\d*+) sekund síðan" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) v síðan", - "(\\d+[.,]?\\d*) vi síðan", - "(\\d+[.,]?\\d*) vika síðan", - "(\\d+[.,]?\\d*) vikur síðan" + "(\\d++[.,]?\\d*+) v síðan", + "(\\d++[.,]?\\d*+) vi síðan", + "(\\d++[.,]?\\d*+) vika síðan", + "(\\d++[.,]?\\d*+) vikur síðan" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) ár síðan" + "(\\d++[.,]?\\d*+) ár síðan" ], "in \\1 day": [ - "um (\\d+[.,]?\\d*) d", - "um (\\d+[.,]?\\d*) da", - "um (\\d+[.,]?\\d*) dag", - "um (\\d+[.,]?\\d*) dagar" + "um (\\d++[.,]?\\d*+) d", + "um (\\d++[.,]?\\d*+) da", + "um (\\d++[.,]?\\d*+) dag", + "um (\\d++[.,]?\\d*+) dagar" ], "in \\1 hour": [ - "um (\\d+[.,]?\\d*) t", - "um (\\d+[.,]?\\d*) tíma", - "um (\\d+[.,]?\\d*) tímar" + "um (\\d++[.,]?\\d*+) t", + "um (\\d++[.,]?\\d*+) tíma", + "um (\\d++[.,]?\\d*+) tímar" ], "in \\1 minute": [ - "um (\\d+[.,]?\\d*) m", - "um (\\d+[.,]?\\d*) min", - "um (\\d+[.,]?\\d*) minutt", - "um (\\d+[.,]?\\d*) minuttir" + "um (\\d++[.,]?\\d*+) m", + "um (\\d++[.,]?\\d*+) min", + "um (\\d++[.,]?\\d*+) minutt", + "um (\\d++[.,]?\\d*+) minuttir" ], "in \\1 month": [ - "um (\\d+[.,]?\\d*) mnð", - "um (\\d+[.,]?\\d*) mánað", - "um (\\d+[.,]?\\d*) mánaðir" + "um (\\d++[.,]?\\d*+) mnð", + "um (\\d++[.,]?\\d*+) mánað", + "um (\\d++[.,]?\\d*+) mánaðir" ], "in \\1 second": [ - "um (\\d+[.,]?\\d*) s", - "um (\\d+[.,]?\\d*) sek", - "um (\\d+[.,]?\\d*) sekund" + "um (\\d++[.,]?\\d*+) s", + "um (\\d++[.,]?\\d*+) sek", + "um (\\d++[.,]?\\d*+) sekund" ], "in \\1 week": [ - "um (\\d+[.,]?\\d*) v", - "um (\\d+[.,]?\\d*) vi", - "um (\\d+[.,]?\\d*) viku", - "um (\\d+[.,]?\\d*) vikur" + "um (\\d++[.,]?\\d*+) v", + "um (\\d++[.,]?\\d*+) vi", + "um (\\d++[.,]?\\d*+) viku", + "um (\\d++[.,]?\\d*+) vikur" ], "in \\1 year": [ - "um (\\d+[.,]?\\d*) ár" + "um (\\d++[.,]?\\d*+) ár" ] }, "locale_specific": { diff --git a/dateparser/data/date_translation_data/fr.py b/dateparser/data/date_translation_data/fr.py index ee7f4c5ba..9a8b315b0 100644 --- a/dateparser/data/date_translation_data/fr.py +++ b/dateparser/data/date_translation_data/fr.py @@ -116,6 +116,7 @@ "hour": [ "h", "heure", + "heures", "heures" ], "minute": [ @@ -183,75 +184,75 @@ }, "relative-type-regex": { "\\1 day ago": [ - "il y a (\\d+[.,]?\\d*) j", - "il y a (\\d+[.,]?\\d*) jour", - "il y a (\\d+[.,]?\\d*) jours" + "il y a (\\d++[.,]?\\d*+) j", + "il y a (\\d++[.,]?\\d*+) jour", + "il y a (\\d++[.,]?\\d*+) jours" ], "\\1 hour ago": [ - "il y a (\\d+[.,]?\\d*) h", - "il y a (\\d+[.,]?\\d*) heure", - "il y a (\\d+[.,]?\\d*) heures", - "il y a (\\d+[.,]?\\d*)h" + "il y a (\\d++[.,]?\\d*+) h", + "il y a (\\d++[.,]?\\d*+) heure", + "il y a (\\d++[.,]?\\d*+) heures", + "il y a (\\d++[.,]?\\d*+)h" ], "\\1 minute ago": [ - "il y a (\\d+[.,]?\\d*) min", - "il y a (\\d+[.,]?\\d*) minute", - "il y a (\\d+[.,]?\\d*) minutes", - "il y a (\\d+[.,]?\\d*)min" + "il y a (\\d++[.,]?\\d*+) min", + "il y a (\\d++[.,]?\\d*+) minute", + "il y a (\\d++[.,]?\\d*+) minutes", + "il y a (\\d++[.,]?\\d*+)min" ], "\\1 month ago": [ - "il y a (\\d+[.,]?\\d*) m", - "il y a (\\d+[.,]?\\d*) mois" + "il y a (\\d++[.,]?\\d*+) m", + "il y a (\\d++[.,]?\\d*+) mois" ], "\\1 second ago": [ - "il y a (\\d+[.,]?\\d*) s", - "il y a (\\d+[.,]?\\d*) seconde", - "il y a (\\d+[.,]?\\d*) secondes" + "il y a (\\d++[.,]?\\d*+) s", + "il y a (\\d++[.,]?\\d*+) seconde", + "il y a (\\d++[.,]?\\d*+) secondes" ], "\\1 week ago": [ - "il y a (\\d+[.,]?\\d*) sem", - "il y a (\\d+[.,]?\\d*) semaine", - "il y a (\\d+[.,]?\\d*) semaines" + "il y a (\\d++[.,]?\\d*+) sem", + "il y a (\\d++[.,]?\\d*+) semaine", + "il y a (\\d++[.,]?\\d*+) semaines" ], "\\1 year ago": [ - "il y a (\\d+[.,]?\\d*) a", - "il y a (\\d+[.,]?\\d*) an", - "il y a (\\d+[.,]?\\d*) ans" + "il y a (\\d++[.,]?\\d*+) a", + "il y a (\\d++[.,]?\\d*+) an", + "il y a (\\d++[.,]?\\d*+) ans" ], "in \\1 day": [ - "dans (\\d+[.,]?\\d*) j", - "dans (\\d+[.,]?\\d*) jour", - "dans (\\d+[.,]?\\d*) jours" + "dans (\\d++[.,]?\\d*+) j", + "dans (\\d++[.,]?\\d*+) jour", + "dans (\\d++[.,]?\\d*+) jours" ], "in \\1 hour": [ - "dans (\\d+[.,]?\\d*) h", - "dans (\\d+[.,]?\\d*) heure", - "dans (\\d+[.,]?\\d*) heures", - "dans (\\d+[.,]?\\d*)h" + "dans (\\d++[.,]?\\d*+) h", + "dans (\\d++[.,]?\\d*+) heure", + "dans (\\d++[.,]?\\d*+) heures", + "dans (\\d++[.,]?\\d*+)h" ], "in \\1 minute": [ - "dans (\\d+[.,]?\\d*) min", - "dans (\\d+[.,]?\\d*) minute", - "dans (\\d+[.,]?\\d*) minutes" + "dans (\\d++[.,]?\\d*+) min", + "dans (\\d++[.,]?\\d*+) minute", + "dans (\\d++[.,]?\\d*+) minutes" ], "in \\1 month": [ - "dans (\\d+[.,]?\\d*) m", - "dans (\\d+[.,]?\\d*) mois" + "dans (\\d++[.,]?\\d*+) m", + "dans (\\d++[.,]?\\d*+) mois" ], "in \\1 second": [ - "dans (\\d+[.,]?\\d*) s", - "dans (\\d+[.,]?\\d*) seconde", - "dans (\\d+[.,]?\\d*) secondes" + "dans (\\d++[.,]?\\d*+) s", + "dans (\\d++[.,]?\\d*+) seconde", + "dans (\\d++[.,]?\\d*+) secondes" ], "in \\1 week": [ - "dans (\\d+[.,]?\\d*) sem", - "dans (\\d+[.,]?\\d*) semaine", - "dans (\\d+[.,]?\\d*) semaines" + "dans (\\d++[.,]?\\d*+) sem", + "dans (\\d++[.,]?\\d*+) semaine", + "dans (\\d++[.,]?\\d*+) semaines" ], "in \\1 year": [ - "dans (\\d+[.,]?\\d*) a", - "dans (\\d+[.,]?\\d*) an", - "dans (\\d+[.,]?\\d*) ans" + "dans (\\d++[.,]?\\d*+) a", + "dans (\\d++[.,]?\\d*+) an", + "dans (\\d++[.,]?\\d*+) ans" ] }, "locale_specific": { @@ -466,22 +467,22 @@ "un": "1" }, { - "(\\d+[.,]?\\d*)\\s+h\\s+(\\d+[.,]?\\d*)\\s+min": "\\1h\\2m" + "(\\d++[.,]?\\d*+)\\s+h\\s+(\\d++[.,]?\\d*+)\\s+min": "\\1h\\2m" }, { - "(\\d+[.,]?\\d*)h(\\d+[.,]?\\d*)m?": "\\1:\\2" + "(\\d++[.,]?\\d*+)h(\\d++[.,]?\\d*+)m?": "\\1:\\2" }, { - "moins\\s(?:de\\s)?(\\d+[.,]?\\d*)\\s?(minute|seconde|heure)": "\\1 \\2" + "moins\\s(?:de\\s)?(\\d++[.,]?\\d*+)\\s?(minute|seconde|heure)": "\\1 \\2" }, { - "moins\\s(?:de\\s)?(\\d+[.,]?\\d*)\\s?s": "\\1 seconde" + "moins\\s(?:de\\s)?(\\d++[.,]?\\d*+)\\s?s": "\\1 seconde" }, { - "moins\\s(?:de\\s)?(\\d+[.,]?\\d*)\\s?m": "\\1 minute" + "moins\\s(?:de\\s)?(\\d++[.,]?\\d*+)\\s?m": "\\1 minute" }, { - "moins\\s(?:de\\s)?(\\d+[.,]?\\d*)\\s?h": "\\1 heure" + "moins\\s(?:de\\s)?(\\d++[.,]?\\d*+)\\s?h": "\\1 heure" }, { "deux": "2" diff --git a/dateparser/data/date_translation_data/fur.py b/dateparser/data/date_translation_data/fur.py index de6789147..7119b24e3 100644 --- a/dateparser/data/date_translation_data/fur.py +++ b/dateparser/data/date_translation_data/fur.py @@ -94,7 +94,8 @@ "dì" ], "hour": [ - "ore" + "ore", + "oris" ], "minute": [ "minût" @@ -151,58 +152,58 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) zornade indaûr", - "(\\d+[.,]?\\d*) zornadis indaûr" + "(\\d++[.,]?\\d*+) zornade indaûr", + "(\\d++[.,]?\\d*+) zornadis indaûr" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) ore indaûr", - "(\\d+[.,]?\\d*) oris indaûr" + "(\\d++[.,]?\\d*+) ore indaûr", + "(\\d++[.,]?\\d*+) oris indaûr" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) minût indaûr", - "(\\d+[.,]?\\d*) minûts indaûr" + "(\\d++[.,]?\\d*+) minût indaûr", + "(\\d++[.,]?\\d*+) minûts indaûr" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) mês indaûr" + "(\\d++[.,]?\\d*+) mês indaûr" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) secont indaûr", - "(\\d+[.,]?\\d*) seconts indaûr" + "(\\d++[.,]?\\d*+) secont indaûr", + "(\\d++[.,]?\\d*+) seconts indaûr" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) setemane indaûr", - "(\\d+[.,]?\\d*) setemanis indaûr" + "(\\d++[.,]?\\d*+) setemane indaûr", + "(\\d++[.,]?\\d*+) setemanis indaûr" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) agns indaûr", - "(\\d+[.,]?\\d*) an indaûr" + "(\\d++[.,]?\\d*+) agns indaûr", + "(\\d++[.,]?\\d*+) an indaûr" ], "in \\1 day": [ - "ca di (\\d+[.,]?\\d*) zornade", - "ca di (\\d+[.,]?\\d*) zornadis" + "ca di (\\d++[.,]?\\d*+) zornade", + "ca di (\\d++[.,]?\\d*+) zornadis" ], "in \\1 hour": [ - "ca di (\\d+[.,]?\\d*) ore", - "ca di (\\d+[.,]?\\d*) oris" + "ca di (\\d++[.,]?\\d*+) ore", + "ca di (\\d++[.,]?\\d*+) oris" ], "in \\1 minute": [ - "ca di (\\d+[.,]?\\d*) minût", - "ca di (\\d+[.,]?\\d*) minûts" + "ca di (\\d++[.,]?\\d*+) minût", + "ca di (\\d++[.,]?\\d*+) minûts" ], "in \\1 month": [ - "ca di (\\d+[.,]?\\d*) mês" + "ca di (\\d++[.,]?\\d*+) mês" ], "in \\1 second": [ - "ca di (\\d+[.,]?\\d*) secont", - "ca di (\\d+[.,]?\\d*) seconts" + "ca di (\\d++[.,]?\\d*+) secont", + "ca di (\\d++[.,]?\\d*+) seconts" ], "in \\1 week": [ - "ca di (\\d+[.,]?\\d*) setemane", - "ca di (\\d+[.,]?\\d*) setemanis" + "ca di (\\d++[.,]?\\d*+) setemane", + "ca di (\\d++[.,]?\\d*+) setemanis" ], "in \\1 year": [ - "ca di (\\d+[.,]?\\d*) agns", - "ca di (\\d+[.,]?\\d*) an" + "ca di (\\d++[.,]?\\d*+) agns", + "ca di (\\d++[.,]?\\d*+) an" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/fy.py b/dateparser/data/date_translation_data/fy.py index f79680119..075372e31 100644 --- a/dateparser/data/date_translation_data/fy.py +++ b/dateparser/data/date_translation_data/fy.py @@ -153,56 +153,56 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) dei lyn", - "(\\d+[.,]?\\d*) deien lyn" + "(\\d++[.,]?\\d*+) dei lyn", + "(\\d++[.,]?\\d*+) deien lyn" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) oere lyn" + "(\\d++[.,]?\\d*+) oere lyn" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) minuten lyn", - "(\\d+[.,]?\\d*) minút lyn" + "(\\d++[.,]?\\d*+) minuten lyn", + "(\\d++[.,]?\\d*+) minút lyn" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) moanne lyn", - "(\\d+[.,]?\\d*) moannen lyn" + "(\\d++[.,]?\\d*+) moanne lyn", + "(\\d++[.,]?\\d*+) moannen lyn" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) sekonde lyn", - "(\\d+[.,]?\\d*) sekonden lyn" + "(\\d++[.,]?\\d*+) sekonde lyn", + "(\\d++[.,]?\\d*+) sekonden lyn" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) wike lyn", - "(\\d+[.,]?\\d*) wiken lyn" + "(\\d++[.,]?\\d*+) wike lyn", + "(\\d++[.,]?\\d*+) wiken lyn" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) jier lyn" + "(\\d++[.,]?\\d*+) jier lyn" ], "in \\1 day": [ - "oer (\\d+[.,]?\\d*) dei", - "oer (\\d+[.,]?\\d*) deien" + "oer (\\d++[.,]?\\d*+) dei", + "oer (\\d++[.,]?\\d*+) deien" ], "in \\1 hour": [ - "oer (\\d+[.,]?\\d*) oere" + "oer (\\d++[.,]?\\d*+) oere" ], "in \\1 minute": [ - "oer (\\d+[.,]?\\d*) minuten", - "oer (\\d+[.,]?\\d*) minút" + "oer (\\d++[.,]?\\d*+) minuten", + "oer (\\d++[.,]?\\d*+) minút" ], "in \\1 month": [ - "oer (\\d+[.,]?\\d*) moanne", - "oer (\\d+[.,]?\\d*) moannen" + "oer (\\d++[.,]?\\d*+) moanne", + "oer (\\d++[.,]?\\d*+) moannen" ], "in \\1 second": [ - "oer (\\d+[.,]?\\d*) sekonde", - "oer (\\d+[.,]?\\d*) sekonden" + "oer (\\d++[.,]?\\d*+) sekonde", + "oer (\\d++[.,]?\\d*+) sekonden" ], "in \\1 week": [ - "oer (\\d+[.,]?\\d*) wike", - "oer (\\d+[.,]?\\d*) wiken" + "oer (\\d++[.,]?\\d*+) wike", + "oer (\\d++[.,]?\\d*+) wiken" ], "in \\1 year": [ - "oer (\\d+[.,]?\\d*) jier" + "oer (\\d++[.,]?\\d*+) jier" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/ga.py b/dateparser/data/date_translation_data/ga.py index daa9b4904..54936ca51 100644 --- a/dateparser/data/date_translation_data/ga.py +++ b/dateparser/data/date_translation_data/ga.py @@ -76,9 +76,11 @@ "dé domhnaigh" ], "am": [ + "rn", "am" ], "pm": [ + "in", "pm" ], "year": [ @@ -130,6 +132,8 @@ "an tseachtain seo" ], "0 year ago": [ + "i mbl", + "i mbliana", "an bhl seo", "an bhliain seo" ], @@ -163,64 +167,71 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) lá ó shin" + "(\\d++[.,]?\\d*+) lá ó shin" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) uair an chloig ó shin", - "(\\d+[.,]?\\d*) uair ó shin" + "(\\d++[.,]?\\d*+) uair an chloig ó shin", + "(\\d++[.,]?\\d*+) uair ó shin" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) nóim ó shin", - "(\\d+[.,]?\\d*) nóiméad ó shin" + "(\\d++[.,]?\\d*+) nóim ó shin", + "(\\d++[.,]?\\d*+) nóiméad ó shin" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) mhí ó shin", - "(\\d+[.,]?\\d*) mí ó shin" + "(\\d++[.,]?\\d*+) mhí ó shin", + "(\\d++[.,]?\\d*+) mí ó shin" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) soic ó shin", - "(\\d+[.,]?\\d*) soicind ó shin" + "(\\d++[.,]?\\d*+) soic ó shin", + "(\\d++[.,]?\\d*+) soicind ó shin" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) scht ó shin", - "(\\d+[.,]?\\d*) seachtain ó shin" + "(\\d++[.,]?\\d*+) scht ó shin", + "(\\d++[.,]?\\d*+) seachtain ó shin" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) bhl ó shin", - "(\\d+[.,]?\\d*) bhliain ó shin", - "(\\d+[.,]?\\d*) bl ó shin", - "(\\d+[.,]?\\d*) bliain ó shin" + "(\\d++[.,]?\\d*+) bhl ó shin", + "(\\d++[.,]?\\d*+) bhliain ó shin", + "(\\d++[.,]?\\d*+) bl ó shin", + "(\\d++[.,]?\\d*+) bliain ó shin" ], "in \\1 day": [ - "i gceann (\\d+[.,]?\\d*) lá" + "i gceann (\\d++[.,]?\\d*+) lá" ], "in \\1 hour": [ - "i gceann (\\d+[.,]?\\d*) uair", - "i gceann (\\d+[.,]?\\d*) uair an chloig" + "i gceann (\\d++[.,]?\\d*+) uair", + "i gceann (\\d++[.,]?\\d*+) uair an chloig" ], "in \\1 minute": [ - "i gceann (\\d+[.,]?\\d*) nóim", - "i gceann (\\d+[.,]?\\d*) nóiméad" + "i gceann (\\d++[.,]?\\d*+) nóim", + "i gceann (\\d++[.,]?\\d*+) nóiméad" ], "in \\1 month": [ - "i gceann (\\d+[.,]?\\d*) mhí", - "i gceann (\\d+[.,]?\\d*) mí" + "i gceann (\\d++[.,]?\\d*+) mhí", + "i gceann (\\d++[.,]?\\d*+) mí", + "i gceann (\\d++[.,]?\\d*+) míosa" ], "in \\1 second": [ - "i gceann (\\d+[.,]?\\d*) soic", - "i gceann (\\d+[.,]?\\d*) soicind" + "i gceann (\\d++[.,]?\\d*+) soic", + "i gceann (\\d++[.,]?\\d*+) soicind" ], "in \\1 week": [ - "i gceann (\\d+[.,]?\\d*) scht", - "i gceann (\\d+[.,]?\\d*) seachtain" + "i gceann (\\d++[.,]?\\d*+) scht", + "i gceann (\\d++[.,]?\\d*+) seachtain", + "i gceann (\\d++[.,]?\\d*+) seachtaine" ], "in \\1 year": [ - "i gceann (\\d+[.,]?\\d*) bhliain", - "i gceann (\\d+[.,]?\\d*) bl", - "i gceann (\\d+[.,]?\\d*) bliain" + "i gceann (\\d++[.,]?\\d*+) bl", + "i gceann (\\d++[.,]?\\d*+) bliain", + "i gceann (\\d++[.,]?\\d*+) bliana", + "i gceann (\\d++[.,]?\\d*+) bhliain" ] }, - "locale_specific": {}, + "locale_specific": { + "ga-GB": { + "name": "ga-GB" + } + }, "skip": [ " ", "'", diff --git a/dateparser/data/date_translation_data/gd.py b/dateparser/data/date_translation_data/gd.py index 83660ecf8..d005f8317 100644 --- a/dateparser/data/date_translation_data/gd.py +++ b/dateparser/data/date_translation_data/gd.py @@ -132,9 +132,15 @@ "an-diugh" ], "0 hour ago": [ + "am broinn uair", + "am broinn uair a thìde", + "san uair", "this hour" ], "0 minute ago": [ + "am broinn mion", + "am broinn mionaid", + "sa mhion", "this minute" ], "0 month ago": [ @@ -189,74 +195,74 @@ }, "relative-type-regex": { "\\1 day ago": [ - "o (\\d+[.,]?\\d*) là", - "(\\d+[.,]?\\d*) latha air ais" + "o (\\d++[.,]?\\d*+) là", + "(\\d++[.,]?\\d*+) latha air ais" ], "\\1 hour ago": [ - "o (\\d+[.,]?\\d*) uair", - "(\\d+[.,]?\\d*) uair a thìde air ais" + "o (\\d++[.,]?\\d*+) uair", + "(\\d++[.,]?\\d*+) uair a thìde air ais" ], "\\1 minute ago": [ - "o (\\d+[.,]?\\d*) mhion", - "o (\\d+[.,]?\\d*) mion", - "(\\d+[.,]?\\d*) mhionaid air ais", - "(\\d+[.,]?\\d*) mionaid air ais" + "o (\\d++[.,]?\\d*+) mhion", + "o (\\d++[.,]?\\d*+) mion", + "(\\d++[.,]?\\d*+) mhionaid air ais", + "(\\d++[.,]?\\d*+) mionaid air ais" ], "\\1 month ago": [ - "o (\\d+[.,]?\\d*) mhìos", - "o (\\d+[.,]?\\d*) mìos", - "(\\d+[.,]?\\d*) mhìos air ais", - "(\\d+[.,]?\\d*) mìos air ais" + "o (\\d++[.,]?\\d*+) mhìos", + "o (\\d++[.,]?\\d*+) mìos", + "(\\d++[.,]?\\d*+) mhìos air ais", + "(\\d++[.,]?\\d*+) mìos air ais" ], "\\1 second ago": [ - "o (\\d+[.,]?\\d*) diog", - "(\\d+[.,]?\\d*) diog air ais" + "o (\\d++[.,]?\\d*+) diog", + "(\\d++[.,]?\\d*+) diog air ais" ], "\\1 week ago": [ - "o (\\d+[.,]?\\d*) seachd", - "o (\\d+[.,]?\\d*) sheachd", - "(\\d+[.,]?\\d*) seachdain air ais" + "o (\\d++[.,]?\\d*+) seachd", + "o (\\d++[.,]?\\d*+) sheachd", + "(\\d++[.,]?\\d*+) seachdain air ais" ], "\\1 year ago": [ - "o (\\d+[.,]?\\d*) bhlia", - "o (\\d+[.,]?\\d*) blia", - "(\\d+[.,]?\\d*) bhliadhna air ais", - "(\\d+[.,]?\\d*) bliadhna air ais" + "o (\\d++[.,]?\\d*+) bhlia", + "o (\\d++[.,]?\\d*+) blia", + "(\\d++[.,]?\\d*+) bhliadhna air ais", + "(\\d++[.,]?\\d*+) bliadhna air ais" ], "in \\1 day": [ - "an ceann (\\d+[.,]?\\d*) latha", - "an (\\d+[.,]?\\d*) là" + "an ceann (\\d++[.,]?\\d*+) latha", + "an (\\d++[.,]?\\d*+) là" ], "in \\1 hour": [ - "an ceann (\\d+[.,]?\\d*) uair a thìde", - "an (\\d+[.,]?\\d*) uair" + "an ceann (\\d++[.,]?\\d*+) uair a thìde", + "an (\\d++[.,]?\\d*+) uair" ], "in \\1 minute": [ - "an ceann (\\d+[.,]?\\d*) mhionaid", - "an ceann (\\d+[.,]?\\d*) mionaid", - "an (\\d+[.,]?\\d*) mhion", - "an (\\d+[.,]?\\d*) mion" + "an ceann (\\d++[.,]?\\d*+) mhionaid", + "an ceann (\\d++[.,]?\\d*+) mionaid", + "an (\\d++[.,]?\\d*+) mhion", + "an (\\d++[.,]?\\d*+) mion" ], "in \\1 month": [ - "an ceann (\\d+[.,]?\\d*) mhìosa", - "an ceann (\\d+[.,]?\\d*) mìosa", - "an (\\d+[.,]?\\d*) mhìos", - "an (\\d+[.,]?\\d*) mìos" + "an ceann (\\d++[.,]?\\d*+) mhìosa", + "an ceann (\\d++[.,]?\\d*+) mìosa", + "an (\\d++[.,]?\\d*+) mhìos", + "an (\\d++[.,]?\\d*+) mìos" ], "in \\1 second": [ - "an ceann (\\d+[.,]?\\d*) diog", - "an (\\d+[.,]?\\d*) diog" + "an ceann (\\d++[.,]?\\d*+) diog", + "an (\\d++[.,]?\\d*+) diog" ], "in \\1 week": [ - "an ceann (\\d+[.,]?\\d*) seachdain", - "an (\\d+[.,]?\\d*) seachd", - "an (\\d+[.,]?\\d*) sheachd" + "an ceann (\\d++[.,]?\\d*+) seachdain", + "an (\\d++[.,]?\\d*+) seachd", + "an (\\d++[.,]?\\d*+) sheachd" ], "in \\1 year": [ - "an ceann (\\d+[.,]?\\d*) bhliadhna", - "an ceann (\\d+[.,]?\\d*) bliadhna", - "an (\\d+[.,]?\\d*) bhlia", - "an (\\d+[.,]?\\d*) blia" + "an ceann (\\d++[.,]?\\d*+) bhliadhna", + "an ceann (\\d++[.,]?\\d*+) bliadhna", + "an (\\d++[.,]?\\d*+) bhlia", + "an (\\d++[.,]?\\d*+) blia" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/gl.py b/dateparser/data/date_translation_data/gl.py index 367412444..4fec9f64e 100644 --- a/dateparser/data/date_translation_data/gl.py +++ b/dateparser/data/date_translation_data/gl.py @@ -81,24 +81,25 @@ "pm" ], "year": [ - "a", - "ano" + "ano", + "a" ], "month": [ - "m", - "mes" + "mes", + "m" ], "week": [ "sem", "semana" ], "day": [ - "d", - "día" + "día", + "d" ], "hour": [ "h", - "hora" + "hora", + "horas" ], "minute": [ "min", @@ -113,14 +114,16 @@ "hoxe" ], "0 hour ago": [ + "esta hora", "nesta hora" ], "0 minute ago": [ + "este minuto", "neste minuto" ], "0 month ago": [ - "este m", - "este mes" + "este mes", + "este m" ], "0 second ago": [ "agora" @@ -136,106 +139,125 @@ "onte" ], "1 month ago": [ - "m pasado", - "o mes pasado" + "o mes pas", + "o mes pasado", + "m pasado" ], "1 week ago": [ + "a sem pas", + "a sem pasada", "a semana pasada", "sem pasada" ], "1 year ago": [ - "ano pasado", - "o ano pasado" + "o ano pas", + "o ano pasado", + "ano pasado" ], "in 1 day": [ "mañá" ], "in 1 month": [ - "m seguinte", - "o próximo mes" + "o próx mes", + "o próximo mes", + "m seguinte" ], "in 1 week": [ + "a próx sem", + "a próxima sem", "a próxima semana", "sem seguinte" ], "in 1 year": [ + "o próx ano", "o próximo ano", "seguinte ano" ] }, "relative-type-regex": { "\\1 day ago": [ - "hai (\\d+[.,]?\\d*) d", - "hai (\\d+[.,]?\\d*) día", - "hai (\\d+[.,]?\\d*) días" + "hai (\\d++[.,]?\\d*+) día", + "hai (\\d++[.,]?\\d*+) días", + "hai (\\d++[.,]?\\d*+) d" ], "\\1 hour ago": [ - "hai (\\d+[.,]?\\d*) h", - "hai (\\d+[.,]?\\d*) hora", - "hai (\\d+[.,]?\\d*) horas" + "hai (\\d++[.,]?\\d*+) h", + "hai (\\d++[.,]?\\d*+) hora", + "hai (\\d++[.,]?\\d*+) horas" ], "\\1 minute ago": [ - "hai (\\d+[.,]?\\d*) min", - "hai (\\d+[.,]?\\d*) minuto", - "hai (\\d+[.,]?\\d*) minutos" + "hai (\\d++[.,]?\\d*+) min", + "hai (\\d++[.,]?\\d*+) minuto", + "hai (\\d++[.,]?\\d*+) minutos" ], "\\1 month ago": [ - "hai (\\d+[.,]?\\d*) m", - "hai (\\d+[.,]?\\d*) mes", - "hai (\\d+[.,]?\\d*) meses" + "hai (\\d++[.,]?\\d*+) mes", + "hai (\\d++[.,]?\\d*+) meses", + "hai (\\d++[.,]?\\d*+) m" ], "\\1 second ago": [ - "hai (\\d+[.,]?\\d*) s", - "hai (\\d+[.,]?\\d*) segundo", - "hai (\\d+[.,]?\\d*) segundos" + "hai (\\d++[.,]?\\d*+) s", + "hai (\\d++[.,]?\\d*+) segundo", + "hai (\\d++[.,]?\\d*+) segundos" ], "\\1 week ago": [ - "hai (\\d+[.,]?\\d*) sem", - "hai (\\d+[.,]?\\d*) semana", - "hai (\\d+[.,]?\\d*) semanas" + "hai (\\d++[.,]?\\d*+) sem", + "hai (\\d++[.,]?\\d*+) semana", + "hai (\\d++[.,]?\\d*+) semanas" ], "\\1 year ago": [ - "hai (\\d+[.,]?\\d*) a", - "hai (\\d+[.,]?\\d*) ano", - "hai (\\d+[.,]?\\d*) anos" + "hai (\\d++[.,]?\\d*+) ano", + "hai (\\d++[.,]?\\d*+) anos", + "hai (\\d++[.,]?\\d*+) a" ], "in \\1 day": [ - "en (\\d+[.,]?\\d*) d", - "en (\\d+[.,]?\\d*) día", - "en (\\d+[.,]?\\d*) días" + "en (\\d++[.,]?\\d*+) día", + "en (\\d++[.,]?\\d*+) días", + "en (\\d++[.,]?\\d*+) d" ], "in \\1 hour": [ - "en (\\d+[.,]?\\d*) h", - "en (\\d+[.,]?\\d*) hora", - "en (\\d+[.,]?\\d*) horas" + "en (\\d++[.,]?\\d*+) h", + "en (\\d++[.,]?\\d*+) hora", + "en (\\d++[.,]?\\d*+) horas" ], "in \\1 minute": [ - "en (\\d+[.,]?\\d*) min", - "en (\\d+[.,]?\\d*) minuto", - "en (\\d+[.,]?\\d*) minutos" + "en (\\d++[.,]?\\d*+) min", + "en (\\d++[.,]?\\d*+) minuto", + "en (\\d++[.,]?\\d*+) minutos" ], "in \\1 month": [ - "en (\\d+[.,]?\\d*) m", - "en (\\d+[.,]?\\d*) mes", - "en (\\d+[.,]?\\d*) meses" + "en (\\d++[.,]?\\d*+) mes", + "en (\\d++[.,]?\\d*+) meses", + "en (\\d++[.,]?\\d*+) m" ], "in \\1 second": [ - "en (\\d+[.,]?\\d*) s", - "en (\\d+[.,]?\\d*) segundo", - "en (\\d+[.,]?\\d*) segundos" + "en (\\d++[.,]?\\d*+) s", + "en (\\d++[.,]?\\d*+) segundo", + "en (\\d++[.,]?\\d*+) segundos" ], "in \\1 week": [ - "en (\\d+[.,]?\\d*) sem", - "en (\\d+[.,]?\\d*) semana", - "en (\\d+[.,]?\\d*) semanas" + "en (\\d++[.,]?\\d*+) sem", + "en (\\d++[.,]?\\d*+) semana", + "en (\\d++[.,]?\\d*+) semanas" ], "in \\1 year": [ - "en (\\d+[.,]?\\d*) a", - "en (\\d+[.,]?\\d*) ano", - "en (\\d+[.,]?\\d*) anos" + "en (\\d++[.,]?\\d*+) ano", + "en (\\d++[.,]?\\d*+) anos", + "en (\\d++[.,]?\\d*+) a" ] }, "locale_specific": {}, + "early_morning": [ + "de madrugada", + "na madrugada", + "pola madrugada", + "madrugada" + ], + "simplifications": [ + { + "esta madrugada": "hoxe madrugada" + } + ], "skip": [ " ", "'", diff --git a/dateparser/data/date_translation_data/gsw.py b/dateparser/data/date_translation_data/gsw.py index b0e6fa9dd..f1fbcfcf0 100644 --- a/dateparser/data/date_translation_data/gsw.py +++ b/dateparser/data/date_translation_data/gsw.py @@ -99,6 +99,7 @@ "tag" ], "hour": [ + "hr", "schtund" ], "minute": [ diff --git a/dateparser/data/date_translation_data/gu.py b/dateparser/data/date_translation_data/gu.py index 161fa15b2..52cc3bbce 100644 --- a/dateparser/data/date_translation_data/gu.py +++ b/dateparser/data/date_translation_data/gu.py @@ -153,49 +153,49 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) દિવસ પહેલાં" + "(\\d++[.,]?\\d*+) દિવસ પહેલાં" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) કલાક પહેલાં" + "(\\d++[.,]?\\d*+) કલાક પહેલાં" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) મિનિટ પહેલાં" + "(\\d++[.,]?\\d*+) મિનિટ પહેલાં" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) મહિના પહેલાં" + "(\\d++[.,]?\\d*+) મહિના પહેલાં" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) સેકંડ પહેલાં" + "(\\d++[.,]?\\d*+) સેકંડ પહેલાં" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) અઠ પહેલાં", - "(\\d+[.,]?\\d*) અઠવાડિયા પહેલાં" + "(\\d++[.,]?\\d*+) અઠ પહેલાં", + "(\\d++[.,]?\\d*+) અઠવાડિયા પહેલાં" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) વર્ષ પહેલા", - "(\\d+[.,]?\\d*) વર્ષ પહેલાં" + "(\\d++[.,]?\\d*+) વર્ષ પહેલાં", + "(\\d++[.,]?\\d*+) વર્ષ પહેલા" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) દિવસમાં" + "(\\d++[.,]?\\d*+) દિવસમાં" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) કલાકમાં" + "(\\d++[.,]?\\d*+) કલાકમાં" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) મિનિટમાં" + "(\\d++[.,]?\\d*+) મિનિટમાં" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) મહિનામાં" + "(\\d++[.,]?\\d*+) મહિનામાં" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) સેકંડમાં" + "(\\d++[.,]?\\d*+) સેકંડમાં" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) અઠ માં", - "(\\d+[.,]?\\d*) અઠવાડિયામાં" + "(\\d++[.,]?\\d*+) અઠ માં", + "(\\d++[.,]?\\d*+) અઠવાડિયામાં" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) વર્ષમાં" + "(\\d++[.,]?\\d*+) વર્ષમાં" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/guz.py b/dateparser/data/date_translation_data/guz.py index 68c32cd29..7cff5b47b 100644 --- a/dateparser/data/date_translation_data/guz.py +++ b/dateparser/data/date_translation_data/guz.py @@ -97,7 +97,8 @@ "rituko" ], "hour": [ - "ensa" + "ensa", + "hr" ], "minute": [ "edakika" diff --git a/dateparser/data/date_translation_data/gv.py b/dateparser/data/date_translation_data/gv.py index 88c3f5e54..341749fdb 100644 --- a/dateparser/data/date_translation_data/gv.py +++ b/dateparser/data/date_translation_data/gv.py @@ -93,7 +93,8 @@ "day" ], "hour": [ - "hour" + "hour", + "hr" ], "minute": [ "minute" diff --git a/dateparser/data/date_translation_data/ha.py b/dateparser/data/date_translation_data/ha.py index 8b40bb625..0e5e50c26 100644 --- a/dateparser/data/date_translation_data/ha.py +++ b/dateparser/data/date_translation_data/ha.py @@ -78,9 +78,13 @@ "lahadi" ], "am": [ + "safiya", + "sf", "am" ], "pm": [ + "yamma", + "ym", "pm" ], "year": [ @@ -96,7 +100,8 @@ "kwana" ], "hour": [ - "awa" + "awa", + "sa'o'i" ], "minute": [ "minti" @@ -109,48 +114,112 @@ "yau" ], "0 hour ago": [ + "wannan awa", "this hour" ], "0 minute ago": [ + "wannan mintin", "this minute" ], "0 month ago": [ + "wannan watan", "this month" ], "0 second ago": [ + "yanzu", "now" ], "0 week ago": [ + "wannan satin", "this week" ], "0 year ago": [ + "bana", "this year" ], "1 day ago": [ "jiya" ], "1 month ago": [ + "watan da ya gabata", "last month" ], "1 week ago": [ + "satin da ya gabata", "last week" ], "1 year ago": [ + "bara", "last year" ], "in 1 day": [ "gobe" ], "in 1 month": [ + "wata na gaba", "next month" ], "in 1 week": [ + "sati na gaba", "next week" ], "in 1 year": [ + "badi", "next year" ] }, + "relative-type-regex": { + "\\1 day ago": [ + "kwanaki da suka gabata (\\d++[.,]?\\d*+)", + "rana da ya gabata (\\d++[.,]?\\d*+)" + ], + "\\1 hour ago": [ + "(\\d++[.,]?\\d*+) awa da ya gabata" + ], + "\\1 minute ago": [ + "(\\d++[.,]?\\d*+) minti da ya gabata" + ], + "\\1 month ago": [ + "watan da ya gabata (\\d++[.,]?\\d*+)", + "watanni da suka gabata (\\d++[.,]?\\d*+)}" + ], + "\\1 second ago": [ + "(\\d++[.,]?\\d*+) dakika da ya gabata" + ], + "\\1 week ago": [ + "mako da suka gabata (\\d++[.,]?\\d*+)", + "mako da ya gabata (\\d++[.,]?\\d*+)", + "makonni da suka gabata (\\d++[.,]?\\d*+)" + ], + "\\1 year ago": [ + "shekara da suka gabata (\\d++[.,]?\\d*+)" + ], + "in \\1 day": [ + "a cikin kwanaki (\\d++[.,]?\\d*+)", + "a cikin rana (\\d++[.,]?\\d*+)" + ], + "in \\1 hour": [ + "cikin (\\d++[.,]?\\d*+) awa" + ], + "in \\1 minute": [ + "cikin (\\d++[.,]?\\d*+) minti" + ], + "in \\1 month": [ + "a cikin watan (\\d++[.,]?\\d*+)", + "a cikin watanni (\\d++[.,]?\\d*+)" + ], + "in \\1 second": [ + "cikin (\\d++[.,]?\\d*+) dakika" + ], + "in \\1 week": [ + "a cikin mako (\\d++[.,]?\\d*+)", + "a cikin makonni (\\d++[.,]?\\d*+)" + ], + "in \\1 year": [ + "a shekarar (\\d++[.,]?\\d*+)", + "a shekaru (\\d++[.,]?\\d*+)" + ] + }, "locale_specific": { "ha-GH": { "name": "ha-GH" diff --git a/dateparser/data/date_translation_data/haw.py b/dateparser/data/date_translation_data/haw.py index 6865f314c..1ec35ef54 100644 --- a/dateparser/data/date_translation_data/haw.py +++ b/dateparser/data/date_translation_data/haw.py @@ -95,7 +95,8 @@ "day" ], "hour": [ - "hour" + "hour", + "hr" ], "minute": [ "minute" diff --git a/dateparser/data/date_translation_data/he.py b/dateparser/data/date_translation_data/he.py index 1f6ce4cef..ff4d188a2 100644 --- a/dateparser/data/date_translation_data/he.py +++ b/dateparser/data/date_translation_data/he.py @@ -126,9 +126,11 @@ "יום א" ], "am": [ + "am", "לפנה״צ" ], "pm": [ + "pm", "אחה״צ" ], "year": [ @@ -155,6 +157,7 @@ ], "hour": [ "שעה", + "שעות", "שע׳", "שעות" ], @@ -177,7 +180,8 @@ "בשעה זו" ], "0 minute ago": [ - "בדקה זו" + "בדקה זו", + "דקה זו" ], "0 month ago": [ "החודש" @@ -218,60 +222,60 @@ }, "relative-type-regex": { "\\1 day ago": [ - "לפני (\\d+[.,]?\\d*) ימים", - "לפני (\\d+[.,]?\\d*) ימ׳", - "לפני יום (\\d+[.,]?\\d*)" + "לפני (\\d++[.,]?\\d*+) ימים", + "לפני יום (\\d++[.,]?\\d*+)", + "לפני (\\d++[.,]?\\d*+) ימ׳" ], "\\1 hour ago": [ - "לפני (\\d+[.,]?\\d*) שעות", - "לפני (\\d+[.,]?\\d*) שע׳" + "לפני (\\d++[.,]?\\d*+) שעות", + "לפני (\\d++[.,]?\\d*+) שע׳" ], "\\1 minute ago": [ - "לפני (\\d+[.,]?\\d*) דקות", - "לפני (\\d+[.,]?\\d*) דק׳" + "לפני (\\d++[.,]?\\d*+) דקות", + "לפני (\\d++[.,]?\\d*+) דק׳" ], "\\1 month ago": [ - "לפני (\\d+[.,]?\\d*) חודשים", - "לפני (\\d+[.,]?\\d*) חו׳" + "לפני (\\d++[.,]?\\d*+) חודשים", + "לפני (\\d++[.,]?\\d*+) חו׳" ], "\\1 second ago": [ - "לפני (\\d+[.,]?\\d*) שניות", - "לפני (\\d+[.,]?\\d*) שנ׳" + "לפני (\\d++[.,]?\\d*+) שניות", + "לפני (\\d++[.,]?\\d*+) שנ׳" ], "\\1 week ago": [ - "לפני (\\d+[.,]?\\d*) שבועות", - "לפני (\\d+[.,]?\\d*) שב׳" + "לפני (\\d++[.,]?\\d*+) שבועות", + "לפני (\\d++[.,]?\\d*+) שב׳" ], "\\1 year ago": [ - "לפני (\\d+[.,]?\\d*) שנים" + "לפני (\\d++[.,]?\\d*+) שנים" ], "in \\1 day": [ - "בעוד (\\d+[.,]?\\d*) ימים", - "בעוד (\\d+[.,]?\\d*) ימ׳", - "בעוד יום (\\d+[.,]?\\d*)" + "בעוד (\\d++[.,]?\\d*+) ימים", + "בעוד יום (\\d++[.,]?\\d*+)", + "בעוד (\\d++[.,]?\\d*+) ימ׳" ], "in \\1 hour": [ - "בעוד (\\d+[.,]?\\d*) שעות", - "בעוד (\\d+[.,]?\\d*) שע׳" + "בעוד (\\d++[.,]?\\d*+) שעות", + "בעוד (\\d++[.,]?\\d*+) שע׳" ], "in \\1 minute": [ - "בעוד (\\d+[.,]?\\d*) דקות", - "בעוד (\\d+[.,]?\\d*) דק׳" + "בעוד (\\d++[.,]?\\d*+) דקות", + "בעוד (\\d++[.,]?\\d*+) דק׳" ], "in \\1 month": [ - "בעוד (\\d+[.,]?\\d*) חודשים", - "בעוד (\\d+[.,]?\\d*) חו׳" + "בעוד (\\d++[.,]?\\d*+) חודשים", + "בעוד (\\d++[.,]?\\d*+) חו׳" ], "in \\1 second": [ - "בעוד (\\d+[.,]?\\d*) שניות", - "בעוד (\\d+[.,]?\\d*) שנ׳" + "בעוד (\\d++[.,]?\\d*+) שניות", + "בעוד (\\d++[.,]?\\d*+) שנ׳" ], "in \\1 week": [ - "בעוד (\\d+[.,]?\\d*) שבועות", - "בעוד (\\d+[.,]?\\d*) שב׳" + "בעוד (\\d++[.,]?\\d*+) שבועות", + "בעוד (\\d++[.,]?\\d*+) שב׳" ], "in \\1 year": [ - "בעוד (\\d+[.,]?\\d*) שנים" + "בעוד (\\d++[.,]?\\d*+) שנים" ] }, "locale_specific": {}, @@ -366,6 +370,24 @@ }, { "בערב": "pm" + }, + { + "(?<=לפני\\s+)שבוע\\b": "1 שבוע" + }, + { + "(?<=לפני\\s+)חודש\\b": "1 חודש" + }, + { + "(?<=לפני\\s+)שנה\\b": "1 שנה" + }, + { + "(?<=לפני\\s+)יום\\b": "1 יום" + }, + { + "(?<=לפני\\s+)שעה\\b": "1 שעה" + }, + { + "(?<=לפני\\s+)דקה\\b": "1 דקה" } ] } diff --git a/dateparser/data/date_translation_data/hi.py b/dateparser/data/date_translation_data/hi.py index eabe94bbf..976d40665 100644 --- a/dateparser/data/date_translation_data/hi.py +++ b/dateparser/data/date_translation_data/hi.py @@ -78,9 +78,11 @@ "रविवार" ], "am": [ + "am", "पूर्वाह्न" ], "pm": [ + "pm", "अपराह्न" ], "year": [ @@ -102,17 +104,20 @@ "दिवस" ], "hour": [ - "घं", "घंटा", - "घंटे" + "घंटे", + "घं॰", + "घंटे", + "घं" ], "minute": [ - "मि", - "मिनट" + "मिनट", + "मि॰", + "मि" ], "second": [ - "से", - "सेकंड" + "सेकंड", + "से॰" ], "relative-type": { "0 day ago": [ @@ -134,10 +139,12 @@ "इस सप्ताह" ], "0 year ago": [ - "इस वर्ष" + "इस वर्ष", + "इस साल" ], "1 day ago": [ - "कल" + "कल", + "बीता कल" ], "1 month ago": [ "पिछला माह" @@ -146,9 +153,11 @@ "पिछला सप्ताह" ], "1 year ago": [ - "पिछला वर्ष" + "पिछला वर्ष", + "पिछले साल" ], "in 1 day": [ + "आने वाला कल", "कल" ], "in 1 month": [ @@ -158,7 +167,8 @@ "अगला सप्ताह" ], "in 1 year": [ - "अगला वर्ष" + "अगला वर्ष", + "अगले साल" ], "2 day ago": [ "परसों" @@ -172,58 +182,64 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) दिन पहले" + "(\\d++[.,]?\\d*+) दिन पहले" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) घं पहले", - "(\\d+[.,]?\\d*) घंटे पहले" + "(\\d++[.,]?\\d*+) घंटे पहले", + "(\\d++[.,]?\\d*+) घं॰ पहले", + "(\\d++[.,]?\\d*+) घं पहले" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) मि पहले", - "(\\d+[.,]?\\d*) मिनट पहले" + "(\\d++[.,]?\\d*+) मिनट पहले", + "(\\d++[.,]?\\d*+) मि॰ पहले", + "(\\d++[.,]?\\d*+) मि पहले" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) माह पहले" + "(\\d++[.,]?\\d*+) माह पहले" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) से पहले", - "(\\d+[.,]?\\d*) सेकंड पहले" + "(\\d++[.,]?\\d*+) सेकंड पहले", + "(\\d++[.,]?\\d*+) से॰ पहले", + "(\\d++[.,]?\\d*+) से पहले" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) सप्ताह पहले" + "(\\d++[.,]?\\d*+) सप्ताह पहले" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) वर्ष पहले" + "(\\d++[.,]?\\d*+) वर्ष पहले" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) दिन में" + "(\\d++[.,]?\\d*+) दिन में" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) घं में", - "(\\d+[.,]?\\d*) घंटे में" + "(\\d++[.,]?\\d*+) घंटे में", + "(\\d++[.,]?\\d*+) घं॰ में", + "(\\d++[.,]?\\d*+) घं में" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) मि में", - "(\\d+[.,]?\\d*) मिनट में" + "(\\d++[.,]?\\d*+) मिनट में", + "(\\d++[.,]?\\d*+) मि॰ में", + "(\\d++[.,]?\\d*+) मि में" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) माह में" + "(\\d++[.,]?\\d*+) माह में" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) से में", - "(\\d+[.,]?\\d*) सेकंड में" + "(\\d++[.,]?\\d*+) सेकंड में", + "(\\d++[.,]?\\d*+) से॰ में", + "(\\d++[.,]?\\d*+) से में" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) सप्ताह में" + "(\\d++[.,]?\\d*+) सप्ताह में" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) वर्ष में" + "(\\d++[.,]?\\d*+) वर्ष में" ], "in \\1 decade": [ - "(\\d+[.,]?\\d*) दशक में" + "(\\d++[.,]?\\d*+) दशक में" ], "\\1 decade ago": [ - "(\\d+[.,]?\\d*) दशक पहले" + "(\\d++[.,]?\\d*+) दशक पहले" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/hr.py b/dateparser/data/date_translation_data/hr.py index 781c52cb4..b94d909fa 100644 --- a/dateparser/data/date_translation_data/hr.py +++ b/dateparser/data/date_translation_data/hr.py @@ -141,7 +141,8 @@ ], "hour": [ "h", - "sat" + "sat", + "sati" ], "minute": [ "min", @@ -261,88 +262,88 @@ }, "relative-type-regex": { "\\1 day ago": [ - "prije (\\d+[.,]?\\d*) d", - "prije (\\d+[.,]?\\d*) dan", - "prije (\\d+[.,]?\\d*) dana" + "prije (\\d++[.,]?\\d*+) d", + "prije (\\d++[.,]?\\d*+) dan", + "prije (\\d++[.,]?\\d*+) dana" ], "\\1 hour ago": [ - "prije (\\d+[.,]?\\d*) h", - "prije (\\d+[.,]?\\d*) sat", - "prije (\\d+[.,]?\\d*) sati", - "prije (\\d+[.,]?\\d*) sata" + "prije (\\d++[.,]?\\d*+) h", + "prije (\\d++[.,]?\\d*+) sat", + "prije (\\d++[.,]?\\d*+) sati", + "prije (\\d++[.,]?\\d*+) sata" ], "\\1 minute ago": [ - "prije (\\d+[.,]?\\d*) min", - "prije (\\d+[.,]?\\d*) minuta", - "prije (\\d+[.,]?\\d*) minutu", - "prije (\\d+[.,]?\\d*) minute" + "prije (\\d++[.,]?\\d*+) min", + "prije (\\d++[.,]?\\d*+) minuta", + "prije (\\d++[.,]?\\d*+) minutu", + "prije (\\d++[.,]?\\d*+) minute" ], "\\1 month ago": [ - "prije (\\d+[.,]?\\d*) mj", - "prije (\\d+[.,]?\\d*) mjesec", - "prije (\\d+[.,]?\\d*) mjeseci", - "prije (\\d+[.,]?\\d*) mjeseca" + "prije (\\d++[.,]?\\d*+) mj", + "prije (\\d++[.,]?\\d*+) mjesec", + "prije (\\d++[.,]?\\d*+) mjeseci", + "prije (\\d++[.,]?\\d*+) mjeseca" ], "\\1 second ago": [ - "prije (\\d+[.,]?\\d*) s", - "prije (\\d+[.,]?\\d*) sekundi", - "prije (\\d+[.,]?\\d*) sekundu", - "prije (\\d+[.,]?\\d*) sekunde", - "prije (\\d+[.,]?\\d*) sekundu" + "prije (\\d++[.,]?\\d*+) s", + "prije (\\d++[.,]?\\d*+) sekundi", + "prije (\\d++[.,]?\\d*+) sekundu", + "prije (\\d++[.,]?\\d*+) sekunde", + "prije (\\d++[.,]?\\d*+) sekundu" ], "\\1 week ago": [ - "prije (\\d+[.,]?\\d*) tj", - "prije (\\d+[.,]?\\d*) tjedan", - "prije (\\d+[.,]?\\d*) tjedana", - "prije (\\d+[.,]?\\d*) tjedna" + "prije (\\d++[.,]?\\d*+) tj", + "prije (\\d++[.,]?\\d*+) tjedan", + "prije (\\d++[.,]?\\d*+) tjedana", + "prije (\\d++[.,]?\\d*+) tjedna" ], "\\1 year ago": [ - "prije (\\d+[.,]?\\d*) g", - "prije (\\d+[.,]?\\d*) godina", - "prije (\\d+[.,]?\\d*) godinu", - "prije (\\d+[.,]?\\d*) godine" + "prije (\\d++[.,]?\\d*+) g", + "prije (\\d++[.,]?\\d*+) godina", + "prije (\\d++[.,]?\\d*+) godinu", + "prije (\\d++[.,]?\\d*+) godine" ], "in \\1 day": [ - "za (\\d+[.,]?\\d*) d", - "za (\\d+[.,]?\\d*) dan", - "za (\\d+[.,]?\\d*) dana" + "za (\\d++[.,]?\\d*+) d", + "za (\\d++[.,]?\\d*+) dan", + "za (\\d++[.,]?\\d*+) dana" ], "in \\1 hour": [ - "za (\\d+[.,]?\\d*) h", - "za (\\d+[.,]?\\d*) sat", - "za (\\d+[.,]?\\d*) sati", - "za (\\d+[.,]?\\d*) sata" + "za (\\d++[.,]?\\d*+) h", + "za (\\d++[.,]?\\d*+) sat", + "za (\\d++[.,]?\\d*+) sati", + "za (\\d++[.,]?\\d*+) sata" ], "in \\1 minute": [ - "za (\\d+[.,]?\\d*) min", - "za (\\d+[.,]?\\d*) minuta", - "za (\\d+[.,]?\\d*) minutu", - "za (\\d+[.,]?\\d*) minute" + "za (\\d++[.,]?\\d*+) min", + "za (\\d++[.,]?\\d*+) minuta", + "za (\\d++[.,]?\\d*+) minutu", + "za (\\d++[.,]?\\d*+) minute" ], "in \\1 month": [ - "za (\\d+[.,]?\\d*) mj", - "za (\\d+[.,]?\\d*) mjesec", - "za (\\d+[.,]?\\d*) mjeseci", - "za (\\d+[.,]?\\d*) mjeseca" + "za (\\d++[.,]?\\d*+) mj", + "za (\\d++[.,]?\\d*+) mjesec", + "za (\\d++[.,]?\\d*+) mjeseci", + "za (\\d++[.,]?\\d*+) mjeseca" ], "in \\1 second": [ - "za (\\d+[.,]?\\d*) s", - "za (\\d+[.,]?\\d*) sekundi", - "za (\\d+[.,]?\\d*) sekundu", - "za (\\d+[.,]?\\d*) sekunde", - "za (\\d+[.,]?\\d*) sekundu" + "za (\\d++[.,]?\\d*+) s", + "za (\\d++[.,]?\\d*+) sekundi", + "za (\\d++[.,]?\\d*+) sekundu", + "za (\\d++[.,]?\\d*+) sekunde", + "za (\\d++[.,]?\\d*+) sekundu" ], "in \\1 week": [ - "za (\\d+[.,]?\\d*) tj", - "za (\\d+[.,]?\\d*) tjedan", - "za (\\d+[.,]?\\d*) tjedana", - "za (\\d+[.,]?\\d*) tjedna" + "za (\\d++[.,]?\\d*+) tj", + "za (\\d++[.,]?\\d*+) tjedan", + "za (\\d++[.,]?\\d*+) tjedana", + "za (\\d++[.,]?\\d*+) tjedna" ], "in \\1 year": [ - "za (\\d+[.,]?\\d*) g", - "za (\\d+[.,]?\\d*) godina", - "za (\\d+[.,]?\\d*) godinu", - "za (\\d+[.,]?\\d*) godine" + "za (\\d++[.,]?\\d*+) g", + "za (\\d++[.,]?\\d*+) godina", + "za (\\d++[.,]?\\d*+) godinu", + "za (\\d++[.,]?\\d*+) godine" ] }, "locale_specific": { @@ -359,6 +360,27 @@ }, { "ponoć": "00:00" + }, + { + "(?<=prije\\s+)tjedan(\\s+dana)?": "1 tjedan" + }, + { + "(?<=prije\\s+)mjesec(\\s+dana)?": "1 mjesec" + }, + { + "(?<=prije\\s+)godinu(\\s+dana)?": "1 godinu" + }, + { + "(?<=prije\\s+)sat(\\s+vremena)?": "1 sat" + }, + { + "(?<=prije\\s+)dan\\b": "1 dan" + }, + { + "(?<=prije\\s+)minutu": "1 minutu" + }, + { + "(?<=prije\\s+)sekundu": "1 sekundu" } ], "skip": [ diff --git a/dateparser/data/date_translation_data/hsb.py b/dateparser/data/date_translation_data/hsb.py index 52b53866c..0dcf14a50 100644 --- a/dateparser/data/date_translation_data/hsb.py +++ b/dateparser/data/date_translation_data/hsb.py @@ -90,9 +90,11 @@ "njedźela" ], "am": [ + "dop", "dopołdnja" ], "pm": [ + "pop", "popołdnju" ], "year": [ @@ -114,7 +116,8 @@ "hour": [ "h", "hodź", - "hodźina" + "hodźina", + "hodźiny" ], "minute": [ "m", @@ -128,129 +131,155 @@ ], "relative-type": { "0 day ago": [ + "dźe", + "dźens", "dźensa" ], "0 hour ago": [ + "w tutej hodźinje", "this hour" ], "0 minute ago": [ + "w tutej mjeńšinje", "this minute" ], "0 month ago": [ + "tu měsac", + "tut měsac", "tutón měsac" ], "0 second ago": [ - "now" + "nětko" ], "0 week ago": [ + "tu tydźeń", + "tut tydźeń", "tutón tydźeń" ], "0 year ago": [ + "lět", + "lěts", "lětsa" ], "1 day ago": [ + "wč", + "wčer", "wčera" ], "1 month ago": [ + "zaš měsac", + "zašł měsac", "zašły měsac" ], "1 week ago": [ + "zaš tydźeń", + "zašł tydźeń", "zašły tydźeń" ], "1 year ago": [ + "lo", + "lon", "loni" ], "in 1 day": [ + "jut", + "jutř", "jutře" ], "in 1 month": [ + "přich měsac", + "přichodn měsac", "přichodny měsac" ], "in 1 week": [ + "přich tydźeń", + "přichodn tydźeń", "přichodny tydźeń" ], "in 1 year": [ + "klě", + "klět", "klětu" ] }, "relative-type-regex": { "\\1 day ago": [ - "před (\\d+[.,]?\\d*) d", - "před (\\d+[.,]?\\d*) dnj", - "před (\\d+[.,]?\\d*) dnjemi", - "před (\\d+[.,]?\\d*) dnjom" + "před (\\d++[.,]?\\d*+) d", + "před (\\d++[.,]?\\d*+) dnj", + "před (\\d++[.,]?\\d*+) dnjemi", + "před (\\d++[.,]?\\d*+) dnjom" ], "\\1 hour ago": [ - "před (\\d+[.,]?\\d*) h", - "před (\\d+[.,]?\\d*) hodź", - "před (\\d+[.,]?\\d*) hodźinami", - "před (\\d+[.,]?\\d*) hodźinu" + "před (\\d++[.,]?\\d*+) h", + "před (\\d++[.,]?\\d*+) hodź", + "před (\\d++[.,]?\\d*+) hodźinami", + "před (\\d++[.,]?\\d*+) hodźinu" ], "\\1 minute ago": [ - "před (\\d+[.,]?\\d*) m", - "před (\\d+[.,]?\\d*) min", - "před (\\d+[.,]?\\d*) minutami", - "před (\\d+[.,]?\\d*) minutu" + "před (\\d++[.,]?\\d*+) m", + "před (\\d++[.,]?\\d*+) min", + "před (\\d++[.,]?\\d*+) minutami", + "před (\\d++[.,]?\\d*+) minutu" ], "\\1 month ago": [ - "před (\\d+[.,]?\\d*) měs", - "před (\\d+[.,]?\\d*) měsacami", - "před (\\d+[.,]?\\d*) měsacom" + "před (\\d++[.,]?\\d*+) měs", + "před (\\d++[.,]?\\d*+) měsacami", + "před (\\d++[.,]?\\d*+) měsacom" ], "\\1 second ago": [ - "před (\\d+[.,]?\\d*) s", - "před (\\d+[.,]?\\d*) sek", - "před (\\d+[.,]?\\d*) sekundami", - "před (\\d+[.,]?\\d*) sekundu" + "před (\\d++[.,]?\\d*+) s", + "před (\\d++[.,]?\\d*+) sek", + "před (\\d++[.,]?\\d*+) sekundami", + "před (\\d++[.,]?\\d*+) sekundu" ], "\\1 week ago": [ - "před (\\d+[.,]?\\d*) tydź", - "před (\\d+[.,]?\\d*) tydźenjemi", - "před (\\d+[.,]?\\d*) tydźenjom" + "před (\\d++[.,]?\\d*+) tydź", + "před (\\d++[.,]?\\d*+) tydźenjemi", + "před (\\d++[.,]?\\d*+) tydźenjom" ], "\\1 year ago": [ - "před (\\d+[.,]?\\d*) l", - "před (\\d+[.,]?\\d*) lětami", - "před (\\d+[.,]?\\d*) lětom" + "před (\\d++[.,]?\\d*+) l", + "před (\\d++[.,]?\\d*+) lětami", + "před (\\d++[.,]?\\d*+) lětom" ], "in \\1 day": [ - "za (\\d+[.,]?\\d*) d", - "za (\\d+[.,]?\\d*) dnj", - "za (\\d+[.,]?\\d*) dnjow", - "za (\\d+[.,]?\\d*) dźeń" + "za (\\d++[.,]?\\d*+) d", + "za (\\d++[.,]?\\d*+) dnj", + "za (\\d++[.,]?\\d*+) dnjow", + "za (\\d++[.,]?\\d*+) dźeń" ], "in \\1 hour": [ - "za (\\d+[.,]?\\d*) h", - "za (\\d+[.,]?\\d*) hodź", - "za (\\d+[.,]?\\d*) hodźin", - "za (\\d+[.,]?\\d*) hodźinu" + "za (\\d++[.,]?\\d*+) h", + "za (\\d++[.,]?\\d*+) hodź", + "za (\\d++[.,]?\\d*+) hodźin", + "za (\\d++[.,]?\\d*+) hodźinu" ], "in \\1 minute": [ - "za (\\d+[.,]?\\d*) m", - "za (\\d+[.,]?\\d*) min", - "za (\\d+[.,]?\\d*) minutow", - "za (\\d+[.,]?\\d*) minutu" + "za (\\d++[.,]?\\d*+) m", + "za (\\d++[.,]?\\d*+) min", + "za (\\d++[.,]?\\d*+) minutow", + "za (\\d++[.,]?\\d*+) minutu" ], "in \\1 month": [ - "za (\\d+[.,]?\\d*) měs", - "za (\\d+[.,]?\\d*) měsac", - "za (\\d+[.,]?\\d*) měsacow" + "za (\\d++[.,]?\\d*+) měs", + "za (\\d++[.,]?\\d*+) měsac", + "za (\\d++[.,]?\\d*+) měsacow" ], "in \\1 second": [ - "za (\\d+[.,]?\\d*) s", - "za (\\d+[.,]?\\d*) sek", - "za (\\d+[.,]?\\d*) sekundow", - "za (\\d+[.,]?\\d*) sekundu" + "za (\\d++[.,]?\\d*+) s", + "za (\\d++[.,]?\\d*+) sek", + "za (\\d++[.,]?\\d*+) sekundow", + "za (\\d++[.,]?\\d*+) sekundu" ], "in \\1 week": [ - "za (\\d+[.,]?\\d*) tydź", - "za (\\d+[.,]?\\d*) tydźenjow", - "za (\\d+[.,]?\\d*) tydźeń" + "za (\\d++[.,]?\\d*+) tydź", + "za (\\d++[.,]?\\d*+) tydźenjow", + "za (\\d++[.,]?\\d*+) tydźeń" ], "in \\1 year": [ - "za (\\d+[.,]?\\d*) l", - "za (\\d+[.,]?\\d*) lět", - "za (\\d+[.,]?\\d*) lěto" + "za (\\d++[.,]?\\d*+) l", + "za (\\d++[.,]?\\d*+) lět", + "za (\\d++[.,]?\\d*+) lěto" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/hu.py b/dateparser/data/date_translation_data/hu.py index e45d89a33..ee7535c1e 100644 --- a/dateparser/data/date_translation_data/hu.py +++ b/dateparser/data/date_translation_data/hu.py @@ -124,6 +124,7 @@ "nappal" ], "hour": [ + "ó", "óra", "ó", "órák", @@ -133,6 +134,7 @@ "órától" ], "minute": [ + "p", "perc", "p", "percek", @@ -142,6 +144,7 @@ "perctől" ], "second": [ + "mp", "másodperc", "mp", "másodpercek", @@ -202,47 +205,53 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) napja", - "(\\d+[.,]?\\d*) nappal ezelőtt" + "(\\d++[.,]?\\d*+) napja", + "(\\d++[.,]?\\d*+) nappal ezelőtt" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) órával ezelőtt" + "(\\d++[.,]?\\d*+) órája", + "(\\d++[.,]?\\d*+) órával ezelőtt" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) perccel ezelőtt" + "(\\d++[.,]?\\d*+) perccel ezelőtt", + "(\\d++[.,]?\\d*+) perce" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) hónappal ezelőtt" + "(\\d++[.,]?\\d*+) hónapja", + "(\\d++[.,]?\\d*+) hónappal ezelőtt" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) másodperccel ezelőtt" + "(\\d++[.,]?\\d*+) mperce", + "(\\d++[.,]?\\d*+) másodperccel ezelőtt" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) héttel ezelőtt" + "(\\d++[.,]?\\d*+) hete", + "(\\d++[.,]?\\d*+) héttel ezelőtt" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) évvel ezelőtt" + "(\\d++[.,]?\\d*+) éve", + "(\\d++[.,]?\\d*+) évvel ezelőtt" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) nap múlva" + "(\\d++[.,]?\\d*+) nap múlva" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) óra múlva" + "(\\d++[.,]?\\d*+) óra múlva" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) perc múlva" + "(\\d++[.,]?\\d*+) perc múlva" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) hónap múlva" + "(\\d++[.,]?\\d*+) hónap múlva" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) másodperc múlva" + "(\\d++[.,]?\\d*+) másodperc múlva" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) hét múlva" + "(\\d++[.,]?\\d*+) hét múlva" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) év múlva" + "(\\d++[.,]?\\d*+) év múlva" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/hy.py b/dateparser/data/date_translation_data/hy.py index 596a2658d..d0c0353f6 100644 --- a/dateparser/data/date_translation_data/hy.py +++ b/dateparser/data/date_translation_data/hy.py @@ -114,7 +114,8 @@ ], "hour": [ "ժ", - "ժամ" + "ժամ", + "ժամեր" ], "minute": [ "ր", @@ -138,6 +139,7 @@ "այս ամիս" ], "0 second ago": [ + "հիմա", "այժմ" ], "0 week ago": [ @@ -150,8 +152,8 @@ "երեկ" ], "1 month ago": [ - "անցյալ ամիս", - "նախորդ ամիս" + "նախորդ ամիս", + "անցյալ ամիս" ], "1 week ago": [ "նախորդ շաբաթ" @@ -174,58 +176,58 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) օր առաջ" + "(\\d++[.,]?\\d*+) օր առաջ" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) ժ առաջ", - "(\\d+[.,]?\\d*) ժամ առաջ" + "(\\d++[.,]?\\d*+) ժ առաջ", + "(\\d++[.,]?\\d*+) ժամ առաջ" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) ր առաջ", - "(\\d+[.,]?\\d*) րոպե առաջ" + "(\\d++[.,]?\\d*+) ր առաջ", + "(\\d++[.,]?\\d*+) րոպե առաջ" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) ամիս առաջ" + "(\\d++[.,]?\\d*+) ամիս առաջ" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) վ առաջ", - "(\\d+[.,]?\\d*) վայրկյան առաջ", - "(\\d+[.,]?\\d*) վրկ առաջ" + "(\\d++[.,]?\\d*+) վ առաջ", + "(\\d++[.,]?\\d*+) վայրկյան առաջ", + "(\\d++[.,]?\\d*+) վրկ առաջ" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) շաբ առաջ", - "(\\d+[.,]?\\d*) շաբաթ առաջ" + "(\\d++[.,]?\\d*+) շաբ առաջ", + "(\\d++[.,]?\\d*+) շաբաթ առաջ" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) տ առաջ", - "(\\d+[.,]?\\d*) տարի առաջ" + "(\\d++[.,]?\\d*+) տ առաջ", + "(\\d++[.,]?\\d*+) տարի առաջ" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) օրից" + "(\\d++[.,]?\\d*+) օրից" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) ժ-ից", - "(\\d+[.,]?\\d*) ժամից" + "(\\d++[.,]?\\d*+) ժ-ից", + "(\\d++[.,]?\\d*+) ժամից" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) ր-ից", - "(\\d+[.,]?\\d*) րոպեից" + "(\\d++[.,]?\\d*+) ր-ից", + "(\\d++[.,]?\\d*+) րոպեից" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) ամսից" + "(\\d++[.,]?\\d*+) ամսից" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) վ-ից", - "(\\d+[.,]?\\d*) վայրկյանից", - "(\\d+[.,]?\\d*) վրկ-ից" + "(\\d++[.,]?\\d*+) վ-ից", + "(\\d++[.,]?\\d*+) վայրկյանից", + "(\\d++[.,]?\\d*+) վրկ-ից" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) շաբ անց", - "(\\d+[.,]?\\d*) շաբ-ից", - "(\\d+[.,]?\\d*) շաբաթից" + "(\\d++[.,]?\\d*+) շաբ անց", + "(\\d++[.,]?\\d*+) շաբ-ից", + "(\\d++[.,]?\\d*+) շաբաթից" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) տարուց" + "(\\d++[.,]?\\d*+) տարուց" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/id.py b/dateparser/data/date_translation_data/id.py index fe3e59e6b..87152dad0 100644 --- a/dateparser/data/date_translation_data/id.py +++ b/dateparser/data/date_translation_data/id.py @@ -29,9 +29,10 @@ "juli" ], "august": [ - "agt", + "agu", "agustus", - "Agu" + "Agu", + "agt" ], "september": [ "sep", @@ -99,7 +100,8 @@ ], "day": [ "h", - "hari" + "hari", + "hr" ], "hour": [ "j", @@ -123,9 +125,11 @@ "jam ini" ], "0 minute ago": [ - "menit ini" + "menit ini", + "mnt ini" ], "0 month ago": [ + "bln ini", "bulan ini" ], "0 second ago": [ @@ -133,34 +137,43 @@ "baru saja" ], "0 week ago": [ + "mgg ini", "minggu ini" ], "0 year ago": [ - "tahun ini" + "tahun ini", + "thn ini" ], "1 day ago": [ "kemarin" ], "1 month ago": [ + "bln lalu", "bulan lalu" ], "1 week ago": [ + "mgg lalu", "minggu lalu" ], "1 year ago": [ - "tahun lalu" + "tahun lalu", + "thn lalu" ], "in 1 day": [ "besok" ], "in 1 month": [ + "bln berikutnya", + "bulan depan", "bulan berikutnya" ], "in 1 week": [ + "mgg depan", "minggu depan" ], "in 1 year": [ - "tahun depan" + "tahun depan", + "thn depan" ], "1 year": [ "setahun" @@ -180,65 +193,66 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) h lalu", - "(\\d+[.,]?\\d*) hari yang lalu" + "(\\d++[.,]?\\d*+) h lalu", + "(\\d++[.,]?\\d*+) hari yang lalu" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) jam lalu", - "(\\d+[.,]?\\d*) jam yang lalu" + "(\\d++[.,]?\\d*+) jam lalu", + "(\\d++[.,]?\\d*+) jam yang lalu" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) menit yang lalu", - "(\\d+[.,]?\\d*) mnt lalu" + "(\\d++[.,]?\\d*+) menit yang lalu", + "(\\d++[.,]?\\d*+) mnt lalu" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) bln lalu", - "(\\d+[.,]?\\d*) bulan yang lalu", - "(\\d+[.,]?\\d*) bulan lalu" + "(\\d++[.,]?\\d*+) bln lalu", + "(\\d++[.,]?\\d*+) bulan yang lalu", + "(\\d++[.,]?\\d*+) bulan lalu" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) detik yang lalu", - "(\\d+[.,]?\\d*) dtk lalu" + "(\\d++[.,]?\\d*+) detik yang lalu", + "(\\d++[.,]?\\d*+) dtk lalu" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) mgg lalu", - "(\\d+[.,]?\\d*) minggu yang lalu", - "(\\d+[.,]?\\d*) minggu lalu" + "(\\d++[.,]?\\d*+) mgg lalu", + "(\\d++[.,]?\\d*+) minggu yang lalu", + "(\\d++[.,]?\\d*+) minggu lalu" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) tahun yang lalu", - "(\\d+[.,]?\\d*) thn lalu", - "(\\d+[.,]?\\d*) tahun lalu" + "(\\d++[.,]?\\d*+) tahun yang lalu", + "(\\d++[.,]?\\d*+) thn lalu", + "(\\d++[.,]?\\d*+) tahun lalu" ], "in \\1 day": [ - "dalam (\\d+[.,]?\\d*) h", - "dalam (\\d+[.,]?\\d*) hari" + "dalam (\\d++[.,]?\\d*+) h", + "dalam (\\d++[.,]?\\d*+) hari" ], "in \\1 hour": [ - "dalam (\\d+[.,]?\\d*) jam" + "dalam (\\d++[.,]?\\d*+) jam", + "dlm (\\d++[.,]?\\d*+) jam" ], "in \\1 minute": [ - "dalam (\\d+[.,]?\\d*) menit", - "dlm (\\d+[.,]?\\d*) mnt" + "dalam (\\d++[.,]?\\d*+) menit", + "dlm (\\d++[.,]?\\d*+) mnt" ], "in \\1 month": [ - "dalam (\\d+[.,]?\\d*) bulan", - "dlm (\\d+[.,]?\\d*) bln" + "dalam (\\d++[.,]?\\d*+) bulan", + "dlm (\\d++[.,]?\\d*+) bln" ], "in \\1 second": [ - "dalam (\\d+[.,]?\\d*) detik", - "dlm (\\d+[.,]?\\d*) dtk" + "dalam (\\d++[.,]?\\d*+) detik", + "dlm (\\d++[.,]?\\d*+) dtk" ], "in \\1 week": [ - "dalam (\\d+[.,]?\\d*) minggu", - "dlm (\\d+[.,]?\\d*) mgg" + "dalam (\\d++[.,]?\\d*+) minggu", + "dlm (\\d++[.,]?\\d*+) mgg" ], "in \\1 year": [ - "dalam (\\d+[.,]?\\d*) tahun", - "dlm (\\d+[.,]?\\d*) thn" + "dalam (\\d++[.,]?\\d*+) tahun", + "dlm (\\d++[.,]?\\d*+) thn" ], "\\1 week": [ - "(\\d+[.,]?\\d*) minggu" + "(\\d++[.,]?\\d*+) minggu" ], "sunday": [ "minggu" diff --git a/dateparser/data/date_translation_data/ig.py b/dateparser/data/date_translation_data/ig.py index e88bac8a4..ec6c67070 100644 --- a/dateparser/data/date_translation_data/ig.py +++ b/dateparser/data/date_translation_data/ig.py @@ -15,6 +15,7 @@ ], "april": [ "epr", + "epreel", "eprel" ], "may": [ @@ -73,13 +74,17 @@ "satọdee" ], "sunday": [ + "sọn", + "sọndee", "mbọsị ụka", "ụka" ], "am": [ - "am" + "am", + "n'ụtụtụ" ], "pm": [ + "n'abali", "pm" ], "year": [ @@ -95,58 +100,74 @@ "ụbọchị" ], "hour": [ - "elekere" + "elekere", + "hr" ], "minute": [ "nkeji" ], "second": [ + "tịm kọm", "nkejinta" ], "relative-type": { "0 day ago": [ + "taa", "taata" ], "0 hour ago": [ + "elekere a", "this hour" ], "0 minute ago": [ + "nkejị a", "this minute" ], "0 month ago": [ + "ọnwa a", "this month" ], "0 second ago": [ + "ụgbụa", "now" ], "0 week ago": [ + "izu a", "this week" ], "0 year ago": [ + "afọ a", "this year" ], "1 day ago": [ + "ụnyaahụ", "nnyaafụ" ], "1 month ago": [ + "ọnwa gara aga", "last month" ], "1 week ago": [ + "izu gara aga", "last week" ], "1 year ago": [ + "afọ gara aga", "last year" ], "in 1 day": [ "echi" ], "in 1 month": [ + "ọnwa ọzọ", "next month" ], "in 1 week": [ + "izu na-esote", "next week" ], "in 1 year": [ + "afọ ọzọ", "next year" ] }, diff --git a/dateparser/data/date_translation_data/ii.py b/dateparser/data/date_translation_data/ii.py index 9db7a906d..463c59f65 100644 --- a/dateparser/data/date_translation_data/ii.py +++ b/dateparser/data/date_translation_data/ii.py @@ -84,6 +84,7 @@ "ꑍ" ], "hour": [ + "hr", "ꄮꈉ" ], "minute": [ diff --git a/dateparser/data/date_translation_data/is.py b/dateparser/data/date_translation_data/is.py index 40e481bb7..d4a9b076b 100644 --- a/dateparser/data/date_translation_data/is.py +++ b/dateparser/data/date_translation_data/is.py @@ -94,12 +94,13 @@ "vika" ], "day": [ - "d", - "dagur" + "dagur", + "d" ], "hour": [ "klst", - "klukkustund" + "klukkustund", + "klukkustundir" ], "minute": [ "mín", @@ -114,9 +115,11 @@ "í dag" ], "0 hour ago": [ + "þessa stundina", "this hour" ], "0 minute ago": [ + "á þessari mínútu", "this minute" ], "0 month ago": [ @@ -161,67 +164,67 @@ }, "relative-type-regex": { "\\1 day ago": [ - "fyrir (\\d+[.,]?\\d*) degi", - "fyrir (\\d+[.,]?\\d*) dögum" + "fyrir (\\d++[.,]?\\d*+) degi", + "fyrir (\\d++[.,]?\\d*+) dögum" ], "\\1 hour ago": [ - "fyrir (\\d+[.,]?\\d*) klst", - "fyrir (\\d+[.,]?\\d*) klukkustund", - "fyrir (\\d+[.,]?\\d*) klukkustundum" + "fyrir (\\d++[.,]?\\d*+) klst", + "fyrir (\\d++[.,]?\\d*+) klukkustund", + "fyrir (\\d++[.,]?\\d*+) klukkustundum" ], "\\1 minute ago": [ - "fyrir (\\d+[.,]?\\d*) mín", - "fyrir (\\d+[.,]?\\d*) mínútu", - "fyrir (\\d+[.,]?\\d*) mínútum" + "fyrir (\\d++[.,]?\\d*+) mín", + "fyrir (\\d++[.,]?\\d*+) mínútu", + "fyrir (\\d++[.,]?\\d*+) mínútum" ], "\\1 month ago": [ - "fyrir (\\d+[.,]?\\d*) mán", - "fyrir (\\d+[.,]?\\d*) mánuði", - "fyrir (\\d+[.,]?\\d*) mánuðum" + "fyrir (\\d++[.,]?\\d*+) mán", + "fyrir (\\d++[.,]?\\d*+) mánuði", + "fyrir (\\d++[.,]?\\d*+) mánuðum" ], "\\1 second ago": [ - "fyrir (\\d+[.,]?\\d*) sek", - "fyrir (\\d+[.,]?\\d*) sekúndu", - "fyrir (\\d+[.,]?\\d*) sekúndum" + "fyrir (\\d++[.,]?\\d*+) sek", + "fyrir (\\d++[.,]?\\d*+) sekúndu", + "fyrir (\\d++[.,]?\\d*+) sekúndum" ], "\\1 week ago": [ - "fyrir (\\d+[.,]?\\d*) viku", - "fyrir (\\d+[.,]?\\d*) vikum" + "fyrir (\\d++[.,]?\\d*+) viku", + "fyrir (\\d++[.,]?\\d*+) vikum" ], "\\1 year ago": [ - "fyrir (\\d+[.,]?\\d*) ári", - "fyrir (\\d+[.,]?\\d*) árum" + "fyrir (\\d++[.,]?\\d*+) ári", + "fyrir (\\d++[.,]?\\d*+) árum" ], "in \\1 day": [ - "eftir (\\d+[.,]?\\d*) dag", - "eftir (\\d+[.,]?\\d*) daga" + "eftir (\\d++[.,]?\\d*+) dag", + "eftir (\\d++[.,]?\\d*+) daga" ], "in \\1 hour": [ - "eftir (\\d+[.,]?\\d*) klst", - "eftir (\\d+[.,]?\\d*) klukkustund", - "eftir (\\d+[.,]?\\d*) klukkustundir" + "eftir (\\d++[.,]?\\d*+) klst", + "eftir (\\d++[.,]?\\d*+) klukkustund", + "eftir (\\d++[.,]?\\d*+) klukkustundir" ], "in \\1 minute": [ - "eftir (\\d+[.,]?\\d*) mín", - "eftir (\\d+[.,]?\\d*) mínútu", - "eftir (\\d+[.,]?\\d*) mínútur" + "eftir (\\d++[.,]?\\d*+) mín", + "eftir (\\d++[.,]?\\d*+) mínútu", + "eftir (\\d++[.,]?\\d*+) mínútur" ], "in \\1 month": [ - "eftir (\\d+[.,]?\\d*) mán", - "eftir (\\d+[.,]?\\d*) mánuð", - "eftir (\\d+[.,]?\\d*) mánuði" + "eftir (\\d++[.,]?\\d*+) mán", + "eftir (\\d++[.,]?\\d*+) mánuð", + "eftir (\\d++[.,]?\\d*+) mánuði" ], "in \\1 second": [ - "eftir (\\d+[.,]?\\d*) sek", - "eftir (\\d+[.,]?\\d*) sekúndu", - "eftir (\\d+[.,]?\\d*) sekúndur" + "eftir (\\d++[.,]?\\d*+) sek", + "eftir (\\d++[.,]?\\d*+) sekúndu", + "eftir (\\d++[.,]?\\d*+) sekúndur" ], "in \\1 week": [ - "eftir (\\d+[.,]?\\d*) viku", - "eftir (\\d+[.,]?\\d*) vikur" + "eftir (\\d++[.,]?\\d*+) viku", + "eftir (\\d++[.,]?\\d*+) vikur" ], "in \\1 year": [ - "eftir (\\d+[.,]?\\d*) ár" + "eftir (\\d++[.,]?\\d*+) ár" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/it.py b/dateparser/data/date_translation_data/it.py index fee99ccc1..0362b3678 100644 --- a/dateparser/data/date_translation_data/it.py +++ b/dateparser/data/date_translation_data/it.py @@ -104,19 +104,20 @@ "hour": [ "h", "ora", + "ore", "ore" ], "minute": [ - "m", "min", "minuto", - "minuti" + "minuti", + "m" ], "second": [ "s", - "sec", "secondo", - "secondi" + "secondi", + "sec" ], "relative-type": { "0 day ago": [ @@ -135,6 +136,7 @@ "ora" ], "0 week ago": [ + "questa sett", "questa settimana" ], "0 year ago": [ @@ -147,6 +149,7 @@ "mese scorso" ], "1 week ago": [ + "sett scorsa", "settimana scorsa" ], "1 year ago": [ @@ -159,6 +162,7 @@ "mese prossimo" ], "in 1 week": [ + "sett prossima", "settimana prossima" ], "in 1 year": [ @@ -170,74 +174,74 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) g fa", - "(\\d+[.,]?\\d*) gg fa", - "(\\d+[.,]?\\d*) giorni fa", - "(\\d+[.,]?\\d*) giorno fa" + "(\\d++[.,]?\\d*+) g fa", + "(\\d++[.,]?\\d*+) gg fa", + "(\\d++[.,]?\\d*+) giorni fa", + "(\\d++[.,]?\\d*+) giorno fa" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) h fa", - "(\\d+[.,]?\\d*) ora fa", - "(\\d+[.,]?\\d*) ore fa" + "(\\d++[.,]?\\d*+) h fa", + "(\\d++[.,]?\\d*+) ora fa", + "(\\d++[.,]?\\d*+) ore fa" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) min fa", - "(\\d+[.,]?\\d*) minuti fa", - "(\\d+[.,]?\\d*) minuto fa" + "(\\d++[.,]?\\d*+) min fa", + "(\\d++[.,]?\\d*+) minuti fa", + "(\\d++[.,]?\\d*+) minuto fa" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) mese fa", - "(\\d+[.,]?\\d*) mesi fa" + "(\\d++[.,]?\\d*+) mese fa", + "(\\d++[.,]?\\d*+) mesi fa" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) s fa", - "(\\d+[.,]?\\d*) sec fa", - "(\\d+[.,]?\\d*) secondi fa", - "(\\d+[.,]?\\d*) secondo fa" + "(\\d++[.,]?\\d*+) s fa", + "(\\d++[.,]?\\d*+) sec fa", + "(\\d++[.,]?\\d*+) secondi fa", + "(\\d++[.,]?\\d*+) secondo fa" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) sett fa", - "(\\d+[.,]?\\d*) settimana fa", - "(\\d+[.,]?\\d*) settimane fa" + "(\\d++[.,]?\\d*+) sett fa", + "(\\d++[.,]?\\d*+) settimana fa", + "(\\d++[.,]?\\d*+) settimane fa" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) anni fa", - "(\\d+[.,]?\\d*) anno fa" + "(\\d++[.,]?\\d*+) anni fa", + "(\\d++[.,]?\\d*+) anno fa" ], "in \\1 day": [ - "tra (\\d+[.,]?\\d*) g", - "tra (\\d+[.,]?\\d*) gg", - "tra (\\d+[.,]?\\d*) giorni", - "tra (\\d+[.,]?\\d*) giorno" + "tra (\\d++[.,]?\\d*+) g", + "tra (\\d++[.,]?\\d*+) gg", + "tra (\\d++[.,]?\\d*+) giorni", + "tra (\\d++[.,]?\\d*+) giorno" ], "in \\1 hour": [ - "tra (\\d+[.,]?\\d*) h", - "tra (\\d+[.,]?\\d*) ora", - "tra (\\d+[.,]?\\d*) ore" + "tra (\\d++[.,]?\\d*+) h", + "tra (\\d++[.,]?\\d*+) ora", + "tra (\\d++[.,]?\\d*+) ore" ], "in \\1 minute": [ - "tra (\\d+[.,]?\\d*) min", - "tra (\\d+[.,]?\\d*) minuti", - "tra (\\d+[.,]?\\d*) minuto" + "tra (\\d++[.,]?\\d*+) min", + "tra (\\d++[.,]?\\d*+) minuti", + "tra (\\d++[.,]?\\d*+) minuto" ], "in \\1 month": [ - "tra (\\d+[.,]?\\d*) mese", - "tra (\\d+[.,]?\\d*) mesi" + "tra (\\d++[.,]?\\d*+) mese", + "tra (\\d++[.,]?\\d*+) mesi" ], "in \\1 second": [ - "tra (\\d+[.,]?\\d*) s", - "tra (\\d+[.,]?\\d*) sec", - "tra (\\d+[.,]?\\d*) secondi", - "tra (\\d+[.,]?\\d*) secondo" + "tra (\\d++[.,]?\\d*+) s", + "tra (\\d++[.,]?\\d*+) sec", + "tra (\\d++[.,]?\\d*+) secondi", + "tra (\\d++[.,]?\\d*+) secondo" ], "in \\1 week": [ - "tra (\\d+[.,]?\\d*) sett", - "tra (\\d+[.,]?\\d*) settimana", - "tra (\\d+[.,]?\\d*) settimane" + "tra (\\d++[.,]?\\d*+) sett", + "tra (\\d++[.,]?\\d*+) settimana", + "tra (\\d++[.,]?\\d*+) settimane" ], "in \\1 year": [ - "tra (\\d+[.,]?\\d*) anni", - "tra (\\d+[.,]?\\d*) anno" + "tra (\\d++[.,]?\\d*+) anni", + "tra (\\d++[.,]?\\d*+) anno" ] }, "locale_specific": { @@ -254,6 +258,7 @@ "skip": [ "circa", "e", + "alle", " ", "'", ",", @@ -276,7 +281,10 @@ ], "simplifications": [ { - "(\\d+[.,]?\\d*)\\s+ora": "\\1 ore" + "(\\d++[.,]?\\d*+)\\s+ora": "\\1 ore" + }, + { + "\\bun[' ]ora\\b": "1 ore" } ] } diff --git a/dateparser/data/date_translation_data/ja.py b/dateparser/data/date_translation_data/ja.py index 730305f6d..d6f8fff2d 100644 --- a/dateparser/data/date_translation_data/ja.py +++ b/dateparser/data/date_translation_data/ja.py @@ -109,6 +109,7 @@ ], "hour": [ "時", + "時間", "時間" ], "minute": [ @@ -159,12 +160,15 @@ "明日" ], "in 1 month": [ + "来月", "翌月" ], "in 1 week": [ + "来週", "翌週" ], "in 1 year": [ + "来年", "翌年" ], "2 day ago": [ @@ -179,60 +183,60 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) 日前", - "(\\d+[.,]?\\d*)日前" + "(\\d++[.,]?\\d*+) 日前", + "(\\d++[.,]?\\d*+)日前" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) 時間前", - "(\\d+[.,]?\\d*)時間前" + "(\\d++[.,]?\\d*+) 時間前", + "(\\d++[.,]?\\d*+)時間前" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) 分前", - "(\\d+[.,]?\\d*)分前" + "(\\d++[.,]?\\d*+) 分前", + "(\\d++[.,]?\\d*+)分前" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) か月前", - "(\\d+[.,]?\\d*)か月前" + "(\\d++[.,]?\\d*+) か月前", + "(\\d++[.,]?\\d*+)か月前" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) 秒前", - "(\\d+[.,]?\\d*)秒前" + "(\\d++[.,]?\\d*+) 秒前", + "(\\d++[.,]?\\d*+)秒前" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) 週間前", - "(\\d+[.,]?\\d*)週間前" + "(\\d++[.,]?\\d*+) 週間前", + "(\\d++[.,]?\\d*+)週間前" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) 年前", - "(\\d+[.,]?\\d*)年前" + "(\\d++[.,]?\\d*+) 年前", + "(\\d++[.,]?\\d*+)年前" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) 日後", - "(\\d+[.,]?\\d*)日後" + "(\\d++[.,]?\\d*+) 日後", + "(\\d++[.,]?\\d*+)日後" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) 時間後", - "(\\d+[.,]?\\d*)時間後" + "(\\d++[.,]?\\d*+) 時間後", + "(\\d++[.,]?\\d*+)時間後" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) 分後", - "(\\d+[.,]?\\d*)分後" + "(\\d++[.,]?\\d*+) 分後", + "(\\d++[.,]?\\d*+)分後" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) か月後", - "(\\d+[.,]?\\d*)か月後" + "(\\d++[.,]?\\d*+) か月後", + "(\\d++[.,]?\\d*+)か月後" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) 秒後", - "(\\d+[.,]?\\d*)秒後" + "(\\d++[.,]?\\d*+) 秒後", + "(\\d++[.,]?\\d*+)秒後" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) 週間後", - "(\\d+[.,]?\\d*)週間後" + "(\\d++[.,]?\\d*+) 週間後", + "(\\d++[.,]?\\d*+)週間後" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) 年後", - "(\\d+[.,]?\\d*)年後" + "(\\d++[.,]?\\d*+) 年後", + "(\\d++[.,]?\\d*+)年後" ] }, "locale_specific": {}, @@ -265,19 +269,19 @@ ], "simplifications": [ { - "(\\d+[.,]?\\d*)年(?:\\s+)?(\\d+[.,]?\\d*)月(?:\\s+)?(\\d+[.,]?\\d*)日": "\\1-\\2-\\3" + "(\\d++[.,]?\\d*+)\\s*年\\s*(\\d++[.,]?\\d*+)\\s*月\\s*(\\d++[.,]?\\d*+)\\s*日": "\\1-\\2-\\3" }, { - "(\\d+[.,]?\\d*)月(?:\\s+)?(\\d+[.,]?\\d*)日": "\\1-\\2" + "(\\d++[.,]?\\d*+)月(?:\\s+)?(\\d++[.,]?\\d*+)日": "\\1-\\2" }, { - "(\\d+[.,]?\\d*)時(?:\\s+)?(\\d+[.,]?\\d*)分(?:\\s+)?(\\d+[.,]?\\d*)秒": "\\1:\\2:\\3" + "(\\d++[.,]?\\d*+)\\s*時\\s*(\\d++[.,]?\\d*+)\\s*分\\s*(\\d++[.,]?\\d*+)\\s*秒": "\\1:\\2:\\3" }, { - "(\\d+[.,]?\\d*)時(?:\\s+)?(\\d+[.,]?\\d*)分": "\\1:\\2" + "(\\d++[.,]?\\d*+)\\s*時\\s*(\\d++[.,]?\\d*+)\\s*分": "\\1:\\2" }, { - "(\\d+[.,]?\\d*)時$": "\\1:00" + "(\\d++[.,]?\\d*+)\\s*時$": "\\1:00" }, { "正午": "12:00" diff --git a/dateparser/data/date_translation_data/jgo.py b/dateparser/data/date_translation_data/jgo.py index 9e52f34bc..7a33ad4c3 100644 --- a/dateparser/data/date_translation_data/jgo.py +++ b/dateparser/data/date_translation_data/jgo.py @@ -77,7 +77,8 @@ "day" ], "hour": [ - "hour" + "hour", + "hr" ], "minute": [ "minute" @@ -134,40 +135,40 @@ }, "relative-type-regex": { "\\1 day ago": [ - "ɛ́ gɛ́ mɔ́ lɛ́ꞌ (\\d+[.,]?\\d*)" + "ɛ́ gɛ́ mɔ́ lɛ́ꞌ (\\d++[.,]?\\d*+)" ], "\\1 hour ago": [ - "ɛ́ gɛ mɔ́ (\\d+[.,]?\\d*) háwa" + "ɛ́ gɛ mɔ́ (\\d++[.,]?\\d*+) háwa" ], "\\1 minute ago": [ - "ɛ́ gɛ́ mɔ́ minút (\\d+[.,]?\\d*)" + "ɛ́ gɛ́ mɔ́ minút (\\d++[.,]?\\d*+)" ], "\\1 month ago": [ - "ɛ́ gɛ́ mɔ́ pɛsaŋ (\\d+[.,]?\\d*)" + "ɛ́ gɛ́ mɔ́ pɛsaŋ (\\d++[.,]?\\d*+)" ], "\\1 week ago": [ - "ɛ́ gɛ́ mɔ (\\d+[.,]?\\d*) ŋgap-mbi" + "ɛ́ gɛ́ mɔ (\\d++[.,]?\\d*+) ŋgap-mbi" ], "\\1 year ago": [ - "ɛ́gɛ́ mɔ́ ŋguꞌ (\\d+[.,]?\\d*)" + "ɛ́gɛ́ mɔ́ ŋguꞌ (\\d++[.,]?\\d*+)" ], "in \\1 day": [ - "nǔu lɛ́ꞌ (\\d+[.,]?\\d*)" + "nǔu lɛ́ꞌ (\\d++[.,]?\\d*+)" ], "in \\1 hour": [ - "nǔu háwa (\\d+[.,]?\\d*)" + "nǔu háwa (\\d++[.,]?\\d*+)" ], "in \\1 minute": [ - "nǔu (\\d+[.,]?\\d*) minút" + "nǔu (\\d++[.,]?\\d*+) minút" ], "in \\1 month": [ - "nǔu (\\d+[.,]?\\d*) saŋ" + "nǔu (\\d++[.,]?\\d*+) saŋ" ], "in \\1 week": [ - "nǔu ŋgap-mbi (\\d+[.,]?\\d*)" + "nǔu ŋgap-mbi (\\d++[.,]?\\d*+)" ], "in \\1 year": [ - "nǔu ŋguꞌ (\\d+[.,]?\\d*)" + "nǔu ŋguꞌ (\\d++[.,]?\\d*+)" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/jmc.py b/dateparser/data/date_translation_data/jmc.py index 7c06f3175..8df005c1c 100644 --- a/dateparser/data/date_translation_data/jmc.py +++ b/dateparser/data/date_translation_data/jmc.py @@ -95,6 +95,7 @@ "mfiri" ], "hour": [ + "hr", "saa" ], "minute": [ diff --git a/dateparser/data/date_translation_data/ka.py b/dateparser/data/date_translation_data/ka.py index f303291fd..60d94a1d8 100644 --- a/dateparser/data/date_translation_data/ka.py +++ b/dateparser/data/date_translation_data/ka.py @@ -160,51 +160,51 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) დღის წინ" + "(\\d++[.,]?\\d*+) დღის წინ" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) საათის წინ", - "(\\d+[.,]?\\d*) სთ წინ" + "(\\d++[.,]?\\d*+) საათის წინ", + "(\\d++[.,]?\\d*+) სთ წინ" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) წთ წინ", - "(\\d+[.,]?\\d*) წუთის წინ" + "(\\d++[.,]?\\d*+) წთ წინ", + "(\\d++[.,]?\\d*+) წუთის წინ" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) თვის წინ" + "(\\d++[.,]?\\d*+) თვის წინ" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) წამის წინ", - "(\\d+[.,]?\\d*) წმ წინ" + "(\\d++[.,]?\\d*+) წამის წინ", + "(\\d++[.,]?\\d*+) წმ წინ" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) კვ წინ", - "(\\d+[.,]?\\d*) კვირის წინ" + "(\\d++[.,]?\\d*+) კვ წინ", + "(\\d++[.,]?\\d*+) კვირის წინ" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) წლის წინ" + "(\\d++[.,]?\\d*+) წლის წინ" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) დღეში" + "(\\d++[.,]?\\d*+) დღეში" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) საათში" + "(\\d++[.,]?\\d*+) საათში" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) წუთში" + "(\\d++[.,]?\\d*+) წუთში" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) თვეში" + "(\\d++[.,]?\\d*+) თვეში" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) წამში" + "(\\d++[.,]?\\d*+) წამში" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) კვირაში" + "(\\d++[.,]?\\d*+) კვირაში" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) წელიწადში", - "(\\d+[.,]?\\d*) წელში" + "(\\d++[.,]?\\d*+) წელიწადში", + "(\\d++[.,]?\\d*+) წელში" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/kab.py b/dateparser/data/date_translation_data/kab.py index fa74984a8..320fcbb8f 100644 --- a/dateparser/data/date_translation_data/kab.py +++ b/dateparser/data/date_translation_data/kab.py @@ -96,6 +96,7 @@ "ass" ], "hour": [ + "hr", "tamert" ], "minute": [ diff --git a/dateparser/data/date_translation_data/kam.py b/dateparser/data/date_translation_data/kam.py index 5479d6b3d..d7df94de9 100644 --- a/dateparser/data/date_translation_data/kam.py +++ b/dateparser/data/date_translation_data/kam.py @@ -96,6 +96,7 @@ "mũthenya" ], "hour": [ + "hr", "saa" ], "minute": [ diff --git a/dateparser/data/date_translation_data/kde.py b/dateparser/data/date_translation_data/kde.py index 9cffae61d..7edb4a4eb 100644 --- a/dateparser/data/date_translation_data/kde.py +++ b/dateparser/data/date_translation_data/kde.py @@ -96,6 +96,7 @@ "lihiku" ], "hour": [ + "hr", "saa" ], "minute": [ diff --git a/dateparser/data/date_translation_data/kea.py b/dateparser/data/date_translation_data/kea.py index b642fa156..8e2ad5d4d 100644 --- a/dateparser/data/date_translation_data/kea.py +++ b/dateparser/data/date_translation_data/kea.py @@ -71,8 +71,8 @@ ], "saturday": [ "sab", - "sabadu", - "sábadu" + "sábadu", + "sabadu" ], "sunday": [ "dum", @@ -116,15 +116,18 @@ "oji" ], "0 hour ago": [ + "es ora li", "this hour" ], "0 minute ago": [ + "es minutu li", "this minute" ], "0 month ago": [ "es mes li" ], "0 second ago": [ + "agora", "now" ], "0 week ago": [ @@ -146,6 +149,7 @@ "anu pasadu" ], "in 1 day": [ + "manhan", "manha" ], "in 1 month": [ @@ -160,56 +164,56 @@ }, "relative-type-regex": { "\\1 day ago": [ - "a ten (\\d+[.,]?\\d*) dia" + "a ten (\\d++[.,]?\\d*+) dia" ], "\\1 hour ago": [ - "a ten (\\d+[.,]?\\d*) ora" + "a ten (\\d++[.,]?\\d*+) ora" ], "\\1 minute ago": [ - "a ten (\\d+[.,]?\\d*) m", - "a ten (\\d+[.,]?\\d*) min", - "a ten (\\d+[.,]?\\d*) minutu" + "a ten (\\d++[.,]?\\d*+) m", + "a ten (\\d++[.,]?\\d*+) min", + "a ten (\\d++[.,]?\\d*+) minutu" ], "\\1 month ago": [ - "a ten (\\d+[.,]?\\d*) mes" + "a ten (\\d++[.,]?\\d*+) mes" ], "\\1 second ago": [ - "a ten (\\d+[.,]?\\d*) s", - "a ten (\\d+[.,]?\\d*) sig", - "a ten (\\d+[.,]?\\d*) sigundu" + "a ten (\\d++[.,]?\\d*+) s", + "a ten (\\d++[.,]?\\d*+) sig", + "a ten (\\d++[.,]?\\d*+) sigundu" ], "\\1 week ago": [ - "a ten (\\d+[.,]?\\d*) sim", - "a ten (\\d+[.,]?\\d*) simana" + "a ten (\\d++[.,]?\\d*+) sim", + "a ten (\\d++[.,]?\\d*+) simana" ], "\\1 year ago": [ - "a ten (\\d+[.,]?\\d*) anu" + "a ten (\\d++[.,]?\\d*+) anu" ], "in \\1 day": [ - "di li (\\d+[.,]?\\d*) dia" + "di li (\\d++[.,]?\\d*+) dia" ], "in \\1 hour": [ - "di li (\\d+[.,]?\\d*) ora" + "di li (\\d++[.,]?\\d*+) ora" ], "in \\1 minute": [ - "di li (\\d+[.,]?\\d*) m", - "di li (\\d+[.,]?\\d*) min", - "di li (\\d+[.,]?\\d*) minutu" + "di li (\\d++[.,]?\\d*+) m", + "di li (\\d++[.,]?\\d*+) min", + "di li (\\d++[.,]?\\d*+) minutu" ], "in \\1 month": [ - "di li (\\d+[.,]?\\d*) mes" + "di li (\\d++[.,]?\\d*+) mes" ], "in \\1 second": [ - "di li (\\d+[.,]?\\d*) s", - "di li (\\d+[.,]?\\d*) sig", - "di li (\\d+[.,]?\\d*) sigundu" + "di li (\\d++[.,]?\\d*+) s", + "di li (\\d++[.,]?\\d*+) sig", + "di li (\\d++[.,]?\\d*+) sigundu" ], "in \\1 week": [ - "di li (\\d+[.,]?\\d*) sim", - "di li (\\d+[.,]?\\d*) simana" + "di li (\\d++[.,]?\\d*+) sim", + "di li (\\d++[.,]?\\d*+) simana" ], "in \\1 year": [ - "di li (\\d+[.,]?\\d*) anu" + "di li (\\d++[.,]?\\d*+) anu" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/khq.py b/dateparser/data/date_translation_data/khq.py index d707ae00b..b9a90fd55 100644 --- a/dateparser/data/date_translation_data/khq.py +++ b/dateparser/data/date_translation_data/khq.py @@ -94,7 +94,8 @@ "jaari" ], "hour": [ - "guuru" + "guuru", + "hr" ], "minute": [ "miniti" diff --git a/dateparser/data/date_translation_data/ki.py b/dateparser/data/date_translation_data/ki.py index 45224f847..29c8c3e93 100644 --- a/dateparser/data/date_translation_data/ki.py +++ b/dateparser/data/date_translation_data/ki.py @@ -96,6 +96,7 @@ "mũthenya" ], "hour": [ + "hr", "ithaa" ], "minute": [ diff --git a/dateparser/data/date_translation_data/kk.py b/dateparser/data/date_translation_data/kk.py index 733522348..5cd1835a6 100644 --- a/dateparser/data/date_translation_data/kk.py +++ b/dateparser/data/date_translation_data/kk.py @@ -158,56 +158,56 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) күн бұрын" + "(\\d++[.,]?\\d*+) күн бұрын" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) сағ бұрын", - "(\\d+[.,]?\\d*) сағат бұрын" + "(\\d++[.,]?\\d*+) сағ бұрын", + "(\\d++[.,]?\\d*+) сағат бұрын" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) мин бұрын", - "(\\d+[.,]?\\d*) минут бұрын" + "(\\d++[.,]?\\d*+) мин бұрын", + "(\\d++[.,]?\\d*+) минут бұрын" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) ай бұрын" + "(\\d++[.,]?\\d*+) ай бұрын" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) сек бұрын", - "(\\d+[.,]?\\d*) секунд бұрын" + "(\\d++[.,]?\\d*+) сек бұрын", + "(\\d++[.,]?\\d*+) секунд бұрын" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) ап бұрын", - "(\\d+[.,]?\\d*) апта бұрын" + "(\\d++[.,]?\\d*+) ап бұрын", + "(\\d++[.,]?\\d*+) апта бұрын" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) ж бұрын", - "(\\d+[.,]?\\d*) жыл бұрын" + "(\\d++[.,]?\\d*+) ж бұрын", + "(\\d++[.,]?\\d*+) жыл бұрын" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) күннен кейін" + "(\\d++[.,]?\\d*+) күннен кейін" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) сағ кейін", - "(\\d+[.,]?\\d*) сағаттан кейін" + "(\\d++[.,]?\\d*+) сағ кейін", + "(\\d++[.,]?\\d*+) сағаттан кейін" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) мин кейін", - "(\\d+[.,]?\\d*) минуттан кейін" + "(\\d++[.,]?\\d*+) мин кейін", + "(\\d++[.,]?\\d*+) минуттан кейін" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) айдан кейін" + "(\\d++[.,]?\\d*+) айдан кейін" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) сек кейін", - "(\\d+[.,]?\\d*) секундтан кейін" + "(\\d++[.,]?\\d*+) сек кейін", + "(\\d++[.,]?\\d*+) секундтан кейін" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) ап кейін", - "(\\d+[.,]?\\d*) аптадан кейін" + "(\\d++[.,]?\\d*+) ап кейін", + "(\\d++[.,]?\\d*+) аптадан кейін" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) ж кейін", - "(\\d+[.,]?\\d*) жылдан кейін" + "(\\d++[.,]?\\d*+) ж кейін", + "(\\d++[.,]?\\d*+) жылдан кейін" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/kl.py b/dateparser/data/date_translation_data/kl.py index eddcea08e..91836c91c 100644 --- a/dateparser/data/date_translation_data/kl.py +++ b/dateparser/data/date_translation_data/kl.py @@ -3,50 +3,76 @@ "date_order": "YMD", "january": [ "jan", + "januaari", + "januaarip", "januari" ], "february": [ + "febr", + "februaari", + "februaarip", "feb", "februari" ], "march": [ "mar", + "marsi", + "marsip", "martsi" ], "april": [ "apr", + "apriili", + "apriilip", "aprili" ], "may": [ + "maaji", + "maajip", "maj", "maji" ], "june": [ "jun", + "juuni", + "juunip", "juni" ], "july": [ "jul", + "juuli", + "juulip", "juli" ], "august": [ + "aggusti", + "aggustip", "aug", "augustusi" ], "september": [ + "sept", + "septembari", + "septembarip", "sep", "septemberi" ], "october": [ "okt", + "oktobari", + "oktobarip", "oktoberi" ], "november": [ "nov", + "novembari", + "novembarip", "novemberi" ], "december": [ "dec", + "decembari", + "decembarip", "decemberi" ], "monday": [ @@ -74,6 +100,8 @@ "arfininngorneq" ], "sunday": [ + "sap", + "sapaat", "sab", "sabaat" ], @@ -96,7 +124,8 @@ "day" ], "hour": [ - "hour" + "hour", + "hr" ], "minute": [ "minute" @@ -153,46 +182,46 @@ }, "relative-type-regex": { "\\1 day ago": [ - "for (\\d+[.,]?\\d*) ulloq unnuarlu siden" + "for (\\d++[.,]?\\d*+) ulloq unnuarlu siden" ], "\\1 hour ago": [ - "for (\\d+[.,]?\\d*) nalunaaquttap-akunnera siden" + "for (\\d++[.,]?\\d*+) nalunaaquttap-akunnera siden" ], "\\1 minute ago": [ - "for (\\d+[.,]?\\d*) minutsi siden" + "for (\\d++[.,]?\\d*+) minutsi siden" ], "\\1 month ago": [ - "for (\\d+[.,]?\\d*) qaammat siden" + "for (\\d++[.,]?\\d*+) qaammat siden" ], "\\1 second ago": [ - "for (\\d+[.,]?\\d*) sekundi siden" + "for (\\d++[.,]?\\d*+) sekundi siden" ], "\\1 week ago": [ - "for (\\d+[.,]?\\d*) sapaatip-akunnera siden" + "for (\\d++[.,]?\\d*+) sapaatip-akunnera siden" ], "\\1 year ago": [ - "for (\\d+[.,]?\\d*) ukioq siden" + "for (\\d++[.,]?\\d*+) ukioq siden" ], "in \\1 day": [ - "om (\\d+[.,]?\\d*) ulloq unnuarlu" + "om (\\d++[.,]?\\d*+) ulloq unnuarlu" ], "in \\1 hour": [ - "om (\\d+[.,]?\\d*) nalunaaquttap-akunnera" + "om (\\d++[.,]?\\d*+) nalunaaquttap-akunnera" ], "in \\1 minute": [ - "om (\\d+[.,]?\\d*) minutsi" + "om (\\d++[.,]?\\d*+) minutsi" ], "in \\1 month": [ - "om (\\d+[.,]?\\d*) qaammat" + "om (\\d++[.,]?\\d*+) qaammat" ], "in \\1 second": [ - "om (\\d+[.,]?\\d*) sekundi" + "om (\\d++[.,]?\\d*+) sekundi" ], "in \\1 week": [ - "om (\\d+[.,]?\\d*) sapaatip-akunnera" + "om (\\d++[.,]?\\d*+) sapaatip-akunnera" ], "in \\1 year": [ - "om (\\d+[.,]?\\d*) ukioq" + "om (\\d++[.,]?\\d*+) ukioq" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/kln.py b/dateparser/data/date_translation_data/kln.py index 0eec0d7a4..4e1b2d7a3 100644 --- a/dateparser/data/date_translation_data/kln.py +++ b/dateparser/data/date_translation_data/kln.py @@ -98,6 +98,7 @@ "betut" ], "hour": [ + "hr", "sait" ], "minute": [ diff --git a/dateparser/data/date_translation_data/km.py b/dateparser/data/date_translation_data/km.py index cda9dad61..279e71bab 100644 --- a/dateparser/data/date_translation_data/km.py +++ b/dateparser/data/date_translation_data/km.py @@ -38,6 +38,7 @@ "ធ្នូ" ], "monday": [ + "ចន្ទ", "ច័ន្ទ" ], "tuesday": [ @@ -47,6 +48,7 @@ "ពុធ" ], "thursday": [ + "ព្រហ", "ព្រហស្បតិ៍" ], "friday": [ @@ -135,49 +137,49 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) ថ្ងៃ​មុន", - "(\\d+[.,]?\\d*) ថ្ងៃ​​មុន" + "(\\d++[.,]?\\d*+) ថ្ងៃ​មុន", + "(\\d++[.,]?\\d*+) ថ្ងៃ​​មុន" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) ម៉ោង​មុន" + "(\\d++[.,]?\\d*+) ម៉ោង​មុន" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) នាទី​មុន", - "(\\d+[.,]?\\d*) នាទី​​មុន" + "(\\d++[.,]?\\d*+) នាទី​មុន", + "(\\d++[.,]?\\d*+) នាទី​​មុន" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) ខែមុន" + "(\\d++[.,]?\\d*+) ខែមុន" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) វិនាទី​មុន" + "(\\d++[.,]?\\d*+) វិនាទី​មុន" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) សប្ដាហ៍​មុន" + "(\\d++[.,]?\\d*+) សប្ដាហ៍​មុន" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) ឆ្នាំ​មុន" + "(\\d++[.,]?\\d*+) ឆ្នាំ​មុន" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) ថ្ងៃទៀត" + "(\\d++[.,]?\\d*+) ថ្ងៃទៀត" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) ម៉ោងទៀត", - "ក្នុង​រយៈ​ពេល (\\d+[.,]?\\d*) ម៉ោង" + "(\\d++[.,]?\\d*+) ម៉ោងទៀត", + "ក្នុង​រយៈ​ពេល (\\d++[.,]?\\d*+) ម៉ោង" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) នាទីទៀត" + "(\\d++[.,]?\\d*+) នាទីទៀត" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) ខែទៀត" + "(\\d++[.,]?\\d*+) ខែទៀត" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) វិនាទីទៀត" + "(\\d++[.,]?\\d*+) វិនាទីទៀត" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) សប្ដាហ៍ទៀត" + "(\\d++[.,]?\\d*+) សប្ដាហ៍ទៀត" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) ឆ្នាំទៀត" + "(\\d++[.,]?\\d*+) ឆ្នាំទៀត" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/kn.py b/dateparser/data/date_translation_data/kn.py index d575334e8..3259a790c 100644 --- a/dateparser/data/date_translation_data/kn.py +++ b/dateparser/data/date_translation_data/kn.py @@ -92,7 +92,8 @@ "ದಿನ" ], "hour": [ - "ಗಂಟೆ" + "ಗಂಟೆ", + "ಗಂಟೆಗಳು" ], "minute": [ "ನಿಮಿಷ" @@ -150,61 +151,61 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) ದಿನಗಳ ಹಿಂದೆ", - "(\\d+[.,]?\\d*) ದಿನದ ಹಿಂದೆ" + "(\\d++[.,]?\\d*+) ದಿನಗಳ ಹಿಂದೆ", + "(\\d++[.,]?\\d*+) ದಿನದ ಹಿಂದೆ" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) ಗಂಟೆ ಹಿಂದೆ", - "(\\d+[.,]?\\d*) ಗಂಟೆಗಳ ಹಿಂದೆ" + "(\\d++[.,]?\\d*+) ಗಂಟೆ ಹಿಂದೆ", + "(\\d++[.,]?\\d*+) ಗಂಟೆಗಳ ಹಿಂದೆ" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) ನಿಮಿಷಗಳ ಹಿಂದೆ", - "(\\d+[.,]?\\d*) ನಿಮಿಷದ ಹಿಂದೆ" + "(\\d++[.,]?\\d*+) ನಿಮಿಷಗಳ ಹಿಂದೆ", + "(\\d++[.,]?\\d*+) ನಿಮಿಷದ ಹಿಂದೆ" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) ತಿಂಗಳ ಹಿಂದೆ", - "(\\d+[.,]?\\d*) ತಿಂಗಳು ಹಿಂದೆ", - "(\\d+[.,]?\\d*) ತಿಂಗಳುಗಳ ಹಿಂದೆ" + "(\\d++[.,]?\\d*+) ತಿಂಗಳ ಹಿಂದೆ", + "(\\d++[.,]?\\d*+) ತಿಂಗಳು ಹಿಂದೆ", + "(\\d++[.,]?\\d*+) ತಿಂಗಳುಗಳ ಹಿಂದೆ" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) ಸೆಕೆಂಡುಗಳ ಹಿಂದೆ", - "(\\d+[.,]?\\d*) ಸೆಕೆಂಡ್ ಹಿಂದೆ" + "(\\d++[.,]?\\d*+) ಸೆಕೆಂಡುಗಳ ಹಿಂದೆ", + "(\\d++[.,]?\\d*+) ಸೆಕೆಂಡ್ ಹಿಂದೆ" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) ವಾರಗಳ ಹಿಂದೆ", - "(\\d+[.,]?\\d*) ವಾರದ ಹಿಂದೆ" + "(\\d++[.,]?\\d*+) ವಾರಗಳ ಹಿಂದೆ", + "(\\d++[.,]?\\d*+) ವಾರದ ಹಿಂದೆ" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) ವರ್ಷಗಳ ಹಿಂದೆ", - "(\\d+[.,]?\\d*) ವರ್ಷದ ಹಿಂದೆ" + "(\\d++[.,]?\\d*+) ವರ್ಷಗಳ ಹಿಂದೆ", + "(\\d++[.,]?\\d*+) ವರ್ಷದ ಹಿಂದೆ" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) ದಿನಗಳಲ್ಲಿ", - "(\\d+[.,]?\\d*) ದಿನದಲ್ಲಿ" + "(\\d++[.,]?\\d*+) ದಿನಗಳಲ್ಲಿ", + "(\\d++[.,]?\\d*+) ದಿನದಲ್ಲಿ" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) ಗಂಟೆಗಳಲ್ಲಿ", - "(\\d+[.,]?\\d*) ಗಂಟೆಯಲ್ಲಿ" + "(\\d++[.,]?\\d*+) ಗಂಟೆಗಳಲ್ಲಿ", + "(\\d++[.,]?\\d*+) ಗಂಟೆಯಲ್ಲಿ" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) ನಿಮಿಷಗಳಲ್ಲಿ", - "(\\d+[.,]?\\d*) ನಿಮಿಷದಲ್ಲಿ" + "(\\d++[.,]?\\d*+) ನಿಮಿಷಗಳಲ್ಲಿ", + "(\\d++[.,]?\\d*+) ನಿಮಿಷದಲ್ಲಿ" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) ತಿಂಗಳಲ್ಲಿ", - "(\\d+[.,]?\\d*) ತಿಂಗಳುಗಳಲ್ಲಿ" + "(\\d++[.,]?\\d*+) ತಿಂಗಳಲ್ಲಿ", + "(\\d++[.,]?\\d*+) ತಿಂಗಳುಗಳಲ್ಲಿ" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) ಸೆಕೆಂಡ್‌ಗಳಲ್ಲಿ", - "(\\d+[.,]?\\d*) ಸೆಕೆಂಡ್‌ನಲ್ಲಿ" + "(\\d++[.,]?\\d*+) ಸೆಕೆಂಡ್‌ಗಳಲ್ಲಿ", + "(\\d++[.,]?\\d*+) ಸೆಕೆಂಡ್‌ನಲ್ಲಿ" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) ವಾರಗಳಲ್ಲಿ", - "(\\d+[.,]?\\d*) ವಾರದಲ್ಲಿ" + "(\\d++[.,]?\\d*+) ವಾರಗಳಲ್ಲಿ", + "(\\d++[.,]?\\d*+) ವಾರದಲ್ಲಿ" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) ವರ್ಷಗಳಲ್ಲಿ", - "(\\d+[.,]?\\d*) ವರ್ಷದಲ್ಲಿ" + "(\\d++[.,]?\\d*+) ವರ್ಷಗಳಲ್ಲಿ", + "(\\d++[.,]?\\d*+) ವರ್ಷದಲ್ಲಿ" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/ko.py b/dateparser/data/date_translation_data/ko.py index 6b361e07a..beb6dfc0c 100644 --- a/dateparser/data/date_translation_data/ko.py +++ b/dateparser/data/date_translation_data/ko.py @@ -86,7 +86,8 @@ "일" ], "hour": [ - "시" + "시", + "시간" ], "minute": [ "분" @@ -96,7 +97,8 @@ ], "relative-type": { "0 day ago": [ - "오늘" + "오늘", + "금일" ], "0 hour ago": [ "현재 시간" @@ -117,7 +119,8 @@ "올해" ], "1 day ago": [ - "어제" + "어제", + "작일" ], "1 month ago": [ "지난달" @@ -129,7 +132,8 @@ "작년" ], "in 1 day": [ - "내일" + "내일", + "명일" ], "in 1 month": [ "다음 달" @@ -143,49 +147,54 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*)일 전" + "(\\d++[.,]?\\d*+)일 전" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*)시간 전" + "(\\d++[.,]?\\d*+)시간 전" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*)분 전" + "(\\d++[.,]?\\d*+)분 전" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*)개월 전" + "(\\d++[.,]?\\d*+)개월 전", + "(\\d++[.,]?\\d*+)달 전" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*)초 전" + "(\\d++[.,]?\\d*+)초 전" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*)주 전" + "(\\d++[.,]?\\d*+)주 전" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*)년 전" + "(\\d++[.,]?\\d*+)년 전" ], "in \\1 day": [ - "(\\d+[.,]?\\d*)일 후" + "(\\d++[.,]?\\d*+)일 후" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*)시간 후" + "(\\d++[.,]?\\d*+)시간 후" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*)분 후" + "(\\d++[.,]?\\d*+)분 후" ], "in \\1 month": [ - "(\\d+[.,]?\\d*)개월 후" + "(\\d++[.,]?\\d*+)개월 후", + "(\\d++[.,]?\\d*+)달 후" ], "in \\1 second": [ - "(\\d+[.,]?\\d*)초 후" + "(\\d++[.,]?\\d*+)초 후" ], "in \\1 week": [ - "(\\d+[.,]?\\d*)주 후" + "(\\d++[.,]?\\d*+)주 후" ], "in \\1 year": [ - "(\\d+[.,]?\\d*)년 후" + "(\\d++[.,]?\\d*+)년 후" ] }, "locale_specific": { + "ko-CN": { + "name": "ko-CN" + }, "ko-KP": { "name": "ko-KP" } diff --git a/dateparser/data/date_translation_data/kok.py b/dateparser/data/date_translation_data/kok.py index 6422aaaea..4a631c234 100644 --- a/dateparser/data/date_translation_data/kok.py +++ b/dateparser/data/date_translation_data/kok.py @@ -1,16 +1,20 @@ info = { "name": "kok", - "date_order": "YMD", + "date_order": "DMY", "january": [ + "जाने", "जानेवारी" ], "february": [ + "फेब्रु", "फेब्रुवारी" ], "march": [ "मार्च" ], "april": [ + "एप्री", + "एप्रील", "एप्रिल" ], "may": [ @@ -20,125 +24,214 @@ "जून" ], "july": [ + "जुल", + "जुलय", "जुलै" ], "august": [ + "ऑग", + "ऑगस्ट", "ओगस्ट" ], "september": [ + "सप्टें", + "सप्टेंबर", "सेप्टेंबर" ], "october": [ + "ऑक्टो", + "ऑक्टोबर", "ओक्टोबर" ], "november": [ + "नो", "नोव्हेंबर" ], "december": [ + "डिसे", "डिसेंबर" ], "monday": [ + "सोमार", "सोम", "सोमवार" ], "tuesday": [ - "मंगळ", - "मंगळार" + "मंगळार", + "मंगळ" ], "wednesday": [ - "बुध", - "बुधवार" + "बुधवार", + "बुध" ], "thursday": [ + "बिरेस्तार", "गुरु", "गुरुवार" ], "friday": [ + "शुक्रार", "शुक्र", "शुक्रवार" ], "saturday": [ + "शेनवार", "शनि", "शनिवार" ], "sunday": [ + "आयतार", "आदित्यवार", "रवि" ], "am": [ + "am", + "सकाळ", "मपू" ], "pm": [ + "pm", + "सांज", "मनं" ], "year": [ + "वर्स", "year" ], "month": [ + "म्हयनो", "month" ], "week": [ + "सप्तक", "week" ], "day": [ + "दीस", "day" ], "hour": [ + "वर", + "वरां", "hour" ], "minute": [ + "मिनीट", "minute" ], "second": [ + "सेकंद", "second" ], "relative-type": { "0 day ago": [ + "आयज", "today" ], "0 hour ago": [ + "हें वर", "this hour" ], "0 minute ago": [ + "हें मिनीट", "this minute" ], "0 month ago": [ + "हो म्हयनो", "this month" ], "0 second ago": [ + "आतां", "now" ], "0 week ago": [ + "हो सप्तक", "this week" ], "0 year ago": [ + "हें वर्स", "this year" ], "1 day ago": [ + "काल", "yesterday" ], "1 month ago": [ + "फाटलो म्हयनो", "last month" ], "1 week ago": [ + "निमाणो सप्तक", "last week" ], "1 year ago": [ + "फाटलें वर्स", "last year" ], "in 1 day": [ + "फाल्यां", "tomorrow" ], "in 1 month": [ + "फुडलो म्हयनो", "next month" ], "in 1 week": [ + "फुडलो सप्तक", "next week" ], "in 1 year": [ + "फुडलें वर्स", "next year" ] }, + "relative-type-regex": { + "\\1 day ago": [ + "(\\d++[.,]?\\d*+) दीस आदीं" + ], + "\\1 hour ago": [ + "(\\d++[.,]?\\d*+) वरा आदीं" + ], + "\\1 minute ago": [ + "(\\d++[.,]?\\d*+) मिन्टां आदीं" + ], + "\\1 month ago": [ + "(\\d++[.,]?\\d*+) म्हयन्यां आदीं" + ], + "\\1 second ago": [ + "(\\d++[.,]?\\d*+) से आदीं", + "(\\d++[.,]?\\d*+) सेकंद आदीं" + ], + "\\1 week ago": [ + "(\\d++[.,]?\\d*+) सप्त आदीं", + "(\\d++[.,]?\\d*+) सप्तकां आदीं" + ], + "\\1 year ago": [ + "(\\d++[.,]?\\d*+) वर्स आदीं", + "(\\d++[.,]?\\d*+) वर्सां आदीं" + ], + "in \\1 day": [ + "(\\d++[.,]?\\d*+) दिसानीं" + ], + "in \\1 hour": [ + "(\\d++[.,]?\\d*+) वरांनीं" + ], + "in \\1 minute": [ + "(\\d++[.,]?\\d*+) मिन्टां" + ], + "in \\1 month": [ + "(\\d++[.,]?\\d*+) म्हयन्यानीं" + ], + "in \\1 second": [ + "(\\d++[.,]?\\d*+) सेकंदानीं" + ], + "in \\1 week": [ + "(\\d++[.,]?\\d*+) सप्तकांनीं" + ], + "in \\1 year": [ + "(\\d++[.,]?\\d*+) वर्सांनीं" + ] + }, "locale_specific": {}, "skip": [ " ", diff --git a/dateparser/data/date_translation_data/ks.py b/dateparser/data/date_translation_data/ks.py index 9f9955a50..bba7908a5 100644 --- a/dateparser/data/date_translation_data/ks.py +++ b/dateparser/data/date_translation_data/ks.py @@ -14,13 +14,15 @@ "اپریل" ], "may": [ + "مئی", "میٔ" ], "june": [ "جوٗن" ], "july": [ - "جوٗلایی" + "جوٗلایی", + "جُلَے" ], "august": [ "اگست" @@ -35,19 +37,24 @@ "نومبر" ], "december": [ - "دسمبر" + "دسمبر", + "دَسَمبَر" ], "monday": [ + "ژٔندرٕروار", + "ژٔندٕروار", "ژٔنٛدرٕروار", "ژٔنٛدٕروار" ], "tuesday": [ + "بۆموار", "بوٚموار" ], "wednesday": [ "بودوار" ], "thursday": [ + "برؠسوار", "برٛٮ۪سوار" ], "friday": [ @@ -61,15 +68,18 @@ "اَتھوار" ], "am": [ - "am" + "am", + "اے ایم" ], "pm": [ - "pm" + "pm", + "پی ایم" ], "year": [ "ؤری" ], "month": [ + "رؠتھ", "رٮ۪تھ" ], "week": [ @@ -79,12 +89,15 @@ "دۄہ" ], "hour": [ + "hr", + "گٲنٹہٕ", "گٲنٛٹہٕ" ], "minute": [ "مِنَٹ" ], "second": [ + "سؠکَنڈ", "سٮ۪کَنڑ" ], "relative-type": { @@ -98,39 +111,48 @@ "this minute" ], "0 month ago": [ + "یٕہ ریتھۍ", "this month" ], "0 second ago": [ "now" ], "0 week ago": [ + "یٕہ ہفتہ", "this week" ], "0 year ago": [ + "یٕہ ؤری", "this year" ], "1 day ago": [ "راتھ" ], "1 month ago": [ + "پٔتِم ریتھۍ", "last month" ], "1 week ago": [ + "پٔتِم ہفتہ", "last week" ], "1 year ago": [ + "پٔتِم ؤری", "last year" ], "in 1 day": [ "پگاہ" ], "in 1 month": [ + "نو ریتھۍ", "next month" ], "in 1 week": [ + "نو ہفتہ", "next week" ], "in 1 year": [ + "نو ؤری", "next year" ] }, diff --git a/dateparser/data/date_translation_data/ksb.py b/dateparser/data/date_translation_data/ksb.py index 7858d0d87..e12826389 100644 --- a/dateparser/data/date_translation_data/ksb.py +++ b/dateparser/data/date_translation_data/ksb.py @@ -95,6 +95,7 @@ "siku" ], "hour": [ + "hr", "saa" ], "minute": [ diff --git a/dateparser/data/date_translation_data/ksf.py b/dateparser/data/date_translation_data/ksf.py index 341309dbf..a57622a0b 100644 --- a/dateparser/data/date_translation_data/ksf.py +++ b/dateparser/data/date_translation_data/ksf.py @@ -96,7 +96,8 @@ "ŋwós" ], "hour": [ - "cámɛɛn" + "cámɛɛn", + "hr" ], "minute": [ "mǝnít" diff --git a/dateparser/data/date_translation_data/ksh.py b/dateparser/data/date_translation_data/ksh.py index 123828698..e540fc195 100644 --- a/dateparser/data/date_translation_data/ksh.py +++ b/dateparser/data/date_translation_data/ksh.py @@ -105,6 +105,7 @@ "hour": [ "s", "schtund", + "schtunde", "std" ], "minute": [ @@ -166,12 +167,12 @@ }, "relative-type-regex": { "\\1 year ago": [ - "vör (\\d+[.,]?\\d*) johr", - "vör (\\d+[.,]?\\d*) johre" + "vör (\\d++[.,]?\\d*+) johr", + "vör (\\d++[.,]?\\d*+) johre" ], "in \\1 year": [ - "en (\\d+[.,]?\\d*) johr", - "en (\\d+[.,]?\\d*) johre" + "en (\\d++[.,]?\\d*+) johr", + "en (\\d++[.,]?\\d*+) johre" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/kw.py b/dateparser/data/date_translation_data/kw.py index 6bc8a1453..995a898e9 100644 --- a/dateparser/data/date_translation_data/kw.py +++ b/dateparser/data/date_translation_data/kw.py @@ -96,7 +96,8 @@ "day" ], "hour": [ - "hour" + "hour", + "hr" ], "minute": [ "minute" diff --git a/dateparser/data/date_translation_data/ky.py b/dateparser/data/date_translation_data/ky.py index 847110dab..ff397deb8 100644 --- a/dateparser/data/date_translation_data/ky.py +++ b/dateparser/data/date_translation_data/ky.py @@ -147,6 +147,7 @@ "былтыр" ], "in 1 day": [ + "эртең", "эртеӊ" ], "in 1 month": [ @@ -162,64 +163,64 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) күн мурун" + "(\\d++[.,]?\\d*+) күн мурун" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) с мурн", - "(\\d+[.,]?\\d*) саат мурун" + "(\\d++[.,]?\\d*+) с мурн", + "(\\d++[.,]?\\d*+) саат мурун" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) мүн мурн", - "(\\d+[.,]?\\d*) мүн мурун", - "(\\d+[.,]?\\d*) мүнөт мурун" + "(\\d++[.,]?\\d*+) мүн мурн", + "(\\d++[.,]?\\d*+) мүн мурун", + "(\\d++[.,]?\\d*+) мүнөт мурун" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) ай мурн", - "(\\d+[.,]?\\d*) ай мурун" + "(\\d++[.,]?\\d*+) ай мурн", + "(\\d++[.,]?\\d*+) ай мурун" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) сек мурн", - "(\\d+[.,]?\\d*) сек мурун", - "(\\d+[.,]?\\d*) секунд мурун" + "(\\d++[.,]?\\d*+) сек мурн", + "(\\d++[.,]?\\d*+) сек мурун", + "(\\d++[.,]?\\d*+) секунд мурун" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) апт мурун", - "(\\d+[.,]?\\d*) апта мурун" + "(\\d++[.,]?\\d*+) апт мурун", + "(\\d++[.,]?\\d*+) апта мурун" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) жыл мурун" + "(\\d++[.,]?\\d*+) жыл мурун" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) күн кийин", - "(\\d+[.,]?\\d*) күндөн кийин" + "(\\d++[.,]?\\d*+) күн кийин", + "(\\d++[.,]?\\d*+) күндөн кийин" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) с кийн", - "(\\d+[.,]?\\d*) саат кийин", - "(\\d+[.,]?\\d*) сааттан кийин" + "(\\d++[.,]?\\d*+) с кийн", + "(\\d++[.,]?\\d*+) саат кийин", + "(\\d++[.,]?\\d*+) сааттан кийин" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) мүн кийин", - "(\\d+[.,]?\\d*) мүн кийн", - "(\\d+[.,]?\\d*) мүнөттөн кийин" + "(\\d++[.,]?\\d*+) мүн кийин", + "(\\d++[.,]?\\d*+) мүн кийн", + "(\\d++[.,]?\\d*+) мүнөттөн кийин" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) айд кийин", - "(\\d+[.,]?\\d*) айд кийн", - "(\\d+[.,]?\\d*) айдан кийин" + "(\\d++[.,]?\\d*+) айд кийин", + "(\\d++[.,]?\\d*+) айд кийн", + "(\\d++[.,]?\\d*+) айдан кийин" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) сек кийин", - "(\\d+[.,]?\\d*) сек кийн", - "(\\d+[.,]?\\d*) секунддан кийин" + "(\\d++[.,]?\\d*+) сек кийин", + "(\\d++[.,]?\\d*+) сек кийн", + "(\\d++[.,]?\\d*+) секунддан кийин" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) апт кийин", - "(\\d+[.,]?\\d*) аптадан кийин" + "(\\d++[.,]?\\d*+) апт кийин", + "(\\d++[.,]?\\d*+) аптадан кийин" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) жыл кийин", - "(\\d+[.,]?\\d*) жылдан кийин" + "(\\d++[.,]?\\d*+) жыл кийин", + "(\\d++[.,]?\\d*+) жылдан кийин" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/lag.py b/dateparser/data/date_translation_data/lag.py index b27c0e556..de84e07ac 100644 --- a/dateparser/data/date_translation_data/lag.py +++ b/dateparser/data/date_translation_data/lag.py @@ -96,6 +96,7 @@ "sikʉ" ], "hour": [ + "hr", "sáa" ], "minute": [ diff --git a/dateparser/data/date_translation_data/lb.py b/dateparser/data/date_translation_data/lb.py index 18afe1be4..48fca68dc 100644 --- a/dateparser/data/date_translation_data/lb.py +++ b/dateparser/data/date_translation_data/lb.py @@ -100,7 +100,8 @@ ], "hour": [ "st", - "stonn" + "stonn", + "stonnen" ], "minute": [ "min", @@ -159,60 +160,60 @@ }, "relative-type-regex": { "\\1 day ago": [ - "virun (\\d+[.,]?\\d*) d", - "virun (\\d+[.,]?\\d*) dag" + "virun (\\d++[.,]?\\d*+) d", + "virun (\\d++[.,]?\\d*+) dag" ], "\\1 hour ago": [ - "virun (\\d+[.,]?\\d*) st", - "virun (\\d+[.,]?\\d*) stonn" + "virun (\\d++[.,]?\\d*+) st", + "virun (\\d++[.,]?\\d*+) stonn" ], "\\1 minute ago": [ - "virun (\\d+[.,]?\\d*) min", - "virun (\\d+[.,]?\\d*) minutt" + "virun (\\d++[.,]?\\d*+) min", + "virun (\\d++[.,]?\\d*+) minutt" ], "\\1 month ago": [ - "virun (\\d+[.,]?\\d*) m", - "virun (\\d+[.,]?\\d*) mount" + "virun (\\d++[.,]?\\d*+) m", + "virun (\\d++[.,]?\\d*+) mount" ], "\\1 second ago": [ - "virun (\\d+[.,]?\\d*) sek", - "virun (\\d+[.,]?\\d*) sekonn" + "virun (\\d++[.,]?\\d*+) sek", + "virun (\\d++[.,]?\\d*+) sekonn" ], "\\1 week ago": [ - "virun (\\d+[.,]?\\d*) w", - "virun (\\d+[.,]?\\d*) woch" + "virun (\\d++[.,]?\\d*+) w", + "virun (\\d++[.,]?\\d*+) woch" ], "\\1 year ago": [ - "virun (\\d+[.,]?\\d*) j", - "virun (\\d+[.,]?\\d*) joer" + "virun (\\d++[.,]?\\d*+) j", + "virun (\\d++[.,]?\\d*+) joer" ], "in \\1 day": [ - "an (\\d+[.,]?\\d*) d", - "an (\\d+[.,]?\\d*) dag" + "an (\\d++[.,]?\\d*+) d", + "an (\\d++[.,]?\\d*+) dag" ], "in \\1 hour": [ - "an (\\d+[.,]?\\d*) st", - "an (\\d+[.,]?\\d*) stonn" + "an (\\d++[.,]?\\d*+) st", + "an (\\d++[.,]?\\d*+) stonn" ], "in \\1 minute": [ - "an (\\d+[.,]?\\d*) min", - "an (\\d+[.,]?\\d*) minutt" + "an (\\d++[.,]?\\d*+) min", + "an (\\d++[.,]?\\d*+) minutt" ], "in \\1 month": [ - "an (\\d+[.,]?\\d*) m", - "an (\\d+[.,]?\\d*) mount" + "an (\\d++[.,]?\\d*+) m", + "an (\\d++[.,]?\\d*+) mount" ], "in \\1 second": [ - "an (\\d+[.,]?\\d*) sek", - "an (\\d+[.,]?\\d*) sekonn" + "an (\\d++[.,]?\\d*+) sek", + "an (\\d++[.,]?\\d*+) sekonn" ], "in \\1 week": [ - "an (\\d+[.,]?\\d*) w", - "an (\\d+[.,]?\\d*) woch" + "an (\\d++[.,]?\\d*+) w", + "an (\\d++[.,]?\\d*+) woch" ], "in \\1 year": [ - "an (\\d+[.,]?\\d*) j", - "an (\\d+[.,]?\\d*) joer" + "an (\\d++[.,]?\\d*+) j", + "an (\\d++[.,]?\\d*+) joer" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/lg.py b/dateparser/data/date_translation_data/lg.py index 9c62fc81a..9b570e4a3 100644 --- a/dateparser/data/date_translation_data/lg.py +++ b/dateparser/data/date_translation_data/lg.py @@ -96,6 +96,7 @@ "lunaku" ], "hour": [ + "hr", "saawa" ], "minute": [ diff --git a/dateparser/data/date_translation_data/lkt.py b/dateparser/data/date_translation_data/lkt.py index 71e9586b6..8ade421dd 100644 --- a/dateparser/data/date_translation_data/lkt.py +++ b/dateparser/data/date_translation_data/lkt.py @@ -1,6 +1,6 @@ info = { "name": "lkt", - "date_order": "YMD", + "date_order": "MDY", "january": [ "wiótheȟika wí" ], @@ -77,6 +77,7 @@ "aŋpétu" ], "hour": [ + "hr", "owápȟe" ], "minute": [ @@ -134,46 +135,46 @@ }, "relative-type-regex": { "\\1 day ago": [ - "hékta (\\d+[.,]?\\d*)-čháŋ k'uŋ héhaŋ" + "hékta (\\d++[.,]?\\d*+)-čháŋ k'uŋ héhaŋ" ], "\\1 hour ago": [ - "hékta owápȟe (\\d+[.,]?\\d*) k'uŋ héhaŋ" + "hékta owápȟe (\\d++[.,]?\\d*+) k'uŋ héhaŋ" ], "\\1 minute ago": [ - "hékta oȟ'áŋkȟo (\\d+[.,]?\\d*) k'uŋ héhaŋ" + "hékta oȟ'áŋkȟo (\\d++[.,]?\\d*+) k'uŋ héhaŋ" ], "\\1 month ago": [ - "hékta wíyawapi (\\d+[.,]?\\d*) k'uŋ héhaŋ" + "hékta wíyawapi (\\d++[.,]?\\d*+) k'uŋ héhaŋ" ], "\\1 second ago": [ - "hékta okpí (\\d+[.,]?\\d*) k'uŋ héhaŋ" + "hékta okpí (\\d++[.,]?\\d*+) k'uŋ héhaŋ" ], "\\1 week ago": [ - "hékta okó (\\d+[.,]?\\d*) k'uŋ héhaŋ" + "hékta okó (\\d++[.,]?\\d*+) k'uŋ héhaŋ" ], "\\1 year ago": [ - "hékta ómakȟa (\\d+[.,]?\\d*) k'uŋ héhaŋ" + "hékta ómakȟa (\\d++[.,]?\\d*+) k'uŋ héhaŋ" ], "in \\1 day": [ - "letáŋhaŋ (\\d+[.,]?\\d*)-čháŋ kiŋháŋ" + "letáŋhaŋ (\\d++[.,]?\\d*+)-čháŋ kiŋháŋ" ], "in \\1 hour": [ - "letáŋhaŋ owápȟe (\\d+[.,]?\\d*) kiŋháŋ" + "letáŋhaŋ owápȟe (\\d++[.,]?\\d*+) kiŋháŋ" ], "in \\1 minute": [ - "letáŋhaŋ oȟ'áŋkȟo (\\d+[.,]?\\d*) kiŋháŋ" + "letáŋhaŋ oȟ'áŋkȟo (\\d++[.,]?\\d*+) kiŋháŋ" ], "in \\1 month": [ - "letáŋhaŋ wíyawapi (\\d+[.,]?\\d*) kiŋháŋ" + "letáŋhaŋ wíyawapi (\\d++[.,]?\\d*+) kiŋháŋ" ], "in \\1 second": [ - "letáŋhaŋ okpí (\\d+[.,]?\\d*) kiŋháŋ" + "letáŋhaŋ okpí (\\d++[.,]?\\d*+) kiŋháŋ" ], "in \\1 week": [ - "letáŋhaŋ okó (\\d+[.,]?\\d*) kiŋháŋ" + "letáŋhaŋ okó (\\d++[.,]?\\d*+) kiŋháŋ" ], "in \\1 year": [ - "letáŋhaŋ ómakȟa (\\d+[.,]?\\d*) kiŋháŋ" + "letáŋhaŋ ómakȟa (\\d++[.,]?\\d*+) kiŋháŋ" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/ln.py b/dateparser/data/date_translation_data/ln.py index 4e4de0a4c..ee1ad0349 100644 --- a/dateparser/data/date_translation_data/ln.py +++ b/dateparser/data/date_translation_data/ln.py @@ -96,6 +96,7 @@ "mokɔlɔ" ], "hour": [ + "hr", "ngonga" ], "minute": [ diff --git a/dateparser/data/date_translation_data/lo.py b/dateparser/data/date_translation_data/lo.py index ba6cfc897..af9e7f316 100644 --- a/dateparser/data/date_translation_data/lo.py +++ b/dateparser/data/date_translation_data/lo.py @@ -158,56 +158,57 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) ມື້ກ່ອນ" + "(\\d++[.,]?\\d*+) ມື້ກ່ອນ" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) ຊມ ກ່ອນ", - "(\\d+[.,]?\\d*) ຊົ່ວໂມງກ່ອນ" + "(\\d++[.,]?\\d*+) ຊມ ກ່ອນ", + "(\\d++[.,]?\\d*+) ຊົ່ວໂມງກ່ອນ" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) ນທ ກ່ອນ", - "(\\d+[.,]?\\d*) ນາທີກ່ອນ" + "(\\d++[.,]?\\d*+) ນທ ກ່ອນ", + "(\\d++[.,]?\\d*+) ນາທີກ່ອນ" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) ດ ກ່ອນ", - "(\\d+[.,]?\\d*) ເດືອນກ່ອນ" + "(\\d++[.,]?\\d*+) ດ ກ່ອນ", + "(\\d++[.,]?\\d*+) ເດືອນກ່ອນ" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) ວິ ກ່ອນ", - "(\\d+[.,]?\\d*) ວິນາທີກ່ອນ" + "(\\d++[.,]?\\d*+) ວິ ກ່ອນ", + "(\\d++[.,]?\\d*+) ວິນາທີກ່ອນ" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) ອທ ກ່ອນ", - "(\\d+[.,]?\\d*) ອາທິດກ່ອນ" + "(\\d++[.,]?\\d*+) ອທ ກ່ອນ", + "(\\d++[.,]?\\d*+) ອາທິດກ່ອນ" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) ປີກ່ອນ" + "(\\d++[.,]?\\d*+) ປີກ່ອນ" ], "in \\1 day": [ - "ໃນອີກ (\\d+[.,]?\\d*) ມື້" + "ໃນອີກ (\\d++[.,]?\\d*+) ມື້" ], "in \\1 hour": [ - "ໃນອີກ (\\d+[.,]?\\d*) ຊມ", - "ໃນອີກ (\\d+[.,]?\\d*) ຊົ່ວໂມງ" + "ໃນອີກ (\\d++[.,]?\\d*+) ຊມ", + "ໃນອີກ (\\d++[.,]?\\d*+) ຊົ່ວໂມງ" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) ໃນອີກ 0 ນາທີ", - "ໃນ (\\d+[.,]?\\d*) ນທ" + "ໃນ (\\d++[.,]?\\d*+) ນທ", + "ໃນອີກ (\\d++[.,]?\\d*+) ນາທີ", + "(\\d++[.,]?\\d*+) ໃນອີກ 0 ນາທີ" ], "in \\1 month": [ - "ໃນອີກ (\\d+[.,]?\\d*) ດ", - "ໃນອີກ (\\d+[.,]?\\d*) ເດືອນ" + "ໃນອີກ (\\d++[.,]?\\d*+) ດ", + "ໃນອີກ (\\d++[.,]?\\d*+) ເດືອນ" ], "in \\1 second": [ - "ໃນ (\\d+[.,]?\\d*) ວິ", - "ໃນອີກ (\\d+[.,]?\\d*) ວິນາທີ" + "ໃນ (\\d++[.,]?\\d*+) ວິ", + "ໃນອີກ (\\d++[.,]?\\d*+) ວິນາທີ" ], "in \\1 week": [ - "ໃນອີກ (\\d+[.,]?\\d*) ອທ", - "ໃນອີກ (\\d+[.,]?\\d*) ອາທິດ" + "ໃນອີກ (\\d++[.,]?\\d*+) ອທ", + "ໃນອີກ (\\d++[.,]?\\d*+) ອາທິດ" ], "in \\1 year": [ - "ໃນອີກ (\\d+[.,]?\\d*) ປີ" + "ໃນອີກ (\\d++[.,]?\\d*+) ປີ" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/lrc.py b/dateparser/data/date_translation_data/lrc.py index ee432f5ee..05b341e79 100644 --- a/dateparser/data/date_translation_data/lrc.py +++ b/dateparser/data/date_translation_data/lrc.py @@ -77,6 +77,7 @@ "روٙز" ], "hour": [ + "hr", "ساأت" ], "minute": [ diff --git a/dateparser/data/date_translation_data/lt.py b/dateparser/data/date_translation_data/lt.py index 529a2dca3..e5a959b76 100644 --- a/dateparser/data/date_translation_data/lt.py +++ b/dateparser/data/date_translation_data/lt.py @@ -114,7 +114,8 @@ "hour": [ "h", "val", - "valanda" + "valanda", + "valandos" ], "minute": [ "min", @@ -174,78 +175,101 @@ }, "relative-type-regex": { "\\1 day ago": [ - "prieš (\\d+[.,]?\\d*) d", - "prieš (\\d+[.,]?\\d*) dieną", - "prieš (\\d+[.,]?\\d*) dienų" + "prieš (\\d++[.,]?\\d*+) d", + "prieš (\\d++[.,]?\\d*+) dieną", + "prieš (\\d++[.,]?\\d*+) dienų" ], "\\1 hour ago": [ - "prieš (\\d+[.,]?\\d*) val", - "prieš (\\d+[.,]?\\d*) valandą", - "prieš (\\d+[.,]?\\d*) valandų" + "prieš (\\d++[.,]?\\d*+) val", + "prieš (\\d++[.,]?\\d*+) valandą", + "prieš (\\d++[.,]?\\d*+) valandų" ], "\\1 minute ago": [ - "prieš (\\d+[.,]?\\d*) min", - "prieš (\\d+[.,]?\\d*) minutę", - "prieš (\\d+[.,]?\\d*) minučių" + "prieš (\\d++[.,]?\\d*+) min", + "prieš (\\d++[.,]?\\d*+) minutę", + "prieš (\\d++[.,]?\\d*+) minučių" ], "\\1 month ago": [ - "prieš (\\d+[.,]?\\d*) mėn", - "prieš (\\d+[.,]?\\d*) mėnesių", - "prieš (\\d+[.,]?\\d*) mėnesį" + "prieš (\\d++[.,]?\\d*+) mėn", + "prieš (\\d++[.,]?\\d*+) mėnesių", + "prieš (\\d++[.,]?\\d*+) mėnesį" ], "\\1 second ago": [ - "prieš (\\d+[.,]?\\d*) s", - "prieš (\\d+[.,]?\\d*) sek", - "prieš (\\d+[.,]?\\d*) sekundę", - "prieš (\\d+[.,]?\\d*) sekundžių" + "prieš (\\d++[.,]?\\d*+) s", + "prieš (\\d++[.,]?\\d*+) sek", + "prieš (\\d++[.,]?\\d*+) sekundę", + "prieš (\\d++[.,]?\\d*+) sekundžių" ], "\\1 week ago": [ - "prieš (\\d+[.,]?\\d*) sav", - "prieš (\\d+[.,]?\\d*) savaitę", - "prieš (\\d+[.,]?\\d*) savaičių" + "prieš (\\d++[.,]?\\d*+) sav", + "prieš (\\d++[.,]?\\d*+) savaitę", + "prieš (\\d++[.,]?\\d*+) savaičių" ], "\\1 year ago": [ - "prieš (\\d+[.,]?\\d*) m", - "prieš (\\d+[.,]?\\d*) metus", - "prieš (\\d+[.,]?\\d*) metų" + "prieš (\\d++[.,]?\\d*+) m", + "prieš (\\d++[.,]?\\d*+) metus", + "prieš (\\d++[.,]?\\d*+) metų" ], "in \\1 day": [ - "po (\\d+[.,]?\\d*) d", - "po (\\d+[.,]?\\d*) dienos", - "po (\\d+[.,]?\\d*) dienų" + "po (\\d++[.,]?\\d*+) d", + "po (\\d++[.,]?\\d*+) dienos", + "po (\\d++[.,]?\\d*+) dienų" ], "in \\1 hour": [ - "po (\\d+[.,]?\\d*) val", - "po (\\d+[.,]?\\d*) valandos", - "po (\\d+[.,]?\\d*) valandų" + "po (\\d++[.,]?\\d*+) val", + "po (\\d++[.,]?\\d*+) valandos", + "po (\\d++[.,]?\\d*+) valandų" ], "in \\1 minute": [ - "po (\\d+[.,]?\\d*) min", - "po (\\d+[.,]?\\d*) minutės", - "po (\\d+[.,]?\\d*) minučių" + "po (\\d++[.,]?\\d*+) min", + "po (\\d++[.,]?\\d*+) minutės", + "po (\\d++[.,]?\\d*+) minučių" ], "in \\1 month": [ - "po (\\d+[.,]?\\d*) mėn", - "po (\\d+[.,]?\\d*) mėnesio", - "po (\\d+[.,]?\\d*) mėnesių" + "po (\\d++[.,]?\\d*+) mėn", + "po (\\d++[.,]?\\d*+) mėnesio", + "po (\\d++[.,]?\\d*+) mėnesių" ], "in \\1 second": [ - "po (\\d+[.,]?\\d*) s", - "po (\\d+[.,]?\\d*) sek", - "po (\\d+[.,]?\\d*) sekundės", - "po (\\d+[.,]?\\d*) sekundžių" + "po (\\d++[.,]?\\d*+) s", + "po (\\d++[.,]?\\d*+) sek", + "po (\\d++[.,]?\\d*+) sekundės", + "po (\\d++[.,]?\\d*+) sekundžių" ], "in \\1 week": [ - "po (\\d+[.,]?\\d*) sav", - "po (\\d+[.,]?\\d*) savaitės", - "po (\\d+[.,]?\\d*) savaičių" + "po (\\d++[.,]?\\d*+) sav", + "po (\\d++[.,]?\\d*+) savaitės", + "po (\\d++[.,]?\\d*+) savaičių" ], "in \\1 year": [ - "po (\\d+[.,]?\\d*) m", - "po (\\d+[.,]?\\d*) metų" + "po (\\d++[.,]?\\d*+) m", + "po (\\d++[.,]?\\d*+) metų" ] }, "locale_specific": {}, + "simplifications": [ + { + "(?<=prieš\\s+)savaitę\\b": "1 savaitę" + }, + { + "(?<=prieš\\s+)mėnesį\\b": "1 mėnesį" + }, + { + "(?<=prieš\\s+)metus\\b": "1 metus" + }, + { + "(?<=prieš\\s+)dieną\\b": "1 dieną" + }, + { + "(?<=prieš\\s+)valandą\\b": "1 valandą" + }, + { + "(?<=prieš\\s+)minutę\\b": "1 minutę" + }, + { + "(?<=prieš\\s+)sekundę\\b": "1 sekundę" + } + ], "skip": [ " ", "'", diff --git a/dateparser/data/date_translation_data/lu.py b/dateparser/data/date_translation_data/lu.py index 62d10bba7..06d9a0d9b 100644 --- a/dateparser/data/date_translation_data/lu.py +++ b/dateparser/data/date_translation_data/lu.py @@ -96,7 +96,8 @@ "dituku" ], "hour": [ - "diba" + "diba", + "hr" ], "minute": [ "kasunsu" diff --git a/dateparser/data/date_translation_data/luo.py b/dateparser/data/date_translation_data/luo.py index 19798d9f7..a01a251e5 100644 --- a/dateparser/data/date_translation_data/luo.py +++ b/dateparser/data/date_translation_data/luo.py @@ -96,6 +96,7 @@ "chieng'" ], "hour": [ + "hr", "saa" ], "minute": [ diff --git a/dateparser/data/date_translation_data/luy.py b/dateparser/data/date_translation_data/luy.py index 5fc38b56e..1fbc67e44 100644 --- a/dateparser/data/date_translation_data/luy.py +++ b/dateparser/data/date_translation_data/luy.py @@ -95,6 +95,7 @@ "ridiku" ], "hour": [ + "hr", "isaa" ], "minute": [ diff --git a/dateparser/data/date_translation_data/lv.py b/dateparser/data/date_translation_data/lv.py index 20a6fbe5e..ed1a47fe5 100644 --- a/dateparser/data/date_translation_data/lv.py +++ b/dateparser/data/date_translation_data/lv.py @@ -127,119 +127,151 @@ "šajā minūtē" ], "0 month ago": [ + "šajā mēn", "šajā mēnesī" ], "0 second ago": [ "tagad" ], "0 week ago": [ + "šajā ned", "šajā nedēļā" ], "0 year ago": [ + "šajā g", "šajā gadā" ], "1 day ago": [ "vakar" ], "1 month ago": [ + "pag mēn", "pagājušajā mēnesī" ], "1 week ago": [ + "pag ned", "pagājušajā nedēļā" ], "1 year ago": [ + "pag gadā", "pagājušajā gadā" ], "in 1 day": [ "rīt" ], "in 1 month": [ + "nāk mēn", "nākamajā mēnesī" ], "in 1 week": [ + "nāk ned", "nākamajā nedēļā" ], "in 1 year": [ + "nāk gadā", "nākamajā gadā" ] }, "relative-type-regex": { "\\1 day ago": [ - "pirms (\\d+[.,]?\\d*) d", - "pirms (\\d+[.,]?\\d*) dienas", - "pirms (\\d+[.,]?\\d*) dienām" + "pirms (\\d++[.,]?\\d*+) d", + "pirms (\\d++[.,]?\\d*+) dienas", + "pirms (\\d++[.,]?\\d*+) dienām" ], "\\1 hour ago": [ - "pirms (\\d+[.,]?\\d*) h", - "pirms (\\d+[.,]?\\d*) st", - "pirms (\\d+[.,]?\\d*) stundas", - "pirms (\\d+[.,]?\\d*) stundām" + "pirms (\\d++[.,]?\\d*+) h", + "pirms (\\d++[.,]?\\d*+) st", + "pirms (\\d++[.,]?\\d*+) stundas", + "pirms (\\d++[.,]?\\d*+) stundām" ], "\\1 minute ago": [ - "pirms (\\d+[.,]?\\d*) min", - "pirms (\\d+[.,]?\\d*) minūtes", - "pirms (\\d+[.,]?\\d*) minūtēm" + "pirms (\\d++[.,]?\\d*+) min", + "pirms (\\d++[.,]?\\d*+) minūtes", + "pirms (\\d++[.,]?\\d*+) minūtēm" ], "\\1 month ago": [ - "pirms (\\d+[.,]?\\d*) mēn", - "pirms (\\d+[.,]?\\d*) mēneša", - "pirms (\\d+[.,]?\\d*) mēnešiem" + "pirms (\\d++[.,]?\\d*+) mēn", + "pirms (\\d++[.,]?\\d*+) mēneša", + "pirms (\\d++[.,]?\\d*+) mēnešiem" ], "\\1 second ago": [ - "pirms (\\d+[.,]?\\d*) s", - "pirms (\\d+[.,]?\\d*) sek", - "pirms (\\d+[.,]?\\d*) sekundes", - "pirms (\\d+[.,]?\\d*) sekundēm" + "pirms (\\d++[.,]?\\d*+) s", + "pirms (\\d++[.,]?\\d*+) sek", + "pirms (\\d++[.,]?\\d*+) sekundes", + "pirms (\\d++[.,]?\\d*+) sekundēm" ], "\\1 week ago": [ - "pirms (\\d+[.,]?\\d*) ned", - "pirms (\\d+[.,]?\\d*) nedēļas", - "pirms (\\d+[.,]?\\d*) nedēļām" + "pirms (\\d++[.,]?\\d*+) ned", + "pirms (\\d++[.,]?\\d*+) nedēļas", + "pirms (\\d++[.,]?\\d*+) nedēļām" ], "\\1 year ago": [ - "pirms (\\d+[.,]?\\d*) g", - "pirms (\\d+[.,]?\\d*) gada", - "pirms (\\d+[.,]?\\d*) gadiem" + "pirms (\\d++[.,]?\\d*+) g", + "pirms (\\d++[.,]?\\d*+) gada", + "pirms (\\d++[.,]?\\d*+) gadiem" ], "in \\1 day": [ - "pēc (\\d+[.,]?\\d*) d", - "pēc (\\d+[.,]?\\d*) dienas", - "pēc (\\d+[.,]?\\d*) dienām" + "pēc (\\d++[.,]?\\d*+) d", + "pēc (\\d++[.,]?\\d*+) dienas", + "pēc (\\d++[.,]?\\d*+) dienām" ], "in \\1 hour": [ - "pēc (\\d+[.,]?\\d*) h", - "pēc (\\d+[.,]?\\d*) st", - "pēc (\\d+[.,]?\\d*) stundas", - "pēc (\\d+[.,]?\\d*) stundām" + "pēc (\\d++[.,]?\\d*+) h", + "pēc (\\d++[.,]?\\d*+) st", + "pēc (\\d++[.,]?\\d*+) stundas", + "pēc (\\d++[.,]?\\d*+) stundām" ], "in \\1 minute": [ - "pēc (\\d+[.,]?\\d*) min", - "pēc (\\d+[.,]?\\d*) minūtes", - "pēc (\\d+[.,]?\\d*) minūtēm" + "pēc (\\d++[.,]?\\d*+) min", + "pēc (\\d++[.,]?\\d*+) minūtes", + "pēc (\\d++[.,]?\\d*+) minūtēm" ], "in \\1 month": [ - "pēc (\\d+[.,]?\\d*) mēn", - "pēc (\\d+[.,]?\\d*) mēneša", - "pēc (\\d+[.,]?\\d*) mēnešiem" + "pēc (\\d++[.,]?\\d*+) mēn", + "pēc (\\d++[.,]?\\d*+) mēneša", + "pēc (\\d++[.,]?\\d*+) mēnešiem" ], "in \\1 second": [ - "pēc (\\d+[.,]?\\d*) s", - "pēc (\\d+[.,]?\\d*) sek", - "pēc (\\d+[.,]?\\d*) sekundes", - "pēc (\\d+[.,]?\\d*) sekundēm" + "pēc (\\d++[.,]?\\d*+) s", + "pēc (\\d++[.,]?\\d*+) sek", + "pēc (\\d++[.,]?\\d*+) sekundes", + "pēc (\\d++[.,]?\\d*+) sekundēm" ], "in \\1 week": [ - "pēc (\\d+[.,]?\\d*) ned", - "pēc (\\d+[.,]?\\d*) nedēļas", - "pēc (\\d+[.,]?\\d*) nedēļām" + "pēc (\\d++[.,]?\\d*+) ned", + "pēc (\\d++[.,]?\\d*+) nedēļas", + "pēc (\\d++[.,]?\\d*+) nedēļām" ], "in \\1 year": [ - "pēc (\\d+[.,]?\\d*) g", - "pēc (\\d+[.,]?\\d*) gada", - "pēc (\\d+[.,]?\\d*) gadiem" + "pēc (\\d++[.,]?\\d*+) g", + "pēc (\\d++[.,]?\\d*+) gada", + "pēc (\\d++[.,]?\\d*+) gadiem" ] }, "locale_specific": {}, + "simplifications": [ + { + "(?<=pirms\\s+)nedēļas\\b": "1 nedēļas" + }, + { + "(?<=pirms\\s+)mēneša\\b": "1 mēneša" + }, + { + "(?<=pirms\\s+)gada\\b": "1 gada" + }, + { + "(?<=pirms\\s+)dienas\\b": "1 dienas" + }, + { + "(?<=pirms\\s+)stundas\\b": "1 stundas" + }, + { + "(?<=pirms\\s+)minūtes\\b": "1 minūtes" + }, + { + "(?<=pirms\\s+)sekundes\\b": "1 sekundes" + } + ], "skip": [ " ", "'", diff --git a/dateparser/data/date_translation_data/mas.py b/dateparser/data/date_translation_data/mas.py index 6efd2de13..6a2df5966 100644 --- a/dateparser/data/date_translation_data/mas.py +++ b/dateparser/data/date_translation_data/mas.py @@ -96,6 +96,7 @@ "ɛnkɔlɔ́ŋ" ], "hour": [ + "hr", "ɛ́sáâ" ], "minute": [ diff --git a/dateparser/data/date_translation_data/mer.py b/dateparser/data/date_translation_data/mer.py index 0901e1a47..617f649ab 100644 --- a/dateparser/data/date_translation_data/mer.py +++ b/dateparser/data/date_translation_data/mer.py @@ -95,6 +95,7 @@ "ntukũ" ], "hour": [ + "hr", "ĩthaa" ], "minute": [ diff --git a/dateparser/data/date_translation_data/mfe.py b/dateparser/data/date_translation_data/mfe.py index fc418155a..d84bf357a 100644 --- a/dateparser/data/date_translation_data/mfe.py +++ b/dateparser/data/date_translation_data/mfe.py @@ -93,6 +93,7 @@ "zour" ], "hour": [ + "hr", "ler" ], "minute": [ diff --git a/dateparser/data/date_translation_data/mg.py b/dateparser/data/date_translation_data/mg.py index 754beb34b..72b9ce371 100644 --- a/dateparser/data/date_translation_data/mg.py +++ b/dateparser/data/date_translation_data/mg.py @@ -95,6 +95,7 @@ "andro" ], "hour": [ + "hr", "ora" ], "minute": [ diff --git a/dateparser/data/date_translation_data/mgh.py b/dateparser/data/date_translation_data/mgh.py index e0dba84eb..573fc3b7a 100644 --- a/dateparser/data/date_translation_data/mgh.py +++ b/dateparser/data/date_translation_data/mgh.py @@ -96,6 +96,7 @@ "nihuku" ], "hour": [ + "hr", "isaa" ], "minute": [ diff --git a/dateparser/data/date_translation_data/mgo.py b/dateparser/data/date_translation_data/mgo.py index 0ff37bb27..2b9839939 100644 --- a/dateparser/data/date_translation_data/mgo.py +++ b/dateparser/data/date_translation_data/mgo.py @@ -78,7 +78,8 @@ "anəg" ], "hour": [ - "hour" + "hour", + "hr" ], "minute": [ "minute" diff --git a/dateparser/data/date_translation_data/mk.py b/dateparser/data/date_translation_data/mk.py index 01762fa10..744d997fe 100644 --- a/dateparser/data/date_translation_data/mk.py +++ b/dateparser/data/date_translation_data/mk.py @@ -33,16 +33,18 @@ "август" ], "september": [ - "септ", - "септември" + "сеп", + "септември", + "септ" ], "october": [ "окт", "октомври" ], "november": [ - "ноем", - "ноември" + "ное", + "ноември", + "ноем" ], "december": [ "дек", @@ -53,9 +55,9 @@ "понеделник" ], "tuesday": [ - "вт", "вто", - "вторник" + "вторник", + "вт" ], "wednesday": [ "сре", @@ -94,14 +96,16 @@ "месец" ], "week": [ - "недела", - "сед" + "сед", + "седмица" ], "day": [ "ден" ], "hour": [ - "час" + "ч", + "час", + "часа" ], "minute": [ "мин", @@ -131,6 +135,7 @@ "оваа седмица" ], "0 year ago": [ + "оваа год", "оваа година" ], "1 day ago": [ @@ -143,6 +148,8 @@ "минатата седмица" ], "1 year ago": [ + "лани", + "минатата год", "минатата година" ], "in 1 day": [ @@ -155,68 +162,96 @@ "следната седмица" ], "in 1 year": [ + "догодина", + "следната год", "следната година" ] }, "relative-type-regex": { "\\1 day ago": [ - "пред (\\d+[.,]?\\d*) ден", - "пред (\\d+[.,]?\\d*) дена" + "пред (\\d++[.,]?\\d*+) ден", + "пред (\\d++[.,]?\\d*+) дена" ], "\\1 hour ago": [ - "пред (\\d+[.,]?\\d*) час", - "пред (\\d+[.,]?\\d*) часа" + "пред (\\d++[.,]?\\d*+) час", + "пред (\\d++[.,]?\\d*+) часа" ], "\\1 minute ago": [ - "пред (\\d+[.,]?\\d*) минута", - "пред (\\d+[.,]?\\d*) минути" + "пред (\\d++[.,]?\\d*+) мин", + "пред (\\d++[.,]?\\d*+) минута", + "пред (\\d++[.,]?\\d*+) минути" ], "\\1 month ago": [ - "пред (\\d+[.,]?\\d*) месец", - "пред (\\d+[.,]?\\d*) месеци" + "пред (\\d++[.,]?\\d*+) месец", + "пред (\\d++[.,]?\\d*+) месеци" ], "\\1 second ago": [ - "пред (\\d+[.,]?\\d*) секунда", - "пред (\\d+[.,]?\\d*) секунди" + "пред (\\d++[.,]?\\d*+) сек", + "пред (\\d++[.,]?\\d*+) секунда", + "пред (\\d++[.,]?\\d*+) секунди" ], "\\1 week ago": [ - "пред (\\d+[.,]?\\d*) седмица", - "пред (\\d+[.,]?\\d*) седмици" + "пред (\\d++[.,]?\\d*+) седмица", + "пред (\\d++[.,]?\\d*+) седмици" ], "\\1 year ago": [ - "пред (\\d+[.,]?\\d*) година", - "пред (\\d+[.,]?\\d*) години" + "пред (\\d++[.,]?\\d*+) год", + "пред (\\d++[.,]?\\d*+) година", + "пред (\\d++[.,]?\\d*+) години" ], "in \\1 day": [ - "за (\\d+[.,]?\\d*) ден", - "за (\\d+[.,]?\\d*) дена" + "за (\\d++[.,]?\\d*+) ден", + "за (\\d++[.,]?\\d*+) дена" ], "in \\1 hour": [ - "за (\\d+[.,]?\\d*) час", - "за (\\d+[.,]?\\d*) часа" + "за (\\d++[.,]?\\d*+) час", + "за (\\d++[.,]?\\d*+) часа" ], "in \\1 minute": [ - "за (\\d+[.,]?\\d*) минута", - "за (\\d+[.,]?\\d*) минути" + "за (\\d++[.,]?\\d*+) мин", + "за (\\d++[.,]?\\d*+) минута", + "за (\\d++[.,]?\\d*+) минути" ], "in \\1 month": [ - "за (\\d+[.,]?\\d*) месец", - "за (\\d+[.,]?\\d*) месеци" + "за (\\d++[.,]?\\d*+) месец", + "за (\\d++[.,]?\\d*+) месеци" ], "in \\1 second": [ - "за (\\d+[.,]?\\d*) секунда", - "за (\\d+[.,]?\\d*) секунди" + "за (\\d++[.,]?\\d*+) сек", + "за (\\d++[.,]?\\d*+) секунда", + "за (\\d++[.,]?\\d*+) секунди" ], "in \\1 week": [ - "за (\\d+[.,]?\\d*) седмица", - "за (\\d+[.,]?\\d*) седмици" + "за (\\d++[.,]?\\d*+) седмица", + "за (\\d++[.,]?\\d*+) седмици" ], "in \\1 year": [ - "за (\\d+[.,]?\\d*) година", - "за (\\d+[.,]?\\d*) години" + "за (\\d++[.,]?\\d*+) год", + "за (\\d++[.,]?\\d*+) година", + "за (\\d++[.,]?\\d*+) години" ] }, "locale_specific": {}, + "simplifications": [ + { + "(?<=пред\\s+)седмица\\b": "1 седмица" + }, + { + "(?<=пред\\s+)месец\\b": "1 месец" + }, + { + "(?<=пред\\s+)година\\b": "1 година" + }, + { + "(?<=пред\\s+)ден\\b": "1 ден" + }, + { + "(?<=пред\\s+)час\\b": "1 час" + }, + { + "(?<=пред\\s+)минута\\b": "1 минута" + } + ], "skip": [ " ", "'", diff --git a/dateparser/data/date_translation_data/ml.py b/dateparser/data/date_translation_data/ml.py index 1b95fa1e3..bda893fcf 100644 --- a/dateparser/data/date_translation_data/ml.py +++ b/dateparser/data/date_translation_data/ml.py @@ -157,46 +157,46 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) ദിവസം മുമ്പ്" + "(\\d++[.,]?\\d*+) ദിവസം മുമ്പ്" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) മണിക്കൂർ മുമ്പ്" + "(\\d++[.,]?\\d*+) മണിക്കൂർ മുമ്പ്" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) മിനിറ്റ് മുമ്പ്" + "(\\d++[.,]?\\d*+) മിനിറ്റ് മുമ്പ്" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) മാസം മുമ്പ്" + "(\\d++[.,]?\\d*+) മാസം മുമ്പ്" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) സെക്കൻഡ് മുമ്പ്" + "(\\d++[.,]?\\d*+) സെക്കൻഡ് മുമ്പ്" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) ആഴ്ച മുമ്പ്" + "(\\d++[.,]?\\d*+) ആഴ്ച മുമ്പ്" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) വർഷം മുമ്പ്" + "(\\d++[.,]?\\d*+) വർഷം മുമ്പ്" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) ദിവസത്തിൽ" + "(\\d++[.,]?\\d*+) ദിവസത്തിൽ" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) മണിക്കൂറിൽ" + "(\\d++[.,]?\\d*+) മണിക്കൂറിൽ" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) മിനിറ്റിൽ" + "(\\d++[.,]?\\d*+) മിനിറ്റിൽ" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) മാസത്തിൽ" + "(\\d++[.,]?\\d*+) മാസത്തിൽ" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) സെക്കൻഡിൽ" + "(\\d++[.,]?\\d*+) സെക്കൻഡിൽ" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) ആഴ്ചയിൽ" + "(\\d++[.,]?\\d*+) ആഴ്ചയിൽ" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) വർഷത്തിൽ" + "(\\d++[.,]?\\d*+) വർഷത്തിൽ" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/mn.py b/dateparser/data/date_translation_data/mn.py index 32fc895d8..484977e9b 100644 --- a/dateparser/data/date_translation_data/mn.py +++ b/dateparser/data/date_translation_data/mn.py @@ -23,10 +23,12 @@ ], "june": [ "6-р сар", + "зургаадугаар сар", "зургадугаар сар" ], "july": [ "7-р сар", + "долоодугаар сар", "долдугаар сар" ], "august": [ @@ -90,8 +92,9 @@ "сар" ], "week": [ - "7х", - "долоо хоног" + "7 хоног", + "долоо хоног", + "7х" ], "day": [ "өдөр" @@ -125,6 +128,7 @@ "одоо" ], "0 week ago": [ + "энэ 7 хоног", "энэ долоо хоног" ], "0 year ago": [ @@ -137,6 +141,7 @@ "өнгөрсөн сар" ], "1 week ago": [ + "өнгөрсөн 7 хоног", "өнгөрсөн долоо хоног" ], "1 year ago": [ @@ -149,6 +154,7 @@ "ирэх сар" ], "in 1 week": [ + "ирэх 7 хоног", "ирэх долоо хоног" ], "in 1 year": [ @@ -157,53 +163,57 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) өдрийн өмнө" + "(\\d++[.,]?\\d*+) өдрийн өмнө" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) ц өмнө", - "(\\d+[.,]?\\d*) цагийн өмнө" + "(\\d++[.,]?\\d*+) ц өмнө", + "(\\d++[.,]?\\d*+) цагийн өмнө" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) мин өмнө", - "(\\d+[.,]?\\d*) минутын өмнө" + "(\\d++[.,]?\\d*+) мин өмнө", + "(\\d++[.,]?\\d*+) минутын өмнө" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) сарын өмнө" + "(\\d++[.,]?\\d*+) сарын өмнө" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) сек өмнө", - "(\\d+[.,]?\\d*) секундын өмнө" + "(\\d++[.,]?\\d*+) сек өмнө", + "(\\d++[.,]?\\d*+) секундын өмнө" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) 7х-ийн өмнө" + "(\\d++[.,]?\\d*+) 7 хоногийн өмнө", + "(\\d++[.,]?\\d*+) долоо хоногийн өмнө", + "(\\d++[.,]?\\d*+) 7х-ийн өмнө" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) жилийн өмнө" + "(\\d++[.,]?\\d*+) жилийн өмнө" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) өдрийн дараа", - "(\\d+[.,]?\\d*) өдөрт" + "(\\d++[.,]?\\d*+) өдрийн дараа", + "(\\d++[.,]?\\d*+) өдөрт" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) ц дараа", - "(\\d+[.,]?\\d*) цагийн дараа" + "(\\d++[.,]?\\d*+) ц дараа", + "(\\d++[.,]?\\d*+) цагийн дараа" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) мин дараа", - "(\\d+[.,]?\\d*) минутын дараа" + "(\\d++[.,]?\\d*+) мин дараа", + "(\\d++[.,]?\\d*+) минутын дараа" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) сарын дараа" + "(\\d++[.,]?\\d*+) сарын дараа" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) сек дараа", - "(\\d+[.,]?\\d*) секундын дараа" + "(\\d++[.,]?\\d*+) сек дараа", + "(\\d++[.,]?\\d*+) секундын дараа" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) 7х-ийн дараа" + "(\\d++[.,]?\\d*+) 7 хоногийн дараа", + "(\\d++[.,]?\\d*+) долоо хоногийн дараа", + "(\\d++[.,]?\\d*+) 7х-ийн дараа" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) жилийн дараа" + "(\\d++[.,]?\\d*+) жилийн дараа" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/mr.py b/dateparser/data/date_translation_data/mr.py index 1fecbd7c3..d1960ed0b 100644 --- a/dateparser/data/date_translation_data/mr.py +++ b/dateparser/data/date_translation_data/mr.py @@ -74,24 +74,30 @@ "रविवार" ], "am": [ + "am", "मपू" ], "pm": [ + "pm", "मउ" ], "year": [ "वर्ष" ], "month": [ + "म", "महिना" ], "week": [ + "आठ", "आठवडा" ], "day": [ + "दि", "दिवस" ], "hour": [ + "ता", "तास" ], "minute": [ @@ -151,64 +157,75 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) दिवसांपूर्वी", - "(\\d+[.,]?\\d*) दिवसापूर्वी" + "(\\d++[.,]?\\d*+) दिवसांपूर्वी", + "(\\d++[.,]?\\d*+) दिवसापूर्वी" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) तासांपूर्वी", - "(\\d+[.,]?\\d*) तासापूर्वी" + "(\\d++[.,]?\\d*+) तासांपूर्वी", + "(\\d++[.,]?\\d*+) तासापूर्वी" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) मिनि पूर्वी", - "(\\d+[.,]?\\d*) मिनिटांपूर्वी", - "(\\d+[.,]?\\d*) मिनिटापूर्वी" + "(\\d++[.,]?\\d*+) मिनि पूर्वी", + "(\\d++[.,]?\\d*+) मिनिटांपूर्वी", + "(\\d++[.,]?\\d*+) मिनिटापूर्वी" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) महिन्यांपूर्वी", - "(\\d+[.,]?\\d*) महिन्यापूर्वी" + "(\\d++[.,]?\\d*+) महिन्यांपूर्वी", + "(\\d++[.,]?\\d*+) महिन्यापूर्वी" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) से पूर्वी", - "(\\d+[.,]?\\d*) सेकंदांपूर्वी", - "(\\d+[.,]?\\d*) सेकंदापूर्वी" + "(\\d++[.,]?\\d*+) से पूर्वी", + "(\\d++[.,]?\\d*+) सेकंदांपूर्वी", + "(\\d++[.,]?\\d*+) सेकंदापूर्वी" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) आठवड्यांपूर्वी", - "(\\d+[.,]?\\d*) आठवड्यापूर्वी" + "(\\d++[.,]?\\d*+) आठवड्यांपूर्वी", + "(\\d++[.,]?\\d*+) आठवड्यापूर्वी" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) वर्षांपूर्वी", - "(\\d+[.,]?\\d*) वर्षापूर्वी" + "(\\d++[.,]?\\d*+) वर्षांपूर्वी", + "(\\d++[.,]?\\d*+) वर्षापूर्वी" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) दिवसांमध्ये", - "(\\d+[.,]?\\d*) दिवसामध्ये" + "(\\d++[.,]?\\d*+) दिवसांमध्ये", + "(\\d++[.,]?\\d*+) दिवसामध्ये", + "येत्या (\\d++[.,]?\\d*+) दिवसांमध्ये", + "येत्या (\\d++[.,]?\\d*+) दिवसामध्ये" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) तासांमध्ये", - "(\\d+[.,]?\\d*) तासामध्ये" + "(\\d++[.,]?\\d*+) तासांमध्ये", + "(\\d++[.,]?\\d*+) तासामध्ये", + "येत्या (\\d++[.,]?\\d*+) तासांमध्ये", + "येत्या (\\d++[.,]?\\d*+) तासामध्ये" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) मिनि मध्ये", - "(\\d+[.,]?\\d*) मिनिटांमध्ये", - "(\\d+[.,]?\\d*) मिनिटामध्ये" + "(\\d++[.,]?\\d*+) मिनि मध्ये", + "(\\d++[.,]?\\d*+) मिनिटांमध्ये", + "(\\d++[.,]?\\d*+) मिनिटामध्ये" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) महिन्यांमध्ये", - "(\\d+[.,]?\\d*) महिन्यामध्ये" + "(\\d++[.,]?\\d*+) महिन्यांमध्ये", + "(\\d++[.,]?\\d*+) महिन्यामध्ये", + "येत्या (\\d++[.,]?\\d*+) महिन्यांमध्ये", + "येत्या (\\d++[.,]?\\d*+) महिन्यामध्ये" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) से मध्ये", - "(\\d+[.,]?\\d*) सेकंदांमध्ये", - "(\\d+[.,]?\\d*) सेकंदामध्ये" + "(\\d++[.,]?\\d*+) से मध्ये", + "(\\d++[.,]?\\d*+) सेकंदांमध्ये", + "(\\d++[.,]?\\d*+) सेकंदामध्ये", + "येत्या (\\d++[.,]?\\d*+) से मध्ये" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) आठवड्यांमध्ये", - "(\\d+[.,]?\\d*) आठवड्यामध्ये" + "(\\d++[.,]?\\d*+) आठवड्यांमध्ये", + "(\\d++[.,]?\\d*+) आठवड्यामध्ये", + "येत्या (\\d++[.,]?\\d*+) आठवड्यांमध्ये", + "येत्या (\\d++[.,]?\\d*+) आठवड्यामध्ये" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) वर्षांमध्ये", - "(\\d+[.,]?\\d*) वर्षामध्ये" + "(\\d++[.,]?\\d*+) वर्षांमध्ये", + "(\\d++[.,]?\\d*+) वर्षामध्ये", + "येत्या (\\d++[.,]?\\d*+) वर्षांमध्ये", + "येत्या (\\d++[.,]?\\d*+) वर्षामध्ये" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/ms.py b/dateparser/data/date_translation_data/ms.py index b685742bc..eb2d66b9b 100644 --- a/dateparser/data/date_translation_data/ms.py +++ b/dateparser/data/date_translation_data/ms.py @@ -123,6 +123,7 @@ "sekarang" ], "0 week ago": [ + "mgu ini", "minggu ini", "mng ini" ], @@ -139,6 +140,7 @@ "bulan lalu" ], "1 week ago": [ + "mgu lepas", "minggu lalu", "mng lepas" ], @@ -154,6 +156,7 @@ "bulan depan" ], "in 1 week": [ + "mgu depan", "minggu depan", "mng depan" ], @@ -164,63 +167,66 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) hari lalu" + "(\\d++[.,]?\\d*+) hari lalu" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) jam lalu" + "(\\d++[.,]?\\d*+) jam lalu" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) min lalu", - "(\\d+[.,]?\\d*) minit lalu" + "(\\d++[.,]?\\d*+) min lalu", + "(\\d++[.,]?\\d*+) minit lalu" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) bln lalu", - "(\\d+[.,]?\\d*) bulan lalu" + "(\\d++[.,]?\\d*+) bln lalu", + "(\\d++[.,]?\\d*+) bulan lalu" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) saat lalu" + "(\\d++[.,]?\\d*+) saat lalu" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) mgu lalu", - "(\\d+[.,]?\\d*) minggu lalu" + "(\\d++[.,]?\\d*+) mgu lalu", + "(\\d++[.,]?\\d*+) minggu lalu" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) tahun lalu", - "(\\d+[.,]?\\d*) thn lalu" + "(\\d++[.,]?\\d*+) tahun lalu", + "(\\d++[.,]?\\d*+) thn lalu" ], "in \\1 day": [ - "dalam (\\d+[.,]?\\d*) hari", - "dlm (\\d+[.,]?\\d*) hari" + "dalam (\\d++[.,]?\\d*+) hari", + "dlm (\\d++[.,]?\\d*+) hari" ], "in \\1 hour": [ - "dalam (\\d+[.,]?\\d*) jam", - "dlm (\\d+[.,]?\\d*) jam" + "dalam (\\d++[.,]?\\d*+) jam", + "dlm (\\d++[.,]?\\d*+) jam" ], "in \\1 minute": [ - "dalam (\\d+[.,]?\\d*) minit", - "dlm (\\d+[.,]?\\d*) min" + "dalam (\\d++[.,]?\\d*+) minit", + "dlm (\\d++[.,]?\\d*+) min" ], "in \\1 month": [ - "dalam (\\d+[.,]?\\d*) bulan", - "dlm (\\d+[.,]?\\d*) bln" + "dalam (\\d++[.,]?\\d*+) bulan", + "dlm (\\d++[.,]?\\d*+) bln" ], "in \\1 second": [ - "dalam (\\d+[.,]?\\d*) saat", - "dlm (\\d+[.,]?\\d*) saat" + "dalam (\\d++[.,]?\\d*+) saat", + "dlm (\\d++[.,]?\\d*+) saat" ], "in \\1 week": [ - "dalam (\\d+[.,]?\\d*) minggu", - "dlm (\\d+[.,]?\\d*) mgu" + "dalam (\\d++[.,]?\\d*+) minggu", + "dlm (\\d++[.,]?\\d*+) mgu" ], "in \\1 year": [ - "dalam (\\d+[.,]?\\d*) saat", - "dalam (\\d+[.,]?\\d*) thn" + "dalam (\\d++[.,]?\\d*+) tahun", + "dalam (\\d++[.,]?\\d*+) thn" ] }, "locale_specific": { "ms-BN": { "name": "ms-BN" }, + "ms-ID": { + "name": "ms-ID" + }, "ms-SG": { "name": "ms-SG" } diff --git a/dateparser/data/date_translation_data/mt.py b/dateparser/data/date_translation_data/mt.py index d11cb0580..ab7cbfe93 100644 --- a/dateparser/data/date_translation_data/mt.py +++ b/dateparser/data/date_translation_data/mt.py @@ -84,24 +84,31 @@ "pm" ], "year": [ - "sena" + "sena", + "sn" ], "month": [ "xahar" ], "week": [ - "ġimgħa" + "ġimgħa", + "ġm" ], "day": [ "jum" ], "hour": [ + "hr", "siegħa" ], "minute": [ + "m", + "min", "minuta" ], "second": [ + "s", + "sek", "sekonda" ], "relative-type": { @@ -109,15 +116,18 @@ "illum" ], "0 hour ago": [ + "din is-siegħa", "this hour" ], "0 minute ago": [ + "din il-minuta", "this minute" ], "0 month ago": [ "dan ix-xahar" ], "0 second ago": [ + "issa", "now" ], "0 week ago": [ @@ -127,6 +137,7 @@ "din is-sena" ], "1 day ago": [ + "lbieraħ", "ilbieraħ" ], "1 month ago": [ @@ -136,6 +147,7 @@ "il-ġimgħa li għaddiet" ], "1 year ago": [ + "is-sena l-oħra", "is-sena li għaddiet" ], "in 1 day": [ @@ -152,9 +164,53 @@ ] }, "relative-type-regex": { + "\\1 day ago": [ + "(\\d++[.,]?\\d*+) ġurnata ilu" + ], + "\\1 hour ago": [ + "(\\d++[.,]?\\d*+) siegħa ilu" + ], + "\\1 minute ago": [ + "(\\d++[.,]?\\d*+) min ilu", + "(\\d++[.,]?\\d*+) minuta ilu" + ], + "\\1 month ago": [ + "(\\d++[.,]?\\d*+) xahar ilu" + ], + "\\1 second ago": [ + "(\\d++[.,]?\\d*+) sek ilu", + "(\\d++[.,]?\\d*+) sekonda ilu" + ], + "\\1 week ago": [ + "(\\d++[.,]?\\d*+) ġimgħa ilu" + ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) sena ilu", - "(\\d+[.,]?\\d*) snin ilu" + "(\\d++[.,]?\\d*+) sena ilu", + "(\\d++[.,]?\\d*+) snin ilu" + ], + "in \\1 day": [ + "fi żmien (\\d++[.,]?\\d*+) ġurnata oħra" + ], + "in \\1 hour": [ + "fi żmien (\\d++[.,]?\\d*+) siegħa" + ], + "in \\1 minute": [ + "sa (\\d++[.,]?\\d*+) min oħra", + "sa (\\d++[.,]?\\d*+) minuta oħra" + ], + "in \\1 month": [ + "fi (\\d++[.,]?\\d*+) xahar oħra", + "sa (\\d++[.,]?\\d*+) xahar oħra" + ], + "in \\1 second": [ + "sa (\\d++[.,]?\\d*+) sek oħra", + "sa (\\d++[.,]?\\d*+) sekonda oħra" + ], + "in \\1 week": [ + "sa (\\d++[.,]?\\d*+) ġimgħa oħra" + ], + "in \\1 year": [ + "fi żmien (\\d++[.,]?\\d*+) sena oħra" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/mua.py b/dateparser/data/date_translation_data/mua.py index dd81cc556..ff42f2744 100644 --- a/dateparser/data/date_translation_data/mua.py +++ b/dateparser/data/date_translation_data/mua.py @@ -96,7 +96,8 @@ "zah'nane/ comme" ], "hour": [ - "cok comme" + "cok comme", + "hr" ], "minute": [ "cok comme ma laŋne" diff --git a/dateparser/data/date_translation_data/my.py b/dateparser/data/date_translation_data/my.py index 9564fa91d..b59b5cd78 100644 --- a/dateparser/data/date_translation_data/my.py +++ b/dateparser/data/date_translation_data/my.py @@ -143,46 +143,46 @@ }, "relative-type-regex": { "\\1 day ago": [ - "ပြီးခဲ့သည့် (\\d+[.,]?\\d*) ရက်" + "ပြီးခဲ့သည့် (\\d++[.,]?\\d*+) ရက်" ], "\\1 hour ago": [ - "ပြီးခဲ့သည့် (\\d+[.,]?\\d*) နာရီ" + "ပြီးခဲ့သည့် (\\d++[.,]?\\d*+) နာရီ" ], "\\1 minute ago": [ - "ပြီးခဲ့သည့် (\\d+[.,]?\\d*) မိနစ်" + "ပြီးခဲ့သည့် (\\d++[.,]?\\d*+) မိနစ်" ], "\\1 month ago": [ - "ပြီးခဲ့သည့် (\\d+[.,]?\\d*) လ" + "ပြီးခဲ့သည့် (\\d++[.,]?\\d*+) လ" ], "\\1 second ago": [ - "ပြီးခဲ့သည့် (\\d+[.,]?\\d*) စက္ကန့်" + "ပြီးခဲ့သည့် (\\d++[.,]?\\d*+) စက္ကန့်" ], "\\1 week ago": [ - "ပြီးခဲ့သည့် (\\d+[.,]?\\d*) ပတ်" + "ပြီးခဲ့သည့် (\\d++[.,]?\\d*+) ပတ်" ], "\\1 year ago": [ - "ပြီးခဲ့သည့် (\\d+[.,]?\\d*) နှစ်" + "ပြီးခဲ့သည့် (\\d++[.,]?\\d*+) နှစ်" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) ရက်အတွင်း" + "(\\d++[.,]?\\d*+) ရက်အတွင်း" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) နာရီအတွင်း" + "(\\d++[.,]?\\d*+) နာရီအတွင်း" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) မိနစ်အတွင်း" + "(\\d++[.,]?\\d*+) မိနစ်အတွင်း" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) လအတွင်း" + "(\\d++[.,]?\\d*+) လအတွင်း" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) စက္ကန့်အတွင်း" + "(\\d++[.,]?\\d*+) စက္ကန့်အတွင်း" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) ပတ်အတွင်း" + "(\\d++[.,]?\\d*+) ပတ်အတွင်း" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) နှစ်အတွင်း" + "(\\d++[.,]?\\d*+) နှစ်အတွင်း" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/mzn.py b/dateparser/data/date_translation_data/mzn.py index 8a9fc6e15..6bc87e95d 100644 --- a/dateparser/data/date_translation_data/mzn.py +++ b/dateparser/data/date_translation_data/mzn.py @@ -136,49 +136,49 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) روز پیش" + "(\\d++[.,]?\\d*+) روز پیش" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) ساعت پیش", - "(\\d+[.,]?\\d*) ساعِت پیش" + "(\\d++[.,]?\\d*+) ساعت پیش", + "(\\d++[.,]?\\d*+) ساعِت پیش" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) دَقه پیش" + "(\\d++[.,]?\\d*+) دَقه پیش" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) ماه پیش" + "(\\d++[.,]?\\d*+) ماه پیش" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) ثانیه پیش" + "(\\d++[.,]?\\d*+) ثانیه پیش" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) هفته پیش" + "(\\d++[.,]?\\d*+) هفته پیش" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) سال پیش" + "(\\d++[.,]?\\d*+) سال پیش" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) روز دله" + "(\\d++[.,]?\\d*+) روز دله" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) ساعت دله", - "(\\d+[.,]?\\d*) ساعِت دله" + "(\\d++[.,]?\\d*+) ساعت دله", + "(\\d++[.,]?\\d*+) ساعِت دله" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) دقیقه دله", - "(\\d+[.,]?\\d*) دَقه دله" + "(\\d++[.,]?\\d*+) دقیقه دله", + "(\\d++[.,]?\\d*+) دَقه دله" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) ماه دله" + "(\\d++[.,]?\\d*+) ماه دله" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) ثانیه دله" + "(\\d++[.,]?\\d*+) ثانیه دله" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) هفته دله" + "(\\d++[.,]?\\d*+) هفته دله" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) سال دله" + "(\\d++[.,]?\\d*+) سال دله" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/naq.py b/dateparser/data/date_translation_data/naq.py index c69358061..b83e7b5ca 100644 --- a/dateparser/data/date_translation_data/naq.py +++ b/dateparser/data/date_translation_data/naq.py @@ -96,6 +96,7 @@ "tsees" ], "hour": [ + "hr", "iiri" ], "minute": [ diff --git a/dateparser/data/date_translation_data/nb.py b/dateparser/data/date_translation_data/nb.py index 921cfb084..944c7a61a 100644 --- a/dateparser/data/date_translation_data/nb.py +++ b/dateparser/data/date_translation_data/nb.py @@ -88,7 +88,8 @@ "month": [ "md", "mnd", - "måned" + "måned", + "måneder" ], "week": [ "u", @@ -103,17 +104,20 @@ "hour": [ "t", "time", + "timer", "timer" ], "minute": [ "m", "min", - "minutt" + "minutt", + "minutter" ], "second": [ "s", "sek", - "sekund" + "sekund", + "sekunder" ], "relative-type": { "0 day ago": [ @@ -167,70 +171,70 @@ }, "relative-type-regex": { "\\1 day ago": [ - "for (\\d+[.,]?\\d*) d siden", - "for (\\d+[.,]?\\d*) døgn siden", - "for (\\d+[.,]?\\d*) dager siden" + "for (\\d++[.,]?\\d*+) d siden", + "for (\\d++[.,]?\\d*+) døgn siden", + "for (\\d++[.,]?\\d*+) dager siden" ], "\\1 hour ago": [ - "for (\\d+[.,]?\\d*) t siden", - "for (\\d+[.,]?\\d*) time siden", - "for (\\d+[.,]?\\d*) timer siden" + "for (\\d++[.,]?\\d*+) t siden", + "for (\\d++[.,]?\\d*+) time siden", + "for (\\d++[.,]?\\d*+) timer siden" ], "\\1 minute ago": [ - "for (\\d+[.,]?\\d*) min siden", - "for (\\d+[.,]?\\d*) minutt siden", - "for (\\d+[.,]?\\d*) minutter siden" + "for (\\d++[.,]?\\d*+) min siden", + "for (\\d++[.,]?\\d*+) minutt siden", + "for (\\d++[.,]?\\d*+) minutter siden" ], "\\1 month ago": [ - "for (\\d+[.,]?\\d*) md siden", - "for (\\d+[.,]?\\d*) måned siden", - "for (\\d+[.,]?\\d*) måneder siden" + "for (\\d++[.,]?\\d*+) md siden", + "for (\\d++[.,]?\\d*+) måned siden", + "for (\\d++[.,]?\\d*+) måneder siden" ], "\\1 second ago": [ - "for (\\d+[.,]?\\d*) sek siden", - "for (\\d+[.,]?\\d*) sekund siden", - "for (\\d+[.,]?\\d*) sekunder siden" + "for (\\d++[.,]?\\d*+) sek siden", + "for (\\d++[.,]?\\d*+) sekund siden", + "for (\\d++[.,]?\\d*+) sekunder siden" ], "\\1 week ago": [ - "for (\\d+[.,]?\\d*) u siden", - "for (\\d+[.,]?\\d*) uke siden", - "for (\\d+[.,]?\\d*) uker siden" + "for (\\d++[.,]?\\d*+) u siden", + "for (\\d++[.,]?\\d*+) uke siden", + "for (\\d++[.,]?\\d*+) uker siden" ], "\\1 year ago": [ - "for (\\d+[.,]?\\d*) år siden", - "–(\\d+[.,]?\\d*) år" + "for (\\d++[.,]?\\d*+) år siden", + "–(\\d++[.,]?\\d*+) år" ], "in \\1 day": [ - "om (\\d+[.,]?\\d*) d", - "om (\\d+[.,]?\\d*) døgn" + "om (\\d++[.,]?\\d*+) d", + "om (\\d++[.,]?\\d*+) døgn" ], "in \\1 hour": [ - "om (\\d+[.,]?\\d*) t", - "om (\\d+[.,]?\\d*) time", - "om (\\d+[.,]?\\d*) timer" + "om (\\d++[.,]?\\d*+) t", + "om (\\d++[.,]?\\d*+) time", + "om (\\d++[.,]?\\d*+) timer" ], "in \\1 minute": [ - "om (\\d+[.,]?\\d*) min", - "om (\\d+[.,]?\\d*) minutt", - "om (\\d+[.,]?\\d*) minutter" + "om (\\d++[.,]?\\d*+) min", + "om (\\d++[.,]?\\d*+) minutt", + "om (\\d++[.,]?\\d*+) minutter" ], "in \\1 month": [ - "om (\\d+[.,]?\\d*) md", - "om (\\d+[.,]?\\d*) måned", - "om (\\d+[.,]?\\d*) måneder" + "om (\\d++[.,]?\\d*+) md", + "om (\\d++[.,]?\\d*+) måned", + "om (\\d++[.,]?\\d*+) måneder" ], "in \\1 second": [ - "om (\\d+[.,]?\\d*) sek", - "om (\\d+[.,]?\\d*) sekund", - "om (\\d+[.,]?\\d*) sekunder" + "om (\\d++[.,]?\\d*+) sek", + "om (\\d++[.,]?\\d*+) sekund", + "om (\\d++[.,]?\\d*+) sekunder" ], "in \\1 week": [ - "om (\\d+[.,]?\\d*) u", - "om (\\d+[.,]?\\d*) uke", - "om (\\d+[.,]?\\d*) uker" + "om (\\d++[.,]?\\d*+) u", + "om (\\d++[.,]?\\d*+) uke", + "om (\\d++[.,]?\\d*+) uker" ], "in \\1 year": [ - "om (\\d+[.,]?\\d*) år" + "om (\\d++[.,]?\\d*+) år" ] }, "locale_specific": { @@ -238,13 +242,11 @@ "name": "nb-SJ" } }, - "ago": [ - "siden" - ], - "in": [ - "om" - ], "skip": [ + "cirka", + "d.", + "kl", + "kl.", " ", "'", ",", @@ -257,5 +259,47 @@ "]", "|", "," + ], + "sentence_splitter_group": 1, + "ago": [ + "siden" + ], + "in": [ + "om" + ], + "simplifications": [ + { + "en": "1" + }, + { + "ett": "1" + }, + { + "to": "2" + }, + { + "tre": "3" + }, + { + "fire": "4" + }, + { + "fem": "5" + }, + { + "seks": "6" + }, + { + "sju": "7" + }, + { + "åtte": "8" + }, + { + "ni": "9" + }, + { + "ti": "10" + } ] } diff --git a/dateparser/data/date_translation_data/nd.py b/dateparser/data/date_translation_data/nd.py index c01d8dc7b..33e7f345d 100644 --- a/dateparser/data/date_translation_data/nd.py +++ b/dateparser/data/date_translation_data/nd.py @@ -96,6 +96,7 @@ "ilanga" ], "hour": [ + "hr", "ihola" ], "minute": [ diff --git a/dateparser/data/date_translation_data/ne.py b/dateparser/data/date_translation_data/ne.py index 1bc4fb6e5..0570f229a 100644 --- a/dateparser/data/date_translation_data/ne.py +++ b/dateparser/data/date_translation_data/ne.py @@ -14,8 +14,8 @@ "अप्रिल" ], "may": [ - "मई", - "मे" + "मे", + "मई" ], "june": [ "जुन" @@ -73,8 +73,8 @@ "अपराह्न" ], "year": [ - "बर्ष", - "वर्ष" + "वर्ष", + "बर्ष" ], "month": [ "महिना" @@ -99,6 +99,7 @@ "आज" ], "0 hour ago": [ + "यस घडीमा", "यो घडीमा" ], "0 minute ago": [ @@ -108,6 +109,7 @@ "यो महिना" ], "0 second ago": [ + "अहिले", "अब" ], "0 week ago": [ @@ -132,57 +134,62 @@ "भोलि" ], "in 1 month": [ - "अर्को महिना" + "अर्को महिना", + "आगामी महिना" ], "in 1 week": [ + "आगामी हप्ता", "आउने हप्ता" ], "in 1 year": [ + "आगामी वर्ष", "अर्को वर्ष" ] }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) दिन पहिले" + "(\\d++[.,]?\\d*+) दिन पहिले" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) घण्टा पहिले" + "(\\d++[.,]?\\d*+) घण्टा पहिले" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) मिनेट पहिले" + "(\\d++[.,]?\\d*+) मिनेट पहिले" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) महिना पहिले" + "(\\d++[.,]?\\d*+) महिना पहिले" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) सेकेण्ड पहिले" + "(\\d++[.,]?\\d*+) सेकेन्ड पहिले", + "(\\d++[.,]?\\d*+) सेकेण्ड पहिले" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) हप्ता पहिले" + "(\\d++[.,]?\\d*+) हप्ता पहिले" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) वर्ष अघि" + "(\\d++[.,]?\\d*+) वर्ष अघि" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) दिनमा" + "(\\d++[.,]?\\d*+) दिनमा" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) घण्टामा" + "(\\d++[.,]?\\d*+) घण्टामा" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) मिनेटमा" + "(\\d++[.,]?\\d*+) मिनेटमा" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) महिनामा" + "(\\d++[.,]?\\d*+) महिनामा" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) सेकेण्डमा" + "(\\d++[.,]?\\d*+) सेकेन्डमा", + "(\\d++[.,]?\\d*+) सेकेण्डमा" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) हप्तामा" + "(\\d++[.,]?\\d*+) हप्तामा" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) वर्षमा" + "(\\d++[.,]?\\d*+) वर्षमा" ] }, "locale_specific": { diff --git a/dateparser/data/date_translation_data/nl.py b/dateparser/data/date_translation_data/nl.py index 4acb1f060..8325bb98f 100644 --- a/dateparser/data/date_translation_data/nl.py +++ b/dateparser/data/date_translation_data/nl.py @@ -101,6 +101,7 @@ "dagen" ], "hour": [ + "u", "uur" ], "minute": [ @@ -170,62 +171,62 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) dag geleden", - "(\\d+[.,]?\\d*) dagen geleden", - "(\\d+[.,]?\\d*) dgn geleden" + "(\\d++[.,]?\\d*+) dag geleden", + "(\\d++[.,]?\\d*+) dagen geleden", + "(\\d++[.,]?\\d*+) dgn geleden" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) uur geleden" + "(\\d++[.,]?\\d*+) uur geleden" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) min geleden", - "(\\d+[.,]?\\d*) minuten geleden", - "(\\d+[.,]?\\d*) minuut geleden" + "(\\d++[.,]?\\d*+) min geleden", + "(\\d++[.,]?\\d*+) minuten geleden", + "(\\d++[.,]?\\d*+) minuut geleden" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) maand geleden", - "(\\d+[.,]?\\d*) maanden geleden" + "(\\d++[.,]?\\d*+) maand geleden", + "(\\d++[.,]?\\d*+) maanden geleden" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) sec geleden", - "(\\d+[.,]?\\d*) seconde geleden", - "(\\d+[.,]?\\d*) seconden geleden" + "(\\d++[.,]?\\d*+) sec geleden", + "(\\d++[.,]?\\d*+) seconde geleden", + "(\\d++[.,]?\\d*+) seconden geleden" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) week geleden", - "(\\d+[.,]?\\d*) weken geleden" + "(\\d++[.,]?\\d*+) week geleden", + "(\\d++[.,]?\\d*+) weken geleden" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) jaar geleden" + "(\\d++[.,]?\\d*+) jaar geleden" ], "in \\1 day": [ - "over (\\d+[.,]?\\d*) dag", - "over (\\d+[.,]?\\d*) dagen", - "over (\\d+[.,]?\\d*) dgn" + "over (\\d++[.,]?\\d*+) dag", + "over (\\d++[.,]?\\d*+) dagen", + "over (\\d++[.,]?\\d*+) dgn" ], "in \\1 hour": [ - "over (\\d+[.,]?\\d*) uur" + "over (\\d++[.,]?\\d*+) uur" ], "in \\1 minute": [ - "over (\\d+[.,]?\\d*) min", - "over (\\d+[.,]?\\d*) minuten", - "over (\\d+[.,]?\\d*) minuut" + "over (\\d++[.,]?\\d*+) min", + "over (\\d++[.,]?\\d*+) minuten", + "over (\\d++[.,]?\\d*+) minuut" ], "in \\1 month": [ - "over (\\d+[.,]?\\d*) maand", - "over (\\d+[.,]?\\d*) maanden" + "over (\\d++[.,]?\\d*+) maand", + "over (\\d++[.,]?\\d*+) maanden" ], "in \\1 second": [ - "over (\\d+[.,]?\\d*) sec", - "over (\\d+[.,]?\\d*) seconde", - "over (\\d+[.,]?\\d*) seconden" + "over (\\d++[.,]?\\d*+) sec", + "over (\\d++[.,]?\\d*+) seconde", + "over (\\d++[.,]?\\d*+) seconden" ], "in \\1 week": [ - "over (\\d+[.,]?\\d*) week", - "over (\\d+[.,]?\\d*) weken" + "over (\\d++[.,]?\\d*+) week", + "over (\\d++[.,]?\\d*+) weken" ], "in \\1 year": [ - "over (\\d+[.,]?\\d*) jaar" + "over (\\d++[.,]?\\d*+) jaar" ] }, "locale_specific": { diff --git a/dateparser/data/date_translation_data/nmg.py b/dateparser/data/date_translation_data/nmg.py index d1fd4de9b..8a35df35d 100644 --- a/dateparser/data/date_translation_data/nmg.py +++ b/dateparser/data/date_translation_data/nmg.py @@ -96,6 +96,7 @@ "duö" ], "hour": [ + "hr", "wulā" ], "minute": [ diff --git a/dateparser/data/date_translation_data/nn.py b/dateparser/data/date_translation_data/nn.py index a0a4bb6b7..b27419735 100644 --- a/dateparser/data/date_translation_data/nn.py +++ b/dateparser/data/date_translation_data/nn.py @@ -95,21 +95,30 @@ "år" ], "month": [ + "md", "månad" ], "week": [ + "v", "veke" ], "day": [ + "d", "dag" ], "hour": [ + "t", + "timar", "time" ], "minute": [ + "m", + "min", "minutt" ], "second": [ + "s", + "sek", "sekund" ], "relative-type": { @@ -117,100 +126,148 @@ "i dag" ], "0 hour ago": [ + "denne timen", "this hour" ], "0 minute ago": [ + "dette minuttet", "this minute" ], "0 month ago": [ + "denne md", + "denne månaden", "this month" ], "0 second ago": [ + "no", "now" ], "0 week ago": [ + "denne veka", "this week" ], "0 year ago": [ + "i år", "this year" ], "1 day ago": [ "i går" ], "1 month ago": [ + "førre md", + "førre månad", "last month" ], "1 week ago": [ + "førre veke", "last week" ], "1 year ago": [ + "i fjor", "last year" ], "in 1 day": [ "i morgon" ], "in 1 month": [ + "neste md", + "neste månad", "next month" ], "in 1 week": [ + "neste veke", "next week" ], "in 1 year": [ + "neste år", "next year" ] }, "relative-type-regex": { "\\1 day ago": [ - "for (\\d+[.,]?\\d*) døgn siden" + "for (\\d++[.,]?\\d*+) d sidan", + "for (\\d++[.,]?\\d*+) døgn sidan", + "–(\\d++[.,]?\\d*+) d", + "for (\\d++[.,]?\\d*+) døgn siden" ], "\\1 hour ago": [ - "for (\\d+[.,]?\\d*) time siden", - "for (\\d+[.,]?\\d*) timer siden" + "for (\\d++[.,]?\\d*+) t sidan", + "for (\\d++[.,]?\\d*+) timar sidan", + "for (\\d++[.,]?\\d*+) time sidan", + "–(\\d++[.,]?\\d*+) t", + "for (\\d++[.,]?\\d*+) time siden", + "for (\\d++[.,]?\\d*+) timer siden" ], "\\1 minute ago": [ - "for (\\d+[.,]?\\d*) minutt siden", - "for (\\d+[.,]?\\d*) minutter siden" + "for (\\d++[.,]?\\d*+) min sidan", + "for (\\d++[.,]?\\d*+) minutt sidan", + "–(\\d++[.,]?\\d*+) min", + "for (\\d++[.,]?\\d*+) minutt siden", + "for (\\d++[.,]?\\d*+) minutter siden" ], "\\1 month ago": [ - "for (\\d+[.,]?\\d*) måned siden", - "for (\\d+[.,]?\\d*) måneder siden" + "for (\\d++[.,]?\\d*+) md sidan", + "for (\\d++[.,]?\\d*+) månad sidan", + "for (\\d++[.,]?\\d*+) månadar sidan", + "–(\\d++[.,]?\\d*+) md", + "for (\\d++[.,]?\\d*+) måned siden", + "for (\\d++[.,]?\\d*+) måneder siden" ], "\\1 second ago": [ - "for (\\d+[.,]?\\d*) sekund siden", - "for (\\d+[.,]?\\d*) sekunder siden" + "for (\\d++[.,]?\\d*+) sek sidan", + "for (\\d++[.,]?\\d*+) sekund sidan", + "–(\\d++[.,]?\\d*+) s", + "for (\\d++[.,]?\\d*+) sekund siden", + "for (\\d++[.,]?\\d*+) sekunder siden" ], "\\1 week ago": [ - "for (\\d+[.,]?\\d*) uke siden", - "for (\\d+[.,]?\\d*) uker siden" + "for (\\d++[.,]?\\d*+) v sidan", + "for (\\d++[.,]?\\d*+) veke sidan", + "for (\\d++[.,]?\\d*+) veker sidan", + "–(\\d++[.,]?\\d*+) v", + "for (\\d++[.,]?\\d*+) uke siden", + "for (\\d++[.,]?\\d*+) uker siden" ], "\\1 year ago": [ - "for (\\d+[.,]?\\d*) år siden" + "for (\\d++[.,]?\\d*+) år sidan", + "for (\\d++[.,]?\\d*+) år siden" ], "in \\1 day": [ - "om (\\d+[.,]?\\d*) døgn" + "om (\\d++[.,]?\\d*+) d", + "om (\\d++[.,]?\\d*+) døgn" ], "in \\1 hour": [ - "om (\\d+[.,]?\\d*) time", - "om (\\d+[.,]?\\d*) timer" + "om (\\d++[.,]?\\d*+) t", + "om (\\d++[.,]?\\d*+) timar", + "om (\\d++[.,]?\\d*+) time", + "om (\\d++[.,]?\\d*+) timer" ], "in \\1 minute": [ - "om (\\d+[.,]?\\d*) minutt", - "om (\\d+[.,]?\\d*) minutter" + "om (\\d++[.,]?\\d*+) min", + "om (\\d++[.,]?\\d*+) minutt", + "om (\\d++[.,]?\\d*+) minutter" ], "in \\1 month": [ - "om (\\d+[.,]?\\d*) måned", - "om (\\d+[.,]?\\d*) måneder" + "om (\\d++[.,]?\\d*+) md", + "om (\\d++[.,]?\\d*+) månad", + "om (\\d++[.,]?\\d*+) månadar", + "om (\\d++[.,]?\\d*+) måned", + "om (\\d++[.,]?\\d*+) måneder" ], "in \\1 second": [ - "om (\\d+[.,]?\\d*) sekund", - "om (\\d+[.,]?\\d*) sekunder" + "om (\\d++[.,]?\\d*+) sek", + "om (\\d++[.,]?\\d*+) sekund", + "om (\\d++[.,]?\\d*+) sekunder" ], "in \\1 week": [ - "om (\\d+[.,]?\\d*) uke", - "om (\\d+[.,]?\\d*) uker" + "om (\\d++[.,]?\\d*+) v", + "om (\\d++[.,]?\\d*+) veke", + "om (\\d++[.,]?\\d*+) veker", + "om (\\d++[.,]?\\d*+) uke", + "om (\\d++[.,]?\\d*+) uker" ], "in \\1 year": [ - "om (\\d+[.,]?\\d*) år" + "om (\\d++[.,]?\\d*+) år" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/nnh.py b/dateparser/data/date_translation_data/nnh.py index 5f2284e67..eabe9cbbd 100644 --- a/dateparser/data/date_translation_data/nnh.py +++ b/dateparser/data/date_translation_data/nnh.py @@ -77,7 +77,8 @@ "lyɛ̌'" ], "hour": [ - "fʉ̀' nèm" + "fʉ̀' nèm", + "hr" ], "minute": [ "minute" diff --git a/dateparser/data/date_translation_data/nus.py b/dateparser/data/date_translation_data/nus.py index 8910752c5..4187fc37a 100644 --- a/dateparser/data/date_translation_data/nus.py +++ b/dateparser/data/date_translation_data/nus.py @@ -93,6 +93,7 @@ "cäŋ" ], "hour": [ + "hr", "thaak" ], "minute": [ diff --git a/dateparser/data/date_translation_data/nyn.py b/dateparser/data/date_translation_data/nyn.py index dbd3301ce..8b4208b94 100644 --- a/dateparser/data/date_translation_data/nyn.py +++ b/dateparser/data/date_translation_data/nyn.py @@ -96,6 +96,7 @@ "eizooba" ], "hour": [ + "hr", "shaaha" ], "minute": [ diff --git a/dateparser/data/date_translation_data/om.py b/dateparser/data/date_translation_data/om.py index c4af00c3f..ffcd120b9 100644 --- a/dateparser/data/date_translation_data/om.py +++ b/dateparser/data/date_translation_data/om.py @@ -96,7 +96,8 @@ "day" ], "hour": [ - "hour" + "hour", + "hr" ], "minute": [ "minute" diff --git a/dateparser/data/date_translation_data/or.py b/dateparser/data/date_translation_data/or.py index 0c190e96c..0c20320e5 100644 --- a/dateparser/data/date_translation_data/or.py +++ b/dateparser/data/date_translation_data/or.py @@ -1,6 +1,6 @@ info = { "name": "or", - "date_order": "DMY", + "date_order": "MDY", "january": [ "ଜାନୁଆରୀ" ], @@ -66,79 +66,165 @@ "ରବିବାର" ], "am": [ - "am" + "am", + "ପୂର୍ବାହ୍ନ" ], "pm": [ - "pm" + "pm", + "ଅପରାହ୍ନ" ], "year": [ + "ବ", + "ବର୍ଷ", "year" ], "month": [ + "ମା", + "ମାସ", "month" ], "week": [ + "ସ", + "ସପ୍ତାହ", "week" ], "day": [ + "ଦିନ", "day" ], "hour": [ + "ଘ", + "ଘଣ୍ଟା", "hour" ], "minute": [ + "ମି", + "ମିନିଟ୍", "minute" ], "second": [ + "ସେ", + "ସେକେଣ୍ଡ୍", "second" ], "relative-type": { "0 day ago": [ + "ଆଜି", "today" ], "0 hour ago": [ + "ଏହି ଘଣ୍ଟା", "this hour" ], "0 minute ago": [ + "ଏହି ମିନିଟ୍", "this minute" ], "0 month ago": [ + "ଏହି ମାସ", "this month" ], "0 second ago": [ + "ବର୍ତ୍ତମାନ", "now" ], "0 week ago": [ + "ଏହି ସପ୍ତାହ", "this week" ], "0 year ago": [ + "ଏହି ବର୍ଷ", "this year" ], "1 day ago": [ + "ଗତକାଲି", "yesterday" ], "1 month ago": [ + "ଗତ ମାସ", "last month" ], "1 week ago": [ + "ଗତ ସପ୍ତାହ", "last week" ], "1 year ago": [ + "ଗତ ବର୍ଷ", "last year" ], "in 1 day": [ + "ଆସନ୍ତାକାଲି", "tomorrow" ], "in 1 month": [ + "ଆଗାମୀ ମାସ", "next month" ], "in 1 week": [ + "ଆଗାମୀ ସପ୍ତାହ", "next week" ], "in 1 year": [ + "ଆଗାମୀ ବର୍ଷ", "next year" ] }, + "relative-type-regex": { + "\\1 day ago": [ + "(\\d++[.,]?\\d*+) ଦିନ ପୂର୍ବେ" + ], + "\\1 hour ago": [ + "(\\d++[.,]?\\d*+) ଘ ପୂର୍ବେ", + "(\\d++[.,]?\\d*+) ଘଣ୍ଟା ପୂର୍ବେ" + ], + "\\1 minute ago": [ + "(\\d++[.,]?\\d*+) ମି ପୂର୍ବେ", + "(\\d++[.,]?\\d*+) ମିନିଟ୍ ପୂର୍ବେ" + ], + "\\1 month ago": [ + "(\\d++[.,]?\\d*+) ମା ପୂର୍ବେ", + "(\\d++[.,]?\\d*+) ମାସ ପୂର୍ବେ" + ], + "\\1 second ago": [ + "(\\d++[.,]?\\d*+) ସେ ପୂର୍ବେ", + "(\\d++[.,]?\\d*+) ସେକେଣ୍ଡ ପୂର୍ବେ" + ], + "\\1 week ago": [ + "(\\d++[.,]?\\d*+) ସପ୍ତା ପୂର୍ବେ", + "(\\d++[.,]?\\d*+) ସପ୍ତାହ ପୂର୍ବେ" + ], + "\\1 year ago": [ + "(\\d++[.,]?\\d*+) ବ ପୂର୍ବେ", + "(\\d++[.,]?\\d*+) ବର୍ଷ ପୂର୍ବେ" + ], + "in \\1 day": [ + "(\\d++[.,]?\\d*+) ଦିନରେ" + ], + "in \\1 hour": [ + "(\\d++[.,]?\\d*+) ଘ ରେ", + "(\\d++[.,]?\\d*+) ଘଣ୍ଟାରେ" + ], + "in \\1 minute": [ + "(\\d++[.,]?\\d*+) ମି ରେ", + "(\\d++[.,]?\\d*+) ମିନିଟ୍‌‌ରେ" + ], + "in \\1 month": [ + "(\\d++[.,]?\\d*+) ମା ରେ", + "(\\d++[.,]?\\d*+) ମାସରେ" + ], + "in \\1 second": [ + "(\\d++[.,]?\\d*+) ସେ ରେ", + "(\\d++[.,]?\\d*+) ସେକେଣ୍ଡରେ" + ], + "in \\1 week": [ + "(\\d++[.,]?\\d*+) ସପ୍ତା ରେ", + "(\\d++[.,]?\\d*+) ସପ୍ତାହରେ" + ], + "in \\1 year": [ + "(\\d++[.,]?\\d*+) ବ ରେ", + "(\\d++[.,]?\\d*+) ବର୍ଷରେ" + ] + }, "locale_specific": {}, "skip": [ " ", diff --git a/dateparser/data/date_translation_data/os.py b/dateparser/data/date_translation_data/os.py index 62ff4867e..6164d1d16 100644 --- a/dateparser/data/date_translation_data/os.py +++ b/dateparser/data/date_translation_data/os.py @@ -111,7 +111,8 @@ "бон" ], "hour": [ - "сахат" + "сахат", + "сахаты" ], "minute": [ "минут" @@ -168,17 +169,17 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) бон раздӕр", - "(\\d+[.,]?\\d*) боны размӕ" + "(\\d++[.,]?\\d*+) бон раздӕр", + "(\\d++[.,]?\\d*+) боны размӕ" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) сахаты размӕ" + "(\\d++[.,]?\\d*+) сахаты размӕ" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) боны фӕстӕ" + "(\\d++[.,]?\\d*+) боны фӕстӕ" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) сахаты фӕстӕ" + "(\\d++[.,]?\\d*+) сахаты фӕстӕ" ] }, "locale_specific": { diff --git a/dateparser/data/date_translation_data/pa-Arab.py b/dateparser/data/date_translation_data/pa-Arab.py index 542582910..34238284a 100644 --- a/dateparser/data/date_translation_data/pa-Arab.py +++ b/dateparser/data/date_translation_data/pa-Arab.py @@ -77,6 +77,7 @@ "دئن" ], "hour": [ + "hr", "گھنٹا" ], "minute": [ diff --git a/dateparser/data/date_translation_data/pa-Guru.py b/dateparser/data/date_translation_data/pa-Guru.py index 4b8d6ccc8..a8fcd1924 100644 --- a/dateparser/data/date_translation_data/pa-Guru.py +++ b/dateparser/data/date_translation_data/pa-Guru.py @@ -94,7 +94,8 @@ ], "hour": [ "ਘੰ", - "ਘੰਟਾ" + "ਘੰਟਾ", + "ਘੰਟੇ" ], "minute": [ "ਮਿੰਟ" @@ -151,56 +152,56 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) ਦਿਨ ਪਹਿਲਾਂ" + "(\\d++[.,]?\\d*+) ਦਿਨ ਪਹਿਲਾਂ" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) ਘੰਟਾ ਪਹਿਲਾਂ", - "(\\d+[.,]?\\d*) ਘੰਟੇ ਪਹਿਲਾਂ" + "(\\d++[.,]?\\d*+) ਘੰਟਾ ਪਹਿਲਾਂ", + "(\\d++[.,]?\\d*+) ਘੰਟੇ ਪਹਿਲਾਂ" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) ਮਿੰਟ ਪਹਿਲਾਂ" + "(\\d++[.,]?\\d*+) ਮਿੰਟ ਪਹਿਲਾਂ" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) ਮਹੀਨਾ ਪਹਿਲਾਂ", - "(\\d+[.,]?\\d*) ਮਹੀਨੇ ਪਹਿਲਾਂ" + "(\\d++[.,]?\\d*+) ਮਹੀਨਾ ਪਹਿਲਾਂ", + "(\\d++[.,]?\\d*+) ਮਹੀਨੇ ਪਹਿਲਾਂ" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) ਸਕਿੰਟ ਪਹਿਲਾਂ" + "(\\d++[.,]?\\d*+) ਸਕਿੰਟ ਪਹਿਲਾਂ" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) ਹਫ਼ਤਾ ਪਹਿਲਾਂ", - "(\\d+[.,]?\\d*) ਹਫ਼ਤੇ ਪਹਿਲਾਂ" + "(\\d++[.,]?\\d*+) ਹਫ਼ਤਾ ਪਹਿਲਾਂ", + "(\\d++[.,]?\\d*+) ਹਫ਼ਤੇ ਪਹਿਲਾਂ" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) ਸਾਲ ਪਹਿਲਾਂ" + "(\\d++[.,]?\\d*+) ਸਾਲ ਪਹਿਲਾਂ" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) ਦਿਨ ਵਿੱਚ", - "(\\d+[.,]?\\d*) ਦਿਨਾਂ ਵਿੱਚ" + "(\\d++[.,]?\\d*+) ਦਿਨ ਵਿੱਚ", + "(\\d++[.,]?\\d*+) ਦਿਨਾਂ ਵਿੱਚ" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) ਘੰਟਿਆਂ ਵਿੱਚ", - "(\\d+[.,]?\\d*) ਘੰਟੇ ਵਿੱਚ" + "(\\d++[.,]?\\d*+) ਘੰਟਿਆਂ ਵਿੱਚ", + "(\\d++[.,]?\\d*+) ਘੰਟੇ ਵਿੱਚ" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) ਮਿੰਟ ਵਿੱਚ", - "(\\d+[.,]?\\d*) ਮਿੰਟਾਂ ਵਿੱਚ" + "(\\d++[.,]?\\d*+) ਮਿੰਟ ਵਿੱਚ", + "(\\d++[.,]?\\d*+) ਮਿੰਟਾਂ ਵਿੱਚ" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) ਮਹੀਨਿਆਂ ਵਿੱਚ", - "(\\d+[.,]?\\d*) ਮਹੀਨੇ ਵਿੱਚ" + "(\\d++[.,]?\\d*+) ਮਹੀਨਿਆਂ ਵਿੱਚ", + "(\\d++[.,]?\\d*+) ਮਹੀਨੇ ਵਿੱਚ" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) ਸਕਿੰਟ ਵਿੱਚ", - "(\\d+[.,]?\\d*) ਸਕਿੰਟਾਂ ਵਿੱਚ" + "(\\d++[.,]?\\d*+) ਸਕਿੰਟ ਵਿੱਚ", + "(\\d++[.,]?\\d*+) ਸਕਿੰਟਾਂ ਵਿੱਚ" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) ਹਫ਼ਤਿਆਂ ਵਿੱਚ", - "(\\d+[.,]?\\d*) ਹਫ਼ਤੇ ਵਿੱਚ" + "(\\d++[.,]?\\d*+) ਹਫ਼ਤਿਆਂ ਵਿੱਚ", + "(\\d++[.,]?\\d*+) ਹਫ਼ਤੇ ਵਿੱਚ" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) ਸਾਲ ਵਿੱਚ", - "(\\d+[.,]?\\d*) ਸਾਲਾਂ ਵਿੱਚ" + "(\\d++[.,]?\\d*+) ਸਾਲ ਵਿੱਚ", + "(\\d++[.,]?\\d*+) ਸਾਲਾਂ ਵਿੱਚ" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/pa.py b/dateparser/data/date_translation_data/pa.py index 60a6425b2..e9319f8a8 100644 --- a/dateparser/data/date_translation_data/pa.py +++ b/dateparser/data/date_translation_data/pa.py @@ -94,7 +94,8 @@ ], "hour": [ "ਘੰ", - "ਘੰਟਾ" + "ਘੰਟਾ", + "ਘੰਟੇ" ], "minute": [ "ਮਿੰਟ" @@ -151,56 +152,56 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) ਦਿਨ ਪਹਿਲਾਂ" + "(\\d++[.,]?\\d*+) ਦਿਨ ਪਹਿਲਾਂ" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) ਘੰਟਾ ਪਹਿਲਾਂ", - "(\\d+[.,]?\\d*) ਘੰਟੇ ਪਹਿਲਾਂ" + "(\\d++[.,]?\\d*+) ਘੰਟਾ ਪਹਿਲਾਂ", + "(\\d++[.,]?\\d*+) ਘੰਟੇ ਪਹਿਲਾਂ" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) ਮਿੰਟ ਪਹਿਲਾਂ" + "(\\d++[.,]?\\d*+) ਮਿੰਟ ਪਹਿਲਾਂ" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) ਮਹੀਨਾ ਪਹਿਲਾਂ", - "(\\d+[.,]?\\d*) ਮਹੀਨੇ ਪਹਿਲਾਂ" + "(\\d++[.,]?\\d*+) ਮਹੀਨਾ ਪਹਿਲਾਂ", + "(\\d++[.,]?\\d*+) ਮਹੀਨੇ ਪਹਿਲਾਂ" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) ਸਕਿੰਟ ਪਹਿਲਾਂ" + "(\\d++[.,]?\\d*+) ਸਕਿੰਟ ਪਹਿਲਾਂ" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) ਹਫ਼ਤਾ ਪਹਿਲਾਂ", - "(\\d+[.,]?\\d*) ਹਫ਼ਤੇ ਪਹਿਲਾਂ" + "(\\d++[.,]?\\d*+) ਹਫ਼ਤਾ ਪਹਿਲਾਂ", + "(\\d++[.,]?\\d*+) ਹਫ਼ਤੇ ਪਹਿਲਾਂ" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) ਸਾਲ ਪਹਿਲਾਂ" + "(\\d++[.,]?\\d*+) ਸਾਲ ਪਹਿਲਾਂ" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) ਦਿਨ ਵਿੱਚ", - "(\\d+[.,]?\\d*) ਦਿਨਾਂ ਵਿੱਚ" + "(\\d++[.,]?\\d*+) ਦਿਨ ਵਿੱਚ", + "(\\d++[.,]?\\d*+) ਦਿਨਾਂ ਵਿੱਚ" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) ਘੰਟਿਆਂ ਵਿੱਚ", - "(\\d+[.,]?\\d*) ਘੰਟੇ ਵਿੱਚ" + "(\\d++[.,]?\\d*+) ਘੰਟਿਆਂ ਵਿੱਚ", + "(\\d++[.,]?\\d*+) ਘੰਟੇ ਵਿੱਚ" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) ਮਿੰਟ ਵਿੱਚ", - "(\\d+[.,]?\\d*) ਮਿੰਟਾਂ ਵਿੱਚ" + "(\\d++[.,]?\\d*+) ਮਿੰਟ ਵਿੱਚ", + "(\\d++[.,]?\\d*+) ਮਿੰਟਾਂ ਵਿੱਚ" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) ਮਹੀਨਿਆਂ ਵਿੱਚ", - "(\\d+[.,]?\\d*) ਮਹੀਨੇ ਵਿੱਚ" + "(\\d++[.,]?\\d*+) ਮਹੀਨਿਆਂ ਵਿੱਚ", + "(\\d++[.,]?\\d*+) ਮਹੀਨੇ ਵਿੱਚ" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) ਸਕਿੰਟ ਵਿੱਚ", - "(\\d+[.,]?\\d*) ਸਕਿੰਟਾਂ ਵਿੱਚ" + "(\\d++[.,]?\\d*+) ਸਕਿੰਟ ਵਿੱਚ", + "(\\d++[.,]?\\d*+) ਸਕਿੰਟਾਂ ਵਿੱਚ" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) ਹਫ਼ਤਿਆਂ ਵਿੱਚ", - "(\\d+[.,]?\\d*) ਹਫ਼ਤੇ ਵਿੱਚ" + "(\\d++[.,]?\\d*+) ਹਫ਼ਤਿਆਂ ਵਿੱਚ", + "(\\d++[.,]?\\d*+) ਹਫ਼ਤੇ ਵਿੱਚ" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) ਸਾਲ ਵਿੱਚ", - "(\\d+[.,]?\\d*) ਸਾਲਾਂ ਵਿੱਚ" + "(\\d++[.,]?\\d*+) ਸਾਲ ਵਿੱਚ", + "(\\d++[.,]?\\d*+) ਸਾਲਾਂ ਵਿੱਚ" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/pl.py b/dateparser/data/date_translation_data/pl.py index 95525291c..614c5e784 100644 --- a/dateparser/data/date_translation_data/pl.py +++ b/dateparser/data/date_translation_data/pl.py @@ -212,6 +212,8 @@ "tygodnie" ], "day": [ + "d", + "dz", "dzień", "dzien", "dnia", @@ -222,6 +224,7 @@ "g", "godz", "godzina", + "godziny", "godzinę", "godzine", "godzin", @@ -246,7 +249,8 @@ ], "relative-type": { "0 day ago": [ - "dzisiaj" + "dzisiaj", + "dziś" ], "0 hour ago": [ "ta godzina" @@ -255,24 +259,29 @@ "ta minuta" ], "0 month ago": [ + "w tym mies", "w tym miesiącu" ], "0 second ago": [ "teraz" ], "0 week ago": [ + "w tym tyg", "w tym tygodniu" ], "0 year ago": [ "w tym roku" ], "1 day ago": [ + "wcz", "wczoraj" ], "1 month ago": [ + "w zeszłym mies", "w zeszłym miesiącu" ], "1 week ago": [ + "w zeszłym tyg", "w zeszłym tygodniu" ], "1 year ago": [ @@ -282,9 +291,11 @@ "jutro" ], "in 1 month": [ + "w przyszłym mies", "w przyszłym miesiącu" ], "in 1 week": [ + "w przyszłym tyg", "w przyszłym tygodniu" ], "in 1 year": [ @@ -293,77 +304,77 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) dnia temu", - "(\\d+[.,]?\\d*) dzień temu" + "(\\d++[.,]?\\d*+) dnia temu", + "(\\d++[.,]?\\d*+) dzień temu" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) g temu", - "(\\d+[.,]?\\d*) godz temu", - "(\\d+[.,]?\\d*) godziny temu", - "(\\d+[.,]?\\d*) godzinę temu" + "(\\d++[.,]?\\d*+) g temu", + "(\\d++[.,]?\\d*+) godz temu", + "(\\d++[.,]?\\d*+) godziny temu", + "(\\d++[.,]?\\d*+) godzinę temu" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) min temu", - "(\\d+[.,]?\\d*) minuty temu", - "(\\d+[.,]?\\d*) minutę temu" + "(\\d++[.,]?\\d*+) min temu", + "(\\d++[.,]?\\d*+) minuty temu", + "(\\d++[.,]?\\d*+) minutę temu" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) mies temu", - "(\\d+[.,]?\\d*) miesiąc temu", - "(\\d+[.,]?\\d*) miesiąca temu", - "–(\\d+[.,]?\\d*) mies" + "(\\d++[.,]?\\d*+) mies temu", + "(\\d++[.,]?\\d*+) miesiąc temu", + "(\\d++[.,]?\\d*+) miesiąca temu", + "–(\\d++[.,]?\\d*+) mies" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) s temu", - "(\\d+[.,]?\\d*) sek temu", - "(\\d+[.,]?\\d*) sekundy temu", - "(\\d+[.,]?\\d*) sekundę temu" + "(\\d++[.,]?\\d*+) s temu", + "(\\d++[.,]?\\d*+) sek temu", + "(\\d++[.,]?\\d*+) sekundy temu", + "(\\d++[.,]?\\d*+) sekundę temu" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) tydz temu", - "(\\d+[.,]?\\d*) tydzień temu", - "(\\d+[.,]?\\d*) tyg temu", - "(\\d+[.,]?\\d*) tygodnia temu" + "(\\d++[.,]?\\d*+) tydz temu", + "(\\d++[.,]?\\d*+) tydzień temu", + "(\\d++[.,]?\\d*+) tyg temu", + "(\\d++[.,]?\\d*+) tygodnia temu" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) rok temu", - "(\\d+[.,]?\\d*) roku temu" + "(\\d++[.,]?\\d*+) rok temu", + "(\\d++[.,]?\\d*+) roku temu" ], "in \\1 day": [ - "za (\\d+[.,]?\\d*) dnia", - "za (\\d+[.,]?\\d*) dzień" + "za (\\d++[.,]?\\d*+) dnia", + "za (\\d++[.,]?\\d*+) dzień" ], "in \\1 hour": [ - "za (\\d+[.,]?\\d*) g", - "za (\\d+[.,]?\\d*) godz", - "za (\\d+[.,]?\\d*) godziny", - "za (\\d+[.,]?\\d*) godzinę" + "za (\\d++[.,]?\\d*+) g", + "za (\\d++[.,]?\\d*+) godz", + "za (\\d++[.,]?\\d*+) godziny", + "za (\\d++[.,]?\\d*+) godzinę" ], "in \\1 minute": [ - "za (\\d+[.,]?\\d*) min", - "za (\\d+[.,]?\\d*) minuty", - "za (\\d+[.,]?\\d*) minutę" + "za (\\d++[.,]?\\d*+) min", + "za (\\d++[.,]?\\d*+) minuty", + "za (\\d++[.,]?\\d*+) minutę" ], "in \\1 month": [ - "za (\\d+[.,]?\\d*) mies", - "za (\\d+[.,]?\\d*) miesiąc", - "za (\\d+[.,]?\\d*) miesiąca" + "za (\\d++[.,]?\\d*+) mies", + "za (\\d++[.,]?\\d*+) miesiąc", + "za (\\d++[.,]?\\d*+) miesiąca" ], "in \\1 second": [ - "za (\\d+[.,]?\\d*) s", - "za (\\d+[.,]?\\d*) sek", - "za (\\d+[.,]?\\d*) sekundy", - "za (\\d+[.,]?\\d*) sekundę" + "za (\\d++[.,]?\\d*+) s", + "za (\\d++[.,]?\\d*+) sek", + "za (\\d++[.,]?\\d*+) sekundy", + "za (\\d++[.,]?\\d*+) sekundę" ], "in \\1 week": [ - "za (\\d+[.,]?\\d*) tydz", - "za (\\d+[.,]?\\d*) tydzień", - "za (\\d+[.,]?\\d*) tyg", - "za (\\d+[.,]?\\d*) tygodnia" + "za (\\d++[.,]?\\d*+) tydz", + "za (\\d++[.,]?\\d*+) tydzień", + "za (\\d++[.,]?\\d*+) tyg", + "za (\\d++[.,]?\\d*+) tygodnia" ], "in \\1 year": [ - "za (\\d+[.,]?\\d*) rok", - "za (\\d+[.,]?\\d*) roku" + "za (\\d++[.,]?\\d*+) rok", + "za (\\d++[.,]?\\d*+) roku" ] }, "locale_specific": {}, @@ -411,6 +422,27 @@ }, { "pojutrze": "za 2 dnia" + }, + { + "(?<=[^\\d]\\s+|^)tydzień(?=\\s+temu)": "1 tydzień" + }, + { + "(?<=[^\\d]\\s+|^)miesiąc(?=\\s+temu)": "1 miesiąc" + }, + { + "(?<=[^\\d]\\s+|^)rok(?=\\s+temu)": "1 rok" + }, + { + "(?<=[^\\d]\\s+|^)dzień(?=\\s+temu)": "1 dzień" + }, + { + "(?<=[^\\d]\\s+|^)godzinę(?=\\s+temu)": "1 godzinę" + }, + { + "(?<=[^\\d]\\s+|^)minutę(?=\\s+temu)": "1 minutę" + }, + { + "(?<=[^\\d]\\s+|^)sekundę(?=\\s+temu)": "1 sekundę" } ] } diff --git a/dateparser/data/date_translation_data/ps.py b/dateparser/data/date_translation_data/ps.py index 01fc7c6d5..a692caaa7 100644 --- a/dateparser/data/date_translation_data/ps.py +++ b/dateparser/data/date_translation_data/ps.py @@ -5,7 +5,8 @@ "جنوري" ], "february": [ - "فبروري" + "فبروري", + "فېبروري" ], "march": [ "مارچ" @@ -26,7 +27,8 @@ "اګست" ], "september": [ - "سپتمبر" + "سپتمبر", + "سېپتمبر" ], "october": [ "اکتوبر" @@ -38,101 +40,209 @@ "دسمبر" ], "monday": [ + "دونۍ", "دوشنبه" ], "tuesday": [ + "درېنۍ", "سه‌شنبه" ], "wednesday": [ + "څلرنۍ", "چهارشنبه" ], "thursday": [ + "پينځنۍ", "پنجشنبه" ], "friday": [ "جمعه" ], "saturday": [ + "اونۍ", "شنبه" ], "sunday": [ + "يونۍ", "یکشنبه" ], "am": [ + "am", "غم" ], "pm": [ + "pm", "غو" ], "year": [ + "کال", "year" ], "month": [ + "مياشت", "month" ], "week": [ + "اونۍ", "week" ], "day": [ + "ورځ", "day" ], "hour": [ + "ساعت", + "ساعتونه", "hour" ], "minute": [ + "دقيقه", "minute" ], "second": [ + "ثانيه", "second" ], "relative-type": { "0 day ago": [ + "نن", "today" ], "0 hour ago": [ + "دا ساعت", "this hour" ], "0 minute ago": [ + "دا دقيقه", "this minute" ], "0 month ago": [ + "دا مياشت", "this month" ], "0 second ago": [ + "اوس", "now" ], "0 week ago": [ + "دا اونۍ", "this week" ], "0 year ago": [ + "سږ کال", + "سږکال", "this year" ], "1 day ago": [ + "پرون", "yesterday" ], "1 month ago": [ + "تېره مياشت", "last month" ], "1 week ago": [ + "تيره اونۍ", + "تېره اونۍ", "last week" ], "1 year ago": [ + "تير کال", + "تېر کال", + "پروسږکال", "last year" ], "in 1 day": [ + "سبا", "tomorrow" ], "in 1 month": [ + "راتلونکې مياشت", "next month" ], "in 1 week": [ + "راتلونکې اونۍ", "next week" ], "in 1 year": [ + "راتلونکی کال", + "روتلونکی کال", "next year" ] }, - "locale_specific": {}, + "relative-type-regex": { + "\\1 day ago": [ + "(\\d++[.,]?\\d*+) ورځ مخکې", + "(\\d++[.,]?\\d*+) ورځې مخکې" + ], + "\\1 hour ago": [ + "(\\d++[.,]?\\d*+) ساعت مخکې", + "(\\d++[.,]?\\d*+) ساعتونه مخکې" + ], + "\\1 minute ago": [ + "(\\d++[.,]?\\d*+) دقيقه مخکې", + "(\\d++[.,]?\\d*+) دقيقې مخکې" + ], + "\\1 month ago": [ + "(\\d++[.,]?\\d*+) مياشت مخکې", + "(\\d++[.,]?\\d*+) مياشتې مخکې" + ], + "\\1 second ago": [ + "(\\d++[.,]?\\d*+) ثانيه مخکې", + "(\\d++[.,]?\\d*+) ثانيه کې", + "(\\d++[.,]?\\d*+) ثانيې مخکې" + ], + "\\1 week ago": [ + "(\\d++[.,]?\\d*+) اونۍ مخکې" + ], + "\\1 year ago": [ + "(\\d++[.,]?\\d*+) کال مخکې", + "(\\d++[.,]?\\d*+) کاله مخکې" + ], + "in \\1 day": [ + "په (\\d++[.,]?\\d*+) ورځ کې", + "په (\\d++[.,]?\\d*+) ورځو کې" + ], + "in \\1 hour": [ + "په (\\d++[.,]?\\d*+) ساعت کې", + "په (\\d++[.,]?\\d*+) ساعتو کې" + ], + "in \\1 minute": [ + "په (\\d++[.,]?\\d*+) دقيقه کې", + "په (\\d++[.,]?\\d*+) دقيقو کې" + ], + "in \\1 month": [ + "په (\\d++[.,]?\\d*+) مياشت کې", + "په (\\d++[.,]?\\d*+) مياشتو کې" + ], + "in \\1 second": [ + "په (\\d++[.,]?\\d*+) ثانيه کې", + "په (\\d++[.,]?\\d*+) ثانيو کې" + ], + "in \\1 week": [ + "په (\\d++[.,]?\\d*+) اونيو کې", + "په (\\d++[.,]?\\d*+) اونۍ کې" + ], + "in \\1 year": [ + "په (\\d++[.,]?\\d*+) کال کې", + "په (\\d++[.,]?\\d*+) کالونو کې" + ] + }, + "locale_specific": { + "ps-PK": { + "name": "ps-PK", + "relative-type-regex": { + "\\1 year ago": [ + "(\\d++[.,]?\\d*+) کال مخکے", + "(\\d++[.,]?\\d*+) کاله مخکے" + ], + "in \\1 year": [ + "په (\\d++[.,]?\\d*+) کال کے", + "په (\\d++[.,]?\\d*+) کالونو کے" + ] + } + } + }, "skip": [ " ", "'", diff --git a/dateparser/data/date_translation_data/pt.py b/dateparser/data/date_translation_data/pt.py index db908355b..06f6eae56 100644 --- a/dateparser/data/date_translation_data/pt.py +++ b/dateparser/data/date_translation_data/pt.py @@ -110,19 +110,20 @@ "hour": [ "h", "hora", + "horas", "horas" ], "minute": [ - "m", "min", "minuto", - "minutos" + "minutos", + "m" ], "second": [ - "s", "seg", "segundo", - "segundos" + "segundos", + "s" ], "relative-type": { "0 day ago": [ @@ -176,71 +177,71 @@ }, "relative-type-regex": { "\\1 day ago": [ - "há (\\d+[.,]?\\d*) dia", - "há (\\d+[.,]?\\d*) dias" + "há (\\d++[.,]?\\d*+) dia", + "há (\\d++[.,]?\\d*+) dias" ], "\\1 hour ago": [ - "há (\\d+[.,]?\\d*) h", - "há (\\d+[.,]?\\d*) hora", - "há (\\d+[.,]?\\d*) horas" + "há (\\d++[.,]?\\d*+) h", + "há (\\d++[.,]?\\d*+) hora", + "há (\\d++[.,]?\\d*+) horas" ], "\\1 minute ago": [ - "há (\\d+[.,]?\\d*) min", - "há (\\d+[.,]?\\d*) mins", - "há (\\d+[.,]?\\d*) minuto", - "há (\\d+[.,]?\\d*) minutos" + "há (\\d++[.,]?\\d*+) min", + "há (\\d++[.,]?\\d*+) minuto", + "há (\\d++[.,]?\\d*+) minutos", + "há (\\d++[.,]?\\d*+) mins" ], "\\1 month ago": [ - "há (\\d+[.,]?\\d*) meses", - "há (\\d+[.,]?\\d*) mês" + "há (\\d++[.,]?\\d*+) meses", + "há (\\d++[.,]?\\d*+) mês" ], "\\1 second ago": [ - "há (\\d+[.,]?\\d*) seg", - "há (\\d+[.,]?\\d*) segundo", - "há (\\d+[.,]?\\d*) segundos" + "há (\\d++[.,]?\\d*+) seg", + "há (\\d++[.,]?\\d*+) segundo", + "há (\\d++[.,]?\\d*+) segundos" ], "\\1 week ago": [ - "há (\\d+[.,]?\\d*) sem", - "há (\\d+[.,]?\\d*) semana", - "há (\\d+[.,]?\\d*) semanas" + "há (\\d++[.,]?\\d*+) sem", + "há (\\d++[.,]?\\d*+) semana", + "há (\\d++[.,]?\\d*+) semanas" ], "\\1 year ago": [ - "há (\\d+[.,]?\\d*) ano", - "há (\\d+[.,]?\\d*) anos" + "há (\\d++[.,]?\\d*+) ano", + "há (\\d++[.,]?\\d*+) anos" ], "in \\1 day": [ - "em (\\d+[.,]?\\d*) dia", - "em (\\d+[.,]?\\d*) dias" + "em (\\d++[.,]?\\d*+) dia", + "em (\\d++[.,]?\\d*+) dias" ], "in \\1 hour": [ - "em (\\d+[.,]?\\d*) h", - "em (\\d+[.,]?\\d*) hora", - "em (\\d+[.,]?\\d*) horas" + "em (\\d++[.,]?\\d*+) h", + "em (\\d++[.,]?\\d*+) hora", + "em (\\d++[.,]?\\d*+) horas" ], "in \\1 minute": [ - "em (\\d+[.,]?\\d*) min", - "em (\\d+[.,]?\\d*) mins", - "em (\\d+[.,]?\\d*) minuto", - "em (\\d+[.,]?\\d*) minutos" + "em (\\d++[.,]?\\d*+) min", + "em (\\d++[.,]?\\d*+) minuto", + "em (\\d++[.,]?\\d*+) minutos", + "em (\\d++[.,]?\\d*+) mins" ], "in \\1 month": [ - "em (\\d+[.,]?\\d*) meses", - "em (\\d+[.,]?\\d*) mês" + "em (\\d++[.,]?\\d*+) meses", + "em (\\d++[.,]?\\d*+) mês" ], "in \\1 second": [ - "em (\\d+[.,]?\\d*) seg", - "em (\\d+[.,]?\\d*) segs", - "em (\\d+[.,]?\\d*) segundo", - "em (\\d+[.,]?\\d*) segundos" + "em (\\d++[.,]?\\d*+) seg", + "em (\\d++[.,]?\\d*+) segundo", + "em (\\d++[.,]?\\d*+) segundos", + "em (\\d++[.,]?\\d*+) segs" ], "in \\1 week": [ - "em (\\d+[.,]?\\d*) sem", - "em (\\d+[.,]?\\d*) semana", - "em (\\d+[.,]?\\d*) semanas" + "em (\\d++[.,]?\\d*+) sem", + "em (\\d++[.,]?\\d*+) semana", + "em (\\d++[.,]?\\d*+) semanas" ], "in \\1 year": [ - "em (\\d+[.,]?\\d*) ano", - "em (\\d+[.,]?\\d*) anos" + "em (\\d++[.,]?\\d*+) ano", + "em (\\d++[.,]?\\d*+) anos" ] }, "locale_specific": { @@ -269,41 +270,44 @@ "da tarde", "tarde" ], + "second": [ + "s" + ], "relative-type-regex": { "\\1 second ago": [ - "há (\\d+[.,]?\\d*) s" + "há (\\d++[.,]?\\d*+) s" ], "in \\1 day": [ - "dentro de (\\d+[.,]?\\d*) dia", - "dentro de (\\d+[.,]?\\d*) dias" + "dentro de (\\d++[.,]?\\d*+) dia", + "dentro de (\\d++[.,]?\\d*+) dias" ], "in \\1 hour": [ - "dentro de (\\d+[.,]?\\d*) h", - "dentro de (\\d+[.,]?\\d*) hora", - "dentro de (\\d+[.,]?\\d*) horas" + "dentro de (\\d++[.,]?\\d*+) h", + "dentro de (\\d++[.,]?\\d*+) hora", + "dentro de (\\d++[.,]?\\d*+) horas" ], "in \\1 minute": [ - "dentro de (\\d+[.,]?\\d*) min", - "dentro de (\\d+[.,]?\\d*) minuto", - "dentro de (\\d+[.,]?\\d*) minutos" + "dentro de (\\d++[.,]?\\d*+) min", + "dentro de (\\d++[.,]?\\d*+) minuto", + "dentro de (\\d++[.,]?\\d*+) minutos" ], "in \\1 month": [ - "dentro de (\\d+[.,]?\\d*) meses", - "dentro de (\\d+[.,]?\\d*) mês" + "dentro de (\\d++[.,]?\\d*+) meses", + "dentro de (\\d++[.,]?\\d*+) mês" ], "in \\1 second": [ - "dentro de (\\d+[.,]?\\d*) s", - "dentro de (\\d+[.,]?\\d*) segundo", - "dentro de (\\d+[.,]?\\d*) segundos" + "dentro de (\\d++[.,]?\\d*+) s", + "dentro de (\\d++[.,]?\\d*+) segundo", + "dentro de (\\d++[.,]?\\d*+) segundos" ], "in \\1 week": [ - "dentro de (\\d+[.,]?\\d*) sem", - "dentro de (\\d+[.,]?\\d*) semana", - "dentro de (\\d+[.,]?\\d*) semanas" + "dentro de (\\d++[.,]?\\d*+) sem", + "dentro de (\\d++[.,]?\\d*+) semana", + "dentro de (\\d++[.,]?\\d*+) semanas" ], "in \\1 year": [ - "dentro de (\\d+[.,]?\\d*) ano", - "dentro de (\\d+[.,]?\\d*) anos" + "dentro de (\\d++[.,]?\\d*+) ano", + "dentro de (\\d++[.,]?\\d*+) anos" ] } }, @@ -332,41 +336,44 @@ "da tarde", "tarde" ], + "second": [ + "s" + ], "relative-type-regex": { "\\1 second ago": [ - "há (\\d+[.,]?\\d*) s" + "há (\\d++[.,]?\\d*+) s" ], "in \\1 day": [ - "dentro de (\\d+[.,]?\\d*) dia", - "dentro de (\\d+[.,]?\\d*) dias" + "dentro de (\\d++[.,]?\\d*+) dia", + "dentro de (\\d++[.,]?\\d*+) dias" ], "in \\1 hour": [ - "dentro de (\\d+[.,]?\\d*) h", - "dentro de (\\d+[.,]?\\d*) hora", - "dentro de (\\d+[.,]?\\d*) horas" + "dentro de (\\d++[.,]?\\d*+) h", + "dentro de (\\d++[.,]?\\d*+) hora", + "dentro de (\\d++[.,]?\\d*+) horas" ], "in \\1 minute": [ - "dentro de (\\d+[.,]?\\d*) min", - "dentro de (\\d+[.,]?\\d*) minuto", - "dentro de (\\d+[.,]?\\d*) minutos" + "dentro de (\\d++[.,]?\\d*+) min", + "dentro de (\\d++[.,]?\\d*+) minuto", + "dentro de (\\d++[.,]?\\d*+) minutos" ], "in \\1 month": [ - "dentro de (\\d+[.,]?\\d*) meses", - "dentro de (\\d+[.,]?\\d*) mês" + "dentro de (\\d++[.,]?\\d*+) meses", + "dentro de (\\d++[.,]?\\d*+) mês" ], "in \\1 second": [ - "dentro de (\\d+[.,]?\\d*) s", - "dentro de (\\d+[.,]?\\d*) segundo", - "dentro de (\\d+[.,]?\\d*) segundos" + "dentro de (\\d++[.,]?\\d*+) s", + "dentro de (\\d++[.,]?\\d*+) segundo", + "dentro de (\\d++[.,]?\\d*+) segundos" ], "in \\1 week": [ - "dentro de (\\d+[.,]?\\d*) sem", - "dentro de (\\d+[.,]?\\d*) semana", - "dentro de (\\d+[.,]?\\d*) semanas" + "dentro de (\\d++[.,]?\\d*+) sem", + "dentro de (\\d++[.,]?\\d*+) semana", + "dentro de (\\d++[.,]?\\d*+) semanas" ], "in \\1 year": [ - "dentro de (\\d+[.,]?\\d*) ano", - "dentro de (\\d+[.,]?\\d*) anos" + "dentro de (\\d++[.,]?\\d*+) ano", + "dentro de (\\d++[.,]?\\d*+) anos" ] } }, @@ -395,41 +402,44 @@ "da tarde", "tarde" ], + "second": [ + "s" + ], "relative-type-regex": { "\\1 second ago": [ - "há (\\d+[.,]?\\d*) s" + "há (\\d++[.,]?\\d*+) s" ], "in \\1 day": [ - "dentro de (\\d+[.,]?\\d*) dia", - "dentro de (\\d+[.,]?\\d*) dias" + "dentro de (\\d++[.,]?\\d*+) dia", + "dentro de (\\d++[.,]?\\d*+) dias" ], "in \\1 hour": [ - "dentro de (\\d+[.,]?\\d*) h", - "dentro de (\\d+[.,]?\\d*) hora", - "dentro de (\\d+[.,]?\\d*) horas" + "dentro de (\\d++[.,]?\\d*+) h", + "dentro de (\\d++[.,]?\\d*+) hora", + "dentro de (\\d++[.,]?\\d*+) horas" ], "in \\1 minute": [ - "dentro de (\\d+[.,]?\\d*) min", - "dentro de (\\d+[.,]?\\d*) minuto", - "dentro de (\\d+[.,]?\\d*) minutos" + "dentro de (\\d++[.,]?\\d*+) min", + "dentro de (\\d++[.,]?\\d*+) minuto", + "dentro de (\\d++[.,]?\\d*+) minutos" ], "in \\1 month": [ - "dentro de (\\d+[.,]?\\d*) meses", - "dentro de (\\d+[.,]?\\d*) mês" + "dentro de (\\d++[.,]?\\d*+) meses", + "dentro de (\\d++[.,]?\\d*+) mês" ], "in \\1 second": [ - "dentro de (\\d+[.,]?\\d*) s", - "dentro de (\\d+[.,]?\\d*) segundo", - "dentro de (\\d+[.,]?\\d*) segundos" + "dentro de (\\d++[.,]?\\d*+) s", + "dentro de (\\d++[.,]?\\d*+) segundo", + "dentro de (\\d++[.,]?\\d*+) segundos" ], "in \\1 week": [ - "dentro de (\\d+[.,]?\\d*) sem", - "dentro de (\\d+[.,]?\\d*) semana", - "dentro de (\\d+[.,]?\\d*) semanas" + "dentro de (\\d++[.,]?\\d*+) sem", + "dentro de (\\d++[.,]?\\d*+) semana", + "dentro de (\\d++[.,]?\\d*+) semanas" ], "in \\1 year": [ - "dentro de (\\d+[.,]?\\d*) ano", - "dentro de (\\d+[.,]?\\d*) anos" + "dentro de (\\d++[.,]?\\d*+) ano", + "dentro de (\\d++[.,]?\\d*+) anos" ] } }, @@ -458,41 +468,44 @@ "da tarde", "tarde" ], + "second": [ + "s" + ], "relative-type-regex": { "\\1 second ago": [ - "há (\\d+[.,]?\\d*) s" + "há (\\d++[.,]?\\d*+) s" ], "in \\1 day": [ - "dentro de (\\d+[.,]?\\d*) dia", - "dentro de (\\d+[.,]?\\d*) dias" + "dentro de (\\d++[.,]?\\d*+) dia", + "dentro de (\\d++[.,]?\\d*+) dias" ], "in \\1 hour": [ - "dentro de (\\d+[.,]?\\d*) h", - "dentro de (\\d+[.,]?\\d*) hora", - "dentro de (\\d+[.,]?\\d*) horas" + "dentro de (\\d++[.,]?\\d*+) h", + "dentro de (\\d++[.,]?\\d*+) hora", + "dentro de (\\d++[.,]?\\d*+) horas" ], "in \\1 minute": [ - "dentro de (\\d+[.,]?\\d*) min", - "dentro de (\\d+[.,]?\\d*) minuto", - "dentro de (\\d+[.,]?\\d*) minutos" + "dentro de (\\d++[.,]?\\d*+) min", + "dentro de (\\d++[.,]?\\d*+) minuto", + "dentro de (\\d++[.,]?\\d*+) minutos" ], "in \\1 month": [ - "dentro de (\\d+[.,]?\\d*) meses", - "dentro de (\\d+[.,]?\\d*) mês" + "dentro de (\\d++[.,]?\\d*+) meses", + "dentro de (\\d++[.,]?\\d*+) mês" ], "in \\1 second": [ - "dentro de (\\d+[.,]?\\d*) s", - "dentro de (\\d+[.,]?\\d*) segundo", - "dentro de (\\d+[.,]?\\d*) segundos" + "dentro de (\\d++[.,]?\\d*+) s", + "dentro de (\\d++[.,]?\\d*+) segundo", + "dentro de (\\d++[.,]?\\d*+) segundos" ], "in \\1 week": [ - "dentro de (\\d+[.,]?\\d*) sem", - "dentro de (\\d+[.,]?\\d*) semana", - "dentro de (\\d+[.,]?\\d*) semanas" + "dentro de (\\d++[.,]?\\d*+) sem", + "dentro de (\\d++[.,]?\\d*+) semana", + "dentro de (\\d++[.,]?\\d*+) semanas" ], "in \\1 year": [ - "dentro de (\\d+[.,]?\\d*) ano", - "dentro de (\\d+[.,]?\\d*) anos" + "dentro de (\\d++[.,]?\\d*+) ano", + "dentro de (\\d++[.,]?\\d*+) anos" ] } }, @@ -521,41 +534,44 @@ "da tarde", "tarde" ], + "second": [ + "s" + ], "relative-type-regex": { "\\1 second ago": [ - "há (\\d+[.,]?\\d*) s" + "há (\\d++[.,]?\\d*+) s" ], "in \\1 day": [ - "dentro de (\\d+[.,]?\\d*) dia", - "dentro de (\\d+[.,]?\\d*) dias" + "dentro de (\\d++[.,]?\\d*+) dia", + "dentro de (\\d++[.,]?\\d*+) dias" ], "in \\1 hour": [ - "dentro de (\\d+[.,]?\\d*) h", - "dentro de (\\d+[.,]?\\d*) hora", - "dentro de (\\d+[.,]?\\d*) horas" + "dentro de (\\d++[.,]?\\d*+) h", + "dentro de (\\d++[.,]?\\d*+) hora", + "dentro de (\\d++[.,]?\\d*+) horas" ], "in \\1 minute": [ - "dentro de (\\d+[.,]?\\d*) min", - "dentro de (\\d+[.,]?\\d*) minuto", - "dentro de (\\d+[.,]?\\d*) minutos" + "dentro de (\\d++[.,]?\\d*+) min", + "dentro de (\\d++[.,]?\\d*+) minuto", + "dentro de (\\d++[.,]?\\d*+) minutos" ], "in \\1 month": [ - "dentro de (\\d+[.,]?\\d*) meses", - "dentro de (\\d+[.,]?\\d*) mês" + "dentro de (\\d++[.,]?\\d*+) meses", + "dentro de (\\d++[.,]?\\d*+) mês" ], "in \\1 second": [ - "dentro de (\\d+[.,]?\\d*) s", - "dentro de (\\d+[.,]?\\d*) segundo", - "dentro de (\\d+[.,]?\\d*) segundos" + "dentro de (\\d++[.,]?\\d*+) s", + "dentro de (\\d++[.,]?\\d*+) segundo", + "dentro de (\\d++[.,]?\\d*+) segundos" ], "in \\1 week": [ - "dentro de (\\d+[.,]?\\d*) sem", - "dentro de (\\d+[.,]?\\d*) semana", - "dentro de (\\d+[.,]?\\d*) semanas" + "dentro de (\\d++[.,]?\\d*+) sem", + "dentro de (\\d++[.,]?\\d*+) semana", + "dentro de (\\d++[.,]?\\d*+) semanas" ], "in \\1 year": [ - "dentro de (\\d+[.,]?\\d*) ano", - "dentro de (\\d+[.,]?\\d*) anos" + "dentro de (\\d++[.,]?\\d*+) ano", + "dentro de (\\d++[.,]?\\d*+) anos" ] } }, @@ -584,41 +600,44 @@ "da tarde", "tarde" ], + "second": [ + "s" + ], "relative-type-regex": { "\\1 second ago": [ - "há (\\d+[.,]?\\d*) s" + "há (\\d++[.,]?\\d*+) s" ], "in \\1 day": [ - "dentro de (\\d+[.,]?\\d*) dia", - "dentro de (\\d+[.,]?\\d*) dias" + "dentro de (\\d++[.,]?\\d*+) dia", + "dentro de (\\d++[.,]?\\d*+) dias" ], "in \\1 hour": [ - "dentro de (\\d+[.,]?\\d*) h", - "dentro de (\\d+[.,]?\\d*) hora", - "dentro de (\\d+[.,]?\\d*) horas" + "dentro de (\\d++[.,]?\\d*+) h", + "dentro de (\\d++[.,]?\\d*+) hora", + "dentro de (\\d++[.,]?\\d*+) horas" ], "in \\1 minute": [ - "dentro de (\\d+[.,]?\\d*) min", - "dentro de (\\d+[.,]?\\d*) minuto", - "dentro de (\\d+[.,]?\\d*) minutos" + "dentro de (\\d++[.,]?\\d*+) min", + "dentro de (\\d++[.,]?\\d*+) minuto", + "dentro de (\\d++[.,]?\\d*+) minutos" ], "in \\1 month": [ - "dentro de (\\d+[.,]?\\d*) meses", - "dentro de (\\d+[.,]?\\d*) mês" + "dentro de (\\d++[.,]?\\d*+) meses", + "dentro de (\\d++[.,]?\\d*+) mês" ], "in \\1 second": [ - "dentro de (\\d+[.,]?\\d*) s", - "dentro de (\\d+[.,]?\\d*) segundo", - "dentro de (\\d+[.,]?\\d*) segundos" + "dentro de (\\d++[.,]?\\d*+) s", + "dentro de (\\d++[.,]?\\d*+) segundo", + "dentro de (\\d++[.,]?\\d*+) segundos" ], "in \\1 week": [ - "dentro de (\\d+[.,]?\\d*) sem", - "dentro de (\\d+[.,]?\\d*) semana", - "dentro de (\\d+[.,]?\\d*) semanas" + "dentro de (\\d++[.,]?\\d*+) sem", + "dentro de (\\d++[.,]?\\d*+) semana", + "dentro de (\\d++[.,]?\\d*+) semanas" ], "in \\1 year": [ - "dentro de (\\d+[.,]?\\d*) ano", - "dentro de (\\d+[.,]?\\d*) anos" + "dentro de (\\d++[.,]?\\d*+) ano", + "dentro de (\\d++[.,]?\\d*+) anos" ] } }, @@ -647,41 +666,44 @@ "da tarde", "tarde" ], + "second": [ + "s" + ], "relative-type-regex": { "\\1 second ago": [ - "há (\\d+[.,]?\\d*) s" + "há (\\d++[.,]?\\d*+) s" ], "in \\1 day": [ - "dentro de (\\d+[.,]?\\d*) dia", - "dentro de (\\d+[.,]?\\d*) dias" + "dentro de (\\d++[.,]?\\d*+) dia", + "dentro de (\\d++[.,]?\\d*+) dias" ], "in \\1 hour": [ - "dentro de (\\d+[.,]?\\d*) h", - "dentro de (\\d+[.,]?\\d*) hora", - "dentro de (\\d+[.,]?\\d*) horas" + "dentro de (\\d++[.,]?\\d*+) h", + "dentro de (\\d++[.,]?\\d*+) hora", + "dentro de (\\d++[.,]?\\d*+) horas" ], "in \\1 minute": [ - "dentro de (\\d+[.,]?\\d*) min", - "dentro de (\\d+[.,]?\\d*) minuto", - "dentro de (\\d+[.,]?\\d*) minutos" + "dentro de (\\d++[.,]?\\d*+) min", + "dentro de (\\d++[.,]?\\d*+) minuto", + "dentro de (\\d++[.,]?\\d*+) minutos" ], "in \\1 month": [ - "dentro de (\\d+[.,]?\\d*) meses", - "dentro de (\\d+[.,]?\\d*) mês" + "dentro de (\\d++[.,]?\\d*+) meses", + "dentro de (\\d++[.,]?\\d*+) mês" ], "in \\1 second": [ - "dentro de (\\d+[.,]?\\d*) s", - "dentro de (\\d+[.,]?\\d*) segundo", - "dentro de (\\d+[.,]?\\d*) segundos" + "dentro de (\\d++[.,]?\\d*+) s", + "dentro de (\\d++[.,]?\\d*+) segundo", + "dentro de (\\d++[.,]?\\d*+) segundos" ], "in \\1 week": [ - "dentro de (\\d+[.,]?\\d*) sem", - "dentro de (\\d+[.,]?\\d*) semana", - "dentro de (\\d+[.,]?\\d*) semanas" + "dentro de (\\d++[.,]?\\d*+) sem", + "dentro de (\\d++[.,]?\\d*+) semana", + "dentro de (\\d++[.,]?\\d*+) semanas" ], "in \\1 year": [ - "dentro de (\\d+[.,]?\\d*) ano", - "dentro de (\\d+[.,]?\\d*) anos" + "dentro de (\\d++[.,]?\\d*+) ano", + "dentro de (\\d++[.,]?\\d*+) anos" ] } }, @@ -710,41 +732,44 @@ "da tarde", "tarde" ], + "second": [ + "s" + ], "relative-type-regex": { "\\1 second ago": [ - "há (\\d+[.,]?\\d*) s" + "há (\\d++[.,]?\\d*+) s" ], "in \\1 day": [ - "dentro de (\\d+[.,]?\\d*) dia", - "dentro de (\\d+[.,]?\\d*) dias" + "dentro de (\\d++[.,]?\\d*+) dia", + "dentro de (\\d++[.,]?\\d*+) dias" ], "in \\1 hour": [ - "dentro de (\\d+[.,]?\\d*) h", - "dentro de (\\d+[.,]?\\d*) hora", - "dentro de (\\d+[.,]?\\d*) horas" + "dentro de (\\d++[.,]?\\d*+) h", + "dentro de (\\d++[.,]?\\d*+) hora", + "dentro de (\\d++[.,]?\\d*+) horas" ], "in \\1 minute": [ - "dentro de (\\d+[.,]?\\d*) min", - "dentro de (\\d+[.,]?\\d*) minuto", - "dentro de (\\d+[.,]?\\d*) minutos" + "dentro de (\\d++[.,]?\\d*+) min", + "dentro de (\\d++[.,]?\\d*+) minuto", + "dentro de (\\d++[.,]?\\d*+) minutos" ], "in \\1 month": [ - "dentro de (\\d+[.,]?\\d*) meses", - "dentro de (\\d+[.,]?\\d*) mês" + "dentro de (\\d++[.,]?\\d*+) meses", + "dentro de (\\d++[.,]?\\d*+) mês" ], "in \\1 second": [ - "dentro de (\\d+[.,]?\\d*) s", - "dentro de (\\d+[.,]?\\d*) segundo", - "dentro de (\\d+[.,]?\\d*) segundos" + "dentro de (\\d++[.,]?\\d*+) s", + "dentro de (\\d++[.,]?\\d*+) segundo", + "dentro de (\\d++[.,]?\\d*+) segundos" ], "in \\1 week": [ - "dentro de (\\d+[.,]?\\d*) sem", - "dentro de (\\d+[.,]?\\d*) semana", - "dentro de (\\d+[.,]?\\d*) semanas" + "dentro de (\\d++[.,]?\\d*+) sem", + "dentro de (\\d++[.,]?\\d*+) semana", + "dentro de (\\d++[.,]?\\d*+) semanas" ], "in \\1 year": [ - "dentro de (\\d+[.,]?\\d*) ano", - "dentro de (\\d+[.,]?\\d*) anos" + "dentro de (\\d++[.,]?\\d*+) ano", + "dentro de (\\d++[.,]?\\d*+) anos" ] } }, @@ -773,41 +798,44 @@ "da tarde", "tarde" ], + "second": [ + "s" + ], "relative-type-regex": { "\\1 second ago": [ - "há (\\d+[.,]?\\d*) s" + "há (\\d++[.,]?\\d*+) s" ], "in \\1 day": [ - "dentro de (\\d+[.,]?\\d*) dia", - "dentro de (\\d+[.,]?\\d*) dias" + "dentro de (\\d++[.,]?\\d*+) dia", + "dentro de (\\d++[.,]?\\d*+) dias" ], "in \\1 hour": [ - "dentro de (\\d+[.,]?\\d*) h", - "dentro de (\\d+[.,]?\\d*) hora", - "dentro de (\\d+[.,]?\\d*) horas" + "dentro de (\\d++[.,]?\\d*+) h", + "dentro de (\\d++[.,]?\\d*+) hora", + "dentro de (\\d++[.,]?\\d*+) horas" ], "in \\1 minute": [ - "dentro de (\\d+[.,]?\\d*) min", - "dentro de (\\d+[.,]?\\d*) minuto", - "dentro de (\\d+[.,]?\\d*) minutos" + "dentro de (\\d++[.,]?\\d*+) min", + "dentro de (\\d++[.,]?\\d*+) minuto", + "dentro de (\\d++[.,]?\\d*+) minutos" ], "in \\1 month": [ - "dentro de (\\d+[.,]?\\d*) meses", - "dentro de (\\d+[.,]?\\d*) mês" + "dentro de (\\d++[.,]?\\d*+) meses", + "dentro de (\\d++[.,]?\\d*+) mês" ], "in \\1 second": [ - "dentro de (\\d+[.,]?\\d*) s", - "dentro de (\\d+[.,]?\\d*) segundo", - "dentro de (\\d+[.,]?\\d*) segundos" + "dentro de (\\d++[.,]?\\d*+) s", + "dentro de (\\d++[.,]?\\d*+) segundo", + "dentro de (\\d++[.,]?\\d*+) segundos" ], "in \\1 week": [ - "dentro de (\\d+[.,]?\\d*) sem", - "dentro de (\\d+[.,]?\\d*) semana", - "dentro de (\\d+[.,]?\\d*) semanas" + "dentro de (\\d++[.,]?\\d*+) sem", + "dentro de (\\d++[.,]?\\d*+) semana", + "dentro de (\\d++[.,]?\\d*+) semanas" ], "in \\1 year": [ - "dentro de (\\d+[.,]?\\d*) ano", - "dentro de (\\d+[.,]?\\d*) anos" + "dentro de (\\d++[.,]?\\d*+) ano", + "dentro de (\\d++[.,]?\\d*+) anos" ] } }, @@ -836,41 +864,44 @@ "da tarde", "tarde" ], + "second": [ + "s" + ], "relative-type-regex": { "\\1 second ago": [ - "há (\\d+[.,]?\\d*) s" + "há (\\d++[.,]?\\d*+) s" ], "in \\1 day": [ - "dentro de (\\d+[.,]?\\d*) dia", - "dentro de (\\d+[.,]?\\d*) dias" + "dentro de (\\d++[.,]?\\d*+) dia", + "dentro de (\\d++[.,]?\\d*+) dias" ], "in \\1 hour": [ - "dentro de (\\d+[.,]?\\d*) h", - "dentro de (\\d+[.,]?\\d*) hora", - "dentro de (\\d+[.,]?\\d*) horas" + "dentro de (\\d++[.,]?\\d*+) h", + "dentro de (\\d++[.,]?\\d*+) hora", + "dentro de (\\d++[.,]?\\d*+) horas" ], "in \\1 minute": [ - "dentro de (\\d+[.,]?\\d*) min", - "dentro de (\\d+[.,]?\\d*) minuto", - "dentro de (\\d+[.,]?\\d*) minutos" + "dentro de (\\d++[.,]?\\d*+) min", + "dentro de (\\d++[.,]?\\d*+) minuto", + "dentro de (\\d++[.,]?\\d*+) minutos" ], "in \\1 month": [ - "dentro de (\\d+[.,]?\\d*) meses", - "dentro de (\\d+[.,]?\\d*) mês" + "dentro de (\\d++[.,]?\\d*+) meses", + "dentro de (\\d++[.,]?\\d*+) mês" ], "in \\1 second": [ - "dentro de (\\d+[.,]?\\d*) s", - "dentro de (\\d+[.,]?\\d*) segundo", - "dentro de (\\d+[.,]?\\d*) segundos" + "dentro de (\\d++[.,]?\\d*+) s", + "dentro de (\\d++[.,]?\\d*+) segundo", + "dentro de (\\d++[.,]?\\d*+) segundos" ], "in \\1 week": [ - "dentro de (\\d+[.,]?\\d*) sem", - "dentro de (\\d+[.,]?\\d*) semana", - "dentro de (\\d+[.,]?\\d*) semanas" + "dentro de (\\d++[.,]?\\d*+) sem", + "dentro de (\\d++[.,]?\\d*+) semana", + "dentro de (\\d++[.,]?\\d*+) semanas" ], "in \\1 year": [ - "dentro de (\\d+[.,]?\\d*) ano", - "dentro de (\\d+[.,]?\\d*) anos" + "dentro de (\\d++[.,]?\\d*+) ano", + "dentro de (\\d++[.,]?\\d*+) anos" ] } }, @@ -899,41 +930,44 @@ "da tarde", "tarde" ], + "second": [ + "s" + ], "relative-type-regex": { "\\1 second ago": [ - "há (\\d+[.,]?\\d*) s" + "há (\\d++[.,]?\\d*+) s" ], "in \\1 day": [ - "dentro de (\\d+[.,]?\\d*) dia", - "dentro de (\\d+[.,]?\\d*) dias" + "dentro de (\\d++[.,]?\\d*+) dia", + "dentro de (\\d++[.,]?\\d*+) dias" ], "in \\1 hour": [ - "dentro de (\\d+[.,]?\\d*) h", - "dentro de (\\d+[.,]?\\d*) hora", - "dentro de (\\d+[.,]?\\d*) horas" + "dentro de (\\d++[.,]?\\d*+) h", + "dentro de (\\d++[.,]?\\d*+) hora", + "dentro de (\\d++[.,]?\\d*+) horas" ], "in \\1 minute": [ - "dentro de (\\d+[.,]?\\d*) min", - "dentro de (\\d+[.,]?\\d*) minuto", - "dentro de (\\d+[.,]?\\d*) minutos" + "dentro de (\\d++[.,]?\\d*+) min", + "dentro de (\\d++[.,]?\\d*+) minuto", + "dentro de (\\d++[.,]?\\d*+) minutos" ], "in \\1 month": [ - "dentro de (\\d+[.,]?\\d*) meses", - "dentro de (\\d+[.,]?\\d*) mês" + "dentro de (\\d++[.,]?\\d*+) meses", + "dentro de (\\d++[.,]?\\d*+) mês" ], "in \\1 second": [ - "dentro de (\\d+[.,]?\\d*) s", - "dentro de (\\d+[.,]?\\d*) segundo", - "dentro de (\\d+[.,]?\\d*) segundos" + "dentro de (\\d++[.,]?\\d*+) s", + "dentro de (\\d++[.,]?\\d*+) segundo", + "dentro de (\\d++[.,]?\\d*+) segundos" ], "in \\1 week": [ - "dentro de (\\d+[.,]?\\d*) sem", - "dentro de (\\d+[.,]?\\d*) semana", - "dentro de (\\d+[.,]?\\d*) semanas" + "dentro de (\\d++[.,]?\\d*+) sem", + "dentro de (\\d++[.,]?\\d*+) semana", + "dentro de (\\d++[.,]?\\d*+) semanas" ], "in \\1 year": [ - "dentro de (\\d+[.,]?\\d*) ano", - "dentro de (\\d+[.,]?\\d*) anos" + "dentro de (\\d++[.,]?\\d*+) ano", + "dentro de (\\d++[.,]?\\d*+) anos" ] } } @@ -960,6 +994,12 @@ "de" ], "sentence_splitter_group": 1, + "early_morning": [ + "de madrugada", + "na madrugada", + "pela madrugada", + "madrugada" + ], "ago": [ "atrás", "há" @@ -968,6 +1008,9 @@ "em" ], "simplifications": [ + { + "esta madrugada": "hoje madrugada" + }, { "uma": "1" }, diff --git a/dateparser/data/date_translation_data/qu.py b/dateparser/data/date_translation_data/qu.py index d741cc899..b281a44d5 100644 --- a/dateparser/data/date_translation_data/qu.py +++ b/dateparser/data/date_translation_data/qu.py @@ -2,50 +2,74 @@ "name": "qu", "date_order": "DMY", "january": [ + "ene", + "enero", "qul", "qulla puquy" ], "february": [ + "feb", + "febrero", "hat", "hatun puquy" ], "march": [ + "mar", + "marzo", "pau", "pauqar waray" ], "april": [ + "abr", + "abril", "ayr", "ayriwa" ], "may": [ + "may", + "mayo", "aym", "aymuray" ], "june": [ + "jun", + "junio", "int", "inti raymi" ], "july": [ + "jul", + "julio", "ant", "anta sitwa" ], "august": [ + "ago", + "agosto", "qha", "qhapaq sitwa" ], "september": [ + "set", + "setiembre", "uma", "uma raymi" ], "october": [ + "oct", + "octubre", "kan", "kantaray" ], "november": [ + "nov", + "noviembre", "aya", "ayamarq'a" ], "december": [ + "dic", + "diciembre", "kap", "kapaq raymi" ], @@ -96,6 +120,7 @@ "day" ], "hour": [ + "hora", "hour" ], "minute": [ @@ -106,48 +131,62 @@ ], "relative-type": { "0 day ago": [ + "kunan punchaw", "today" ], "0 hour ago": [ + "kay hora", "this hour" ], "0 minute ago": [ + "kay minuto", "this minute" ], "0 month ago": [ + "kunan killa", "this month" ], "0 second ago": [ "now" ], "0 week ago": [ + "kunan semana", "this week" ], "0 year ago": [ + "kunan wata", "this year" ], "1 day ago": [ + "qayna punchaw", "yesterday" ], "1 month ago": [ + "qayna killa", "last month" ], "1 week ago": [ + "qayna semana", "last week" ], "1 year ago": [ + "qayna wata", "last year" ], "in 1 day": [ + "paqarin", "tomorrow" ], "in 1 month": [ + "hamuq killa", "next month" ], "in 1 week": [ + "hamuq semana", "next week" ], "in 1 year": [ + "hamuq wata", "next year" ] }, diff --git a/dateparser/data/date_translation_data/rm.py b/dateparser/data/date_translation_data/rm.py index 3fb858f90..e874974b3 100644 --- a/dateparser/data/date_translation_data/rm.py +++ b/dateparser/data/date_translation_data/rm.py @@ -2,47 +2,59 @@ "name": "rm", "date_order": "DMY", "january": [ + "da schaner", "schan", "schaner" ], "february": [ + "da favrer", "favr", "favrer" ], "march": [ + "da mars", "mars" ], "april": [ "avr", - "avrigl" + "avrigl", + "d'avrigl" ], "may": [ + "da matg", "matg" ], "june": [ + "da zercladur", "zercl", "zercladur" ], "july": [ + "da fanadur", "fan", "fanadur" ], "august": [ - "avust" + "avust", + "d'avust" ], "september": [ + "da settember", "sett", "settember" ], "october": [ + "d'october", "oct", "october" ], "november": [ + "da november", "nov", "november" ], "december": [ + "da december", "dec", "december" ], @@ -90,15 +102,20 @@ "emna" ], "day": [ + "d", + "di", "tag" ], "hour": [ - "ura" + "ura", + "uras" ], "minute": [ + "min", "minuta" ], "second": [ + "s", "secunda" ], "relative-type": { @@ -121,6 +138,7 @@ "this week" ], "0 year ago": [ + "quest onn", "this year" ], "1 day ago": [ @@ -133,6 +151,7 @@ "last week" ], "1 year ago": [ + "l'onn passà", "last year" ], "in 1 day": [ @@ -145,6 +164,7 @@ "next week" ], "in 1 year": [ + "l'onn proxim", "next year" ] }, diff --git a/dateparser/data/date_translation_data/rn.py b/dateparser/data/date_translation_data/rn.py index 5a557babe..c2951c7a2 100644 --- a/dateparser/data/date_translation_data/rn.py +++ b/dateparser/data/date_translation_data/rn.py @@ -96,6 +96,7 @@ "umusi" ], "hour": [ + "hr", "isaha" ], "minute": [ diff --git a/dateparser/data/date_translation_data/ro.py b/dateparser/data/date_translation_data/ro.py index 6dcfb16e8..e07355b4a 100644 --- a/dateparser/data/date_translation_data/ro.py +++ b/dateparser/data/date_translation_data/ro.py @@ -106,6 +106,7 @@ ], "hour": [ "h", + "ore", "oră", "ore" ], @@ -138,6 +139,7 @@ "acum" ], "0 week ago": [ + "săpt aceasta", "săptămâna aceasta" ], "0 year ago": [ @@ -150,6 +152,7 @@ "luna trecută" ], "1 week ago": [ + "săpt trecută", "săptămâna trecută" ], "1 year ago": [ @@ -162,6 +165,7 @@ "luna viitoare" ], "in 1 week": [ + "săpt viitoare", "săptămâna viitoare" ], "in 1 year": [ @@ -170,73 +174,73 @@ }, "relative-type-regex": { "\\1 day ago": [ - "acum (\\d+[.,]?\\d*) de zile", - "acum (\\d+[.,]?\\d*) zi", - "acum (\\d+[.,]?\\d*) zile" + "acum (\\d++[.,]?\\d*+) de zile", + "acum (\\d++[.,]?\\d*+) zi", + "acum (\\d++[.,]?\\d*+) zile" ], "\\1 hour ago": [ - "acum (\\d+[.,]?\\d*) de ore", - "acum (\\d+[.,]?\\d*) h", - "acum (\\d+[.,]?\\d*) oră" + "acum (\\d++[.,]?\\d*+) de ore", + "acum (\\d++[.,]?\\d*+) h", + "acum (\\d++[.,]?\\d*+) oră" ], "\\1 minute ago": [ - "acum (\\d+[.,]?\\d*) de minute", - "acum (\\d+[.,]?\\d*) min", - "acum (\\d+[.,]?\\d*) minut" + "acum (\\d++[.,]?\\d*+) de minute", + "acum (\\d++[.,]?\\d*+) min", + "acum (\\d++[.,]?\\d*+) minut" ], "\\1 month ago": [ - "acum (\\d+[.,]?\\d*) de luni", - "acum (\\d+[.,]?\\d*) luni", - "acum (\\d+[.,]?\\d*) lună" + "acum (\\d++[.,]?\\d*+) de luni", + "acum (\\d++[.,]?\\d*+) luni", + "acum (\\d++[.,]?\\d*+) lună" ], "\\1 second ago": [ - "acum (\\d+[.,]?\\d*) de secunde", - "acum (\\d+[.,]?\\d*) sec", - "acum (\\d+[.,]?\\d*) secundă" + "acum (\\d++[.,]?\\d*+) de secunde", + "acum (\\d++[.,]?\\d*+) sec", + "acum (\\d++[.,]?\\d*+) secundă" ], "\\1 week ago": [ - "acum (\\d+[.,]?\\d*) de săptămâni", - "acum (\\d+[.,]?\\d*) săpt", - "acum (\\d+[.,]?\\d*) săptămână" + "acum (\\d++[.,]?\\d*+) de săptămâni", + "acum (\\d++[.,]?\\d*+) săpt", + "acum (\\d++[.,]?\\d*+) săptămână" ], "\\1 year ago": [ - "acum (\\d+[.,]?\\d*) an", - "acum (\\d+[.,]?\\d*) de ani" + "acum (\\d++[.,]?\\d*+) an", + "acum (\\d++[.,]?\\d*+) de ani" ], "in \\1 day": [ - "peste (\\d+[.,]?\\d*) de zile", - "peste (\\d+[.,]?\\d*) zi", - "peste (\\d+[.,]?\\d*) zile" + "peste (\\d++[.,]?\\d*+) de zile", + "peste (\\d++[.,]?\\d*+) zi", + "peste (\\d++[.,]?\\d*+) zile" ], "in \\1 hour": [ - "peste (\\d+[.,]?\\d*) de ore", - "peste (\\d+[.,]?\\d*) h", - "peste (\\d+[.,]?\\d*) oră" + "peste (\\d++[.,]?\\d*+) de ore", + "peste (\\d++[.,]?\\d*+) h", + "peste (\\d++[.,]?\\d*+) oră" ], "in \\1 minute": [ - "peste (\\d+[.,]?\\d*) de minute", - "peste (\\d+[.,]?\\d*) min", - "peste (\\d+[.,]?\\d*) minut" + "peste (\\d++[.,]?\\d*+) de minute", + "peste (\\d++[.,]?\\d*+) min", + "peste (\\d++[.,]?\\d*+) minut" ], "in \\1 month": [ - "peste (\\d+[.,]?\\d*) de luni", - "peste (\\d+[.,]?\\d*) luni", - "peste (\\d+[.,]?\\d*) lună" + "peste (\\d++[.,]?\\d*+) de luni", + "peste (\\d++[.,]?\\d*+) luni", + "peste (\\d++[.,]?\\d*+) lună" ], "in \\1 second": [ - "peste (\\d+[.,]?\\d*) de secunde", - "peste (\\d+[.,]?\\d*) sec", - "peste (\\d+[.,]?\\d*) secundă" + "peste (\\d++[.,]?\\d*+) de secunde", + "peste (\\d++[.,]?\\d*+) sec", + "peste (\\d++[.,]?\\d*+) secundă" ], "in \\1 week": [ - "peste (\\d+[.,]?\\d*) de săptămâni", - "peste (\\d+[.,]?\\d*) săpt", - "peste (\\d+[.,]?\\d*) săptămână" + "peste (\\d++[.,]?\\d*+) de săptămâni", + "peste (\\d++[.,]?\\d*+) săpt", + "peste (\\d++[.,]?\\d*+) săptămână" ], "in \\1 year": [ - "peste (\\d+[.,]?\\d*) an", - "peste (\\d+[.,]?\\d*) ani", - "peste (\\d+[.,]?\\d*) de ani" + "peste (\\d++[.,]?\\d*+) an", + "peste (\\d++[.,]?\\d*+) de ani", + "peste (\\d++[.,]?\\d*+) ani" ] }, "locale_specific": { diff --git a/dateparser/data/date_translation_data/rof.py b/dateparser/data/date_translation_data/rof.py index 958c869ac..1967b29e3 100644 --- a/dateparser/data/date_translation_data/rof.py +++ b/dateparser/data/date_translation_data/rof.py @@ -84,6 +84,7 @@ "mfiri" ], "hour": [ + "hr", "isaa" ], "minute": [ diff --git a/dateparser/data/date_translation_data/ru.py b/dateparser/data/date_translation_data/ru.py index 052647747..ea6a819c8 100644 --- a/dateparser/data/date_translation_data/ru.py +++ b/dateparser/data/date_translation_data/ru.py @@ -103,9 +103,11 @@ "вск" ], "am": [ + "am", "дп" ], "pm": [ + "pm", "пп" ], "year": [ @@ -139,6 +141,7 @@ "hour": [ "ч", "час", + "часы", "часа", "часов" ], @@ -162,45 +165,64 @@ "сегодня" ], "0 hour ago": [ + "в этот час", "в этом часе" ], "0 minute ago": [ "в эту минуту" ], "0 month ago": [ + "в эт мес", + "в этом мес", "в этом месяце" ], "0 second ago": [ "сейчас" ], "0 week ago": [ + "на эт нед", + "на этой нед", "на этой неделе" ], "0 year ago": [ + "в эт г", + "в этом г", "в этом году" ], "1 day ago": [ "вчера" ], "1 month ago": [ + "в пр мес", + "в прошлом мес", "в прошлом месяце" ], "1 week ago": [ + "на пр нед", + "на прошлой нед", "на прошлой неделе" ], "1 year ago": [ + "в пр г", + "в прошлом г", "в прошлом году" ], "in 1 day": [ "завтра" ], "in 1 month": [ + "в след мес", + "в следующем мес", "в следующем месяце" ], "in 1 week": [ + "на след нед", + "на следующей нед", "на следующей неделе" ], "in 1 year": [ + "в сл г", + "в след г", "в следующем году" ], "2 day ago": [ @@ -215,76 +237,76 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) д назад", - "(\\d+[.,]?\\d*) день назад", - "(\\d+[.,]?\\d*) дн назад", - "(\\d+[.,]?\\d*) дня назад" + "(\\d++[.,]?\\d*+) день назад", + "(\\d++[.,]?\\d*+) дн назад", + "(\\d++[.,]?\\d*+) дня назад", + "(\\d++[.,]?\\d*+) д назад" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) ч назад", - "(\\d+[.,]?\\d*) час назад", - "(\\d+[.,]?\\d*) часа назад" + "(\\d++[.,]?\\d*+) ч назад", + "(\\d++[.,]?\\d*+) час назад", + "(\\d++[.,]?\\d*+) часа назад" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) мин назад", - "(\\d+[.,]?\\d*) минуту назад", - "(\\d+[.,]?\\d*) минуты назад" + "(\\d++[.,]?\\d*+) мин назад", + "(\\d++[.,]?\\d*+) минуту назад", + "(\\d++[.,]?\\d*+) минуты назад" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) мес назад", - "(\\d+[.,]?\\d*) месяц назад", - "(\\d+[.,]?\\d*) месяца назад" + "(\\d++[.,]?\\d*+) мес назад", + "(\\d++[.,]?\\d*+) месяц назад", + "(\\d++[.,]?\\d*+) месяца назад" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) сек назад", - "(\\d+[.,]?\\d*) секунду назад", - "(\\d+[.,]?\\d*) секунды назад" + "(\\d++[.,]?\\d*+) сек назад", + "(\\d++[.,]?\\d*+) секунду назад", + "(\\d++[.,]?\\d*+) секунды назад" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) нед назад", - "(\\d+[.,]?\\d*) недели назад", - "(\\d+[.,]?\\d*) неделю назад" + "(\\d++[.,]?\\d*+) нед назад", + "(\\d++[.,]?\\d*+) недели назад", + "(\\d++[.,]?\\d*+) неделю назад" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) г назад", - "(\\d+[.,]?\\d*) год назад", - "(\\d+[.,]?\\d*) года назад" + "(\\d++[.,]?\\d*+) г назад", + "(\\d++[.,]?\\d*+) год назад", + "(\\d++[.,]?\\d*+) года назад" ], "in \\1 day": [ - "через (\\d+[.,]?\\d*) д", - "через (\\d+[.,]?\\d*) день", - "через (\\d+[.,]?\\d*) дн", - "через (\\d+[.,]?\\d*) дня" + "через (\\d++[.,]?\\d*+) день", + "через (\\d++[.,]?\\d*+) дн", + "через (\\d++[.,]?\\d*+) дня", + "через (\\d++[.,]?\\d*+) д" ], "in \\1 hour": [ - "через (\\d+[.,]?\\d*) ч", - "через (\\d+[.,]?\\d*) час", - "через (\\d+[.,]?\\d*) часа" + "через (\\d++[.,]?\\d*+) ч", + "через (\\d++[.,]?\\d*+) час", + "через (\\d++[.,]?\\d*+) часа" ], "in \\1 minute": [ - "через (\\d+[.,]?\\d*) мин", - "через (\\d+[.,]?\\d*) минуту", - "через (\\d+[.,]?\\d*) минуты" + "через (\\d++[.,]?\\d*+) мин", + "через (\\d++[.,]?\\d*+) минуту", + "через (\\d++[.,]?\\d*+) минуты" ], "in \\1 month": [ - "через (\\d+[.,]?\\d*) мес", - "через (\\d+[.,]?\\d*) месяц", - "через (\\d+[.,]?\\d*) месяца" + "через (\\d++[.,]?\\d*+) мес", + "через (\\d++[.,]?\\d*+) месяц", + "через (\\d++[.,]?\\d*+) месяца" ], "in \\1 second": [ - "через (\\d+[.,]?\\d*) сек", - "через (\\d+[.,]?\\d*) секунду", - "через (\\d+[.,]?\\d*) секунды" + "через (\\d++[.,]?\\d*+) сек", + "через (\\d++[.,]?\\d*+) секунду", + "через (\\d++[.,]?\\d*+) секунды" ], "in \\1 week": [ - "через (\\d+[.,]?\\d*) нед", - "через (\\d+[.,]?\\d*) недели", - "через (\\d+[.,]?\\d*) неделю" + "через (\\d++[.,]?\\d*+) нед", + "через (\\d++[.,]?\\d*+) недели", + "через (\\d++[.,]?\\d*+) неделю" ], "in \\1 year": [ - "через (\\d+[.,]?\\d*) г", - "через (\\d+[.,]?\\d*) год", - "через (\\d+[.,]?\\d*) года" + "через (\\d++[.,]?\\d*+) г", + "через (\\d++[.,]?\\d*+) год", + "через (\\d++[.,]?\\d*+) года" ] }, "locale_specific": { @@ -301,13 +323,7 @@ "name": "ru-MD" }, "ru-UA": { - "name": "ru-UA", - "am": [ - "am" - ], - "pm": [ - "pm" - ] + "name": "ru-UA" } }, "skip": [ diff --git a/dateparser/data/date_translation_data/rw.py b/dateparser/data/date_translation_data/rw.py index 4a34e9e32..0f5b0c95a 100644 --- a/dateparser/data/date_translation_data/rw.py +++ b/dateparser/data/date_translation_data/rw.py @@ -19,6 +19,7 @@ ], "may": [ "gic", + "gicurasi", "gicuransi" ], "june": [ @@ -96,7 +97,8 @@ "day" ], "hour": [ - "hour" + "hour", + "hr" ], "minute": [ "minute" diff --git a/dateparser/data/date_translation_data/rwk.py b/dateparser/data/date_translation_data/rwk.py index ef8384c93..1151f5581 100644 --- a/dateparser/data/date_translation_data/rwk.py +++ b/dateparser/data/date_translation_data/rwk.py @@ -95,6 +95,7 @@ "mfiri" ], "hour": [ + "hr", "saa" ], "minute": [ diff --git a/dateparser/data/date_translation_data/sah.py b/dateparser/data/date_translation_data/sah.py index da5a7d0be..5dae996cc 100644 --- a/dateparser/data/date_translation_data/sah.py +++ b/dateparser/data/date_translation_data/sah.py @@ -158,47 +158,47 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) күн ынараа өттүгэр" + "(\\d++[.,]?\\d*+) күн ынараа өттүгэр" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) чаас ынараа өттүгэр" + "(\\d++[.,]?\\d*+) чаас ынараа өттүгэр" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) мүнүүтэ ынараа өттүгэр" + "(\\d++[.,]?\\d*+) мүнүүтэ ынараа өттүгэр" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) ый ынараа өттүгэр" + "(\\d++[.,]?\\d*+) ый ынараа өттүгэр" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) сөк анараа өттүгэр", - "(\\d+[.,]?\\d*) сөкүүндэ ынараа өттүгэр" + "(\\d++[.,]?\\d*+) сөк анараа өттүгэр", + "(\\d++[.,]?\\d*+) сөкүүндэ ынараа өттүгэр" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) нэдиэлэ анараа өттүгэр" + "(\\d++[.,]?\\d*+) нэдиэлэ анараа өттүгэр" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) сыл ынараа өттүгэр" + "(\\d++[.,]?\\d*+) сыл ынараа өттүгэр" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) күнүнэн" + "(\\d++[.,]?\\d*+) күнүнэн" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) чааһынан" + "(\\d++[.,]?\\d*+) чааһынан" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) мүнүүтэннэн" + "(\\d++[.,]?\\d*+) мүнүүтэннэн" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) ыйынан" + "(\\d++[.,]?\\d*+) ыйынан" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) сөкүүндэннэн" + "(\\d++[.,]?\\d*+) сөкүүндэннэн" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) нэдиэлэннэн" + "(\\d++[.,]?\\d*+) нэдиэлэннэн" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) сылынан" + "(\\d++[.,]?\\d*+) сылынан" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/saq.py b/dateparser/data/date_translation_data/saq.py index b6105f34b..a2fdd4fc9 100644 --- a/dateparser/data/date_translation_data/saq.py +++ b/dateparser/data/date_translation_data/saq.py @@ -96,6 +96,7 @@ "mpari" ], "hour": [ + "hr", "saai" ], "minute": [ diff --git a/dateparser/data/date_translation_data/sbp.py b/dateparser/data/date_translation_data/sbp.py index 5e1f3d90c..7b0bd53d0 100644 --- a/dateparser/data/date_translation_data/sbp.py +++ b/dateparser/data/date_translation_data/sbp.py @@ -96,6 +96,7 @@ "lusiku" ], "hour": [ + "hr", "ilisala" ], "minute": [ diff --git a/dateparser/data/date_translation_data/se.py b/dateparser/data/date_translation_data/se.py index 481d63a47..0de1da24c 100644 --- a/dateparser/data/date_translation_data/se.py +++ b/dateparser/data/date_translation_data/se.py @@ -100,7 +100,8 @@ "beaivi" ], "hour": [ - "diibmu" + "diibmu", + "diibmur" ], "minute": [ "minuhtta" @@ -157,105 +158,217 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) jándor árat", - "(\\d+[.,]?\\d*) jándora árat" + "(\\d++[.,]?\\d*+) jándor árat", + "(\\d++[.,]?\\d*+) jándora árat" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) diibmu árat", - "(\\d+[.,]?\\d*) diibmur árat" + "(\\d++[.,]?\\d*+) diibmu árat", + "(\\d++[.,]?\\d*+) diibmur árat" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) minuhta árat", - "(\\d+[.,]?\\d*) minuhtta árat" + "(\\d++[.,]?\\d*+) minuhta árat", + "(\\d++[.,]?\\d*+) minuhtta árat" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) mánotbadji árat" + "(\\d++[.,]?\\d*+) mánotbadji árat" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) sekunda árat", - "(\\d+[.,]?\\d*) sekundda árat" + "(\\d++[.,]?\\d*+) sekunda árat", + "(\\d++[.,]?\\d*+) sekundda árat" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) vahkku árat", - "(\\d+[.,]?\\d*) vahku árat" + "(\\d++[.,]?\\d*+) vahkku árat", + "(\\d++[.,]?\\d*+) vahku árat" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) jahki árat", - "(\\d+[.,]?\\d*) jahkki árat" + "(\\d++[.,]?\\d*+) jahki árat", + "(\\d++[.,]?\\d*+) jahkki árat" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) jándor maŋŋilit", - "(\\d+[.,]?\\d*) jándora maŋŋilit" + "(\\d++[.,]?\\d*+) jándor maŋŋilit", + "(\\d++[.,]?\\d*+) jándora maŋŋilit" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) diibmu maŋŋilit", - "(\\d+[.,]?\\d*) diibmur maŋŋilit" + "(\\d++[.,]?\\d*+) diibmu maŋŋilit", + "(\\d++[.,]?\\d*+) diibmur maŋŋilit" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) minuhta maŋŋilit", - "(\\d+[.,]?\\d*) minuhtta maŋŋilit" + "(\\d++[.,]?\\d*+) minuhta maŋŋilit", + "(\\d++[.,]?\\d*+) minuhtta maŋŋilit" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) mánotbadji maŋŋilit" + "(\\d++[.,]?\\d*+) mánotbadji maŋŋilit" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) sekunda maŋŋilit", - "(\\d+[.,]?\\d*) sekundda maŋŋilit" + "(\\d++[.,]?\\d*+) sekunda maŋŋilit", + "(\\d++[.,]?\\d*+) sekundda maŋŋilit" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) vahkku maŋŋilit", - "(\\d+[.,]?\\d*) vahku maŋŋilit" + "(\\d++[.,]?\\d*+) vahkku maŋŋilit", + "(\\d++[.,]?\\d*+) vahku maŋŋilit" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) jahki maŋŋilit", - "(\\d+[.,]?\\d*) jahkki maŋŋilit" + "(\\d++[.,]?\\d*+) jahki maŋŋilit", + "(\\d++[.,]?\\d*+) jahkki maŋŋilit" ] }, "locale_specific": { "se-FI": { "name": "se-FI", + "date_order": "DMY", + "april": [ + "cuoŋ" + ], "monday": [ + "má", + "mánnodat", "vuossárgga" ], "tuesday": [ + "di", + "disdat", "maŋŋebárgga" ], "wednesday": [ + "ga", "gaskavahku" ], "thursday": [ + "du", + "duorastat", "duorastaga" ], "friday": [ + "be", "bearjadaga" ], "saturday": [ + "lá", + "lávvordat", "lávvardaga" ], + "sunday": [ + "so" + ], "year": [ "j", "jahki" ], + "month": [ + "m" + ], "week": [ + "v(k)", "vahkku" ], + "day": [ + "b" + ], + "hour": [ + "dmu" + ], + "minute": [ + "min" + ], + "second": [ + "sek" + ], "relative-type": { + "0 hour ago": [ + "dán diimmu" + ], + "0 minute ago": [ + "dán minuhta" + ], + "0 month ago": [ + "dán mánu" + ], + "0 second ago": [ + "dál" + ], + "0 week ago": [ + "dán vahku" + ], "0 year ago": [ "dán jagi" ], + "1 month ago": [ + "mannan mánu" + ], + "1 week ago": [ + "mannan vahku" + ], "1 year ago": [ + "diibmá", "mannan jagi" ], + "in 1 month": [ + "boahtte mánu" + ], + "in 1 week": [ + "boahtte vahku" + ], "in 1 year": [ "boahtte jagi" ] }, "relative-type-regex": { + "\\1 day ago": [ + "(\\d++[.,]?\\d*+) beaivve dás ovdal" + ], + "\\1 hour ago": [ + "(\\d++[.,]?\\d*+) diibmu áigi", + "(\\d++[.,]?\\d*+) diimmu áigi", + "(\\d++[.,]?\\d*+) dmu áigi" + ], + "\\1 minute ago": [ + "(\\d++[.,]?\\d*+) min áigi", + "(\\d++[.,]?\\d*+) minuhta áigi", + "(\\d++[.,]?\\d*+) minuhtta áigi" + ], + "\\1 month ago": [ + "(\\d++[.,]?\\d*+) mánnu dás ovdal", + "(\\d++[.,]?\\d*+) mánu dás ovdal" + ], + "\\1 second ago": [ + "(\\d++[.,]?\\d*+) sek áigi", + "(\\d++[.,]?\\d*+) sekunda áigi", + "(\\d++[.,]?\\d*+) sekundda áigi" + ], + "\\1 week ago": [ + "(\\d++[.,]?\\d*+) vahkku dás ovdal", + "(\\d++[.,]?\\d*+) vahku dás ovdal" + ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) jagi árat" + "(\\d++[.,]?\\d*+) j dás ovdal", + "(\\d++[.,]?\\d*+) jagi dás ovdal", + "(\\d++[.,]?\\d*+) jagi árat" + ], + "in \\1 day": [ + "(\\d++[.,]?\\d*+) beaivve siste" + ], + "in \\1 hour": [ + "(\\d++[.,]?\\d*+) diimmu siste", + "(\\d++[.,]?\\d*+) dmu siste" + ], + "in \\1 minute": [ + "(\\d++[.,]?\\d*+) min siste", + "(\\d++[.,]?\\d*+) minuhta siste" + ], + "in \\1 month": [ + "(\\d++[.,]?\\d*+) mánu geahčen", + "(\\d++[.,]?\\d*+) mánu siste" + ], + "in \\1 second": [ + "(\\d++[.,]?\\d*+) sek siste", + "(\\d++[.,]?\\d*+) sekundda siste" + ], + "in \\1 week": [ + "(\\d++[.,]?\\d*+) vahku geahčen" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) jagi siste" + "(\\d++[.,]?\\d*+) j siste", + "(\\d++[.,]?\\d*+) jagi siste" ] } }, diff --git a/dateparser/data/date_translation_data/seh.py b/dateparser/data/date_translation_data/seh.py index 608c8d163..fc573e737 100644 --- a/dateparser/data/date_translation_data/seh.py +++ b/dateparser/data/date_translation_data/seh.py @@ -96,7 +96,8 @@ "ntsiku" ], "hour": [ - "hora" + "hora", + "hr" ], "minute": [ "minuto" diff --git a/dateparser/data/date_translation_data/ses.py b/dateparser/data/date_translation_data/ses.py index 4ced09b8b..e99bb38f9 100644 --- a/dateparser/data/date_translation_data/ses.py +++ b/dateparser/data/date_translation_data/ses.py @@ -94,7 +94,8 @@ "zaari" ], "hour": [ - "guuru" + "guuru", + "hr" ], "minute": [ "miniti" diff --git a/dateparser/data/date_translation_data/sg.py b/dateparser/data/date_translation_data/sg.py index 65b0ff2ad..fdfb4f07d 100644 --- a/dateparser/data/date_translation_data/sg.py +++ b/dateparser/data/date_translation_data/sg.py @@ -96,6 +96,7 @@ "lâ" ], "hour": [ + "hr", "ngbonga" ], "minute": [ diff --git a/dateparser/data/date_translation_data/shi-Latn.py b/dateparser/data/date_translation_data/shi-Latn.py index 0943af4f1..82faaefb7 100644 --- a/dateparser/data/date_translation_data/shi-Latn.py +++ b/dateparser/data/date_translation_data/shi-Latn.py @@ -96,6 +96,7 @@ "ass" ], "hour": [ + "hr", "tasragt" ], "minute": [ diff --git a/dateparser/data/date_translation_data/shi-Tfng.py b/dateparser/data/date_translation_data/shi-Tfng.py index d8601fa30..a033c6cbd 100644 --- a/dateparser/data/date_translation_data/shi-Tfng.py +++ b/dateparser/data/date_translation_data/shi-Tfng.py @@ -96,6 +96,7 @@ "ⴰⵙⵙ" ], "hour": [ + "hr", "ⵜⴰⵙⵔⴰⴳⵜ" ], "minute": [ diff --git a/dateparser/data/date_translation_data/shi.py b/dateparser/data/date_translation_data/shi.py index 4c498356f..ce1f623e9 100644 --- a/dateparser/data/date_translation_data/shi.py +++ b/dateparser/data/date_translation_data/shi.py @@ -96,6 +96,7 @@ "ⴰⵙⵙ" ], "hour": [ + "hr", "ⵜⴰⵙⵔⴰⴳⵜ" ], "minute": [ diff --git a/dateparser/data/date_translation_data/si.py b/dateparser/data/date_translation_data/si.py index d69a822b8..5351a1b2b 100644 --- a/dateparser/data/date_translation_data/si.py +++ b/dateparser/data/date_translation_data/si.py @@ -92,18 +92,18 @@ "දිනය" ], "hour": [ - "පැ", - "පැය" + "පැය", + "පැ" ], "minute": [ - "මි", "මිනි", - "මිනිත්තුව" + "මිනිත්තුව", + "මි" ], "second": [ - "ත", "තත්", - "තත්පරය" + "තත්පරය", + "ත" ], "relative-type": { "0 day ago": [ @@ -160,46 +160,46 @@ }, "relative-type-regex": { "\\1 day ago": [ - "දින (\\d+[.,]?\\d*)කට පෙර" + "දින (\\d++[.,]?\\d*+)කට පෙර" ], "\\1 hour ago": [ - "පැය (\\d+[.,]?\\d*)කට පෙර" + "පැය (\\d++[.,]?\\d*+)කට පෙර" ], "\\1 minute ago": [ - "මිනිත්තු (\\d+[.,]?\\d*)කට පෙර" + "මිනිත්තු (\\d++[.,]?\\d*+)කට පෙර" ], "\\1 month ago": [ - "මාස (\\d+[.,]?\\d*)කට පෙර" + "මාස (\\d++[.,]?\\d*+)කට පෙර" ], "\\1 second ago": [ - "තත්පර (\\d+[.,]?\\d*)කට පෙර" + "තත්පර (\\d++[.,]?\\d*+)කට පෙර" ], "\\1 week ago": [ - "සති (\\d+[.,]?\\d*)කට පෙර" + "සති (\\d++[.,]?\\d*+)කට පෙර" ], "\\1 year ago": [ - "වසර (\\d+[.,]?\\d*)කට පෙර" + "වසර (\\d++[.,]?\\d*+)කට පෙර" ], "in \\1 day": [ - "දින (\\d+[.,]?\\d*)න්" + "දින (\\d++[.,]?\\d*+)න්" ], "in \\1 hour": [ - "පැය (\\d+[.,]?\\d*)කින්" + "පැය (\\d++[.,]?\\d*+)කින්" ], "in \\1 minute": [ - "මිනිත්තු (\\d+[.,]?\\d*)කින්" + "මිනිත්තු (\\d++[.,]?\\d*+)කින්" ], "in \\1 month": [ - "මාස (\\d+[.,]?\\d*)කින්" + "මාස (\\d++[.,]?\\d*+)කින්" ], "in \\1 second": [ - "තත්පර (\\d+[.,]?\\d*)කින්" + "තත්පර (\\d++[.,]?\\d*+)කින්" ], "in \\1 week": [ - "සති (\\d+[.,]?\\d*)කින්" + "සති (\\d++[.,]?\\d*+)කින්" ], "in \\1 year": [ - "වසර (\\d+[.,]?\\d*)කින්" + "වසර (\\d++[.,]?\\d*+)කින්" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/sk.py b/dateparser/data/date_translation_data/sk.py index df71e31ba..8fa24eae3 100644 --- a/dateparser/data/date_translation_data/sk.py +++ b/dateparser/data/date_translation_data/sk.py @@ -113,7 +113,8 @@ ], "hour": [ "h", - "hodina" + "hodina", + "hodiny" ], "minute": [ "min", @@ -134,12 +135,14 @@ "v tejto minúte" ], "0 month ago": [ + "tento mes", "tento mesiac" ], "0 second ago": [ "teraz" ], "0 week ago": [ + "tento týž", "tento týždeň" ], "0 year ago": [ @@ -149,9 +152,11 @@ "včera" ], "1 month ago": [ + "minulý mes", "minulý mesiac" ], "1 week ago": [ + "minulý týž", "minulý týždeň" ], "1 year ago": [ @@ -161,9 +166,11 @@ "zajtra" ], "in 1 month": [ + "budúci mes", "budúci mesiac" ], "in 1 week": [ + "budúci týž", "budúci týždeň" ], "in 1 year": [ @@ -178,81 +185,81 @@ }, "relative-type-regex": { "\\1 day ago": [ - "pred (\\d+[.,]?\\d*) d", - "pred (\\d+[.,]?\\d*) dňami", - "pred (\\d+[.,]?\\d*) dňom" + "pred (\\d++[.,]?\\d*+) d", + "pred (\\d++[.,]?\\d*+) dňami", + "pred (\\d++[.,]?\\d*+) dňom" ], "\\1 hour ago": [ - "pred (\\d+[.,]?\\d*) h", - "pred (\\d+[.,]?\\d*) hodinami", - "pred (\\d+[.,]?\\d*) hodinou" + "pred (\\d++[.,]?\\d*+) h", + "pred (\\d++[.,]?\\d*+) hodinami", + "pred (\\d++[.,]?\\d*+) hodinou" ], "\\1 minute ago": [ - "pred (\\d+[.,]?\\d*) min", - "pred (\\d+[.,]?\\d*) minútami", - "pred (\\d+[.,]?\\d*) minútou" + "pred (\\d++[.,]?\\d*+) min", + "pred (\\d++[.,]?\\d*+) minútami", + "pred (\\d++[.,]?\\d*+) minútou" ], "\\1 month ago": [ - "pred (\\d+[.,]?\\d*) mes", - "pred (\\d+[.,]?\\d*) mesiacmi", - "pred (\\d+[.,]?\\d*) mesiacom" + "pred (\\d++[.,]?\\d*+) mes", + "pred (\\d++[.,]?\\d*+) mesiacmi", + "pred (\\d++[.,]?\\d*+) mesiacom" ], "\\1 second ago": [ - "pred (\\d+[.,]?\\d*) s", - "pred (\\d+[.,]?\\d*) sekundami", - "pred (\\d+[.,]?\\d*) sekundou" + "pred (\\d++[.,]?\\d*+) s", + "pred (\\d++[.,]?\\d*+) sekundami", + "pred (\\d++[.,]?\\d*+) sekundou" ], "\\1 week ago": [ - "pred (\\d+[.,]?\\d*) týž", - "pred (\\d+[.,]?\\d*) týždňami", - "pred (\\d+[.,]?\\d*) týždňom" + "pred (\\d++[.,]?\\d*+) týž", + "pred (\\d++[.,]?\\d*+) týždňami", + "pred (\\d++[.,]?\\d*+) týždňom" ], "\\1 year ago": [ - "pred (\\d+[.,]?\\d*) r", - "pred (\\d+[.,]?\\d*) rokmi", - "pred (\\d+[.,]?\\d*) rokom" + "pred (\\d++[.,]?\\d*+) r", + "pred (\\d++[.,]?\\d*+) rokmi", + "pred (\\d++[.,]?\\d*+) rokom" ], "in \\1 day": [ - "o (\\d+[.,]?\\d*) d", - "o (\\d+[.,]?\\d*) deň", - "o (\\d+[.,]?\\d*) dní", - "o (\\d+[.,]?\\d*) dni" + "o (\\d++[.,]?\\d*+) d", + "o (\\d++[.,]?\\d*+) deň", + "o (\\d++[.,]?\\d*+) dní", + "o (\\d++[.,]?\\d*+) dni" ], "in \\1 hour": [ - "o (\\d+[.,]?\\d*) h", - "o (\\d+[.,]?\\d*) hodinu", - "o (\\d+[.,]?\\d*) hodín", - "o (\\d+[.,]?\\d*) hodiny" + "o (\\d++[.,]?\\d*+) h", + "o (\\d++[.,]?\\d*+) hodinu", + "o (\\d++[.,]?\\d*+) hodín", + "o (\\d++[.,]?\\d*+) hodiny" ], "in \\1 minute": [ - "o (\\d+[.,]?\\d*) min", - "o (\\d+[.,]?\\d*) minút", - "o (\\d+[.,]?\\d*) minútu", - "o (\\d+[.,]?\\d*) minúty" + "o (\\d++[.,]?\\d*+) min", + "o (\\d++[.,]?\\d*+) minút", + "o (\\d++[.,]?\\d*+) minútu", + "o (\\d++[.,]?\\d*+) minúty" ], "in \\1 month": [ - "o (\\d+[.,]?\\d*) mes", - "o (\\d+[.,]?\\d*) mesiac", - "o (\\d+[.,]?\\d*) mesiacov", - "o (\\d+[.,]?\\d*) mesiace" + "o (\\d++[.,]?\\d*+) mes", + "o (\\d++[.,]?\\d*+) mesiac", + "o (\\d++[.,]?\\d*+) mesiacov", + "o (\\d++[.,]?\\d*+) mesiace" ], "in \\1 second": [ - "o (\\d+[.,]?\\d*) s", - "o (\\d+[.,]?\\d*) sekundu", - "o (\\d+[.,]?\\d*) sekúnd", - "o (\\d+[.,]?\\d*) sekundy" + "o (\\d++[.,]?\\d*+) s", + "o (\\d++[.,]?\\d*+) sekundu", + "o (\\d++[.,]?\\d*+) sekúnd", + "o (\\d++[.,]?\\d*+) sekundy" ], "in \\1 week": [ - "o (\\d+[.,]?\\d*) týž", - "o (\\d+[.,]?\\d*) týždeň", - "o (\\d+[.,]?\\d*) týždňov", - "o (\\d+[.,]?\\d*) týždne" + "o (\\d++[.,]?\\d*+) týž", + "o (\\d++[.,]?\\d*+) týždeň", + "o (\\d++[.,]?\\d*+) týždňov", + "o (\\d++[.,]?\\d*+) týždne" ], "in \\1 year": [ - "o (\\d+[.,]?\\d*) r", - "o (\\d+[.,]?\\d*) rok", - "o (\\d+[.,]?\\d*) rokov", - "o (\\d+[.,]?\\d*) roky" + "o (\\d++[.,]?\\d*+) r", + "o (\\d++[.,]?\\d*+) rok", + "o (\\d++[.,]?\\d*+) rokov", + "o (\\d++[.,]?\\d*+) roky" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/sl.py b/dateparser/data/date_translation_data/sl.py index 4985c9b9e..6100baaae 100644 --- a/dateparser/data/date_translation_data/sl.py +++ b/dateparser/data/date_translation_data/sl.py @@ -100,7 +100,8 @@ ], "hour": [ "h", - "ura" + "ura", + "ure" ], "minute": [ "min", @@ -122,12 +123,14 @@ "to minuto" ], "0 month ago": [ + "ta mes", "ta mesec" ], "0 second ago": [ "zdaj" ], "0 week ago": [ + "ta ted", "ta teden" ], "0 year ago": [ @@ -137,9 +140,13 @@ "včeraj" ], "1 month ago": [ + "prej mes", + "prejšnji mes", "prejšnji mesec" ], "1 week ago": [ + "prej ted", + "prejšnji ted", "prejšnji teden" ], "1 year ago": [ @@ -149,9 +156,13 @@ "jutri" ], "in 1 month": [ + "nasl mes", + "naslednji mes", "naslednji mesec" ], "in 1 week": [ + "nasl ted", + "naslednji ted", "naslednji teden" ], "in 1 year": [ @@ -160,73 +171,96 @@ }, "relative-type-regex": { "\\1 day ago": [ - "pred (\\d+[.,]?\\d*) dnevi", - "pred (\\d+[.,]?\\d*) dnevom" + "pred (\\d++[.,]?\\d*+) dnevi", + "pred (\\d++[.,]?\\d*+) dnevom" ], "\\1 hour ago": [ - "pred (\\d+[.,]?\\d*) h", - "pred (\\d+[.,]?\\d*) urami", - "pred (\\d+[.,]?\\d*) uro" + "pred (\\d++[.,]?\\d*+) h", + "pred (\\d++[.,]?\\d*+) urami", + "pred (\\d++[.,]?\\d*+) uro" ], "\\1 minute ago": [ - "pred (\\d+[.,]?\\d*) min", - "pred (\\d+[.,]?\\d*) minutami", - "pred (\\d+[.,]?\\d*) minuto" + "pred (\\d++[.,]?\\d*+) min", + "pred (\\d++[.,]?\\d*+) minutami", + "pred (\\d++[.,]?\\d*+) minuto" ], "\\1 month ago": [ - "pred (\\d+[.,]?\\d*) mes", - "pred (\\d+[.,]?\\d*) mesecem", - "pred (\\d+[.,]?\\d*) meseci" + "pred (\\d++[.,]?\\d*+) mes", + "pred (\\d++[.,]?\\d*+) mesecem", + "pred (\\d++[.,]?\\d*+) meseci" ], "\\1 second ago": [ - "pred (\\d+[.,]?\\d*) s", - "pred (\\d+[.,]?\\d*) sekundami", - "pred (\\d+[.,]?\\d*) sekundo" + "pred (\\d++[.,]?\\d*+) s", + "pred (\\d++[.,]?\\d*+) sekundami", + "pred (\\d++[.,]?\\d*+) sekundo" ], "\\1 week ago": [ - "pred (\\d+[.,]?\\d*) ted", - "pred (\\d+[.,]?\\d*) tedni", - "pred (\\d+[.,]?\\d*) tednom" + "pred (\\d++[.,]?\\d*+) ted", + "pred (\\d++[.,]?\\d*+) tedni", + "pred (\\d++[.,]?\\d*+) tednom" ], "\\1 year ago": [ - "pred (\\d+[.,]?\\d*) leti", - "pred (\\d+[.,]?\\d*) letom" + "pred (\\d++[.,]?\\d*+) leti", + "pred (\\d++[.,]?\\d*+) letom" ], "in \\1 day": [ - "čez (\\d+[.,]?\\d*) dan", - "čez (\\d+[.,]?\\d*) dni" + "čez (\\d++[.,]?\\d*+) dan", + "čez (\\d++[.,]?\\d*+) dni" ], "in \\1 hour": [ - "čez (\\d+[.,]?\\d*) h", - "čez (\\d+[.,]?\\d*) ur", - "čez (\\d+[.,]?\\d*) uro" + "čez (\\d++[.,]?\\d*+) h", + "čez (\\d++[.,]?\\d*+) ur", + "čez (\\d++[.,]?\\d*+) uro" ], "in \\1 minute": [ - "čez (\\d+[.,]?\\d*) min", - "čez (\\d+[.,]?\\d*) minut", - "čez (\\d+[.,]?\\d*) minuto" + "čez (\\d++[.,]?\\d*+) min", + "čez (\\d++[.,]?\\d*+) minut", + "čez (\\d++[.,]?\\d*+) minuto" ], "in \\1 month": [ - "čez (\\d+[.,]?\\d*) mes", - "čez (\\d+[.,]?\\d*) mesec", - "čez (\\d+[.,]?\\d*) mesecev" + "čez (\\d++[.,]?\\d*+) mes", + "čez (\\d++[.,]?\\d*+) mesec", + "čez (\\d++[.,]?\\d*+) mesecev" ], "in \\1 second": [ - "čez (\\d+[.,]?\\d*) s", - "čez (\\d+[.,]?\\d*) sekund", - "čez (\\d+[.,]?\\d*) sekundo" + "čez (\\d++[.,]?\\d*+) s", + "čez (\\d++[.,]?\\d*+) sekund", + "čez (\\d++[.,]?\\d*+) sekundo" ], "in \\1 week": [ - "čez (\\d+[.,]?\\d*) ted", - "čez (\\d+[.,]?\\d*) teden", - "čez (\\d+[.,]?\\d*) tednov" + "čez (\\d++[.,]?\\d*+) ted", + "čez (\\d++[.,]?\\d*+) teden", + "čez (\\d++[.,]?\\d*+) tednov" ], "in \\1 year": [ - "čez (\\d+[.,]?\\d*) let", - "čez (\\d+[.,]?\\d*) leto" + "čez (\\d++[.,]?\\d*+) let", + "čez (\\d++[.,]?\\d*+) leto" ] }, "locale_specific": {}, + "simplifications": [ + { + "(?<=pred\\s+)tednom\\b": "1 tednom" + }, + { + "(?<=pred\\s+)mesecem\\b": "1 mesecem" + }, + { + "(?<=pred\\s+)letom\\b": "1 letom" + }, + { + "(?<=pred\\s+)dnevom\\b": "1 dnevom" + }, + { + "(?<=pred\\s+)uro\\b": "1 uro" + }, + { + "(?<=pred\\s+)minuto\\b": "1 minuto" + }, + { + "(?<=pred\\s+)sekundo\\b": "1 sekundo" + } + ], "skip": [ " ", "'", diff --git a/dateparser/data/date_translation_data/smn.py b/dateparser/data/date_translation_data/smn.py index 628485a1f..59395dc34 100644 --- a/dateparser/data/date_translation_data/smn.py +++ b/dateparser/data/date_translation_data/smn.py @@ -103,7 +103,8 @@ "day" ], "hour": [ - "hour" + "hour", + "tiijmeh" ], "minute": [ "minute" diff --git a/dateparser/data/date_translation_data/sn.py b/dateparser/data/date_translation_data/sn.py index b22665608..40f4cb9a2 100644 --- a/dateparser/data/date_translation_data/sn.py +++ b/dateparser/data/date_translation_data/sn.py @@ -96,7 +96,8 @@ "zuva" ], "hour": [ - "awa" + "awa", + "hr" ], "minute": [ "mineti" diff --git a/dateparser/data/date_translation_data/so.py b/dateparser/data/date_translation_data/so.py index 9430810a3..79cdea5f8 100644 --- a/dateparser/data/date_translation_data/so.py +++ b/dateparser/data/date_translation_data/so.py @@ -3,50 +3,73 @@ "date_order": "DMY", "january": [ "bisha koobaad", + "jan", + "jannaayo", "kob" ], "february": [ "bisha labaad", + "feb", + "febraayo", "lab" ], "march": [ "bisha saddexaad", + "maarso", + "mar", "sad" ], "april": [ - "afr", - "bisha afraad" + "abr", + "abriil", + "bisha afraad", + "afr" ], "may": [ "bisha shanaad", + "may", "sha" ], "june": [ "bisha lixaad", + "jun", + "juun", "lix" ], "july": [ "bisha todobaad", + "lul", + "luuliyo", "tod" ], "august": [ "bisha sideedaad", + "ogosto", + "ogs", "sid" ], "september": [ "bisha sagaalaad", + "seb", + "sebteembar", "sag" ], "october": [ "bisha tobnaad", + "okt", + "oktoobar", "tob" ], "november": [ "bisha kow iyo tobnaad", + "nof", + "noofeembar", "kit" ], "december": [ "bisha laba iyo tobnaad", + "dis", + "diseembar", "lit" ], "monday": [ @@ -54,54 +77,76 @@ "isniin" ], "tuesday": [ - "tal", - "talaado" + "talaado", + "tldo", + "tal" ], "wednesday": [ - "arb", - "arbaco" + "arbaco", + "arbc", + "arb" ], "thursday": [ - "kha", - "khamiis" + "khamiis", + "khms", + "kha" ], "friday": [ - "jim", - "jimco" + "jimco", + "jmc", + "jim" ], "saturday": [ - "sab", - "sabti" + "sabti", + "sbti", + "sab" ], "sunday": [ "axad", "axd" ], "am": [ + "am", + "gh", "sn" ], "pm": [ + "gd", "gn" ], "year": [ + "sannad", + "snd", "year" ], "month": [ + "bil", "month" ], "week": [ + "tdbd", + "toddobaad", "week" ], "day": [ + "maalin", + "mln", "day" ], "hour": [ + "saacad", + "saacado", + "scd", "hour" ], "minute": [ + "daqiiqad", + "dqqd", "minute" ], "second": [ + "ilbiriqsi", + "ilbrqsi", "second" ], "relative-type": { @@ -109,48 +154,133 @@ "maanta" ], "0 hour ago": [ + "saacadan", "this hour" ], "0 minute ago": [ + "daqiiqadan", "this minute" ], "0 month ago": [ + "bishan", "this month" ], "0 second ago": [ + "imika", + "iminka", "now" ], "0 week ago": [ + "toddobaadkan", + "usbuucan", "this week" ], "0 year ago": [ + "sannadkan", "this year" ], "1 day ago": [ "shalay" ], "1 month ago": [ + "bishii hore", "last month" ], "1 week ago": [ + "toddobaadkii hore", "last week" ], "1 year ago": [ + "sannadkii hore", + "sannadkii la soo dhaafay", "last year" ], "in 1 day": [ "berri" ], "in 1 month": [ + "bisha danbe", "next month" ], "in 1 week": [ + "toddobaadka danbe", "next week" ], "in 1 year": [ + "sannadka danbe", + "sannadka xiga", "next year" ] }, + "relative-type-regex": { + "\\1 day ago": [ + "(\\d++[.,]?\\d*+) maalin kahor", + "(\\d++[.,]?\\d*+) maalmood kahor", + "(\\d++[.,]?\\d*+) mlmd khr", + "(\\d++[.,]?\\d*+) mln khr" + ], + "\\1 hour ago": [ + "(\\d++[.,]?\\d*+) saacad kahor", + "(\\d++[.,]?\\d*+) saacadood kahor", + "(\\d++[.,]?\\d*+) scd khr" + ], + "\\1 minute ago": [ + "(\\d++[.,]?\\d*+) daqiiqad kahor", + "(\\d++[.,]?\\d*+) daqiiqadood kahor", + "(\\d++[.,]?\\d*+) dqqd khr" + ], + "\\1 month ago": [ + "(\\d++[.,]?\\d*+) bil kahor", + "(\\d++[.,]?\\d*+) bil khr", + "(\\d++[.,]?\\d*+) bilood kahor" + ], + "\\1 second ago": [ + "(\\d++[.,]?\\d*+) ilbiriqsi kahor", + "(\\d++[.,]?\\d*+) ilbrqsi khr" + ], + "\\1 week ago": [ + "(\\d++[.,]?\\d*+) tdbd khr", + "(\\d++[.,]?\\d*+) toddobaad kahor" + ], + "\\1 year ago": [ + "(\\d++[.,]?\\d*+) sannad kahor", + "(\\d++[.,]?\\d*+) sannadood kahor", + "(\\d++[.,]?\\d*+) snd khr" + ], + "in \\1 day": [ + "(\\d++[.,]?\\d*+) maalin", + "(\\d++[.,]?\\d*+) maalmood", + "(\\d++[.,]?\\d*+) mlmd", + "(\\d++[.,]?\\d*+) mln" + ], + "in \\1 hour": [ + "(\\d++[.,]?\\d*+) saacad", + "(\\d++[.,]?\\d*+) saacadood", + "(\\d++[.,]?\\d*+) scd" + ], + "in \\1 minute": [ + "(\\d++[.,]?\\d*+) daqiidadood", + "(\\d++[.,]?\\d*+) daqiiqad", + "(\\d++[.,]?\\d*+) dqqd" + ], + "in \\1 month": [ + "(\\d++[.,]?\\d*+) bil", + "(\\d++[.,]?\\d*+) bilood" + ], + "in \\1 second": [ + "(\\d++[.,]?\\d*+) ilbiriqsi", + "(\\d++[.,]?\\d*+) ilbrqsi" + ], + "in \\1 week": [ + "(\\d++[.,]?\\d*+) tdbd", + "(\\d++[.,]?\\d*+) toddobaad" + ], + "in \\1 year": [ + "(\\d++[.,]?\\d*+) sannad", + "(\\d++[.,]?\\d*+) sannadood", + "(\\d++[.,]?\\d*+) snd" + ] + }, "locale_specific": { "so-DJ": { "name": "so-DJ" diff --git a/dateparser/data/date_translation_data/sq.py b/dateparser/data/date_translation_data/sq.py index a43364af2..dcb9ec9f9 100644 --- a/dateparser/data/date_translation_data/sq.py +++ b/dateparser/data/date_translation_data/sq.py @@ -25,12 +25,14 @@ "qershor" ], "july": [ - "kor", - "korrik" + "korr", + "korrik", + "kor" ], "august": [ - "gsh", - "gusht" + "gush", + "gusht", + "gsh" ], "september": [ "sht", @@ -78,10 +80,12 @@ ], "am": [ "e paradites", - "paradite" + "paradite", + "pd" ], "pm": [ "e pasdites", + "md", "pasdite" ], "year": [ @@ -127,7 +131,8 @@ "këtë javë" ], "0 year ago": [ - "këtë vit" + "këtë vit", + "sivjet" ], "1 day ago": [ "dje" @@ -139,7 +144,8 @@ "javën e kaluar" ], "1 year ago": [ - "vitin e kaluar" + "vitin e kaluar", + "vjet" ], "in 1 day": [ "nesër" @@ -151,65 +157,66 @@ "javën e ardhshme" ], "in 1 year": [ + "mot", "vitin e ardhshëm" ] }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) ditë më parë" + "(\\d++[.,]?\\d*+) ditë më parë" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) orë më parë" + "(\\d++[.,]?\\d*+) orë më parë" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) min më parë", - "(\\d+[.,]?\\d*) minuta më parë", - "(\\d+[.,]?\\d*) minutë më parë" + "(\\d++[.,]?\\d*+) min më parë", + "(\\d++[.,]?\\d*+) minuta më parë", + "(\\d++[.,]?\\d*+) minutë më parë" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) muaj më parë" + "(\\d++[.,]?\\d*+) muaj më parë" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) sek më parë", - "(\\d+[.,]?\\d*) sekonda më parë", - "(\\d+[.,]?\\d*) sekondë më parë" + "(\\d++[.,]?\\d*+) sek më parë", + "(\\d++[.,]?\\d*+) sekonda më parë", + "(\\d++[.,]?\\d*+) sekondë më parë" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) javë më parë" + "(\\d++[.,]?\\d*+) javë më parë" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) vit më parë", - "(\\d+[.,]?\\d*) vjet më parë" + "(\\d++[.,]?\\d*+) vit më parë", + "(\\d++[.,]?\\d*+) vjet më parë" ], "in \\1 day": [ - "pas (\\d+[.,]?\\d*) dite", - "pas (\\d+[.,]?\\d*) ditësh" + "pas (\\d++[.,]?\\d*+) dite", + "pas (\\d++[.,]?\\d*+) ditësh" ], "in \\1 hour": [ - "pas (\\d+[.,]?\\d*) ore", - "pas (\\d+[.,]?\\d*) orësh" + "pas (\\d++[.,]?\\d*+) ore", + "pas (\\d++[.,]?\\d*+) orësh" ], "in \\1 minute": [ - "pas (\\d+[.,]?\\d*) min", - "pas (\\d+[.,]?\\d*) minutash", - "pas (\\d+[.,]?\\d*) minute" + "pas (\\d++[.,]?\\d*+) min", + "pas (\\d++[.,]?\\d*+) minutash", + "pas (\\d++[.,]?\\d*+) minute" ], "in \\1 month": [ - "pas (\\d+[.,]?\\d*) muaji", - "pas (\\d+[.,]?\\d*) muajsh" + "pas (\\d++[.,]?\\d*+) muaji", + "pas (\\d++[.,]?\\d*+) muajsh" ], "in \\1 second": [ - "pas (\\d+[.,]?\\d*) sek", - "pas (\\d+[.,]?\\d*) sekondash", - "pas (\\d+[.,]?\\d*) sekonde" + "pas (\\d++[.,]?\\d*+) sek", + "pas (\\d++[.,]?\\d*+) sekondash", + "pas (\\d++[.,]?\\d*+) sekonde" ], "in \\1 week": [ - "pas (\\d+[.,]?\\d*) jave", - "pas (\\d+[.,]?\\d*) javësh" + "pas (\\d++[.,]?\\d*+) jave", + "pas (\\d++[.,]?\\d*+) javësh" ], "in \\1 year": [ - "pas (\\d+[.,]?\\d*) viti", - "pas (\\d+[.,]?\\d*) vjetësh" + "pas (\\d++[.,]?\\d*+) viti", + "pas (\\d++[.,]?\\d*+) vjetësh" ] }, "locale_specific": { diff --git a/dateparser/data/date_translation_data/sr-Cyrl.py b/dateparser/data/date_translation_data/sr-Cyrl.py index 4e15696b9..24a7a5244 100644 --- a/dateparser/data/date_translation_data/sr-Cyrl.py +++ b/dateparser/data/date_translation_data/sr-Cyrl.py @@ -75,9 +75,11 @@ "недеља" ], "am": [ + "am", "пре подне" ], "pm": [ + "pm", "по подне" ], "year": [ @@ -86,14 +88,14 @@ "година" ], "month": [ - "м", "мес", - "месец" + "месец", + "м" ], "week": [ - "н", "нед", - "недеља" + "недеља", + "н" ], "day": [ "д", @@ -101,6 +103,7 @@ ], "hour": [ "сат", + "сати", "ч" ], "minute": [ @@ -123,138 +126,253 @@ "овог минута" ], "0 month ago": [ + "овог мес", "овог месеца" ], "0 second ago": [ "сада" ], "0 week ago": [ + "ове н", + "ове нед", "ове недеље" ], "0 year ago": [ + "ове г", + "ове год", "ове године" ], "1 day ago": [ "јуче" ], "1 month ago": [ + "прошлог мес", "прошлог месеца" ], "1 week ago": [ + "прошле н", + "прошле нед", "прошле недеље" ], "1 year ago": [ + "прошле г", + "прошле год", "прошле године" ], "in 1 day": [ "сутра" ], "in 1 month": [ + "следећег мес", "следећег месеца" ], "in 1 week": [ + "следеће н", + "следеће нед", "следеће недеље" ], "in 1 year": [ + "следеће г", + "следеће год", "следеће године" ] }, "relative-type-regex": { "\\1 day ago": [ - "пре (\\d+[.,]?\\d*) д", - "пре (\\d+[.,]?\\d*) дана" + "пре (\\d++[.,]?\\d*+) д", + "пре (\\d++[.,]?\\d*+) дана" ], "\\1 hour ago": [ - "пре (\\d+[.,]?\\d*) сата", - "пре (\\d+[.,]?\\d*) сати", - "пре (\\d+[.,]?\\d*) ч" + "пре (\\d++[.,]?\\d*+) сата", + "пре (\\d++[.,]?\\d*+) сати", + "пре (\\d++[.,]?\\d*+) ч" ], "\\1 minute ago": [ - "пре (\\d+[.,]?\\d*) мин", - "пре (\\d+[.,]?\\d*) минута" + "пре (\\d++[.,]?\\d*+) мин", + "пре (\\d++[.,]?\\d*+) минута" ], "\\1 month ago": [ - "пре (\\d+[.,]?\\d*) м", - "пре (\\d+[.,]?\\d*) мес", - "пре (\\d+[.,]?\\d*) месеца", - "пре (\\d+[.,]?\\d*) месеци" + "пре (\\d++[.,]?\\d*+) м", + "пре (\\d++[.,]?\\d*+) мес", + "пре (\\d++[.,]?\\d*+) месеца", + "пре (\\d++[.,]?\\d*+) месеци" ], "\\1 second ago": [ - "пре (\\d+[.,]?\\d*) с", - "пре (\\d+[.,]?\\d*) сек", - "пре (\\d+[.,]?\\d*) секунде", - "пре (\\d+[.,]?\\d*) секунди" + "пре (\\d++[.,]?\\d*+) с", + "пре (\\d++[.,]?\\d*+) сек", + "пре (\\d++[.,]?\\d*+) секунде", + "пре (\\d++[.,]?\\d*+) секунди" ], "\\1 week ago": [ - "пре (\\d+[.,]?\\d*) н", - "пре (\\d+[.,]?\\d*) нед", - "пре (\\d+[.,]?\\d*) недеља", - "пре (\\d+[.,]?\\d*) недеље" + "пре (\\d++[.,]?\\d*+) н", + "пре (\\d++[.,]?\\d*+) нед", + "пре (\\d++[.,]?\\d*+) недеља", + "пре (\\d++[.,]?\\d*+) недеље" ], "\\1 year ago": [ - "пре (\\d+[.,]?\\d*) г", - "пре (\\d+[.,]?\\d*) год", - "пре (\\d+[.,]?\\d*) година", - "пре (\\d+[.,]?\\d*) године" + "пре (\\d++[.,]?\\d*+) г", + "пре (\\d++[.,]?\\d*+) год", + "пре (\\d++[.,]?\\d*+) година", + "пре (\\d++[.,]?\\d*+) године" ], "in \\1 day": [ - "за (\\d+[.,]?\\d*) д", - "за (\\d+[.,]?\\d*) дан", - "за (\\d+[.,]?\\d*) дана" + "за (\\d++[.,]?\\d*+) д", + "за (\\d++[.,]?\\d*+) дан", + "за (\\d++[.,]?\\d*+) дана" ], "in \\1 hour": [ - "за (\\d+[.,]?\\d*) сат", - "за (\\d+[.,]?\\d*) сати", - "за (\\d+[.,]?\\d*) ч" + "за (\\d++[.,]?\\d*+) сат", + "за (\\d++[.,]?\\d*+) сати", + "за (\\d++[.,]?\\d*+) ч" ], "in \\1 minute": [ - "за (\\d+[.,]?\\d*) мин", - "за (\\d+[.,]?\\d*) минут", - "за (\\d+[.,]?\\d*) минута" + "за (\\d++[.,]?\\d*+) мин", + "за (\\d++[.,]?\\d*+) минут", + "за (\\d++[.,]?\\d*+) минута" ], "in \\1 month": [ - "за (\\d+[.,]?\\d*) м", - "за (\\d+[.,]?\\d*) мес", - "за (\\d+[.,]?\\d*) месец", - "за (\\d+[.,]?\\d*) месеци" + "за (\\d++[.,]?\\d*+) м", + "за (\\d++[.,]?\\d*+) мес", + "за (\\d++[.,]?\\d*+) месец", + "за (\\d++[.,]?\\d*+) месеци" ], "in \\1 second": [ - "за (\\d+[.,]?\\d*) с", - "за (\\d+[.,]?\\d*) сек", - "за (\\d+[.,]?\\d*) секунди", - "за (\\d+[.,]?\\d*) секунду" + "за (\\d++[.,]?\\d*+) с", + "за (\\d++[.,]?\\d*+) сек", + "за (\\d++[.,]?\\d*+) секунди", + "за (\\d++[.,]?\\d*+) секунду" ], "in \\1 week": [ - "за (\\d+[.,]?\\d*) н", - "за (\\d+[.,]?\\d*) нед", - "за (\\d+[.,]?\\d*) недеља", - "за (\\d+[.,]?\\d*) недељу" + "за (\\d++[.,]?\\d*+) н", + "за (\\d++[.,]?\\d*+) нед", + "за (\\d++[.,]?\\d*+) недеља", + "за (\\d++[.,]?\\d*+) недељу" ], "in \\1 year": [ - "за (\\d+[.,]?\\d*) г", - "за (\\d+[.,]?\\d*) год", - "за (\\d+[.,]?\\d*) година", - "за (\\d+[.,]?\\d*) годину" + "за (\\d++[.,]?\\d*+) г", + "за (\\d++[.,]?\\d*+) год", + "за (\\d++[.,]?\\d*+) година", + "за (\\d++[.,]?\\d*+) годину" ] }, "locale_specific": { "sr-Cyrl-BA": { "name": "sr-Cyrl-BA", - "september": [ - "септ" - ], - "tuesday": [ - "ут" + "monday": [ + "понедјељак" ], "wednesday": [ - "ср", - "сриједа" + "сри", + "сриједа", + "ср" ], "sunday": [ "недјеља" ], "am": [ "прије подне" + ], + "pm": [ + "по подне" + ], + "month": [ + "мјес", + "мјесец" + ], + "week": [ + "седм", + "седмица" + ], + "relative-type": { + "0 month ago": [ + "овог мјес", + "овог мјесеца" + ], + "0 week ago": [ + "ове с", + "ове седм", + "ове седмице" + ], + "1 month ago": [ + "прошлог мјес", + "прошлог мјесеца" + ], + "1 week ago": [ + "прошле с", + "прошле седм", + "прошле седмице" + ], + "in 1 month": [ + "сљедећег м", + "сљедећег мјес", + "сљедећег мјесеца" + ], + "in 1 week": [ + "сљедеће с", + "сљедеће седм", + "сљедеће седмице" + ], + "in 1 year": [ + "сљедеће г", + "сљедеће год", + "сљедеће године" + ] + }, + "relative-type-regex": { + "\\1 day ago": [ + "прије (\\d++[.,]?\\d*+) д", + "прије (\\d++[.,]?\\d*+) дана" + ], + "\\1 hour ago": [ + "прије (\\d++[.,]?\\d*+) сата", + "прије (\\d++[.,]?\\d*+) сати", + "прије (\\d++[.,]?\\d*+) ч" + ], + "\\1 minute ago": [ + "прије (\\d++[.,]?\\d*+) мин", + "прије (\\d++[.,]?\\d*+) минута" + ], + "\\1 month ago": [ + "прије (\\d++[.,]?\\d*+) м", + "прије (\\d++[.,]?\\d*+) мјес", + "прије (\\d++[.,]?\\d*+) мјесеца", + "прије (\\d++[.,]?\\d*+) мјесеци" + ], + "\\1 second ago": [ + "прије (\\d++[.,]?\\d*+) с", + "прије (\\d++[.,]?\\d*+) сек", + "прије (\\d++[.,]?\\d*+) секунде", + "прије (\\d++[.,]?\\d*+) секунди" + ], + "\\1 week ago": [ + "прије (\\d++[.,]?\\d*+) с", + "прије (\\d++[.,]?\\d*+) седм", + "прије (\\d++[.,]?\\d*+) седмица", + "прије (\\d++[.,]?\\d*+) седмице" + ], + "\\1 year ago": [ + "прије (\\d++[.,]?\\d*+) г", + "прије (\\d++[.,]?\\d*+) год", + "прије (\\d++[.,]?\\d*+) година", + "прије (\\d++[.,]?\\d*+) године" + ], + "in \\1 month": [ + "за (\\d++[.,]?\\d*+) мјес", + "за (\\d++[.,]?\\d*+) мјесец", + "за (\\d++[.,]?\\d*+) мјесеци" + ], + "in \\1 week": [ + "за (\\d++[.,]?\\d*+) с", + "за (\\d++[.,]?\\d*+) седм", + "за (\\d++[.,]?\\d*+) седмица", + "за (\\d++[.,]?\\d*+) седмицу" + ] + }, + "tuesday": [ + "ут" + ], + "september": [ + "септ" ] }, "sr-Cyrl-ME": { @@ -262,18 +380,21 @@ "september": [ "септ" ], - "tuesday": [ - "ут" - ], "wednesday": [ - "ср", - "сриједа" + "сриједа", + "ср" ], "sunday": [ "недјеља" ], "am": [ "прије подне" + ], + "pm": [ + "по подне" + ], + "tuesday": [ + "ут" ] }, "sr-Cyrl-XK": { diff --git a/dateparser/data/date_translation_data/sr-Latn.py b/dateparser/data/date_translation_data/sr-Latn.py index a0daf4639..3bef6b588 100644 --- a/dateparser/data/date_translation_data/sr-Latn.py +++ b/dateparser/data/date_translation_data/sr-Latn.py @@ -75,9 +75,11 @@ "nedelja" ], "am": [ + "am", "pre podne" ], "pm": [ + "pm", "po podne" ], "year": [ @@ -86,14 +88,14 @@ "godina" ], "month": [ - "m", "mes", - "mesec" + "mesec", + "m" ], "week": [ - "n", "ned", - "nedelja" + "nedelja", + "n" ], "day": [ "d", @@ -101,6 +103,7 @@ ], "hour": [ "sat", + "sati", "č" ], "minute": [ @@ -123,138 +126,253 @@ "ovog minuta" ], "0 month ago": [ + "ovog mes", "ovog meseca" ], "0 second ago": [ "sada" ], "0 week ago": [ + "ove n", + "ove ned", "ove nedelje" ], "0 year ago": [ + "ove g", + "ove god", "ove godine" ], "1 day ago": [ "juče" ], "1 month ago": [ + "prošlog mes", "prošlog meseca" ], "1 week ago": [ + "prošle n", + "prošle ned", "prošle nedelje" ], "1 year ago": [ + "prošle g", + "prošle god", "prošle godine" ], "in 1 day": [ "sutra" ], "in 1 month": [ + "sledećeg mes", "sledećeg meseca" ], "in 1 week": [ + "sledeće n", + "sledeće ned", "sledeće nedelje" ], "in 1 year": [ + "sledeće g", + "sledeće god", "sledeće godine" ] }, "relative-type-regex": { "\\1 day ago": [ - "pre (\\d+[.,]?\\d*) d", - "pre (\\d+[.,]?\\d*) dana" + "pre (\\d++[.,]?\\d*+) d", + "pre (\\d++[.,]?\\d*+) dana" ], "\\1 hour ago": [ - "pre (\\d+[.,]?\\d*) sata", - "pre (\\d+[.,]?\\d*) sati", - "pre (\\d+[.,]?\\d*) č" + "pre (\\d++[.,]?\\d*+) sata", + "pre (\\d++[.,]?\\d*+) sati", + "pre (\\d++[.,]?\\d*+) č" ], "\\1 minute ago": [ - "pre (\\d+[.,]?\\d*) min", - "pre (\\d+[.,]?\\d*) minuta" + "pre (\\d++[.,]?\\d*+) min", + "pre (\\d++[.,]?\\d*+) minuta" ], "\\1 month ago": [ - "pre (\\d+[.,]?\\d*) m", - "pre (\\d+[.,]?\\d*) mes", - "pre (\\d+[.,]?\\d*) meseca", - "pre (\\d+[.,]?\\d*) meseci" + "pre (\\d++[.,]?\\d*+) m", + "pre (\\d++[.,]?\\d*+) mes", + "pre (\\d++[.,]?\\d*+) meseca", + "pre (\\d++[.,]?\\d*+) meseci" ], "\\1 second ago": [ - "pre (\\d+[.,]?\\d*) s", - "pre (\\d+[.,]?\\d*) sek", - "pre (\\d+[.,]?\\d*) sekunde", - "pre (\\d+[.,]?\\d*) sekundi" + "pre (\\d++[.,]?\\d*+) s", + "pre (\\d++[.,]?\\d*+) sek", + "pre (\\d++[.,]?\\d*+) sekunde", + "pre (\\d++[.,]?\\d*+) sekundi" ], "\\1 week ago": [ - "pre (\\d+[.,]?\\d*) n", - "pre (\\d+[.,]?\\d*) ned", - "pre (\\d+[.,]?\\d*) nedelja", - "pre (\\d+[.,]?\\d*) nedelje" + "pre (\\d++[.,]?\\d*+) n", + "pre (\\d++[.,]?\\d*+) ned", + "pre (\\d++[.,]?\\d*+) nedelja", + "pre (\\d++[.,]?\\d*+) nedelje" ], "\\1 year ago": [ - "pre (\\d+[.,]?\\d*) g", - "pre (\\d+[.,]?\\d*) god", - "pre (\\d+[.,]?\\d*) godina", - "pre (\\d+[.,]?\\d*) godine" + "pre (\\d++[.,]?\\d*+) g", + "pre (\\d++[.,]?\\d*+) god", + "pre (\\d++[.,]?\\d*+) godina", + "pre (\\d++[.,]?\\d*+) godine" ], "in \\1 day": [ - "za (\\d+[.,]?\\d*) d", - "za (\\d+[.,]?\\d*) dan", - "za (\\d+[.,]?\\d*) dana" + "za (\\d++[.,]?\\d*+) d", + "za (\\d++[.,]?\\d*+) dan", + "za (\\d++[.,]?\\d*+) dana" ], "in \\1 hour": [ - "za (\\d+[.,]?\\d*) sat", - "za (\\d+[.,]?\\d*) sati", - "za (\\d+[.,]?\\d*) č" + "za (\\d++[.,]?\\d*+) sat", + "za (\\d++[.,]?\\d*+) sati", + "za (\\d++[.,]?\\d*+) č" ], "in \\1 minute": [ - "za (\\d+[.,]?\\d*) min", - "za (\\d+[.,]?\\d*) minut", - "za (\\d+[.,]?\\d*) minuta" + "za (\\d++[.,]?\\d*+) min", + "za (\\d++[.,]?\\d*+) minut", + "za (\\d++[.,]?\\d*+) minuta" ], "in \\1 month": [ - "za (\\d+[.,]?\\d*) m", - "za (\\d+[.,]?\\d*) mes", - "za (\\d+[.,]?\\d*) mesec", - "za (\\d+[.,]?\\d*) meseci" + "za (\\d++[.,]?\\d*+) m", + "za (\\d++[.,]?\\d*+) mes", + "za (\\d++[.,]?\\d*+) mesec", + "za (\\d++[.,]?\\d*+) meseci" ], "in \\1 second": [ - "za (\\d+[.,]?\\d*) s", - "za (\\d+[.,]?\\d*) sek", - "za (\\d+[.,]?\\d*) sekundi", - "za (\\d+[.,]?\\d*) sekundu" + "za (\\d++[.,]?\\d*+) s", + "za (\\d++[.,]?\\d*+) sek", + "za (\\d++[.,]?\\d*+) sekundi", + "za (\\d++[.,]?\\d*+) sekundu" ], "in \\1 week": [ - "za (\\d+[.,]?\\d*) n", - "za (\\d+[.,]?\\d*) ned", - "za (\\d+[.,]?\\d*) nedelja", - "za (\\d+[.,]?\\d*) nedelju" + "za (\\d++[.,]?\\d*+) n", + "za (\\d++[.,]?\\d*+) ned", + "za (\\d++[.,]?\\d*+) nedelja", + "za (\\d++[.,]?\\d*+) nedelju" ], "in \\1 year": [ - "za (\\d+[.,]?\\d*) g", - "za (\\d+[.,]?\\d*) god", - "za (\\d+[.,]?\\d*) godina", - "za (\\d+[.,]?\\d*) godinu" + "za (\\d++[.,]?\\d*+) g", + "za (\\d++[.,]?\\d*+) god", + "za (\\d++[.,]?\\d*+) godina", + "za (\\d++[.,]?\\d*+) godinu" ] }, "locale_specific": { "sr-Latn-BA": { "name": "sr-Latn-BA", - "september": [ - "sept" - ], - "tuesday": [ - "ut" + "monday": [ + "ponedjeljak" ], "wednesday": [ - "sr", - "srijeda" + "sri", + "srijeda", + "sr" ], "sunday": [ "nedjelja" ], "am": [ "prije podne" + ], + "pm": [ + "po podne" + ], + "month": [ + "mjes", + "mjesec" + ], + "week": [ + "sedm", + "sedmica" + ], + "relative-type": { + "0 month ago": [ + "ovog mjes", + "ovog mjeseca" + ], + "0 week ago": [ + "ove s", + "ove sedm", + "ove sedmice" + ], + "1 month ago": [ + "prošlog mjes", + "prošlog mjeseca" + ], + "1 week ago": [ + "prošle s", + "prošle sedm", + "prošle sedmice" + ], + "in 1 month": [ + "sljedećeg m", + "sljedećeg mjes", + "sljedećeg mjeseca" + ], + "in 1 week": [ + "sljedeće s", + "sljedeće sedm", + "sljedeće sedmice" + ], + "in 1 year": [ + "sljedeće g", + "sljedeće god", + "sljedeće godine" + ] + }, + "relative-type-regex": { + "\\1 day ago": [ + "prije (\\d++[.,]?\\d*+) d", + "prije (\\d++[.,]?\\d*+) dana" + ], + "\\1 hour ago": [ + "prije (\\d++[.,]?\\d*+) sata", + "prije (\\d++[.,]?\\d*+) sati", + "prije (\\d++[.,]?\\d*+) č" + ], + "\\1 minute ago": [ + "prije (\\d++[.,]?\\d*+) min", + "prije (\\d++[.,]?\\d*+) minuta" + ], + "\\1 month ago": [ + "prije (\\d++[.,]?\\d*+) m", + "prije (\\d++[.,]?\\d*+) mjes", + "prije (\\d++[.,]?\\d*+) mjeseca", + "prije (\\d++[.,]?\\d*+) mjeseci" + ], + "\\1 second ago": [ + "prije (\\d++[.,]?\\d*+) s", + "prije (\\d++[.,]?\\d*+) sek", + "prije (\\d++[.,]?\\d*+) sekunde", + "prije (\\d++[.,]?\\d*+) sekundi" + ], + "\\1 week ago": [ + "prije (\\d++[.,]?\\d*+) s", + "prije (\\d++[.,]?\\d*+) sedm", + "prije (\\d++[.,]?\\d*+) sedmica", + "prije (\\d++[.,]?\\d*+) sedmice" + ], + "\\1 year ago": [ + "prije (\\d++[.,]?\\d*+) g", + "prije (\\d++[.,]?\\d*+) god", + "prije (\\d++[.,]?\\d*+) godina", + "prije (\\d++[.,]?\\d*+) godine" + ], + "in \\1 month": [ + "za (\\d++[.,]?\\d*+) mjes", + "za (\\d++[.,]?\\d*+) mjesec", + "za (\\d++[.,]?\\d*+) mjeseci" + ], + "in \\1 week": [ + "za (\\d++[.,]?\\d*+) s", + "za (\\d++[.,]?\\d*+) sedm", + "za (\\d++[.,]?\\d*+) sedmica", + "za (\\d++[.,]?\\d*+) sedmicu" + ] + }, + "tuesday": [ + "ut" + ], + "september": [ + "sept" ] }, "sr-Latn-ME": { @@ -262,18 +380,21 @@ "september": [ "sept" ], - "tuesday": [ - "ut" - ], "wednesday": [ - "sr", - "srijeda" + "srijeda", + "sr" ], "sunday": [ "nedjelja" ], "am": [ "prije podne" + ], + "pm": [ + "po podne" + ], + "tuesday": [ + "ut" ] }, "sr-Latn-XK": { diff --git a/dateparser/data/date_translation_data/sr.py b/dateparser/data/date_translation_data/sr.py index 42a967bc9..f17b88a57 100644 --- a/dateparser/data/date_translation_data/sr.py +++ b/dateparser/data/date_translation_data/sr.py @@ -75,9 +75,11 @@ "недеља" ], "am": [ + "am", "пре подне" ], "pm": [ + "pm", "по подне" ], "year": [ @@ -86,14 +88,14 @@ "година" ], "month": [ - "м", "мес", - "месец" + "месец", + "м" ], "week": [ - "н", "нед", - "недеља" + "недеља", + "н" ], "day": [ "д", @@ -101,6 +103,7 @@ ], "hour": [ "сат", + "сати", "ч" ], "minute": [ @@ -123,118 +126,133 @@ "овог минута" ], "0 month ago": [ + "овог мес", "овог месеца" ], "0 second ago": [ "сада" ], "0 week ago": [ + "ове н", + "ове нед", "ове недеље" ], "0 year ago": [ + "ове г", + "ове год", "ове године" ], "1 day ago": [ "јуче" ], "1 month ago": [ + "прошлог мес", "прошлог месеца" ], "1 week ago": [ + "прошле н", + "прошле нед", "прошле недеље" ], "1 year ago": [ + "прошле г", + "прошле год", "прошле године" ], "in 1 day": [ "сутра" ], "in 1 month": [ + "следећег мес", "следећег месеца" ], "in 1 week": [ + "следеће н", + "следеће нед", "следеће недеље" ], "in 1 year": [ + "следеће г", + "следеће год", "следеће године" ] }, "relative-type-regex": { "\\1 day ago": [ - "пре (\\d+[.,]?\\d*) д", - "пре (\\d+[.,]?\\d*) дана" + "пре (\\d++[.,]?\\d*+) д", + "пре (\\d++[.,]?\\d*+) дана" ], "\\1 hour ago": [ - "пре (\\d+[.,]?\\d*) сата", - "пре (\\d+[.,]?\\d*) сати", - "пре (\\d+[.,]?\\d*) ч" + "пре (\\d++[.,]?\\d*+) сата", + "пре (\\d++[.,]?\\d*+) сати", + "пре (\\d++[.,]?\\d*+) ч" ], "\\1 minute ago": [ - "пре (\\d+[.,]?\\d*) мин", - "пре (\\d+[.,]?\\d*) минута" + "пре (\\d++[.,]?\\d*+) мин", + "пре (\\d++[.,]?\\d*+) минута" ], "\\1 month ago": [ - "пре (\\d+[.,]?\\d*) м", - "пре (\\d+[.,]?\\d*) мес", - "пре (\\d+[.,]?\\d*) месеца", - "пре (\\d+[.,]?\\d*) месеци" + "пре (\\d++[.,]?\\d*+) м", + "пре (\\d++[.,]?\\d*+) мес", + "пре (\\d++[.,]?\\d*+) месеца", + "пре (\\d++[.,]?\\d*+) месеци" ], "\\1 second ago": [ - "пре (\\d+[.,]?\\d*) с", - "пре (\\d+[.,]?\\d*) сек", - "пре (\\d+[.,]?\\d*) секунде", - "пре (\\d+[.,]?\\d*) секунди" + "пре (\\d++[.,]?\\d*+) с", + "пре (\\d++[.,]?\\d*+) сек", + "пре (\\d++[.,]?\\d*+) секунде", + "пре (\\d++[.,]?\\d*+) секунди" ], "\\1 week ago": [ - "пре (\\d+[.,]?\\d*) н", - "пре (\\d+[.,]?\\d*) нед", - "пре (\\d+[.,]?\\d*) недеља", - "пре (\\d+[.,]?\\d*) недеље" + "пре (\\d++[.,]?\\d*+) н", + "пре (\\d++[.,]?\\d*+) нед", + "пре (\\d++[.,]?\\d*+) недеља", + "пре (\\d++[.,]?\\d*+) недеље" ], "\\1 year ago": [ - "пре (\\d+[.,]?\\d*) г", - "пре (\\d+[.,]?\\d*) год", - "пре (\\d+[.,]?\\d*) година", - "пре (\\d+[.,]?\\d*) године" + "пре (\\d++[.,]?\\d*+) г", + "пре (\\d++[.,]?\\d*+) год", + "пре (\\d++[.,]?\\d*+) година", + "пре (\\d++[.,]?\\d*+) године" ], "in \\1 day": [ - "за (\\d+[.,]?\\d*) д", - "за (\\d+[.,]?\\d*) дан", - "за (\\d+[.,]?\\d*) дана" + "за (\\d++[.,]?\\d*+) д", + "за (\\d++[.,]?\\d*+) дан", + "за (\\d++[.,]?\\d*+) дана" ], "in \\1 hour": [ - "за (\\d+[.,]?\\d*) сат", - "за (\\d+[.,]?\\d*) сати", - "за (\\d+[.,]?\\d*) ч" + "за (\\d++[.,]?\\d*+) сат", + "за (\\d++[.,]?\\d*+) сати", + "за (\\d++[.,]?\\d*+) ч" ], "in \\1 minute": [ - "за (\\d+[.,]?\\d*) мин", - "за (\\d+[.,]?\\d*) минут", - "за (\\d+[.,]?\\d*) минута" + "за (\\d++[.,]?\\d*+) мин", + "за (\\d++[.,]?\\d*+) минут", + "за (\\d++[.,]?\\d*+) минута" ], "in \\1 month": [ - "за (\\d+[.,]?\\d*) м", - "за (\\d+[.,]?\\d*) мес", - "за (\\d+[.,]?\\d*) месец", - "за (\\d+[.,]?\\d*) месеци" + "за (\\d++[.,]?\\d*+) м", + "за (\\d++[.,]?\\d*+) мес", + "за (\\d++[.,]?\\d*+) месец", + "за (\\d++[.,]?\\d*+) месеци" ], "in \\1 second": [ - "за (\\d+[.,]?\\d*) с", - "за (\\d+[.,]?\\d*) сек", - "за (\\d+[.,]?\\d*) секунди", - "за (\\d+[.,]?\\d*) секунду" + "за (\\d++[.,]?\\d*+) с", + "за (\\d++[.,]?\\d*+) сек", + "за (\\d++[.,]?\\d*+) секунди", + "за (\\d++[.,]?\\d*+) секунду" ], "in \\1 week": [ - "за (\\d+[.,]?\\d*) н", - "за (\\d+[.,]?\\d*) нед", - "за (\\d+[.,]?\\d*) недеља", - "за (\\d+[.,]?\\d*) недељу" + "за (\\d++[.,]?\\d*+) н", + "за (\\d++[.,]?\\d*+) нед", + "за (\\d++[.,]?\\d*+) недеља", + "за (\\d++[.,]?\\d*+) недељу" ], "in \\1 year": [ - "за (\\d+[.,]?\\d*) г", - "за (\\d+[.,]?\\d*) год", - "за (\\d+[.,]?\\d*) година", - "за (\\d+[.,]?\\d*) годину" + "за (\\d++[.,]?\\d*+) г", + "за (\\d++[.,]?\\d*+) год", + "за (\\d++[.,]?\\d*+) година", + "за (\\d++[.,]?\\d*+) годину" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/sv.py b/dateparser/data/date_translation_data/sv.py index 5f10e71e9..d0226249e 100644 --- a/dateparser/data/date_translation_data/sv.py +++ b/dateparser/data/date_translation_data/sv.py @@ -114,6 +114,7 @@ "hour": [ "h", "tim", + "timmar", "timme", "timmar", "t" @@ -133,6 +134,7 @@ "relative-type": { "0 day ago": [ "i dag", + "idag", "idag" ], "0 hour ago": [ @@ -142,6 +144,7 @@ "denna minut" ], "0 month ago": [ + "den här månaden", "denna mån", "denna månad" ], @@ -157,6 +160,7 @@ ], "1 day ago": [ "i går", + "igår", "igår" ], "1 month ago": [ @@ -173,6 +177,7 @@ ], "in 1 day": [ "i morgon", + "imorgon", "imorgon" ], "in 1 month": [ @@ -192,77 +197,81 @@ }, "relative-type-regex": { "\\1 day ago": [ - "för (\\d+[.,]?\\d*) d sedan", - "för (\\d+[.,]?\\d*) dag sedan", - "för (\\d+[.,]?\\d*) dagar sedan", - "−(\\d+[.,]?\\d*) d" + "för (\\d++[.,]?\\d*+) d sedan", + "för (\\d++[.,]?\\d*+) dag sedan", + "för (\\d++[.,]?\\d*+) dagar sedan", + "−(\\d++[.,]?\\d*+) d" ], "\\1 hour ago": [ - "för (\\d+[.,]?\\d*) tim sedan", - "för (\\d+[.,]?\\d*) timmar sedan", - "för (\\d+[.,]?\\d*) timme sedan", - "−(\\d+[.,]?\\d*) h" + "för (\\d++[.,]?\\d*+) tim sedan", + "för (\\d++[.,]?\\d*+) timmar sedan", + "för (\\d++[.,]?\\d*+) timme sedan", + "−(\\d++[.,]?\\d*+) h" ], "\\1 minute ago": [ - "för (\\d+[.,]?\\d*) min sedan", - "för (\\d+[.,]?\\d*) minut sedan", - "för (\\d+[.,]?\\d*) minuter sedan", - "−(\\d+[.,]?\\d*) min" + "för (\\d++[.,]?\\d*+) min sen", + "för (\\d++[.,]?\\d*+) minut sedan", + "för (\\d++[.,]?\\d*+) minuter sedan", + "−(\\d++[.,]?\\d*+) min", + "för (\\d++[.,]?\\d*+) min sedan" ], "\\1 month ago": [ - "för (\\d+[.,]?\\d*) mån sedan", - "för (\\d+[.,]?\\d*) månad sedan", - "för (\\d+[.,]?\\d*) månader sedan", - "−(\\d+[.,]?\\d*) mån" + "för (\\d++[.,]?\\d*+) mån sen", + "för (\\d++[.,]?\\d*+) månad sedan", + "för (\\d++[.,]?\\d*+) månader sedan", + "−(\\d++[.,]?\\d*+) mån", + "för (\\d++[.,]?\\d*+) mån sedan" ], "\\1 second ago": [ - "för (\\d+[.,]?\\d*) sek sedan", - "för (\\d+[.,]?\\d*) sekund sedan", - "för (\\d+[.,]?\\d*) sekunder sedan", - "−(\\d+[.,]?\\d*) s" + "för (\\d++[.,]?\\d*+) s sen", + "för (\\d++[.,]?\\d*+) sekund sedan", + "för (\\d++[.,]?\\d*+) sekunder sedan", + "−(\\d++[.,]?\\d*+) s", + "för (\\d++[.,]?\\d*+) sek sedan" ], "\\1 week ago": [ - "för (\\d+[.,]?\\d*) v sedan", - "för (\\d+[.,]?\\d*) vecka sedan", - "för (\\d+[.,]?\\d*) veckor sedan", - "−(\\d+[.,]?\\d*) v" + "för (\\d++[.,]?\\d*+) v sedan", + "för (\\d++[.,]?\\d*+) vecka sedan", + "för (\\d++[.,]?\\d*+) veckor sedan", + "−(\\d++[.,]?\\d*+) v" ], "\\1 year ago": [ - "för (\\d+[.,]?\\d*) år sedan", - "−(\\d+[.,]?\\d*) år" + "för (\\d++[.,]?\\d*+) år sedan", + "för (\\d++[.,]?\\d*+) år sen", + "−(\\d++[.,]?\\d*+) år" ], "in \\1 day": [ - "om (\\d+[.,]?\\d*) d", - "om (\\d+[.,]?\\d*) dag", - "om (\\d+[.,]?\\d*) dagar" + "om (\\d++[.,]?\\d*+) d", + "om (\\d++[.,]?\\d*+) dag", + "om (\\d++[.,]?\\d*+) dagar" ], "in \\1 hour": [ - "om (\\d+[.,]?\\d*) tim", - "om (\\d+[.,]?\\d*) timmar", - "om (\\d+[.,]?\\d*) timme" + "om (\\d++[.,]?\\d*+) tim", + "om (\\d++[.,]?\\d*+) timmar", + "om (\\d++[.,]?\\d*+) timme" ], "in \\1 minute": [ - "om (\\d+[.,]?\\d*) min", - "om (\\d+[.,]?\\d*) minut", - "om (\\d+[.,]?\\d*) minuter" + "om (\\d++[.,]?\\d*+) min", + "om (\\d++[.,]?\\d*+) minut", + "om (\\d++[.,]?\\d*+) minuter" ], "in \\1 month": [ - "om (\\d+[.,]?\\d*) mån", - "om (\\d+[.,]?\\d*) månad", - "om (\\d+[.,]?\\d*) månader" + "om (\\d++[.,]?\\d*+) mån", + "om (\\d++[.,]?\\d*+) månad", + "om (\\d++[.,]?\\d*+) månader" ], "in \\1 second": [ - "om (\\d+[.,]?\\d*) sek", - "om (\\d+[.,]?\\d*) sekund", - "om (\\d+[.,]?\\d*) sekunder" + "om (\\d++[.,]?\\d*+) sek", + "om (\\d++[.,]?\\d*+) sekund", + "om (\\d++[.,]?\\d*+) sekunder" ], "in \\1 week": [ - "om (\\d+[.,]?\\d*) v", - "om (\\d+[.,]?\\d*) vecka", - "om (\\d+[.,]?\\d*) veckor" + "om (\\d++[.,]?\\d*+) v", + "om (\\d++[.,]?\\d*+) vecka", + "om (\\d++[.,]?\\d*+) veckor" ], "in \\1 year": [ - "om (\\d+[.,]?\\d*) år" + "om (\\d++[.,]?\\d*+) år" ] }, "locale_specific": { @@ -270,8 +279,7 @@ "name": "sv-AX" }, "sv-FI": { - "name": "sv-FI", - "date_order": "DMY" + "name": "sv-FI" } }, "skip": [ @@ -299,6 +307,9 @@ "från nu" ], "simplifications": [ + { + "(\\d+):[ae]\\b": "\\1" + }, { "en": "1" }, diff --git a/dateparser/data/date_translation_data/sw.py b/dateparser/data/date_translation_data/sw.py index eee516e31..4981f20bf 100644 --- a/dateparser/data/date_translation_data/sw.py +++ b/dateparser/data/date_translation_data/sw.py @@ -74,8 +74,8 @@ "asubuhi" ], "pm": [ - "mchana", - "pm" + "pm", + "mchana" ], "year": [ "mwaka" @@ -149,55 +149,55 @@ }, "relative-type-regex": { "\\1 day ago": [ - "siku (\\d+[.,]?\\d*) iliyopita", - "siku (\\d+[.,]?\\d*) zilizopita" + "siku (\\d++[.,]?\\d*+) iliyopita", + "siku (\\d++[.,]?\\d*+) zilizopita" ], "\\1 hour ago": [ - "saa (\\d+[.,]?\\d*) iliyopita", - "saa (\\d+[.,]?\\d*) zilizopita" + "saa (\\d++[.,]?\\d*+) iliyopita", + "saa (\\d++[.,]?\\d*+) zilizopita" ], "\\1 minute ago": [ - "dakika (\\d+[.,]?\\d*) iliyopita", - "dakika (\\d+[.,]?\\d*) zilizopita" + "dakika (\\d++[.,]?\\d*+) iliyopita", + "dakika (\\d++[.,]?\\d*+) zilizopita" ], "\\1 month ago": [ - "miezi (\\d+[.,]?\\d*) iliyopita", - "mwezi (\\d+[.,]?\\d*) uliopita" + "miezi (\\d++[.,]?\\d*+) iliyopita", + "mwezi (\\d++[.,]?\\d*+) uliopita" ], "\\1 second ago": [ - "sekunde (\\d+[.,]?\\d*) iliyopita", - "sekunde (\\d+[.,]?\\d*) zilizopita" + "sekunde (\\d++[.,]?\\d*+) iliyopita", + "sekunde (\\d++[.,]?\\d*+) zilizopita" ], "\\1 week ago": [ - "wiki (\\d+[.,]?\\d*) iliyopita", - "wiki (\\d+[.,]?\\d*) zilizopita" + "wiki (\\d++[.,]?\\d*+) iliyopita", + "wiki (\\d++[.,]?\\d*+) zilizopita" ], "\\1 year ago": [ - "miaka (\\d+[.,]?\\d*) iliyopita", - "mwaka (\\d+[.,]?\\d*) uliopita" + "miaka (\\d++[.,]?\\d*+) iliyopita", + "mwaka (\\d++[.,]?\\d*+) uliopita" ], "in \\1 day": [ - "baada ya siku (\\d+[.,]?\\d*)" + "baada ya siku (\\d++[.,]?\\d*+)" ], "in \\1 hour": [ - "baada ya saa (\\d+[.,]?\\d*)" + "baada ya saa (\\d++[.,]?\\d*+)" ], "in \\1 minute": [ - "baada ya dakika (\\d+[.,]?\\d*)" + "baada ya dakika (\\d++[.,]?\\d*+)" ], "in \\1 month": [ - "baada ya miezi (\\d+[.,]?\\d*)", - "baada ya mwezi (\\d+[.,]?\\d*)" + "baada ya miezi (\\d++[.,]?\\d*+)", + "baada ya mwezi (\\d++[.,]?\\d*+)" ], "in \\1 second": [ - "baada ya sekunde (\\d+[.,]?\\d*)" + "baada ya sekunde (\\d++[.,]?\\d*+)" ], "in \\1 week": [ - "baada ya wiki (\\d+[.,]?\\d*)" + "baada ya wiki (\\d++[.,]?\\d*+)" ], "in \\1 year": [ - "baada ya miaka (\\d+[.,]?\\d*)", - "baada ya mwaka (\\d+[.,]?\\d*)" + "baada ya miaka (\\d++[.,]?\\d*+)", + "baada ya mwaka (\\d++[.,]?\\d*+)" ] }, "locale_specific": { diff --git a/dateparser/data/date_translation_data/ta.py b/dateparser/data/date_translation_data/ta.py index 43c53f1b6..e01988790 100644 --- a/dateparser/data/date_translation_data/ta.py +++ b/dateparser/data/date_translation_data/ta.py @@ -74,6 +74,7 @@ "ஞாயிறு" ], "am": [ + "am", "முற்பகல்" ], "pm": [ @@ -98,7 +99,8 @@ ], "hour": [ "ம", - "மணி" + "மணி", + "மணிநேரங்கள்" ], "minute": [ "நிமி", @@ -158,82 +160,83 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) நா முன்", - "(\\d+[.,]?\\d*) நாட்களுக்கு முன்", - "(\\d+[.,]?\\d*) நாளுக்கு முன்" + "(\\d++[.,]?\\d*+) நா முன்", + "(\\d++[.,]?\\d*+) நாட்களுக்கு முன்", + "(\\d++[.,]?\\d*+) நாளுக்கு முன்" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) ம முன்", - "(\\d+[.,]?\\d*) மணி முன்", - "(\\d+[.,]?\\d*) மணிநேரம் முன்" + "(\\d++[.,]?\\d*+) ம முன்", + "(\\d++[.,]?\\d*+) மணி முன்", + "(\\d++[.,]?\\d*+) மணிநேரம் முன்" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) நி முன்", - "(\\d+[.,]?\\d*) நிமி முன்", - "(\\d+[.,]?\\d*) நிமிடங்களுக்கு முன்", - "(\\d+[.,]?\\d*) நிமிடத்திற்கு முன்" + "(\\d++[.,]?\\d*+) நி முன்", + "(\\d++[.,]?\\d*+) நிமி முன்", + "(\\d++[.,]?\\d*+) நிமிடங்களுக்கு முன்", + "(\\d++[.,]?\\d*+) நிமிடத்திற்கு முன்" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) மா முன்", - "(\\d+[.,]?\\d*) மாத முன்", - "(\\d+[.,]?\\d*) மாதங்களுக்கு முன்", - "(\\d+[.,]?\\d*) மாதத்துக்கு முன்" + "(\\d++[.,]?\\d*+) மா முன்", + "(\\d++[.,]?\\d*+) மாத முன்", + "(\\d++[.,]?\\d*+) மாதங்களுக்கு முன்", + "(\\d++[.,]?\\d*+) மாதத்துக்கு முன்" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) வி முன்", - "(\\d+[.,]?\\d*) விநா முன்", - "(\\d+[.,]?\\d*) விநாடிகளுக்கு முன்", - "(\\d+[.,]?\\d*) விநாடிக்கு முன்" + "(\\d++[.,]?\\d*+) வி முன்", + "(\\d++[.,]?\\d*+) விநா முன்", + "(\\d++[.,]?\\d*+) விநாடிகளுக்கு முன்", + "(\\d++[.,]?\\d*+) விநாடிக்கு முன்" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) வா முன்", - "(\\d+[.,]?\\d*) வார முன்", - "(\\d+[.,]?\\d*) வாரங்களுக்கு முன்", - "(\\d+[.,]?\\d*) வாரத்திற்கு முன்பு" + "(\\d++[.,]?\\d*+) வா முன்", + "(\\d++[.,]?\\d*+) வார முன்", + "(\\d++[.,]?\\d*+) வாரங்களுக்கு முன்", + "(\\d++[.,]?\\d*+) வாரத்திற்கு முன்", + "(\\d++[.,]?\\d*+) வாரத்திற்கு முன்பு" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) ஆ முன்", - "(\\d+[.,]?\\d*) ஆண்டிற்கு முன்", - "(\\d+[.,]?\\d*) ஆண்டுகளுக்கு முன்" + "(\\d++[.,]?\\d*+) ஆ முன்", + "(\\d++[.,]?\\d*+) ஆண்டிற்கு முன்", + "(\\d++[.,]?\\d*+) ஆண்டுகளுக்கு முன்" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) நா", - "(\\d+[.,]?\\d*) நாட்களில்", - "(\\d+[.,]?\\d*) நாளில்" + "(\\d++[.,]?\\d*+) நா", + "(\\d++[.,]?\\d*+) நாட்களில்", + "(\\d++[.,]?\\d*+) நாளில்" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) ம", - "(\\d+[.,]?\\d*) மணி", - "(\\d+[.,]?\\d*) மணிநேரத்தில்" + "(\\d++[.,]?\\d*+) ம", + "(\\d++[.,]?\\d*+) மணி", + "(\\d++[.,]?\\d*+) மணிநேரத்தில்" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) நி", - "(\\d+[.,]?\\d*) நிமி", - "(\\d+[.,]?\\d*) நிமிடங்களில்", - "(\\d+[.,]?\\d*) நிமிடத்தில்" + "(\\d++[.,]?\\d*+) நி", + "(\\d++[.,]?\\d*+) நிமி", + "(\\d++[.,]?\\d*+) நிமிடங்களில்", + "(\\d++[.,]?\\d*+) நிமிடத்தில்" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) மா", - "(\\d+[.,]?\\d*) மாத", - "(\\d+[.,]?\\d*) மாதங்களில்", - "(\\d+[.,]?\\d*) மாதத்தில்" + "(\\d++[.,]?\\d*+) மா", + "(\\d++[.,]?\\d*+) மாத", + "(\\d++[.,]?\\d*+) மாதங்களில்", + "(\\d++[.,]?\\d*+) மாதத்தில்" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) வி", - "(\\d+[.,]?\\d*) விநா", - "(\\d+[.,]?\\d*) விநாடிகளில்", - "(\\d+[.,]?\\d*) விநாடியில்" + "(\\d++[.,]?\\d*+) வி", + "(\\d++[.,]?\\d*+) விநா", + "(\\d++[.,]?\\d*+) விநாடிகளில்", + "(\\d++[.,]?\\d*+) விநாடியில்" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) வா", - "(\\d+[.,]?\\d*) வார", - "(\\d+[.,]?\\d*) வாரங்களில்", - "(\\d+[.,]?\\d*) வாரத்தில்" + "(\\d++[.,]?\\d*+) வா", + "(\\d++[.,]?\\d*+) வார", + "(\\d++[.,]?\\d*+) வாரங்களில்", + "(\\d++[.,]?\\d*+) வாரத்தில்" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) ஆ", - "(\\d+[.,]?\\d*) ஆண்டில்", - "(\\d+[.,]?\\d*) ஆண்டுகளில்" + "(\\d++[.,]?\\d*+) ஆ", + "(\\d++[.,]?\\d*+) ஆண்டில்", + "(\\d++[.,]?\\d*+) ஆண்டுகளில்" ] }, "locale_specific": { diff --git a/dateparser/data/date_translation_data/te.py b/dateparser/data/date_translation_data/te.py index c488d68fa..831ae9995 100644 --- a/dateparser/data/date_translation_data/te.py +++ b/dateparser/data/date_translation_data/te.py @@ -92,17 +92,19 @@ "వారము" ], "day": [ - "ది", - "దినం" + "దినం", + "రోజు", + "ది" ], "hour": [ "గం", - "గంట" + "గంట", + "గంటలు" ], "minute": [ - "ని", "నిమి", - "నిమిషము" + "నిమిషము", + "ని" ], "second": [ "సెక", @@ -128,6 +130,8 @@ "ఈ వారం" ], "0 year ago": [ + "ఈ సం", + "ఈ సంవ", "ఈ సంవత్సరం" ], "1 day ago": [ @@ -140,6 +144,8 @@ "గత వారం" ], "1 year ago": [ + "గత సం", + "గత సంవ", "గత సంవత్సరం" ], "in 1 day": [ @@ -152,73 +158,77 @@ "తదుపరి వారం" ], "in 1 year": [ + "తదుపరి సం", + "తదుపరి సంవ", "తదుపరి సంవత్సరం" ] }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) రోజు క్రితం", - "(\\d+[.,]?\\d*) రోజుల క్రితం" + "(\\d++[.,]?\\d*+) రోజు క్రితం", + "(\\d++[.,]?\\d*+) రోజుల క్రితం" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) గం క్రితం", - "(\\d+[.,]?\\d*) గంట క్రితం", - "(\\d+[.,]?\\d*) గంటల క్రితం" + "(\\d++[.,]?\\d*+) గం క్రితం", + "(\\d++[.,]?\\d*+) గంట క్రితం", + "(\\d++[.,]?\\d*+) గంటల క్రితం" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) నిమి క్రితం", - "(\\d+[.,]?\\d*) నిమిషం క్రితం", - "(\\d+[.,]?\\d*) నిమిషాల క్రితం" + "(\\d++[.,]?\\d*+) నిమి క్రితం", + "(\\d++[.,]?\\d*+) నిమిషం క్రితం", + "(\\d++[.,]?\\d*+) నిమిషాల క్రితం" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) నెల క్రితం", - "(\\d+[.,]?\\d*) నెలల క్రితం" + "(\\d++[.,]?\\d*+) నెల క్రితం", + "(\\d++[.,]?\\d*+) నెలల క్రితం" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) సెక క్రితం", - "(\\d+[.,]?\\d*) సెకను క్రితం", - "(\\d+[.,]?\\d*) సెకన్ల క్రితం" + "(\\d++[.,]?\\d*+) సెక క్రితం", + "(\\d++[.,]?\\d*+) సెకను క్రితం", + "(\\d++[.,]?\\d*+) సెకన్ల క్రితం" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) వారం క్రితం", - "(\\d+[.,]?\\d*) వారాల క్రితం" + "(\\d++[.,]?\\d*+) వారం క్రితం", + "(\\d++[.,]?\\d*+) వారాల క్రితం" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) సం క్రితం", - "(\\d+[.,]?\\d*) సంవత్సరం క్రితం", - "(\\d+[.,]?\\d*) సంవత్సరాల క్రితం" + "(\\d++[.,]?\\d*+) సం క్రితం", + "(\\d++[.,]?\\d*+) సంవత్సరం క్రితం", + "(\\d++[.,]?\\d*+) సంవత్సరాల క్రితం" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) రోజులో", - "(\\d+[.,]?\\d*) రోజుల్లో" + "(\\d++[.,]?\\d*+) రోజులో", + "(\\d++[.,]?\\d*+) రోజుల్లో" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) గంటలో", - "(\\d+[.,]?\\d*) గంటల్లో", - "(\\d+[.,]?\\d*) గంలో" + "(\\d++[.,]?\\d*+) గంటలో", + "(\\d++[.,]?\\d*+) గంటల్లో", + "(\\d++[.,]?\\d*+) గంలో" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) నిమిలో", - "(\\d+[.,]?\\d*) నిమిషంలో", - "(\\d+[.,]?\\d*) నిమిషాల్లో" + "(\\d++[.,]?\\d*+) నిమిలో", + "(\\d++[.,]?\\d*+) నిమిషంలో", + "(\\d++[.,]?\\d*+) నిమిషాల్లో" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) నెలలో", - "(\\d+[.,]?\\d*) నెలల్లో" + "(\\d++[.,]?\\d*+) నెలలో", + "(\\d++[.,]?\\d*+) నెలల్లో" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) సెక లో", - "(\\d+[.,]?\\d*) సెకనులో", - "(\\d+[.,]?\\d*) సెకన్లలో" + "(\\d++[.,]?\\d*+) సెక లో", + "(\\d++[.,]?\\d*+) సెకనులో", + "(\\d++[.,]?\\d*+) సెకన్లలో", + "(\\d++[.,]?\\d*+) సెకలో" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) వారంలో", - "(\\d+[.,]?\\d*) వారాల్లో" + "(\\d++[.,]?\\d*+) వారంలో", + "(\\d++[.,]?\\d*+) వారాల్లో" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) సంలో", - "(\\d+[.,]?\\d*) సంవత్సరంలో", - "(\\d+[.,]?\\d*) సంవత్సరాల్లో" + "(\\d++[.,]?\\d*+) సంలో", + "(\\d++[.,]?\\d*+) సంల్లో", + "(\\d++[.,]?\\d*+) సంవత్సరంలో", + "(\\d++[.,]?\\d*+) సంవత్సరాల్లో" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/teo.py b/dateparser/data/date_translation_data/teo.py index 94c9877e5..30a6bd1a3 100644 --- a/dateparser/data/date_translation_data/teo.py +++ b/dateparser/data/date_translation_data/teo.py @@ -96,7 +96,8 @@ "aparan" ], "hour": [ - "esaa" + "esaa", + "hr" ], "minute": [ "idakika" diff --git a/dateparser/data/date_translation_data/th.py b/dateparser/data/date_translation_data/th.py index 031920ced..f019337f7 100644 --- a/dateparser/data/date_translation_data/th.py +++ b/dateparser/data/date_translation_data/th.py @@ -117,9 +117,11 @@ "วันอาทิตย์ที่" ], "am": [ + "am", "ก่อนเที่ยง" ], "pm": [ + "pm", "หลังเที่ยง" ], "year": [ @@ -139,8 +141,8 @@ "ชั่วโมง" ], "minute": [ - "น", - "นาที" + "นาที", + "น" ], "second": [ "วิ", @@ -195,59 +197,59 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) วันที่ผ่านมา", - "(\\d+[.,]?\\d*) วันที่แล้ว" + "(\\d++[.,]?\\d*+) วันที่ผ่านมา", + "(\\d++[.,]?\\d*+) วันที่แล้ว" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) ชม ที่แล้ว", - "(\\d+[.,]?\\d*) ชั่วโมงที่ผ่านมา" + "(\\d++[.,]?\\d*+) ชม ที่แล้ว", + "(\\d++[.,]?\\d*+) ชั่วโมงที่ผ่านมา" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) นาทีที่ผ่านมา", - "(\\d+[.,]?\\d*) นาทีที่แล้ว" + "(\\d++[.,]?\\d*+) นาทีที่ผ่านมา", + "(\\d++[.,]?\\d*+) นาทีที่แล้ว" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) เดือนที่ผ่านมา", - "(\\d+[.,]?\\d*) เดือนที่แล้ว" + "(\\d++[.,]?\\d*+) เดือนที่ผ่านมา", + "(\\d++[.,]?\\d*+) เดือนที่แล้ว" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) วินาทีที่ผ่านมา", - "(\\d+[.,]?\\d*) วินาทีที่แล้ว" + "(\\d++[.,]?\\d*+) วินาทีที่ผ่านมา", + "(\\d++[.,]?\\d*+) วินาทีที่แล้ว" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) สัปดาห์ที่ผ่านมา", - "(\\d+[.,]?\\d*) สัปดาห์ที่แล้ว" + "(\\d++[.,]?\\d*+) สัปดาห์ที่ผ่านมา", + "(\\d++[.,]?\\d*+) สัปดาห์ที่แล้ว" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) ปีที่แล้ว" + "(\\d++[.,]?\\d*+) ปีที่แล้ว" ], "in \\1 day": [ - "ใน (\\d+[.,]?\\d*) วัน", - "ในอีก (\\d+[.,]?\\d*) วัน" + "ใน (\\d++[.,]?\\d*+) วัน", + "ในอีก (\\d++[.,]?\\d*+) วัน" ], "in \\1 hour": [ - "ใน (\\d+[.,]?\\d*) ชม", - "ในอีก (\\d+[.,]?\\d*) ชั่วโมง" + "ใน (\\d++[.,]?\\d*+) ชม", + "ในอีก (\\d++[.,]?\\d*+) ชั่วโมง" ], "in \\1 minute": [ - "ใน (\\d+[.,]?\\d*) นาที", - "ในอีก (\\d+[.,]?\\d*) นาที" + "ใน (\\d++[.,]?\\d*+) นาที", + "ในอีก (\\d++[.,]?\\d*+) นาที" ], "in \\1 month": [ - "ใน (\\d+[.,]?\\d*) เดือน", - "ในอีก (\\d+[.,]?\\d*) เดือน" + "ใน (\\d++[.,]?\\d*+) เดือน", + "ในอีก (\\d++[.,]?\\d*+) เดือน" ], "in \\1 second": [ - "ใน (\\d+[.,]?\\d*) วินาที", - "ในอีก (\\d+[.,]?\\d*) วินาที" + "ใน (\\d++[.,]?\\d*+) วินาที", + "ในอีก (\\d++[.,]?\\d*+) วินาที" ], "in \\1 week": [ - "ใน (\\d+[.,]?\\d*) สัปดาห์", - "ในอีก (\\d+[.,]?\\d*) สัปดาห์" + "ใน (\\d++[.,]?\\d*+) สัปดาห์", + "ในอีก (\\d++[.,]?\\d*+) สัปดาห์" ], "in \\1 year": [ - "ใน (\\d+[.,]?\\d*) ปี", - "ในอีก (\\d+[.,]?\\d*) ปี" + "ใน (\\d++[.,]?\\d*+) ปี", + "ในอีก (\\d++[.,]?\\d*+) ปี" ] }, "locale_specific": {}, @@ -272,10 +274,13 @@ "ago": [ "แต่ก่อน", "มาแล้ว", - "ก่อน" + "ก่อน", + "ที่แล้ว", + "ที่ผ่านมา" ], "in": [ - "ใน" + "ใน", + "อีก" ], "simplifications": [ { diff --git a/dateparser/data/date_translation_data/ti.py b/dateparser/data/date_translation_data/ti.py index 284937e53..2b4b31f15 100644 --- a/dateparser/data/date_translation_data/ti.py +++ b/dateparser/data/date_translation_data/ti.py @@ -52,9 +52,9 @@ "ሰኑይ" ], "tuesday": [ - "ሠሉስ", "ሰሉ", - "ሰሉስ" + "ሰሉስ", + "ሠሉስ" ], "wednesday": [ "ረቡ", @@ -78,79 +78,150 @@ "ሰንበት" ], "am": [ + "ቅቀ", "ንጉሆ ሰዓተ" ], "pm": [ + "ድቀ", "ድሕር ሰዓት" ], "year": [ + "ዓመት", "year" ], "month": [ + "ወርሒ", "month" ], "week": [ + "ሰሙን", "week" ], "day": [ + "መዓልቲ", "day" ], "hour": [ + "hr", + "ሰዓት", "hour" ], "minute": [ + "ደቒ", + "ደቒቕ", "minute" ], "second": [ + "ካልኢት", "second" ], "relative-type": { "0 day ago": [ + "ሎሚ", "today" ], "0 hour ago": [ + "ኣብዚ ሰዓት", "this hour" ], "0 minute ago": [ + "ኣብዚ ደቒቕ", "this minute" ], "0 month ago": [ + "ህሉው ወርሒ", "this month" ], "0 second ago": [ + "ሕጂ", "now" ], "0 week ago": [ + "ህሉው ሰሙን", "this week" ], "0 year ago": [ + "ሎሚ ዓመት", "this year" ], "1 day ago": [ + "ትማሊ", "yesterday" ], "1 month ago": [ + "ዝሓለፈ ወርሒ", "last month" ], "1 week ago": [ + "ዝሓለፈ ሰሙን", "last week" ], "1 year ago": [ + "ዓሚ", "last year" ], "in 1 day": [ + "ጽባሕ", "tomorrow" ], "in 1 month": [ + "ዝመጽእ ወርሒ", "next month" ], "in 1 week": [ + "ዝመጽእ ሰሙን", "next week" ], "in 1 year": [ + "ንዓመታ", "next year" ] }, + "relative-type-regex": { + "\\1 day ago": [ + "ቅድሚ (\\d++[.,]?\\d*+) መዓልቲ", + "ኣብ (\\d++[.,]?\\d*+) መዓልቲ" + ], + "\\1 hour ago": [ + "ቅድሚ (\\d++[.,]?\\d*+) ሰዓት" + ], + "\\1 minute ago": [ + "ቅድሚ (\\d++[.,]?\\d*+) ደቒቕ" + ], + "\\1 month ago": [ + "ቅድሚ (\\d++[.,]?\\d*+) ወርሒ" + ], + "\\1 second ago": [ + "ቅድሚ (\\d++[.,]?\\d*+) ካልኢት" + ], + "\\1 week ago": [ + "ቅድሚ (\\d++[.,]?\\d*+) ሰሙን" + ], + "\\1 year ago": [ + "ቅድሚ (\\d++[.,]?\\d*+) ዓ" + ], + "in \\1 day": [ + "ኣብ (\\d++[.,]?\\d*+) መዓልቲ" + ], + "in \\1 hour": [ + "ኣብ (\\d++[.,]?\\d*+) ሰዓት" + ], + "in \\1 minute": [ + "ኣብ (\\d++[.,]?\\d*+) ደቒቕ" + ], + "in \\1 month": [ + "ኣብ (\\d++[.,]?\\d*+) ወርሒ" + ], + "in \\1 second": [ + "ኣብ (\\d++[.,]?\\d*+) ካልኢት" + ], + "in \\1 week": [ + "ኣብ (\\d++[.,]?\\d*+) ሰሙን" + ], + "in \\1 year": [ + "ኣብ (\\d++[.,]?\\d*+) ዓ" + ] + }, "locale_specific": { "ti-ER": { "name": "ti-ER" diff --git a/dateparser/data/date_translation_data/to.py b/dateparser/data/date_translation_data/to.py index ea4d3b411..7d2985b40 100644 --- a/dateparser/data/date_translation_data/to.py +++ b/dateparser/data/date_translation_data/to.py @@ -33,8 +33,10 @@ "'aokosi" ], "september": [ - "sep", - "sepitema" + "sepitema", + "sēp", + "sēpitema", + "sep" ], "october": [ "'oka", @@ -77,9 +79,9 @@ "sāpate" ], "am": [ - "am", "hengihengi", - "hh" + "hh", + "am" ], "pm": [ "ea", @@ -87,115 +89,136 @@ "pm" ], "year": [ + "t", "ta'u" ], "month": [ + "mh", "māhina" ], "week": [ + "ui", "uike" ], "day": [ + "'a", "'aho" ], "hour": [ + "h", "houa" ], "minute": [ + "m", "miniti" ], "second": [ + "s", "sekoni" ], "relative-type": { "0 day ago": [ - "'ahó ni" + "'ahó ni", + "'ani" ], "0 hour ago": [ + "ko e houa 'eni", "this hour" ], "0 minute ago": [ + "ko e miniti 'eni", "this minute" ], "0 month ago": [ + "mhni", "māhiná ni" ], "0 second ago": [ "taimí ni" ], "0 week ago": [ - "uiké ni" + "uiké ni", + "uini" ], "0 year ago": [ - "ta'ú ni" + "ta'ú ni", + "tni" ], "1 day ago": [ + "'ane", "'aneafi" ], "1 month ago": [ + "mh'osi", "māhina kuo'osi" ], "1 week ago": [ + "ui'osi", "uike kuo'osi" ], "1 year ago": [ + "t'osi", "ta'u kuo'osi" ], "in 1 day": [ + "'apo", "'apongipongi" ], "in 1 month": [ + "mhha'u", "māhina kaha'u" ], "in 1 week": [ + "uiha'u", "uike kaha'u" ], "in 1 year": [ - "ta'u kaha'u" + "ta'u kaha'u", + "tha'u" ] }, "relative-type-regex": { "\\1 day ago": [ - "'aho 'e (\\d+[.,]?\\d*) kuo'osi" + "'aho 'e (\\d++[.,]?\\d*+) kuo'osi" ], "\\1 hour ago": [ - "houa 'e (\\d+[.,]?\\d*) kuo'osi" + "houa 'e (\\d++[.,]?\\d*+) kuo'osi" ], "\\1 minute ago": [ - "miniti 'e (\\d+[.,]?\\d*) kuo'osi" + "miniti 'e (\\d++[.,]?\\d*+) kuo'osi" ], "\\1 month ago": [ - "māhina 'e (\\d+[.,]?\\d*) kuo'osi" + "māhina 'e (\\d++[.,]?\\d*+) kuo'osi" ], "\\1 second ago": [ - "sekoni 'e (\\d+[.,]?\\d*) kuo'osi" + "sekoni 'e (\\d++[.,]?\\d*+) kuo'osi" ], "\\1 week ago": [ - "uike 'e (\\d+[.,]?\\d*) kuo'osi" + "uike 'e (\\d++[.,]?\\d*+) kuo'osi" ], "\\1 year ago": [ - "ta'u 'e (\\d+[.,]?\\d*) kuo'osi" + "ta'u 'e (\\d++[.,]?\\d*+) kuo'osi" ], "in \\1 day": [ - "'i he 'aho 'e (\\d+[.,]?\\d*)" + "'i he 'aho 'e (\\d++[.,]?\\d*+)" ], "in \\1 hour": [ - "'i he houa 'e (\\d+[.,]?\\d*)" + "'i he houa 'e (\\d++[.,]?\\d*+)" ], "in \\1 minute": [ - "'i he miniti 'e (\\d+[.,]?\\d*)" + "'i he miniti 'e (\\d++[.,]?\\d*+)" ], "in \\1 month": [ - "'i he māhina 'e (\\d+[.,]?\\d*)" + "'i he māhina 'e (\\d++[.,]?\\d*+)" ], "in \\1 second": [ - "'i he sekoni 'e (\\d+[.,]?\\d*)" + "'i he sekoni 'e (\\d++[.,]?\\d*+)" ], "in \\1 week": [ - "'i he uike 'e (\\d+[.,]?\\d*)" + "'i he uike 'e (\\d++[.,]?\\d*+)" ], "in \\1 year": [ - "'i he ta'u 'e (\\d+[.,]?\\d*)" + "'i he ta'u 'e (\\d++[.,]?\\d*+)" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/tr.py b/dateparser/data/date_translation_data/tr.py index 8688a4438..2e47c258f 100644 --- a/dateparser/data/date_translation_data/tr.py +++ b/dateparser/data/date_translation_data/tr.py @@ -138,7 +138,8 @@ "şimdi" ], "0 week ago": [ - "bu hafta" + "bu hafta", + "bu hf" ], "0 year ago": [ "bu yıl" @@ -151,7 +152,8 @@ "geçen ay" ], "1 week ago": [ - "geçen hafta" + "geçen hafta", + "geçen hf" ], "1 year ago": [ "geçen yıl" @@ -166,6 +168,7 @@ ], "in 1 week": [ "gelecek hafta", + "gelecek hf", "haftaya", "önümüzdeki hafta" ], @@ -176,54 +179,54 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) gün önce" + "(\\d++[.,]?\\d*+) gün önce" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) sa önce", - "(\\d+[.,]?\\d*) saat önce" + "(\\d++[.,]?\\d*+) sa önce", + "(\\d++[.,]?\\d*+) saat önce" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) dakika önce", - "(\\d+[.,]?\\d*) dk önce" + "(\\d++[.,]?\\d*+) dakika önce", + "(\\d++[.,]?\\d*+) dk önce" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) ay önce" + "(\\d++[.,]?\\d*+) ay önce" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) saniye önce", - "(\\d+[.,]?\\d*) sn önce" + "(\\d++[.,]?\\d*+) saniye önce", + "(\\d++[.,]?\\d*+) sn önce" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) hafta önce", - "(\\d+[.,]?\\d*) hf önce" + "(\\d++[.,]?\\d*+) hafta önce", + "(\\d++[.,]?\\d*+) hf önce" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) yıl önce" + "(\\d++[.,]?\\d*+) yıl önce" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) gün sonra" + "(\\d++[.,]?\\d*+) gün sonra" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) sa sonra", - "(\\d+[.,]?\\d*) saat sonra" + "(\\d++[.,]?\\d*+) sa sonra", + "(\\d++[.,]?\\d*+) saat sonra" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) dakika sonra", - "(\\d+[.,]?\\d*) dk sonra" + "(\\d++[.,]?\\d*+) dakika sonra", + "(\\d++[.,]?\\d*+) dk sonra" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) ay sonra" + "(\\d++[.,]?\\d*+) ay sonra" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) saniye sonra", - "(\\d+[.,]?\\d*) sn sonra" + "(\\d++[.,]?\\d*+) saniye sonra", + "(\\d++[.,]?\\d*+) sn sonra" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) hafta sonra", - "(\\d+[.,]?\\d*) hf sonra" + "(\\d++[.,]?\\d*+) hafta sonra", + "(\\d++[.,]?\\d*+) hf sonra" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) yıl sonra" + "(\\d++[.,]?\\d*+) yıl sonra" ] }, "locale_specific": { diff --git a/dateparser/data/date_translation_data/twq.py b/dateparser/data/date_translation_data/twq.py index 2146c0b40..55ea8260a 100644 --- a/dateparser/data/date_translation_data/twq.py +++ b/dateparser/data/date_translation_data/twq.py @@ -94,7 +94,8 @@ "zaari" ], "hour": [ - "guuru" + "guuru", + "hr" ], "minute": [ "miniti" diff --git a/dateparser/data/date_translation_data/tzm.py b/dateparser/data/date_translation_data/tzm.py index efba48a80..a88a45fc2 100644 --- a/dateparser/data/date_translation_data/tzm.py +++ b/dateparser/data/date_translation_data/tzm.py @@ -96,6 +96,7 @@ "ass" ], "hour": [ + "hr", "tasragt" ], "minute": [ diff --git a/dateparser/data/date_translation_data/ug.py b/dateparser/data/date_translation_data/ug.py index b55b8419b..31ec22778 100644 --- a/dateparser/data/date_translation_data/ug.py +++ b/dateparser/data/date_translation_data/ug.py @@ -86,6 +86,7 @@ "كۈن" ], "hour": [ + "hr", "سائەت" ], "minute": [ @@ -143,46 +144,46 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) كۈن ئىلگىرى" + "(\\d++[.,]?\\d*+) كۈن ئىلگىرى" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) سائەت ئىلگىرى" + "(\\d++[.,]?\\d*+) سائەت ئىلگىرى" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) مىنۇت ئىلگىرى" + "(\\d++[.,]?\\d*+) مىنۇت ئىلگىرى" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) ئاي ئىلگىرى" + "(\\d++[.,]?\\d*+) ئاي ئىلگىرى" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) سېكۇنت ئىلگىرى" + "(\\d++[.,]?\\d*+) سېكۇنت ئىلگىرى" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) ھەپتە ئىلگىرى" + "(\\d++[.,]?\\d*+) ھەپتە ئىلگىرى" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) يىل ئىلگىرى" + "(\\d++[.,]?\\d*+) يىل ئىلگىرى" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) كۈندىن كېيىن" + "(\\d++[.,]?\\d*+) كۈندىن كېيىن" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) سائەتتىن كېيىن" + "(\\d++[.,]?\\d*+) سائەتتىن كېيىن" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) مىنۇتتىن كېيىن" + "(\\d++[.,]?\\d*+) مىنۇتتىن كېيىن" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) ئايدىن كېيىن" + "(\\d++[.,]?\\d*+) ئايدىن كېيىن" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) سېكۇنتتىن كېيىن" + "(\\d++[.,]?\\d*+) سېكۇنتتىن كېيىن" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) ھەپتىدىن كېيىن" + "(\\d++[.,]?\\d*+) ھەپتىدىن كېيىن" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) يىلدىن كېيىن" + "(\\d++[.,]?\\d*+) يىلدىن كېيىن" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/uk.py b/dateparser/data/date_translation_data/uk.py index 4733942cf..b29a94332 100644 --- a/dateparser/data/date_translation_data/uk.py +++ b/dateparser/data/date_translation_data/uk.py @@ -18,22 +18,22 @@ "берез" ], "april": [ - "кві", "квіт", "квітень", - "квітня" + "квітня", + "кві" ], "may": [ - "тра", "трав", "травень", - "травня" + "травня", + "тра" ], "june": [ - "чер", "черв", "червень", - "червня" + "червня", + "чер" ], "july": [ "лип", @@ -41,10 +41,10 @@ "липня" ], "august": [ - "сер", "серп", "серпень", - "серпня" + "серпня", + "сер" ], "september": [ "вер", @@ -53,23 +53,23 @@ "верес" ], "october": [ - "жов", "жовт", "жовтень", - "жовтня" + "жовтня", + "жов" ], "november": [ - "лис", "лист", "листопад", "листопада", - "листоп" + "листоп", + "лис" ], "december": [ - "гру", "груд", "грудень", - "грудня" + "грудня", + "гру" ], "monday": [ "пн", @@ -89,6 +89,7 @@ ], "wednesday": [ "середа", + "середу", "ср", "ср", "сер", @@ -104,6 +105,7 @@ "четвер" ], "friday": [ + "п'ятницю", "п'ятниця", "пт", "пят" @@ -111,6 +113,7 @@ "saturday": [ "сб", "субота", + "суботу", "сб", "суб", "субот", @@ -119,6 +122,7 @@ ], "sunday": [ "нд", + "неділю", "неділя", "нд", "нед", @@ -151,6 +155,7 @@ "рокові" ], "month": [ + "м", "міс", "місяць", "м", @@ -167,6 +172,7 @@ "місяцями" ], "week": [ + "т", "тиж", "тиждень", "т", @@ -197,6 +203,7 @@ "hour": [ "год", "година", + "години", "г", "год", "годин", @@ -245,6 +252,7 @@ "цієї хвилини" ], "0 month ago": [ + "цього міс", "цього місяця" ], "0 second ago": [ @@ -254,31 +262,39 @@ "цього тижня" ], "0 year ago": [ - "цього року" + "цього року", + "цьогоріч" ], "1 day ago": [ "учора", "вчора" ], "1 month ago": [ + "мин міс", "минулого місяця" ], "1 week ago": [ + "мин тижня", "минулого тижня" ], "1 year ago": [ + "минулого року", "торік" ], "in 1 day": [ "завтра" ], "in 1 month": [ + "наст міс", "наступного місяця" ], "in 1 week": [ + "наст тижня", "наступного тижня" ], "in 1 year": [ + "наст р", + "наст року", "наступного року" ], "2 day ago": [ @@ -290,85 +306,86 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) д тому", - "(\\d+[.,]?\\d*) день тому", - "(\\d+[.,]?\\d*) дн тому", - "(\\d+[.,]?\\d*) дня тому" + "(\\d++[.,]?\\d*+) день тому", + "(\\d++[.,]?\\d*+) дн тому", + "(\\d++[.,]?\\d*+) дня тому", + "(\\d++[.,]?\\d*+) д тому" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) год тому", - "(\\d+[.,]?\\d*) години тому", - "(\\d+[.,]?\\d*) годину тому", - "(\\d+[.,]?\\d*) година тому" + "(\\d++[.,]?\\d*+) год тому", + "(\\d++[.,]?\\d*+) години тому", + "(\\d++[.,]?\\d*+) годину тому", + "(\\d++[.,]?\\d*+) година тому" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) хв тому", - "(\\d+[.,]?\\d*) хвилини тому", - "(\\d+[.,]?\\d*) хвилину тому", - "(\\d+[.,]?\\d*) хвилина тому" + "(\\d++[.,]?\\d*+) хв тому", + "(\\d++[.,]?\\d*+) хвилини тому", + "(\\d++[.,]?\\d*+) хвилину тому", + "(\\d++[.,]?\\d*+) хвилина тому" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) міс тому", - "(\\d+[.,]?\\d*) місяць тому", - "(\\d+[.,]?\\d*) місяця тому" + "(\\d++[.,]?\\d*+) міс тому", + "(\\d++[.,]?\\d*+) місяць тому", + "(\\d++[.,]?\\d*+) місяця тому" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) с тому", - "(\\d+[.,]?\\d*) секунди тому", - "(\\d+[.,]?\\d*) секунду тому", - "(\\d+[.,]?\\d*) секунда тому" + "(\\d++[.,]?\\d*+) с тому", + "(\\d++[.,]?\\d*+) секунди тому", + "(\\d++[.,]?\\d*+) секунду тому", + "(\\d++[.,]?\\d*+) секунда тому" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) тиж тому", - "(\\d+[.,]?\\d*) тиждень тому", - "(\\d+[.,]?\\d*) тижня тому" + "(\\d++[.,]?\\d*+) тиж тому", + "(\\d++[.,]?\\d*+) тиждень тому", + "(\\d++[.,]?\\d*+) тижня тому" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) р тому", - "(\\d+[.,]?\\d*) року тому", - "(\\d+[.,]?\\d*) рік тому" + "(\\d++[.,]?\\d*+) р тому", + "(\\d++[.,]?\\d*+) року тому", + "(\\d++[.,]?\\d*+) рік тому" ], "in \\1 day": [ - "за (\\d+[.,]?\\d*) д", - "через (\\d+[.,]?\\d*) день", - "через (\\d+[.,]?\\d*) дн", - "через (\\d+[.,]?\\d*) дня" + "за (\\d++[.,]?\\d*+) дн", + "через (\\d++[.,]?\\d*+) день", + "через (\\d++[.,]?\\d*+) дн", + "через (\\d++[.,]?\\d*+) дня", + "за (\\d++[.,]?\\d*+) д" ], "in \\1 hour": [ - "за (\\d+[.,]?\\d*) год", - "через (\\d+[.,]?\\d*) год", - "через (\\d+[.,]?\\d*) години", - "через (\\d+[.,]?\\d*) годину" + "за (\\d++[.,]?\\d*+) год", + "через (\\d++[.,]?\\d*+) год", + "через (\\d++[.,]?\\d*+) години", + "через (\\d++[.,]?\\d*+) годину" ], "in \\1 minute": [ - "за (\\d+[.,]?\\d*) хв", - "через (\\d+[.,]?\\d*) хв", - "через (\\d+[.,]?\\d*) хвилини", - "через (\\d+[.,]?\\d*) хвилину" + "за (\\d++[.,]?\\d*+) хв", + "через (\\d++[.,]?\\d*+) хв", + "через (\\d++[.,]?\\d*+) хвилини", + "через (\\d++[.,]?\\d*+) хвилину" ], "in \\1 month": [ - "за (\\d+[.,]?\\d*) міс", - "через (\\d+[.,]?\\d*) міс", - "через (\\d+[.,]?\\d*) місяць", - "через (\\d+[.,]?\\d*) місяця" + "за (\\d++[.,]?\\d*+) міс", + "через (\\d++[.,]?\\d*+) міс", + "через (\\d++[.,]?\\d*+) місяць", + "через (\\d++[.,]?\\d*+) місяця" ], "in \\1 second": [ - "за (\\d+[.,]?\\d*) с", - "через (\\d+[.,]?\\d*) с", - "через (\\d+[.,]?\\d*) секунди", - "через (\\d+[.,]?\\d*) секунду" + "за (\\d++[.,]?\\d*+) с", + "через (\\d++[.,]?\\d*+) с", + "через (\\d++[.,]?\\d*+) секунди", + "через (\\d++[.,]?\\d*+) секунду" ], "in \\1 week": [ - "за (\\d+[.,]?\\d*) тиж", - "через (\\d+[.,]?\\d*) тиж", - "через (\\d+[.,]?\\d*) тиждень", - "через (\\d+[.,]?\\d*) тижня" + "за (\\d++[.,]?\\d*+) тиж", + "через (\\d++[.,]?\\d*+) тиж", + "через (\\d++[.,]?\\d*+) тиждень", + "через (\\d++[.,]?\\d*+) тижня" ], "in \\1 year": [ - "за (\\d+[.,]?\\d*) р", - "через (\\d+[.,]?\\d*) р", - "через (\\d+[.,]?\\d*) року", - "через (\\d+[.,]?\\d*) рік" + "за (\\d++[.,]?\\d*+) р", + "через (\\d++[.,]?\\d*+) р", + "через (\\d++[.,]?\\d*+) року", + "через (\\d++[.,]?\\d*+) рік" ] }, "locale_specific": {}, @@ -497,6 +514,18 @@ }, { "за чверть": "15 хвилин" + }, + { + "(?<=[^\\d]\\s+|^)тиждень(?=\\s+тому)": "1 тиждень" + }, + { + "(?<=[^\\d]\\s+|^)місяць(?=\\s+тому)": "1 місяць" + }, + { + "(?<=[^\\d]\\s+|^)рік(?=\\s+тому)": "1 рік" + }, + { + "(?<=[^\\d]\\s+|^)день(?=\\s+тому)": "1 день" } ] } diff --git a/dateparser/data/date_translation_data/ur.py b/dateparser/data/date_translation_data/ur.py index c00110d60..5b4fdcc86 100644 --- a/dateparser/data/date_translation_data/ur.py +++ b/dateparser/data/date_translation_data/ur.py @@ -38,6 +38,7 @@ "دسمبر" ], "monday": [ + "پیر", "سوموار" ], "tuesday": [ @@ -78,7 +79,8 @@ "دن" ], "hour": [ - "گھنٹہ" + "گھنٹہ", + "گھنٹے" ], "minute": [ "منٹ" @@ -97,6 +99,7 @@ "اس منٹ" ], "0 month ago": [ + "اس ماہ", "اس مہینہ" ], "0 second ago": [ @@ -112,10 +115,12 @@ "گزشتہ کل" ], "1 month ago": [ - "پچھلے مہینہ" + "پچھلے مہینہ", + "گزشتہ ماہ" ], "1 week ago": [ - "پچھلے ہفتہ" + "پچھلے ہفتہ", + "گزشتہ ہفتے" ], "1 year ago": [ "گزشتہ سال" @@ -124,10 +129,13 @@ "آئندہ کل" ], "in 1 month": [ + "اگلا مہینہ", + "اگلے ماہ", "اگلے مہینہ" ], "in 1 week": [ - "اگلے ہفتہ" + "اگلے ہفتہ", + "اگلے ہفتے" ], "in 1 year": [ "اگلے سال" @@ -135,106 +143,94 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) دن پہلے", - "(\\d+[.,]?\\d*) دنوں پہلے" + "(\\d++[.,]?\\d*+) دن پہلے", + "(\\d++[.,]?\\d*+) دنوں پہلے" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) گھنٹہ پہلے", - "(\\d+[.,]?\\d*) گھنٹے پہلے" + "(\\d++[.,]?\\d*+) گھنٹہ پہلے", + "(\\d++[.,]?\\d*+) گھنٹے پہلے" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) منٹ پہلے" + "(\\d++[.,]?\\d*+) منٹ پہلے" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) ماہ قبل", - "(\\d+[.,]?\\d*) ماہ پہلے", - "(\\d+[.,]?\\d*) مہینہ پہلے", - "(\\d+[.,]?\\d*) مہینے پہلے" + "(\\d++[.,]?\\d*+) ماہ قبل", + "(\\d++[.,]?\\d*+) ماہ پہلے", + "(\\d++[.,]?\\d*+) مہینہ پہلے", + "(\\d++[.,]?\\d*+) مہینے پہلے" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) سیکنڈ پہلے" + "(\\d++[.,]?\\d*+) سیکنڈ پہلے" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) ہفتہ پہلے", - "(\\d+[.,]?\\d*) ہفتے پہلے" + "(\\d++[.,]?\\d*+) ہفتہ پہلے", + "(\\d++[.,]?\\d*+) ہفتے پہلے" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) سال پہلے" + "(\\d++[.,]?\\d*+) سال پہلے" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) دن میں", - "(\\d+[.,]?\\d*) دنوں میں" + "(\\d++[.,]?\\d*+) دن میں", + "(\\d++[.,]?\\d*+) دنوں میں" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) گھنٹوں میں", - "(\\d+[.,]?\\d*) گھنٹہ میں", - "(\\d+[.,]?\\d*) گھنٹے میں" + "(\\d++[.,]?\\d*+) گھنٹوں میں", + "(\\d++[.,]?\\d*+) گھنٹے میں", + "(\\d++[.,]?\\d*+) گھنٹہ میں" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) منٹ میں" + "(\\d++[.,]?\\d*+) منٹ میں" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) ماہ میں", - "(\\d+[.,]?\\d*) مہینہ میں", - "(\\d+[.,]?\\d*) مہینے میں" + "(\\d++[.,]?\\d*+) ماہ میں", + "(\\d++[.,]?\\d*+) مہینہ میں", + "(\\d++[.,]?\\d*+) مہینے میں" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) سیکنڈ میں" + "(\\d++[.,]?\\d*+) سیکنڈ میں" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) ہفتہ میں", - "(\\d+[.,]?\\d*) ہفتے میں" + "(\\d++[.,]?\\d*+) ہفتہ میں", + "(\\d++[.,]?\\d*+) ہفتے میں" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) سال میں" + "(\\d++[.,]?\\d*+) سال میں" ] }, "locale_specific": { "ur-IN": { "name": "ur-IN", - "monday": [ - "پیر" - ], "relative-type": { - "0 month ago": [ - "اس ماہ" - ], - "1 month ago": [ - "گزشتہ ماہ" - ], "1 week ago": [ "گزشتہ ہفتہ" - ], - "in 1 month": [ - "اگلے ماہ" ] }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) دن قبل" + "(\\d++[.,]?\\d*+) دن قبل" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) گھنٹہ قبل", - "(\\d+[.,]?\\d*) گھنٹے قبل" + "(\\d++[.,]?\\d*+) گھنٹہ قبل", + "(\\d++[.,]?\\d*+) گھنٹے قبل" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) منٹ قبل" + "(\\d++[.,]?\\d*+) منٹ قبل" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) سیکنڈ قبل" + "(\\d++[.,]?\\d*+) سیکنڈ قبل" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) ہفتہ قبل", - "(\\d+[.,]?\\d*) ہفتے قبل" + "(\\d++[.,]?\\d*+) ہفتہ قبل", + "(\\d++[.,]?\\d*+) ہفتے قبل" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) سالوں پہلے" + "(\\d++[.,]?\\d*+) سالوں پہلے" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) ہفتوں میں" + "(\\d++[.,]?\\d*+) ہفتوں میں" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) سالوں میں" + "(\\d++[.,]?\\d*+) سالوں میں" ] } } diff --git a/dateparser/data/date_translation_data/uz-Arab.py b/dateparser/data/date_translation_data/uz-Arab.py index 00f0f570e..63ce35dcf 100644 --- a/dateparser/data/date_translation_data/uz-Arab.py +++ b/dateparser/data/date_translation_data/uz-Arab.py @@ -94,7 +94,8 @@ "day" ], "hour": [ - "hour" + "hour", + "hr" ], "minute": [ "minute" diff --git a/dateparser/data/date_translation_data/uz-Cyrl.py b/dateparser/data/date_translation_data/uz-Cyrl.py index 44c3d0974..ed4ef4c05 100644 --- a/dateparser/data/date_translation_data/uz-Cyrl.py +++ b/dateparser/data/date_translation_data/uz-Cyrl.py @@ -93,6 +93,7 @@ "кун" ], "hour": [ + "hr", "соат" ], "minute": [ @@ -150,46 +151,46 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) кун олдин" + "(\\d++[.,]?\\d*+) кун олдин" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) соат олдин" + "(\\d++[.,]?\\d*+) соат олдин" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) дақиқа олдин" + "(\\d++[.,]?\\d*+) дақиқа олдин" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) ой аввал" + "(\\d++[.,]?\\d*+) ой аввал" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) сония олдин" + "(\\d++[.,]?\\d*+) сония олдин" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) ҳафта олдин" + "(\\d++[.,]?\\d*+) ҳафта олдин" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) йил аввал" + "(\\d++[.,]?\\d*+) йил аввал" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) кундан сўнг" + "(\\d++[.,]?\\d*+) кундан сўнг" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) соатдан сўнг" + "(\\d++[.,]?\\d*+) соатдан сўнг" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) дақиқадан сўнг" + "(\\d++[.,]?\\d*+) дақиқадан сўнг" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) ойдан сўнг" + "(\\d++[.,]?\\d*+) ойдан сўнг" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) сониядан сўнг" + "(\\d++[.,]?\\d*+) сониядан сўнг" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) ҳафтадан сўнг" + "(\\d++[.,]?\\d*+) ҳафтадан сўнг" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) йилдан сўнг" + "(\\d++[.,]?\\d*+) йилдан сўнг" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/uz-Latn.py b/dateparser/data/date_translation_data/uz-Latn.py index 5435fafa0..a65711151 100644 --- a/dateparser/data/date_translation_data/uz-Latn.py +++ b/dateparser/data/date_translation_data/uz-Latn.py @@ -116,12 +116,14 @@ "shu daqiqada" ], "0 month ago": [ + "bu oy", "shu oy" ], "0 second ago": [ "hozir" ], "0 week ago": [ + "bu hafta", "shu hafta" ], "0 year ago": [ @@ -138,8 +140,9 @@ "o‘tgan hafta" ], "1 year ago": [ - "o'tgan yil", - "o‘tgan yil" + "o‘'tgan yil", + "o‘tgan yil", + "o'tgan yil" ], "in 1 day": [ "ertaga" @@ -156,46 +159,46 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) kun oldin" + "(\\d++[.,]?\\d*+) kun oldin" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) soat oldin" + "(\\d++[.,]?\\d*+) soat oldin" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) daqiqa oldin" + "(\\d++[.,]?\\d*+) daqiqa oldin" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) oy oldin" + "(\\d++[.,]?\\d*+) oy oldin" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) soniya oldin" + "(\\d++[.,]?\\d*+) soniya oldin" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) hafta oldin" + "(\\d++[.,]?\\d*+) hafta oldin" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) yil oldin" + "(\\d++[.,]?\\d*+) yil oldin" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) kundan keyin" + "(\\d++[.,]?\\d*+) kundan keyin" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) soatdan keyin" + "(\\d++[.,]?\\d*+) soatdan keyin" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) daqiqadan keyin" + "(\\d++[.,]?\\d*+) daqiqadan keyin" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) oydan keyin" + "(\\d++[.,]?\\d*+) oydan keyin" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) soniyadan keyin" + "(\\d++[.,]?\\d*+) soniyadan keyin" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) haftadan keyin" + "(\\d++[.,]?\\d*+) haftadan keyin" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) yildan keyin" + "(\\d++[.,]?\\d*+) yildan keyin" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/uz.py b/dateparser/data/date_translation_data/uz.py index 488e9cbdf..0bd3ce885 100644 --- a/dateparser/data/date_translation_data/uz.py +++ b/dateparser/data/date_translation_data/uz.py @@ -116,12 +116,14 @@ "shu daqiqada" ], "0 month ago": [ + "bu oy", "shu oy" ], "0 second ago": [ "hozir" ], "0 week ago": [ + "bu hafta", "shu hafta" ], "0 year ago": [ @@ -138,8 +140,9 @@ "o‘tgan hafta" ], "1 year ago": [ - "o'tgan yil", - "o‘tgan yil" + "o‘'tgan yil", + "o‘tgan yil", + "o'tgan yil" ], "in 1 day": [ "ertaga" @@ -156,46 +159,46 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) kun oldin" + "(\\d++[.,]?\\d*+) kun oldin" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) soat oldin" + "(\\d++[.,]?\\d*+) soat oldin" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) daqiqa oldin" + "(\\d++[.,]?\\d*+) daqiqa oldin" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) oy oldin" + "(\\d++[.,]?\\d*+) oy oldin" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) soniya oldin" + "(\\d++[.,]?\\d*+) soniya oldin" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) hafta oldin" + "(\\d++[.,]?\\d*+) hafta oldin" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) yil oldin" + "(\\d++[.,]?\\d*+) yil oldin" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) kundan keyin" + "(\\d++[.,]?\\d*+) kundan keyin" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) soatdan keyin" + "(\\d++[.,]?\\d*+) soatdan keyin" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) daqiqadan keyin" + "(\\d++[.,]?\\d*+) daqiqadan keyin" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) oydan keyin" + "(\\d++[.,]?\\d*+) oydan keyin" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) soniyadan keyin" + "(\\d++[.,]?\\d*+) soniyadan keyin" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) haftadan keyin" + "(\\d++[.,]?\\d*+) haftadan keyin" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) yildan keyin" + "(\\d++[.,]?\\d*+) yildan keyin" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/vi.py b/dateparser/data/date_translation_data/vi.py index 10cfd5b94..4753f02d9 100644 --- a/dateparser/data/date_translation_data/vi.py +++ b/dateparser/data/date_translation_data/vi.py @@ -4,47 +4,65 @@ "january": [ "thg 1", "tháng 1", - "Tháng một" + "Tháng một", + "tháng 01", + "thg 01" ], "february": [ "thg 2", "tháng 2", - "Tháng hai" + "Tháng hai", + "tháng 02", + "thg 02" ], "march": [ "thg 3", "tháng 3", - "Tháng ba" + "Tháng ba", + "tháng 03", + "thg 03" ], "april": [ "thg 4", "tháng 4", - "Tháng tư" + "Tháng tư", + "tháng 04", + "thg 04" ], "may": [ "thg 5", "tháng 5", - "Tháng năm" + "Tháng năm", + "tháng 05", + "thg 05" ], "june": [ "thg 6", "tháng 6", - "Tháng sáu" + "Tháng sáu", + "tháng 06", + "thg 06" ], "july": [ "thg 7", "tháng 7", - "Tháng bảy" + "Tháng bảy", + "tháng 07", + "thg 07" ], "august": [ "thg 8", "tháng 8", - "Tháng tám" + "Tháng tám", + "tháng 08", + "thg 08" ], "september": [ "thg 9", "tháng 9", - "Tháng chín" + "Tháng chín", + "tháng 09", + "thg 09" ], "october": [ "thg 10", @@ -182,46 +200,46 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) ngày trước" + "(\\d++[.,]?\\d*+) ngày trước" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) giờ trước" + "(\\d++[.,]?\\d*+) giờ trước" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) phút trước" + "(\\d++[.,]?\\d*+) phút trước" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) tháng trước" + "(\\d++[.,]?\\d*+) tháng trước" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) giây trước" + "(\\d++[.,]?\\d*+) giây trước" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) tuần trước" + "(\\d++[.,]?\\d*+) tuần trước" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) năm trước" + "(\\d++[.,]?\\d*+) năm trước" ], "in \\1 day": [ - "sau (\\d+[.,]?\\d*) ngày nữa" + "sau (\\d++[.,]?\\d*+) ngày nữa" ], "in \\1 hour": [ - "sau (\\d+[.,]?\\d*) giờ nữa" + "sau (\\d++[.,]?\\d*+) giờ nữa" ], "in \\1 minute": [ - "sau (\\d+[.,]?\\d*) phút nữa" + "sau (\\d++[.,]?\\d*+) phút nữa" ], "in \\1 month": [ - "sau (\\d+[.,]?\\d*) tháng nữa" + "sau (\\d++[.,]?\\d*+) tháng nữa" ], "in \\1 second": [ - "sau (\\d+[.,]?\\d*) giây nữa" + "sau (\\d++[.,]?\\d*+) giây nữa" ], "in \\1 week": [ - "sau (\\d+[.,]?\\d*) tuần nữa" + "sau (\\d++[.,]?\\d*+) tuần nữa" ], "in \\1 year": [ - "sau (\\d+[.,]?\\d*) năm nữa" + "sau (\\d++[.,]?\\d*+) năm nữa" ] }, "locale_specific": {}, @@ -240,7 +258,7 @@ ], "simplifications": [ { - "(?:ngày|năm)\\s(\\d+[.,]?\\d*)": "\\1" + "(?:ngày|năm)\\s(\\d++[.,]?\\d*+)": "\\1" } ], "skip": [ diff --git a/dateparser/data/date_translation_data/vun.py b/dateparser/data/date_translation_data/vun.py index 431c71473..633dd8716 100644 --- a/dateparser/data/date_translation_data/vun.py +++ b/dateparser/data/date_translation_data/vun.py @@ -95,6 +95,7 @@ "mfiri" ], "hour": [ + "hr", "saa" ], "minute": [ diff --git a/dateparser/data/date_translation_data/wae.py b/dateparser/data/date_translation_data/wae.py index e24dd1176..614eb62c5 100644 --- a/dateparser/data/date_translation_data/wae.py +++ b/dateparser/data/date_translation_data/wae.py @@ -96,7 +96,8 @@ "tag" ], "hour": [ - "schtund" + "schtund", + "stunde" ], "minute": [ "mínütta" @@ -153,57 +154,57 @@ }, "relative-type-regex": { "\\1 day ago": [ - "vor (\\d+[.,]?\\d*) tag", - "vor (\\d+[.,]?\\d*) täg" + "vor (\\d++[.,]?\\d*+) tag", + "vor (\\d++[.,]?\\d*+) täg" ], "\\1 hour ago": [ - "vor (\\d+[.,]?\\d*) stund", - "vor (\\d+[.,]?\\d*) stunde" + "vor (\\d++[.,]?\\d*+) stund", + "vor (\\d++[.,]?\\d*+) stunde" ], "\\1 minute ago": [ - "vor (\\d+[.,]?\\d*) minüta", - "vor (\\d+[.,]?\\d*) minüte" + "vor (\\d++[.,]?\\d*+) minüta", + "vor (\\d++[.,]?\\d*+) minüte" ], "\\1 month ago": [ - "vor (\\d+[.,]?\\d*) mánet" + "vor (\\d++[.,]?\\d*+) mánet" ], "\\1 second ago": [ - "vor (\\d+[.,]?\\d*) sekund", - "vor (\\d+[.,]?\\d*) sekunde" + "vor (\\d++[.,]?\\d*+) sekund", + "vor (\\d++[.,]?\\d*+) sekunde" ], "\\1 week ago": [ - "cor (\\d+[.,]?\\d*) wučä", - "vor (\\d+[.,]?\\d*) wuča" + "cor (\\d++[.,]?\\d*+) wučä", + "vor (\\d++[.,]?\\d*+) wuča" ], "\\1 year ago": [ - "cor (\\d+[.,]?\\d*) jár", - "vor (\\d+[.,]?\\d*) jár" + "cor (\\d++[.,]?\\d*+) jár", + "vor (\\d++[.,]?\\d*+) jár" ], "in \\1 day": [ - "i (\\d+[.,]?\\d*) tag", - "i (\\d+[.,]?\\d*) täg" + "i (\\d++[.,]?\\d*+) tag", + "i (\\d++[.,]?\\d*+) täg" ], "in \\1 hour": [ - "i (\\d+[.,]?\\d*) stund", - "i (\\d+[.,]?\\d*) stunde" + "i (\\d++[.,]?\\d*+) stund", + "i (\\d++[.,]?\\d*+) stunde" ], "in \\1 minute": [ - "i (\\d+[.,]?\\d*) minüta", - "i (\\d+[.,]?\\d*) minüte" + "i (\\d++[.,]?\\d*+) minüta", + "i (\\d++[.,]?\\d*+) minüte" ], "in \\1 month": [ - "i (\\d+[.,]?\\d*) mánet" + "i (\\d++[.,]?\\d*+) mánet" ], "in \\1 second": [ - "i (\\d+[.,]?\\d*) sekund", - "i (\\d+[.,]?\\d*) sekunde" + "i (\\d++[.,]?\\d*+) sekund", + "i (\\d++[.,]?\\d*+) sekunde" ], "in \\1 week": [ - "i (\\d+[.,]?\\d*) wuča", - "i (\\d+[.,]?\\d*) wučä" + "i (\\d++[.,]?\\d*+) wuča", + "i (\\d++[.,]?\\d*+) wučä" ], "in \\1 year": [ - "i (\\d+[.,]?\\d*) jár" + "i (\\d++[.,]?\\d*+) jár" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/xog.py b/dateparser/data/date_translation_data/xog.py index 125158899..e30aa5949 100644 --- a/dateparser/data/date_translation_data/xog.py +++ b/dateparser/data/date_translation_data/xog.py @@ -96,7 +96,8 @@ "olunaku" ], "hour": [ - "essawa" + "essawa", + "hr" ], "minute": [ "edakiika" diff --git a/dateparser/data/date_translation_data/yav.py b/dateparser/data/date_translation_data/yav.py index f59defcd5..24b76d278 100644 --- a/dateparser/data/date_translation_data/yav.py +++ b/dateparser/data/date_translation_data/yav.py @@ -96,6 +96,7 @@ "puɔ́sɛ́" ], "hour": [ + "hr", "kisikɛl," ], "minute": [ diff --git a/dateparser/data/date_translation_data/yi.py b/dateparser/data/date_translation_data/yi.py index 6d10a8935..a93450b8b 100644 --- a/dateparser/data/date_translation_data/yi.py +++ b/dateparser/data/date_translation_data/yi.py @@ -85,6 +85,7 @@ "טאָג" ], "hour": [ + "hr", "שעה" ], "minute": [ @@ -142,22 +143,22 @@ }, "relative-type-regex": { "\\1 month ago": [ - "פֿאַר (\\d+[.,]?\\d*) חדשים", - "פֿאַר (\\d+[.,]?\\d*) חודש" + "פֿאַר (\\d++[.,]?\\d*+) חדשים", + "פֿאַר (\\d++[.,]?\\d*+) חודש" ], "\\1 year ago": [ - "פֿאַר (\\d+[.,]?\\d*) יאָר" + "פֿאַר (\\d++[.,]?\\d*+) יאָר" ], "in \\1 day": [ - "אין (\\d+[.,]?\\d*) טאָג אַרום", - "אין (\\d+[.,]?\\d*) טעג אַרום" + "אין (\\d++[.,]?\\d*+) טאָג אַרום", + "אין (\\d++[.,]?\\d*+) טעג אַרום" ], "in \\1 month": [ - "איבער (\\d+[.,]?\\d*) חדשים", - "איבער (\\d+[.,]?\\d*) חודש" + "איבער (\\d++[.,]?\\d*+) חדשים", + "איבער (\\d++[.,]?\\d*+) חודש" ], "in \\1 year": [ - "איבער (\\d+[.,]?\\d*) יאָר" + "איבער (\\d++[.,]?\\d*+) יאָר" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/yo.py b/dateparser/data/date_translation_data/yo.py index a33322489..7ba3009cf 100644 --- a/dateparser/data/date_translation_data/yo.py +++ b/dateparser/data/date_translation_data/yo.py @@ -3,75 +3,106 @@ "date_order": "DMY", "january": [ "oṣù ṣẹ́rẹ́", + "ṣẹ́", + "ṣẹ́r", "ṣẹ́rẹ́" ], "february": [ "oṣù èrèlè", + "èr", + "èrèl", "èrèlè" ], "march": [ "oṣù ẹrẹ̀nà", + "ẹr", + "ẹrẹ̀n", "ẹrẹ̀nà" ], "april": [ "oṣù ìgbé", + "ìg", + "ìgb", "ìgbé" ], "may": [ "oṣù ẹ̀bibi", + "ẹ̀b", + "ẹ̀bi", "ẹ̀bibi" ], "june": [ "oṣù òkúdu", + "òk", + "òkú", "òkúdu" ], "july": [ + "ag", + "agẹ", "agẹmọ", "oṣù agẹmọ" ], "august": [ "oṣù ògún", + "òg", + "ògú", "ògún" ], "september": [ + "ow", + "owe", "owewe", "oṣù owewe" ], "october": [ "oṣù ọ̀wàrà", + "ọ̀w", + "ọ̀wà", "ọ̀wàrà" ], "november": [ + "bé", + "bél", "bélú", "oṣù bélú" ], "december": [ "oṣù ọ̀pẹ̀", + "ọ̀p", + "ọ̀pẹ", "ọ̀pẹ̀" ], "monday": [ + "aj", "ajé", "ọjọ́ ajé" ], "tuesday": [ + "ìsẹ́g", "ìsẹ́gun", "ọjọ́ ìsẹ́gun" ], "wednesday": [ + "ọjọ́r", "ọjọ́rú" ], "thursday": [ + "ọjọ́b", "ọjọ́bọ" ], "friday": [ + "ẹt", "ẹtì", "ọjọ́ ẹtì" ], "saturday": [ + "àbám", "àbámẹ́ta", "ọjọ́ àbámẹ́ta" ], "sunday": [ + "àìk", "àìkú", "ọjọ́ àìkú" ], @@ -85,15 +116,18 @@ "ọdún" ], "month": [ - "osù" + "osù", + "oṣù" ], "week": [ + "ọ̀sẹ̀", "ọ̀sè" ], "day": [ "ọjọ́" ], "hour": [ + "wkt", "wákàtí" ], "minute": [ @@ -113,39 +147,51 @@ "this minute" ], "0 month ago": [ + "oṣù yìí", "this month" ], "0 second ago": [ "now" ], "0 week ago": [ + "ọ̀sẹ̀ yìí", "this week" ], "0 year ago": [ + "ọdún yìí", + "ọdúnǹí", "this year" ], "1 day ago": [ "àná" ], "1 month ago": [ + "óṣù tó kọjá", "last month" ], "1 week ago": [ + "ọ̀sẹ̀ tó kọjá", "last week" ], "1 year ago": [ + "èṣín", + "ọdún tó kọjá", "last year" ], "in 1 day": [ "ọ̀la" ], "in 1 month": [ + "óṣù tó ń bọ̀,", "next month" ], "in 1 week": [ + "ọ́sẹ̀ tó ń bọ̀", "next week" ], "in 1 year": [ + "àmọ́dún", + "ọdún tó ńbọ̀", "next year" ] }, @@ -154,6 +200,8 @@ "name": "yo-BJ", "january": [ "oshù shɛ́rɛ́", + "shɛ́", + "shɛ́r", "shɛ́rɛ́" ], "february": [ @@ -161,6 +209,8 @@ ], "march": [ "oshù ɛrɛ̀nà", + "ɛr", + "ɛrɛ̀n", "ɛrɛ̀nà" ], "april": [ @@ -168,12 +218,15 @@ ], "may": [ "oshù ɛ̀bibi", + "ɛ̀b", + "ɛ̀bi", "ɛ̀bibi" ], "june": [ "oshù òkúdu" ], "july": [ + "agɛ", "agɛmɔ", "oshù agɛmɔ" ], @@ -185,6 +238,8 @@ ], "october": [ "oshù ɔ̀wàrà", + "ɔ̀w", + "ɔ̀wà", "ɔ̀wàrà" ], "november": [ @@ -192,23 +247,29 @@ ], "december": [ "oshù ɔ̀pɛ̀", + "ɔ̀p", + "ɔ̀pɛ", "ɔ̀pɛ̀" ], "monday": [ "ɔjɔ́ ajé" ], "tuesday": [ + "ìsɛ́g", "ìsɛ́gun", "ɔjɔ́ ìsɛ́gun" ], "wednesday": [ + "ɔjɔ́r", "ɔjɔ́rú" ], "thursday": [ + "ɔjɔ́b", "ɔjɔ́bɔ" ], "friday": [ "ɔjɔ́ ɛtì", + "ɛt", "ɛtì" ], "saturday": [ @@ -227,7 +288,11 @@ "year": [ "ɔdún" ], + "month": [ + "oshù" + ], "week": [ + "ɔ̀sɛ̀", "ɔ̀sè" ], "day": [ @@ -240,8 +305,38 @@ "ìsɛ́jú ààyá" ], "relative-type": { + "0 month ago": [ + "oshù yìí" + ], + "0 week ago": [ + "ɔ̀sɛ̀ yìí" + ], + "0 year ago": [ + "ɔdún yìí", + "ɔdúnǹí" + ], + "1 month ago": [ + "óshù tó kɔjá" + ], + "1 week ago": [ + "ɔ̀sɛ̀ tó kɔjá" + ], + "1 year ago": [ + "èshín", + "ɔdún tó kɔjá" + ], "in 1 day": [ "ɔ̀la" + ], + "in 1 month": [ + "óshù tó ń bɔ̀," + ], + "in 1 week": [ + "ɔ́sɛ̀ tó ń bɔ̀" + ], + "in 1 year": [ + "àmɔ́dún", + "ɔdún tó ńbɔ̀" ] } } diff --git a/dateparser/data/date_translation_data/yue.py b/dateparser/data/date_translation_data/yue.py index aabf0ec61..207726931 100644 --- a/dateparser/data/date_translation_data/yue.py +++ b/dateparser/data/date_translation_data/yue.py @@ -141,46 +141,46 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) 日前" + "(\\d++[.,]?\\d*+) 日前" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) 小時前" + "(\\d++[.,]?\\d*+) 小時前" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) 分鐘前" + "(\\d++[.,]?\\d*+) 分鐘前" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) 個月前" + "(\\d++[.,]?\\d*+) 個月前" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) 秒前" + "(\\d++[.,]?\\d*+) 秒前" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) 個星期前" + "(\\d++[.,]?\\d*+) 個星期前" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) 年前" + "(\\d++[.,]?\\d*+) 年前" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) 日後" + "(\\d++[.,]?\\d*+) 日後" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) 小時後" + "(\\d++[.,]?\\d*+) 小時後" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) 分鐘後" + "(\\d++[.,]?\\d*+) 分鐘後" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) 個月後" + "(\\d++[.,]?\\d*+) 個月後" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) 秒後" + "(\\d++[.,]?\\d*+) 秒後" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) 個星期後" + "(\\d++[.,]?\\d*+) 個星期後" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) 年後" + "(\\d++[.,]?\\d*+) 年後" ] }, "locale_specific": {}, diff --git a/dateparser/data/date_translation_data/zgh.py b/dateparser/data/date_translation_data/zgh.py index 06337d547..a2542f50f 100644 --- a/dateparser/data/date_translation_data/zgh.py +++ b/dateparser/data/date_translation_data/zgh.py @@ -96,6 +96,7 @@ "ⴰⵙⵙ" ], "hour": [ + "hr", "ⵜⴰⵙⵔⴰⴳⵜ" ], "minute": [ diff --git a/dateparser/data/date_translation_data/zh-Hans.py b/dateparser/data/date_translation_data/zh-Hans.py index af855eeaf..c92e9cbb1 100644 --- a/dateparser/data/date_translation_data/zh-Hans.py +++ b/dateparser/data/date_translation_data/zh-Hans.py @@ -163,48 +163,48 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*)天前" + "(\\d++[.,]?\\d*+)天前" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*)小时前" + "(\\d++[.,]?\\d*+)小时前" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*)分钟前" + "(\\d++[.,]?\\d*+)分钟前" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*)个月前" + "(\\d++[.,]?\\d*+)个月前" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*)秒前", - "(\\d+[.,]?\\d*)秒钟前" + "(\\d++[.,]?\\d*+)秒前", + "(\\d++[.,]?\\d*+)秒钟前" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*)周前" + "(\\d++[.,]?\\d*+)周前" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*)年前" + "(\\d++[.,]?\\d*+)年前" ], "in \\1 day": [ - "(\\d+[.,]?\\d*)天后" + "(\\d++[.,]?\\d*+)天后" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*)小时后" + "(\\d++[.,]?\\d*+)小时后" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*)分钟后" + "(\\d++[.,]?\\d*+)分钟后" ], "in \\1 month": [ - "(\\d+[.,]?\\d*)个月后" + "(\\d++[.,]?\\d*+)个月后" ], "in \\1 second": [ - "(\\d+[.,]?\\d*)秒后", - "(\\d+[.,]?\\d*)秒钟后" + "(\\d++[.,]?\\d*+)秒后", + "(\\d++[.,]?\\d*+)秒钟后" ], "in \\1 week": [ - "(\\d+[.,]?\\d*)周后" + "(\\d++[.,]?\\d*+)周后" ], "in \\1 year": [ - "(\\d+[.,]?\\d*)年后" + "(\\d++[.,]?\\d*+)年后" ] }, "locale_specific": { diff --git a/dateparser/data/date_translation_data/zh-Hant.py b/dateparser/data/date_translation_data/zh-Hant.py index 9a51ecd32..adf523cfd 100644 --- a/dateparser/data/date_translation_data/zh-Hant.py +++ b/dateparser/data/date_translation_data/zh-Hant.py @@ -141,46 +141,46 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) 天前" + "(\\d++[.,]?\\d*+) 天前" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) 小時前" + "(\\d++[.,]?\\d*+) 小時前" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) 分鐘前" + "(\\d++[.,]?\\d*+) 分鐘前" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) 個月前" + "(\\d++[.,]?\\d*+) 個月前" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) 秒前" + "(\\d++[.,]?\\d*+) 秒前" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) 週前" + "(\\d++[.,]?\\d*+) 週前" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) 年前" + "(\\d++[.,]?\\d*+) 年前" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) 天後" + "(\\d++[.,]?\\d*+) 天後" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*) 小時後" + "(\\d++[.,]?\\d*+) 小時後" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*) 分鐘後" + "(\\d++[.,]?\\d*+) 分鐘後" ], "in \\1 month": [ - "(\\d+[.,]?\\d*) 個月後" + "(\\d++[.,]?\\d*+) 個月後" ], "in \\1 second": [ - "(\\d+[.,]?\\d*) 秒後" + "(\\d++[.,]?\\d*+) 秒後" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) 週後" + "(\\d++[.,]?\\d*+) 週後" ], "in \\1 year": [ - "(\\d+[.,]?\\d*) 年後" + "(\\d++[.,]?\\d*+) 年後" ] }, "locale_specific": { @@ -212,9 +212,6 @@ "1 day ago": [ "昨日" ], - "1 month ago": [ - "上月" - ], "1 week ago": [ "上星期" ], @@ -224,62 +221,67 @@ "in 1 day": [ "明日" ], - "in 1 month": [ - "下月" - ], "in 1 week": [ "下星期" ], "in 1 year": [ "下年" + ], + "1 month ago": [ + "上月" + ], + "in 1 month": [ + "下月" ] }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) 日前", - "(\\d+[.,]?\\d*)日前" + "(\\d++[.,]?\\d*+) 日前", + "(\\d++[.,]?\\d*+)日前" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*)小時前" + "(\\d++[.,]?\\d*+)小時前" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*)分前" + "(\\d++[.,]?\\d*+)分前" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*)個月前" + "(\\d++[.,]?\\d*+)個月前" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*)秒前" + "(\\d++[.,]?\\d*+)秒前" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) 星期前", - "(\\d+[.,]?\\d*)週前" + "(\\d++[.,]?\\d*+) 星期前", + "(\\d++[.,]?\\d*+)星期前", + "(\\d++[.,]?\\d*+)週前" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*)年前" + "(\\d++[.,]?\\d*+)年前" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) 日後", - "(\\d+[.,]?\\d*)日後" + "(\\d++[.,]?\\d*+) 日後", + "(\\d++[.,]?\\d*+)日後" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*)小時後" + "(\\d++[.,]?\\d*+)小時後" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*)分後" + "(\\d++[.,]?\\d*+)分後" ], "in \\1 month": [ - "(\\d+[.,]?\\d*)個月後" + "(\\d++[.,]?\\d*+)個月後" ], "in \\1 second": [ - "(\\d+[.,]?\\d*)秒後" + "(\\d++[.,]?\\d*+)秒後" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) 星期後", - "(\\d+[.,]?\\d*)週後" + "(\\d++[.,]?\\d*+) 星期後", + "(\\d++[.,]?\\d*+)星期後", + "(\\d++[.,]?\\d*+)週後" ], "in \\1 year": [ - "(\\d+[.,]?\\d*)年後" + "(\\d++[.,]?\\d*+)年後" ] } }, @@ -311,9 +313,6 @@ "1 day ago": [ "昨日" ], - "1 month ago": [ - "上月" - ], "1 week ago": [ "上星期" ], @@ -323,62 +322,67 @@ "in 1 day": [ "明日" ], - "in 1 month": [ - "下月" - ], "in 1 week": [ "下星期" ], "in 1 year": [ "下年" + ], + "1 month ago": [ + "上月" + ], + "in 1 month": [ + "下月" ] }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) 日前", - "(\\d+[.,]?\\d*)日前" + "(\\d++[.,]?\\d*+) 日前", + "(\\d++[.,]?\\d*+)日前" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*)小時前" + "(\\d++[.,]?\\d*+)小時前" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*)分前" + "(\\d++[.,]?\\d*+)分前" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*)個月前" + "(\\d++[.,]?\\d*+)個月前" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*)秒前" + "(\\d++[.,]?\\d*+)秒前" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*) 星期前", - "(\\d+[.,]?\\d*)週前" + "(\\d++[.,]?\\d*+) 星期前", + "(\\d++[.,]?\\d*+)星期前", + "(\\d++[.,]?\\d*+)週前" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*)年前" + "(\\d++[.,]?\\d*+)年前" ], "in \\1 day": [ - "(\\d+[.,]?\\d*) 日後", - "(\\d+[.,]?\\d*)日後" + "(\\d++[.,]?\\d*+) 日後", + "(\\d++[.,]?\\d*+)日後" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*)小時後" + "(\\d++[.,]?\\d*+)小時後" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*)分後" + "(\\d++[.,]?\\d*+)分後" ], "in \\1 month": [ - "(\\d+[.,]?\\d*)個月後" + "(\\d++[.,]?\\d*+)個月後" ], "in \\1 second": [ - "(\\d+[.,]?\\d*)秒後" + "(\\d++[.,]?\\d*+)秒後" ], "in \\1 week": [ - "(\\d+[.,]?\\d*) 星期後", - "(\\d+[.,]?\\d*)週後" + "(\\d++[.,]?\\d*+) 星期後", + "(\\d++[.,]?\\d*+)星期後", + "(\\d++[.,]?\\d*+)週後" ], "in \\1 year": [ - "(\\d+[.,]?\\d*)年後" + "(\\d++[.,]?\\d*+)年後" ] } } diff --git a/dateparser/data/date_translation_data/zh.py b/dateparser/data/date_translation_data/zh.py index 6a5ad288e..a5966426f 100644 --- a/dateparser/data/date_translation_data/zh.py +++ b/dateparser/data/date_translation_data/zh.py @@ -176,48 +176,48 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*)天前" + "(\\d++[.,]?\\d*+)天前" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*)小时前" + "(\\d++[.,]?\\d*+)小时前" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*)分钟前" + "(\\d++[.,]?\\d*+)分钟前" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*)个月前" + "(\\d++[.,]?\\d*+)个月前" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*)秒前", - "(\\d+[.,]?\\d*)秒钟前" + "(\\d++[.,]?\\d*+)秒前", + "(\\d++[.,]?\\d*+)秒钟前" ], "\\1 week ago": [ - "(\\d+[.,]?\\d*)周前" + "(\\d++[.,]?\\d*+)周前" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*)年前" + "(\\d++[.,]?\\d*+)年前" ], "in \\1 day": [ - "(\\d+[.,]?\\d*)天后" + "(\\d++[.,]?\\d*+)天后" ], "in \\1 hour": [ - "(\\d+[.,]?\\d*)小时后" + "(\\d++[.,]?\\d*+)小时后" ], "in \\1 minute": [ - "(\\d+[.,]?\\d*)分钟后" + "(\\d++[.,]?\\d*+)分钟后" ], "in \\1 month": [ - "(\\d+[.,]?\\d*)个月后" + "(\\d++[.,]?\\d*+)个月后" ], "in \\1 second": [ - "(\\d+[.,]?\\d*)秒后", - "(\\d+[.,]?\\d*)秒钟后" + "(\\d++[.,]?\\d*+)秒后", + "(\\d++[.,]?\\d*+)秒钟后" ], "in \\1 week": [ - "(\\d+[.,]?\\d*)周后" + "(\\d++[.,]?\\d*+)周后" ], "in \\1 year": [ - "(\\d+[.,]?\\d*)年后" + "(\\d++[.,]?\\d*+)年后" ] }, "locale_specific": {}, @@ -249,25 +249,25 @@ "半小时前": "30分前" }, { - "(?:中午|下午|(?:晚上?))(?:\\s*)(\\d+[.,]?\\d*)(?:\\s*):(?:\\s+|:)?(\\d+[.,]?\\d*)": "\\1:\\2 pm" + "(?:中午|下午|(?:晚上?))(?:\\s*)(\\d++[.,]?\\d*+)(?:\\s*):(?:\\s+|:)?(\\d++[.,]?\\d*+(?::\\d++[.,]?\\d*+)?)": "\\1:\\2 pm" }, { - "(?:上午|早上|凌晨)(?:\\s*)(\\d+[.,]?\\d*)(?:\\s*):(?:\\s+|:)?(\\d+[.,]?\\d*)": "\\1:\\2 am" + "(?:上午|早上|凌晨)(?:\\s*)(\\d++[.,]?\\d*+)(?:\\s*):(?:\\s+|:)?(\\d++[.,]?\\d*+(?::\\d++[.,]?\\d*+)?)": "\\1:\\2 am" }, { "中午": "12:00" }, { - "(\\d+[.,]?\\d*)年(?:\\s+)?(\\d+[.,]?\\d*)月(?:\\s+)?(\\d+[.,]?\\d*)日(?:\\s+)?(\\d+[.,]?\\d*)时(?:\\s+)?(\\d+[.,]?\\d*)分": "\\1-\\2-\\3 \\4:\\5" + "(\\d++[.,]?\\d*+)\\s*年\\s*(\\d++[.,]?\\d*+)\\s*月\\s*(\\d++[.,]?\\d*+)\\s*日\\s*(\\d++[.,]?\\d*+)\\s*时\\s*(\\d++[.,]?\\d*+)\\s*分": "\\1-\\2-\\3 \\4:\\5" }, { - "(\\d+[.,]?\\d*)年(?:\\s+)?(\\d+[.,]?\\d*)月(?:\\s+)?(\\d{1,2})(?:日)?(?:\\s+)?(\\d{1,2})(?:点|:)(\\d{1,2})": "\\1-\\2-\\3 \\4:\\5" + "(\\d++[.,]?\\d*+)\\s*年\\s*(\\d++[.,]?\\d*+)\\s*月\\s*(\\d{1,2})\\s*(?:日)?\\s*(\\d{1,2})\\s*(?:点|:)\\s*(\\d{1,2})": "\\1-\\2-\\3 \\4:\\5" }, { - "(\\d+[.,]?\\d*)年(?:\\s+)?(\\d+[.,]?\\d*)月(?:\\s+)?(\\d{1,2})(?:日)?": "\\1-\\2-\\3" + "(\\d++[.,]?\\d*+)\\s*年\\s*(\\d++[.,]?\\d*+)\\s*月\\s*(\\d{1,2})\\s*(?:日)?": "\\1-\\2-\\3" }, { - "(\\d+[.,]?\\d*)月(?=.*[前后])": "\\1 月" + "(\\d++[.,]?\\d*+)月(?=.*[前后])": "\\1 月" } ] } diff --git a/dateparser/data/date_translation_data/zu.py b/dateparser/data/date_translation_data/zu.py index 5c6c8d931..ae4fa914e 100644 --- a/dateparser/data/date_translation_data/zu.py +++ b/dateparser/data/date_translation_data/zu.py @@ -97,6 +97,7 @@ "usuku" ], "hour": [ + "amahora", "ihora" ], "minute": [ @@ -154,28 +155,28 @@ }, "relative-type-regex": { "\\1 day ago": [ - "(\\d+[.,]?\\d*) izinsuku ezedlule", - "(\\d+[.,]?\\d*) usuku olwedlule" + "(\\d++[.,]?\\d*+) izinsuku ezedlule", + "(\\d++[.,]?\\d*+) usuku olwedlule" ], "\\1 hour ago": [ - "(\\d+[.,]?\\d*) amahora edlule", - "(\\d+[.,]?\\d*) ihora eledlule" + "(\\d++[.,]?\\d*+) amahora edlule", + "(\\d++[.,]?\\d*+) ihora eledlule" ], "\\1 minute ago": [ - "(\\d+[.,]?\\d*) amaminithi edlule", - "(\\d+[.,]?\\d*) iminithi eledlule" + "(\\d++[.,]?\\d*+) amaminithi edlule", + "(\\d++[.,]?\\d*+) iminithi eledlule" ], "\\1 month ago": [ - "(\\d+[.,]?\\d*) inyanga edlule", - "(\\d+[.,]?\\d*) izinyanga ezedlule" + "(\\d++[.,]?\\d*+) inyanga edlule", + "(\\d++[.,]?\\d*+) izinyanga ezedlule" ], "\\1 second ago": [ - "(\\d+[.,]?\\d*) amasekhondi edlule", - "(\\d+[.,]?\\d*) isekhondi eledlule" + "(\\d++[.,]?\\d*+) amasekhondi edlule", + "(\\d++[.,]?\\d*+) isekhondi eledlule" ], "\\1 year ago": [ - "(\\d+[.,]?\\d*) iminyaka edlule", - "(\\d+[.,]?\\d*) unyaka odlule" + "(\\d++[.,]?\\d*+) iminyaka edlule", + "(\\d++[.,]?\\d*+) unyaka odlule" ] }, "locale_specific": {}, diff --git a/dateparser/data/dateparser_tz_cache.pkl b/dateparser/data/dateparser_tz_cache.pkl deleted file mode 100644 index 4eac858ab..000000000 Binary files a/dateparser/data/dateparser_tz_cache.pkl and /dev/null differ diff --git a/dateparser/data/languages_info.py b/dateparser/data/languages_info.py index 9d0f3d475..fa72c2f5c 100644 --- a/dateparser/data/languages_info.py +++ b/dateparser/data/languages_info.py @@ -496,6 +496,7 @@ "en-TZ", "en-UG", "en-UM", + "en-US", "en-VC", "en-VG", "en-VI", diff --git a/dateparser/date.py b/dateparser/date.py index e23444720..fdfa8ec39 100644 --- a/dateparser/date.py +++ b/dateparser/date.py @@ -1,26 +1,43 @@ import collections -from collections.abc import Set -from datetime import datetime, timedelta +import functools +import itertools +import threading +from collections.abc import Callable, Iterable, Iterator +from collections.abc import Set as AbstractSet +from datetime import date, datetime, timedelta, tzinfo +from itertools import count +from typing import TYPE_CHECKING, Any, TypeGuard, TypeVar import regex as re from dateutil.relativedelta import relativedelta -from tzlocal import get_localzone -from dateparser.conf import apply_settings, check_settings +from dateparser._parts_of_day import PartOfDay, _replace_part_of_day +from dateparser.conf import Settings, apply_settings, check_settings from dateparser.custom_language_detection.language_mapping import map_languages from dateparser.date_parser import date_parser from dateparser.freshness_date_parser import freshness_date_parser from dateparser.languages.loader import LocaleDataLoader -from dateparser.parser import _parse_absolute, _parse_nospaces +from dateparser.parser import _parse_absolute, _parse_nospaces, _StrictDateOrderError from dateparser.timezone_parser import pop_tz_offset_from_string from dateparser.utils import ( + _get_localzone, + _get_missing_parts, + _get_parts, + _now, apply_timezone_from_settings, + get_next_leap_year, + get_previous_leap_year, get_timezone_from_tz_string, set_correct_day_from_settings, set_correct_month_from_settings, ) from dateparser.utils.strptime import strptime as patched_strptime +if TYPE_CHECKING: + from dateparser.languages.locale import Locale + +_D = TypeVar("_D", bound=date) + APOSTROPHE_LOOK_ALIKE_CHARS = [ "\N{RIGHT SINGLE QUOTATION MARK}", # '\u2019' "\N{MODIFIER LETTER APOSTROPHE}", # '\u02bc' @@ -33,6 +50,44 @@ "\N{FULLWIDTH APOSTROPHE}", # '\uff07' ] +# Unicode Dash Characters, per the "Dash" property table in the Unicode Standard +# (https://www.unicode.org/versions/latest/core-spec/chapter-6/#G9697), excluding +# U+002D HYPHEN-MINUS itself. Written as \u/\U escapes rather than \N{...} names +# since some of these (e.g. Garay Hyphen, Yezidi Hyphenation Mark) are recent +# Unicode additions not present in the unicodedata name tables of older Pythons. +DASH_LOOK_ALIKE_CHARS = [ + "\u058a", # ARMENIAN HYPHEN + "\u05be", # HEBREW PUNCTUATION MAQAF + "\u1400", # CANADIAN SYLLABICS HYPHEN + "\u1806", # MONGOLIAN TODO SOFT HYPHEN + "\u2010", # HYPHEN + "\u2011", # NON-BREAKING HYPHEN + "\u2012", # FIGURE DASH + "\u2013", # EN DASH + "\u2014", # EM DASH + "\u2015", # HORIZONTAL BAR + "\u2053", # SWUNG DASH + "\u207b", # SUPERSCRIPT MINUS + "\u208b", # SUBSCRIPT MINUS + "\u2212", # MINUS SIGN + "\u2e17", # DOUBLE OBLIQUE HYPHEN + "\u2e1a", # HYPHEN WITH DIAERESIS + "\u2e3a", # TWO-EM DASH + "\u2e3b", # THREE-EM DASH + "\u2e40", # DOUBLE HYPHEN + "\u2e5d", # OBLIQUE HYPHEN + "\u301c", # WAVE DASH + "\u3030", # WAVY DASH + "\u30a0", # KATAKANA-HIRAGANA DOUBLE HYPHEN + "\ufe31", # PRESENTATION FORM FOR VERTICAL EM DASH + "\ufe32", # PRESENTATION FORM FOR VERTICAL EN DASH + "\ufe58", # SMALL EM DASH + "\ufe63", # SMALL HYPHEN-MINUS + "\uff0d", # FULLWIDTH HYPHEN-MINUS + "\U00010d6e", # GARAY HYPHEN + "\U00010ead", # YEZIDI HYPHENATION MARK +] + RE_NBSP = re.compile("\xa0", flags=re.UNICODE) RE_SPACES = re.compile(r"\s+") RE_TRIM_SPACES = re.compile(r"^\s+(\S.*?)\s+$") @@ -46,21 +101,36 @@ r"(\d+)\.\s?(\d+)\.\s?(\d+)\.( u)?", flags=re.I | re.U ) RE_SANITIZE_PERIOD = re.compile(r"(?<=[^0-9\s])\.", flags=re.U) +RE_SANITIZE_DECIMAL_COMMA = re.compile(r"(?<=\d:\d{2}:\d{2}),(?=\d{3})") RE_SANITIZE_ON = re.compile(r"^.*?on:\s+(.*)") RE_SANITIZE_APOSTROPHE = re.compile("|".join(APOSTROPHE_LOOK_ALIKE_CHARS)) +RE_SANITIZE_DASH = re.compile("|".join(DASH_LOOK_ALIKE_CHARS)) +# Uppercase Roman numerals from 1000 on, allowing the additive IIII, XXXX and +# CCCC of old prints. +_RE_ROMAN_YEAR = re.compile( + r"\bM{1,3}(?:CM|CD|D?C{0,4})(?:XC|XL|L?X{0,4})(?:IX|IV|V?I{0,4})\b" +) +_ROMAN_NUMERAL_VALUES = { + "M": 1000, + "D": 500, + "C": 100, + "L": 50, + "X": 10, + "V": 5, + "I": 1, +} RE_SEARCH_TIMESTAMP = re.compile(r"^(\d{10})(\d{3})?(\d{3})?(?![^.])") RE_SEARCH_NEGATIVE_TIMESTAMP = re.compile(r"^([-]\d{10})(\d{3})?(\d{3})?(?![^.])") -def sanitize_spaces(date_string): +def sanitize_spaces(date_string: str) -> str: date_string = RE_NBSP.sub(" ", date_string) date_string = RE_SPACES.sub(" ", date_string) - date_string = RE_TRIM_SPACES.sub(r"\1", date_string) - return date_string + return RE_TRIM_SPACES.sub(r"\1", date_string) -def date_range(begin, end, **kwargs): +def date_range(begin: _D, end: _D, **kwargs: Any) -> Iterator[_D]: dateutil_error_prone_args = [ "year", "month", @@ -72,7 +142,7 @@ def date_range(begin, end, **kwargs): ] for arg in dateutil_error_prone_args: if arg in kwargs: - raise ValueError("Invalid argument: %s" % arg) + raise ValueError(f"Invalid argument: {arg}") step = relativedelta(**kwargs) if kwargs else relativedelta(days=1) @@ -86,7 +156,7 @@ def date_range(begin, end, **kwargs): yield end -def get_intersecting_periods(low, high, period="day"): +def get_intersecting_periods(low: _D, high: _D, period: str = "day") -> Iterator[_D]: if period not in [ "year", "month", @@ -97,16 +167,17 @@ def get_intersecting_periods(low, high, period="day"): "second", "microsecond", ]: - raise ValueError("Invalid period: {}".format(period)) + raise ValueError(f"Invalid period: {period}") if high <= low: return - step = relativedelta(**{period + "s": 1}) + step_kwargs: dict[str, Any] = {period + "s": 1} + step = relativedelta(**step_kwargs) current_period_start = low if isinstance(current_period_start, datetime): - reset_arguments = {} + reset_arguments: dict[str, Any] = {} for test_period in ["microsecond", "second", "minute", "hour"]: if test_period == period: break @@ -128,7 +199,7 @@ def get_intersecting_periods(low, high, period="day"): current_period_start += step -def sanitize_date(date_string): +def sanitize_date(date_string: str) -> str: date_string = RE_SANITIZE_SKIP.sub(" ", date_string) date_string = RE_SANITIZE_RUSSIAN.sub( r"\1 ", date_string @@ -138,14 +209,32 @@ def sanitize_date(date_string): ) # extra '.' and 'u' interferes with parsing relative fractional dates date_string = sanitize_spaces(date_string) date_string = RE_SANITIZE_PERIOD.sub("", date_string) + date_string = _RE_ROMAN_YEAR.sub(_roman_year_to_digits, date_string) + date_string = RE_SANITIZE_DECIMAL_COMMA.sub(".", date_string) date_string = RE_SANITIZE_ON.sub(r"\1", date_string) date_string = RE_TRIM_COLONS.sub(r"\1", date_string) date_string = RE_SANITIZE_APOSTROPHE.sub("'", date_string) - date_string = date_string.strip() - return date_string + date_string = RE_SANITIZE_DASH.sub("-", date_string) + return date_string.strip() + + +def _roman_year_to_digits(match: re.Match[str]) -> str: + numeral = match[0] + # Too ambiguous with abbreviations like MD or MC. + if len(numeral) < 3: + return numeral + values = [_ROMAN_NUMERAL_VALUES[char] for char in numeral] + return str( + sum( + -value if value < next_value else value + for value, next_value in zip(values, [*values[1:], 0], strict=True) + ) + ) -def get_date_from_timestamp(date_string, settings, negative=False): +def get_date_from_timestamp( + date_string: str, settings: Settings | None, negative: bool = False +) -> datetime | None: if negative: match = RE_SEARCH_NEGATIVE_TIMESTAMP.search(date_string) else: @@ -159,7 +248,7 @@ def get_date_from_timestamp(date_string, settings, negative=False): ): # If the timezone in settings is unset, or it's 'local', use the # local timezone - timezone = get_localzone() + timezone: tzinfo = _get_localzone() else: # Otherwise, use the timezone given in settings timezone = get_timezone_from_tz_string(settings.TIMEZONE) @@ -170,11 +259,46 @@ def get_date_from_timestamp(date_string, settings, negative=False): date_obj = datetime.fromtimestamp(seconds, timezone).replace( microsecond=millis * 1000 + micros, tzinfo=None ) - date_obj = apply_timezone_from_settings(date_obj, settings) + return apply_timezone_from_settings(date_obj, settings) + return None + + +def _apply_century_preference( + date_obj: datetime, now: datetime, prefer_from: str +) -> datetime: + """Shift *date_obj* by ±100 years to satisfy PREFER_DATES_FROM. + + *now* is normalised to naive so a tz-aware RELATIVE_BASE does not raise + TypeError. When the shifted year falls on Feb 29 in a non-leap year, the + nearest valid leap year in the preferred direction is used — matching the + behaviour of the NLP path in ``parser.py``. + + Returns the adjusted datetime, or the original when no shift is needed. + """ + now_naive = now.replace(tzinfo=None) if now.tzinfo is not None else now + + if now_naive < date_obj and prefer_from == "past": + target_year = date_obj.year - 100 + elif now_naive >= date_obj and prefer_from == "future": + target_year = date_obj.year + 100 + else: return date_obj + try: + return date_obj.replace(year=target_year) + except ValueError: + # Feb 29 shifted into a non-leap year — find the nearest valid one + target_year = ( + get_next_leap_year(target_year) + if prefer_from == "future" + else get_previous_leap_year(target_year) + ) + return date_obj.replace(year=target_year) + -def parse_with_formats(date_string, date_formats, settings): +def parse_with_formats( + date_string: str, date_formats: Iterable[str], settings: Settings +) -> "DateData": """Parse with formats and return a dictionary with 'period' and 'obj_date'. :returns: :class:`datetime.datetime`, dict or None @@ -187,8 +311,9 @@ def parse_with_formats(date_string, date_formats, settings): except ValueError: continue else: - missing_month = not any(m in date_format for m in ["%m", "%b", "%B"]) - missing_day = "%d" not in date_format + _missing = _get_missing_parts(date_format) + missing_month = "month" in _missing + missing_day = "day" in _missing if missing_month and missing_day: period = "year" date_obj = set_correct_month_from_settings(date_obj, settings) @@ -202,29 +327,136 @@ def parse_with_formats(date_string, date_formats, settings): period = "month" date_obj = set_correct_day_from_settings(date_obj, settings) - if not ("%y" in date_format or "%Y" in date_format): - today = datetime.today() - date_obj = date_obj.replace(year=today.year) + now = settings.RELATIVE_BASE or _now(settings) + if "year" in _missing: + date_obj = date_obj.replace(year=now.year) + elif "%y" in date_format and "%Y" not in date_format: + date_obj = _apply_century_preference( + date_obj, now, settings.PREFER_DATES_FROM + ) date_obj = apply_timezone_from_settings(date_obj, settings) - return DateData(date_obj=date_obj, period=period) - else: - return DateData(date_obj=None, period=period) + return DateData( + date_obj=date_obj, period=period, parts=_get_parts(date_format) + ) + return DateData(date_obj=None, period=period) + + +_MONTHS = ( + "january", + "february", + "march", + "april", + "may", + "june", + "july", + "august", + "september", + "october", + "november", + "december", +) +_WEEKDAYS = ( + "monday", + "tuesday", + "wednesday", + "thursday", + "friday", + "saturday", + "sunday", +) + + +@functools.cache +def _get_name_translations( + locale: "Locale", month_form: str | None, weekday_form: str | None +) -> tuple[re.Pattern[str], dict[str, list[str]]] | None: + """Return a pattern matching the month and weekday names of *locale*, and + a mapping of each lowercase name to the English names it can stand for, or + ``None`` if there are no such names. + + *month_form* and *weekday_form* are ``"full"``, ``"abbr"`` or ``None``, + the English form to translate each kind of name into, or ``None`` to leave + that kind of name untranslated. + """ + translations: dict[str, list[str]] = collections.defaultdict(list) + for words, form in ((_MONTHS, month_form), (_WEEKDAYS, weekday_form)): + if form is None: + continue + for word in words: + english = word if form == "full" else word[:3] + for name in map(str.lower, locale.info.get(word, ())): + if english not in translations[name]: + translations[name].append(english) + if not translations: + return None + names = sorted(translations, key=len, reverse=True) + pattern = re.compile( + r"(? Iterator[str]: + """Yield the variants of *date_string* that result from replacing the + month and weekday names of *locale* with the English names that the + directives of *date_format* expect.""" + month_form = ( + "full" if "%B" in date_format else "abbr" if "%b" in date_format else None + ) + weekday_form = ( + "full" if "%A" in date_format else "abbr" if "%a" in date_format else None + ) + name_translations = _get_name_translations(locale, month_form, weekday_form) + if name_translations is None: + return + pattern, translations = name_translations + matches = pattern.findall(date_string) + if not matches: + return + parts = pattern.split(date_string) + # A name can stand for several English names, e.g. "mar" is both "martes" + # and "marzo" in Spanish, so every combination is yielded. + for combination in itertools.product( + *(translations[match.lower()] for match in matches) + ): + yield "".join( + part + name for part, name in zip(parts, (*combination, ""), strict=True) + ) class _DateLocaleParser: - def __init__(self, locale, date_string, date_formats, settings=None): + def __init__( + self, + locale: "Locale", + date_string: str, + date_formats: Iterable[str] | None, + settings: Settings | None = None, + ignore_surrounding_text: bool = False, + alternatives: bool = False, + ) -> None: + assert settings is not None self._settings = settings - if not (date_formats is None or isinstance(date_formats, (list, tuple, Set))): + if not ( + date_formats is None or isinstance(date_formats, (list, tuple, AbstractSet)) + ): raise TypeError("Date formats should be list, tuple or set of strings") self.locale = locale self.date_string = date_string self.date_formats = date_formats - self._translated_date = None - self._translated_date_with_formatting = None - self._parsers = { + self._ignore_surrounding_text = ignore_surrounding_text + self._alternatives = alternatives + self._alternative = 0 + self._translated_date: str | None = None + self._translated_date_with_formatting: str | None = None + self._part_of_day: PartOfDay | None = None + self._part_of_day_sets_time = False + self._parsers: dict[str, Callable[[], DateData | None]] = { "timestamp": self._try_timestamp, "negative-timestamp": self._try_negative_timestamp, "relative-time": self._try_freshness_parser, @@ -234,33 +466,80 @@ def __init__(self, locale, date_string, date_formats, settings=None): } @classmethod - def parse(cls, locale, date_string, date_formats=None, settings=None): - instance = cls(locale, date_string, date_formats, settings) + def parse( + cls, + locale: "Locale", + date_string: str, + date_formats: Iterable[str] | None = None, + settings: Settings | None = None, + ignore_surrounding_text: bool = False, + alternatives: bool = False, + ) -> "DateData | None": + instance = cls( + locale, + date_string, + date_formats, + settings, + ignore_surrounding_text, + alternatives, + ) return instance._parse() - def _parse(self): + def _parse(self) -> "DateData | None": + if not self._alternatives: + return self._parse_translation() + for self._alternative in count(1): + self._set_translated_date() + if self._translated_date is None: + return None + self._translated_date_with_formatting = None + date_data = self._parse_translation() + if date_data: + return date_data + return None + + def _parse_translation(self) -> "DateData | None": + rejected: _StrictDateOrderError | None = None for parser_name in self._settings.PARSERS: - date_data = self._parsers[parser_name]() + if rejected is not None and parser_name == "no-spaces-time": + # It would read the same numbers in a date order again. + continue + try: + date_data = self._parsers[parser_name]() + except _StrictDateOrderError as error: + # STRICT_DATE_ORDER rejected the reading of this parser. The + # other parsers may still read the date string. + rejected = error + continue if self._is_valid_date_data(date_data): + if self._part_of_day: + date_data.part_of_day = self._part_of_day + if ( + self._part_of_day_sets_time + and self._settings.RETURN_TIME_AS_PERIOD + ): + date_data.period = "part_of_day" return date_data - else: - return None + if rejected is not None: + raise rejected + return None - def _try_timestamp_parser(self, negative=False): + def _try_timestamp_parser(self, negative: bool = False) -> "DateData": return DateData( date_obj=get_date_from_timestamp( self.date_string, self._settings, negative=negative ), period="time" if self._settings.RETURN_TIME_AS_PERIOD else "day", + parts=("year", "month", "day", "time"), ) - def _try_timestamp(self): + def _try_timestamp(self) -> "DateData": return self._try_timestamp_parser() - def _try_negative_timestamp(self): + def _try_negative_timestamp(self) -> "DateData": return self._try_timestamp_parser(negative=True) - def _try_freshness_parser(self): + def _try_freshness_parser(self) -> "DateData | None": try: return freshness_date_parser.get_date_data( self._get_translated_date(), self._settings @@ -268,37 +547,62 @@ def _try_freshness_parser(self): except (OverflowError, ValueError): return None - def _try_absolute_parser(self): + def _try_absolute_parser(self) -> "DateData | None": return self._try_parser(parse_method=_parse_absolute) - def _try_nospaces_parser(self): + def _try_nospaces_parser(self) -> "DateData | None": return self._try_parser(parse_method=_parse_nospaces) - def _try_parser(self, parse_method): - _order = self._settings.DATE_ORDER - try: - if self._settings.PREFER_LOCALE_DATE_ORDER: - if "DATE_ORDER" not in self._settings._mod_settings: - self._settings.DATE_ORDER = self.locale.info.get( - "date_order", _order - ) - date_obj, period = date_parser.parse( - self._get_translated_date(), - parse_method=parse_method, - settings=self._settings, - ) - self._settings.DATE_ORDER = _order - return DateData( - date_obj=date_obj, - period=period, - ) - except ValueError: - self._settings.DATE_ORDER = _order - return None + def _try_parser( + self, parse_method: Callable[..., tuple[datetime, str | None, tuple[str, ...]]] + ) -> "DateData | None": + original_order = self._settings.DATE_ORDER + + # Use locale date order unless DATE_ORDER was explicitly set by the caller. + if ( + self._settings.PREFER_LOCALE_DATE_ORDER + and "DATE_ORDER" not in self._settings._mod_settings + ): + first_order = self.locale.info.get("date_order", original_order) + else: + first_order = original_order - def _try_given_formats(self): + candidates = [first_order] + + # If the caller requires a year (and not a day) and did not set DATE_ORDER, + # retry once or twice with year-biased orders to resolve month-number ambiguity. + require_parts = set(getattr(self._settings, "REQUIRE_PARTS", None) or []) + if ( + "DATE_ORDER" not in self._settings._mod_settings + and "year" in require_parts + and "day" not in require_parts + ): + for order in ("MYD", "YMD"): + if order not in candidates: + candidates.append(order) + + translated = self._get_translated_date() + + for order in candidates: + try: + date_obj, period, parts = date_parser.parse( + translated, + parse_method=parse_method, + settings=self._settings, + date_order=order, + ) + return DateData(date_obj=date_obj, period=period, parts=parts) + except _StrictDateOrderError: + # Only raised with an explicit DATE_ORDER, which leaves a single + # candidate order. + raise + except ValueError: + continue + return None + + def _try_given_formats(self) -> "DateData | None": if not self.date_formats: - return + return None return parse_with_formats( self._get_translated_date_with_formatting(), @@ -306,30 +610,48 @@ def _try_given_formats(self): settings=self._settings, ) - def _get_translated_date(self): + def _translate(self, keep_formatting: bool) -> str | None: + return self.locale._translate( + self.date_string, + keep_formatting=keep_formatting, + settings=self._settings, + ignore_surrounding_text=self._ignore_surrounding_text, + alternative=self._alternative, + ) + + def _set_translated_date(self) -> None: + translated = self._translate(keep_formatting=False) + if translated is None: + self._translated_date = None + return + ( + self._translated_date, + self._part_of_day, + self._part_of_day_sets_time, + ) = _replace_part_of_day(translated, self._settings.PARTS_OF_DAY) + + def _get_translated_date(self) -> str: if self._translated_date is None: - self._translated_date = self.locale.translate( - self.date_string, keep_formatting=False, settings=self._settings - ) + self._set_translated_date() + assert self._translated_date is not None return self._translated_date - def _get_translated_date_with_formatting(self): + def _get_translated_date_with_formatting(self) -> str: if self._translated_date_with_formatting is None: - self._translated_date_with_formatting = self.locale.translate( - self.date_string, keep_formatting=True, settings=self._settings + self._translated_date_with_formatting = self._translate( + keep_formatting=True ) + assert self._translated_date_with_formatting is not None return self._translated_date_with_formatting - def _is_valid_date_data(self, date_data): + def _is_valid_date_data(self, date_data: object) -> TypeGuard["DateData"]: if not isinstance(date_data, DateData): return False if not date_data["date_obj"] or not date_data["period"]: return False if date_data["date_obj"] and not isinstance(date_data["date_obj"], datetime): return False - if date_data["period"] not in ("time", "day", "week", "month", "year"): - return False - return True + return date_data["period"] in ("time", "day", "week", "month", "year") class DateData: @@ -338,27 +660,51 @@ class DateData: It can be accessed with square brackets like a dict object. """ - def __init__(self, *, date_obj=None, period=None, locale=None): + part_of_day: PartOfDay | None = None + """:class:`~dateparser.PartOfDay` that the date string refers to, e.g. + :attr:`~dateparser.PartOfDay.NIGHT` for ``"tonight"``, or ``None``. + + .. versionadded:: VERSION + + Its time comes from the ``PARTS_OF_DAY`` :ref:`setting `, unless + the date string also has a time, e.g. ``"tonight at 11pm"``. If it does + not, and the ``RETURN_TIME_AS_PERIOD`` setting is enabled, ``period`` is + ``"part_of_day"``. + """ + + def __init__( + self, + *, + date_obj: datetime | None = None, + period: str | None = None, + locale: str | None = None, + parts: tuple[str, ...] = (), + ) -> None: self.date_obj = date_obj self.period = period self.locale = locale + self.parts = parts + """Parts of :attr:`date_obj` determined by the parsed string, as a + tuple with some or all of ``"year"``, ``"month"``, ``"day"`` and + ``"time"``, in that order. The remaining parts come from + :ref:`settings`, e.g. ``RELATIVE_BASE`` or ``PREFER_DAY_OF_MONTH``.""" - def __getitem__(self, k): + def __getitem__(self, k: str) -> Any: if not hasattr(self, k): raise KeyError(k) return getattr(self, k) - def __setitem__(self, k, v): + def __setitem__(self, k: str, v: Any) -> None: if not hasattr(self, k): raise KeyError(k) setattr(self, k, v) - def __repr__(self): + def __repr__(self) -> str: properties_text = ", ".join( - "{}={}".format(prop, val.__repr__()) for prop, val in self.__dict__.items() + f"{prop}={val!r}" for prop, val in self.__dict__.items() ) - return "{}({})".format(self.__class__.__name__, properties_text) + return f"{self.__class__.__name__}({properties_text})" class DateDataParser: @@ -389,7 +735,9 @@ class DateDataParser: :param use_given_order: If True, locales are tried for translation of date string - in the order in which they are given. + in the order in which they are given. This is equivalent to the + ``USE_GIVEN_LANGUAGE_ORDER`` setting; the given order is preserved if + either is enabled. :type use_given_order: bool :param settings: @@ -409,42 +757,43 @@ class DateDataParser: ``SettingValidationError``: A provided setting is not valid. """ - locale_loader = None + locale_loader: LocaleDataLoader | None = None @apply_settings def __init__( self, - languages=None, - locales=None, - region=None, - try_previous_locales=False, - use_given_order=False, - settings=None, - detect_languages_function=None, - ): - if languages is not None and not isinstance(languages, (list, tuple, Set)): + languages: Iterable[str] | None = None, + locales: Iterable[str] | None = None, + region: str | None = None, + try_previous_locales: bool = False, + use_given_order: bool = False, + settings: Settings | dict[str, Any] | None = None, + detect_languages_function: Callable[..., list[str]] | None = None, + ) -> None: + assert isinstance(settings, Settings) + if languages is not None and not isinstance( + languages, (list, tuple, AbstractSet) + ): raise TypeError( - "languages argument must be a list (%r given)" % type(languages) + f"languages argument must be a list ({type(languages)!r} given)" ) - if locales is not None and not isinstance(locales, (list, tuple, Set)): + if locales is not None and not isinstance(locales, (list, tuple, AbstractSet)): raise TypeError( - "locales argument must be a list (%r given)" % type(locales) + f"locales argument must be a list ({type(locales)!r} given)" ) if region is not None and not isinstance(region, str): - raise TypeError("region argument must be str (%r given)" % type(region)) + raise TypeError(f"region argument must be str ({type(region)!r} given)") if not isinstance(try_previous_locales, bool): raise TypeError( - "try_previous_locales argument must be a boolean (%r given)" - % type(try_previous_locales) + f"try_previous_locales argument must be a boolean ({type(try_previous_locales)!r} given)" ) if not isinstance(use_given_order, bool): raise TypeError( - "use_given_order argument must be a boolean (%r given)" - % type(use_given_order) + f"use_given_order argument must be a boolean ({type(use_given_order)!r} given)" ) if not locales and not languages and use_given_order: @@ -461,9 +810,16 @@ def __init__( self.locales = locales self.region = region self.detect_languages_function = detect_languages_function - self.previous_locales = collections.OrderedDict() + self.previous_locales: collections.OrderedDict[Locale, None] = ( + collections.OrderedDict() + ) + # Guards the per-instance state mutated when a parser is shared by + # multiple threads (previous_locales and the lazily detected languages). + self._lock = threading.RLock() - def get_date_data(self, date_string, date_formats=None): + def get_date_data( + self, date_string: str, date_formats: Iterable[str] | None = None + ) -> DateData: """ Parse string representing date and/or time in recognizable localized formats. Supports parsing multiple languages and timezones. @@ -481,7 +837,8 @@ def get_date_data(self, date_string, date_formats=None): :raises: ValueError - Unknown Language - .. note:: *Period* values can be a 'day' (default), 'week', 'month', 'year', 'time'. + .. note:: *Period* values can be a 'day' (default), 'week', 'month', 'year', 'time', + 'part_of_day'. *Period* represents the granularity of date parsed from the given string. @@ -490,20 +847,29 @@ def get_date_data(self, date_string, date_formats=None): Hence, the level of precision is ``month``: >>> DateDataParser().get_date_data('March 2015') - DateData(date_obj=datetime.datetime(2015, 3, 16, 0, 0), period='month', locale='en') + DateData(date_obj=datetime.datetime(2015, 3, 16, 0, 0), period='month', locale='en', + parts=('year', 'month')) Similarly, for date strings with no day and month information present, level of precision is ``year`` and day ``16`` and month ``6`` are from *current_date*. >>> DateDataParser().get_date_data('2014') - DateData(date_obj=datetime.datetime(2014, 6, 16, 0, 0), period='year', locale='en') + DateData(date_obj=datetime.datetime(2014, 6, 16, 0, 0), period='year', locale='en', + parts=('year',)) + + *Parts* lists the parts of the date that the given string determines, + including those that *period* cannot tell apart, like a missing year: + + >>> DateDataParser().get_date_data('16 March') + DateData(date_obj=datetime.datetime(2015, 3, 16, 0, 0), period='day', locale='en', + parts=('month', 'day')) Dates with time zone indications or UTC offsets are returned in UTC time unless specified using `Settings `__. >>> DateDataParser().get_date_data('23 March 2000, 1:21 PM CET') DateData(date_obj=datetime.datetime(2000, 3, 23, 13, 21, tzinfo=), - period='day', locale='en') + period='day', locale='en', parts=('year', 'month', 'day', 'time')) """ if not isinstance(date_string, str): @@ -512,35 +878,134 @@ def get_date_data(self, date_string, date_formats=None): res = parse_with_formats(date_string, date_formats or [], self._settings) if res["date_obj"]: return res + if date_formats: + localized_res = self._parse_with_localized_formats( + date_string, date_formats + ) + if localized_res: + return localized_res date_string = sanitize_date(date_string) - for locale in self._get_applicable_locales(date_string): - parsed_date = _DateLocaleParser.parse( - locale, date_string, date_formats, settings=self._settings + try: + parsed_date = self._parse_using_applicable_locales( + date_string, date_formats + ) + if not parsed_date and self._settings.IGNORE_SURROUNDING_TEXT: + # The whole string could not be parsed as a date. Retry, + # ignoring unrecognized words at the edges of the string, so + # that a date wrapped in harmless extra text is still parsed + # (issue #518), e.g. "Actualisé le 17 avril 2019". Strings that + # can be parsed as a whole never reach this fallback, so they + # are unaffected. + parsed_date = self._parse_using_applicable_locales( + date_string, date_formats, ignore_surrounding_text=True + ) + except _StrictDateOrderError: + # STRICT_DATE_ORDER rejected a reading of the date string, which + # is final: no other locale may guess another reading of it. + parsed_date = None + return parsed_date or DateData(date_obj=None, period="day", locale=None) + + def _parse_with_localized_formats( + self, date_string: str, date_formats: Iterable[str] + ) -> DateData | None: + for locale in self._get_locale_loader().get_locales( + languages=self.languages, + locales=self.locales, + region=self.region, + use_given_order=self.use_given_order + or self._settings.USE_GIVEN_LANGUAGE_ORDER, + ): + for date_format in date_formats: + for translated in _translate_names(date_string, date_format, locale): + res = parse_with_formats(translated, [date_format], self._settings) + if res["date_obj"]: + res["locale"] = locale.shortname + return res + return None + + def _parse_using_applicable_locales( + self, + date_string: str, + date_formats: Iterable[str] | None, + ignore_surrounding_text: bool = False, + ) -> DateData | None: + locales = [] + for locale in self._get_applicable_locales( + date_string, ignore_surrounding_text=ignore_surrounding_text + ): + locales.append(locale) + parsed_date = self._parse_using_locale( + locale, date_string, date_formats, ignore_surrounding_text ) if parsed_date: - parsed_date["locale"] = locale.shortname - if self.try_previous_locales: - self.previous_locales[locale] = None return parsed_date - else: - return DateData(date_obj=None, period="day", locale=None) + # Words with several meanings (e.g. Spanish "mar", Tuesday or March) + # get their other meanings only once no locale can parse the string + # with the default ones. + for locale in locales: + parsed_date = self._parse_using_locale( + locale, + date_string, + date_formats, + ignore_surrounding_text, + alternatives=True, + ) + if parsed_date: + return parsed_date + return None + + def _parse_using_locale( + self, + locale: "Locale", + date_string: str, + date_formats: Iterable[str] | None, + ignore_surrounding_text: bool, + alternatives: bool = False, + ) -> DateData | None: + parsed_date = _DateLocaleParser.parse( + locale, + date_string, + date_formats, + settings=self._settings, + ignore_surrounding_text=ignore_surrounding_text, + alternatives=alternatives, + ) + if parsed_date: + parsed_date["locale"] = locale.shortname + if self.try_previous_locales: + with self._lock: + self.previous_locales[locale] = None + return parsed_date - def get_date_tuple(self, *args, **kwargs): + def get_date_tuple(self, *args: Any, **kwargs: Any) -> tuple[Any, ...]: date_data = self.get_date_data(*args, **kwargs) - fields = date_data.__dict__.keys() - date_tuple = collections.namedtuple("DateData", fields) - return date_tuple(**date_data.__dict__) + fields = {k: v for k, v in date_data.__dict__.items() if k != "parts"} + date_tuple = collections.namedtuple("DateData", fields) # type: ignore[misc] # noqa: PYI024 + result: tuple[Any, ...] = date_tuple(**fields) + return result + + def _get_applicable_locales( + self, date_string: str, ignore_surrounding_text: bool = False + ) -> Iterator["Locale"]: + # The given order is preserved if requested either through the + # ``use_given_order`` constructor argument or the + # ``USE_GIVEN_LANGUAGE_ORDER`` setting (which also reaches the + # top-level :func:`dateparser.parse`). When no languages or locales are + # given there is nothing to order, so the default order is used. + use_given_order = ( + self.use_given_order or self._settings.USE_GIVEN_LANGUAGE_ORDER + ) - def _get_applicable_locales(self, date_string): - pop_tz_cache = [] + pop_tz_cache: list[str | None] = [] - def date_strings(): + def date_strings() -> Iterator[str]: """A generator instead of a static list to avoid calling pop_tz_offset_from_string if the first locale matches on unmodified date_string. """ + stripped_date_string: str | None yield date_string if not pop_tz_cache: stripped_date_string, _ = pop_tz_offset_from_string( @@ -554,9 +1019,11 @@ def date_strings(): yield stripped_date_string if self.try_previous_locales: - for locale in self.previous_locales.keys(): + with self._lock: + previous_locales = list(self.previous_locales.keys()) + for locale in previous_locales: for s in date_strings(): - if self._is_applicable_locale(locale, s): + if self._is_applicable_locale(locale, s, ignore_surrounding_text): yield locale if self.detect_languages_function and not self.languages and not self.locales: @@ -571,10 +1038,10 @@ def date_strings(): languages=self.languages, locales=self.locales, region=self.region, - use_given_order=self.use_given_order, + use_given_order=use_given_order, ): for s in date_strings(): - if self._is_applicable_locale(locale, s): + if self._is_applicable_locale(locale, s, ignore_surrounding_text): yield locale if self._settings.DEFAULT_LANGUAGES: @@ -582,19 +1049,29 @@ def date_strings(): languages=self._settings.DEFAULT_LANGUAGES, locales=None, region=self.region, - use_given_order=self.use_given_order, + use_given_order=use_given_order, ): yield locale - def _is_applicable_locale(self, locale, date_string): + def _is_applicable_locale( + self, + locale: "Locale", + date_string: str, + ignore_surrounding_text: bool = False, + ) -> bool: return locale.is_applicable( date_string, strip_timezone=False, # it is stripped outside settings=self._settings, + ignore_surrounding_text=ignore_surrounding_text, ) + _locale_loader_lock = threading.Lock() + @classmethod - def _get_locale_loader(cls): + def _get_locale_loader(cls) -> LocaleDataLoader: if not cls.locale_loader: - cls.locale_loader = LocaleDataLoader() + with cls._locale_loader_lock: + if not cls.locale_loader: + cls.locale_loader = LocaleDataLoader() return cls.locale_loader diff --git a/dateparser/date_parser.py b/dateparser/date_parser.py index d65b03eb5..47490ed60 100644 --- a/dateparser/date_parser.py +++ b/dateparser/date_parser.py @@ -1,15 +1,22 @@ -import sys +from collections.abc import Callable +from datetime import datetime +from typing import Any -from tzlocal import get_localzone - -from .conf import apply_settings +from .conf import Settings, apply_settings from .timezone_parser import pop_tz_offset_from_string -from .utils import apply_timezone, localize_timezone, strip_braces +from .utils import _get_localzone, apply_timezone, localize_timezone, strip_braces class DateParser: @apply_settings - def parse(self, date_string, parse_method, settings=None): + def parse( + self, + date_string: str, + parse_method: Callable[..., tuple[datetime, str | None, tuple[str, ...]]], + settings: Settings | dict[str, Any] | None = None, + date_order: str | None = None, + ) -> tuple[datetime, str | None, tuple[str, ...]]: + assert isinstance(settings, Settings) date_string = str(date_string) if not date_string.strip(): @@ -18,7 +25,9 @@ def parse(self, date_string, parse_method, settings=None): date_string = strip_braces(date_string) date_string, ptz = pop_tz_offset_from_string(date_string) - date_obj, period = parse_method(date_string, settings=settings, tz=ptz) + date_obj, period, parts = parse_method( + date_string, settings=settings, tz=ptz, date_order=date_order + ) _settings_tz = settings.TIMEZONE.lower() @@ -29,15 +38,10 @@ def parse(self, date_string, parse_method, settings=None): date_obj = date_obj.replace(tzinfo=ptz) if "local" not in _settings_tz: date_obj = apply_timezone(date_obj, settings.TIMEZONE) + elif "local" in _settings_tz: + date_obj = date_obj.replace(tzinfo=_get_localzone()) else: - if "local" in _settings_tz: - stz = get_localzone() - if hasattr(stz, "localize") and sys.version_info < (3, 6): - date_obj = stz.localize(date_obj) - else: - date_obj = date_obj.replace(tzinfo=stz) - else: - date_obj = localize_timezone(date_obj, settings.TIMEZONE) + date_obj = localize_timezone(date_obj, settings.TIMEZONE) if settings.TO_TIMEZONE: date_obj = apply_timezone(date_obj, settings.TO_TIMEZONE) @@ -49,7 +53,7 @@ def parse(self, date_string, parse_method, settings=None): ): date_obj = date_obj.replace(tzinfo=None) - return date_obj, period + return date_obj, period, parts date_parser = DateParser() diff --git a/dateparser/freshness_date_parser.py b/dateparser/freshness_date_parser.py index 024fe023e..0780bb89a 100644 --- a/dateparser/freshness_date_parser.py +++ b/dateparser/freshness_date_parser.py @@ -1,51 +1,70 @@ -from datetime import datetime, time, timezone +import contextlib +from datetime import datetime, time, timezone, tzinfo +from typing import TYPE_CHECKING, Any import regex as re from dateutil.relativedelta import relativedelta -from tzlocal import get_localzone -from dateparser.utils import apply_timezone, localize_timezone, strip_braces +from dateparser.utils import ( + _get_localzone, + apply_timezone, + localize_timezone, + set_correct_day_from_settings, + set_correct_month_from_settings, + strip_braces, +) from .parser import time_parser from .timezone_parser import pop_tz_offset_from_string +if TYPE_CHECKING: + from .conf import Settings + from .date import DateData + _UNITS = r"decade|year|month|week|day|hour|minute|second" -PATTERN = re.compile(r"(\d+[.,]?\d*)\s*(%s)\b" % _UNITS, re.I | re.S | re.U) +PATTERN = re.compile(rf"([+-]?\s*\d++[.,]?\d*+)\s*({_UNITS})\b", re.I | re.S | re.U) +# "the 1st of last month" translates to " 1 1 month ago". +_DAY_OF_MONTH = re.compile(r"^\s*(\d{1,2})\s+(?=(?:in\s+)?\d+\s+month\b)") class FreshnessDateDataParser: - """Parses date string like "1 year, 2 months ago" and "3 hours, 50 minutes ago" """ + """Parses date string like "1 year, 2 months ago" and "3 hours, 50 minutes ago".""" - def _are_all_words_units(self, date_string): + def _are_all_words_units(self, date_string: str) -> bool: skip = [_UNITS, r"ago|in|\d+", r":|[ap]m"] date_string = re.sub(r"\s+", " ", date_string.strip()) words = [x for x in re.split(r"\W", date_string) if x] - words = [x for x in words if not re.match(r"%s" % "|".join(skip), x)] + words = [x for x in words if not re.match("|".join(skip), x)] return not words - def _parse_time(self, date_string, settings): + def _parse_time(self, date_string: str, settings: "Settings") -> time | None: """Attempts to parse time part of date strings like '1 day ago, 2 PM'""" date_string = PATTERN.sub("", date_string) date_string = re.sub(r"\b(?:ago|in)\b", "", date_string) - try: + with contextlib.suppress(Exception): return time_parser(date_string) - except Exception: - pass + return None - def get_local_tz(self): - return get_localzone() + def get_local_tz(self) -> tzinfo: + return _get_localzone() - def parse(self, date_string, settings): + def parse( # noqa: PLR0912, PLR0915 + self, date_string: str, settings: "Settings" + ) -> tuple[datetime | None, str | None, tuple[str, ...]]: date_string = strip_braces(date_string) date_string, ptz = pop_tz_offset_from_string(date_string) + day = None + if match := _DAY_OF_MONTH.match(date_string): + day = int(match[1]) + date_string = date_string[match.end() :] _time = self._parse_time(date_string, settings) _settings_tz = settings.TIMEZONE.lower() - def apply_time(dateobj, timeobj): - if not isinstance(_time, time): + def apply_time(dateobj: datetime, timeobj: time | None) -> datetime: + if not isinstance(timeobj, time): return dateobj return dateobj.replace( @@ -62,13 +81,7 @@ def apply_time(dateobj, timeobj): now = localize_timezone(now, settings.TIMEZONE) if ptz: - if now.tzinfo: - now = now.astimezone(ptz) - else: - if hasattr(ptz, "localize"): - now = ptz.localize(now) - else: - now = now.replace(tzinfo=ptz) + now = now.astimezone(ptz) if now.tzinfo else ptz.localize(now) if not now.tzinfo: now = now.replace(tzinfo=self.get_local_tz()) @@ -81,20 +94,37 @@ def apply_time(dateobj, timeobj): else: now = apply_timezone(localized_now, settings.TIMEZONE) + elif "local" not in _settings_tz: + utc_dt = datetime.now(tz=timezone.utc) + now = apply_timezone(utc_dt, settings.TIMEZONE) else: - if "local" not in _settings_tz: - utc_dt = datetime.now(tz=timezone.utc) - now = apply_timezone(utc_dt, settings.TIMEZONE) - else: - now = datetime.now(self.get_local_tz()) - - date, period = self._parse_date(date_string, now, settings.PREFER_DATES_FROM) + now = datetime.now(self.get_local_tz()) + + date, period, parts = self._parse_date( + date_string, now, settings.PREFER_DATES_FROM + ) + + if date and day is not None: + if period != "month": + return None, None, () + try: + date = date.replace(day=day) + except ValueError: + return None, None, () + period = "day" + parts += ("day",) if date: + if period == "year": + date = set_correct_month_from_settings(date, settings, date.month) + if period in ("year", "month"): + date = set_correct_day_from_settings(date, settings, date.day) old_date = date date = apply_time(date, _time) if settings.RETURN_TIME_AS_PERIOD and old_date != date: period = "time" + if isinstance(_time, time) and "time" not in parts: + parts += ("time",) if settings.TO_TIMEZONE: date = apply_timezone(date, settings.TO_TIMEZONE) @@ -106,51 +136,91 @@ def apply_time(dateobj, timeobj): ): date = date.replace(tzinfo=None) - return date, period + return date, period, parts - def _parse_date(self, date_string, now, prefer_dates_from): + def _parse_date( # noqa: PLR0912 + self, date_string: str, now: datetime, prefer_dates_from: str + ) -> tuple[datetime, str, tuple[str, ...]] | tuple[None, None, tuple[()]]: if not self._are_all_words_units(date_string): - return None, None + return None, None, () + + result = self.get_kwargs(date_string) + if isinstance(result, tuple): + kwargs, explicit_signs = result + else: + kwargs = result + explicit_signs = {} - kwargs = self.get_kwargs(date_string) if not kwargs: - return None, None + return None, None, () period = "day" if "days" not in kwargs: - for k in ["weeks", "months", "years"]: + for k in ["weeks", "months", "years", "decades"]: if k in kwargs: - period = k[:-1] + period = "year" if k == "decades" else k[:-1] break - td = relativedelta(**kwargs) - if ( - re.search(r"\bin\b", date_string) - or re.search(r"\bfuture\b", prefer_dates_from) + going_forward = re.search(r"\bin\b", date_string) or ( + re.search(r"\bfuture\b", prefer_dates_from) and not re.search(r"\bago\b", date_string) - ): - date = now + td + ) + + adjusted_kwargs: dict[str, Any] = {} + for key, value in kwargs.items(): + if explicit_signs.get(key, False) or going_forward: + adjusted_kwargs[key] = value + else: + adjusted_kwargs[key] = -value + + # Fold ``decades`` into ``years`` after each component's sign has been + # resolved so that an unsigned component combined with an explicitly + # signed one still follows the default ago/future context (fixes + # #1304). + if "decades" in adjusted_kwargs: + adjusted_kwargs["years"] = adjusted_kwargs.get( + "years", 0 + ) + 10 * adjusted_kwargs.pop("decades") + + td = relativedelta(**adjusted_kwargs) + + date = now + td + + # The smallest unit in the string determines which parts of the + # resulting date are meaningful. + parts: tuple[str, ...] + if kwargs.keys() & {"seconds", "minutes", "hours"}: + parts = ("year", "month", "day", "time") + elif kwargs.keys() & {"days", "weeks"}: + parts = ("year", "month", "day") + elif "months" in kwargs: + parts = ("year", "month") else: - date = now - td - return date, period + parts = ("year",) + + return date, period, parts - def get_kwargs(self, date_string): + def get_kwargs( + self, date_string: str + ) -> tuple[dict[str, float], dict[str, bool]] | dict[str, float]: m = PATTERN.findall(date_string) if not m: return {} - kwargs = {} + kwargs: dict[str, float] = {} + explicit_signs: dict[str, bool] = {} + for num, unit in m: - kwargs[unit + "s"] = float(num.replace(",", ".")) - if "decades" in kwargs: - kwargs["years"] = 10 * kwargs["decades"] + kwargs.get("years", 0) - del kwargs["decades"] - return kwargs + has_explicit_sign = num.startswith(("+", "-")) + explicit_signs[unit + "s"] = has_explicit_sign + kwargs[unit + "s"] = float(num.replace(",", ".").replace(" ", "")) + + return kwargs, explicit_signs - def get_date_data(self, date_string, settings=None): - from dateparser.date import DateData + def get_date_data(self, date_string: str, settings: "Settings") -> "DateData": + from dateparser.date import DateData # noqa: PLC0415 - date, period = self.parse(date_string, settings) - return DateData(date_obj=date, period=period) + date, period, parts = self.parse(date_string, settings) + return DateData(date_obj=date, period=period, parts=parts) freshness_date_parser = FreshnessDateDataParser() diff --git a/dateparser/languages/__init__.py b/dateparser/languages/__init__.py index 7270a7b93..2f14a878d 100644 --- a/dateparser/languages/__init__.py +++ b/dateparser/languages/__init__.py @@ -1,2 +1,2 @@ -from .loader import default_loader -from .locale import Locale +from .loader import default_loader as default_loader +from .locale import Locale as Locale diff --git a/dateparser/languages/dictionary.py b/dateparser/languages/dictionary.py index a4f3f0af1..6b67781ca 100644 --- a/dateparser/languages/dictionary.py +++ b/dateparser/languages/dictionary.py @@ -1,13 +1,22 @@ +import threading +from collections.abc import Iterable, Iterator from itertools import chain, zip_longest from operator import methodcaller +from typing import TYPE_CHECKING, Any, ClassVar, TypeVar, cast import regex as re +from dateparser.timezone_parser import is_timezone_token from dateparser.utils import normalize_unicode +if TYPE_CHECKING: + from dateparser.conf import Settings + +_T = TypeVar("_T") + PARSER_HARDCODED_TOKENS = [":", ".", " ", "-", "/"] -PARSER_KNOWN_TOKENS = ["am", "pm", "UTC", "GMT", "Z"] -ALWAYS_KEEP_TOKENS = ["+"] + PARSER_HARDCODED_TOKENS +PARSER_KNOWN_TOKENS = ["am", "pm", "UTC", "GMT", "Z", "early_morning"] +ALWAYS_KEEP_TOKENS = ["+", *PARSER_HARDCODED_TOKENS] KNOWN_WORD_TOKENS = [ "monday", "tuesday", @@ -40,17 +49,33 @@ "in", "am", "pm", + "early_morning", + "morning", + "afternoon", + "evening", + "night", ] PARENTHESES_PATTERN = re.compile(r"[\(\)]") NUMERAL_PATTERN = re.compile(r"(\d+)") KEEP_TOKEN_PATTERN = re.compile(r"^.*[^\W_].*$", flags=re.U) +_WEEKDAY_TOKENS = KNOWN_WORD_TOKENS[0:7] +_MONTH_TOKENS = KNOWN_WORD_TOKENS[7:19] + class UnknownTokenError(Exception): pass +def _parse_bool(value: object) -> bool: + if isinstance(value, bool): + return value + if isinstance(value, str): + return value.strip().lower() in ("true", "1", "yes") + return False + + class Dictionary: """ Class that modifies and stores translations and handles splitting of date string. @@ -66,27 +91,64 @@ class Dictionary: :return: a Dictionary instance. """ - _split_regex_cache = {} - _sorted_words_cache = {} - _split_relative_regex_cache = {} - _sorted_relative_strings_cache = {} - _match_relative_regex_cache = {} - - def __init__(self, locale_info, settings=None): - dictionary = {} - self._settings = settings + _split_regex_cache: ClassVar[dict[str, dict[str, re.Pattern[str]]]] = {} + _sorted_words_cache: ClassVar[dict[str, dict[str, list[str]]]] = {} + _split_relative_regex_cache: ClassVar[dict[str, dict[str, re.Pattern[str]]]] = {} + _sorted_relative_strings_cache: ClassVar[dict[str, dict[str, list[str]]]] = {} + _match_relative_regex_cache: ClassVar[dict[str, dict[str, re.Pattern[str]]]] = {} + + # The caches above are shared across all Dictionary instances and threads. + # The lock keeps each check-populate-evict-read sequence atomic, so a + # concurrent eviction cannot drop an entry between its check and its read. + _cache_lock = threading.RLock() + + def __init__( + self, locale_info: dict[str, Any], settings: "Settings | None" = None + ) -> None: + dictionary: dict[str, str | None] = {} + self._settings = cast("Settings", settings) self.info = locale_info if "skip" in locale_info: skip = map(methodcaller("lower"), locale_info["skip"]) - dictionary.update(zip_longest(skip, [], fillvalue=None)) + dictionary.update(dict.fromkeys(skip)) if "pertain" in locale_info: pertain = map(methodcaller("lower"), locale_info["pertain"]) - dictionary.update(zip_longest(pertain, [], fillvalue=None)) + dictionary.update(dict.fromkeys(pertain)) + meanings: dict[str, list[str]] = {} for word in KNOWN_WORD_TOKENS: if word in locale_info: - translations = map(methodcaller("lower"), locale_info[word]) + translations = list(map(methodcaller("lower"), locale_info[word])) dictionary.update(zip_longest(translations, [], fillvalue=word)) + for translation in translations: + meanings.setdefault(translation, []).append(word) + self._meanings = meanings + + # Some locales (mostly Romance languages) reuse the same abbreviation for a + # weekday and a month (e.g. Italian "mar" is both "martedì" and "marzo"). + # The loop above always resolves those in favor of the month, since months + # are listed after weekdays in KNOWN_WORD_TOKENS. Keep track of the weekday + # each conflicting token could also mean, and of which tokens are + # unambiguously months, so a caller with extra context (e.g. another, + # unambiguous month elsewhere in the same string) can recover the weekday + # reading. + weekday_translations = {} + for word in _WEEKDAY_TOKENS: + if word in locale_info: + for token in map(methodcaller("lower"), locale_info[word]): + weekday_translations[token] = word + self._month_translations: set[str] = set() + for word in _MONTH_TOKENS: + if word in locale_info: + self._month_translations.update( + map(methodcaller("lower"), locale_info[word]) + ) + self._weekday_month_conflicts = { + token: weekday + for token, weekday in weekday_translations.items() + if token in self._month_translations + } + dictionary.update(zip_longest(ALWAYS_KEEP_TOKENS, ALWAYS_KEEP_TOKENS)) dictionary.update( zip_longest( @@ -101,26 +163,45 @@ def __init__(self, locale_info, settings=None): self._dictionary = dictionary - no_word_spacing = locale_info.get("no_word_spacing", "False") - self._no_word_spacing = bool(eval(no_word_spacing)) + no_word_spacing = locale_info.get("no_word_spacing", False) + self._no_word_spacing = _parse_bool(no_word_spacing) relative_type_regex = locale_info.get("relative-type-regex", {}) self._relative_strings = list(chain.from_iterable(relative_type_regex.values())) - def __contains__(self, key): + def _is_unambiguous_month(self, token: str) -> bool: + """ + Whether ``token`` (already lowercased) names a month and, unlike the + tokens in :attr:`_weekday_month_conflicts`, cannot also mean a weekday. + """ + return ( + token in self._month_translations + and token not in self._weekday_month_conflicts + ) + + def __contains__(self, key: object) -> bool: if key in self._settings.SKIP_TOKENS: return True return self._dictionary.__contains__(key) - def __getitem__(self, key): + def __getitem__(self, key: str) -> str | None: if key in self._settings.SKIP_TOKENS: return None return self._dictionary.__getitem__(key) - def __iter__(self): + def __iter__(self) -> Iterator[str]: return chain(self._settings.SKIP_TOKENS, iter(self._dictionary)) - def are_tokens_valid(self, tokens): + def _get_meanings(self, key: str) -> list[str]: + """Return every meaning of *key*, starting with the one that indexing + returns, if any.""" + default = self[key] + if default is None: + return [] + others = [m for m in self._meanings.get(key, ()) if m != default] + return [default, *others] + + def are_tokens_valid(self, tokens: Iterable[str]) -> bool: """ Check if tokens are valid tokens for the locale. @@ -134,15 +215,63 @@ def are_tokens_valid(self, tokens): if has_only_keep_tokens: return False match_relative_regex = self._get_match_relative_regex_cache() - for token in tokens: - if token.isdigit() or match_relative_regex.match(token) or token in self: - continue - else: - return False - else: - return True + return all( + self._is_known_token(token, match_relative_regex) for token in tokens + ) + + def _is_known_token( + self, token: str, match_relative_regex: re.Pattern[str] + ) -> bool: + """Whether ``token`` is recognised by this locale: a number, a relative + expression, or a dictionary word (the same per-token check that + :meth:`are_tokens_valid` applies).""" + return bool( + token.isdigit() or match_relative_regex.match(token) or token in self + ) + + def _strip_unknown_edge_tokens(self, tokens: list[str]) -> list[str]: + """Return ``tokens`` without the leading and trailing tokens that this + locale does not recognise (neither digits, relative expressions, nor + dictionary words), along with any whitespace those removals leave at + the edges. Interior tokens are left untouched. Used when the + ``IGNORE_SURROUNDING_TEXT`` setting is enabled. + + A timezone abbreviation that is the final token (e.g. a trailing + ``"EST"``) is kept even though the locale dictionary does not list it, + so that the offset is applied rather than silently discarded. It + survives translation and is popped later by + :func:`~dateparser.timezone_parser.pop_tz_offset_from_string`. The + timezone is kept only when it is the last token: if further + unrecognized text follows it, the tokenizer merges the two and the + timezone is dropped together with that text, like any other edge noise. + + This timezone exception is deliberately made at the trailing edge + only: a timezone conventionally follows the date it qualifies + (``"... 1:21 PM EST"``) and does not precede it, so the leading edge + keeps stripping unrecognized tokens unconditionally.""" + match_relative_regex = self._get_match_relative_regex_cache() - def split(self, string, keep_formatting=False): + def is_extra_text(token: str) -> bool: + return token.isspace() or not self._is_known_token( + token, match_relative_regex + ) + + start, end = 0, len(tokens) + # Leading edge: drop every unrecognized token. A timezone does not + # precede the date it qualifies, so no timezone exception is made here. + while start < end and is_extra_text(tokens[start]): + start += 1 + # Trailing edge: drop unrecognized tokens, but keep a recognized + # timezone abbreviation (e.g. ``" est"``) so its offset is applied. + while ( + end > start + and is_extra_text(tokens[end - 1]) + and not is_timezone_token(tokens[end - 1]) + ): + end -= 1 + return tokens[start:end] + + def split(self, string: str, keep_formatting: bool = False) -> list[str]: """ Split the date string using translations in locale info. @@ -158,12 +287,12 @@ def split(self, string, keep_formatting=False): :return: A list of string tokens formed after splitting the date string. """ if not string: - return string + return [] split_relative_regex = self._get_split_relative_regex_cache() match_relative_regex = self._get_match_relative_regex_cache() - tokens = split_relative_regex.split(string) + tokens: list[Any] = split_relative_regex.split(string) for i, token in enumerate(tokens): if match_relative_regex.match(token): @@ -173,17 +302,21 @@ def split(self, string, keep_formatting=False): return list(filter(bool, chain.from_iterable(tokens))) - def _add_to_cache(self, value, cache): - cache.setdefault(self._settings.registry_key, {})[self.info["name"]] = value - if ( - self._settings.CACHE_SIZE_LIMIT - and len(cache) > self._settings.CACHE_SIZE_LIMIT - ): - cache.pop(list(cache.keys())[0]) - - def _split_by_known_words(self, string: str, keep_formatting: bool): + def _add_to_cache(self, value: _T, cache: dict[str, dict[str, _T]]) -> None: + with self._cache_lock: + key = self._settings.registry_key + entry = cache.pop(key, {}) + entry[self.info["name"]] = value + cache[key] = entry + if ( + self._settings.CACHE_SIZE_LIMIT + and len(cache) > self._settings.CACHE_SIZE_LIMIT + ): + cache.pop(next(iter(cache))) + + def _split_by_known_words(self, string: str, keep_formatting: bool) -> list[str]: regex = self._get_split_regex_cache() - splitted = [] + splitted: list[str] = [] unknown = string while unknown: @@ -222,119 +355,128 @@ def _split_by_known_words(self, string: str, keep_formatting: bool): return splitted - def _split_by_numerals(self, string, keep_formatting): + def _split_by_numerals(self, string: str, keep_formatting: bool) -> list[str]: return [ token for token in NUMERAL_PATTERN.split(string) if self._should_capture(token, keep_formatting) ] - def _should_capture(self, token, keep_formatting): + def _should_capture( + self, token: str, keep_formatting: bool + ) -> bool | re.Match[str] | None: return ( keep_formatting or token in ALWAYS_KEEP_TOKENS or KEEP_TOKEN_PATTERN.match(token) ) - def _get_sorted_words_from_cache(self): - if ( - self._settings.registry_key not in self._sorted_words_cache - or self.info["name"] - not in self._sorted_words_cache[self._settings.registry_key] - ): - self._add_to_cache( - cache=self._sorted_words_cache, - value=sorted([key for key in self], key=len, reverse=True), - ) - return self._sorted_words_cache[self._settings.registry_key][self.info["name"]] - - def _get_split_regex_cache(self): - if ( - self._settings.registry_key not in self._split_regex_cache - or self.info["name"] - not in self._split_regex_cache[self._settings.registry_key] - ): - self._construct_split_regex() - return self._split_regex_cache[self._settings.registry_key][self.info["name"]] - - def _construct_split_regex(self): + def _get_sorted_words_from_cache(self) -> list[str]: + with self._cache_lock: + if ( + self._settings.registry_key not in self._sorted_words_cache + or self.info["name"] + not in self._sorted_words_cache[self._settings.registry_key] + ): + self._add_to_cache( + cache=self._sorted_words_cache, + value=sorted(self, key=len, reverse=True), + ) + return self._sorted_words_cache[self._settings.registry_key][ + self.info["name"] + ] + + def _get_split_regex_cache(self) -> re.Pattern[str]: + with self._cache_lock: + if ( + self._settings.registry_key not in self._split_regex_cache + or self.info["name"] + not in self._split_regex_cache[self._settings.registry_key] + ): + self._construct_split_regex() + return self._split_regex_cache[self._settings.registry_key][ + self.info["name"] + ] + + def _construct_split_regex(self) -> None: known_words_group = "|".join( map(re.escape, self._get_sorted_words_from_cache()) ) if self._no_word_spacing: - regex = r"^(.*?)({})(.*)$".format(known_words_group) + regex = rf"^(.*?)({known_words_group})(.*)$" else: - regex = r"^(.*?(?:\A|\W|_|\d))({})((?:\Z|\W|_|\d).*)$".format( - known_words_group - ) + regex = rf"^(.*?(?:\A|\W|_|\d))({known_words_group})((?:\Z|\W|_|\d).*)$" self._add_to_cache( cache=self._split_regex_cache, value=re.compile(regex, re.UNICODE | re.IGNORECASE), ) - def _get_sorted_relative_strings_from_cache(self): - if ( - self._settings.registry_key not in self._sorted_relative_strings_cache - or self.info["name"] - not in self._sorted_relative_strings_cache[self._settings.registry_key] - ): - self._add_to_cache( - cache=self._sorted_relative_strings_cache, - value=sorted( - [ - PARENTHESES_PATTERN.sub("", key) - for key in self._relative_strings - ], - key=len, - reverse=True, - ), - ) - return self._sorted_relative_strings_cache[self._settings.registry_key][ - self.info["name"] - ] - - def _get_split_relative_regex_cache(self): - if ( - self._settings.registry_key not in self._split_relative_regex_cache - or self.info["name"] - not in self._split_relative_regex_cache[self._settings.registry_key] - ): - self._construct_split_relative_regex() - return self._split_relative_regex_cache[self._settings.registry_key][ - self.info["name"] - ] - - def _construct_split_relative_regex(self): + def _get_sorted_relative_strings_from_cache(self) -> list[str]: + with self._cache_lock: + if ( + self._settings.registry_key not in self._sorted_relative_strings_cache + or self.info["name"] + not in self._sorted_relative_strings_cache[self._settings.registry_key] + ): + self._add_to_cache( + cache=self._sorted_relative_strings_cache, + value=sorted( + [ + PARENTHESES_PATTERN.sub("", key) + for key in self._relative_strings + ], + key=len, + reverse=True, + ), + ) + return self._sorted_relative_strings_cache[self._settings.registry_key][ + self.info["name"] + ] + + def _get_split_relative_regex_cache(self) -> re.Pattern[str]: + with self._cache_lock: + if ( + self._settings.registry_key not in self._split_relative_regex_cache + or self.info["name"] + not in self._split_relative_regex_cache[self._settings.registry_key] + ): + self._construct_split_relative_regex() + return self._split_relative_regex_cache[self._settings.registry_key][ + self.info["name"] + ] + + def _construct_split_relative_regex(self) -> None: known_relative_strings_group = "|".join( self._get_sorted_relative_strings_from_cache() ) if self._no_word_spacing: - regex = "({})".format(known_relative_strings_group) + regex = f"({known_relative_strings_group})" else: - regex = "(?<=(?:\\A|\\W|_))({})(?=(?:\\Z|\\W|_))".format( - known_relative_strings_group + regex = ( + f"(?<=(?:\\A|\\W|_))({known_relative_strings_group})(?=(?:\\Z|\\W|_))" ) self._add_to_cache( cache=self._split_relative_regex_cache, value=re.compile(regex, re.UNICODE | re.IGNORECASE), ) - def _get_match_relative_regex_cache(self): - if ( - self._settings.registry_key not in self._match_relative_regex_cache - or self.info["name"] - not in self._match_relative_regex_cache[self._settings.registry_key] - ): - self._construct_match_relative_regex() - return self._match_relative_regex_cache[self._settings.registry_key][ - self.info["name"] - ] - - def _construct_match_relative_regex(self): + def _get_match_relative_regex_cache(self) -> re.Pattern[str]: + with self._cache_lock: + if ( + self._settings.registry_key not in self._match_relative_regex_cache + or self.info["name"] + not in self._match_relative_regex_cache[self._settings.registry_key] + ): + self._construct_match_relative_regex() + return self._match_relative_regex_cache[self._settings.registry_key][ + self.info["name"] + ] + + def _construct_match_relative_regex(self) -> None: known_relative_strings_group = "|".join( self._get_sorted_relative_strings_from_cache() ) - regex = "^({})$".format(known_relative_strings_group) + regex = f"^({known_relative_strings_group})$" self._add_to_cache( cache=self._match_relative_regex_cache, value=re.compile(regex, re.UNICODE | re.IGNORECASE), @@ -342,12 +484,14 @@ def _construct_match_relative_regex(self): class NormalizedDictionary(Dictionary): - def __init__(self, locale_info, settings=None): + def __init__( + self, locale_info: dict[str, Any], settings: "Settings | None" = None + ) -> None: super().__init__(locale_info, settings) self._normalize() - def _normalize(self): - new_dict = {} + def _normalize(self) -> None: + new_dict: dict[str, str | None] = {} conflicting_keys = [] for key, value in self._dictionary.items(): normalized = normalize_unicode(key) @@ -360,4 +504,11 @@ def _normalize(self): if key in (self.info.get("skip", []) + self.info.get("pertain", [])): new_dict[normalized] = self._dictionary[key] self._dictionary = new_dict + meanings: dict[str, list[str]] = {} + for key, key_meanings in self._meanings.items(): + normalized_meanings = meanings.setdefault(normalize_unicode(key), []) + normalized_meanings.extend( + m for m in key_meanings if m not in normalized_meanings + ) + self._meanings = meanings self._relative_strings = list(map(normalize_unicode, self._relative_strings)) diff --git a/dateparser/languages/loader.py b/dateparser/languages/loader.py index 023e02eaa..b60e5640e 100644 --- a/dateparser/languages/loader.py +++ b/dateparser/languages/loader.py @@ -1,36 +1,36 @@ +import threading from collections import OrderedDict +from collections.abc import Iterable, Iterator from copy import deepcopy from importlib import import_module from itertools import zip_longest +from typing import Any, ClassVar import regex as re -from ..data import language_locale_dict, language_order +from dateparser.data.languages_info import language_locale_dict, language_order + from .locale import Locale LOCALE_SPLIT_PATTERN = re.compile(r"-(?=[A-Z0-9]+$)") -def _isvalidlocale(locale): +def _isvalidlocale(locale: str) -> bool: language = LOCALE_SPLIT_PATTERN.split(locale)[0] if language not in language_order: return False - else: - locales_list = language_locale_dict[language] - if locale == language or locale in locales_list: - return True - else: - return False + locales_list = language_locale_dict[language] + return locale == language or locale in locales_list -def _filter_valid_locales(locales): +def _filter_valid_locales(locales: Iterable[str]) -> list[str]: return [locale for locale in locales if _isvalidlocale(locale)] -def _construct_locales(languages, region): +def _construct_locales(languages: Iterable[str], region: str) -> Iterable[str]: if region: possible_locales = [language + "-" + region for language in languages] - locales = _filter_valid_locales(possible_locales) + locales: Iterable[str] = _filter_valid_locales(possible_locales) else: locales = languages return locales @@ -39,17 +39,18 @@ def _construct_locales(languages, region): class LocaleDataLoader: """Class that handles loading of locale instances.""" - _loaded_languages = {} - _loaded_locales = {} + _loaded_languages: ClassVar[dict[str, dict[str, Any]]] = {} + _loaded_locales: ClassVar[dict[str, Locale]] = {} + _load_lock = threading.Lock() def get_locale_map( self, - languages=None, - locales=None, - region=None, - use_given_order=False, - allow_conflicting_locales=False, - ): + languages: Iterable[str] | None = None, + locales: Iterable[str] | None = None, + region: str | None = None, + use_given_order: bool = False, + allow_conflicting_locales: bool = False, + ) -> OrderedDict[str, Locale]: """ Get an ordered mapping with locale codes as keys and corresponding locale instances as values. @@ -93,12 +94,12 @@ def get_locale_map( def get_locales( self, - languages=None, - locales=None, - region=None, - use_given_order=False, - allow_conflicting_locales=False, - ): + languages: Iterable[str] | None = None, + locales: Iterable[str] | None = None, + region: str | None = None, + use_given_order: bool = False, + allow_conflicting_locales: bool = False, + ) -> Iterator[Locale]: """ Yield locale instances. @@ -138,7 +139,7 @@ def get_locales( ): yield locale - def get_locale(self, shortname): + def get_locale(self, shortname: str) -> Locale: """ Get a locale instance. @@ -148,36 +149,37 @@ def get_locale(self, shortname): :return: locale instance """ - return list(self.get_locales(locales=[shortname]))[0] + return next(iter(self.get_locales(locales=[shortname]))) - def _load_data( + def _load_data( # noqa: PLR0912 self, - languages=None, - locales=None, - region=None, - use_given_order=False, - allow_conflicting_locales=False, - ): - locale_dict = OrderedDict() + languages: Iterable[str] | None = None, + locales: Iterable[str] | None = None, + region: str | None = None, + use_given_order: bool = False, + allow_conflicting_locales: bool = False, + ) -> Iterator[tuple[str, Locale]]: + locale_dict: dict[str, tuple[str, ...]] = {} if locales: invalid_locales = [] for locale in locales: - lang_reg = LOCALE_SPLIT_PATTERN.split(locale) - if len(lang_reg) == 1: - lang_reg.append("") - locale_dict[locale] = tuple(lang_reg) + split_locale = LOCALE_SPLIT_PATTERN.split(locale) + if len(split_locale) == 1: + split_locale.append("") + locale_dict[locale] = tuple(split_locale) if not _isvalidlocale(locale): invalid_locales.append(locale) if invalid_locales: raise ValueError( - "Unknown locale(s): %s" % ", ".join(map(repr, invalid_locales)) + f"Unknown locale(s): {', '.join(map(repr, invalid_locales))}" ) - if not allow_conflicting_locales: - if len(set(locales)) > len({t[0] for t in locale_dict.values()}): - raise ValueError( - "Locales should not have same language and different region" - ) + if not allow_conflicting_locales and len(set(locales)) > len( + {t[0] for t in locale_dict.values()} + ): + raise ValueError( + "Locales should not have same language and different region" + ) else: if languages is None: @@ -185,8 +187,7 @@ def _load_data( unsupported_languages = set(languages) - set(language_order) if unsupported_languages: raise ValueError( - "Unknown language(s): %s" - % ", ".join(map(repr, unsupported_languages)) + f"Unknown language(s): {', '.join(map(repr, unsupported_languages))}" ) if region is None: region = "" @@ -198,27 +199,34 @@ def _load_data( ) if not use_given_order: - locale_dict = OrderedDict( + locale_dict = dict( sorted(locale_dict.items(), key=lambda x: language_order.index(x[1][0])) ) for shortname, lang_reg in locale_dict.items(): - if shortname not in self._loaded_locales: - lang, reg = lang_reg - if lang in self._loaded_languages: - locale = Locale( - shortname, language_info=deepcopy(self._loaded_languages[lang]) - ) - self._loaded_locales[shortname] = locale - else: - language_info = getattr( - import_module("dateparser.data.date_translation_data." + lang), - "info", - ) - locale = Locale(shortname, language_info=deepcopy(language_info)) - self._loaded_languages[lang] = language_info - self._loaded_locales[shortname] = locale - yield shortname, self._loaded_locales[shortname] + with self._load_lock: + if shortname not in self._loaded_locales: + lang, _reg = lang_reg + if lang in self._loaded_languages: + locale_obj = Locale( + shortname, + language_info=deepcopy(self._loaded_languages[lang]), + ) + else: + language_info = ( + import_module( + "dateparser.data.date_translation_data." + lang + ) + ).info + locale_obj = Locale( + shortname, language_info=deepcopy(language_info) + ) + self._loaded_languages[lang] = language_info + # Store only once fully built so concurrent readers never see + # a half-initialised locale. + self._loaded_locales[shortname] = locale_obj + locale_obj = self._loaded_locales[shortname] + yield shortname, locale_obj default_loader = LocaleDataLoader() diff --git a/dateparser/languages/locale.py b/dateparser/languages/locale.py index d47ab528b..ae9832986 100644 --- a/dateparser/languages/locale.py +++ b/dateparser/languages/locale.py @@ -1,15 +1,38 @@ -from collections import OrderedDict -from itertools import chain +import copy +import threading +from collections.abc import Iterable, Iterator, Mapping, Sequence +from itertools import chain, islice, product +from typing import TYPE_CHECKING, Any, TypeVar import regex as re -from dateutil import parser from dateparser.timezone_parser import pop_tz_offset_from_string, word_is_tz from dateparser.utils import combine_dicts, normalize_unicode from .dictionary import ALWAYS_KEEP_TOKENS, Dictionary, NormalizedDictionary +if TYPE_CHECKING: + from dateparser.conf import Settings + +_D = TypeVar("_D", bound=Dictionary) +_T = TypeVar("_T") + NUMERAL_PATTERN = re.compile(r"(\d+)", re.U) +_MAX_TRANSLATIONS = 16 + + +def _parse_bool(value: object) -> bool: + if isinstance(value, bool): + return value + if isinstance(value, str): + return value.strip().lower() in ("true", "1", "yes") + return False + + +# Punctuation a word can be written next to without ceasing to be that word: +# it is looked up in the dictionary without it, and the translation carries +# it on so the text and its translation keep the same separators. +PUNCTUATION = "()\"'{}[],.،" class Locale: @@ -27,27 +50,36 @@ class Locale: :return: A Locale instance """ - _dictionary = None - _normalized_dictionary = None - _simplifications = None - _normalized_simplifications = None - _splitters = None - _wordchars = None - _relative_translations = None - _normalized_relative_translations = None - _abbreviations = None - _split_dictionary = None - _wordchars_for_detection = None - - def __init__(self, shortname, language_info): + _dictionary: Dictionary | None = None + _normalized_dictionary: NormalizedDictionary | None = None + _simplifications: list[dict[re.Pattern[str], str]] | None = None + _normalized_simplifications: list[dict[re.Pattern[str], str]] | None = None + _splitters: dict[str, set[str]] | None = None + _wordchars: set[str] | None = None + _relative_translations: dict[re.Pattern[str], str] | None = None + _normalized_relative_translations: dict[re.Pattern[str], str] | None = None + _abbreviations: list[str] | None = None + _split_dictionary: dict[str, str | None] | None = None + _wordchars_for_detection: set[str] | None = None + + def __init__(self, shortname: str, language_info: Mapping[str, Any]) -> None: self.shortname = shortname locale_specific_info = language_info.get("locale_specific", {}).get( shortname, {} ) self.info = combine_dicts(language_info, locale_specific_info) self.info.pop("locale_specific", None) - - def is_applicable(self, date_string, strip_timezone=False, settings=None): + # This locale instance is cached and shared across threads; the lock + # guards lazy initialisation of the cached attributes below. + self._lock = threading.RLock() + + def is_applicable( + self, + date_string: str, + strip_timezone: bool = False, + settings: "Settings | None" = None, + ignore_surrounding_text: bool = False, + ) -> bool: """ Check if the locale is applicable to translate date string. @@ -59,20 +91,33 @@ def is_applicable(self, date_string, strip_timezone=False, settings=None): If True, timezone is stripped from date string. :type strip_timezone: bool + :param ignore_surrounding_text: + If True, tokens that the locale does not recognise are ignored at + the edges of the date string (``IGNORE_SURROUNDING_TEXT`` setting). + :type ignore_surrounding_text: bool + :return: boolean value representing if the locale is applicable for the date string or not. """ if strip_timezone: date_string, _ = pop_tz_offset_from_string(date_string, as_offset=False) date_string = self._translate_numerals(date_string) + assert settings is not None if settings.NORMALIZE: date_string = normalize_unicode(date_string) date_string = self._simplify(date_string, settings=settings) dictionary = self._get_dictionary(settings) date_tokens = dictionary.split(date_string) + if ignore_surrounding_text: + date_tokens = dictionary._strip_unknown_edge_tokens(date_tokens) return dictionary.are_tokens_valid(date_tokens) - def count_applicability(self, text, strip_timezone=False, settings=None): + def count_applicability( + self, + text: str, + strip_timezone: bool = False, + settings: "Settings | None" = None, + ) -> list[int]: if strip_timezone: text, _ = pop_tz_offset_from_string(text, as_offset=False) @@ -83,7 +128,9 @@ def count_applicability(self, text, strip_timezone=False, settings=None): tokens.extend(self._split(sent, keep_formatting=False, settings=settings)) return self._count_words_present_in_the_dictionary(tokens, settings) - def _count_words_present_in_the_dictionary(self, words, settings=None): + def _count_words_present_in_the_dictionary( + self, words: Iterable[str], settings: "Settings | None" = None + ) -> list[int]: dictionary = self.clean_dictionary( self._get_split_dictionary(settings=settings) ) @@ -100,16 +147,21 @@ def _count_words_present_in_the_dictionary(self, words, settings=None): return [dict_cnt, skip_cnt] @staticmethod - def clean_dictionary(dictionary, threshold=2): - del_keys = [] - for key in dictionary: - if len(key) < threshold: - del_keys.append(key) + def clean_dictionary( + dictionary: dict[str, _T], threshold: int = 2 + ) -> dict[str, _T]: + del_keys = [key for key in dictionary if len(key) < threshold] for del_key in del_keys: del dictionary[del_key] return dictionary - def translate(self, date_string, keep_formatting=False, settings=None): + def translate( + self, + date_string: str, + keep_formatting: bool = False, + settings: "Settings | None" = None, + ignore_surrounding_text: bool = False, + ) -> str: """ Translate the date string to its English equivalent. @@ -121,83 +173,192 @@ def translate(self, date_string, keep_formatting=False, settings=None): If True, retain formatting of the date string after translation. :type keep_formatting: bool + :param ignore_surrounding_text: + If True, tokens that the locale does not recognise are dropped from + the edges of the date string before translation + (``IGNORE_SURROUNDING_TEXT`` setting). + :type ignore_surrounding_text: bool + :return: translated date string. """ + translation = self._translate( + date_string, + keep_formatting=keep_formatting, + settings=settings, + ignore_surrounding_text=ignore_surrounding_text, + ) + assert translation is not None + return translation + + def _translate( # noqa: PLR0912, PLR0915 + self, + date_string: str, + keep_formatting: bool = False, + settings: "Settings | None" = None, + ignore_surrounding_text: bool = False, + alternative: int = 0, + ) -> str | None: + """Return the translation of *date_string* that reads its words with + several meanings according to the combination of meanings with index + *alternative*, where 0 is the combination that :meth:`translate` uses, + or ``None`` if there is no such combination.""" + if alternative >= _MAX_TRANSLATIONS: + return None date_string = self._translate_numerals(date_string) + assert settings is not None if settings.NORMALIZE: date_string = normalize_unicode(date_string) date_string = self._simplify(date_string, settings=settings) dictionary = self._get_dictionary(settings) date_string_tokens = dictionary.split(date_string, keep_formatting) + if ignore_surrounding_text: + date_string_tokens = dictionary._strip_unknown_edge_tokens( + date_string_tokens + ) relative_translations = self._get_relative_translations(settings=settings) - for i, word in enumerate(date_string_tokens): - word = word.lower() + ambiguous_tokens: dict[int, list[str]] = {} + # A token that could be either a weekday or a month abbreviation (see + # Dictionary._weekday_month_conflicts) can only be the weekday if another, + # unambiguous month is present elsewhere in the string - otherwise it keeps + # meaning a month, as it does everywhere else in the string's locale. + has_unambiguous_month = any( + dictionary._is_unambiguous_month(token.lower()) + for token in date_string_tokens + ) + + for i, token in enumerate(date_string_tokens): + word = token.lower() for pattern, replacement in relative_translations.items(): if pattern.match(word): date_string_tokens[i] = pattern.sub(replacement, word) break else: - if word in dictionary: + if ( + has_unambiguous_month + and word in dictionary._weekday_month_conflicts + ): + date_string_tokens[i] = dictionary._weekday_month_conflicts[word] + elif word in dictionary: fallback = word if keep_formatting and not word.isalpha() else "" date_string_tokens[i] = dictionary[word] or fallback + meanings = dictionary._get_meanings(word) + if len(meanings) > 1: + ambiguous_tokens[i] = meanings + if alternative: + combinations = product(*ambiguous_tokens.values()) + combination = next(islice(combinations, alternative, None), None) + if combination is None: + return None + for i, meaning in zip(ambiguous_tokens, combination, strict=True): + date_string_tokens[i] = meaning if "in" in date_string_tokens: date_string_tokens = self._clear_future_words(date_string_tokens) + + # Remove empty tokens (skip words) and handle adjacent whitespace + # When a skip token is removed between spaces, keep the maximum number of spaces + filtered_tokens: list[str] = [] + i = 0 + while i < len(date_string_tokens): + token = date_string_tokens[i] + + # Skip empty tokens (removed skip words) + if not token: + # Count preceding spaces already in filtered_tokens + prev_spaces = 0 + j = len(filtered_tokens) - 1 + while j >= 0 and filtered_tokens[j] == " ": + prev_spaces += 1 + j -= 1 + + # Count following spaces in the remaining tokens + next_spaces = 0 + j = i + 1 + while j < len(date_string_tokens) and date_string_tokens[j] == " ": + next_spaces += 1 + j += 1 + + # If surrounded by spaces, keep max(prev_spaces, next_spaces) + if prev_spaces > 0 and next_spaces > 0: + # Remove prev_spaces from filtered_tokens + for _ in range(prev_spaces): + filtered_tokens.pop() + + # Add back the maximum number of spaces + max_spaces = max(prev_spaces, next_spaces) + filtered_tokens.extend(" " * max_spaces) + + # Skip the empty token and all following spaces + i += next_spaces + 1 + continue + + i += 1 + continue + + filtered_tokens.append(token) + i += 1 + return self._join( - list(filter(bool, date_string_tokens)), + filtered_tokens, separator="" if keep_formatting else " ", settings=settings, ) - def _translate_numerals(self, date_string): + def _translate_numerals(self, date_string: str) -> str: date_string_tokens = NUMERAL_PATTERN.split(date_string) for i, token in enumerate(date_string_tokens): if token.isdecimal(): date_string_tokens[i] = str(int(token)).zfill(len(token)) return "".join(date_string_tokens) - def _get_relative_translations(self, settings=None): - if settings.NORMALIZE: - if self._normalized_relative_translations is None: - self._normalized_relative_translations = ( - self._generate_relative_translations(normalize=True) - ) - return self._normalized_relative_translations - else: + def _get_relative_translations( + self, settings: "Settings | None" = None + ) -> dict[re.Pattern[str], str]: + assert settings is not None + with self._lock: + if settings.NORMALIZE: + if self._normalized_relative_translations is None: + self._normalized_relative_translations = ( + self._generate_relative_translations(normalize=True) + ) + return self._normalized_relative_translations if self._relative_translations is None: self._relative_translations = self._generate_relative_translations( normalize=False ) return self._relative_translations - def _generate_relative_translations(self, normalize=False): + def _generate_relative_translations( + self, normalize: bool = False + ) -> dict[re.Pattern[str], str]: relative_translations = self.info.get("relative-type-regex", {}) - relative_dictionary = OrderedDict() + relative_dictionary = {} for key, value in relative_translations.items(): - if normalize: - value = list(map(normalize_unicode, value)) - pattern = "|".join(sorted(value, key=len, reverse=True)) + translations = map(normalize_unicode, value) if normalize else value + pattern = "|".join(sorted(translations, key=len, reverse=True)) pattern = pattern.replace(r"(\d+", r"(?P\d+") - pattern = re.compile( - r"^(?:{})$".format(pattern), re.UNICODE | re.IGNORECASE + compiled_pattern = re.compile( + rf"^(?:{pattern})$", re.UNICODE | re.IGNORECASE ) - relative_dictionary[pattern] = key + relative_dictionary[compiled_pattern] = key return relative_dictionary - def translate_search(self, search_string, settings=None): + def translate_search( # noqa: PLR0912 + self, search_string: str, settings: "Settings | None" = None + ) -> tuple[list[str], list[str]]: dashes = ["-", "——", "—", "~"] word_joint_unsupported_languages = ["zh", "ja"] sentences = self._sentence_split(search_string, settings=settings) dictionary = self._get_dictionary(settings=settings) - translated = [] - original = [] + translated: list[Any] = [] + original: list[Any] = [] for sentence in sentences: original_tokens, simplified_tokens = self._simplify_split_align( sentence, settings=settings ) - translated_chunk = [] - original_chunk = [] + translated_chunk: list[str | None] = [] + original_chunk: list[str] = [] last_token_index = len(simplified_tokens) - 1 skip_next_token = False for i, word in enumerate(simplified_tokens): @@ -209,7 +370,7 @@ def translate_search(self, search_string, settings=None): skip_next_token = False continue - if word == "" or word == " ": + if word in {"", " "}: translated_chunk.append(word) original_chunk.append(original_tokens[i]) elif ( @@ -228,28 +389,25 @@ def translate_search(self, search_string, settings=None): elif word in dictionary and word not in dashes: translated_chunk.append(dictionary[word]) original_chunk.append(original_tokens[i]) - elif word.strip("()\"'{}[],.،") in dictionary and word not in dashes: - punct = word[len(word.strip("()\"'{}[],.،")) :] - if punct and dictionary[word.strip("()\"'{}[],.،")]: - translated_chunk.append( - dictionary[word.strip("()\"'{}[],.،")] + punct - ) + elif word.strip(PUNCTUATION) in dictionary and word not in dashes: + bare_word = word.strip(PUNCTUATION) + punct = word[len(bare_word) :] + bare_translation = dictionary[bare_word] + if punct and bare_translation: + translated_chunk.append(bare_translation + punct) else: - translated_chunk.append(dictionary[word.strip("()\"'{}[],.،")]) + translated_chunk.append(bare_translation) original_chunk.append(original_tokens[i]) - elif self._token_with_digits_is_ok(word): - translated_chunk.append(word) - original_chunk.append(original_tokens[i]) - # Use original token because word_is_tz is case sensitive - elif translated_chunk and word_is_tz(original_tokens[i]): + elif self._token_with_digits_is_ok(word) or ( + translated_chunk and word_is_tz(original_tokens[i]) + ): translated_chunk.append(word) original_chunk.append(original_tokens[i]) - else: - if translated_chunk: - translated.append(translated_chunk) - translated_chunk = [] - original.append(original_chunk) - original_chunk = [] + elif translated_chunk: + translated.append(translated_chunk) + translated_chunk = [] + original.append(original_chunk) + original_chunk = [] if translated_chunk: translated.append(translated_chunk) original.append(original_chunk) @@ -264,17 +422,18 @@ def translate_search(self, search_string, settings=None): ) return translated, original - def _get_abbreviations(self, settings): + def _get_abbreviations(self, settings: "Settings | None") -> list[str]: dictionary = self._get_dictionary(settings=settings) - abbreviations = [] - if self._abbreviations is None: - for item in dictionary: - if item.endswith(".") and len(item) > 1: - abbreviations.append(item) - self._abbreviations = abbreviations - return self._abbreviations - - def _sentence_split(self, string, settings): + with self._lock: + if self._abbreviations is None: + self._abbreviations = [ + item for item in dictionary if item.endswith(".") and len(item) > 1 + ] + return self._abbreviations + + def _sentence_split( + self, string: str, settings: "Settings | None" + ) -> Iterator[str]: abbreviations = self._get_abbreviations(settings=settings) digit_abbreviations = ["[0-9]"] # numeric date with full stop abbreviation_string = "" @@ -298,6 +457,8 @@ def _sentence_split(self, string, settings): 5: r"[\r\n]+", # Thai 6: r"[\r\n؟!\.…]+(?:\s|$)+", } # Arabic and Farsi + # Full stops of fractional seconds and of dates like 13.07.2016. + abbreviation_string += r"(?!(?<=:\d\d)\.\d|(?<=\d)\.\d+\.\d|(?<=\d\.\d+)\.\d)" if "sentence_splitter_group" not in self.info: split_reg = abbreviation_string + splitters_dict[1] sentences = re.split(split_reg, string) @@ -308,10 +469,11 @@ def _sentence_split(self, string, settings): ) sentences = re.split(split_reg, string) - sentences = filter(None, sentences) - return sentences + return filter(None, sentences) - def _simplify_split_align(self, original, settings): + def _simplify_split_align( # noqa: PLR0912 + self, original: str, settings: "Settings | None" + ) -> tuple[list[str], list[str]]: # TODO: Switch to new split method. original_tokens = self._word_split(original, settings=settings) simplified_tokens = self._word_split( @@ -321,18 +483,17 @@ def _simplify_split_align(self, original, settings): if len(original_tokens) == len(simplified_tokens): return original_tokens, simplified_tokens - elif len(original_tokens) < len(simplified_tokens): + if len(original_tokens) < len(simplified_tokens): add_empty = False for i, token in enumerate(simplified_tokens): if i < len(original_tokens): if token == normalize_unicode(original_tokens[i].lower()): add_empty = False + elif not add_empty: + add_empty = True + continue else: - if not add_empty: - add_empty = True - continue - else: - original_tokens.insert(i, "") + original_tokens.insert(i, "") else: original_tokens.insert(i, "") else: @@ -341,12 +502,11 @@ def _simplify_split_align(self, original, settings): if i < len(simplified_tokens): if normalize_unicode(token.lower()) == simplified_tokens[i]: add_empty = False + elif not add_empty: + add_empty = True + continue else: - if not add_empty: - add_empty = True - continue - else: - simplified_tokens.insert(i, "") + simplified_tokens.insert(i, "") else: simplified_tokens.insert(i, "") @@ -357,14 +517,21 @@ def _simplify_split_align(self, original, settings): simplified_tokens.remove("") return original_tokens, simplified_tokens - def _get_split_dictionary(self, settings): - if self._split_dictionary is None: - settings.NORMALIZE = True - dictionary = self._get_dictionary(settings=settings) - self._split_dictionary = self._split_dict(dictionary) - return self._split_dictionary + def _get_split_dictionary( + self, settings: "Settings | None" + ) -> dict[str, str | None]: + assert settings is not None + with self._lock: + if self._split_dictionary is None: + # The split dictionary is always built from the normalized + # dictionary, regardless of the ``NORMALIZE`` setting. + dictionary = self._bind_settings( + self._get_normalized_dictionary(settings), settings + ) + self._split_dictionary = self._split_dict(dictionary) + return self._split_dictionary - def _split_dict(self, dictionary): + def _split_dict(self, dictionary: Dictionary) -> dict[str, str | None]: newdict = {} for item in dictionary: if " " in item: @@ -375,54 +542,54 @@ def _split_dict(self, dictionary): newdict[item] = dictionary[item] return newdict - def _word_split(self, string, settings): + def _word_split(self, string: str, settings: "Settings | None") -> list[str]: if "no_word_spacing" in self.info: return self._split(string, keep_formatting=True, settings=settings) - else: - return string.split() - - def _split(self, date_string, keep_formatting, settings=None): + return string.split() + + def _split( + self, + date_string: str, + keep_formatting: bool, + settings: "Settings | None" = None, + ) -> list[str]: tokens = [date_string] tokens = list(self._split_tokens_with_regex(tokens, r"(\d+)")) - tokens = list( + return list( self._split_tokens_by_known_words( tokens, keep_formatting, settings=settings ) ) - return tokens - def _split_tokens_with_regex(self, tokens, regex): + def _split_tokens_with_regex(self, tokens: list[Any], regex: str) -> Iterator[str]: tokens = tokens[:] for i, token in enumerate(tokens): tokens[i] = re.split(regex, token) return filter(bool, chain.from_iterable(tokens)) - def _split_tokens_by_known_words(self, tokens, keep_formatting, settings=None): + def _split_tokens_by_known_words( + self, + tokens: list[Any], + keep_formatting: bool, + settings: "Settings | None" = None, + ) -> list[str]: dictionary = self._get_dictionary(settings) for i, token in enumerate(tokens): tokens[i] = dictionary.split(token, keep_formatting) return list(chain.from_iterable(tokens)) - def _join_chunk(self, chunk, settings): + def _join_chunk(self, chunk: Sequence[str], settings: "Settings | None") -> str: if "no_word_spacing" in self.info: return self._join(chunk, separator="", settings=settings) - else: - return re.sub(r"\s{2,}", " ", " ".join(chunk)) + return re.sub(r"\s{2,}", " ", " ".join(chunk)) - def _token_with_digits_is_ok(self, token): + def _token_with_digits_is_ok(self, token: str) -> bool: if "no_word_spacing" in self.info: - if re.search(r"[\d\.:\-/]+", token) is not None: - return True - else: - return False + return re.search(r"[\d\.:\-/]+", token) is not None - else: - if re.search(r"\d+", token) is not None: - return True - else: - return False + return re.search(r"\d+", token) is not None - def _simplify(self, date_string, settings=None): + def _simplify(self, date_string: str, settings: "Settings | None" = None) -> str: date_string = date_string.lower() simplifications = self._get_simplifications(settings=settings) @@ -435,17 +602,25 @@ def _simplify(self, date_string, settings=None): return date_string - def _apply_simplifications(self, date_string, simplifications): + def _apply_simplifications( + self, + date_string: str, + simplifications: Iterable[Mapping[re.Pattern[str], str]], + ) -> str: for simplification in simplifications: - pattern, replacement = list(simplification.items())[0] + pattern, replacement = next(iter(simplification.items())) date_string = pattern.sub(replacement, date_string).lower() return date_string - def _process_russian_compound_ordinals(self, date_string, simplifications): + def _process_russian_compound_ordinals( + self, + date_string: str, + simplifications: Iterable[Mapping[re.Pattern[str], str]], + ) -> str: """Process Russian compound ordinals mathematically (двадцать + первое = 21).""" date_string = self._apply_simplifications(date_string, simplifications) - def replace_number_pairs(match): + def replace_number_pairs(match: re.Match[str]) -> str: first_num = int(match.group(1)) second_num = int(match.group(2)) result = first_num + second_num @@ -454,41 +629,50 @@ def replace_number_pairs(match): return match.group(0) number_pair_pattern = r"\b(\d+)\s+(\d+)\b" - date_string = re.sub(number_pair_pattern, replace_number_pairs, date_string) - - return date_string - - def _get_simplifications(self, settings=None): - no_word_spacing = eval(self.info.get("no_word_spacing", "False")) - if settings.NORMALIZE: - if self._normalized_simplifications is None: - self._normalized_simplifications = [] - simplifications = self._generate_simplifications(normalize=True) - for simplification in simplifications: - pattern, replacement = list(simplification.items())[0] - if not no_word_spacing: - pattern = r"(?<=\A|\W|_)%s(?=\Z|\W|_)" % pattern - pattern = re.compile(pattern, flags=re.I | re.U) - self._normalized_simplifications.append({pattern: replacement}) - return self._normalized_simplifications + return re.sub(number_pair_pattern, replace_number_pairs, date_string) + + def _get_simplifications( + self, settings: "Settings | None" = None + ) -> list[dict[re.Pattern[str], str]]: + no_word_spacing = _parse_bool(self.info.get("no_word_spacing", False)) + assert settings is not None + with self._lock: + if settings.NORMALIZE: + if self._normalized_simplifications is None: + normalized_simplifications = [] + simplifications = self._generate_simplifications(normalize=True) + for simplification in simplifications: + pattern, replacement = next(iter(simplification.items())) + if not no_word_spacing: + pattern = rf"(?<=\A|\W|_){pattern}(?=\Z|\W|_)" + compiled_pattern = re.compile(pattern, flags=re.I | re.U) + normalized_simplifications.append( + {compiled_pattern: replacement} + ) + # Assign only once fully built so other threads never observe + # a partially-populated list. + self._normalized_simplifications = normalized_simplifications + return self._normalized_simplifications - else: if self._simplifications is None: - self._simplifications = [] + simplifications_built = [] simplifications = self._generate_simplifications(normalize=False) for simplification in simplifications: - pattern, replacement = list(simplification.items())[0] + pattern, replacement = next(iter(simplification.items())) if not no_word_spacing: - pattern = r"(?<=\A|\W|_)%s(?=\Z|\W|_)" % pattern - pattern = re.compile(pattern, flags=re.I | re.U) - self._simplifications.append({pattern: replacement}) + pattern = rf"(?<=\A|\W|_){pattern}(?=\Z|\W|_)" + compiled_pattern = re.compile(pattern, flags=re.I | re.U) + simplifications_built.append({compiled_pattern: replacement}) + self._simplifications = simplifications_built return self._simplifications - def _generate_simplifications(self, normalize=False): + def _generate_simplifications( + self, normalize: bool = False + ) -> list[dict[str, str]]: simplifications = [] for simplification in self.info.get("simplifications", []): - c_simplification = {} - key, value = list(simplification.items())[0] + c_simplification: dict[str, str] = {} + key, value = next(iter(simplification.items())) if normalize: key = normalize_unicode(key) @@ -500,13 +684,22 @@ def _generate_simplifications(self, normalize=False): simplifications.append(c_simplification) return simplifications - def _clear_future_words(self, words): + def _clear_future_words(self, words: list[str]) -> list[str]: freshness_words = {"day", "week", "month", "year", "hour", "minute", "second"} - if set(words).isdisjoint(freshness_words): - words.remove("in") + # A unit keeps the punctuation it was written next to, so "2 hours," + # becomes "hour,". That is still the unit of a future expression, and + # dropping the "in" of one is what turns it into a past date. + bare_words = {word.strip(PUNCTUATION) for word in words if word} + if bare_words.isdisjoint(freshness_words): + words[words.index("in")] = "" return words - def _join(self, tokens, separator=" ", settings=None): + def _join( + self, + tokens: Sequence[str], + separator: str = " ", + settings: "Settings | None" = None, + ) -> str: if not tokens: return "" @@ -520,30 +713,53 @@ def _join(self, tokens, separator=" ", settings=None): return joined - def _get_dictionary(self, settings=None): + def _get_dictionary(self, settings: "Settings | None" = None) -> Dictionary: + assert settings is not None if not settings.NORMALIZE: + return self._bind_settings(self._get_base_dictionary(), settings) + return self._bind_settings(self._get_normalized_dictionary(settings), settings) + + def _get_base_dictionary(self) -> Dictionary: + with self._lock: if self._dictionary is None: self._generate_dictionary() - self._dictionary._settings = settings + assert self._dictionary is not None return self._dictionary - else: + + def _get_normalized_dictionary( + self, settings: "Settings | None" = None + ) -> NormalizedDictionary: + with self._lock: if self._normalized_dictionary is None: self._generate_normalized_dictionary() - self._normalized_dictionary._settings = settings + assert self._normalized_dictionary is not None return self._normalized_dictionary - def _get_wordchars(self, settings=None): - if self._wordchars is None: - self._set_wordchars(settings) - return self._wordchars - - def _get_splitters(self, settings=None): - if self._splitters is None: - self._set_splitters(settings) - return self._splitters - - def _set_splitters(self, settings=None): - splitters = { + @staticmethod + def _bind_settings(dictionary: _D, settings: "Settings") -> _D: + # A shallow copy shares the heavy state (translations, regex caches) by + # reference but gets its own settings, so the shared, cached dictionary + # instance is not mutated per call. + bound = copy.copy(dictionary) + bound._settings = settings + return bound + + def _get_wordchars(self, settings: "Settings | None" = None) -> set[str]: + with self._lock: + if self._wordchars is None: + self._set_wordchars(settings) + assert self._wordchars is not None + return self._wordchars + + def _get_splitters(self, settings: "Settings | None" = None) -> dict[str, set[str]]: + with self._lock: + if self._splitters is None: + self._set_splitters(settings) + assert self._splitters is not None + return self._splitters + + def _set_splitters(self, settings: "Settings | None" = None) -> None: + splitters: dict[str, set[str]] = { # The ones that split string only if they are not surrounded by letters from both sides: "wordchars": set(), # The ones that are not filtered out from tokens after split: @@ -561,8 +777,8 @@ def _set_splitters(self, settings=None): self._splitters = splitters - def _set_wordchars(self, settings=None): - wordchars = set() + def _set_wordchars(self, settings: "Settings | None" = None) -> None: + wordchars: set[str] = set() for word in self._get_dictionary(settings): if re.match(r"^[\W\d_]+$", word, re.UNICODE): continue @@ -582,9 +798,11 @@ def _set_wordchars(self, settings=None): "9", } - def get_wordchars_for_detection(self, settings): - if self._wordchars_for_detection is None: - wordchars = set() + def get_wordchars_for_detection(self, settings: "Settings | None") -> set[str]: + with self._lock: + if self._wordchars_for_detection is not None: + return self._wordchars_for_detection + wordchars: set[str] = set() for word in self._get_dictionary(settings): if re.match(r"^[\W\d_]+$", word, re.UNICODE): continue @@ -613,40 +831,10 @@ def get_wordchars_for_detection(self, settings): } return self._wordchars_for_detection - def _generate_dictionary(self, settings=None): + def _generate_dictionary(self, settings: "Settings | None" = None) -> None: self._dictionary = Dictionary(self.info, settings=settings) - def _generate_normalized_dictionary(self, settings=None): + def _generate_normalized_dictionary( + self, settings: "Settings | None" = None + ) -> None: self._normalized_dictionary = NormalizedDictionary(self.info, settings=settings) - - def to_parserinfo(self, base_cls=parser.parserinfo): - attributes = { - "JUMP": self.info.get("skip", []), - "PERTAIN": self.info.get("pertain", []), - "WEEKDAYS": [ - self.info["monday"], - self.info["tuesday"], - self.info["wednesday"], - self.info["thursday"], - self.info["friday"], - self.info["saturday"], - self.info["sunday"], - ], - "MONTHS": [ - self.info["january"], - self.info["february"], - self.info["march"], - self.info["april"], - self.info["may"], - self.info["june"], - self.info["july"], - self.info["august"], - self.info["september"], - self.info["october"], - self.info["november"], - self.info["december"], - ], - "HMS": [self.info["hour"], self.info["minute"], self.info["second"]], - } - name = "{language}ParserInfo".format(language=self.info["name"]) - return type(name, bases=[base_cls], dict=attributes) diff --git a/dateparser/languages/validation.py b/dateparser/languages/validation.py index 3b4233869..daffb55b7 100644 --- a/dateparser/languages/validation.py +++ b/dateparser/languages/validation.py @@ -1,12 +1,15 @@ +import logging +from typing import Any, ClassVar + import regex as re from dateparser.utils import get_logger class LanguageValidator: - logger = None + logger: logging.Logger | None = None - VALID_KEYS = [ + VALID_KEYS: ClassVar[list[str]] = [ "name", "skip", "pertain", @@ -40,17 +43,22 @@ class LanguageValidator: "hour", "minute", "second", + "early_morning", + "morning", + "afternoon", + "evening", + "night", "sentence_splitter_group", ] @classmethod - def get_logger(cls): + def get_logger(cls) -> logging.Logger: if cls.logger is None: cls.logger = get_logger() return cls.logger @classmethod - def validate_info(cls, language_id, info): + def validate_info(cls, language_id: str, info: Any) -> bool: result = True result &= cls._validate_type(language_id, info) @@ -70,7 +78,7 @@ def validate_info(cls, language_id, info): return result @classmethod - def _validate_type(cls, language_id, info): + def _validate_type(cls, language_id: str, info: Any) -> bool: result = True if not isinstance(info, dict): @@ -83,7 +91,7 @@ def _validate_type(cls, language_id, info): return result @classmethod - def _validate_name(cls, language_id, info): + def _validate_name(cls, language_id: str, info: Any) -> bool: result = True if "name" not in info or not isinstance(info["name"], str) or not info["name"]: @@ -95,7 +103,7 @@ def _validate_name(cls, language_id, info): return result @classmethod - def _validate_word_spacing(cls, language_id, info): + def _validate_word_spacing(cls, language_id: str, info: Any) -> bool: if "no_word_spacing" not in info: return True # Optional key @@ -113,7 +121,7 @@ def _validate_word_spacing(cls, language_id, info): return result @classmethod - def _validate_sentence_splitter_group(cls, language_id, info): + def _validate_sentence_splitter_group(cls, language_id: str, info: Any) -> bool: if "sentence_splitter_group" not in info: return True # Optional key @@ -139,7 +147,7 @@ def _validate_sentence_splitter_group(cls, language_id, info): return result @classmethod - def _validate_skip_list(cls, language_id, info): + def _validate_skip_list(cls, language_id: str, info: Any) -> bool: if "skip" not in info: return True # Optional key @@ -166,7 +174,7 @@ def _validate_skip_list(cls, language_id, info): return result @classmethod - def _validate_pertain_list(cls, language_id, info): + def _validate_pertain_list(cls, language_id: str, info: Any) -> bool: if "pertain" not in info: return True # Optional key @@ -193,7 +201,7 @@ def _validate_pertain_list(cls, language_id, info): return result @classmethod - def _validate_weekdays(cls, language_id, info): + def _validate_weekdays(cls, language_id: str, info: Any) -> bool: result = True for weekday in ( @@ -238,7 +246,7 @@ def _validate_weekdays(cls, language_id, info): return result @classmethod - def _validate_months(cls, language_id, info): + def _validate_months(cls, language_id: str, info: Any) -> bool: result = True for month in ( @@ -288,7 +296,7 @@ def _validate_months(cls, language_id, info): return result @classmethod - def _validate_units(cls, language_id, info): + def _validate_units(cls, language_id: str, info: Any) -> bool: result = True for unit in "year", "month", "week", "day", "hour", "minute", "second": @@ -325,7 +333,7 @@ def _validate_units(cls, language_id, info): return result @classmethod - def _validate_other_words(cls, language_id, info): + def _validate_other_words(cls, language_id: str, info: Any) -> bool: result = True for word in ("ago",): @@ -362,7 +370,7 @@ def _validate_other_words(cls, language_id, info): return result @classmethod - def _validate_simplifications(cls, language_id, info): + def _validate_simplifications(cls, language_id: str, info: Any) -> bool: if "simplifications" not in info: return True # Optional key @@ -380,7 +388,7 @@ def _validate_simplifications(cls, language_id, info): result = False continue - key, value = list(simplification.items())[0] + key, value = next(iter(simplification.items())) if not isinstance(key, str) or not isinstance(value, (str, int)): cls.get_logger().error( "Invalid simplification %(simplification)r for '%(id)s' language: " @@ -395,7 +403,7 @@ def _validate_simplifications(cls, language_id, info): replacements = re.findall(r"\\(\d+)", value) replacements.extend(re.findall(r"\\g<(.+?)>", value)) - groups = [] + groups: list[int] = [] for group in replacements: if group.isdigit(): groups.append(int(group)) @@ -414,7 +422,7 @@ def _validate_simplifications(cls, language_id, info): result = False used_groups = set(map(int, groups)) - expected_groups = set(range(0, compiled_key.groups + 1)) + expected_groups = set(range(compiled_key.groups + 1)) extra_groups = used_groups - expected_groups not_used_groups = expected_groups - used_groups not_used_groups -= {0} # Entire substring is not required to be used @@ -453,7 +461,7 @@ def _validate_simplifications(cls, language_id, info): return result @classmethod - def _validate_extra_keys(cls, language_id, info): + def _validate_extra_keys(cls, language_id: str, info: Any) -> bool: result = True extra_keys = set(info.keys()) - set(cls.VALID_KEYS) diff --git a/dateparser/parser.py b/dateparser/parser.py index 67a586e9b..d123cb2af 100644 --- a/dateparser/parser.py +++ b/dateparser/parser.py @@ -1,13 +1,18 @@ import calendar -from collections import OrderedDict -from datetime import datetime, timedelta, timezone +import contextlib +from collections.abc import Callable, Iterable, Iterator +from datetime import datetime, time, timedelta, tzinfo +from functools import partial from io import StringIO +from typing import TYPE_CHECKING, Any, ClassVar, Literal, overload import pytz import regex as re from dateparser.utils import ( _get_missing_parts, + _get_parts, + _now, get_last_day_of_month, get_next_leap_year, get_previous_leap_year, @@ -17,21 +22,23 @@ ) from dateparser.utils.strptime import strptime +if TYPE_CHECKING: + from dateparser.conf import Settings + NSP_COMPATIBLE = re.compile(r"\D+") MERIDIAN = re.compile(r"am|pm") MICROSECOND = re.compile(r"\d{1,6}") EIGHT_DIGIT = re.compile(r"^\d{8}$") HOUR_MINUTE_REGEX = re.compile(r"^([0-9]|0[0-9]|1[0-9]|2[0-3]):[0-5][0-9]$") +_RANGE_DASHES = {"-", "–"} -def no_space_parser_eligibile(datestring): +def no_space_parser_eligibile(datestring: str) -> bool: src = NSP_COMPATIBLE.search(datestring) - if not src or ":" == src.group(): - return True - return False + return not src or src.group() == ":" -def get_unresolved_attrs(parser_object): +def get_unresolved_attrs(parser_object: object) -> tuple[list[str], list[str]]: attrs = ["year", "month", "day"] seen = [] unseen = [] @@ -53,7 +60,15 @@ def get_unresolved_attrs(parser_object): } -def resolve_date_order(order, lst=None): +@overload +def resolve_date_order(order: str, lst: Literal[False] | None = None) -> str: ... + + +@overload +def resolve_date_order(order: str, lst: Literal[True]) -> list[str]: ... + + +def resolve_date_order(order: str, lst: bool | None = None) -> str | list[str]: chart_list = { "DMY": ["day", "month", "year"], "DYM": ["day", "year", "month"], @@ -66,16 +81,83 @@ def resolve_date_order(order, lst=None): return chart_list[order] if lst else date_order_chart[order] -def _parse_absolute(datestring, settings, tz=None): - return _parser.parse(datestring, settings, tz) - - -def _parse_nospaces(datestring, settings, tz=None): - return _no_spaces_parser.parse(datestring, settings) +class _StrictDateOrderError(ValueError): + """The date string does not fit DATE_ORDER as STRICT_DATE_ORDER requires: + a number was read as a part that the order does not put at its position, + or with "all", a number could not be read in that order at all. + The other parsers of the locale may still read the date string, but no + other locale should guess a reading of it.""" + + +_PART_OF_DIRECTIVE = {"%d": "day", "%m": "month", "%y": "year", "%Y": "year"} + + +def _strict_date_order(settings: "Settings") -> str: + """Return the STRICT_DATE_ORDER value in effect, which is "none" unless the + caller set DATE_ORDER.""" + if "DATE_ORDER" in settings._mod_settings: + return settings.STRICT_DATE_ORDER + return "none" + + +def _check_strict_date_order( + parts: list[str], four_digit_year: bool, date_order: str, strict: str +) -> None: + """Raise _StrictDateOrderError if *parts*, the parts of the date that were + read from numbers, in the order they were read, are not where DATE_ORDER + puts them, as far as *strict*, the STRICT_DATE_ORDER value, requires. A + month name and a missing part are not in *parts*, so they are not checked: + "32 DEC" with DMY is still December 2032.""" + if strict == "none": + return + order = resolve_date_order(date_order, lst=True) + if strict == "year": + # Any number that is not a valid day or month is read as a two-digit + # year, so check that it is where DATE_ORDER puts the year: in + # "32 DEC 10" with DMY, 32 is an invalid day, not the year 2032. Of the + # parts read, those before the year must be exactly those that the order + # puts before it, whichever way they are misplaced: "10 DEC 32" with MYD + # reads the day before the year. A four-digit year cannot be anything + # else. + if four_digit_year or "year" not in parts: + return + before_year = order[: order.index("year")] + if set(parts[: parts.index("year")]) != set(before_year).intersection(parts): + raise _StrictDateOrderError(f"The year is not where {date_order} puts it") + return + # "all": the day and month must be where DATE_ORDER puts them too, so they + # are not swapped when they do not fit. + if four_digit_year: + # A four-digit year is read wherever it is, and a date that starts + # with one is read as year, month and day unless DATE_ORDER starts + # with the year. + if parts[:1] == ["year"] and not date_order.startswith("Y"): + order = ["month", "day"] + parts = [part for part in parts if part != "year"] + if parts != [part for part in order if part in parts]: + raise _StrictDateOrderError(f"The date parts are not in {date_order} order") + + +def _parse_absolute( + datestring: str, + settings: "Settings", + tz: tzinfo | None = None, + date_order: str | None = None, +) -> tuple[datetime, str | None, tuple[str, ...]]: + return _parser.parse(datestring, settings, tz, date_order=date_order) + + +def _parse_nospaces( + datestring: str, + settings: "Settings", + tz: tzinfo | None = None, + date_order: str | None = None, +) -> tuple[datetime, str, tuple[str, ...]]: + return _no_spaces_parser.parse(datestring, settings, date_order=date_order) class _time_parser: - time_directives = [ + time_directives: ClassVar[list[str]] = [ "%H:%M:%S", "%I:%M:%S %p", "%H:%M", @@ -86,22 +168,21 @@ class _time_parser: "%H:%M %p", ] - def __call__(self, timestring): + def __call__(self, timestring: str) -> time: _timestring = timestring for directive in self.time_directives: try: return strptime(timestring.strip(), directive).time() except ValueError: pass - else: - raise ValueError("%s does not seem to be a valid time string" % _timestring) + raise ValueError(f"{_timestring} does not seem to be a valid time string") time_parser = _time_parser() class _no_spaces_parser: - _dateformats = [ + _dateformats: ClassVar[list[str]] = [ "%Y%m%d", "%Y%d%m", "%m%Y%d", @@ -116,9 +197,13 @@ class _no_spaces_parser: "%d%m%y", ] - _preferred_formats = ["%Y%m%d%H%M", "%Y%m%d%H%M%S", "%Y%m%d%H%M%S.%f"] + _preferred_formats: ClassVar[list[str]] = [ + "%Y%m%d%H%M", + "%Y%m%d%H%M%S", + "%Y%m%d%H%M%S.%f", + ] - _preferred_formats_ordered_8_digit = [ + _preferred_formats_ordered_8_digit: ClassVar[list[str]] = [ "%m%d%Y", "%d%m%Y", "%Y%m%d", @@ -127,13 +212,16 @@ class _no_spaces_parser: "%d%Y%m", ] - _timeformats = ["%H%M%S.%f", "%H%M%S", "%H%M", "%H"] + _timeformats: ClassVar[list[str]] = ["%H%M%S.%f", "%H%M%S", "%H%M", "%H"] - period = {"day": ["%d", "%H", "%M", "%S"], "month": ["%m"]} + period: ClassVar[dict[str, list[str]]] = { + "day": ["%d", "%H", "%M", "%S"], + "month": ["%m"], + } _default_order = resolve_date_order("MDY") - def __init__(self, *args, **kwargs): + def __init__(self, *args: Any, **kwargs: Any) -> None: self._all = ( self._dateformats + [x + y for x in self._dateformats for y in self._timeformats] @@ -167,36 +255,38 @@ def __init__(self, *args, **kwargs): } @classmethod - def _get_period(cls, format_string): + def _get_period(cls, format_string: str) -> str: for pname, pdrv in sorted(cls.period.items(), key=lambda x: x[0]): for drv in pdrv: if drv in format_string: return pname - else: - return "year" + return "year" @classmethod - def _find_best_matching_date(cls, datestring): + def _find_best_matching_date( + cls, datestring: str + ) -> tuple[datetime, str, tuple[str, ...]] | None: for fmt in cls._preferred_formats_ordered_8_digit: - try: - dt = strptime(datestring, fmt), cls._get_period(fmt) + with contextlib.suppress(Exception): + dt = strptime(datestring, fmt), cls._get_period(fmt), _get_parts(fmt) if len(str(dt[0].year)) == 4: return dt - except Exception: - pass return None @classmethod - def parse(cls, datestring, settings): + def parse( + cls, datestring: str, settings: "Settings", date_order: str | None = None + ) -> tuple[datetime, str, tuple[str, ...]]: if not no_space_parser_eligibile(datestring): - raise ValueError("Unable to parse date from: %s" % datestring) + raise ValueError(f"Unable to parse date from: {datestring}") datestring = datestring.replace(":", "") if not datestring: raise ValueError("Empty string") tokens = tokenizer(datestring) - if settings.DATE_ORDER: - order = resolve_date_order(settings.DATE_ORDER) + date_order = date_order or settings.DATE_ORDER + if date_order: + order = resolve_date_order(date_order) else: order = cls._default_order if EIGHT_DIGIT.match(datestring): @@ -204,89 +294,143 @@ def parse(cls, datestring, settings): if dt is not None: return dt nsp = cls() - ambiguous_date = None + found: tuple[tuple[datetime, str, tuple[str, ...]], str] | None = None + ambiguous: tuple[tuple[datetime, str, tuple[str, ...]], str] | None = None for token, _ in tokens.tokenize(): for fmt in nsp.date_formats[order]: - try: - dt = strptime(token, fmt), cls._get_period(fmt) + with contextlib.suppress(Exception): + dt = strptime(token, fmt), cls._get_period(fmt), _get_parts(fmt) if len(str(dt[0].year)) < 4: - ambiguous_date = dt + ambiguous = dt, fmt continue missing = _get_missing_parts(fmt) _check_strict_parsing(missing, settings) - return dt - except Exception: - pass - else: - if ambiguous_date: - return ambiguous_date - else: - raise ValueError("Unable to parse date from: %s" % datestring) + found = dt, fmt + if found: + break + if found: + break + found = found or ambiguous + if found is None: + raise ValueError(f"Unable to parse date from: {datestring}") + dt, fmt = found + # The formats are only sorted by DATE_ORDER, so the one that matched + # may read the numbers in another order. + _check_strict_date_order( + [_PART_OF_DIRECTIVE[directive] for directive in re.findall("%[dmyY]", fmt)], + four_digit_year="%Y" in fmt, + date_order=date_order, + strict=_strict_date_order(settings), + ) + return dt -def _get_missing_error(missing): +def _get_missing_error(missing: Iterable[str]) -> str: return "Fields missing from the date string: {}".format(", ".join(missing)) -def _check_strict_parsing(missing, settings): +def _check_strict_parsing(missing: list[str], settings: "Settings") -> None: if settings.STRICT_PARSING and missing: raise ValueError(_get_missing_error(missing)) - elif settings.REQUIRE_PARTS and missing: + if settings.REQUIRE_PARTS and missing: errors = [part for part in settings.REQUIRE_PARTS if part in missing] if errors: raise ValueError(_get_missing_error(errors)) class _parser: - alpha_directives = OrderedDict( - [ - ("weekday", ["%A", "%a"]), - ("month", ["%B", "%b"]), - ] - ) + alpha_directives: ClassVar[dict[str, list[str]]] = { + "weekday": ["%A", "%a"], + "month": ["%B", "%b"], + } - num_directives = { + num_directives: ClassVar[dict[str, list[str]]] = { "month": ["%m"], "day": ["%d"], "year": ["%y", "%Y"], } - def __init__(self, tokens, settings): + day: int | None + month: int | None + year: int | None + time: Callable[[], time] | None + now: datetime + _token_day: tuple[str, int] | str | int | None + _token_month: tuple[str, int] | str | int | None + _token_year: tuple[str, int] | str | None + _token_time: str | None + + def __init__( # noqa: PLR0912, PLR0915 + self, + tokens: Iterable[tuple[str, int]], + settings: "Settings", + date_order: str | None = None, + tz: tzinfo | None = None, + ) -> None: self.settings = settings + self._tz = tz + self._date_order = date_order or settings.DATE_ORDER + self._strict = _strict_date_order(settings) self.tokens = [(t[0].strip(), t[1]) for t in list(tokens)] self.filtered_tokens = [ (t[0], t[1], i) for i, t in enumerate(self.tokens) if t[1] <= 1 ] - - self.unset_tokens = [] + # Move a meridian written before a time (e.g. Chinese 下午 02:26) after + # it, where the time parsing below looks for it. + for i in range(len(self.filtered_tokens) - 1): + current, following = self.filtered_tokens[i : i + 2] + preceding = self.filtered_tokens[i - 1][0] if i else "" + if ( + current[0] in ("am", "pm") + and ":" in following[0] + and ":" not in preceding + ): + self.filtered_tokens[i : i + 2] = [following, current] + + self.unset_tokens: list[tuple[str, int, str]] = [] self.day = None self.month = None self.year = None self.time = None - self.auto_order = [] + self.auto_order: list[str] = [] self._token_day = None self._token_month = None self._token_year = None self._token_time = None - self.ordered_num_directives = OrderedDict( - (k, self.num_directives[k]) - for k in (resolve_date_order(settings.DATE_ORDER, lst=True)) + self.ordered_num_directives = { + k: self.num_directives[k] + for k in resolve_date_order(self._date_order, lst=True) + } + numbers = sorted( + (t[0] for t in self.filtered_tokens if t[1] == 0 and t[0].isdigit()), + key=len, ) - - skip_index = [] - skip_component = None + if ( + not any(t[1] == 1 for t in self.filtered_tokens) + and len(numbers) == 2 + and len(numbers[0]) <= 2 + and len(numbers[1]) == 4 + ): + # A year and a single other number (e.g. "05/2020"): the other + # number is the month whatever the date order. + self.ordered_num_directives = { + k: self.num_directives[k] for k in ("month", "day", "year") + } + + skip_index: list[int] = [] + skip_component: str | None = None skip_tokens = ["t", "year", "hour", "minute"] for index, token_type_original_index in enumerate(self.filtered_tokens): if index in skip_index: continue - token, type, original_index = token_type_original_index + token, token_type, original_index = token_type_original_index if token in skip_tokens: continue @@ -294,7 +438,7 @@ def __init__(self, tokens, settings): if self.time is None: meridian_index = index + 1 - try: + with contextlib.suppress(Exception): # try case where hours and minutes are separated by a period. Example: 13.20. _is_before_period = self.tokens[original_index + 1][0] == "." _is_after_period = ( @@ -321,11 +465,9 @@ def __init__(self, tokens, settings): token = new_token skip_index.append(index + 1) meridian_index += 1 - except Exception: - pass try: - microsecond = MICROSECOND.search( + microsecond = MICROSECOND.search( # type: ignore[union-attr] self.filtered_tokens[index + 1][0] ).group() # Is after time token? raise ValueError if ':' can't be found: @@ -339,7 +481,7 @@ def __init__(self, tokens, settings): meridian_index += 1 try: - meridian = MERIDIAN.search( + meridian = MERIDIAN.search( # type: ignore[union-attr] self.filtered_tokens[meridian_index][0] ).group() except Exception: @@ -347,41 +489,127 @@ def __init__(self, tokens, settings): if any([":" in token, meridian, microsecond]): if meridian and not microsecond: - self._token_time = "%s %s" % (token, meridian) + self._token_time = f"{token} {meridian}" skip_index.append(meridian_index) elif microsecond and not meridian: - self._token_time = "%s.%s" % (token, microsecond) + self._token_time = f"{token}.{microsecond}" skip_index.append(index + 1) elif meridian and microsecond: - self._token_time = "%s.%s %s" % (token, microsecond, meridian) + self._token_time = f"{token}.{microsecond} {meridian}" skip_index.append(index + 1) skip_index.append(meridian_index) else: self._token_time = token - self.time = lambda: time_parser(self._token_time) + self.time = partial(time_parser, self._token_time) continue - results = self._parse(type, token, skip_component=skip_component) + results = self._parse(token_type, token, skip_component=skip_component) for res in results: if len(token) == 4 and res[0] == "year": skip_component = "year" setattr(self, *res) known, unknown = get_unresolved_attrs(self) - params = {} + unset_tokens = [ + unset_token + for unset_token in self.unset_tokens + if not ( + self._token_day and self._is_range(self._token_day[0], unset_token[0]) + ) + ] + if unset_tokens and self._strict == "all": + # A four-digit year displaced a number that was read as the year, + # so that number was not where DATE_ORDER puts the year. + raise _StrictDateOrderError( + f"{unset_tokens[0][0]} is not where {self._date_order} puts it" + ) + _check_strict_date_order( + self.auto_order, + four_digit_year=self._token_year is not None + and len(self._token_year[0]) == 4, + date_order=self._date_order, + strict=self._strict, + ) + if len(unset_tokens) > len(unknown): + raise ValueError("Too many numbers in date string") + params: dict[str, int] = {} for attr in known: params.update({attr: getattr(self, attr)}) for attr in unknown: - for token, type, _ in self.unset_tokens: - if type == 0: + for token, token_type, _ in unset_tokens: + if token_type == 0: params.update({attr: int(token)}) - setattr(self, "_token_%s" % attr, token) + setattr(self, f"_token_{attr}", token) setattr(self, attr, int(token)) - def _get_period(self): - if self.settings.RETURN_TIME_AS_PERIOD: - if getattr(self, "time", None): - return "time" + def _is_range(self, first: object, last: object) -> bool: + """Return whether *first* and *last* are the ends of a range, e.g. 12 + and 14 in “June 12-14, 2021”. A dash before *first* or after *last* + makes them part of a date instead, e.g. 4 and 25 in “6-4-25”.""" + + def is_dash(index: int) -> bool: + return ( + 0 <= index < len(self.tokens) + and self.tokens[index][0].lstrip(".") in _RANGE_DASHES + ) + + return any( + self.tokens[index][0] == first + and is_dash(index + 1) + and self.tokens[index + 2][0] == last + and not is_dash(index - 1) + and not is_dash(index + 3) + for index in range(len(self.tokens) - 2) + ) + + @classmethod + def _has_month_name(cls, tokens: Iterable[tuple[str, int]]) -> bool: + for token, token_type in tokens: + if token_type != 1: + continue + for directive in cls.alpha_directives["month"]: + try: + strptime(token.strip(), directive) + return True + except ValueError: + pass + return False + + def _month_number_becomes_day(self) -> None: + """Record in auto_order that the number read as the month is the day, + now that a month name was found, and that the other end of the range, + which was read as the day, is dropped. That end comes after the month + in "12-14 June" with MDY, but before it in "12-12 June" with DMY.""" + if self.day: + self.auto_order.remove("day") + self.auto_order[self.auto_order.index("month")] = "day" + + def _unparsed_number_error(self, token: str) -> ValueError: + """Return the error for a number that fits none of the parts of the date + that are left in the order.""" + if self._strict == "all" and self._is_date_part(token): + # The number is a date part, but not where DATE_ORDER puts it, so + # the date string cannot be read in that order: no other locale + # may read it either, e.g. as a relative date. + return _StrictDateOrderError( + f"{token} is not where {self._date_order} puts it" + ) + return ValueError(f"Unable to parse: {token}") + + def _is_date_part(self, token: str) -> bool: + """Return whether *token* can be read as a day, month or year.""" + for directives in self.num_directives.values(): + for directive in directives: + try: + self._get_date_obj(token, directive) + except ValueError: + continue + return True + return False + + def _get_period(self) -> str: + if self.settings.RETURN_TIME_AS_PERIOD and getattr(self, "time", None): + return "time" for period in ["time", "day"]: if getattr(self, period, None): @@ -391,10 +619,19 @@ def _get_period(self): if getattr(self, period, None): return period - if self._results(): - return "day" + return "day" + + def _get_parts(self) -> tuple[str, ...]: + parts = tuple(part for part in ("year", "month", "day") if getattr(self, part)) + if not parts and (hasattr(self, "_token_weekday") or self.time): + # A weekday or a time on its own is resolved to a full date by + # _correct_for_time_frame. + parts = ("year", "month", "day") + if self.time: + parts += ("time",) + return parts - def _get_datetime_obj(self, **params): + def _get_datetime_obj(self, **params: Any) -> datetime: try: return datetime(**params) except ValueError as e: @@ -407,7 +644,7 @@ def _get_datetime_obj(self, **params): params["year"], params["month"] ) return datetime(**params) - elif ( + if ( not self._token_year and params["day"] == 29 and params["month"] == 2 @@ -418,9 +655,9 @@ def _get_datetime_obj(self, **params): self.settings.PREFER_DATES_FROM, params["year"] ) return datetime(**params) - raise e + raise - def _get_correct_leap_year(self, prefer_dates_from, current_year): + def _get_correct_leap_year(self, prefer_dates_from: str, current_year: int) -> int: if prefer_dates_from == "future": return get_next_leap_year(current_year) if prefer_dates_from == "past": @@ -434,16 +671,14 @@ def _get_correct_leap_year(self, prefer_dates_from, current_year): ) return next_leap_year if next_leap_year_is_closer else previous_leap_year - def _set_relative_base(self): - self.now = self.settings.RELATIVE_BASE - if not self.now: - self.now = datetime.now(tz=timezone.utc).replace(tzinfo=None) + def _set_relative_base(self) -> None: + self.now = self.settings.RELATIVE_BASE or _now(self.settings, self._tz) - def _get_datetime_obj_params(self): + def _get_datetime_obj_params(self) -> dict[str, int]: if not self.now: self._set_relative_base() - params = { + return { "day": self.day or self.now.day, "month": self.month or self.now.month, "year": self.year or self.now.year, @@ -452,12 +687,11 @@ def _get_datetime_obj_params(self): "second": 0, "microsecond": 0, } - return params - def _get_date_obj(self, token, directive): + def _get_date_obj(self, token: str, directive: str) -> datetime: return strptime(token, directive) - def _results(self): + def _results(self) -> datetime: missing = [ field for field in ("day", "month", "year") if not getattr(self, field) ] @@ -469,17 +703,19 @@ def _results(self): if time: params.update( - dict( - hour=time.hour, - minute=time.minute, - second=time.second, - microsecond=time.microsecond, - ) + { + "hour": time.hour, + "minute": time.minute, + "second": time.second, + "microsecond": time.microsecond, + } ) return self._get_datetime_obj(**params) - def _correct_for_time_frame(self, dateobj, tz): + def _correct_for_time_frame( # noqa: PLR0912, PLR0915 + self, dateobj: datetime, tz: tzinfo | None + ) -> datetime: days = ["mon", "tue", "wed", "thu", "fri", "sat", "sun"] token_weekday, _ = getattr(self, "_token_weekday", (None, None)) @@ -500,10 +736,7 @@ def _correct_for_time_frame(self, dateobj, tz): delta = timedelta(days=steps) else: if days[day_index] == day: - if self.settings.PREFER_DATES_FROM == "past": - steps = 7 - else: - steps = 0 + steps = 7 if self.settings.PREFER_DATES_FROM == "past" else 0 else: while days[day_index] != day: day_index -= 1 @@ -533,28 +766,26 @@ def _correct_for_time_frame(self, dateobj, tz): if self.month and not self.year: try: - if self.now < dateobj: + if self.now < self._correct_for_day(dateobj): if self.settings.PREFER_DATES_FROM == "past": dateobj = dateobj.replace(year=dateobj.year - 1) - else: - if self.settings.PREFER_DATES_FROM == "future": - dateobj = dateobj.replace(year=dateobj.year + 1) - except ValueError as e: + elif self.settings.PREFER_DATES_FROM == "future": + dateobj = dateobj.replace(year=dateobj.year + 1) + except ValueError: if dateobj.day == 29 and dateobj.month == 2: valid_year = self._get_correct_leap_year( self.settings.PREFER_DATES_FROM, dateobj.year ) dateobj = dateobj.replace(year=valid_year) else: - raise e + raise if self._token_year and len(self._token_year[0]) == 2: if self.now < dateobj: if "past" in self.settings.PREFER_DATES_FROM: dateobj = dateobj.replace(year=dateobj.year - 100) - else: - if "future" in self.settings.PREFER_DATES_FROM: - dateobj = dateobj.replace(year=dateobj.year + 100) + elif "future" in self.settings.PREFER_DATES_FROM: + dateobj = dateobj.replace(year=dateobj.year + 100) if self._token_time and not any( [ @@ -564,27 +795,31 @@ def _correct_for_time_frame(self, dateobj, tz): hasattr(self, "_token_weekday"), ] ): - # Convert dateobj to utc time to compare with self.now - try: - tz = tz or get_timezone_from_tz_string(self.settings.TIMEZONE) - tz_offset = tz.utcoffset(dateobj) - except (pytz.UnknownTimeZoneError, pytz.NonExistentTimeError): - tz_offset = timedelta(hours=0) - - if "past" in self.settings.PREFER_DATES_FROM: - if self.now < dateobj - tz_offset: - dateobj = dateobj + timedelta(days=-1) - if "future" in self.settings.PREFER_DATES_FROM: - if self.now > dateobj - tz_offset: - dateobj = dateobj + timedelta(days=1) + tz_offset = timedelta(hours=0) + if self.settings.RELATIVE_BASE: + # Convert dateobj to utc time to compare with RELATIVE_BASE + try: + tz = tz or get_timezone_from_tz_string(self.settings.TIMEZONE) + tz_offset = tz.utcoffset(dateobj) or tz_offset + except (pytz.UnknownTimeZoneError, pytz.NonExistentTimeError): + pass + + if ( + "past" in self.settings.PREFER_DATES_FROM + and self.now < dateobj - tz_offset + ): + dateobj = dateobj + timedelta(days=-1) + if ( + "future" in self.settings.PREFER_DATES_FROM + and self.now > dateobj - tz_offset + ): + dateobj = dateobj + timedelta(days=1) # Reset dateobj to the original value, thus removing any offset awareness that may # have been set earlier. - dateobj = dateobj.replace(tzinfo=original_dateobj.tzinfo) - - return dateobj + return dateobj.replace(tzinfo=original_dateobj.tzinfo) - def _correct_for_day(self, dateobj): + def _correct_for_day(self, dateobj: datetime) -> datetime: if ( getattr(self, "_token_day", None) or getattr(self, "_token_weekday", None) @@ -592,30 +827,48 @@ def _correct_for_day(self, dateobj): ): return dateobj - dateobj = set_correct_day_from_settings( + return set_correct_day_from_settings( dateobj, self.settings, current_day=self.now.day ) - return dateobj - - def _correct_for_month(self, dateobj): - relative_base = getattr(self.settings, "RELATIVE_BASE", None) - relative_base_month = ( - relative_base.month if hasattr(relative_base, "month") else relative_base - ) + def _correct_for_month(self, dateobj: datetime) -> datetime: if getattr(self, "_token_month", None): return dateobj - dateobj = set_correct_month_from_settings( - dateobj, self.settings, relative_base_month + return set_correct_month_from_settings( + dateobj, self.settings, current_month=self.now.month ) - return dateobj @classmethod - def parse(cls, datestring, settings, tz=None): - tokens = tokenizer(datestring) - po = cls(tokens.tokenize(), settings) - dateobj = po._results() + def parse( + cls, + datestring: str, + settings: "Settings", + tz: tzinfo | None = None, + date_order: str | None = None, + ) -> tuple[datetime, str | None, tuple[str, ...]]: + tokens = list(tokenizer(datestring).tokenize()) + date_order = date_order or settings.DATE_ORDER + try: + po = cls(tokens, settings, date_order=date_order, tz=tz) + dateobj = po._results() + except ValueError as error: + if ( + "DATE_ORDER" not in settings._mod_settings + # The swap would replace a reading that STRICT_DATE_ORDER + # rejected with a date that the default never gives, and + # "all" forbids the swap altogether. + or isinstance(error, _StrictDateOrderError) + or settings.STRICT_DATE_ORDER == "all" + or str(error).startswith("Fields missing") + or cls._has_month_name(tokens) + ): + raise + # The numbers do not fit the date order set by the caller, so read + # them with the day and month swapped, e.g. "2021-01-13" with YDM. + swapped = date_order.translate(str.maketrans("DM", "MD")) + po = cls(tokens, settings, date_order=swapped, tz=tz) + dateobj = po._results() # correction for past, future if applicable dateobj = po._correct_for_time_frame(dateobj, tz) @@ -629,90 +882,148 @@ def parse(cls, datestring, settings, tz=None): period = po._get_period() - return dateobj, period - - def _parse(self, type, token, skip_component=None): - def set_and_return(token, type, component, dateobj, skip_date_order=False): + return dateobj, period, po._get_parts() + + def _parse( + self, token_type: int, token: str, skip_component: str | None = None + ) -> list[tuple[str, int]]: + def set_and_return( + token: str, + token_type: int, + component: str, + dateobj: Any, + skip_date_order: bool = False, + ) -> list[tuple[str, int]]: if not skip_date_order: self.auto_order.append(component) - setattr(self, "_token_%s" % component, (token, type)) + setattr(self, f"_token_{component}", (token, token_type)) return [(component, getattr(dateobj, component))] - def parse_number(token, skip_component=None): - type = 0 - - for component, directives in self.ordered_num_directives.items(): - if skip_component == component: - continue - for directive in directives: - try: - do = self._get_date_obj(token, directive) - prev_value = getattr(self, component, None) - if not prev_value: - return set_and_return(token, type, component, do) - else: + def parse_number( + token: str, skip_component: str | None = None + ) -> list[tuple[str, int]]: + token_type = 0 + + num_directives = self.ordered_num_directives + if ( + skip_component == "year" + and self.day is None + and self.month is None + and not self._date_order.startswith("Y") + ): + # The date string starts with a four-digit year (e.g. an + # ISO 8601 date like "2017-06-22"), so the remaining numeric + # components are expected in month-day order, unless the date + # order itself puts the year first (e.g. YDM). + num_directives = { + k: self.num_directives[k] for k in ("month", "day", "year") + } + + def try_directives( + skip_directive: str | None = None, + ) -> list[tuple[str, int]]: + for component, directives in num_directives.items(): + if skip_component == component: + continue + for directive in directives: + if directive == skip_directive: + continue + try: + do = self._get_date_obj(token, directive) + prev_value = getattr(self, component, None) + if not prev_value: + return set_and_return(token, token_type, component, do) try: prev_token, prev_type = getattr( - self, "_token_%s" % component + self, f"_token_{component}" ) - if prev_type == type: + if prev_type == token_type: do = self._get_date_obj(prev_token, directive) except ValueError: self.unset_tokens.append( (prev_token, prev_type, component) ) - return set_and_return(token, type, component, do) - except ValueError: - pass - else: - raise ValueError("Unable to parse: %s" % token) + return set_and_return(token, token_type, component, do) + except ValueError: + pass + raise self._unparsed_number_error(token) + + order = list(self.ordered_num_directives) + components_after_year = order[order.index("year") + 1 :] + year_position_already_passed = any( + getattr(self, component) is not None + for component in components_after_year + ) + if year_position_already_passed: + # A component that the date order places after the year has + # already been found, so the year position in the date string + # has already been passed and this number cannot be a + # two-digit year: in "4月20日" ("April 20"), 20 is the day, + # not the year 2020 (#519). Read it as a two-digit year only + # if it cannot be anything else (e.g. 99 in "4-99"). + try: + return try_directives(skip_directive="%y") + except ValueError: + pass + return try_directives() - def parse_alpha(token, skip_component=None): - type = 1 + def parse_alpha( + token: str, skip_component: str | None = None + ) -> list[tuple[str, int]]: + token_type = 1 for component, directives in self.alpha_directives.items(): if skip_component == component: continue for directive in directives: - try: + with contextlib.suppress(Exception): do = self._get_date_obj(token, directive) prev_value = getattr(self, component, None) if not prev_value: return set_and_return( - token, type, component, do, skip_date_order=True + token, token_type, component, do, skip_date_order=True + ) + if component == "month" and ( + not self.day + or self._is_range( + self._token_month[0], # type: ignore[index] + self._token_day[0], # type: ignore[index] ) - elif component == "month": - index = self.auto_order.index("month") - self.auto_order[index] = "day" - setattr(self, "_token_day", self._token_month) - setattr(self, "_token_month", (token, type)) + ): + # A number read as the month becomes the day, which + # requires the day to be free, or to be the end of + # a range that starts at that number, e.g. 14 in + # “12-14 June”. + self._month_number_becomes_day() + self._token_day = self._token_month + self._token_month = token, token_type return [ (component, getattr(do, component)), ("day", prev_value), ] - except Exception: - pass - else: - raise ValueError("Unable to parse: %s" % token) + raise ValueError(f"Unable to parse: {token}") - handlers = {0: parse_number, 1: parse_alpha} - return handlers[type](token, skip_component) + handlers: dict[int, Callable[[str, str | None], list[tuple[str, int]]]] = { + 0: parse_number, + 1: parse_alpha, + } + return handlers[token_type](token, skip_component) class tokenizer: digits = "0123456789:" letters = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ" - def _isletter(self, tkn): + def _isletter(self, tkn: str) -> bool: return tkn in self.letters - def _isdigit(self, tkn): + def _isdigit(self, tkn: str) -> bool: return tkn in self.digits - def __init__(self, ds): + def __init__(self, ds: str) -> None: self.instream = StringIO(ds) - def _switch(self, chara, charb): + def _switch(self, chara: str, charb: str) -> tuple[int, bool]: if self._isdigit(chara): return 0, not self._isdigit(charb) @@ -721,7 +1032,7 @@ def _switch(self, chara, charb): return 2, self._isdigit(charb) or self._isletter(charb) - def tokenize(self): + def tokenize(self) -> Iterator[tuple[str, int]]: token = "" EOF = False @@ -730,17 +1041,17 @@ def tokenize(self): if not nextchar: EOF = True - type, _ = self._switch(token[-1], nextchar) - yield token, type + token_type, _ = self._switch(token[-1], nextchar) + yield token, token_type return if token: - type, switch = self._switch(token[-1], nextchar) + token_type, switch = self._switch(token[-1], nextchar) if not switch: token += nextchar else: - yield token, type + yield token, token_type token = nextchar else: token += nextchar diff --git a/dateparser/search/__init__.py b/dateparser/search/__init__.py index a1707b679..6a9a2f6c7 100644 --- a/dateparser/search/__init__.py +++ b/dateparser/search/__init__.py @@ -1,15 +1,21 @@ +from collections.abc import Callable, Iterable +from datetime import datetime +from typing import Any + +from dateparser.conf import Settings from dateparser.search.search import DateSearchWithDetection _search_with_detection = DateSearchWithDetection() def search_dates( - text, - languages=None, - settings=None, - add_detected_language=False, - detect_languages_function=None, -): + text: str, + languages: Iterable[str] | None = None, + settings: Settings | dict[str, Any] | None = None, + add_detected_language: bool = False, + detect_languages_function: Callable[..., list[str]] | None = None, + strategy: str = "split", +) -> list[tuple[str, datetime]] | list[tuple[str, datetime, str | None]] | None: """Find all substrings of the given string which represent date and/or time and parse them. :param text: @@ -35,6 +41,13 @@ def search_dates( Note: detect_languages_function is only uses if `languages` are not provided. :type detect_languages_function: function + :param strategy: + The search strategy to use: "split" (default) translates the text and splits it + into chunks that are likely to contain dates, while "ngram" tries to parse the + longest possible sequences of tokens as dates. The "ngram" strategy tends to + produce more predictable results, at the cost of more parse attempts. + :type strategy: str + :return: Returns list of tuples containing: substrings representing date and/or time, corresponding :mod:`datetime.datetime` object and detected language if *add_detected_language* is True. @@ -64,10 +77,12 @@ def search_dates( languages=languages, settings=settings, detect_languages_function=detect_languages_function, + strategy=strategy, ) dates = result.get("Dates") if dates: if add_detected_language: language = result.get("Language") - dates = [date + (language,) for date in dates] + return [(*date, language) for date in dates] return dates + return None diff --git a/dateparser/search/detection.py b/dateparser/search/detection.py index 9103d0513..74f1db530 100644 --- a/dateparser/search/detection.py +++ b/dateparser/search/detection.py @@ -1,36 +1,50 @@ +from collections.abc import Callable, Iterator from functools import wraps +from typing import TYPE_CHECKING, Concatenate, ParamSpec, TypeVar +if TYPE_CHECKING: + from dateparser.conf import Settings + from dateparser.languages.locale import Locale -def _restore_languages_on_generator_exit(method): +_S = TypeVar("_S", bound="BaseLanguageDetector") +_P = ParamSpec("_P") + + +def _restore_languages_on_generator_exit( + method: Callable[Concatenate[_S, _P], Iterator["Locale"]], +) -> Callable[Concatenate[_S, _P], Iterator["Locale"]]: @wraps(method) - def wrapped(self, *args, **kwargs): + def wrapped(self: _S, /, *args: _P.args, **kwargs: _P.kwargs) -> Iterator["Locale"]: stored_languages = self.languages[:] - for language in method(self, *args, **kwargs): - yield language - else: - self.languages[:] = stored_languages + yield from method(self, *args, **kwargs) + self.languages[:] = stored_languages return wrapped class BaseLanguageDetector: - def __init__(self, languages): + def __init__(self, languages: list["Locale"]) -> None: self.languages = languages[:] @_restore_languages_on_generator_exit - def iterate_applicable_languages(self, date_string, settings=None, modify=False): + def iterate_applicable_languages( + self, + date_string: str, + settings: "Settings | None" = None, + modify: bool = False, + ) -> Iterator["Locale"]: languages = self.languages if modify else self.languages[:] yield from self._filter_languages(date_string, languages, settings) @staticmethod - def _filter_languages(date_string, languages, settings=None): + def _filter_languages( + date_string: str, languages: list["Locale"], settings: "Settings | None" = None + ) -> Iterator["Locale"]: while languages: language = languages[0] if language.is_applicable( date_string, strip_timezone=False, settings=settings - ): - yield language - elif language.is_applicable( + ) or language.is_applicable( date_string, strip_timezone=True, settings=settings ): yield language @@ -39,13 +53,20 @@ def _filter_languages(date_string, languages, settings=None): class AutoDetectLanguage(BaseLanguageDetector): - def __init__(self, languages, allow_redetection=False): + def __init__( + self, languages: list["Locale"], allow_redetection: bool = False + ) -> None: super().__init__(languages=languages[:]) self.language_pool = languages[:] self.allow_redetection = allow_redetection @_restore_languages_on_generator_exit - def iterate_applicable_languages(self, date_string, modify=False, settings=None): + def iterate_applicable_languages( # type: ignore[override] + self, + date_string: str, + modify: bool = False, + settings: "Settings | None" = None, + ) -> Iterator["Locale"]: languages = self.languages if modify else self.languages[:] initial_languages = languages[:] yield from self._filter_languages(date_string, languages, settings=settings) @@ -66,13 +87,18 @@ def iterate_applicable_languages(self, date_string, modify=False, settings=None) class ExactLanguages(BaseLanguageDetector): - def __init__(self, languages): + def __init__(self, languages: list["Locale"] | None) -> None: if languages is None: raise ValueError("language cannot be None for ExactLanguages") super().__init__(languages=languages) @_restore_languages_on_generator_exit - def iterate_applicable_languages(self, date_string, modify=False, settings=None): + def iterate_applicable_languages( # type: ignore[override] + self, + date_string: str, + modify: bool = False, + settings: "Settings | None" = None, + ) -> Iterator["Locale"]: yield from super().iterate_applicable_languages( date_string, modify=False, settings=settings ) diff --git a/dateparser/search/ngram_search.py b/dateparser/search/ngram_search.py new file mode 100644 index 000000000..4c3376df5 --- /dev/null +++ b/dateparser/search/ngram_search.py @@ -0,0 +1,114 @@ +"""Date search based on parsing token n-grams. + +This module implements an alternative strategy for +:func:`dateparser.search.search_dates` that looks for the longest sequences +of tokens that can be parsed as dates. It originates from a production date +extraction pipeline where it consistently produced more predictable results +than the translation-based search. +""" + +import logging +from collections.abc import Sequence +from datetime import datetime + +import regex as re + +from dateparser.conf import Settings +from dateparser.date import DateDataParser + +logger = logging.getLogger(__name__) + +# Characters that never occur inside a date expression and can therefore be +# used to split a text into tokens. Unlike whitespace, ",", "|", "(", ")" +# and "@", characters such as ".", "/", "-" and ":" *can* be part of a date +# (e.g. "1.10.2020", "2020-10-01", "10:30") and must not be split on. +_TOKEN_RE = re.compile(r"[^\s,|()@]+") + +# Words that often connect a date to the surrounding text and cause +# annoying false positives; dropping them allows parsing token sequences +# such as "on May 6th 2004" or "6 of October". +_NOISE_TOKENS = frozenset(["on", "at", "of", "a"]) + +# Whole candidates that are blacklisted because they are known to produce +# false positives. They can still be parsed as part of a longer candidate. +_BAD_CANDIDATE_RE = re.compile( + "^(" + + "|".join( # noqa: FLY002 + [ + r"\d{1,3}", # bare numbers of less than 4 digits + r"#\d+", # sequence numbers + r"[-/.]+", # bare separators, parsed as the current date + r"\w\.?", # single letters, with an optional dot + "an", # parsed as a year in some languages + ] + ) + + ")$" +) + +# Punctuation stripped from the returned substrings, matching the behavior +# of the translation-based search strategy. +_STRIP_CHARS = " .,:()[]-'" + + +class _NgramDateSearch: + """Search for dates by trying to parse token n-grams, longest first. + + The text is split into tokens using characters that never occur inside + a date expression as separators. The tokens are then scanned left to + right; at each position the longest n-gram (up to ``max_tokens`` + tokens) is tried first, so that the most complete date is parsed. + Whenever an n-gram is parsed successfully, the scan continues after it, + so the reported dates never overlap. + """ + + def __init__(self, max_tokens: int = 7) -> None: + self.max_tokens = max_tokens + + def search_parse( + self, languages: list[str], text: str, settings: Settings + ) -> list[tuple[str, datetime]]: + """Find all dates in ``text`` and return ``(substring, date)`` pairs. + + ``languages`` are tried in the given order for every candidate + n-gram. + """ + parser = DateDataParser( + languages=languages, use_given_order=True, settings=settings + ) + tokens = [ + token + for token in _TOKEN_RE.finditer(text) + if token.group() not in _NOISE_TOKENS + ] + results: list[tuple[str, datetime]] = [] + index = 0 + while index < len(tokens): + for size in range(min(self.max_tokens, len(tokens) - index), 0, -1): + ngram = tokens[index : index + size] + candidate = " ".join(token.group() for token in ngram) + if _BAD_CANDIDATE_RE.match(candidate): + continue + date_obj = self._parse_candidate(parser, candidate, languages) + if date_obj is not None: + substring = text[ngram[0].start() : ngram[-1].end()] + results.append((substring.strip(_STRIP_CHARS), date_obj)) + index += size + break + else: + index += 1 + return results + + @staticmethod + def _parse_candidate( + parser: DateDataParser, candidate: str, languages: Sequence[str] + ) -> datetime | None: + try: + return parser.get_date_data(candidate).date_obj + except Exception: + logger.warning( + "Failed to parse %r (languages=%r)", + candidate, + languages, + exc_info=True, + ) + return None diff --git a/dateparser/search/search.py b/dateparser/search/search.py index 3d38d2792..2db342a5c 100644 --- a/dateparser/search/search.py +++ b/dateparser/search/search.py @@ -1,38 +1,71 @@ -from collections.abc import Set +from collections.abc import Callable, Iterable, Sequence +from collections.abc import Set as AbstractSet from datetime import datetime +from typing import Any, TypedDict import regex as re from dateparser.conf import Settings, apply_settings, check_settings from dateparser.custom_language_detection.language_mapping import map_languages -from dateparser.date import DateDataParser +from dateparser.date import DateData, DateDataParser +from dateparser.freshness_date_parser import _UNITS from dateparser.languages.loader import LocaleDataLoader +from dateparser.languages.locale import Locale +from dateparser.search.ngram_search import _NgramDateSearch from dateparser.search.text_detection import FullTextLanguageDetector from dateparser.utils.time_spans import detect_time_span, generate_time_span RELATIVE_REG = re.compile("(ago|in|from now|tomorrow|today|yesterday)") +# How a relative expression looks once translated. A single word such as "today" +# turns into several words ("0 day ago"), which is why the translation of a +# chunk can hold more words than the text it was translated from. +TRANSLATED_RELATIVE_REG = re.compile( + rf"\bin \d+ (?:{_UNITS})s?\b|\b\d+ (?:{_UNITS})s? ago\b" +) -def date_is_relative(translation): + +class _SearchResult(TypedDict): + Language: str | None + Dates: list[tuple[str, datetime]] | None + + +def date_is_relative(translation: str) -> bool: return re.search(RELATIVE_REG, translation) is not None +def _add_time_span_results( + results: list[tuple[str, datetime]], text: str, settings: Settings +) -> list[tuple[str, datetime]]: + """Append time span start/end dates if RETURN_TIME_SPAN is enabled.""" + if getattr(settings, "RETURN_TIME_SPAN", False): + span_info = detect_time_span(text) + if span_info: + base_date = getattr(settings, "RELATIVE_BASE", None) or datetime.now() + start_date, end_date = generate_time_span(span_info, base_date, settings) + matched_text = span_info["matched_text"] + results.append((matched_text + " (start)", start_date)) + results.append((matched_text + " (end)", end_date)) + return results + + class _ExactLanguageSearch: - def __init__(self, loader): + def __init__(self, loader: LocaleDataLoader) -> None: self.loader = loader - self.language = None - def get_current_language(self, shortname): - if self.language is None or self.language.shortname != shortname: - self.language = self.loader.get_locale(shortname) + def get_current_language(self, shortname: str) -> Locale: + return self.loader.get_locale(shortname) - def search(self, shortname, text, settings): - self.get_current_language(shortname) - result = self.language.translate_search(text, settings=settings) - return result + def search( + self, shortname: str, text: str, settings: Settings + ) -> tuple[list[str], list[str]]: + language = self.get_current_language(shortname) + return language.translate_search(text, settings=settings) @staticmethod - def set_relative_base(substring, already_parsed): + def set_relative_base( + substring: str, already_parsed: Sequence[tuple[DateData, bool]] + ) -> tuple[str, datetime | None]: if len(already_parsed) == 0: return substring, None @@ -44,8 +77,12 @@ def set_relative_base(substring, already_parsed): relative_base = already_parsed[i][0]["date_obj"] return substring, relative_base - def choose_best_split(self, possible_parsed_splits, possible_substrings_splits): - rating = [] + def choose_best_split( + self, + possible_parsed_splits: Sequence[list[tuple[DateData, bool]]], + possible_substrings_splits: Sequence[list[str]], + ) -> tuple[list[tuple[DateData, bool]], list[str]]: + rating: list[list[float]] = [] for i in range(len(possible_parsed_splits)): num_substrings = len(possible_substrings_splits[i]) num_substrings_without_digits = 0 @@ -66,7 +103,7 @@ def choose_best_split(self, possible_parsed_splits, possible_substrings_splits): else (float(num_substrings_without_digits) / float(num_substrings)), ] ) - best_index, best_rating = min( + best_index, _best_rating = min( enumerate(rating), key=lambda p: (p[1][1], p[1][0], p[1][2]) ) return ( @@ -74,7 +111,9 @@ def choose_best_split(self, possible_parsed_splits, possible_substrings_splits): possible_substrings_splits[best_index], ) - def split_by(self, item, original, splitter): + def split_by( + self, item: str, original: str, splitter: str + ) -> list[list[list[str]]]: if item.count(splitter) <= 2: return [[item.split(splitter), original.split(splitter)]] @@ -92,15 +131,137 @@ def split_by(self, item, original, splitter): all_possible_splits.append([item_partially_split, original_partially_split]) return all_possible_splits - def split_if_not_parsed(self, item, original): - splitters = [",", "،", "——", "—", "–", ".", " "] + def split_by_relative_expression( + self, + parser: DateDataParser, + item: str, + original: str, + language: Locale, + settings: Settings, + ) -> list[list[list[str]]]: + """Split a chunk into a relative expression and the date next to it. + + A word translated into a multi-word relative expression gives the + translation more separators than the text it was translated from, which + is what keeps the splitters above from lining the two up. Cutting the + chunk in two where the expression ends lines them up again, once the + word the expression was translated from is known and the rest of the + chunk turns out to be the date it was written next to. + """ + words = original.split() + possible_splits: list[list[list[str]]] = [] + for match in TRANSLATED_RELATIVE_REG.finditer(item): + before = item[: match.start()].strip() + after = item[match.end() :].strip() + if bool(before) == bool(after): + # The expression is the whole chunk, or sits between two parts of + # it, which leaves no boundary the original text can be cut at. + continue + rest = after or before + if len(rest.split()) != len(words) - 1: + # What is left of the translation does not keep one word per + # remaining original one, so it would not line up either. + continue + index = 1 if after else len(words) - 1 + expression = words[0] if after else words[-1] + if language.translate(expression, settings=settings) != match.group(): + # The word next to the boundary is not the one the expression was + # translated from: some other word of the chunk also changed the + # word count, and only made the one above add up. + continue + if parser.get_date_data(rest)["date_obj"] is None: + # There is no date next to the expression, so cutting the chunk + # would report the expression and drop the rest of it. + continue + possible_splits.append( + [ + [match.group(), after] if after else [before, match.group()], + [" ".join(words[:index]), " ".join(words[index:])], + ] + ) + return possible_splits + + def split_around_skipped_words( + self, item: str, original: str, language: Locale, settings: Settings + ) -> list[list[list[str]]]: + """Split a chunk by spaces, ignoring the words its translation skips. + + Words like "and" or "of" are left out of the translation but not of + the original text, so splitting both by spaces does not line them up. + Each part of the original text spans from its first word that is not + skipped to its last one. + """ + words = original.split() + kept = [] + for index, word in enumerate(words): + translation = language.translate(word, settings=settings).split() + if len(translation) > 1: + return [] + if translation: + kept.append(index) + item_words = item.split() + if len(kept) == len(words) or len(kept) != len(item_words): + return [] + sizes = [1] if len(kept) <= 3 else [1, 2, 3] possible_splits = [] + for size in sizes: + starts = range(0, len(kept), size) + possible_splits.append( + [ + [" ".join(item_words[i : i + size]) for i in starts], + [ + " ".join(words[kept[i] : kept[i : i + size][-1] + 1]) + for i in starts + ], + ] + ) + return possible_splits + + def split_off_leading_number( + self, parser: DateDataParser, item: str, original: str + ) -> list[list[list[str]]]: + """Split a chunk that starts with a number into that number and the + rest, to find a date written after a number that is not part of it, + e.g. the decimals of “-58.5” before “06 Mar 2009”.""" + number, _, rest = item.partition(" ") + original_number, _, original_rest = original.partition(" ") + if ( + not number.isdigit() + or number != original_number + or parser.get_date_data(rest)["date_obj"] is None + ): + return [] + return [[[number, rest], [original_number, original_rest]]] + + def split_if_not_parsed( + self, + parser: DateDataParser, + item: str, + original: str, + language: Locale, + settings: Settings, + ) -> list[list[list[str]]]: + splitters = [",", "،", "——", "—", "–", ".", " "] + possible_splits = self.split_off_leading_number(parser, item, original) for splitter in splitters: if splitter in item and item.count(splitter) == original.count(splitter): possible_splits.extend(self.split_by(item, original, splitter)) + if not possible_splits: + # Only when no splitter lines up, so that a chunk which already + # splits keeps being split exactly the way it is split today. + possible_splits = self.split_by_relative_expression( + parser, item, original, language, settings + ) or self.split_around_skipped_words(item, original, language, settings) return possible_splits - def parse_item(self, parser, item, translated_item, parsed, need_relative_base): + def parse_item( + self, + parser: DateDataParser, + item: str, + translated_item: str, + parsed: Sequence[tuple[DateData, bool]], + need_relative_base: bool, + ) -> tuple[DateData, bool]: relative_base = None item = item.replace("ngày", "") item = item.replace("am", "") @@ -111,12 +272,20 @@ def parse_item(self, parser, item, translated_item, parsed, need_relative_base): item, relative_base = self.set_relative_base(item, parsed) if relative_base: - parser._settings.RELATIVE_BASE = relative_base + parser._settings = parser._settings.replace(RELATIVE_BASE=relative_base) parsed_item = parser.get_date_data(item) return parsed_item, is_relative - def parse_found_objects(self, parser, to_parse, original, translated, settings): - parsed = [] + def parse_found_objects( + self, + parser: DateDataParser, + to_parse: Sequence[str], + original: Sequence[str], + translated: Sequence[str], + settings: Settings, + language: Locale, + ) -> tuple[list[tuple[DateData, bool]], list[str]]: + parsed: list[tuple[DateData, bool]] = [] substrings = [] need_relative_base = True if settings.RELATIVE_BASE: @@ -133,15 +302,17 @@ def parse_found_objects(self, parser, to_parse, original, translated, settings): substrings.append(original[i].strip(" .,:()[]-'")) continue - possible_splits = self.split_if_not_parsed(item, original[i]) + possible_splits = self.split_if_not_parsed( + parser, item, original[i], language, settings + ) if not possible_splits: continue - possible_parsed = [] - possible_substrings = [] + possible_parsed: list[list[tuple[DateData, bool]]] = [] + possible_substrings: list[list[str]] = [] for split_translated, split_original in possible_splits: - current_parsed = [] - current_substrings = [] + current_parsed: list[tuple[DateData, bool]] = [] + current_substrings: list[str] = [] if split_translated: for j, jtem in enumerate(split_translated): if len(jtem) <= 2: @@ -149,7 +320,7 @@ def parse_found_objects(self, parser, to_parse, original, translated, settings): parsed_jtem, is_relative_jtem = self.parse_item( parser, jtem, - split_translated[j], + jtem, current_parsed, need_relative_base, ) @@ -166,7 +337,10 @@ def parse_found_objects(self, parser, to_parse, original, translated, settings): substrings.append(substrings_best[k]) return parsed, substrings - def search_parse(self, shortname, text, settings): + def search_parse( + self, shortname: str, text: str, settings: Settings + ) -> list[tuple[str, datetime]]: + language = self.get_current_language(shortname) translated, original = self.search(shortname, text, settings) bad_translate_with_search = [ "vi", @@ -186,23 +360,13 @@ def search_parse(self, shortname, text, settings): original=original, translated=translated, settings=settings, + language=language, ) - results = list(zip(substrings, [i[0]["date_obj"] for i in parsed])) - - if getattr(settings, "RETURN_TIME_SPAN", False): - span_info = detect_time_span(text) - if span_info: - base_date = getattr(settings, "RELATIVE_BASE", None) or datetime.now() - start_date, end_date = generate_time_span( - span_info, base_date, settings - ) + results = list(zip(substrings, [i[0]["date_obj"] for i in parsed], strict=True)) - matched_text = span_info["matched_text"] - results.append((matched_text + " (start)", start_date)) - results.append((matched_text + " (end)", end_date)) + _add_time_span_results(results, text, settings) - parser._settings = Settings() return results @@ -213,15 +377,33 @@ class DateSearchWithDetection: """ - def __init__(self): + def __init__(self) -> None: self.loader = LocaleDataLoader() self.available_language_map = self.loader.get_locale_map() self.search = _ExactLanguageSearch(self.loader) + self.ngram_search = _NgramDateSearch() + + def _get_candidate_languages( + self, detected_language: str | None, languages: Iterable[str] | None + ) -> list[str]: + candidates = [] + if detected_language: + candidates.append(detected_language) + + if isinstance(languages, (list, tuple, AbstractSet)) and len(languages) > 1: + candidates.extend(languages) + + return list(dict.fromkeys(candidates)) @apply_settings def detect_language( - self, text, languages, settings=None, detect_languages_function=None - ): + self, + text: str, + languages: Iterable[str] | None, + settings: Settings | dict[str, Any] | None = None, + detect_languages_function: Callable[..., list[str]] | None = None, + ) -> str | None: + assert isinstance(settings, Settings) if detect_languages_function and not languages: detected_languages = detect_languages_function( text, @@ -232,9 +414,10 @@ def detect_language( ) return detected_languages[0] if detected_languages else None - if isinstance(languages, (list, tuple, Set)): - if all([language in self.available_language_map for language in languages]): - languages = [ + locales = None + if isinstance(languages, (list, tuple, AbstractSet)): + if all(language in self.available_language_map for language in languages): + locales = [ self.available_language_map[language] for language in languages ] else: @@ -242,30 +425,33 @@ def detect_language( self.available_language_map.keys() ) raise ValueError( - "Unknown language(s): %s" - % ", ".join(map(repr, unsupported_languages)) + f"Unknown language(s): {', '.join(map(repr, unsupported_languages))}" ) elif languages is not None: raise TypeError( - "languages argument must be a list (%r given)" % type(languages) + f"languages argument must be a list ({type(languages)!r} given)" ) - if languages: - self.language_detector = FullTextLanguageDetector(languages=languages) + if locales: + language_detector = FullTextLanguageDetector(languages=locales) else: - self.language_detector = FullTextLanguageDetector( + language_detector = FullTextLanguageDetector( list(self.available_language_map.values()) ) - detected_language = self.language_detector._best_language(text) or ( + return language_detector._best_language(text) or ( settings.DEFAULT_LANGUAGES[0] if settings.DEFAULT_LANGUAGES else None ) - return detected_language @apply_settings def search_dates( - self, text, languages=None, settings=None, detect_languages_function=None - ): + self, + text: str, + languages: Iterable[str] | None = None, + settings: Settings | dict[str, Any] | None = None, + detect_languages_function: Callable[..., list[str]] | None = None, + strategy: str = "split", + ) -> _SearchResult: """ Find all substrings of the given string which represent date and/or time and parse them. @@ -287,6 +473,13 @@ def search_dates( returns a list of detected language codes. :type detect_languages_function: function + :param strategy: + The search strategy to use: "split" (default) translates the text and splits it + into chunks that are likely to contain dates, while "ngram" tries to parse the + longest possible sequences of tokens as dates. The "ngram" strategy tends to + produce more predictable results, at the cost of more parse attempts. + :type strategy: str + :return: a dict mapping keys to two letter language code and a list of tuples of pairs: substring representing date expressions and corresponding :mod:`datetime.datetime` object. For example: @@ -295,7 +488,12 @@ def search_dates( {'Language': None, 'Dates': None} :raises: ValueError - Unknown Language """ + if strategy not in ("split", "ngram"): + raise ValueError( + f'strategy must be "split" or "ngram" ({strategy!r} given)' + ) + assert isinstance(settings, Settings) check_settings(settings) language_shortname = self.detect_language( @@ -304,16 +502,33 @@ def search_dates( settings=settings, detect_languages_function=detect_languages_function, ) - if not language_shortname: + + candidate_languages = self._get_candidate_languages( + language_shortname, languages + ) + if not candidate_languages: return {"Language": None, "Dates": None} + + if strategy == "ngram": + dates = self.ngram_search.search_parse( + candidate_languages, text, settings=settings + ) + _add_time_span_results(dates, text, settings) + return {"Language": language_shortname, "Dates": dates} + + for candidate_language in candidate_languages: + dates = self.search.search_parse( + candidate_language, text, settings=settings + ) + if dates: + return {"Language": candidate_language, "Dates": dates} + return { "Language": language_shortname, - "Dates": self.search.search_parse( - language_shortname, text, settings=settings - ), + "Dates": [], } - def preprocess_text(self, text, languages): + def preprocess_text(self, text: str, languages: Iterable[str] | None) -> str: """Preprocess text to handle language-specific quirks.""" if languages and "ru" in languages: # Replace "с" (from) before numbers with a placeholder diff --git a/dateparser/search/text_detection.py b/dateparser/search/text_detection.py index e05efecfb..127b19b69 100644 --- a/dateparser/search/text_detection.py +++ b/dateparser/search/text_detection.py @@ -1,16 +1,19 @@ -from dateparser.conf import apply_settings +from typing import Any + +from dateparser.conf import Settings, apply_settings +from dateparser.languages.locale import Locale from dateparser.search.detection import BaseLanguageDetector from dateparser.utils import normalize_unicode class FullTextLanguageDetector(BaseLanguageDetector): - def __init__(self, languages): + def __init__(self, languages: list[Locale]) -> None: super(BaseLanguageDetector, self).__init__() self.languages = languages[:] - self.language_unique_chars = [] - self.language_chars = [] + self.language_unique_chars: list[set[str]] = [] + self.language_chars: list[set[str]] = [] - def get_unique_characters(self, settings): + def get_unique_characters(self, settings: Settings) -> None: settings = settings.replace(NORMALIZE=False) for language in self.languages: @@ -24,7 +27,7 @@ def get_unique_characters(self, settings): unique_chars = unique_chars - other_char_set self.language_unique_chars.append(unique_chars) - def character_check(self, date_string, settings): + def character_check(self, date_string: str, settings: Settings) -> None: date_string_set = set(date_string.lower()) symbol_set = { "0", @@ -57,16 +60,20 @@ def character_check(self, date_string, settings): if char.lower() in date_string.lower(): self.languages = [self.languages[i]] return - indices_to_pop = [] - for i in range(len(self.languages)): - if len(date_string_set & self.language_chars[i]) == 0: - indices_to_pop.append(i) + indices_to_pop = [ + i + for i in range(len(self.languages)) + if len(date_string_set & self.language_chars[i]) == 0 + ] self.languages = [ i for j, i in enumerate(self.languages) if j not in indices_to_pop ] @apply_settings - def _best_language(self, date_string, settings=None): + def _best_language( + self, date_string: str, settings: Settings | dict[str, Any] | None = None + ) -> str | None: + assert isinstance(settings, Settings) self.character_check(date_string, settings) date_string = normalize_unicode(date_string.lower()) if len(self.languages) == 1: diff --git a/dateparser/timezone_parser.py b/dateparser/timezone_parser.py index 6ff6c9224..0cdd83ea6 100644 --- a/dateparser/timezone_parser.py +++ b/dateparser/timezone_parser.py @@ -1,65 +1,145 @@ -import os -import pickle -import zlib +import warnings +from collections.abc import Iterator from datetime import datetime, timedelta, timezone, tzinfo -from pathlib import Path +from typing import Literal, TypedDict, overload import regex as re from .timezones import timezone_info_list +class _TzOffsetInfo(TypedDict): + regex: re.Pattern[str] + offset: timedelta + + class StaticTzInfo(tzinfo): - def __init__(self, name, offset): + def __init__(self, name: str, offset: timedelta) -> None: self.__offset = offset self.__name = name - def tzname(self, dt): + def tzname(self, dt: datetime | None) -> str: return self.__name - def utcoffset(self, dt): + def utcoffset(self, dt: datetime | None) -> timedelta: return self.__offset - def dst(self, dt): + def dst(self, dt: datetime | None) -> timedelta: return timedelta(0) - def __repr__(self): - return "<%s '%s'>" % (self.__class__.__name__, self.__name) + def __repr__(self) -> str: + return f"<{self.__class__.__name__} '{self.__name}'>" - def localize(self, dt, is_dst=False): + def localize(self, dt: datetime, is_dst: bool = False) -> datetime: if dt.tzinfo is not None: raise ValueError("Not naive datetime (tzinfo is already set)") return dt.replace(tzinfo=self) - def __getinitargs__(self): + def __getinitargs__(self) -> tuple[str, timedelta]: return self.__name, self.__offset -def pop_tz_offset_from_string(date_string, as_offset=True): - if _search_regex_ignorecase.search(date_string): - for name, info in _tz_offsets: - timezone_re = info["regex"] - timezone_match = timezone_re.search(date_string) - if timezone_match: - start, stop = timezone_match.span() - date_string = date_string[: start + 1] + date_string[stop:] - return ( - date_string, - StaticTzInfo(name, info["offset"]) if as_offset else name, - ) - return date_string, None - - -def word_is_tz(word): +def _search_and_pop_tz(date_string: str) -> tuple[str, str, _TzOffsetInfo] | None: + """Find and remove the first timezone token from ``date_string``. + + Returns a ``(new_string, name, info)`` tuple, or ``None`` if no timezone + token is present. + """ + if not _search_regex_ignorecase.search(date_string): + return None + for name, info in _tz_offsets: + timezone_match = info["regex"].search(date_string) + if timezone_match: + start, stop = timezone_match.span() + # A token glued to the digits that follow, as in + # 2019-09-28WIB19:17:34, leaves a space so that the date and time + # digits stay apart. + glued = stop < len(date_string) and date_string[stop - 1].isalpha() + separator = " " if glued else "" + return ( + date_string[: start + 1] + separator + date_string[stop:], + name, + info, + ) + return None + + +@overload +def pop_tz_offset_from_string( + date_string: str, as_offset: Literal[True] = True +) -> tuple[str, StaticTzInfo | None]: ... + + +@overload +def pop_tz_offset_from_string( + date_string: str, as_offset: Literal[False] +) -> tuple[str, str | None]: ... + + +def pop_tz_offset_from_string( + date_string: str, as_offset: bool = True +) -> tuple[str, StaticTzInfo | str | None]: + match = _search_and_pop_tz(date_string) + if match is None: + return date_string, None + + date_string, name, info = match + result = StaticTzInfo(name, info["offset"]) if as_offset else name + + # A date string may carry both a numeric UTC offset and a redundant, + # equivalent timezone abbreviation, e.g. the RFC 2822 email form + # ``-0500 (CDT)`` (the parenthesised name is informational and the numeric + # offset is authoritative). Only one token is removed above; strip a second, + # equivalent one so the leftover does not break the rest of the parser. + # The remainder is right-stripped first because the numeric-offset regexes + # are anchored at the end of the string. + while True: + extra = _search_and_pop_tz(date_string.rstrip()) + if extra is None or extra[2]["offset"] != info["offset"]: + break + date_string = extra[0] + + return date_string, result + + +def word_is_tz(word: str) -> bool: return bool(_search_regex.match(word)) -def convert_to_local_tz(datetime_obj, datetime_tz_offset): +def is_timezone_token(token: str) -> bool: + """Whether ``token`` is, on its own, a recognized timezone abbreviation. + + Unlike :func:`word_is_tz` (a case-sensitive prefix match used while + scanning original-cased text), this trims surrounding whitespace and does a + case-insensitive *full* match, so it recognizes an already-lowercased, + space-padded token such as ``" est"``. Because the match is anchored, an + ordinary word that merely begins with a timezone abbreviation is not + treated as a timezone (e.g. ``"actualisé"`` is not the ``ACT`` zone). This + is used only on single edge tokens, so the trailing ``.*`` in the UTC/GMT + numeric-offset patterns (which a full match would otherwise let absorb + following text) is not a concern here. + """ + return bool(_search_regex_ignorecase.fullmatch(token.strip())) + + +def convert_to_local_tz( + datetime_obj: datetime, datetime_tz_offset: timedelta +) -> datetime: + warnings.warn( + "dateparser.timezone_parser.convert_to_local_tz is deprecated and " + "will be removed in a future version.", + FutureWarning, + stacklevel=2, + ) return datetime_obj - datetime_tz_offset + local_tz_offset -def build_tz_offsets(search_regex_parts): - def get_offset(tz_obj, regex, repl="", replw=""): +def build_tz_offsets( + search_regex_parts: list[str], +) -> Iterator[tuple[str, _TzOffsetInfo]]: + def get_offset( + tz_obj: tuple[str, int], regex: str, repl: str = "", replw: str = "" + ) -> tuple[str, _TzOffsetInfo]: return ( tz_obj[0], { @@ -82,53 +162,13 @@ def get_offset(tz_obj, regex, repl="", replw=""): yield get_offset(tz_obj, regex, repl=replace, replw=replacewith) -def get_local_tz_offset(): +def get_local_tz_offset() -> timedelta: offset = datetime.now() - datetime.now(tz=timezone.utc).replace(tzinfo=None) - offset = timedelta(days=offset.days, seconds=round(offset.seconds, -1)) - return offset + return timedelta(days=offset.days, seconds=round(offset.seconds, -1)) +_search_regex_parts: list[str] = [] +_tz_offsets = list(build_tz_offsets(_search_regex_parts)) +_search_regex = re.compile("|".join(_search_regex_parts)) +_search_regex_ignorecase = re.compile("|".join(_search_regex_parts), re.IGNORECASE) local_tz_offset = get_local_tz_offset() - -_tz_offsets = None -_search_regex = None -_search_regex_ignorecase = None - - -def _load_offsets(cache_path, current_hash): - global _tz_offsets, _search_regex, _search_regex_ignorecase - - try: - with open(cache_path, mode="rb") as file: - ( - serialized_hash, - _tz_offsets, - _search_regex, - _search_regex_ignorecase, - ) = pickle.load(file) - if current_hash is None or current_hash == serialized_hash: - return - except (FileNotFoundError, ValueError, TypeError): - pass - - _search_regex_parts = [] - _tz_offsets = list(build_tz_offsets(_search_regex_parts)) - _search_regex = re.compile("|".join(_search_regex_parts)) - _search_regex_ignorecase = re.compile("|".join(_search_regex_parts), re.IGNORECASE) - - with open(cache_path, mode="wb") as file: - pickle.dump( - (current_hash, _tz_offsets, _search_regex, _search_regex_ignorecase), - file, - protocol=5, - ) - - -CACHE_PATH = Path(__file__).parent.joinpath("data", "dateparser_tz_cache.pkl") - -if "BUILD_TZ_CACHE" in os.environ: - current_hash = zlib.crc32(str(timezone_info_list).encode("utf-8")) -else: - current_hash = None - -_load_offsets(CACHE_PATH, current_hash) diff --git a/dateparser/timezones.py b/dateparser/timezones.py index 9ac35dafd..248ecc907 100644 --- a/dateparser/timezones.py +++ b/dateparser/timezones.py @@ -2,8 +2,17 @@ # As well as http://en.wikipedia.org/wiki/List_of_time_zone_abbreviations # As well as https://github.com/scrapinghub/dateparser/pull/4 # As well as http://en.wikipedia.org/wiki/List_of_UTC_time_offsets +# +# The IANA tz database names several zones with the same abbreviation at +# different UTC offsets (e.g. "CST", "IST", "PST"), and gives no preferred +# meaning for those, so one offset was picked arbitrarily per abbreviation. +# Where the tz database names only one offset for an abbreviation, this table +# has to agree with it: "BST" and "HDT" did not, and were corrected in #1322. +# Run dateparser_scripts/tz_abbreviation_conflicts.py to re-check the table. -timezone_info_list = [ +from typing import Any + +timezone_info_list: list[dict[str, Any]] = [ { "regex_patterns": [r"(.)%s$"], "replace": [ @@ -67,7 +76,7 @@ ], }, { - "regex_patterns": [r"(\W|\d|_)%s($|\W)"], + "regex_patterns": [r"(\W|\d|_)%s($|\W|(?=\d))"], "timezones": [ ("ACDT", 37800), ("ACST", 34200), @@ -123,7 +132,7 @@ ("BOT", -14400), ("BRST", -7200), ("BRT", -10800), - ("BST", 39600), + ("BST", 3600), ("BTT", 21600), ("BURT", 23400), ("CANT", -3600), @@ -218,7 +227,7 @@ ("HAST", -36000), ("HAT", -9000), ("HAY", -28800), - ("HDT", -34200), + ("HDT", -32400), ("HKST", 32400), ("HKT", 28800), ("HLV", -16200), diff --git a/dateparser/utils/__init__.py b/dateparser/utils/__init__.py index 023c5fbb3..f813437b5 100644 --- a/dateparser/utils/__init__.py +++ b/dateparser/utils/__init__.py @@ -1,9 +1,15 @@ import calendar import logging +import logging.config +import os +import threading import types import unicodedata from collections import OrderedDict -from datetime import datetime +from collections.abc import Callable, Mapping +from datetime import datetime, tzinfo +from datetime import timezone as dt_timezone +from typing import TYPE_CHECKING, Any, Literal, TypeVar import regex as re from pytz import UTC, UnknownTimeZoneError, timezone @@ -11,12 +17,29 @@ from dateparser.timezone_parser import StaticTzInfo, _tz_offsets +if TYPE_CHECKING: + from dateparser.conf import Settings -def strip_braces(date_string): +_T = TypeVar("_T") + + +def _get_localzone() -> tzinfo: + try: + return get_localzone() + except ValueError as error: + raise RuntimeError( + f"Could not determine the local timezone " + f"(TZ={os.environ.get('TZ')!r}): {error}" + ) from error + + +def strip_braces(date_string: str) -> str: return re.sub(r"[{}()<>\[\]]+", "", date_string) -def normalize_unicode(string, form="NFKD"): +def normalize_unicode( + string: str, form: Literal["NFC", "NFD", "NFKC", "NFKD"] = "NFKD" +) -> str: return "".join( c for c in unicodedata.normalize(form, string) @@ -24,8 +47,10 @@ def normalize_unicode(string, form="NFKD"): ) -def combine_dicts(primary_dict, supplementary_dict): - combined_dict = OrderedDict() +def combine_dicts( + primary_dict: Mapping[str, Any], supplementary_dict: Mapping[str, Any] +) -> "OrderedDict[str, Any]": + combined_dict: OrderedDict[str, Any] = OrderedDict() for key, value in primary_dict.items(): if key in supplementary_dict: if isinstance(value, list): @@ -35,52 +60,71 @@ def combine_dicts(primary_dict, supplementary_dict): else: combined_dict[key] = supplementary_dict[key] else: - combined_dict[key] = primary_dict[key] - remaining_keys = [ - key for key in supplementary_dict.keys() if key not in primary_dict.keys() - ] + combined_dict[key] = value + remaining_keys = [key for key in supplementary_dict if key not in primary_dict] for key in remaining_keys: combined_dict[key] = supplementary_dict[key] return combined_dict -def find_date_separator(format): +def find_date_separator(format: str) -> str | None: # noqa: A002 m = re.search(r"(?:(?:%[dbBmaA])(\W))+", format) if m: return m.group(1) + return None + + +_PART_DIRECTIVES = { + "year": ["%y", "%-y", "%Y"], + # %j (day of year) encodes month implicitly: a successful strptime with %j always + # populates the month field, so %j should count as providing month information. + "month": ["%b", "%B", "%m", "%-m", "%j", "%-j"], + "day": ["%d", "%-d", "%j", "%-j"], + "time": ["%H", "%-H", "%I", "%-I", "%M", "%-M", "%S", "%-S"], +} + + +def _get_parts(fmt: str) -> tuple[str, ...]: + """Return a tuple with the parts (year, month, day, time) that a date format + provides, based on its directives.""" + complete_week_date = False + if "%U" in fmt or "%W" in fmt or "%V" in fmt: + # A year, week number and weekday determine the complete date. Consume + # %% pairs so literal directive names do not count as date components. + directives = set(re.findall(r"%[%UWVwuAaYyG]", fmt)) + complete_week_date = bool( + directives & {"%U", "%W", "%V"} + and directives & {"%w", "%u", "%a", "%A"} + and directives & {"%Y", "%y", "%G"} + ) + return tuple( + part + for part, directives in _PART_DIRECTIVES.items() + if (complete_week_date and part != "time") + or any(directive in fmt for directive in directives) + ) -def _get_missing_parts(fmt): +def _get_missing_parts(fmt: str) -> list[str]: """ Return a list containing missing parts (day, month, year) from a date format checking its directives """ - directive_mapping = { - "day": ["%d", "%-d", "%j", "%-j"], - "month": ["%b", "%B", "%m", "%-m"], - "year": ["%y", "%-y", "%Y"], - } + parts = _get_parts(fmt) + return [field for field in ("day", "month", "year") if field not in parts] - missing = [ - field - for field in ("day", "month", "year") - if not any(directive in fmt for directive in directive_mapping[field]) - ] - return missing - -def get_timezone_from_tz_string(tz_string): +def get_timezone_from_tz_string(tz_string: str) -> tzinfo: try: return timezone(tz_string) - except UnknownTimeZoneError as e: + except UnknownTimeZoneError: for name, info in _tz_offsets: - if info["regex"].search(" %s" % tz_string): + if info["regex"].search(f" {tz_string}"): return StaticTzInfo(name, info["offset"]) - else: - raise e + raise -def localize_timezone(date_time, tz_string): +def localize_timezone(date_time: datetime, tz_string: str) -> datetime: if date_time.tzinfo: return date_time @@ -94,7 +138,7 @@ def localize_timezone(date_time, tz_string): return date_time -def apply_tzdatabase_timezone(date_time, pytz_string): +def apply_tzdatabase_timezone(date_time: datetime, pytz_string: str) -> datetime: usr_timezone = timezone(pytz_string) if date_time.tzinfo != usr_timezone: @@ -103,14 +147,17 @@ def apply_tzdatabase_timezone(date_time, pytz_string): return date_time -def apply_dateparser_timezone(utc_datetime, offset_or_timezone_abb): +def apply_dateparser_timezone( + utc_datetime: datetime, offset_or_timezone_abb: str +) -> datetime | None: for name, info in _tz_offsets: - if info["regex"].search(" %s" % offset_or_timezone_abb): + if info["regex"].search(f" {offset_or_timezone_abb}"): tz = StaticTzInfo(name, info["offset"]) return utc_datetime.astimezone(tz) + return None -def apply_timezone(date_time, tz_string): +def apply_timezone(date_time: datetime, tz_string: str) -> datetime: if not date_time.tzinfo: if hasattr(UTC, "localize"): date_time = UTC.localize(date_time) @@ -125,8 +172,21 @@ def apply_timezone(date_time, tz_string): return new_datetime -def apply_timezone_from_settings(date_obj, settings): - tz = get_localzone() +def _now(settings: "Settings", tz: tzinfo | None = None) -> datetime: + """Return the current time as a naive datetime in *tz*, or in the + ``TIMEZONE`` setting if *tz* is ``None``.""" + if tz is not None: + return datetime.now(tz).replace(tzinfo=None) + if "local" in settings.TIMEZONE.lower(): + return datetime.now() + utc_now = datetime.now(dt_timezone.utc) + return apply_timezone(utc_now, settings.TIMEZONE).replace(tzinfo=None) + + +def apply_timezone_from_settings( + date_obj: datetime, settings: "Settings | None" +) -> datetime: + tz = _get_localzone() if settings is None: return date_obj @@ -147,19 +207,19 @@ def apply_timezone_from_settings(date_obj, settings): return date_obj -def get_last_day_of_month(year, month): +def get_last_day_of_month(year: int, month: int) -> int: return calendar.monthrange(year, month)[1] -def get_previous_leap_year(year): +def get_previous_leap_year(year: int) -> int: return _get_leap_year(year, future=False) -def get_next_leap_year(year): +def get_next_leap_year(year: int) -> int: return _get_leap_year(year, future=True) -def _get_leap_year(year, future): +def _get_leap_year(year: int, future: bool) -> int: """ Iterate through previous or next years until it gets a valid leap year This is performed to avoid missing or including centurial leap years @@ -171,7 +231,9 @@ def _get_leap_year(year, future): return leap_year -def set_correct_day_from_settings(date_obj, settings, current_day=None): +def set_correct_day_from_settings( + date_obj: datetime, settings: "Settings", current_day: int | None = None +) -> datetime: """Set correct day attending the `PREFER_DAY_OF_MONTH` setting.""" options = { "first": 1, @@ -185,7 +247,9 @@ def set_correct_day_from_settings(date_obj, settings, current_day=None): return date_obj.replace(day=options["last"]) -def set_correct_month_from_settings(date_obj, settings, current_month=None): +def set_correct_month_from_settings( + date_obj: datetime, settings: "Settings", current_month: int | None = None +) -> datetime: """Set correct month attending the `PREFER_MONTH_OF_YEAR` setting.""" options = {"first": 1, "last": 12, "current": current_month or datetime.now().month} @@ -195,41 +259,45 @@ def set_correct_month_from_settings(date_obj, settings, current_month=None): return date_obj.replace(month=options["last"]) -def registry(cls): - def choose(creator): - def constructor(cls, *args, **kwargs): +_registry_lock = threading.Lock() + + +def registry(cls: type[_T]) -> type[_T]: + def choose(creator: Callable[..., Any]) -> "staticmethod[..., Any]": + def constructor(cls: Any, *args: Any, **kwargs: Any) -> Any: key = cls.get_key(*args, **kwargs) - if not hasattr(cls, "__registry_dict"): - setattr(cls, "__registry_dict", {}) - registry_dict = getattr(cls, "__registry_dict") + with _registry_lock: + if not hasattr(cls, "__registry_dict"): + setattr(cls, "__registry_dict", {}) + registry_dict = getattr(cls, "__registry_dict") - if key not in registry_dict: - registry_dict[key] = creator(cls, *args) - setattr(registry_dict[key], "registry_key", key) - return registry_dict[key] + if key not in registry_dict: + instance = creator(cls, *args) + # Set the key before publishing the instance so other + # threads never observe an entry without ``registry_key``. + instance.registry_key = key + registry_dict[key] = instance + return registry_dict[key] return staticmethod(constructor) - if not ( - hasattr(cls, "get_key") - and isinstance(cls.get_key, types.MethodType) - and cls.get_key.__self__ is cls - ): + get_key = getattr(cls, "get_key", None) + if not (isinstance(get_key, types.MethodType) and get_key.__self__ is cls): raise NotImplementedError( "Registry classes require to implement class method get_key" ) - setattr(cls, "__new__", choose(cls.__new__)) + cls.__new__ = choose(cls.__new__) # type: ignore[method-assign] return cls -def get_logger(): +def get_logger() -> logging.Logger: setup_logging() return logging.getLogger("dateparser") -def setup_logging(): +def setup_logging() -> None: if len(logging.root.handlers): return diff --git a/dateparser/utils/strptime.py b/dateparser/utils/strptime.py index b22356753..642144951 100644 --- a/dateparser/utils/strptime.py +++ b/dateparser/utils/strptime.py @@ -1,6 +1,11 @@ +import calendar import importlib.util import sys +from collections.abc import Callable from datetime import datetime +from time import struct_time +from types import ModuleType +from typing import Any import regex as re @@ -15,17 +20,7 @@ MS_SEARCHER = re.compile(r"\.(?P[0-9]{1,6})") -def _exec_module(spec, module): - if hasattr(spec.loader, "exec_module"): - spec.loader.exec_module(module) - else: - # This can happen before Python 3.10 - # if spec.loader is a zipimporter and the Python runtime is in a zipfile - code = spec.loader.get_code(module.__name__) - exec(code, module.__dict__) - - -def patch_strptime(): +def patch_strptime() -> Callable[[str, str], struct_time]: """Monkey patching _strptime to avoid problems related with non-english locale changes on the system. @@ -33,12 +28,16 @@ def patch_strptime(): any date since all languages are translated to english dates. """ _strptime_spec = importlib.util.find_spec("_strptime") - _strptime = importlib.util.module_from_spec(_strptime_spec) - _exec_module(_strptime_spec, _strptime) + assert _strptime_spec is not None + assert _strptime_spec.loader is not None + _strptime: Any = importlib.util.module_from_spec(_strptime_spec) + _strptime_spec.loader.exec_module(_strptime) sys.modules["strptime_patched"] = _strptime - _calendar = importlib.util.module_from_spec(_strptime_spec) - _exec_module(_strptime_spec, _calendar) + # Copy the namespace without re-executing calendar, whose enum decorators + # would modify the original module. English names are rebound only here. + _calendar = ModuleType("calendar_patched") + _calendar.__dict__.update(vars(calendar), __name__="calendar_patched") sys.modules["calendar_patched"] = _calendar _strptime._getlang = lambda: ("en_US", "UTF-8") @@ -84,50 +83,71 @@ def patch_strptime(): "december", ] - return _strptime._strptime_time + strptime_time: Callable[[str, str], struct_time] = _strptime._strptime_time + return strptime_time __strptime = patch_strptime() -def _prepare_format(date_string: str, og_format: str) -> tuple[str, str]: +def _prepare_format(date_string: str, og_format: str) -> tuple[str, str, bool]: # Adapted from std lib: https://github.com/python/cpython/blob/e34a5e33049ce845de646cf24a498766a2da3586/Lib/_strptime.py#L448 - format = re.sub(r"([\\.^$*+?\(\){}\[\]|])", r"\\\1", og_format) - format = re.sub(r"\s+", r"\\s+", format) - format = re.sub(r"'", "['\u02bc]", format) + regex_format = re.sub(r"([\\.^$*+?\(\){}\[\]|])", r"\\\1", og_format) + regex_format = re.sub(r"\s+", r"\\s+", regex_format) + regex_format = re.sub(r"'", "['\u02bc]", regex_format) year_in_format = False day_of_month_in_format = False + day_of_year_in_format = False def repl(m: re.Match[str]) -> str: format_char = m[1] if format_char in ("Y", "y", "G"): nonlocal year_in_format year_in_format = True - elif format_char in ("d",): + elif format_char == "d": nonlocal day_of_month_in_format day_of_month_in_format = True + elif format_char == "j": + nonlocal day_of_year_in_format + day_of_year_in_format = True return "" - _ = re.sub(r"%[-_0^#]*[0-9]*([OE]?\\?.?)", repl, format) + _ = re.sub(r"%[-_0^#]*[0-9]*([OE]?\\?.?)", repl, regex_format) if day_of_month_in_format and not year_in_format: current_year = datetime.today().year - return f"{current_year} {date_string}", f"%Y {og_format}" - return date_string, og_format - - -def strptime(date_string: str, format: str) -> datetime: - date_string, format = _prepare_format(date_string, format) - obj = datetime(*__strptime(date_string, format)[:-3]) - - if "%f" in format: + return ( + f"{current_year} {date_string}", + f"%Y {og_format}", + day_of_year_in_format, + ) + return date_string, og_format, day_of_year_in_format + + +def strptime(date_string: str, format: str) -> datetime: # noqa: A002 + date_string, prepared_format, day_of_year_in_format = _prepare_format( + date_string, format + ) + time_tuple = __strptime(date_string, prepared_format) + obj = datetime(*time_tuple[:-3]) + + if day_of_year_in_format and time_tuple.tm_yday != obj.timetuple().tm_yday: + # A day of year past the end of the parsed year is rolled over into the + # next year by the std lib (e.g. day 366 of 1999 becomes 2000-01-01), + # which keeps the original value in tm_yday. Such a day does not belong + # to the parsed year, so reject it instead of returning another year. + raise ValueError( + f"day of year {time_tuple.tm_yday} is out of range for year {obj.year - 1}" + ) + + if "%f" in prepared_format: try: - match_groups = TIME_MATCHER.match(date_string).groupdict() + match_groups = TIME_MATCHER.match(date_string).groupdict() # type: ignore[union-attr] ms = match_groups["microsecond"] ms = ms + ((6 - len(ms)) * "0") obj = obj.replace(microsecond=int(ms)) except AttributeError: - match_groups = MS_SEARCHER.search(date_string).groupdict() + match_groups = MS_SEARCHER.search(date_string).groupdict() # type: ignore[union-attr] ms = match_groups["microsecond"] ms = ms + ((6 - len(ms)) * "0") obj = obj.replace(microsecond=int(ms)) diff --git a/dateparser/utils/time_spans.py b/dateparser/utils/time_spans.py index fcf7e06be..6e110b830 100644 --- a/dateparser/utils/time_spans.py +++ b/dateparser/utils/time_spans.py @@ -1,29 +1,15 @@ -""" -Utilities for handling time spans and date ranges. -""" - import re +from collections.abc import Mapping from datetime import datetime, timedelta -from dateutil.relativedelta import relativedelta - - -def get_week_start(date, start_of_week="monday"): - """Get the start of the week for a given date.""" - if start_of_week == "monday": - days_back = date.weekday() - else: # sunday - days_back = (date.weekday() + 1) % 7 - - return date - timedelta(days=days_back) +from typing import TYPE_CHECKING, Any +from dateutil.relativedelta import relativedelta -def get_week_end(date, start_of_week="monday"): - """Get the end of the week for a given date.""" - week_start = get_week_start(date, start_of_week) - return week_start + timedelta(days=6) +if TYPE_CHECKING: + from dateparser.conf import Settings -def detect_time_span(text): +def detect_time_span(text: str) -> dict[str, Any] | None: """Detect time span expressions in text and return span information.""" span_patterns = [ { @@ -81,7 +67,7 @@ def detect_time_span(text): for pattern_info in span_patterns: match = re.search(pattern_info["pattern"], text, re.IGNORECASE) if match: - result = { + result: dict[str, Any] = { "type": pattern_info["type"], "direction": pattern_info["direction"], "matched_text": match.group(0), @@ -97,56 +83,34 @@ def detect_time_span(text): return None -def generate_time_span(span_info, base_date=None, settings=None): - """Generate start and end dates for a time span.""" - if base_date is None: - base_date = datetime.now() - - if settings is None: - start_of_week = "monday" - days_in_month = 30 - else: - start_of_week = getattr(settings, "DEFAULT_START_OF_WEEK", "monday") - days_in_month = getattr(settings, "DEFAULT_DAYS_IN_MONTH", 30) - +def generate_time_span( + span_info: Mapping[str, Any], base_date: datetime, settings: "Settings" +) -> tuple[datetime, datetime]: + """Return the start and end dates of the span described by *span_info*.""" span_type = span_info["type"] - direction = span_info["direction"] number = span_info.get("number", 1) - - if direction == "past": - end_date = base_date - - if span_type == "month": - start_date = end_date - relativedelta(days=days_in_month) - elif span_type == "week": - week_start = get_week_start(end_date, start_of_week) - start_date = week_start - timedelta(days=7) - end_date = week_start - timedelta(days=1) - elif span_type == "days": - start_date = end_date - timedelta(days=number) - elif span_type == "weeks": - start_date = end_date - timedelta(weeks=number) - elif span_type == "months": - start_date = end_date - relativedelta(months=number) - else: - start_date = end_date - timedelta(days=1) - + past = span_info["direction"] == "past" + + if span_type == "week": + days_back = base_date.weekday() + if settings.DEFAULT_START_OF_WEEK == "sunday": + days_back = (days_back + 1) % 7 + week_start = base_date - timedelta(days=days_back) + if past: + return week_start - timedelta(days=7), week_start - timedelta(days=1) + start_date = week_start + timedelta(days=7) + return start_date, start_date + timedelta(days=6) + + span: timedelta | relativedelta + if span_type == "month": + span = timedelta(days=settings.DEFAULT_DAYS_IN_MONTH) + elif span_type == "days": + span = timedelta(days=number) + elif span_type == "weeks": + span = timedelta(weeks=number) else: - start_date = base_date - - if span_type == "month": - end_date = start_date + relativedelta(days=days_in_month) - elif span_type == "week": - week_start = get_week_start(start_date, start_of_week) - start_date = week_start + timedelta(days=7) - end_date = start_date + timedelta(days=6) - elif span_type == "days": - end_date = start_date + timedelta(days=number) - elif span_type == "weeks": - end_date = start_date + timedelta(weeks=number) - elif span_type == "months": - end_date = start_date + relativedelta(months=number) - else: - end_date = start_date + timedelta(days=1) + span = relativedelta(months=number) - return (start_date, end_date) + if past: + return base_date - span, base_date + return base_date, base_date + span diff --git a/dateparser_cli/cli.py b/dateparser_cli/cli.py index f51a8c9cd..979ff241c 100644 --- a/dateparser_cli/cli.py +++ b/dateparser_cli/cli.py @@ -1,18 +1,20 @@ import argparse import logging +import warnings -from .fasttext_manager import fasttext_downloader from .utils import clear_cache +logger = logging.getLogger(__name__) -def entrance(): + +def entrance() -> None: dateparser_argparse = argparse.ArgumentParser( description="dateparser download manager." ) dateparser_argparse.add_argument( "--fasttext", type=str, - help='To download a fasttext language detection models. Supported models are "small" and "large"', + help="[DEPRECATED] fastText is no longer supported. Please use langdetect instead.", ) dateparser_argparse.add_argument( "--clear", @@ -25,12 +27,20 @@ def entrance(): if args.clear: clear_cache() - logging.info("dateparser-download: All cache deleted") + logger.info("dateparser-download: All cache deleted") if args.fasttext: - fasttext_downloader(args.fasttext) + warnings.warn( + "fastText support has been removed as the library is archived and unmaintained. " + "Please migrate to langdetect. Install with: pip install dateparser[langdetect]", + DeprecationWarning, + stacklevel=2, + ) + dateparser_argparse.error( + "fastText is no longer supported. Please use langdetect for language detection." + ) - if not (args.clear or args.fasttext): + if not args.clear: dateparser_argparse.error( - "dateparser-download: You need to specify the command (i.e.: --fasttext or --clear)" + "dateparser-download: You need to specify the command (i.e.: --clear)" ) diff --git a/dateparser_cli/exceptions.py b/dateparser_cli/exceptions.py deleted file mode 100644 index 8bf38679b..000000000 --- a/dateparser_cli/exceptions.py +++ /dev/null @@ -1,2 +0,0 @@ -class FastTextModelNotFoundException(Exception): - pass diff --git a/dateparser_cli/fasttext_manager.py b/dateparser_cli/fasttext_manager.py deleted file mode 100644 index a6ced6a2d..000000000 --- a/dateparser_cli/fasttext_manager.py +++ /dev/null @@ -1,42 +0,0 @@ -import logging -import os -import urllib.request -from pathlib import Path - -from .exceptions import FastTextModelNotFoundException -from .utils import create_data_model_home, dateparser_model_home - - -def fasttext_downloader(model_name): - create_data_model_home() - models = { - "small": "https://dl.fbaipublicfiles.com/fasttext/supervised-models/lid.176.ftz", - "large": "https://dl.fbaipublicfiles.com/fasttext/supervised-models/lid.176.bin", - } - if model_name not in models: - message = 'dateparser-download: Couldn\'t find a model called "{}". Supported models are: {}'.format( - model_name, ", ".join(models.keys()) - ) - raise FastTextModelNotFoundException(message) - - models_directory_path = os.path.join(dateparser_model_home, (model_name + ".bin")) - - if not Path(models_directory_path).is_file(): - model_url = models[model_name] - logging.info( - 'dateparser-download: Downloading model "{}" from "{}"...'.format( - model_name, model_url - ) - ) - try: - urllib.request.urlretrieve(model_url, models_directory_path) - except urllib.error.HTTPError as e: - raise Exception( - "dateparser-download: Fasttext model cannot be downloaded due to HTTP error" - ) from e - else: - logging.info( - 'dateparser-download: The model "{}" is already downloaded'.format( - model_name - ) - ) diff --git a/dateparser_cli/utils.py b/dateparser_cli/utils.py index 796f01b39..78897c7b7 100644 --- a/dateparser_cli/utils.py +++ b/dateparser_cli/utils.py @@ -1,11 +1,10 @@ -import os import sys from pathlib import Path DEFAULT_DIR_NAME = "dateparser_models" DEFAULT_UNIX_CACHE_DIR = "~/.cache" -DEFAULT_WINDOWS_CACHE_DIR = os.path.join(Path.home(), "AppData", "Roaming") +DEFAULT_WINDOWS_CACHE_DIR = Path.home() / "AppData" / "Roaming" if sys.platform.startswith("win"): @@ -15,13 +14,9 @@ # UNIX & OS X: _cache_dir = DEFAULT_UNIX_CACHE_DIR -dateparser_model_home = os.path.expanduser(os.path.join(_cache_dir, DEFAULT_DIR_NAME)) +dateparser_model_home = (Path(_cache_dir) / DEFAULT_DIR_NAME).expanduser() -def create_data_model_home(): - os.makedirs(dateparser_model_home, exist_ok=True) - - -def clear_cache(*args): - for path in Path(dateparser_model_home).rglob("*.*"): - os.remove(path) +def clear_cache(*args: object) -> None: + for path in dateparser_model_home.rglob("*.*"): + path.unlink() diff --git a/dateparser_data/cldr_language_data/date_translation_data/af.json b/dateparser_data/cldr_language_data/date_translation_data/af.json index a96e9f0f4..dfe398227 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/af.json +++ b/dateparser_data/cldr_language_data/date_translation_data/af.json @@ -109,7 +109,6 @@ ], "second": [ "s", - "sek", "sekonde" ], "relative-type": { @@ -123,39 +122,48 @@ "hierdie minuut" ], "0 month ago": [ + "hierdie md", "vandeesmaand" ], "0 second ago": [ "nou" ], "0 week ago": [ - "vandeesweek" + "hierdie w", + "hierdie week" ], "0 year ago": [ + "hierdie j", "hierdie jaar" ], "1 day ago": [ "gister" ], "1 month ago": [ - "verlede maand" + "verlede maand", + "verlede md" ], "1 week ago": [ + "verlede w", "verlede week" ], "1 year ago": [ + "verlede j", "verlede jaar" ], "in 1 day": [ "môre" ], "in 1 month": [ - "volgende maand" + "volgende maand", + "volgende md" ], "in 1 week": [ + "volgende w", "volgende week" ], "in 1 year": [ + "volgende j", "volgende jaar" ] }, @@ -165,6 +173,7 @@ "{0} dag gelede" ], "\\1 hour ago": [ + "{0} u gelede", "{0} uur gelede" ], "\\1 minute ago": [ @@ -178,7 +187,7 @@ "{0} md gelede" ], "\\1 second ago": [ - "{0} sek gelede", + "{0} s gelede", "{0} sekonde gelede", "{0} sekondes gelede" ], @@ -188,26 +197,29 @@ "{0} weke gelede" ], "\\1 year ago": [ + "{0} j gelede", "{0} jaar gelede" ], "in \\1 day": [ "oor {0} dae", - "oor {0} dag", - "oor {0} minuut" + "oor {0} dag" ], "in \\1 hour": [ + "oor {0} u", "oor {0} uur" ], "in \\1 minute": [ "oor {0} min", + "oor {0} minute", "oor {0} minuut" ], "in \\1 month": [ - "oor {0} md", - "oor {0} minuut" + "oor {0} maand", + "oor {0} maande", + "oor {0} md" ], "in \\1 second": [ - "oor {0} sek", + "oor {0} s", "oor {0} sekonde", "oor {0} sekondes" ], @@ -217,6 +229,7 @@ "oor {0} weke" ], "in \\1 year": [ + "oor {0} j", "oor {0} jaar" ] }, diff --git a/dateparser_data/cldr_language_data/date_translation_data/agq.json b/dateparser_data/cldr_language_data/date_translation_data/agq.json index 7de864742..3f9f4469c 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/agq.json +++ b/dateparser_data/cldr_language_data/date_translation_data/agq.json @@ -96,6 +96,7 @@ "utsuʔ" ], "hour": [ + "hr", "tàm" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/ak.json b/dateparser_data/cldr_language_data/date_translation_data/ak.json index c21f1124c..e0e678fbe 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ak.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ak.json @@ -96,7 +96,8 @@ "da" ], "hour": [ - "dɔnhwer" + "dɔnhwer", + "hr" ], "minute": [ "sema" diff --git a/dateparser_data/cldr_language_data/date_translation_data/am.json b/dateparser_data/cldr_language_data/date_translation_data/am.json index 9418a71bb..810cbdfa3 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/am.json +++ b/dateparser_data/cldr_language_data/date_translation_data/am.json @@ -2,12 +2,12 @@ "name": "am", "date_order": "DMY", "january": [ - "ጃንዩ", - "ጃንዩወሪ" + "ጃን", + "ጃንዋሪ" ], "february": [ - "ፌብሩ", - "ፌብሩወሪ" + "ፌብ", + "ፌብሩዋሪ" ], "march": [ "ማርች" @@ -86,7 +86,8 @@ "ቀን" ], "hour": [ - "ሰዓት" + "ሰዓት", + "ሰዓቶች" ], "minute": [ "ደቂቃ" diff --git a/dateparser_data/cldr_language_data/date_translation_data/ar.json b/dateparser_data/cldr_language_data/date_translation_data/ar.json index f144bddce..5dbeb4b27 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ar.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ar.json @@ -79,7 +79,8 @@ "يوم" ], "hour": [ - "الساعات" + "الساعات", + "ساعات" ], "minute": [ "الدقائق" @@ -262,8 +263,7 @@ "أيلول" ], "october": [ - "تشرين الأول", - "تشرین الأول" + "تشرين الأول" ], "november": [ "تشرين الثاني" diff --git a/dateparser_data/cldr_language_data/date_translation_data/as.json b/dateparser_data/cldr_language_data/date_translation_data/as.json index bb432d2b8..048ebdf1c 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/as.json +++ b/dateparser_data/cldr_language_data/date_translation_data/as.json @@ -1,6 +1,6 @@ { "name": "as", - "date_order": "YMD", + "date_order": "DMY", "january": [ "জানু", "জানুৱাৰী" @@ -16,7 +16,7 @@ "এপ্ৰিল" ], "may": [ - "মে" + "মে'" ], "june": [ "জুন" @@ -29,20 +29,20 @@ "আগষ্ট" ], "september": [ - "ছেপ্তেম্বৰ", - "সেপ্ট" + "ছেপ্তে", + "ছেপ্তেম্বৰ" ], "october": [ "অক্টো", "অক্টোবৰ" ], "november": [ - "নভে", + "নৱে", "নৱেম্বৰ" ], "december": [ - "ডিচেম্বৰ", - "ডিসে" + "ডিচে", + "ডিচেম্বৰ" ], "monday": [ "সোম", @@ -57,8 +57,8 @@ "বুধবাৰ" ], "thursday": [ - "বৃহষ্পতি", - "বৃহষ্পতিবাৰ" + "বৃহ", + "বৃহস্পতিবাৰ" ], "friday": [ "শুক্ৰ", @@ -69,14 +69,14 @@ "শনিবাৰ" ], "sunday": [ - "দেওবাৰ", - "ৰবি" + "দেও", + "দেওবাৰ" ], "am": [ - "পূৰ্বাহ্ণ" + "পূৰ্বাহ্ন" ], "pm": [ - "অপৰাহ্ণ" + "অপৰাহ্ন" ], "year": [ "বছৰ" @@ -104,46 +104,92 @@ "আজি" ], "0 hour ago": [ - "this hour" + "এইটো ঘণ্টাত" ], "0 minute ago": [ - "this minute" + "এইটো মিনিটত" ], "0 month ago": [ - "this month" + "এই মা", + "এই মাহ" ], "0 second ago": [ - "now" + "এতিয়া" ], "0 week ago": [ - "this week" + "এই সপ্তাহ" ], "0 year ago": [ - "this year" + "এই বছৰ" ], "1 day ago": [ "কালি" ], "1 month ago": [ - "last month" + "যোৱা মা", + "যোৱা মাহ" ], "1 week ago": [ - "last week" + "যোৱা সপ্তাহ" ], "1 year ago": [ - "last year" + "যোৱা বছৰ" ], "in 1 day": [ "কাইলৈ" ], "in 1 month": [ - "next month" + "অহা মাহ" ], "in 1 week": [ - "next week" + "অহা সপ্তাহ" ], "in 1 year": [ - "next year" + "অহা বছৰ" + ] + }, + "relative-type-regex": { + "\\1 day ago": [ + "{0} দিন পূৰ্বে" + ], + "\\1 hour ago": [ + "{0} ঘণ্টা পূৰ্বে" + ], + "\\1 minute ago": [ + "{0} মিনিট পূৰ্বে" + ], + "\\1 month ago": [ + "{0} মাহ পূৰ্বে" + ], + "\\1 second ago": [ + "{0} ছেকেণ্ড পূৰ্বে" + ], + "\\1 week ago": [ + "{0} সপ্তাহ পূৰ্বে" + ], + "\\1 year ago": [ + "{0} বছৰৰ পূৰ্বে" + ], + "in \\1 day": [ + "{0} দিনত" + ], + "in \\1 hour": [ + "{0} ঘণ্টাত" + ], + "in \\1 minute": [ + "{0} মিনিটত" + ], + "in \\1 month": [ + "{0} মাহত" + ], + "in \\1 second": [ + "{0} ছেকেণ্ডত" + ], + "in \\1 week": [ + "{0} সপ্তাহত" + ], + "in \\1 year": [ + "{0} বছৰত" ] }, "locale_specific": {} diff --git a/dateparser_data/cldr_language_data/date_translation_data/asa.json b/dateparser_data/cldr_language_data/date_translation_data/asa.json index 0fb5fcd39..28c9cbb1b 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/asa.json +++ b/dateparser_data/cldr_language_data/date_translation_data/asa.json @@ -95,6 +95,7 @@ "thiku" ], "hour": [ + "hr", "thaa" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/ast.json b/dateparser_data/cldr_language_data/date_translation_data/ast.json index bde84f295..88e831430 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ast.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ast.json @@ -114,7 +114,8 @@ ], "hour": [ "h", - "hora" + "hora", + "hores" ], "minute": [ "m", diff --git a/dateparser_data/cldr_language_data/date_translation_data/az-Cyrl.json b/dateparser_data/cldr_language_data/date_translation_data/az-Cyrl.json index 120985fcb..a7792ece7 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/az-Cyrl.json +++ b/dateparser_data/cldr_language_data/date_translation_data/az-Cyrl.json @@ -95,7 +95,8 @@ "day" ], "hour": [ - "hour" + "hour", + "hr" ], "minute": [ "minute" diff --git a/dateparser_data/cldr_language_data/date_translation_data/az-Latn.json b/dateparser_data/cldr_language_data/date_translation_data/az-Latn.json index d0a3d6bac..59a971ceb 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/az-Latn.json +++ b/dateparser_data/cldr_language_data/date_translation_data/az-Latn.json @@ -22,13 +22,11 @@ ], "june": [ "iyn", - "iyun", - "i̇yun" + "iyun" ], "july": [ "iyl", - "iyul", - "i̇yul" + "iyul" ], "august": [ "avq", diff --git a/dateparser_data/cldr_language_data/date_translation_data/az.json b/dateparser_data/cldr_language_data/date_translation_data/az.json index 7607667bf..0f5684f45 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/az.json +++ b/dateparser_data/cldr_language_data/date_translation_data/az.json @@ -22,13 +22,11 @@ ], "june": [ "iyn", - "iyun", - "i̇yun" + "iyun" ], "july": [ "iyl", - "iyul", - "i̇yul" + "iyul" ], "august": [ "avq", diff --git a/dateparser_data/cldr_language_data/date_translation_data/bas.json b/dateparser_data/cldr_language_data/date_translation_data/bas.json index d6792c897..2a58d0d41 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/bas.json +++ b/dateparser_data/cldr_language_data/date_translation_data/bas.json @@ -96,6 +96,7 @@ "kɛl" ], "hour": [ + "hr", "ŋgɛŋ" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/be.json b/dateparser_data/cldr_language_data/date_translation_data/be.json index 4ebcf51a9..f76bb1f83 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/be.json +++ b/dateparser_data/cldr_language_data/date_translation_data/be.json @@ -111,7 +111,8 @@ ], "hour": [ "гадз", - "гадзіна" + "гадзіна", + "гадзіны" ], "minute": [ "хв", @@ -132,12 +133,14 @@ "у гэту хвіліну" ], "0 month ago": [ + "у гэтым мес", "у гэтым месяцы" ], "0 second ago": [ "цяпер" ], "0 week ago": [ + "на гэтым тыд", "на гэтым тыдні" ], "0 year ago": [ @@ -147,30 +150,35 @@ "учора" ], "1 month ago": [ + "у мін мес", "у мінулым месяцы" ], "1 week ago": [ + "на мін тыд", "на мінулым тыдні" ], "1 year ago": [ + "у мін годзе", "у мінулым годзе" ], "in 1 day": [ "заўтра" ], "in 1 month": [ + "у наст мес", "у наступным месяцы" ], "in 1 week": [ + "на наст тыд", "на наступным тыдні" ], "in 1 year": [ + "у наст годзе", "у наступным годзе" ] }, "relative-type-regex": { "\\1 day ago": [ - "{0} д таму", "{0} дзень таму", "{0} дня таму" ], @@ -205,7 +213,6 @@ "{0} года таму" ], "in \\1 day": [ - "праз {0} д", "праз {0} дзень", "праз {0} дня" ], diff --git a/dateparser_data/cldr_language_data/date_translation_data/bem.json b/dateparser_data/cldr_language_data/date_translation_data/bem.json index a67b7bbfd..50d29b792 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/bem.json +++ b/dateparser_data/cldr_language_data/date_translation_data/bem.json @@ -88,6 +88,7 @@ "ubushiku" ], "hour": [ + "hr", "insa" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/bez.json b/dateparser_data/cldr_language_data/date_translation_data/bez.json index 5e6eca7e5..d331940a6 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/bez.json +++ b/dateparser_data/cldr_language_data/date_translation_data/bez.json @@ -96,6 +96,7 @@ "sihu" ], "hour": [ + "hr", "saa" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/bg.json b/dateparser_data/cldr_language_data/date_translation_data/bg.json index 63b57171d..e279706b5 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/bg.json +++ b/dateparser_data/cldr_language_data/date_translation_data/bg.json @@ -83,10 +83,11 @@ ], "year": [ "г", + "год", "година" ], "month": [ - "м", + "мес", "месец" ], "week": [ @@ -99,14 +100,15 @@ ], "hour": [ "ч", - "час" + "час", + "часове" ], "minute": [ "мин", "минута" ], "second": [ - "с", + "сек", "секунда" ], "relative-type": { @@ -145,7 +147,6 @@ ], "1 week ago": [ "мин седм", - "миналата седмица", "предходната седмица" ], "1 year ago": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/bm.json b/dateparser_data/cldr_language_data/date_translation_data/bm.json index 5f869a256..297b4e716 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/bm.json +++ b/dateparser_data/cldr_language_data/date_translation_data/bm.json @@ -94,6 +94,7 @@ "don" ], "hour": [ + "hr", "lɛrɛ" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/bn.json b/dateparser_data/cldr_language_data/date_translation_data/bn.json index 323afb47d..0cc83110b 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/bn.json +++ b/dateparser_data/cldr_language_data/date_translation_data/bn.json @@ -13,6 +13,7 @@ "মার্চ" ], "april": [ + "এপ্রি", "এপ্রিল" ], "may": [ @@ -22,21 +23,27 @@ "জুন" ], "july": [ + "জুল", "জুলাই" ], "august": [ + "আগ", "আগস্ট" ], "september": [ + "সেপ", "সেপ্টেম্বর" ], "october": [ + "অক্টো", "অক্টোবর" ], "november": [ + "নভে", "নভেম্বর" ], "december": [ + "ডিসে", "ডিসেম্বর" ], "monday": [ @@ -52,7 +59,6 @@ "বুধবার" ], "thursday": [ - "বৃহষ্পতিবার", "বৃহস্পতি", "বৃহস্পতিবার" ], @@ -87,6 +93,7 @@ "দিন" ], "hour": [ + "ঘণ্টা", "ঘন্টা" ], "minute": [ @@ -150,8 +157,7 @@ "{0} ঘন্টা আগে" ], "\\1 minute ago": [ - "{0} মিনিট আগে", - "{0} মিনিট পূর্বে" + "{0} মিনিট আগে" ], "\\1 month ago": [ "{0} মাস আগে" @@ -190,7 +196,19 @@ }, "locale_specific": { "bn-IN": { - "name": "bn-IN" + "name": "bn-IN", + "september": [ + "সেপ্টেঃ" + ], + "october": [ + "অক্টোঃ" + ], + "november": [ + "নভেঃ" + ], + "december": [ + "ডিসেঃ" + ] } } } \ No newline at end of file diff --git a/dateparser_data/cldr_language_data/date_translation_data/bo.json b/dateparser_data/cldr_language_data/date_translation_data/bo.json index 8a93daa47..7c9bff6a1 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/bo.json +++ b/dateparser_data/cldr_language_data/date_translation_data/bo.json @@ -108,6 +108,7 @@ "ཉིན།" ], "hour": [ + "hr", "ཆུ་ཚོད་" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/br.json b/dateparser_data/cldr_language_data/date_translation_data/br.json index 87ce96aff..036e88d63 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/br.json +++ b/dateparser_data/cldr_language_data/date_translation_data/br.json @@ -1,6 +1,6 @@ { "name": "br", - "date_order": "YMD", + "date_order": "DMY", "january": [ "gen", "genver" @@ -42,7 +42,6 @@ "du" ], "december": [ - "ker", "kerzu", "kzu" ], @@ -78,13 +77,16 @@ "gm" ], "year": [ + "b", "bl", "bloaz" ], "month": [ + "m", "miz" ], "week": [ + "sizh", "sizhun" ], "day": [ @@ -93,7 +95,8 @@ ], "hour": [ "e", - "eur" + "eur", + "eurioù" ], "minute": [ "min", @@ -108,12 +111,13 @@ "hiziv" ], "0 hour ago": [ - "this hour" + "d'an eur-mañ" ], "0 minute ago": [ - "this minute" + "ar munut-mañ" ], "0 month ago": [ + "ar m-mañ", "ar miz-mañ" ], "0 second ago": [ @@ -121,6 +125,7 @@ "bremañ" ], "0 week ago": [ + "ar sizh-mañ", "ar sizhun-mañ" ], "0 year ago": [ @@ -130,9 +135,11 @@ "dec'h" ], "1 month ago": [ + "ar m diaraok", "ar miz diaraok" ], "1 week ago": [ + "ar sizh diaraok", "ar sizhun diaraok" ], "1 year ago": [ @@ -142,9 +149,11 @@ "warc'hoazh" ], "in 1 month": [ + "ar m a zeu", "ar miz a zeu" ], "in 1 week": [ + "ar sizh a zeu", "ar sizhun a zeu" ], "in 1 year": [ @@ -173,6 +182,7 @@ "{0} s zo" ], "\\1 week ago": [ + "{0} sizh zo", "{0} sizhun zo" ], "\\1 year ago": [ @@ -200,6 +210,7 @@ "a-benn {0} s" ], "in \\1 week": [ + "a-benn {0} sizh", "a-benn {0} sizhun" ], "in \\1 year": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/brx.json b/dateparser_data/cldr_language_data/date_translation_data/brx.json index bcac7ebb7..c46097549 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/brx.json +++ b/dateparser_data/cldr_language_data/date_translation_data/brx.json @@ -1,17 +1,20 @@ { "name": "brx", - "date_order": "MDY", + "date_order": "DMY", "january": [ + "जान", "जानुवारी" ], "february": [ - "फेब्रुवारी" + "फेब", + "फेब्रूवारी" ], "march": [ - "मार्स" + "मार्च" ], "april": [ - "एफ्रिल" + "एप्रि", + "एप्रिल" ], "may": [ "मे" @@ -20,22 +23,28 @@ "जुन" ], "july": [ - "जुलाइ" + "जुल", + "जुलाई" ], "august": [ - "आगस्थ" + "आग", + "आगष्ट" ], "september": [ - "सेबथेज्ब़र" + "सेप", + "सेप्थेम्बर" ], "october": [ - "अखथबर" + "अक्ट'", + "अक्ट'बर" ], "november": [ - "नबेज्ब़र" + "नवे", + "नवेम्बर" ], "december": [ - "दिसेज्ब़र" + "डिसे", + "डिसेम्बर" ], "monday": [ "सम", @@ -46,20 +55,21 @@ "मंगलबार" ], "wednesday": [ - "बुद", - "बुदबार" + "बुध", + "बुधबार" ], "thursday": [ - "बिसथि", - "बिसथिबार" + "बिस्थि", + "बिस्थिबार" ], "friday": [ "सुखुर", - "सुखुरबार" + "सुखुरबार", + "सुुखुरबार" ], "saturday": [ - "सुनि", - "सुनिबार" + "सनि", + "सनिबार" ], "sunday": [ "रबि", @@ -78,65 +88,110 @@ "दान" ], "week": [ - "सबथा/हबथा" + "सप्थाह" ], "day": [ "सान" ], "hour": [ - "रिंगा" + "hr", + "घन्टा" ], "minute": [ - "मिनिथ" + "मिनित" ], "second": [ - "सेखेन्द" + "सेकेण्ड" ], "relative-type": { "0 day ago": [ "दिनै" ], "0 hour ago": [ - "this hour" + "बे घन्टा" ], "0 minute ago": [ - "this minute" + "बे मिनिट" ], "0 month ago": [ - "this month" + "बे दान" ], "0 second ago": [ - "now" + "दा" ], "0 week ago": [ - "this week" + "बे सप्थाह" ], "0 year ago": [ - "this year" + "बे बोसोर" ], "1 day ago": [ "मैया" ], "1 month ago": [ - "last month" + "थांनाय दान" ], "1 week ago": [ - "last week" + "थांनाय सप्थाह" ], "1 year ago": [ - "last year" + "थांनाय बोसोर" ], "in 1 day": [ "गाबोन" ], "in 1 month": [ - "next month" + "फैगौ दान" ], "in 1 week": [ - "next week" + "फैगौ सप्थाह" ], "in 1 year": [ - "next year" + "फैगौ बोसोर" + ] + }, + "relative-type-regex": { + "\\1 day ago": [ + "{0} सान सिगां" + ], + "\\1 hour ago": [ + "{0} घन्टा सिगां" + ], + "\\1 minute ago": [ + "{0} मिनिट सिगां" + ], + "\\1 month ago": [ + "{0} दान सिगां" + ], + "\\1 second ago": [ + "{0} सेकेण्ड सिगां" + ], + "\\1 week ago": [ + "{0} सप्थाह सिगां" + ], + "\\1 year ago": [ + "{0} बोसोर सिगां" + ], + "in \\1 day": [ + "{0} सानाव" + ], + "in \\1 hour": [ + "{0} घन्टायाव" + ], + "in \\1 minute": [ + "{0} मिनिटआव" + ], + "in \\1 month": [ + "{0} दानाव" + ], + "in \\1 second": [ + "{0} सेकेण्डआव" + ], + "in \\1 week": [ + "{0} सप्थाहयाव" + ], + "in \\1 year": [ + "{0} बोसोरआव" ] }, "locale_specific": {} diff --git a/dateparser_data/cldr_language_data/date_translation_data/bs-Cyrl.json b/dateparser_data/cldr_language_data/date_translation_data/bs-Cyrl.json index 855eebd8c..c9e190cdd 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/bs-Cyrl.json +++ b/dateparser_data/cldr_language_data/date_translation_data/bs-Cyrl.json @@ -29,8 +29,8 @@ "јули" ], "august": [ - "авг", - "август" + "ауг", + "аугуст" ], "september": [ "сеп", @@ -50,7 +50,7 @@ ], "monday": [ "пон", - "понедељак" + "понедјељак" ], "tuesday": [ "уто", @@ -74,33 +74,41 @@ ], "sunday": [ "нед", - "недеља" + "недјеља" ], "am": [ - "пре подне" + "пре подне", + "прије подне" ], "pm": [ - "поподне" + "поподне", + "послије подне" ], "year": [ + "год", "година" ], "month": [ - "месец" + "мјес", + "мјесец" ], "week": [ - "недеља" + "седм", + "седмица" ], "day": [ "дан" ], "hour": [ - "час" + "сат", + "сати" ], "minute": [ + "мин", "минут" ], "second": [ + "сек", "секунд" ], "relative-type": { @@ -108,76 +116,92 @@ "данас" ], "0 hour ago": [ - "this hour" + "овог сата" ], "0 minute ago": [ - "this minute" + "овог минута" ], "0 month ago": [ - "овог месеца" + "ов мјес", + "овог мјес", + "овог мјесеца" ], "0 second ago": [ - "now" + "сада" ], "0 week ago": [ - "ове недеље" + "ове седм", + "ове седмице" ], "0 year ago": [ + "ове год", "ове године" ], "1 day ago": [ "јуче" ], "1 month ago": [ - "прошлог месеца" + "прош мјес", + "прош мјесеца", + "прошлог мјесеца" ], "1 week ago": [ - "прошле недеље" + "прош седм", + "прошле седмице" ], "1 year ago": [ + "прош године", "прошле године" ], "in 1 day": [ "сутра" ], "in 1 month": [ - "следећег месеца" + "сљ мјес", + "сљед мјесеца", + "сљедећег мјесеца" ], "in 1 week": [ - "следеће недеље" + "сљ седм", + "сљедеће седмице" ], "in 1 year": [ - "следеће године" + "сљед године", + "сљедеће године" ] }, "relative-type-regex": { "\\1 day ago": [ - "пре {0} дан", - "пре {0} дана" + "прије {0} дан", + "прије {0} дана" ], "\\1 hour ago": [ - "пре {0} сат", - "пре {0} сати" + "прије {0} сат", + "прије {0} сати" ], "\\1 minute ago": [ - "пре {0} минут", - "пре {0} минута" + "прије {0} мин", + "прије {0} минут", + "прије {0} минута" ], "\\1 month ago": [ - "пре {0} месец", - "пре {0} месеци" + "прије {0} мјес", + "прије {0} мјесец", + "прије {0} мјесеци" ], "\\1 second ago": [ - "пре {0} секунд", - "пре {0} секунди" + "прије {0} сек", + "прије {0} секунд", + "прије {0} секунди" ], "\\1 week ago": [ - "пре {0} недеља", - "пре {0} недељу" + "прије {0} седм", + "прије {0} седмица", + "прије {0} седмицу" ], "\\1 year ago": [ - "пре {0} година", - "пре {0} годину" + "прије {0} година", + "прије {0} годину" ], "in \\1 day": [ "за {0} дан", @@ -192,16 +216,19 @@ "за {0} минута" ], "in \\1 month": [ - "за {0} месец", - "за {0} месеци" + "за {0} мјес", + "за {0} мјесец", + "за {0} мјесеци" ], "in \\1 second": [ + "за {0} сек", "за {0} секунд", "за {0} секунди" ], "in \\1 week": [ - "за {0} недеља", - "за {0} недељу" + "за {0} седм", + "за {0} седмица", + "за {0} седмицу" ], "in \\1 year": [ "за {0} година", diff --git a/dateparser_data/cldr_language_data/date_translation_data/bs-Latn.json b/dateparser_data/cldr_language_data/date_translation_data/bs-Latn.json index 8054554e8..a56d562f5 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/bs-Latn.json +++ b/dateparser_data/cldr_language_data/date_translation_data/bs-Latn.json @@ -29,8 +29,8 @@ "juli" ], "august": [ - "avg", - "avgust" + "aug", + "august" ], "september": [ "sep", @@ -77,9 +77,11 @@ "nedjelja" ], "am": [ + "am", "prijepodne" ], "pm": [ + "pm", "popodne" ], "year": [ @@ -100,7 +102,8 @@ ], "hour": [ "h", - "sat" + "sat", + "sati" ], "minute": [ "min", diff --git a/dateparser_data/cldr_language_data/date_translation_data/bs.json b/dateparser_data/cldr_language_data/date_translation_data/bs.json index 19707b019..7f2b8693f 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/bs.json +++ b/dateparser_data/cldr_language_data/date_translation_data/bs.json @@ -29,8 +29,8 @@ "juli" ], "august": [ - "avg", - "avgust" + "aug", + "august" ], "september": [ "sep", @@ -77,9 +77,11 @@ "nedjelja" ], "am": [ + "am", "prijepodne" ], "pm": [ + "pm", "popodne" ], "year": [ @@ -100,7 +102,8 @@ ], "hour": [ "h", - "sat" + "sat", + "sati" ], "minute": [ "min", diff --git a/dateparser_data/cldr_language_data/date_translation_data/ca.json b/dateparser_data/cldr_language_data/date_translation_data/ca.json index eff1aaae8..411384232 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ca.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ca.json @@ -116,7 +116,8 @@ ], "hour": [ "h", - "hora" + "hora", + "hores" ], "minute": [ "min", @@ -153,13 +154,11 @@ "ahir" ], "1 month ago": [ - "el mes passat", - "mes passat" + "el mes passat" ], "1 week ago": [ "la setm passada", - "la setmana passada", - "setm passada" + "la setmana passada" ], "1 year ago": [ "l'any passat" @@ -168,13 +167,11 @@ "demà" ], "in 1 month": [ - "el mes que ve", - "mes vinent" + "el mes que ve" ], "in 1 week": [ "la setm que ve", - "la setmana que ve", - "setm vinent" + "la setmana que ve" ], "in 1 year": [ "l'any que ve" diff --git a/dateparser_data/cldr_language_data/date_translation_data/ce.json b/dateparser_data/cldr_language_data/date_translation_data/ce.json index cacb80538..70f935ce2 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ce.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ce.json @@ -49,25 +49,32 @@ "декабрь" ], "monday": [ - "оршотан де" + "ор", + "оршот" ], "tuesday": [ - "шинарин де" + "ши", + "шинара" ], "wednesday": [ - "кхаарин де" + "кха", + "кхаара" ], "thursday": [ - "еарин де" + "еа", + "еара" ], "friday": [ - "пӏераскан де" + "пӏе", + "пӏераска" ], "saturday": [ - "шот де" + "шуо", + "шуот" ], "sunday": [ - "кӏиранан де" + "кӏи", + "кӏира" ], "am": [ "am" @@ -92,7 +99,8 @@ ], "hour": [ "сахь", - "сахьт" + "сахьт", + "сахьташ" ], "minute": [ "мин", @@ -107,16 +115,16 @@ "тахана" ], "0 hour ago": [ - "this hour" + "хӏокху сахьтехь" ], "0 minute ago": [ - "this minute" + "хӏокху минотехь" ], "0 month ago": [ "карарчу баттахь" ], "0 second ago": [ - "now" + "хӏинца" ], "0 week ago": [ "карарчу кӏирнахь" diff --git a/dateparser_data/cldr_language_data/date_translation_data/cgg.json b/dateparser_data/cldr_language_data/date_translation_data/cgg.json index 7765763cc..752cf9e55 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/cgg.json +++ b/dateparser_data/cldr_language_data/date_translation_data/cgg.json @@ -96,6 +96,7 @@ "eizooba" ], "hour": [ + "hr", "shaaha" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/chr.json b/dateparser_data/cldr_language_data/date_translation_data/chr.json index aa484dbb8..018369055 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/chr.json +++ b/dateparser_data/cldr_language_data/date_translation_data/chr.json @@ -81,6 +81,7 @@ "ꮜꮎꮄ" ], "pm": [ + "ꮢꭿᏹꭲ", "ꮢꭿᏹꭲꮧꮲ" ], "year": [ @@ -99,6 +100,7 @@ "ꭲꭶ" ], "hour": [ + "ꭲᏻꮯꮆꮣ", "ꮡꮯ", "ꮡꮯꮆꮣ" ], @@ -107,6 +109,7 @@ "ꭲꮿꮤꮼꮝꮤꮕ" ], "second": [ + "ꭰꮞ", "ꭰꮞꮲ" ], "relative-type": { @@ -120,6 +123,7 @@ "ꭿꭰ ꭲꮿꮤꮼꮝꮤꮕ" ], "0 month ago": [ + "ꭿꭰ ꭷꮈ", "ꭿꭰ ꭷꮈꭲ" ], "0 second ago": [ @@ -135,6 +139,7 @@ "ꮢꭿ" ], "1 month ago": [ + "ꭷꮈ ꮵꭸꮢ", "ꭷꮈꭲ ꮵꭸꮢ" ], "1 week ago": [ @@ -147,6 +152,8 @@ "ꮜꮎꮄꭲ" ], "in 1 month": [ + "ꭿꭰ ꭷꮈ", + "ꮤꮅꮑ ꭷꮈ", "ꮤꮅꮑ ꭷꮈꭲ" ], "in 1 week": [ @@ -163,31 +170,32 @@ ], "\\1 hour ago": [ "{0} ꭲᏻꮯꮆꮣ ꮵꭸꮢ", - "{0} ꮡꮯꮆꮣ ꮵꭸꮢ", - "ꮎꮏ {0} ꮡꮯ ꮵꭸꮢ" + "{0} ꮡꮯ ꮵꭸꮢ", + "{0} ꮡꮯꮆꮣ ꮵꭸꮢ" ], "\\1 minute ago": [ - "ꮎꮏ {0} ꭲꮿꮤ ꮵꭸꮢ", - "ꮎꮏ {0} ꭲꮿꮤꮼꮝꮤꮕ ꮵꭸꮢ" + "{0} ꭲꮿꮤ ꮵꭸꮢ", + "{0} ꭲꮿꮤꮼꮝꮤꮕ ꮵꭸꮢ" ], "\\1 month ago": [ - "ꮎꮏ {0} ꭷꮈ ꮵꭸꮢ", - "ꮎꮏ {0} ꭷꮈꭲ ꮵꭸꮢ", - "ꮎꮏ {0} ꮧꭷꮈꭲ ꮵꭸꮢ" + "{0} ꭷꮈ ꮵꭸꮢ", + "{0} ꭷꮈꭲ ꮵꭸꮢ", + "{0} ꮧꭷꮈꭲ ꮵꭸꮢ" ], "\\1 second ago": [ + "{0} ꭰꮞ ꮵꭸꮢ", "{0} ꭰꮞꮲ ꮵꭸꮢ", "{0} ꮣꮣꮎꮹꮝꭼ ꮵꭸꮢ" ], "\\1 week ago": [ - "ꮎꮏ {0} ꭲᏻꮎꮩꮣꮖꮝꮧ ꮵꭸꮢ", - "ꮎꮏ {0} ꮢꮎ ꮵꭸꮢ", - "ꮎꮏ {0} ꮢꮎꮩꮣꮖꮝꮧ ꮵꭸꮢ" + "{0} ꭲᏻꮎꮩꮣꮖꮝꮧ ꮵꭸꮢ", + "{0} ꮢꮎ ꮵꭸꮢ", + "{0} ꮢꮎꮩꮣꮖꮝꮧ ꮵꭸꮢ" ], "\\1 year ago": [ "{0} ꭲꮷꮥꮨᏼꮜꮧꮢꭲ ꮵꭸꮢ", - "{0} ꭴꮥꮨᏼꮜꮧꮢꭲ ꮵꭸꮢ", - "ꮎꮏ {0} ꭴꮥ ꮵꭸꮢ" + "{0} ꭴꮥ ꮵꭸꮢ", + "{0} ꭴꮥꮨᏼꮜꮧꮢꭲ ꮵꭸꮢ" ], "in \\1 day": [ "ꮎꮏ {0} ꭲꭶ", @@ -208,6 +216,7 @@ "ꮎꮏ {0} ꮧꭷꮈꭲ" ], "in \\1 second": [ + "ꮎꮏ {0} ꭰꮞ", "ꮎꮏ {0} ꭰꮞꮲ", "ꮎꮏ {0} ꮣꮣꮎꮹꮝꭼ ꮵꭸꮢ" ], diff --git a/dateparser_data/cldr_language_data/date_translation_data/ckb.json b/dateparser_data/cldr_language_data/date_translation_data/ckb.json index 77e79baf7..d04ed463d 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ckb.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ckb.json @@ -77,7 +77,8 @@ "day" ], "hour": [ - "hour" + "hour", + "hr" ], "minute": [ "minute" diff --git a/dateparser_data/cldr_language_data/date_translation_data/cs.json b/dateparser_data/cldr_language_data/date_translation_data/cs.json index 1b3e38285..2e4db6421 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/cs.json +++ b/dateparser_data/cldr_language_data/date_translation_data/cs.json @@ -111,7 +111,8 @@ ], "hour": [ "h", - "hodina" + "hodina", + "hodiny" ], "minute": [ "min", @@ -132,6 +133,7 @@ "tuto minutu" ], "0 month ago": [ + "tento měs", "tento měsíc" ], "0 second ago": [ @@ -148,6 +150,7 @@ "včera" ], "1 month ago": [ + "minulý měs", "minulý měsíc" ], "1 week ago": [ @@ -161,6 +164,7 @@ "zítra" ], "in 1 month": [ + "příští měs", "příští měsíc" ], "in 1 week": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/cy.json b/dateparser_data/cldr_language_data/date_translation_data/cy.json index 26a012079..815b42d59 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/cy.json +++ b/dateparser_data/cldr_language_data/date_translation_data/cy.json @@ -78,9 +78,11 @@ "sul" ], "am": [ + "am", "yb" ], "pm": [ + "pm", "yh" ], "year": [ @@ -94,10 +96,11 @@ "wythnos" ], "day": [ - "dydd" + "diwrnod" ], "hour": [ - "awr" + "awr", + "oriau" ], "minute": [ "mun", @@ -123,6 +126,7 @@ "nawr" ], "0 week ago": [ + "yr ws hon", "yr wythnos hon" ], "0 year ago": [ @@ -135,6 +139,7 @@ "mis diwethaf" ], "1 week ago": [ + "ws ddiwethaf", "wythnos ddiwethaf" ], "1 year ago": [ @@ -147,9 +152,11 @@ "mis nesaf" ], "in 1 week": [ + "ws nesaf", "wythnos nesaf" ], "in 1 year": [ + "bl nesaf", "blwyddyn nesaf" ] }, @@ -168,12 +175,15 @@ "{0} mis yn ôl" ], "\\1 second ago": [ + "{0} eil yn ôl", "{0} eiliad yn ôl" ], "\\1 week ago": [ + "{0} ws yn ôl", "{0} wythnos yn ôl" ], "\\1 year ago": [ + "{0} bl yn ôl", "{0} o flynyddoedd yn ôl" ], "in \\1 day": [ @@ -190,9 +200,11 @@ "ymhen {0} mis" ], "in \\1 second": [ + "ymhen {0} eil", "ymhen {0} eiliad" ], "in \\1 week": [ + "ymhen {0} ws", "ymhen {0} wythnos" ], "in \\1 year": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/da.json b/dateparser_data/cldr_language_data/date_translation_data/da.json index 73ac01944..fd3a95b10 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/da.json +++ b/dateparser_data/cldr_language_data/date_translation_data/da.json @@ -53,7 +53,7 @@ "mandag" ], "tuesday": [ - "tir", + "tirs", "tirsdag" ], "wednesday": [ @@ -61,7 +61,7 @@ "onsdag" ], "thursday": [ - "tor", + "tors", "torsdag" ], "friday": [ @@ -97,7 +97,8 @@ ], "hour": [ "t", - "time" + "time", + "timer" ], "minute": [ "min", @@ -113,10 +114,10 @@ "i dag" ], "0 hour ago": [ - "i den kommende time" + "denne time" ], "0 minute ago": [ - "i det kommende minut" + "dette minut" ], "0 month ago": [ "denne md", @@ -161,34 +162,41 @@ "relative-type-regex": { "\\1 day ago": [ "for {0} dag siden", - "for {0} dage siden" + "for {0} dage siden", + "{0} dag siden", + "{0} dage siden" ], "\\1 hour ago": [ "for {0} time siden", - "for {0} timer siden" + "for {0} timer siden", + "{0} time siden", + "{0} timer siden" ], "\\1 minute ago": [ - "for {0} min siden", "for {0} minut siden", - "for {0} minutter siden" + "for {0} minutter siden", + "{0} min siden" ], "\\1 month ago": [ - "for {0} md siden", - "for {0} mdr siden", "for {0} måned siden", - "for {0} måneder siden" + "for {0} måneder siden", + "{0} md siden", + "{0} mdr siden" ], "\\1 second ago": [ - "for {0} sek siden", "for {0} sekund siden", - "for {0} sekunder siden" + "for {0} sekunder siden", + "{0} sek siden" ], "\\1 week ago": [ "for {0} uge siden", - "for {0} uger siden" + "for {0} uger siden", + "{0} uge siden", + "{0} uger siden" ], "\\1 year ago": [ - "for {0} år siden" + "for {0} år siden", + "{0} år siden" ], "in \\1 day": [ "om {0} dag", diff --git a/dateparser_data/cldr_language_data/date_translation_data/dav.json b/dateparser_data/cldr_language_data/date_translation_data/dav.json index 2b157008c..519408bdc 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/dav.json +++ b/dateparser_data/cldr_language_data/date_translation_data/dav.json @@ -96,6 +96,7 @@ "ituku" ], "hour": [ + "hr", "saa" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/de.json b/dateparser_data/cldr_language_data/date_translation_data/de.json index 8eb30291b..761171dbd 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/de.json +++ b/dateparser_data/cldr_language_data/date_translation_data/de.json @@ -34,6 +34,7 @@ ], "september": [ "sep", + "sept", "september" ], "october": [ @@ -77,10 +78,10 @@ "sonntag" ], "am": [ - "vorm" + "am" ], "pm": [ - "nachm" + "pm" ], "year": [ "j", @@ -99,7 +100,8 @@ ], "hour": [ "std", - "stunde" + "stunde", + "stunden" ], "minute": [ "min", diff --git a/dateparser_data/cldr_language_data/date_translation_data/dje.json b/dateparser_data/cldr_language_data/date_translation_data/dje.json index bbfbcc970..05fe9d802 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/dje.json +++ b/dateparser_data/cldr_language_data/date_translation_data/dje.json @@ -94,7 +94,8 @@ "zaari" ], "hour": [ - "guuru" + "guuru", + "hr" ], "minute": [ "miniti" diff --git a/dateparser_data/cldr_language_data/date_translation_data/dsb.json b/dateparser_data/cldr_language_data/date_translation_data/dsb.json index af9617796..0e219da76 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/dsb.json +++ b/dateparser_data/cldr_language_data/date_translation_data/dsb.json @@ -89,9 +89,11 @@ "njeźela" ], "am": [ + "dop", "dopołdnja" ], "pm": [ + "wótp", "wótpołdnja" ], "year": [ @@ -113,7 +115,8 @@ "hour": [ "g", "góź", - "góźina" + "góźina", + "góźiny" ], "minute": [ "m", @@ -127,48 +130,70 @@ ], "relative-type": { "0 day ago": [ - "źinsa" + "źins", + "źinsa", + "źis" ], "0 hour ago": [ - "this hour" + "w toś tej góźinje" ], "0 minute ago": [ - "this minute" + "w toś tej minuśe" ], "0 month ago": [ - "ten mjasec" + "te mjasec", + "ten mjasec", + "tot mjasec" ], "0 second ago": [ - "now" + "něnto" ], "0 week ago": [ - "ten tyźeń" + "te tyźeń", + "ten tyźeń", + "tot tyźeń" ], "0 year ago": [ - "lětosa" + "lět", + "lětosa", + "lěts" ], "1 day ago": [ - "cora" + "cora", + "cr", + "cra" ], "1 month ago": [ - "slědny mjasec" + "zajź mjasec", + "zajźony mjasec" ], "1 week ago": [ - "slědny tyźeń" + "zajź tyźeń", + "zajźony tyźeń" ], "1 year ago": [ + "ło", + "łon", "łoni" ], "in 1 day": [ + "wit", + "witś", "witśe" ], "in 1 month": [ + "pśid mjasec", + "pśiduc mjasec", "pśiducy mjasec" ], "in 1 week": [ + "pśid tyźeń", + "pśiduc tyźeń", "pśiducy tyźeń" ], "in 1 year": [ + "zno", + "znow", "znowa" ] }, diff --git a/dateparser_data/cldr_language_data/date_translation_data/dua.json b/dateparser_data/cldr_language_data/date_translation_data/dua.json index 7dab932cf..1945d3117 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/dua.json +++ b/dateparser_data/cldr_language_data/date_translation_data/dua.json @@ -96,6 +96,7 @@ "búnyá" ], "hour": [ + "hr", "ŋgandɛ" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/dyo.json b/dateparser_data/cldr_language_data/date_translation_data/dyo.json index 39d23972e..974da2b3f 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/dyo.json +++ b/dateparser_data/cldr_language_data/date_translation_data/dyo.json @@ -95,7 +95,8 @@ "funak" ], "hour": [ - "hour" + "hour", + "hr" ], "minute": [ "minute" diff --git a/dateparser_data/cldr_language_data/date_translation_data/dz.json b/dateparser_data/cldr_language_data/date_translation_data/dz.json index c5379b378..0ac4382b1 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/dz.json +++ b/dateparser_data/cldr_language_data/date_translation_data/dz.json @@ -108,6 +108,7 @@ "ཚེས་" ], "hour": [ + "hr", "ཆུ་ཚོད" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/ebu.json b/dateparser_data/cldr_language_data/date_translation_data/ebu.json index fe8af614d..162b39c34 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ebu.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ebu.json @@ -96,6 +96,7 @@ "mũthenya" ], "hour": [ + "hr", "ithaa" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/ee.json b/dateparser_data/cldr_language_data/date_translation_data/ee.json index e688958ae..657174584 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ee.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ee.json @@ -96,7 +96,8 @@ "ŋkeke" ], "hour": [ - "gaƒoƒo" + "gaƒoƒo", + "gaƒoƒowo" ], "minute": [ "aɖabaƒoƒo" diff --git a/dateparser_data/cldr_language_data/date_translation_data/el.json b/dateparser_data/cldr_language_data/date_translation_data/el.json index a9bb09f60..93f4c4a0f 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/el.json +++ b/dateparser_data/cldr_language_data/date_translation_data/el.json @@ -114,12 +114,13 @@ "εβδομάδα" ], "day": [ + "ημ", "ημέρα" ], "hour": [ "ώ", - "ώρ", - "ώρα" + "ώρα", + "ώρες" ], "minute": [ "λ", @@ -136,19 +137,22 @@ "σήμερα" ], "0 hour ago": [ - "αυτήν την ώρα" + "τρέχουσα ώρα" ], "0 minute ago": [ - "αυτό το λεπτό" + "τρέχον λεπτό" ], "0 month ago": [ + "τρέχ μήνας", "τρέχων μήνας" ], "0 second ago": [ "τώρα" ], "0 week ago": [ - "αυτήν την εβδομάδα" + "τρέχ εβδ", + "τρέχ εβδομάδα", + "τρέχουσα εβδομάδα" ], "0 year ago": [ "φέτος" @@ -157,9 +161,12 @@ "χθες" ], "1 month ago": [ + "προηγ μήνας", "προηγούμενος μήνας" ], "1 week ago": [ + "προηγ εβδ", + "προηγ εβδομάδα", "προηγούμενη εβδομάδα" ], "1 year ago": [ @@ -169,9 +176,12 @@ "αύριο" ], "in 1 month": [ + "επόμ μήνας", "επόμενος μήνας" ], "in 1 week": [ + "επόμ εβδ", + "επόμ εβδομάδα", "επόμενη εβδομάδα" ], "in 1 year": [ @@ -181,12 +191,13 @@ "relative-type-regex": { "\\1 day ago": [ "{0} ημ πριν", + "πριν από {0} ημ", "πριν από {0} ημέρα", "πριν από {0} ημέρες" ], "\\1 hour ago": [ "{0} ώ πριν", - "πριν από {0} ώρ", + "πριν από {0} ώ", "πριν από {0} ώρα", "πριν από {0} ώρες" ], @@ -226,7 +237,6 @@ ], "in \\1 hour": [ "σε {0} ώ", - "σε {0} ώρ", "σε {0} ώρα", "σε {0} ώρες" ], diff --git a/dateparser_data/cldr_language_data/date_translation_data/en.json b/dateparser_data/cldr_language_data/date_translation_data/en.json index 3efae0a6a..86f92c72d 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/en.json +++ b/dateparser_data/cldr_language_data/date_translation_data/en.json @@ -99,6 +99,7 @@ ], "hour": [ "hour", + "hours", "hr" ], "minute": [ @@ -168,132 +169,213 @@ "relative-type-regex": { "\\1 day ago": [ "{0} day ago", - "{0} days ago" + "{0} days ago", + "{0}d ago" ], "\\1 hour ago": [ "{0} hour ago", "{0} hours ago", - "{0} hr ago" + "{0} hr ago", + "{0}h ago" ], "\\1 minute ago": [ "{0} min ago", "{0} minute ago", - "{0} minutes ago" + "{0} minutes ago", + "{0}m ago" ], "\\1 month ago": [ "{0} mo ago", "{0} month ago", - "{0} months ago" + "{0} months ago", + "{0}mo ago" ], "\\1 second ago": [ "{0} sec ago", "{0} second ago", - "{0} seconds ago" + "{0} seconds ago", + "{0}s ago" ], "\\1 week ago": [ "{0} week ago", "{0} weeks ago", - "{0} wk ago" + "{0} wk ago", + "{0}w ago" ], "\\1 year ago": [ "{0} year ago", "{0} years ago", - "{0} yr ago" + "{0} yr ago", + "{0}y ago" ], "in \\1 day": [ "in {0} day", - "in {0} days" + "in {0} days", + "in {0}d" ], "in \\1 hour": [ "in {0} hour", "in {0} hours", - "in {0} hr" + "in {0} hr", + "in {0}h" ], "in \\1 minute": [ "in {0} min", "in {0} minute", - "in {0} minutes" + "in {0} minutes", + "in {0}m" ], "in \\1 month": [ "in {0} mo", "in {0} month", - "in {0} months" + "in {0} months", + "in {0}mo" ], "in \\1 second": [ "in {0} sec", "in {0} second", - "in {0} seconds" + "in {0} seconds", + "in {0}s" ], "in \\1 week": [ "in {0} week", "in {0} weeks", - "in {0} weeks time", - "in {0} weeks' time", - "in {0} wk" + "in {0} wk", + "in {0}w" ], "in \\1 year": [ "in {0} year", "in {0} years", - "in {0} yr" + "in {0} yr", + "in {0}y" ] }, "locale_specific": { "en-001": { "name": "en-001", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-150": { "name": "en-150", + "date_order": "DMY", + "september": [ + "sept" + ] + }, + "en-AE": { + "name": "en-AE", "date_order": "DMY" }, "en-AG": { "name": "en-AG", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-AI": { "name": "en-AI", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-AS": { "name": "en-AS" }, "en-AT": { "name": "en-AT", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-AU": { "name": "en-AU", "date_order": "DMY", - "hour": [ - "h" - ] + "september": [ + "sept" + ], + "relative-type-regex": { + "\\1 hour ago": [ + "{0} hrs ago" + ], + "\\1 minute ago": [ + "{0} mins ago" + ], + "\\1 second ago": [ + "{0} secs ago" + ], + "\\1 week ago": [ + "{0} wks ago" + ], + "\\1 year ago": [ + "{0} yrs ago" + ], + "in \\1 hour": [ + "in {0} hrs" + ], + "in \\1 minute": [ + "in {0} mins" + ], + "in \\1 second": [ + "in {0} secs" + ], + "in \\1 week": [ + "in {0} wks" + ], + "in \\1 year": [ + "in {0} yrs" + ] + } }, "en-BB": { "name": "en-BB", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-BE": { "name": "en-BE", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-BI": { "name": "en-BI" }, "en-BM": { "name": "en-BM", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-BS": { "name": "en-BS", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-BW": { "name": "en-BW", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-BZ": { "name": "en-BZ", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-CA": { "name": "en-CA", @@ -339,263 +421,459 @@ }, "en-CC": { "name": "en-CC", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-CH": { "name": "en-CH", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-CK": { "name": "en-CK", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-CM": { "name": "en-CM", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-CX": { "name": "en-CX", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-CY": { "name": "en-CY", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-DE": { "name": "en-DE", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-DG": { "name": "en-DG", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-DK": { "name": "en-DK", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-DM": { "name": "en-DM", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-ER": { "name": "en-ER", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-FI": { "name": "en-FI", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-FJ": { "name": "en-FJ", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-FK": { "name": "en-FK", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-FM": { "name": "en-FM", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-GB": { "name": "en-GB", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-GD": { "name": "en-GD", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-GG": { "name": "en-GG", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-GH": { "name": "en-GH", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-GI": { "name": "en-GI", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-GM": { "name": "en-GM", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-GU": { "name": "en-GU" }, "en-GY": { "name": "en-GY", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-HK": { "name": "en-HK", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] + }, + "en-ID": { + "name": "en-ID", + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-IE": { "name": "en-IE", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-IL": { "name": "en-IL", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-IM": { "name": "en-IM", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-IN": { "name": "en-IN", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-IO": { "name": "en-IO", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-JE": { "name": "en-JE", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-JM": { "name": "en-JM", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-KE": { "name": "en-KE", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-KI": { "name": "en-KI", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-KN": { "name": "en-KN", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-KY": { "name": "en-KY", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-LC": { "name": "en-LC", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-LR": { "name": "en-LR", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-LS": { "name": "en-LS", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-MG": { "name": "en-MG", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-MH": { "name": "en-MH" }, "en-MO": { "name": "en-MO", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-MP": { "name": "en-MP" }, "en-MS": { "name": "en-MS", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-MT": { "name": "en-MT", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-MU": { "name": "en-MU", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] + }, + "en-MV": { + "name": "en-MV", + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-MW": { "name": "en-MW", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-MY": { "name": "en-MY", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-NA": { "name": "en-NA", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-NF": { "name": "en-NF", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-NG": { "name": "en-NG", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-NL": { "name": "en-NL", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-NR": { "name": "en-NR", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-NU": { "name": "en-NU", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-NZ": { "name": "en-NZ", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-PG": { "name": "en-PG", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-PH": { - "name": "en-PH", - "date_order": "DMY" + "name": "en-PH" }, "en-PK": { "name": "en-PK", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-PN": { "name": "en-PN", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-PR": { "name": "en-PR" }, "en-PW": { "name": "en-PW", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-RW": { "name": "en-RW", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-SB": { "name": "en-SB", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-SC": { "name": "en-SC", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-SD": { "name": "en-SD", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-SE": { "name": "en-SE", - "date_order": "YMD" + "date_order": "YMD", + "september": [ + "sept" + ] }, "en-SG": { "name": "en-SG", "date_order": "DMY", + "september": [ + "sept" + ], "month": [ "mth" ], @@ -621,89 +899,149 @@ }, "en-SH": { "name": "en-SH", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-SI": { "name": "en-SI", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-SL": { "name": "en-SL", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-SS": { "name": "en-SS", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-SX": { "name": "en-SX", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-SZ": { "name": "en-SZ", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-TC": { "name": "en-TC", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-TK": { "name": "en-TK", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-TO": { "name": "en-TO", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-TT": { "name": "en-TT", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-TV": { "name": "en-TV", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-TZ": { "name": "en-TZ", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-UG": { "name": "en-UG", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-UM": { "name": "en-UM" }, "en-VC": { "name": "en-VC", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-VG": { "name": "en-VG", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-VI": { "name": "en-VI" }, "en-VU": { "name": "en-VU", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-WS": { "name": "en-WS", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-ZA": { "name": "en-ZA", - "date_order": "YMD" + "date_order": "YMD", + "september": [ + "sept" + ] }, "en-ZM": { "name": "en-ZM", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] }, "en-ZW": { "name": "en-ZW", - "date_order": "DMY" + "date_order": "DMY", + "september": [ + "sept" + ] } } } \ No newline at end of file diff --git a/dateparser_data/cldr_language_data/date_translation_data/eo.json b/dateparser_data/cldr_language_data/date_translation_data/eo.json index 635541d39..76511e9fc 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/eo.json +++ b/dateparser_data/cldr_language_data/date_translation_data/eo.json @@ -96,7 +96,8 @@ "day" ], "hour": [ - "hour" + "hour", + "hr" ], "minute": [ "minute" diff --git a/dateparser_data/cldr_language_data/date_translation_data/es.json b/dateparser_data/cldr_language_data/date_translation_data/es.json index f72bde156..07e936e1e 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/es.json +++ b/dateparser_data/cldr_language_data/date_translation_data/es.json @@ -101,7 +101,8 @@ ], "hour": [ "h", - "hora" + "hora", + "horas" ], "minute": [ "min", @@ -128,6 +129,7 @@ "ahora" ], "0 week ago": [ + "esta sem", "esta semana" ], "0 year ago": [ @@ -140,7 +142,8 @@ "el mes pasado" ], "1 week ago": [ - "la semana pasada" + "la semana pasada", + "sem ant" ], "1 year ago": [ "el año pasado" @@ -152,7 +155,8 @@ "el próximo mes" ], "in 1 week": [ - "la próxima semana" + "la próxima semana", + "próx sem" ], "in 1 year": [ "el próximo año" @@ -160,6 +164,7 @@ }, "relative-type-regex": { "\\1 day ago": [ + "hace {0} d", "hace {0} día", "hace {0} días" ], @@ -194,6 +199,7 @@ "hace {0} años" ], "in \\1 day": [ + "dentro de {0} d", "dentro de {0} día", "dentro de {0} días" ], @@ -231,18 +237,25 @@ "locale_specific": { "es-419": { "name": "es-419", - "september": [ - "sep" - ] + "relative-type": { + "1 week ago": [ + "sem pas" + ] + } }, "es-AR": { "name": "es-AR", - "september": [ - "sep" + "hour": [ + "hs" ], "second": [ "seg" ], + "relative-type": { + "1 week ago": [ + "sem pas" + ] + }, "relative-type-regex": { "\\1 second ago": [ "hace {0} seg" @@ -254,75 +267,97 @@ }, "es-BO": { "name": "es-BO", - "september": [ - "sep" - ] + "relative-type": { + "1 week ago": [ + "sem pas" + ] + } }, "es-BR": { "name": "es-BR", - "september": [ - "sep" - ] + "relative-type": { + "1 week ago": [ + "sem pas" + ] + } }, "es-BZ": { "name": "es-BZ", - "september": [ - "sep" - ] + "relative-type": { + "1 week ago": [ + "sem pas" + ] + } }, "es-CL": { "name": "es-CL", - "september": [ - "sep" - ] + "relative-type": { + "1 week ago": [ + "sem pas" + ] + } }, "es-CO": { "name": "es-CO", - "september": [ - "sep" - ] + "relative-type": { + "1 week ago": [ + "sem pas" + ] + } }, "es-CR": { "name": "es-CR", - "september": [ - "sep" - ] + "relative-type": { + "1 week ago": [ + "sem pas" + ] + } }, "es-CU": { "name": "es-CU", - "september": [ - "sep" - ] + "relative-type": { + "1 week ago": [ + "sem pas" + ] + } }, "es-DO": { "name": "es-DO", - "september": [ - "sep" - ] + "relative-type": { + "1 week ago": [ + "sem pas" + ] + } }, "es-EA": { "name": "es-EA" }, "es-EC": { "name": "es-EC", - "september": [ - "sep" - ] + "relative-type": { + "1 week ago": [ + "sem pas" + ] + } }, "es-GQ": { "name": "es-GQ" }, "es-GT": { "name": "es-GT", - "september": [ - "sep" - ] + "relative-type": { + "1 week ago": [ + "sem pas" + ] + } }, "es-HN": { "name": "es-HN", - "september": [ - "sep" - ] + "relative-type": { + "1 week ago": [ + "sem pas" + ] + } }, "es-IC": { "name": "es-IC" @@ -333,6 +368,9 @@ "sep" ], "relative-type": { + "1 week ago": [ + "sem pas" + ], "in 1 month": [ "el mes próximo" ], @@ -352,9 +390,6 @@ "en {0} h", "en {0} n" ], - "in \\1 minute": [ - "en {0} min" - ], "in \\1 month": [ "en {0} m", "en {0} mes", @@ -373,23 +408,32 @@ }, "es-NI": { "name": "es-NI", - "september": [ - "sep" - ] + "relative-type": { + "1 week ago": [ + "sem pas" + ] + } }, "es-PA": { "name": "es-PA", "date_order": "MDY", - "september": [ - "sep" - ] + "relative-type": { + "1 week ago": [ + "sem pas" + ] + } }, "es-PE": { "name": "es-PE", "september": [ "set", "setiembre" - ] + ], + "relative-type": { + "1 week ago": [ + "sem pas" + ] + } }, "es-PH": { "name": "es-PH" @@ -397,15 +441,22 @@ "es-PR": { "name": "es-PR", "date_order": "MDY", - "september": [ - "sep" - ] + "relative-type": { + "1 week ago": [ + "sem pas" + ] + } }, "es-PY": { "name": "es-PY", "second": [ "seg" ], + "relative-type": { + "1 week ago": [ + "sem pas" + ] + }, "relative-type-regex": { "\\1 second ago": [ "hace {0} seg" @@ -417,25 +468,42 @@ }, "es-SV": { "name": "es-SV", - "september": [ - "sep" - ] + "relative-type": { + "1 week ago": [ + "sem pas" + ] + } }, "es-US": { "name": "es-US", - "september": [ - "sep" - ] + "relative-type": { + "1 week ago": [ + "sem pasada" + ], + "in 1 week": [ + "próxima sem" + ] + } }, "es-UY": { "name": "es-UY", "september": [ "set", "setiembre" - ] + ], + "relative-type": { + "1 week ago": [ + "sem pas" + ] + } }, "es-VE": { - "name": "es-VE" + "name": "es-VE", + "relative-type": { + "1 week ago": [ + "sem pas" + ] + } } } } \ No newline at end of file diff --git a/dateparser_data/cldr_language_data/date_translation_data/et.json b/dateparser_data/cldr_language_data/date_translation_data/et.json index 43e33427f..5c9bea17e 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/et.json +++ b/dateparser_data/cldr_language_data/date_translation_data/et.json @@ -97,7 +97,8 @@ ], "hour": [ "t", - "tund" + "tund", + "tunnid" ], "minute": [ "min", @@ -119,39 +120,57 @@ "praegusel minutil" ], "0 month ago": [ - "käesolev kuu" + "käesolev kuu", + "see k", + "see kuu" ], "0 second ago": [ "nüüd" ], "0 week ago": [ - "käesolev nädal" + "käesolev nädal", + "see n", + "see näd" ], "0 year ago": [ - "käesolev aasta" + "käesolev a", + "käesolev aasta", + "see a" ], "1 day ago": [ "eile" ], "1 month ago": [ + "eelm k", + "eelm kuu", "eelmine kuu" ], "1 week ago": [ + "eelm n", + "eelm näd", "eelmine nädal" ], "1 year ago": [ + "eelm a", + "eelmine a", "eelmine aasta" ], "in 1 day": [ "homme" ], "in 1 month": [ + "järgm k", + "järgm kuu", "järgmine kuu" ], "in 1 week": [ + "järgm n", + "järgm näd", "järgmine nädal" ], "in 1 year": [ + "järgm a", + "järgmine a", "järgmine aasta" ] }, diff --git a/dateparser_data/cldr_language_data/date_translation_data/eu.json b/dateparser_data/cldr_language_data/date_translation_data/eu.json index 762c7d105..94cbb4632 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/eu.json +++ b/dateparser_data/cldr_language_data/date_translation_data/eu.json @@ -100,7 +100,8 @@ ], "hour": [ "h", - "ordua" + "ordua", + "orduak" ], "minute": [ "min", @@ -121,13 +122,13 @@ "minutu honetan" ], "0 month ago": [ - "hilabete hau" + "hilabete honetan" ], "0 second ago": [ "orain" ], "0 week ago": [ - "aste hau" + "aste honetan" ], "0 year ago": [ "aurten" @@ -136,25 +137,27 @@ "atzo" ], "1 month ago": [ - "aurreko hilabetea" + "aurreko hilabetean" ], "1 week ago": [ - "aurreko astea" + "aurreko astean" ], "1 year ago": [ - "aurreko urtea" + "aurreko urtea", + "iaz" ], "in 1 day": [ "bihar" ], "in 1 month": [ - "hurrengo hilabetea" + "hurrengo hilabetean" ], "in 1 week": [ - "hurrengo astea" + "hurrengo astean" ], "in 1 year": [ - "hurrengo urtea" + "hurrengo urtea", + "hurrengo urtean" ] }, "relative-type-regex": { diff --git a/dateparser_data/cldr_language_data/date_translation_data/ewo.json b/dateparser_data/cldr_language_data/date_translation_data/ewo.json index 9b8b5411f..48a79201a 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ewo.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ewo.json @@ -96,7 +96,8 @@ "amǒs" ], "hour": [ - "awola" + "awola", + "hr" ], "minute": [ "enútɛn" diff --git a/dateparser_data/cldr_language_data/date_translation_data/fa.json b/dateparser_data/cldr_language_data/date_translation_data/fa.json index 5fdd6216a..046c50fb9 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/fa.json +++ b/dateparser_data/cldr_language_data/date_translation_data/fa.json @@ -117,7 +117,6 @@ "دیروز" ], "1 month ago": [ - "ماه پیش", "ماه گذشته" ], "1 week ago": [ @@ -162,7 +161,8 @@ "{0} سال پیش" ], "in \\1 day": [ - "{0} روز بعد" + "{0} روز بعد", + "{0} روز دیگر" ], "in \\1 hour": [ "{0} ساعت بعد" diff --git a/dateparser_data/cldr_language_data/date_translation_data/ff.json b/dateparser_data/cldr_language_data/date_translation_data/ff.json index cf0517d49..0f76d2ab4 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ff.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ff.json @@ -96,6 +96,7 @@ "ñalnde" ], "hour": [ + "hr", "waktu" ], "minute": [ @@ -151,15 +152,5 @@ "next year" ] }, - "locale_specific": { - "ff-CM": { - "name": "ff-CM" - }, - "ff-GN": { - "name": "ff-GN" - }, - "ff-MR": { - "name": "ff-MR" - } - } + "locale_specific": {} } \ No newline at end of file diff --git a/dateparser_data/cldr_language_data/date_translation_data/fi.json b/dateparser_data/cldr_language_data/date_translation_data/fi.json index 36772ec69..e8a69a0e7 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/fi.json +++ b/dateparser_data/cldr_language_data/date_translation_data/fi.json @@ -132,6 +132,7 @@ ], "hour": [ "t", + "tunnit", "tunti" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/fil.json b/dateparser_data/cldr_language_data/date_translation_data/fil.json index d83cbba83..61b2c0a05 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/fil.json +++ b/dateparser_data/cldr_language_data/date_translation_data/fil.json @@ -96,6 +96,7 @@ "araw" ], "hour": [ + "mga oras", "oras" ], "minute": [ @@ -160,8 +161,7 @@ "{0} araw ang nakalipas" ], "\\1 hour ago": [ - "{0} oras ang nakalipas", - "{0} oras nakalipas" + "{0} oras ang nakalipas" ], "\\1 minute ago": [ "{0} min ang nakalipas", @@ -172,7 +172,6 @@ ], "\\1 second ago": [ "{0} seg ang nakalipas", - "{0} seg nakalipas", "{0} segundo ang nakalipas" ], "\\1 week ago": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/fo.json b/dateparser_data/cldr_language_data/date_translation_data/fo.json index b49f86b3e..3a4c9855b 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/fo.json +++ b/dateparser_data/cldr_language_data/date_translation_data/fo.json @@ -101,6 +101,7 @@ ], "hour": [ "t", + "tímar", "tími" ], "minute": [ @@ -124,12 +125,15 @@ "hendan minuttin" ], "0 month ago": [ + "henda mnð", "henda mánaðin" ], "0 second ago": [ "nú" ], "0 week ago": [ + "hesu v", + "hesu vi", "hesu viku" ], "0 year ago": [ @@ -139,9 +143,12 @@ "í gjár" ], "1 month ago": [ + "seinasta mnð", "seinasta mánað" ], "1 week ago": [ + "seinastu v", + "seinastu vi", "seinastu viku" ], "1 year ago": [ @@ -151,9 +158,12 @@ "í morgin" ], "in 1 month": [ + "næsta mnð", "næsta mánað" ], "in 1 week": [ + "næstu v", + "næstu vi", "næstu viku" ], "in 1 year": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/fr.json b/dateparser_data/cldr_language_data/date_translation_data/fr.json index 8de40f824..0e2476142 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/fr.json +++ b/dateparser_data/cldr_language_data/date_translation_data/fr.json @@ -98,7 +98,8 @@ ], "hour": [ "h", - "heure" + "heure", + "heures" ], "minute": [ "min", @@ -164,14 +165,12 @@ "\\1 hour ago": [ "il y a {0} h", "il y a {0} heure", - "il y a {0} heures", - "il y a {0}h" + "il y a {0} heures" ], "\\1 minute ago": [ "il y a {0} min", "il y a {0} minute", - "il y a {0} minutes", - "il y a {0}min" + "il y a {0} minutes" ], "\\1 month ago": [ "il y a {0} m", @@ -200,8 +199,7 @@ "in \\1 hour": [ "dans {0} h", "dans {0} heure", - "dans {0} heures", - "dans {0}h" + "dans {0} heures" ], "in \\1 minute": [ "dans {0} min", diff --git a/dateparser_data/cldr_language_data/date_translation_data/fur.json b/dateparser_data/cldr_language_data/date_translation_data/fur.json index a65e0736a..c847e71bd 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/fur.json +++ b/dateparser_data/cldr_language_data/date_translation_data/fur.json @@ -94,7 +94,8 @@ "dì" ], "hour": [ - "ore" + "ore", + "oris" ], "minute": [ "minût" diff --git a/dateparser_data/cldr_language_data/date_translation_data/ga.json b/dateparser_data/cldr_language_data/date_translation_data/ga.json index bea9d952c..249c31c6f 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ga.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ga.json @@ -76,10 +76,10 @@ "dé domhnaigh" ], "am": [ - "am" + "rn" ], "pm": [ - "pm" + "in" ], "year": [ "bl", @@ -130,8 +130,8 @@ "an tseachtain seo" ], "0 year ago": [ - "an bhl seo", - "an bhliain seo" + "i mbl", + "i mbliana" ], "1 day ago": [ "inné" @@ -204,7 +204,8 @@ ], "in \\1 month": [ "i gceann {0} mhí", - "i gceann {0} mí" + "i gceann {0} mí", + "i gceann {0} míosa" ], "in \\1 second": [ "i gceann {0} soic", @@ -212,13 +213,18 @@ ], "in \\1 week": [ "i gceann {0} scht", - "i gceann {0} seachtain" + "i gceann {0} seachtain", + "i gceann {0} seachtaine" ], "in \\1 year": [ - "i gceann {0} bhliain", "i gceann {0} bl", - "i gceann {0} bliain" + "i gceann {0} bliain", + "i gceann {0} bliana" ] }, - "locale_specific": {} + "locale_specific": { + "ga-GB": { + "name": "ga-GB" + } + } } \ No newline at end of file diff --git a/dateparser_data/cldr_language_data/date_translation_data/gd.json b/dateparser_data/cldr_language_data/date_translation_data/gd.json index e26903cfd..8f52d418d 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/gd.json +++ b/dateparser_data/cldr_language_data/date_translation_data/gd.json @@ -132,10 +132,14 @@ "an-diugh" ], "0 hour ago": [ - "this hour" + "am broinn uair", + "am broinn uair a thìde", + "san uair" ], "0 minute ago": [ - "this minute" + "am broinn mion", + "am broinn mionaid", + "sa mhion" ], "0 month ago": [ "am mì seo", diff --git a/dateparser_data/cldr_language_data/date_translation_data/gl.json b/dateparser_data/cldr_language_data/date_translation_data/gl.json index d38482e0f..8a3b46b5e 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/gl.json +++ b/dateparser_data/cldr_language_data/date_translation_data/gl.json @@ -81,11 +81,9 @@ "pm" ], "year": [ - "a", "ano" ], "month": [ - "m", "mes" ], "week": [ @@ -93,12 +91,12 @@ "semana" ], "day": [ - "d", "día" ], "hour": [ "h", - "hora" + "hora", + "horas" ], "minute": [ "min", @@ -113,13 +111,12 @@ "hoxe" ], "0 hour ago": [ - "nesta hora" + "esta hora" ], "0 minute ago": [ - "neste minuto" + "este minuto" ], "0 month ago": [ - "este m", "este mes" ], "0 second ago": [ @@ -136,36 +133,37 @@ "onte" ], "1 month ago": [ - "m pasado", + "o mes pas", "o mes pasado" ], "1 week ago": [ - "a semana pasada", - "sem pasada" + "a sem pas", + "a sem pasada", + "a semana pasada" ], "1 year ago": [ - "ano pasado", + "o ano pas", "o ano pasado" ], "in 1 day": [ "mañá" ], "in 1 month": [ - "m seguinte", + "o próx mes", "o próximo mes" ], "in 1 week": [ - "a próxima semana", - "sem seguinte" + "a próx sem", + "a próxima sem", + "a próxima semana" ], "in 1 year": [ - "o próximo ano", - "seguinte ano" + "o próx ano", + "o próximo ano" ] }, "relative-type-regex": { "\\1 day ago": [ - "hai {0} d", "hai {0} día", "hai {0} días" ], @@ -180,7 +178,6 @@ "hai {0} minutos" ], "\\1 month ago": [ - "hai {0} m", "hai {0} mes", "hai {0} meses" ], @@ -195,12 +192,10 @@ "hai {0} semanas" ], "\\1 year ago": [ - "hai {0} a", "hai {0} ano", "hai {0} anos" ], "in \\1 day": [ - "en {0} d", "en {0} día", "en {0} días" ], @@ -215,7 +210,6 @@ "en {0} minutos" ], "in \\1 month": [ - "en {0} m", "en {0} mes", "en {0} meses" ], @@ -230,7 +224,6 @@ "en {0} semanas" ], "in \\1 year": [ - "en {0} a", "en {0} ano", "en {0} anos" ] diff --git a/dateparser_data/cldr_language_data/date_translation_data/gsw.json b/dateparser_data/cldr_language_data/date_translation_data/gsw.json index 7d57904c5..d2ed95874 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/gsw.json +++ b/dateparser_data/cldr_language_data/date_translation_data/gsw.json @@ -99,6 +99,7 @@ "tag" ], "hour": [ + "hr", "schtund" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/gu.json b/dateparser_data/cldr_language_data/date_translation_data/gu.json index c08747a36..04c9d6284 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/gu.json +++ b/dateparser_data/cldr_language_data/date_translation_data/gu.json @@ -172,7 +172,6 @@ "{0} અઠવાડિયા પહેલાં" ], "\\1 year ago": [ - "{0} વર્ષ પહેલા", "{0} વર્ષ પહેલાં" ], "in \\1 day": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/guz.json b/dateparser_data/cldr_language_data/date_translation_data/guz.json index 576390b5d..2ec82c64b 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/guz.json +++ b/dateparser_data/cldr_language_data/date_translation_data/guz.json @@ -97,7 +97,8 @@ "rituko" ], "hour": [ - "ensa" + "ensa", + "hr" ], "minute": [ "edakika" diff --git a/dateparser_data/cldr_language_data/date_translation_data/gv.json b/dateparser_data/cldr_language_data/date_translation_data/gv.json index d2764794f..644619445 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/gv.json +++ b/dateparser_data/cldr_language_data/date_translation_data/gv.json @@ -93,7 +93,8 @@ "day" ], "hour": [ - "hour" + "hour", + "hr" ], "minute": [ "minute" diff --git a/dateparser_data/cldr_language_data/date_translation_data/ha.json b/dateparser_data/cldr_language_data/date_translation_data/ha.json index 19a5140fe..2f30883f6 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ha.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ha.json @@ -78,10 +78,12 @@ "lahadi" ], "am": [ - "am" + "safiya", + "sf" ], "pm": [ - "pm" + "yamma", + "ym" ], "year": [ "shekara" @@ -96,7 +98,8 @@ "kwana" ], "hour": [ - "awa" + "awa", + "sa'o'i" ], "minute": [ "minti" @@ -109,46 +112,98 @@ "yau" ], "0 hour ago": [ - "this hour" + "wannan awa" ], "0 minute ago": [ - "this minute" + "wannan mintin" ], "0 month ago": [ - "this month" + "wannan watan" ], "0 second ago": [ - "now" + "yanzu" ], "0 week ago": [ - "this week" + "wannan satin" ], "0 year ago": [ - "this year" + "bana" ], "1 day ago": [ "jiya" ], "1 month ago": [ - "last month" + "watan da ya gabata" ], "1 week ago": [ - "last week" + "satin da ya gabata" ], "1 year ago": [ - "last year" + "bara" ], "in 1 day": [ "gobe" ], "in 1 month": [ - "next month" + "wata na gaba" ], "in 1 week": [ - "next week" + "sati na gaba" ], "in 1 year": [ - "next year" + "badi" + ] + }, + "relative-type-regex": { + "\\1 day ago": [ + "kwanaki da suka gabata {0}", + "rana da ya gabata {0}" + ], + "\\1 hour ago": [ + "{0} awa da ya gabata" + ], + "\\1 minute ago": [ + "{0} minti da ya gabata" + ], + "\\1 month ago": [ + "watan da ya gabata {0}", + "watanni da suka gabata {0}}" + ], + "\\1 second ago": [ + "{0} dakika da ya gabata" + ], + "\\1 week ago": [ + "mako da suka gabata {0}", + "mako da ya gabata {0}", + "makonni da suka gabata {0}" + ], + "\\1 year ago": [ + "shekara da suka gabata {0}" + ], + "in \\1 day": [ + "a cikin kwanaki {0}", + "a cikin rana {0}" + ], + "in \\1 hour": [ + "cikin {0} awa" + ], + "in \\1 minute": [ + "cikin {0} minti" + ], + "in \\1 month": [ + "a cikin watan {0}", + "a cikin watanni {0}" + ], + "in \\1 second": [ + "cikin {0} dakika" + ], + "in \\1 week": [ + "a cikin mako {0}", + "a cikin makonni {0}" + ], + "in \\1 year": [ + "a shekarar {0}", + "a shekaru {0}" ] }, "locale_specific": { diff --git a/dateparser_data/cldr_language_data/date_translation_data/haw.json b/dateparser_data/cldr_language_data/date_translation_data/haw.json index b53dfe76d..6726e9506 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/haw.json +++ b/dateparser_data/cldr_language_data/date_translation_data/haw.json @@ -95,7 +95,8 @@ "day" ], "hour": [ - "hour" + "hour", + "hr" ], "minute": [ "minute" diff --git a/dateparser_data/cldr_language_data/date_translation_data/he.json b/dateparser_data/cldr_language_data/date_translation_data/he.json index 12b9a92d4..0686375f7 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/he.json +++ b/dateparser_data/cldr_language_data/date_translation_data/he.json @@ -74,9 +74,11 @@ "יום ראשון" ], "am": [ + "am", "לפנה״צ" ], "pm": [ + "pm", "אחה״צ" ], "year": [ @@ -96,6 +98,7 @@ ], "hour": [ "שעה", + "שעות", "שע׳" ], "minute": [ @@ -114,7 +117,8 @@ "בשעה זו" ], "0 minute ago": [ - "בדקה זו" + "בדקה זו", + "דקה זו" ], "0 month ago": [ "החודש" @@ -156,7 +160,6 @@ "relative-type-regex": { "\\1 day ago": [ "לפני {0} ימים", - "לפני {0} ימ׳", "לפני יום {0}" ], "\\1 hour ago": [ @@ -184,7 +187,6 @@ ], "in \\1 day": [ "בעוד {0} ימים", - "בעוד {0} ימ׳", "בעוד יום {0}" ], "in \\1 hour": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/hi.json b/dateparser_data/cldr_language_data/date_translation_data/hi.json index 09ef1c048..bbdaf0891 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/hi.json +++ b/dateparser_data/cldr_language_data/date_translation_data/hi.json @@ -74,10 +74,10 @@ "रविवार" ], "am": [ - "पूर्वाह्न" + "am" ], "pm": [ - "अपराह्न" + "pm" ], "year": [ "वर्ष" @@ -92,16 +92,17 @@ "दिन" ], "hour": [ - "घं", - "घंटा" + "घंटा", + "घंटे", + "घं॰" ], "minute": [ - "मि", - "मिनट" + "मिनट", + "मि॰" ], "second": [ - "से", - "सेकंड" + "सेकंड", + "से॰" ], "relative-type": { "0 day ago": [ @@ -123,10 +124,12 @@ "इस सप्ताह" ], "0 year ago": [ - "इस वर्ष" + "इस वर्ष", + "इस साल" ], "1 day ago": [ - "कल" + "कल", + "बीता कल" ], "1 month ago": [ "पिछला माह" @@ -135,9 +138,11 @@ "पिछला सप्ताह" ], "1 year ago": [ - "पिछला वर्ष" + "पिछला वर्ष", + "पिछले साल" ], "in 1 day": [ + "आने वाला कल", "कल" ], "in 1 month": [ @@ -147,7 +152,8 @@ "अगला सप्ताह" ], "in 1 year": [ - "अगला वर्ष" + "अगला वर्ष", + "अगले साल" ] }, "relative-type-regex": { @@ -155,19 +161,19 @@ "{0} दिन पहले" ], "\\1 hour ago": [ - "{0} घं पहले", - "{0} घंटे पहले" + "{0} घंटे पहले", + "{0} घं॰ पहले" ], "\\1 minute ago": [ - "{0} मि पहले", - "{0} मिनट पहले" + "{0} मिनट पहले", + "{0} मि॰ पहले" ], "\\1 month ago": [ "{0} माह पहले" ], "\\1 second ago": [ - "{0} से पहले", - "{0} सेकंड पहले" + "{0} सेकंड पहले", + "{0} से॰ पहले" ], "\\1 week ago": [ "{0} सप्ताह पहले" @@ -179,19 +185,19 @@ "{0} दिन में" ], "in \\1 hour": [ - "{0} घं में", - "{0} घंटे में" + "{0} घंटे में", + "{0} घं॰ में" ], "in \\1 minute": [ - "{0} मि में", - "{0} मिनट में" + "{0} मिनट में", + "{0} मि॰ में" ], "in \\1 month": [ "{0} माह में" ], "in \\1 second": [ - "{0} से में", - "{0} सेकंड में" + "{0} सेकंड में", + "{0} से॰ में" ], "in \\1 week": [ "{0} सप्ताह में" diff --git a/dateparser_data/cldr_language_data/date_translation_data/hr.json b/dateparser_data/cldr_language_data/date_translation_data/hr.json index 150bab092..03981c4c3 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/hr.json +++ b/dateparser_data/cldr_language_data/date_translation_data/hr.json @@ -114,7 +114,8 @@ ], "hour": [ "h", - "sat" + "sat", + "sati" ], "minute": [ "min", diff --git a/dateparser_data/cldr_language_data/date_translation_data/hsb.json b/dateparser_data/cldr_language_data/date_translation_data/hsb.json index cc3f6ea3f..7fec618d4 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/hsb.json +++ b/dateparser_data/cldr_language_data/date_translation_data/hsb.json @@ -90,9 +90,11 @@ "njedźela" ], "am": [ + "dop", "dopołdnja" ], "pm": [ + "pop", "popołdnju" ], "year": [ @@ -114,7 +116,8 @@ "hour": [ "h", "hodź", - "hodźina" + "hodźina", + "hodźiny" ], "minute": [ "m", @@ -128,48 +131,72 @@ ], "relative-type": { "0 day ago": [ + "dźe", + "dźens", "dźensa" ], "0 hour ago": [ - "this hour" + "w tutej hodźinje" ], "0 minute ago": [ - "this minute" + "w tutej mjeńšinje" ], "0 month ago": [ + "tu měsac", + "tut měsac", "tutón měsac" ], "0 second ago": [ - "now" + "nětko" ], "0 week ago": [ + "tu tydźeń", + "tut tydźeń", "tutón tydźeń" ], "0 year ago": [ + "lět", + "lěts", "lětsa" ], "1 day ago": [ + "wč", + "wčer", "wčera" ], "1 month ago": [ + "zaš měsac", + "zašł měsac", "zašły měsac" ], "1 week ago": [ + "zaš tydźeń", + "zašł tydźeń", "zašły tydźeń" ], "1 year ago": [ + "lo", + "lon", "loni" ], "in 1 day": [ + "jut", + "jutř", "jutře" ], "in 1 month": [ + "přich měsac", + "přichodn měsac", "přichodny měsac" ], "in 1 week": [ + "přich tydźeń", + "přichodn tydźeń", "přichodny tydźeń" ], "in 1 year": [ + "klě", + "klět", "klětu" ] }, diff --git a/dateparser_data/cldr_language_data/date_translation_data/hu.json b/dateparser_data/cldr_language_data/date_translation_data/hu.json index 094d547aa..99460888f 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/hu.json +++ b/dateparser_data/cldr_language_data/date_translation_data/hu.json @@ -96,12 +96,15 @@ "nap" ], "hour": [ + "ó", "óra" ], "minute": [ + "p", "perc" ], "second": [ + "mp", "másodperc" ], "relative-type": { @@ -157,21 +160,27 @@ "{0} nappal ezelőtt" ], "\\1 hour ago": [ + "{0} órája", "{0} órával ezelőtt" ], "\\1 minute ago": [ - "{0} perccel ezelőtt" + "{0} perccel ezelőtt", + "{0} perce" ], "\\1 month ago": [ + "{0} hónapja", "{0} hónappal ezelőtt" ], "\\1 second ago": [ + "{0} mperce", "{0} másodperccel ezelőtt" ], "\\1 week ago": [ + "{0} hete", "{0} héttel ezelőtt" ], "\\1 year ago": [ + "{0} éve", "{0} évvel ezelőtt" ], "in \\1 day": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/hy.json b/dateparser_data/cldr_language_data/date_translation_data/hy.json index 0f47ad0c8..19c735ab0 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/hy.json +++ b/dateparser_data/cldr_language_data/date_translation_data/hy.json @@ -90,12 +90,10 @@ "կիրակի" ], "am": [ - "am", - "կա" + "am" ], "pm": [ - "pm", - "կհ" + "pm" ], "year": [ "տ", @@ -114,7 +112,8 @@ ], "hour": [ "ժ", - "ժամ" + "ժամ", + "ժամեր" ], "minute": [ "ր", @@ -138,7 +137,7 @@ "այս ամիս" ], "0 second ago": [ - "այժմ" + "հիմա" ], "0 week ago": [ "այս շաբաթ" @@ -150,7 +149,6 @@ "երեկ" ], "1 month ago": [ - "անցյալ ամիս", "նախորդ ամիս" ], "1 week ago": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/id.json b/dateparser_data/cldr_language_data/date_translation_data/id.json index 120620634..afef324fa 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/id.json +++ b/dateparser_data/cldr_language_data/date_translation_data/id.json @@ -29,7 +29,7 @@ "juli" ], "august": [ - "agt", + "agu", "agustus" ], "september": [ @@ -96,7 +96,8 @@ ], "day": [ "h", - "hari" + "hari", + "hr" ], "hour": [ "j", @@ -120,43 +121,53 @@ "jam ini" ], "0 minute ago": [ - "menit ini" + "menit ini", + "mnt ini" ], "0 month ago": [ + "bln ini", "bulan ini" ], "0 second ago": [ "sekarang" ], "0 week ago": [ + "mgg ini", "minggu ini" ], "0 year ago": [ - "tahun ini" + "tahun ini", + "thn ini" ], "1 day ago": [ "kemarin" ], "1 month ago": [ + "bln lalu", "bulan lalu" ], "1 week ago": [ + "mgg lalu", "minggu lalu" ], "1 year ago": [ - "tahun lalu" + "tahun lalu", + "thn lalu" ], "in 1 day": [ "besok" ], "in 1 month": [ - "bulan berikutnya" + "bln berikutnya", + "bulan depan" ], "in 1 week": [ + "mgg depan", "minggu depan" ], "in 1 year": [ - "tahun depan" + "tahun depan", + "thn depan" ] }, "relative-type-regex": { @@ -193,7 +204,8 @@ "dalam {0} hari" ], "in \\1 hour": [ - "dalam {0} jam" + "dalam {0} jam", + "dlm {0} jam" ], "in \\1 minute": [ "dalam {0} menit", diff --git a/dateparser_data/cldr_language_data/date_translation_data/ig.json b/dateparser_data/cldr_language_data/date_translation_data/ig.json index 540fe8588..e039bd560 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ig.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ig.json @@ -15,7 +15,7 @@ ], "april": [ "epr", - "eprel" + "epreel" ], "may": [ "mee" @@ -73,13 +73,15 @@ "satọdee" ], "sunday": [ - "mbọsị ụka", - "ụka" + "sọn", + "sọndee" ], "am": [ - "am" + "am", + "n'ụtụtụ" ], "pm": [ + "n'abali", "pm" ], "year": [ @@ -95,59 +97,61 @@ "ụbọchị" ], "hour": [ - "elekere" + "elekere", + "hr" ], "minute": [ "nkeji" ], "second": [ - "nkejinta" + "tịm kọm" ], "relative-type": { "0 day ago": [ + "taa", "taata" ], "0 hour ago": [ - "this hour" + "elekere a" ], "0 minute ago": [ - "this minute" + "nkejị a" ], "0 month ago": [ - "this month" + "ọnwa a" ], "0 second ago": [ - "now" + "ụgbụa" ], "0 week ago": [ - "this week" + "izu a" ], "0 year ago": [ - "this year" + "afọ a" ], "1 day ago": [ - "nnyaafụ" + "ụnyaahụ" ], "1 month ago": [ - "last month" + "ọnwa gara aga" ], "1 week ago": [ - "last week" + "izu gara aga" ], "1 year ago": [ - "last year" + "afọ gara aga" ], "in 1 day": [ "echi" ], "in 1 month": [ - "next month" + "ọnwa ọzọ" ], "in 1 week": [ - "next week" + "izu na-esote" ], "in 1 year": [ - "next year" + "afọ ọzọ" ] }, "locale_specific": {} diff --git a/dateparser_data/cldr_language_data/date_translation_data/ii.json b/dateparser_data/cldr_language_data/date_translation_data/ii.json index 3d80342b2..7e25d1ff5 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ii.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ii.json @@ -84,6 +84,7 @@ "ꑍ" ], "hour": [ + "hr", "ꄮꈉ" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/is.json b/dateparser_data/cldr_language_data/date_translation_data/is.json index 1f5815825..fe034da87 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/is.json +++ b/dateparser_data/cldr_language_data/date_translation_data/is.json @@ -94,12 +94,12 @@ "vika" ], "day": [ - "d", "dagur" ], "hour": [ "klst", - "klukkustund" + "klukkustund", + "klukkustundir" ], "minute": [ "mín", @@ -114,10 +114,10 @@ "í dag" ], "0 hour ago": [ - "this hour" + "þessa stundina" ], "0 minute ago": [ - "this minute" + "á þessari mínútu" ], "0 month ago": [ "í þessum mán", diff --git a/dateparser_data/cldr_language_data/date_translation_data/it.json b/dateparser_data/cldr_language_data/date_translation_data/it.json index 7d7524ce5..f44102df4 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/it.json +++ b/dateparser_data/cldr_language_data/date_translation_data/it.json @@ -99,16 +99,15 @@ ], "hour": [ "h", - "ora" + "ora", + "ore" ], "minute": [ - "m", "min", "minuto" ], "second": [ "s", - "sec", "secondo" ], "relative-type": { @@ -128,6 +127,7 @@ "ora" ], "0 week ago": [ + "questa sett", "questa settimana" ], "0 year ago": [ @@ -140,6 +140,7 @@ "mese scorso" ], "1 week ago": [ + "sett scorsa", "settimana scorsa" ], "1 year ago": [ @@ -152,6 +153,7 @@ "mese prossimo" ], "in 1 week": [ + "sett prossima", "settimana prossima" ], "in 1 year": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/ja.json b/dateparser_data/cldr_language_data/date_translation_data/ja.json index 7b8596ff6..76566ef81 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ja.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ja.json @@ -84,7 +84,8 @@ "日" ], "hour": [ - "時" + "時", + "時間" ], "minute": [ "分" @@ -130,13 +131,13 @@ "明日" ], "in 1 month": [ - "翌月" + "来月" ], "in 1 week": [ - "翌週" + "来週" ], "in 1 year": [ - "翌年" + "来年" ] }, "relative-type-regex": { diff --git a/dateparser_data/cldr_language_data/date_translation_data/jgo.json b/dateparser_data/cldr_language_data/date_translation_data/jgo.json index d1a58fc60..e8542cbc0 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/jgo.json +++ b/dateparser_data/cldr_language_data/date_translation_data/jgo.json @@ -77,7 +77,8 @@ "day" ], "hour": [ - "hour" + "hour", + "hr" ], "minute": [ "minute" diff --git a/dateparser_data/cldr_language_data/date_translation_data/jmc.json b/dateparser_data/cldr_language_data/date_translation_data/jmc.json index 97240f49b..3ff3cb380 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/jmc.json +++ b/dateparser_data/cldr_language_data/date_translation_data/jmc.json @@ -95,6 +95,7 @@ "mfiri" ], "hour": [ + "hr", "saa" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/ka.json b/dateparser_data/cldr_language_data/date_translation_data/ka.json index 3a7b4f783..ffdba8c92 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ka.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ka.json @@ -81,8 +81,7 @@ "am" ], "pm": [ - "pm", - "შუადღ შემდეგ" + "pm" ], "year": [ "წ", diff --git a/dateparser_data/cldr_language_data/date_translation_data/kab.json b/dateparser_data/cldr_language_data/date_translation_data/kab.json index 8098f20b3..2964812fa 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/kab.json +++ b/dateparser_data/cldr_language_data/date_translation_data/kab.json @@ -96,6 +96,7 @@ "ass" ], "hour": [ + "hr", "tamert" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/kam.json b/dateparser_data/cldr_language_data/date_translation_data/kam.json index 77dc7515d..dbd084ff8 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/kam.json +++ b/dateparser_data/cldr_language_data/date_translation_data/kam.json @@ -96,6 +96,7 @@ "mũthenya" ], "hour": [ + "hr", "saa" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/kde.json b/dateparser_data/cldr_language_data/date_translation_data/kde.json index eb38ec1a4..8cd05fa05 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/kde.json +++ b/dateparser_data/cldr_language_data/date_translation_data/kde.json @@ -96,6 +96,7 @@ "lihiku" ], "hour": [ + "hr", "saa" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/kea.json b/dateparser_data/cldr_language_data/date_translation_data/kea.json index 5be041a23..9fb61e47f 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/kea.json +++ b/dateparser_data/cldr_language_data/date_translation_data/kea.json @@ -71,7 +71,6 @@ ], "saturday": [ "sab", - "sabadu", "sábadu" ], "sunday": [ @@ -116,16 +115,16 @@ "oji" ], "0 hour ago": [ - "this hour" + "es ora li" ], "0 minute ago": [ - "this minute" + "es minutu li" ], "0 month ago": [ "es mes li" ], "0 second ago": [ - "now" + "agora" ], "0 week ago": [ "es simana li" @@ -146,7 +145,7 @@ "anu pasadu" ], "in 1 day": [ - "manha" + "manhan" ], "in 1 month": [ "prósimu mes" diff --git a/dateparser_data/cldr_language_data/date_translation_data/khq.json b/dateparser_data/cldr_language_data/date_translation_data/khq.json index c1b0c883f..7457f5b58 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/khq.json +++ b/dateparser_data/cldr_language_data/date_translation_data/khq.json @@ -94,7 +94,8 @@ "jaari" ], "hour": [ - "guuru" + "guuru", + "hr" ], "minute": [ "miniti" diff --git a/dateparser_data/cldr_language_data/date_translation_data/ki.json b/dateparser_data/cldr_language_data/date_translation_data/ki.json index df75e61dc..db3d4eb1f 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ki.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ki.json @@ -96,6 +96,7 @@ "mũthenya" ], "hour": [ + "hr", "ithaa" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/kl.json b/dateparser_data/cldr_language_data/date_translation_data/kl.json index 90e80016a..abd37af29 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/kl.json +++ b/dateparser_data/cldr_language_data/date_translation_data/kl.json @@ -3,51 +3,63 @@ "date_order": "YMD", "january": [ "jan", - "januari" + "januaari", + "januaarip" ], "february": [ - "feb", - "februari" + "febr", + "februaari", + "februaarip" ], "march": [ "mar", - "martsi" + "marsi", + "marsip" ], "april": [ "apr", - "aprili" + "apriili", + "apriilip" ], "may": [ - "maj", - "maji" + "maaji", + "maajip", + "maj" ], "june": [ "jun", - "juni" + "juuni", + "juunip" ], "july": [ "jul", - "juli" + "juuli", + "juulip" ], "august": [ - "aug", - "augustusi" + "aggusti", + "aggustip", + "aug" ], "september": [ - "sep", - "septemberi" + "sept", + "septembari", + "septembarip" ], "october": [ "okt", - "oktoberi" + "oktobari", + "oktobarip" ], "november": [ "nov", - "novemberi" + "novembari", + "novembarip" ], "december": [ "dec", - "decemberi" + "decembari", + "decembarip" ], "monday": [ "ata", @@ -74,8 +86,8 @@ "arfininngorneq" ], "sunday": [ - "sab", - "sabaat" + "sap", + "sapaat" ], "am": [ "am" @@ -96,7 +108,8 @@ "day" ], "hour": [ - "hour" + "hour", + "hr" ], "minute": [ "minute" diff --git a/dateparser_data/cldr_language_data/date_translation_data/kln.json b/dateparser_data/cldr_language_data/date_translation_data/kln.json index d62ec4ca1..88433d15f 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/kln.json +++ b/dateparser_data/cldr_language_data/date_translation_data/kln.json @@ -98,6 +98,7 @@ "betut" ], "hour": [ + "hr", "sait" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/km.json b/dateparser_data/cldr_language_data/date_translation_data/km.json index f57e747c2..027602d4b 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/km.json +++ b/dateparser_data/cldr_language_data/date_translation_data/km.json @@ -38,6 +38,7 @@ "ធ្នូ" ], "monday": [ + "ចន្ទ", "ច័ន្ទ" ], "tuesday": [ @@ -47,6 +48,7 @@ "ពុធ" ], "thursday": [ + "ព្រហ", "ព្រហស្បតិ៍" ], "friday": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/kn.json b/dateparser_data/cldr_language_data/date_translation_data/kn.json index 8197f4aee..152ff7501 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/kn.json +++ b/dateparser_data/cldr_language_data/date_translation_data/kn.json @@ -92,7 +92,8 @@ "ದಿನ" ], "hour": [ - "ಗಂಟೆ" + "ಗಂಟೆ", + "ಗಂಟೆಗಳು" ], "minute": [ "ನಿಮಿಷ" diff --git a/dateparser_data/cldr_language_data/date_translation_data/ko.json b/dateparser_data/cldr_language_data/date_translation_data/ko.json index 0aa9a72fb..c786e76d4 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ko.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ko.json @@ -86,7 +86,8 @@ "일" ], "hour": [ - "시" + "시", + "시간" ], "minute": [ "분" @@ -186,6 +187,9 @@ ] }, "locale_specific": { + "ko-CN": { + "name": "ko-CN" + }, "ko-KP": { "name": "ko-KP" } diff --git a/dateparser_data/cldr_language_data/date_translation_data/kok.json b/dateparser_data/cldr_language_data/date_translation_data/kok.json index c9bbfcd99..fa4692b95 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/kok.json +++ b/dateparser_data/cldr_language_data/date_translation_data/kok.json @@ -1,17 +1,20 @@ { "name": "kok", - "date_order": "YMD", + "date_order": "DMY", "january": [ + "जाने", "जानेवारी" ], "february": [ + "फेब्रु", "फेब्रुवारी" ], "march": [ "मार्च" ], "april": [ - "एप्रिल" + "एप्री", + "एप्रील" ], "may": [ "मे" @@ -20,123 +23,172 @@ "जून" ], "july": [ - "जुलै" + "जुल", + "जुलय" ], "august": [ - "ओगस्ट" + "ऑग", + "ऑगस्ट" ], "september": [ - "सेप्टेंबर" + "सप्टें", + "सप्टेंबर" ], "october": [ - "ओक्टोबर" + "ऑक्टो", + "ऑक्टोबर" ], "november": [ + "नो", "नोव्हेंबर" ], "december": [ + "डिसे", "डिसेंबर" ], "monday": [ - "सोम", - "सोमवार" + "सोमार" ], "tuesday": [ - "मंगळ", "मंगळार" ], "wednesday": [ - "बुध", "बुधवार" ], "thursday": [ - "गुरु", - "गुरुवार" + "बिरेस्तार" ], "friday": [ - "शुक्र", - "शुक्रवार" + "शुक्रार" ], "saturday": [ - "शनि", - "शनिवार" + "शेनवार" ], "sunday": [ - "आदित्यवार", - "रवि" + "आयतार" ], "am": [ - "मपू" + "am", + "सकाळ" ], "pm": [ - "मनं" + "pm", + "सांज" ], "year": [ - "year" + "वर्स" ], "month": [ - "month" + "म्हयनो" ], "week": [ - "week" + "सप्तक" ], "day": [ - "day" + "दीस" ], "hour": [ - "hour" + "वर", + "वरां" ], "minute": [ - "minute" + "मिनीट" ], "second": [ - "second" + "सेकंद" ], "relative-type": { "0 day ago": [ - "today" + "आयज" ], "0 hour ago": [ - "this hour" + "हें वर" ], "0 minute ago": [ - "this minute" + "हें मिनीट" ], "0 month ago": [ - "this month" + "हो म्हयनो" ], "0 second ago": [ - "now" + "आतां" ], "0 week ago": [ - "this week" + "हो सप्तक" ], "0 year ago": [ - "this year" + "हें वर्स" ], "1 day ago": [ - "yesterday" + "काल" ], "1 month ago": [ - "last month" + "फाटलो म्हयनो" ], "1 week ago": [ - "last week" + "निमाणो सप्तक" ], "1 year ago": [ - "last year" + "फाटलें वर्स" ], "in 1 day": [ - "tomorrow" + "फाल्यां" ], "in 1 month": [ - "next month" + "फुडलो म्हयनो" ], "in 1 week": [ - "next week" + "फुडलो सप्तक" ], "in 1 year": [ - "next year" + "फुडलें वर्स" + ] + }, + "relative-type-regex": { + "\\1 day ago": [ + "{0} दीस आदीं" + ], + "\\1 hour ago": [ + "{0} वरा आदीं" + ], + "\\1 minute ago": [ + "{0} मिन्टां आदीं" + ], + "\\1 month ago": [ + "{0} म्हयन्यां आदीं" + ], + "\\1 second ago": [ + "{0} से आदीं", + "{0} सेकंद आदीं" + ], + "\\1 week ago": [ + "{0} सप्त आदीं", + "{0} सप्तकां आदीं" + ], + "\\1 year ago": [ + "{0} वर्स आदीं", + "{0} वर्सां आदीं" + ], + "in \\1 day": [ + "{0} दिसानीं" + ], + "in \\1 hour": [ + "{0} वरांनीं" + ], + "in \\1 minute": [ + "{0} मिन्टां" + ], + "in \\1 month": [ + "{0} म्हयन्यानीं" + ], + "in \\1 second": [ + "{0} सेकंदानीं" + ], + "in \\1 week": [ + "{0} सप्तकांनीं" + ], + "in \\1 year": [ + "{0} वर्सांनीं" ] }, "locale_specific": {} diff --git a/dateparser_data/cldr_language_data/date_translation_data/ks.json b/dateparser_data/cldr_language_data/date_translation_data/ks.json index 2452fdeea..83373ee43 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ks.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ks.json @@ -14,13 +14,14 @@ "اپریل" ], "may": [ - "میٔ" + "مئی" ], "june": [ "جوٗن" ], "july": [ - "جوٗلایی" + "جوٗلایی", + "جُلَے" ], "august": [ "اگست" @@ -35,20 +36,21 @@ "نومبر" ], "december": [ - "دسمبر" + "دسمبر", + "دَسَمبَر" ], "monday": [ - "ژٔنٛدرٕروار", - "ژٔنٛدٕروار" + "ژٔندرٕروار", + "ژٔندٕروار" ], "tuesday": [ - "بوٚموار" + "بۆموار" ], "wednesday": [ "بودوار" ], "thursday": [ - "برٛٮ۪سوار" + "برؠسوار" ], "friday": [ "جُمہ" @@ -61,16 +63,18 @@ "اَتھوار" ], "am": [ - "am" + "am", + "اے ایم" ], "pm": [ - "pm" + "pm", + "پی ایم" ], "year": [ "ؤری" ], "month": [ - "رٮ۪تھ" + "رؠتھ" ], "week": [ "ہفتہٕ" @@ -79,13 +83,14 @@ "دۄہ" ], "hour": [ - "گٲنٛٹہٕ" + "hr", + "گٲنٹہٕ" ], "minute": [ "مِنَٹ" ], "second": [ - "سٮ۪کَنڑ" + "سؠکَنڈ" ], "relative-type": { "0 day ago": [ @@ -98,40 +103,40 @@ "this minute" ], "0 month ago": [ - "this month" + "یٕہ ریتھۍ" ], "0 second ago": [ "now" ], "0 week ago": [ - "this week" + "یٕہ ہفتہ" ], "0 year ago": [ - "this year" + "یٕہ ؤری" ], "1 day ago": [ "راتھ" ], "1 month ago": [ - "last month" + "پٔتِم ریتھۍ" ], "1 week ago": [ - "last week" + "پٔتِم ہفتہ" ], "1 year ago": [ - "last year" + "پٔتِم ؤری" ], "in 1 day": [ "پگاہ" ], "in 1 month": [ - "next month" + "نو ریتھۍ" ], "in 1 week": [ - "next week" + "نو ہفتہ" ], "in 1 year": [ - "next year" + "نو ؤری" ] }, "locale_specific": {} diff --git a/dateparser_data/cldr_language_data/date_translation_data/ksb.json b/dateparser_data/cldr_language_data/date_translation_data/ksb.json index 463811890..8bf838594 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ksb.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ksb.json @@ -95,6 +95,7 @@ "siku" ], "hour": [ + "hr", "saa" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/ksf.json b/dateparser_data/cldr_language_data/date_translation_data/ksf.json index 21eec6922..d07c4c33a 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ksf.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ksf.json @@ -96,7 +96,8 @@ "ŋwós" ], "hour": [ - "cámɛɛn" + "cámɛɛn", + "hr" ], "minute": [ "mǝnít" diff --git a/dateparser_data/cldr_language_data/date_translation_data/ksh.json b/dateparser_data/cldr_language_data/date_translation_data/ksh.json index ad9d7c509..18bc30aba 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ksh.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ksh.json @@ -105,6 +105,7 @@ "hour": [ "s", "schtund", + "schtunde", "std" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/kw.json b/dateparser_data/cldr_language_data/date_translation_data/kw.json index 2c2038b1c..e671e8738 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/kw.json +++ b/dateparser_data/cldr_language_data/date_translation_data/kw.json @@ -96,7 +96,8 @@ "day" ], "hour": [ - "hour" + "hour", + "hr" ], "minute": [ "minute" diff --git a/dateparser_data/cldr_language_data/date_translation_data/ky.json b/dateparser_data/cldr_language_data/date_translation_data/ky.json index b74d3287c..b8df5edb6 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ky.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ky.json @@ -147,7 +147,7 @@ "былтыр" ], "in 1 day": [ - "эртеӊ" + "эртең" ], "in 1 month": [ "эмдиги айда" diff --git a/dateparser_data/cldr_language_data/date_translation_data/lag.json b/dateparser_data/cldr_language_data/date_translation_data/lag.json index 3cfeddc6c..f6bb5e81c 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/lag.json +++ b/dateparser_data/cldr_language_data/date_translation_data/lag.json @@ -96,6 +96,7 @@ "sikʉ" ], "hour": [ + "hr", "sáa" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/lb.json b/dateparser_data/cldr_language_data/date_translation_data/lb.json index c8385fc12..d3798c988 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/lb.json +++ b/dateparser_data/cldr_language_data/date_translation_data/lb.json @@ -100,7 +100,8 @@ ], "hour": [ "st", - "stonn" + "stonn", + "stonnen" ], "minute": [ "min", diff --git a/dateparser_data/cldr_language_data/date_translation_data/lg.json b/dateparser_data/cldr_language_data/date_translation_data/lg.json index 3ee5fc230..df2c022b3 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/lg.json +++ b/dateparser_data/cldr_language_data/date_translation_data/lg.json @@ -96,6 +96,7 @@ "lunaku" ], "hour": [ + "hr", "saawa" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/lkt.json b/dateparser_data/cldr_language_data/date_translation_data/lkt.json index 74707657c..e70d94c86 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/lkt.json +++ b/dateparser_data/cldr_language_data/date_translation_data/lkt.json @@ -1,6 +1,6 @@ { "name": "lkt", - "date_order": "YMD", + "date_order": "MDY", "january": [ "wiótheȟika wí" ], @@ -77,6 +77,7 @@ "aŋpétu" ], "hour": [ + "hr", "owápȟe" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/ln.json b/dateparser_data/cldr_language_data/date_translation_data/ln.json index 7e6321da6..66bd8665e 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ln.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ln.json @@ -96,6 +96,7 @@ "mokɔlɔ" ], "hour": [ + "hr", "ngonga" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/lo.json b/dateparser_data/cldr_language_data/date_translation_data/lo.json index 113c3931a..bb2e285cb 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/lo.json +++ b/dateparser_data/cldr_language_data/date_translation_data/lo.json @@ -191,8 +191,8 @@ "ໃນອີກ {0} ຊົ່ວໂມງ" ], "in \\1 minute": [ - "{0} ໃນອີກ 0 ນາທີ", - "ໃນ {0} ນທ" + "ໃນ {0} ນທ", + "ໃນອີກ {0} ນາທີ" ], "in \\1 month": [ "ໃນອີກ {0} ດ", diff --git a/dateparser_data/cldr_language_data/date_translation_data/lrc.json b/dateparser_data/cldr_language_data/date_translation_data/lrc.json index 2c20cf10e..ad8346d7d 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/lrc.json +++ b/dateparser_data/cldr_language_data/date_translation_data/lrc.json @@ -77,6 +77,7 @@ "روٙز" ], "hour": [ + "hr", "ساأت" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/lt.json b/dateparser_data/cldr_language_data/date_translation_data/lt.json index 8981948c7..9b397dba9 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/lt.json +++ b/dateparser_data/cldr_language_data/date_translation_data/lt.json @@ -114,7 +114,8 @@ "hour": [ "h", "val", - "valanda" + "valanda", + "valandos" ], "minute": [ "min", diff --git a/dateparser_data/cldr_language_data/date_translation_data/lu.json b/dateparser_data/cldr_language_data/date_translation_data/lu.json index 88c33d7e4..8705a76b7 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/lu.json +++ b/dateparser_data/cldr_language_data/date_translation_data/lu.json @@ -96,7 +96,8 @@ "dituku" ], "hour": [ - "diba" + "diba", + "hr" ], "minute": [ "kasunsu" diff --git a/dateparser_data/cldr_language_data/date_translation_data/luo.json b/dateparser_data/cldr_language_data/date_translation_data/luo.json index 6834a4af1..3f051df39 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/luo.json +++ b/dateparser_data/cldr_language_data/date_translation_data/luo.json @@ -96,6 +96,7 @@ "chieng'" ], "hour": [ + "hr", "saa" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/luy.json b/dateparser_data/cldr_language_data/date_translation_data/luy.json index dddfb7506..00bfce102 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/luy.json +++ b/dateparser_data/cldr_language_data/date_translation_data/luy.json @@ -95,6 +95,7 @@ "ridiku" ], "hour": [ + "hr", "isaa" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/lv.json b/dateparser_data/cldr_language_data/date_translation_data/lv.json index f768fb4fb..7e038300f 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/lv.json +++ b/dateparser_data/cldr_language_data/date_translation_data/lv.json @@ -127,39 +127,48 @@ "šajā minūtē" ], "0 month ago": [ + "šajā mēn", "šajā mēnesī" ], "0 second ago": [ "tagad" ], "0 week ago": [ + "šajā ned", "šajā nedēļā" ], "0 year ago": [ + "šajā g", "šajā gadā" ], "1 day ago": [ "vakar" ], "1 month ago": [ + "pag mēn", "pagājušajā mēnesī" ], "1 week ago": [ + "pag ned", "pagājušajā nedēļā" ], "1 year ago": [ + "pag gadā", "pagājušajā gadā" ], "in 1 day": [ "rīt" ], "in 1 month": [ + "nāk mēn", "nākamajā mēnesī" ], "in 1 week": [ + "nāk ned", "nākamajā nedēļā" ], "in 1 year": [ + "nāk gadā", "nākamajā gadā" ] }, diff --git a/dateparser_data/cldr_language_data/date_translation_data/mas.json b/dateparser_data/cldr_language_data/date_translation_data/mas.json index 38ac9cda8..a795bd07d 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/mas.json +++ b/dateparser_data/cldr_language_data/date_translation_data/mas.json @@ -96,6 +96,7 @@ "ɛnkɔlɔ́ŋ" ], "hour": [ + "hr", "ɛ́sáâ" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/mer.json b/dateparser_data/cldr_language_data/date_translation_data/mer.json index 52158fb38..65e0e5602 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/mer.json +++ b/dateparser_data/cldr_language_data/date_translation_data/mer.json @@ -95,6 +95,7 @@ "ntukũ" ], "hour": [ + "hr", "ĩthaa" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/mfe.json b/dateparser_data/cldr_language_data/date_translation_data/mfe.json index d77abaf84..a3bcc1b3c 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/mfe.json +++ b/dateparser_data/cldr_language_data/date_translation_data/mfe.json @@ -93,6 +93,7 @@ "zour" ], "hour": [ + "hr", "ler" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/mg.json b/dateparser_data/cldr_language_data/date_translation_data/mg.json index 36d8a84a3..20857e892 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/mg.json +++ b/dateparser_data/cldr_language_data/date_translation_data/mg.json @@ -95,6 +95,7 @@ "andro" ], "hour": [ + "hr", "ora" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/mgh.json b/dateparser_data/cldr_language_data/date_translation_data/mgh.json index 4dd179be5..8ef7c5167 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/mgh.json +++ b/dateparser_data/cldr_language_data/date_translation_data/mgh.json @@ -96,6 +96,7 @@ "nihuku" ], "hour": [ + "hr", "isaa" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/mgo.json b/dateparser_data/cldr_language_data/date_translation_data/mgo.json index a13337522..b3c32da77 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/mgo.json +++ b/dateparser_data/cldr_language_data/date_translation_data/mgo.json @@ -78,7 +78,8 @@ "anəg" ], "hour": [ - "hour" + "hour", + "hr" ], "minute": [ "minute" diff --git a/dateparser_data/cldr_language_data/date_translation_data/mk.json b/dateparser_data/cldr_language_data/date_translation_data/mk.json index ecabcd0c0..2c36202c4 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/mk.json +++ b/dateparser_data/cldr_language_data/date_translation_data/mk.json @@ -33,7 +33,7 @@ "август" ], "september": [ - "септ", + "сеп", "септември" ], "october": [ @@ -41,7 +41,7 @@ "октомври" ], "november": [ - "ноем", + "ное", "ноември" ], "december": [ @@ -53,7 +53,6 @@ "понеделник" ], "tuesday": [ - "вт", "вто", "вторник" ], @@ -78,12 +77,10 @@ "недела" ], "am": [ - "претпл", - "претпладне" + "претпл" ], "pm": [ - "попл", - "попладне" + "попл" ], "year": [ "год", @@ -94,14 +91,16 @@ "месец" ], "week": [ - "недела", - "сед" + "сед", + "седмица" ], "day": [ "ден" ], "hour": [ - "час" + "ч", + "час", + "часа" ], "minute": [ "мин", @@ -131,6 +130,7 @@ "оваа седмица" ], "0 year ago": [ + "оваа год", "оваа година" ], "1 day ago": [ @@ -143,7 +143,8 @@ "минатата седмица" ], "1 year ago": [ - "минатата година" + "лани", + "минатата год" ], "in 1 day": [ "утре" @@ -155,7 +156,8 @@ "следната седмица" ], "in 1 year": [ - "следната година" + "догодина", + "следната год" ] }, "relative-type-regex": { @@ -168,6 +170,7 @@ "пред {0} часа" ], "\\1 minute ago": [ + "пред {0} мин", "пред {0} минута", "пред {0} минути" ], @@ -176,6 +179,7 @@ "пред {0} месеци" ], "\\1 second ago": [ + "пред {0} сек", "пред {0} секунда", "пред {0} секунди" ], @@ -184,6 +188,7 @@ "пред {0} седмици" ], "\\1 year ago": [ + "пред {0} год", "пред {0} година", "пред {0} години" ], @@ -196,6 +201,7 @@ "за {0} часа" ], "in \\1 minute": [ + "за {0} мин", "за {0} минута", "за {0} минути" ], @@ -204,6 +210,7 @@ "за {0} месеци" ], "in \\1 second": [ + "за {0} сек", "за {0} секунда", "за {0} секунди" ], @@ -212,6 +219,7 @@ "за {0} седмици" ], "in \\1 year": [ + "за {0} год", "за {0} година", "за {0} години" ] diff --git a/dateparser_data/cldr_language_data/date_translation_data/mn.json b/dateparser_data/cldr_language_data/date_translation_data/mn.json index 1ec4c969e..a1a89dfe1 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/mn.json +++ b/dateparser_data/cldr_language_data/date_translation_data/mn.json @@ -23,11 +23,11 @@ ], "june": [ "6-р сар", - "зургадугаар сар" + "зургаадугаар сар" ], "july": [ "7-р сар", - "долдугаар сар" + "долоодугаар сар" ], "august": [ "8-р сар", @@ -90,7 +90,7 @@ "сар" ], "week": [ - "7х", + "7 хоног", "долоо хоног" ], "day": [ @@ -125,6 +125,7 @@ "одоо" ], "0 week ago": [ + "энэ 7 хоног", "энэ долоо хоног" ], "0 year ago": [ @@ -137,6 +138,7 @@ "өнгөрсөн сар" ], "1 week ago": [ + "өнгөрсөн 7 хоног", "өнгөрсөн долоо хоног" ], "1 year ago": [ @@ -149,6 +151,7 @@ "ирэх сар" ], "in 1 week": [ + "ирэх 7 хоног", "ирэх долоо хоног" ], "in 1 year": [ @@ -175,14 +178,14 @@ "{0} секундын өмнө" ], "\\1 week ago": [ - "{0} 7х-ийн өмнө" + "{0} 7 хоногийн өмнө", + "{0} долоо хоногийн өмнө" ], "\\1 year ago": [ "{0} жилийн өмнө" ], "in \\1 day": [ - "{0} өдрийн дараа", - "{0} өдөрт" + "{0} өдрийн дараа" ], "in \\1 hour": [ "{0} ц дараа", @@ -200,7 +203,8 @@ "{0} секундын дараа" ], "in \\1 week": [ - "{0} 7х-ийн дараа" + "{0} 7 хоногийн дараа", + "{0} долоо хоногийн дараа" ], "in \\1 year": [ "{0} жилийн дараа" diff --git a/dateparser_data/cldr_language_data/date_translation_data/mr.json b/dateparser_data/cldr_language_data/date_translation_data/mr.json index 6b9cba56f..956c6ec8b 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/mr.json +++ b/dateparser_data/cldr_language_data/date_translation_data/mr.json @@ -74,24 +74,28 @@ "रविवार" ], "am": [ - "मपू" + "am" ], "pm": [ - "मउ" + "pm" ], "year": [ "वर्ष" ], "month": [ + "म", "महिना" ], "week": [ + "आठ", "आठवडा" ], "day": [ + "दि", "दिवस" ], "hour": [ + "ता", "तास" ], "minute": [ @@ -182,11 +186,15 @@ ], "in \\1 day": [ "{0} दिवसांमध्ये", - "{0} दिवसामध्ये" + "{0} दिवसामध्ये", + "येत्या {0} दिवसांमध्ये", + "येत्या {0} दिवसामध्ये" ], "in \\1 hour": [ "{0} तासांमध्ये", - "{0} तासामध्ये" + "{0} तासामध्ये", + "येत्या {0} तासांमध्ये", + "येत्या {0} तासामध्ये" ], "in \\1 minute": [ "{0} मिनि मध्ये", @@ -195,20 +203,27 @@ ], "in \\1 month": [ "{0} महिन्यांमध्ये", - "{0} महिन्यामध्ये" + "{0} महिन्यामध्ये", + "येत्या {0} महिन्यांमध्ये", + "येत्या {0} महिन्यामध्ये" ], "in \\1 second": [ "{0} से मध्ये", "{0} सेकंदांमध्ये", - "{0} सेकंदामध्ये" + "{0} सेकंदामध्ये", + "येत्या {0} से मध्ये" ], "in \\1 week": [ "{0} आठवड्यांमध्ये", - "{0} आठवड्यामध्ये" + "{0} आठवड्यामध्ये", + "येत्या {0} आठवड्यांमध्ये", + "येत्या {0} आठवड्यामध्ये" ], "in \\1 year": [ "{0} वर्षांमध्ये", - "{0} वर्षामध्ये" + "{0} वर्षामध्ये", + "येत्या {0} वर्षांमध्ये", + "येत्या {0} वर्षामध्ये" ] }, "locale_specific": {} diff --git a/dateparser_data/cldr_language_data/date_translation_data/ms.json b/dateparser_data/cldr_language_data/date_translation_data/ms.json index 3de154dd6..c7e63b73c 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ms.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ms.json @@ -123,8 +123,8 @@ "sekarang" ], "0 week ago": [ - "minggu ini", - "mng ini" + "mgu ini", + "minggu ini" ], "0 year ago": [ "tahun ini", @@ -139,8 +139,8 @@ "bulan lalu" ], "1 week ago": [ - "minggu lalu", - "mng lepas" + "mgu lepas", + "minggu lalu" ], "1 year ago": [ "tahun lalu", @@ -154,8 +154,8 @@ "bulan depan" ], "in 1 week": [ - "minggu depan", - "mng depan" + "mgu depan", + "minggu depan" ], "in 1 year": [ "tahun depan", @@ -213,7 +213,7 @@ "dlm {0} mgu" ], "in \\1 year": [ - "dalam {0} saat", + "dalam {0} tahun", "dalam {0} thn" ] }, @@ -221,6 +221,9 @@ "ms-BN": { "name": "ms-BN" }, + "ms-ID": { + "name": "ms-ID" + }, "ms-SG": { "name": "ms-SG" } diff --git a/dateparser_data/cldr_language_data/date_translation_data/mt.json b/dateparser_data/cldr_language_data/date_translation_data/mt.json index 2b31830c8..85e5ee439 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/mt.json +++ b/dateparser_data/cldr_language_data/date_translation_data/mt.json @@ -84,24 +84,31 @@ "pm" ], "year": [ - "sena" + "sena", + "sn" ], "month": [ "xahar" ], "week": [ - "ġimgħa" + "ġimgħa", + "ġm" ], "day": [ "jum" ], "hour": [ + "hr", "siegħa" ], "minute": [ + "m", + "min", "minuta" ], "second": [ + "s", + "sek", "sekonda" ], "relative-type": { @@ -109,16 +116,16 @@ "illum" ], "0 hour ago": [ - "this hour" + "din is-siegħa" ], "0 minute ago": [ - "this minute" + "din il-minuta" ], "0 month ago": [ "dan ix-xahar" ], "0 second ago": [ - "now" + "issa" ], "0 week ago": [ "din il-ġimgħa" @@ -127,7 +134,7 @@ "din is-sena" ], "1 day ago": [ - "ilbieraħ" + "lbieraħ" ], "1 month ago": [ "ix-xahar li għadda" @@ -136,7 +143,7 @@ "il-ġimgħa li għaddiet" ], "1 year ago": [ - "is-sena li għaddiet" + "is-sena l-oħra" ], "in 1 day": [ "għada" @@ -152,9 +159,52 @@ ] }, "relative-type-regex": { + "\\1 day ago": [ + "{0} ġurnata ilu" + ], + "\\1 hour ago": [ + "{0} siegħa ilu" + ], + "\\1 minute ago": [ + "{0} min ilu", + "{0} minuta ilu" + ], + "\\1 month ago": [ + "{0} xahar ilu" + ], + "\\1 second ago": [ + "{0} sek ilu", + "{0} sekonda ilu" + ], + "\\1 week ago": [ + "{0} ġimgħa ilu" + ], "\\1 year ago": [ - "{0} sena ilu", - "{0} snin ilu" + "{0} sena ilu" + ], + "in \\1 day": [ + "fi żmien {0} ġurnata oħra" + ], + "in \\1 hour": [ + "fi żmien {0} siegħa" + ], + "in \\1 minute": [ + "sa {0} min oħra", + "sa {0} minuta oħra" + ], + "in \\1 month": [ + "fi {0} xahar oħra", + "sa {0} xahar oħra" + ], + "in \\1 second": [ + "sa {0} sek oħra", + "sa {0} sekonda oħra" + ], + "in \\1 week": [ + "sa {0} ġimgħa oħra" + ], + "in \\1 year": [ + "fi żmien {0} sena oħra" ] }, "locale_specific": {} diff --git a/dateparser_data/cldr_language_data/date_translation_data/mua.json b/dateparser_data/cldr_language_data/date_translation_data/mua.json index cd38efd39..b993730e0 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/mua.json +++ b/dateparser_data/cldr_language_data/date_translation_data/mua.json @@ -96,7 +96,8 @@ "zah'nane/ comme" ], "hour": [ - "cok comme" + "cok comme", + "hr" ], "minute": [ "cok comme ma laŋne" diff --git a/dateparser_data/cldr_language_data/date_translation_data/naq.json b/dateparser_data/cldr_language_data/date_translation_data/naq.json index fb7235fc4..e29213842 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/naq.json +++ b/dateparser_data/cldr_language_data/date_translation_data/naq.json @@ -96,6 +96,7 @@ "tsees" ], "hour": [ + "hr", "iiri" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/nb.json b/dateparser_data/cldr_language_data/date_translation_data/nb.json index 0cc2aeaca..b782c52f4 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/nb.json +++ b/dateparser_data/cldr_language_data/date_translation_data/nb.json @@ -100,7 +100,8 @@ ], "hour": [ "t", - "time" + "time", + "timer" ], "minute": [ "m", @@ -193,8 +194,7 @@ "for {0} uker siden" ], "\\1 year ago": [ - "for {0} år siden", - "–{0} år" + "for {0} år siden" ], "in \\1 day": [ "om {0} d", diff --git a/dateparser_data/cldr_language_data/date_translation_data/nd.json b/dateparser_data/cldr_language_data/date_translation_data/nd.json index 52d196951..02e7bac1b 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/nd.json +++ b/dateparser_data/cldr_language_data/date_translation_data/nd.json @@ -96,6 +96,7 @@ "ilanga" ], "hour": [ + "hr", "ihola" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/ne.json b/dateparser_data/cldr_language_data/date_translation_data/ne.json index 68757c5a8..402c83d69 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ne.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ne.json @@ -14,7 +14,6 @@ "अप्रिल" ], "may": [ - "मई", "मे" ], "june": [ @@ -73,7 +72,6 @@ "अपराह्न" ], "year": [ - "बर्ष", "वर्ष" ], "month": [ @@ -99,7 +97,7 @@ "आज" ], "0 hour ago": [ - "यो घडीमा" + "यस घडीमा" ], "0 minute ago": [ "यही मिनेटमा" @@ -108,7 +106,7 @@ "यो महिना" ], "0 second ago": [ - "अब" + "अहिले" ], "0 week ago": [ "यो हप्ता" @@ -132,13 +130,14 @@ "भोलि" ], "in 1 month": [ - "अर्को महिना" + "अर्को महिना", + "आगामी महिना" ], "in 1 week": [ - "आउने हप्ता" + "आगामी हप्ता" ], "in 1 year": [ - "अर्को वर्ष" + "आगामी वर्ष" ] }, "relative-type-regex": { @@ -155,7 +154,7 @@ "{0} महिना पहिले" ], "\\1 second ago": [ - "{0} सेकेण्ड पहिले" + "{0} सेकेन्ड पहिले" ], "\\1 week ago": [ "{0} हप्ता पहिले" @@ -176,7 +175,7 @@ "{0} महिनामा" ], "in \\1 second": [ - "{0} सेकेण्डमा" + "{0} सेकेन्डमा" ], "in \\1 week": [ "{0} हप्तामा" diff --git a/dateparser_data/cldr_language_data/date_translation_data/nl.json b/dateparser_data/cldr_language_data/date_translation_data/nl.json index effe53b6f..bbfd1b614 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/nl.json +++ b/dateparser_data/cldr_language_data/date_translation_data/nl.json @@ -98,6 +98,7 @@ "dag" ], "hour": [ + "u", "uur" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/nmg.json b/dateparser_data/cldr_language_data/date_translation_data/nmg.json index 47a6b722f..8749959ad 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/nmg.json +++ b/dateparser_data/cldr_language_data/date_translation_data/nmg.json @@ -96,6 +96,7 @@ "duö" ], "hour": [ + "hr", "wulā" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/nn.json b/dateparser_data/cldr_language_data/date_translation_data/nn.json index d0dda1795..e801e0fc3 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/nn.json +++ b/dateparser_data/cldr_language_data/date_translation_data/nn.json @@ -84,32 +84,39 @@ "søndag" ], "am": [ - "fm", - "formiddag" + "fm" ], "pm": [ - "em", - "ettermiddag" + "em" ], "year": [ "år" ], "month": [ + "md", "månad" ], "week": [ + "v", "veke" ], "day": [ + "d", "dag" ], "hour": [ + "t", + "timar", "time" ], "minute": [ + "m", + "min", "minutt" ], "second": [ + "s", + "sek", "sekund" ], "relative-type": { @@ -117,97 +124,114 @@ "i dag" ], "0 hour ago": [ - "this hour" + "denne timen" ], "0 minute ago": [ - "this minute" + "dette minuttet" ], "0 month ago": [ - "this month" + "denne md", + "denne månaden" ], "0 second ago": [ - "now" + "no" ], "0 week ago": [ - "this week" + "denne veka" ], "0 year ago": [ - "this year" + "i år" ], "1 day ago": [ "i går" ], "1 month ago": [ - "last month" + "førre md", + "førre månad" ], "1 week ago": [ - "last week" + "førre veke" ], "1 year ago": [ - "last year" + "i fjor" ], "in 1 day": [ "i morgon" ], "in 1 month": [ - "next month" + "neste md", + "neste månad" ], "in 1 week": [ - "next week" + "neste veke" ], "in 1 year": [ - "next year" + "neste år" ] }, "relative-type-regex": { "\\1 day ago": [ - "for {0} døgn siden" + "for {0} d sidan", + "for {0} døgn sidan", + "–{0} d" ], "\\1 hour ago": [ - "for {0} time siden", - "for {0} timer siden" + "for {0} t sidan", + "for {0} timar sidan", + "for {0} time sidan", + "–{0} t" ], "\\1 minute ago": [ - "for {0} minutt siden", - "for {0} minutter siden" + "for {0} min sidan", + "for {0} minutt sidan", + "–{0} min" ], "\\1 month ago": [ - "for {0} måned siden", - "for {0} måneder siden" + "for {0} md sidan", + "for {0} månad sidan", + "for {0} månadar sidan", + "–{0} md" ], "\\1 second ago": [ - "for {0} sekund siden", - "for {0} sekunder siden" + "for {0} sek sidan", + "for {0} sekund sidan", + "–{0} s" ], "\\1 week ago": [ - "for {0} uke siden", - "for {0} uker siden" + "for {0} v sidan", + "for {0} veke sidan", + "for {0} veker sidan", + "–{0} v" ], "\\1 year ago": [ - "for {0} år siden" + "for {0} år sidan" ], "in \\1 day": [ + "om {0} d", "om {0} døgn" ], "in \\1 hour": [ - "om {0} time", - "om {0} timer" + "om {0} t", + "om {0} timar", + "om {0} time" ], "in \\1 minute": [ - "om {0} minutt", - "om {0} minutter" + "om {0} min", + "om {0} minutt" ], "in \\1 month": [ - "om {0} måned", - "om {0} måneder" + "om {0} md", + "om {0} månad", + "om {0} månadar" ], "in \\1 second": [ - "om {0} sekund", - "om {0} sekunder" + "om {0} sek", + "om {0} sekund" ], "in \\1 week": [ - "om {0} uke", - "om {0} uker" + "om {0} v", + "om {0} veke", + "om {0} veker" ], "in \\1 year": [ "om {0} år" diff --git a/dateparser_data/cldr_language_data/date_translation_data/nnh.json b/dateparser_data/cldr_language_data/date_translation_data/nnh.json index c8d5ff8bf..4383eacde 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/nnh.json +++ b/dateparser_data/cldr_language_data/date_translation_data/nnh.json @@ -77,7 +77,8 @@ "lyɛ̌'" ], "hour": [ - "fʉ̀' nèm" + "fʉ̀' nèm", + "hr" ], "minute": [ "minute" diff --git a/dateparser_data/cldr_language_data/date_translation_data/nus.json b/dateparser_data/cldr_language_data/date_translation_data/nus.json index f79ebb4cd..75d6756cc 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/nus.json +++ b/dateparser_data/cldr_language_data/date_translation_data/nus.json @@ -93,6 +93,7 @@ "cäŋ" ], "hour": [ + "hr", "thaak" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/nyn.json b/dateparser_data/cldr_language_data/date_translation_data/nyn.json index 519bc9ac3..f8f929b1e 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/nyn.json +++ b/dateparser_data/cldr_language_data/date_translation_data/nyn.json @@ -96,6 +96,7 @@ "eizooba" ], "hour": [ + "hr", "shaaha" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/om.json b/dateparser_data/cldr_language_data/date_translation_data/om.json index a4bc22e56..c09f1039d 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/om.json +++ b/dateparser_data/cldr_language_data/date_translation_data/om.json @@ -96,7 +96,8 @@ "day" ], "hour": [ - "hour" + "hour", + "hr" ], "minute": [ "minute" diff --git a/dateparser_data/cldr_language_data/date_translation_data/or.json b/dateparser_data/cldr_language_data/date_translation_data/or.json index 92ed23210..845691458 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/or.json +++ b/dateparser_data/cldr_language_data/date_translation_data/or.json @@ -1,6 +1,6 @@ { "name": "or", - "date_order": "DMY", + "date_order": "MDY", "january": [ "ଜାନୁଆରୀ" ], @@ -66,77 +66,141 @@ "ରବିବାର" ], "am": [ - "am" + "am", + "ପୂର୍ବାହ୍ନ" ], "pm": [ - "pm" + "pm", + "ଅପରାହ୍ନ" ], "year": [ - "year" + "ବ", + "ବର୍ଷ" ], "month": [ - "month" + "ମା", + "ମାସ" ], "week": [ - "week" + "ସ", + "ସପ୍ତାହ" ], "day": [ - "day" + "ଦିନ" ], "hour": [ - "hour" + "ଘ", + "ଘଣ୍ଟା" ], "minute": [ - "minute" + "ମି", + "ମିନିଟ୍" ], "second": [ - "second" + "ସେ", + "ସେକେଣ୍ଡ୍" ], "relative-type": { "0 day ago": [ - "today" + "ଆଜି" ], "0 hour ago": [ - "this hour" + "ଏହି ଘଣ୍ଟା" ], "0 minute ago": [ - "this minute" + "ଏହି ମିନିଟ୍" ], "0 month ago": [ - "this month" + "ଏହି ମାସ" ], "0 second ago": [ - "now" + "ବର୍ତ୍ତମାନ" ], "0 week ago": [ - "this week" + "ଏହି ସପ୍ତାହ" ], "0 year ago": [ - "this year" + "ଏହି ବର୍ଷ" ], "1 day ago": [ - "yesterday" + "ଗତକାଲି" ], "1 month ago": [ - "last month" + "ଗତ ମାସ" ], "1 week ago": [ - "last week" + "ଗତ ସପ୍ତାହ" ], "1 year ago": [ - "last year" + "ଗତ ବର୍ଷ" ], "in 1 day": [ - "tomorrow" + "ଆସନ୍ତାକାଲି" ], "in 1 month": [ - "next month" + "ଆଗାମୀ ମାସ" ], "in 1 week": [ - "next week" + "ଆଗାମୀ ସପ୍ତାହ" ], "in 1 year": [ - "next year" + "ଆଗାମୀ ବର୍ଷ" + ] + }, + "relative-type-regex": { + "\\1 day ago": [ + "{0} ଦିନ ପୂର୍ବେ" + ], + "\\1 hour ago": [ + "{0} ଘ ପୂର୍ବେ", + "{0} ଘଣ୍ଟା ପୂର୍ବେ" + ], + "\\1 minute ago": [ + "{0} ମି ପୂର୍ବେ", + "{0} ମିନିଟ୍ ପୂର୍ବେ" + ], + "\\1 month ago": [ + "{0} ମା ପୂର୍ବେ", + "{0} ମାସ ପୂର୍ବେ" + ], + "\\1 second ago": [ + "{0} ସେ ପୂର୍ବେ", + "{0} ସେକେଣ୍ଡ ପୂର୍ବେ" + ], + "\\1 week ago": [ + "{0} ସପ୍ତା ପୂର୍ବେ", + "{0} ସପ୍ତାହ ପୂର୍ବେ" + ], + "\\1 year ago": [ + "{0} ବ ପୂର୍ବେ", + "{0} ବର୍ଷ ପୂର୍ବେ" + ], + "in \\1 day": [ + "{0} ଦିନରେ" + ], + "in \\1 hour": [ + "{0} ଘ ରେ", + "{0} ଘଣ୍ଟାରେ" + ], + "in \\1 minute": [ + "{0} ମି ରେ", + "{0} ମିନିଟ୍‌‌ରେ" + ], + "in \\1 month": [ + "{0} ମା ରେ", + "{0} ମାସରେ" + ], + "in \\1 second": [ + "{0} ସେ ରେ", + "{0} ସେକେଣ୍ଡରେ" + ], + "in \\1 week": [ + "{0} ସପ୍ତା ରେ", + "{0} ସପ୍ତାହରେ" + ], + "in \\1 year": [ + "{0} ବ ରେ", + "{0} ବର୍ଷରେ" ] }, "locale_specific": {} diff --git a/dateparser_data/cldr_language_data/date_translation_data/os.json b/dateparser_data/cldr_language_data/date_translation_data/os.json index c2cd204c0..5762d8afb 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/os.json +++ b/dateparser_data/cldr_language_data/date_translation_data/os.json @@ -111,7 +111,8 @@ "бон" ], "hour": [ - "сахат" + "сахат", + "сахаты" ], "minute": [ "минут" diff --git a/dateparser_data/cldr_language_data/date_translation_data/pa-Arab.json b/dateparser_data/cldr_language_data/date_translation_data/pa-Arab.json index ee529521e..9b2155c58 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/pa-Arab.json +++ b/dateparser_data/cldr_language_data/date_translation_data/pa-Arab.json @@ -77,6 +77,7 @@ "دئن" ], "hour": [ + "hr", "گھنٹا" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/pa-Guru.json b/dateparser_data/cldr_language_data/date_translation_data/pa-Guru.json index 37718bb20..fb79a30df 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/pa-Guru.json +++ b/dateparser_data/cldr_language_data/date_translation_data/pa-Guru.json @@ -94,7 +94,8 @@ ], "hour": [ "ਘੰ", - "ਘੰਟਾ" + "ਘੰਟਾ", + "ਘੰਟੇ" ], "minute": [ "ਮਿੰਟ" diff --git a/dateparser_data/cldr_language_data/date_translation_data/pa.json b/dateparser_data/cldr_language_data/date_translation_data/pa.json index 6b6c980db..fe76d5c0c 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/pa.json +++ b/dateparser_data/cldr_language_data/date_translation_data/pa.json @@ -94,7 +94,8 @@ ], "hour": [ "ਘੰ", - "ਘੰਟਾ" + "ਘੰਟਾ", + "ਘੰਟੇ" ], "minute": [ "ਮਿੰਟ" diff --git a/dateparser_data/cldr_language_data/date_translation_data/pl.json b/dateparser_data/cldr_language_data/date_translation_data/pl.json index 1a8f6e9e1..8a73f7486 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/pl.json +++ b/dateparser_data/cldr_language_data/date_translation_data/pl.json @@ -108,12 +108,15 @@ "tydzień" ], "day": [ + "d", + "dz", "dzień" ], "hour": [ "g", "godz", - "godzina" + "godzina", + "godziny" ], "minute": [ "min", @@ -126,7 +129,8 @@ ], "relative-type": { "0 day ago": [ - "dzisiaj" + "dzisiaj", + "dziś" ], "0 hour ago": [ "ta godzina" @@ -135,24 +139,29 @@ "ta minuta" ], "0 month ago": [ + "w tym mies", "w tym miesiącu" ], "0 second ago": [ "teraz" ], "0 week ago": [ + "w tym tyg", "w tym tygodniu" ], "0 year ago": [ "w tym roku" ], "1 day ago": [ + "wcz", "wczoraj" ], "1 month ago": [ + "w zeszłym mies", "w zeszłym miesiącu" ], "1 week ago": [ + "w zeszłym tyg", "w zeszłym tygodniu" ], "1 year ago": [ @@ -162,9 +171,11 @@ "jutro" ], "in 1 month": [ + "w przyszłym mies", "w przyszłym miesiącu" ], "in 1 week": [ + "w przyszłym tyg", "w przyszłym tygodniu" ], "in 1 year": [ @@ -190,8 +201,7 @@ "\\1 month ago": [ "{0} mies temu", "{0} miesiąc temu", - "{0} miesiąca temu", - "–{0} mies" + "{0} miesiąca temu" ], "\\1 second ago": [ "{0} s temu", diff --git a/dateparser_data/cldr_language_data/date_translation_data/ps.json b/dateparser_data/cldr_language_data/date_translation_data/ps.json index 0cd9f6c11..821df60f2 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ps.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ps.json @@ -5,7 +5,8 @@ "جنوري" ], "february": [ - "فبروري" + "فبروري", + "فېبروري" ], "march": [ "مارچ" @@ -26,7 +27,8 @@ "اګست" ], "september": [ - "سپتمبر" + "سپتمبر", + "سېپتمبر" ], "october": [ "اکتوبر" @@ -38,99 +40,179 @@ "دسمبر" ], "monday": [ - "دوشنبه" + "دونۍ" ], "tuesday": [ - "سه‌شنبه" + "درېنۍ" ], "wednesday": [ - "چهارشنبه" + "څلرنۍ" ], "thursday": [ - "پنجشنبه" + "پينځنۍ" ], "friday": [ "جمعه" ], "saturday": [ - "شنبه" + "اونۍ" ], "sunday": [ - "یکشنبه" + "يونۍ" ], "am": [ + "am", "غم" ], "pm": [ + "pm", "غو" ], "year": [ - "year" + "کال" ], "month": [ - "month" + "مياشت" ], "week": [ - "week" + "اونۍ" ], "day": [ - "day" + "ورځ" ], "hour": [ - "hour" + "ساعت", + "ساعتونه" ], "minute": [ - "minute" + "دقيقه" ], "second": [ - "second" + "ثانيه" ], "relative-type": { "0 day ago": [ - "today" + "نن" ], "0 hour ago": [ - "this hour" + "دا ساعت" ], "0 minute ago": [ - "this minute" + "دا دقيقه" ], "0 month ago": [ - "this month" + "دا مياشت" ], "0 second ago": [ - "now" + "اوس" ], "0 week ago": [ - "this week" + "دا اونۍ" ], "0 year ago": [ - "this year" + "سږ کال", + "سږکال" ], "1 day ago": [ - "yesterday" + "پرون" ], "1 month ago": [ - "last month" + "تېره مياشت" ], "1 week ago": [ - "last week" + "تيره اونۍ", + "تېره اونۍ" ], "1 year ago": [ - "last year" + "تير کال", + "تېر کال", + "پروسږکال" ], "in 1 day": [ - "tomorrow" + "سبا" ], "in 1 month": [ - "next month" + "راتلونکې مياشت" ], "in 1 week": [ - "next week" + "راتلونکې اونۍ" ], "in 1 year": [ - "next year" + "راتلونکی کال", + "روتلونکی کال" ] }, - "locale_specific": {} + "relative-type-regex": { + "\\1 day ago": [ + "{0} ورځ مخکې", + "{0} ورځې مخکې" + ], + "\\1 hour ago": [ + "{0} ساعت مخکې", + "{0} ساعتونه مخکې" + ], + "\\1 minute ago": [ + "{0} دقيقه مخکې", + "{0} دقيقې مخکې" + ], + "\\1 month ago": [ + "{0} مياشت مخکې", + "{0} مياشتې مخکې" + ], + "\\1 second ago": [ + "{0} ثانيه مخکې", + "{0} ثانيه کې", + "{0} ثانيې مخکې" + ], + "\\1 week ago": [ + "{0} اونۍ مخکې" + ], + "\\1 year ago": [ + "{0} کال مخکې", + "{0} کاله مخکې" + ], + "in \\1 day": [ + "په {0} ورځ کې", + "په {0} ورځو کې" + ], + "in \\1 hour": [ + "په {0} ساعت کې", + "په {0} ساعتو کې" + ], + "in \\1 minute": [ + "په {0} دقيقه کې", + "په {0} دقيقو کې" + ], + "in \\1 month": [ + "په {0} مياشت کې", + "په {0} مياشتو کې" + ], + "in \\1 second": [ + "په {0} ثانيه کې", + "په {0} ثانيو کې" + ], + "in \\1 week": [ + "په {0} اونيو کې", + "په {0} اونۍ کې" + ], + "in \\1 year": [ + "په {0} کال کې", + "په {0} کالونو کې" + ] + }, + "locale_specific": { + "ps-PK": { + "name": "ps-PK", + "relative-type-regex": { + "\\1 year ago": [ + "{0} کال مخکے", + "{0} کاله مخکے" + ], + "in \\1 year": [ + "په {0} کال کے", + "په {0} کالونو کے" + ] + } + } + } } \ No newline at end of file diff --git a/dateparser_data/cldr_language_data/date_translation_data/pt.json b/dateparser_data/cldr_language_data/date_translation_data/pt.json index afb0132f1..05584c30b 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/pt.json +++ b/dateparser_data/cldr_language_data/date_translation_data/pt.json @@ -98,15 +98,14 @@ ], "hour": [ "h", - "hora" + "hora", + "horas" ], "minute": [ - "m", "min", "minuto" ], "second": [ - "s", "seg", "segundo" ], @@ -169,7 +168,6 @@ ], "\\1 minute ago": [ "há {0} min", - "há {0} mins", "há {0} minuto", "há {0} minutos" ], @@ -202,7 +200,6 @@ ], "in \\1 minute": [ "em {0} min", - "em {0} mins", "em {0} minuto", "em {0} minutos" ], @@ -212,7 +209,6 @@ ], "in \\1 second": [ "em {0} seg", - "em {0} segs", "em {0} segundo", "em {0} segundos" ], @@ -252,6 +248,9 @@ "da tarde", "tarde" ], + "second": [ + "s" + ], "relative-type-regex": { "\\1 second ago": [ "há {0} s" @@ -315,6 +314,9 @@ "da tarde", "tarde" ], + "second": [ + "s" + ], "relative-type-regex": { "\\1 second ago": [ "há {0} s" @@ -378,6 +380,9 @@ "da tarde", "tarde" ], + "second": [ + "s" + ], "relative-type-regex": { "\\1 second ago": [ "há {0} s" @@ -441,6 +446,9 @@ "da tarde", "tarde" ], + "second": [ + "s" + ], "relative-type-regex": { "\\1 second ago": [ "há {0} s" @@ -504,6 +512,9 @@ "da tarde", "tarde" ], + "second": [ + "s" + ], "relative-type-regex": { "\\1 second ago": [ "há {0} s" @@ -567,6 +578,9 @@ "da tarde", "tarde" ], + "second": [ + "s" + ], "relative-type-regex": { "\\1 second ago": [ "há {0} s" @@ -630,6 +644,9 @@ "da tarde", "tarde" ], + "second": [ + "s" + ], "relative-type-regex": { "\\1 second ago": [ "há {0} s" @@ -693,6 +710,9 @@ "da tarde", "tarde" ], + "second": [ + "s" + ], "relative-type-regex": { "\\1 second ago": [ "há {0} s" @@ -756,6 +776,9 @@ "da tarde", "tarde" ], + "second": [ + "s" + ], "relative-type-regex": { "\\1 second ago": [ "há {0} s" @@ -819,6 +842,9 @@ "da tarde", "tarde" ], + "second": [ + "s" + ], "relative-type-regex": { "\\1 second ago": [ "há {0} s" @@ -882,6 +908,9 @@ "da tarde", "tarde" ], + "second": [ + "s" + ], "relative-type-regex": { "\\1 second ago": [ "há {0} s" diff --git a/dateparser_data/cldr_language_data/date_translation_data/qu.json b/dateparser_data/cldr_language_data/date_translation_data/qu.json index 6b58c6cae..0a42aa547 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/qu.json +++ b/dateparser_data/cldr_language_data/date_translation_data/qu.json @@ -2,52 +2,52 @@ "name": "qu", "date_order": "DMY", "january": [ - "qul", - "qulla puquy" + "ene", + "enero" ], "february": [ - "hat", - "hatun puquy" + "feb", + "febrero" ], "march": [ - "pau", - "pauqar waray" + "mar", + "marzo" ], "april": [ - "ayr", - "ayriwa" + "abr", + "abril" ], "may": [ - "aym", - "aymuray" + "may", + "mayo" ], "june": [ - "int", - "inti raymi" + "jun", + "junio" ], "july": [ - "ant", - "anta sitwa" + "jul", + "julio" ], "august": [ - "qha", - "qhapaq sitwa" + "ago", + "agosto" ], "september": [ - "uma", - "uma raymi" + "set", + "setiembre" ], "october": [ - "kan", - "kantaray" + "oct", + "octubre" ], "november": [ - "aya", - "ayamarq'a" + "nov", + "noviembre" ], "december": [ - "kap", - "kapaq raymi" + "dic", + "diciembre" ], "monday": [ "lun", @@ -96,6 +96,7 @@ "day" ], "hour": [ + "hora", "hour" ], "minute": [ @@ -106,49 +107,49 @@ ], "relative-type": { "0 day ago": [ - "today" + "kunan punchaw" ], "0 hour ago": [ - "this hour" + "kay hora" ], "0 minute ago": [ - "this minute" + "kay minuto" ], "0 month ago": [ - "this month" + "kunan killa" ], "0 second ago": [ "now" ], "0 week ago": [ - "this week" + "kunan semana" ], "0 year ago": [ - "this year" + "kunan wata" ], "1 day ago": [ - "yesterday" + "qayna punchaw" ], "1 month ago": [ - "last month" + "qayna killa" ], "1 week ago": [ - "last week" + "qayna semana" ], "1 year ago": [ - "last year" + "qayna wata" ], "in 1 day": [ - "tomorrow" + "paqarin" ], "in 1 month": [ - "next month" + "hamuq killa" ], "in 1 week": [ - "next week" + "hamuq semana" ], "in 1 year": [ - "next year" + "hamuq wata" ] }, "locale_specific": { diff --git a/dateparser_data/cldr_language_data/date_translation_data/rm.json b/dateparser_data/cldr_language_data/date_translation_data/rm.json index 69d1b68c5..35402b266 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/rm.json +++ b/dateparser_data/cldr_language_data/date_translation_data/rm.json @@ -2,47 +2,59 @@ "name": "rm", "date_order": "DMY", "january": [ + "da schaner", "schan", "schaner" ], "february": [ + "da favrer", "favr", "favrer" ], "march": [ + "da mars", "mars" ], "april": [ "avr", - "avrigl" + "avrigl", + "d'avrigl" ], "may": [ + "da matg", "matg" ], "june": [ + "da zercladur", "zercl", "zercladur" ], "july": [ + "da fanadur", "fan", "fanadur" ], "august": [ - "avust" + "avust", + "d'avust" ], "september": [ + "da settember", "sett", "settember" ], "october": [ + "d'october", "oct", "october" ], "november": [ + "da november", "nov", "november" ], "december": [ + "da december", "dec", "december" ], @@ -90,15 +102,19 @@ "emna" ], "day": [ - "tag" + "d", + "di" ], "hour": [ - "ura" + "ura", + "uras" ], "minute": [ + "min", "minuta" ], "second": [ + "s", "secunda" ], "relative-type": { @@ -121,7 +137,7 @@ "this week" ], "0 year ago": [ - "this year" + "quest onn" ], "1 day ago": [ "ier" @@ -133,7 +149,7 @@ "last week" ], "1 year ago": [ - "last year" + "l'onn passà" ], "in 1 day": [ "damaun" @@ -145,7 +161,7 @@ "next week" ], "in 1 year": [ - "next year" + "l'onn proxim" ] }, "locale_specific": {} diff --git a/dateparser_data/cldr_language_data/date_translation_data/rn.json b/dateparser_data/cldr_language_data/date_translation_data/rn.json index f2226ce37..dae88e0b8 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/rn.json +++ b/dateparser_data/cldr_language_data/date_translation_data/rn.json @@ -96,6 +96,7 @@ "umusi" ], "hour": [ + "hr", "isaha" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/ro.json b/dateparser_data/cldr_language_data/date_translation_data/ro.json index 41f9cc339..996d53fde 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ro.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ro.json @@ -96,6 +96,7 @@ ], "hour": [ "h", + "ore", "oră" ], "minute": [ @@ -125,6 +126,7 @@ "acum" ], "0 week ago": [ + "săpt aceasta", "săptămâna aceasta" ], "0 year ago": [ @@ -137,6 +139,7 @@ "luna trecută" ], "1 week ago": [ + "săpt trecută", "săptămâna trecută" ], "1 year ago": [ @@ -149,6 +152,7 @@ "luna viitoare" ], "in 1 week": [ + "săpt viitoare", "săptămâna viitoare" ], "in 1 year": [ @@ -158,8 +162,7 @@ "relative-type-regex": { "\\1 day ago": [ "acum {0} de zile", - "acum {0} zi", - "acum {0} zile" + "acum {0} zi" ], "\\1 hour ago": [ "acum {0} de ore", @@ -192,8 +195,7 @@ ], "in \\1 day": [ "peste {0} de zile", - "peste {0} zi", - "peste {0} zile" + "peste {0} zi" ], "in \\1 hour": [ "peste {0} de ore", @@ -222,7 +224,6 @@ ], "in \\1 year": [ "peste {0} an", - "peste {0} ani", "peste {0} de ani" ] }, diff --git a/dateparser_data/cldr_language_data/date_translation_data/rof.json b/dateparser_data/cldr_language_data/date_translation_data/rof.json index d13b18c97..859d73603 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/rof.json +++ b/dateparser_data/cldr_language_data/date_translation_data/rof.json @@ -84,6 +84,7 @@ "mfiri" ], "hour": [ + "hr", "isaa" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/ru.json b/dateparser_data/cldr_language_data/date_translation_data/ru.json index 8994aaa86..fc6130eb3 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ru.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ru.json @@ -89,10 +89,10 @@ "вс" ], "am": [ - "дп" + "am" ], "pm": [ - "пп" + "pm" ], "year": [ "г", @@ -112,7 +112,8 @@ ], "hour": [ "ч", - "час" + "час", + "часы" ], "minute": [ "мин", @@ -128,51 +129,68 @@ "сегодня" ], "0 hour ago": [ - "в этом часе" + "в этот час" ], "0 minute ago": [ "в эту минуту" ], "0 month ago": [ + "в эт мес", + "в этом мес", "в этом месяце" ], "0 second ago": [ "сейчас" ], "0 week ago": [ + "на эт нед", + "на этой нед", "на этой неделе" ], "0 year ago": [ + "в эт г", + "в этом г", "в этом году" ], "1 day ago": [ "вчера" ], "1 month ago": [ + "в пр мес", + "в прошлом мес", "в прошлом месяце" ], "1 week ago": [ + "на пр нед", + "на прошлой нед", "на прошлой неделе" ], "1 year ago": [ + "в пр г", + "в прошлом г", "в прошлом году" ], "in 1 day": [ "завтра" ], "in 1 month": [ + "в след мес", + "в следующем мес", "в следующем месяце" ], "in 1 week": [ + "на след нед", + "на следующей нед", "на следующей неделе" ], "in 1 year": [ + "в сл г", + "в след г", "в следующем году" ] }, "relative-type-regex": { "\\1 day ago": [ - "{0} д назад", "{0} день назад", "{0} дн назад", "{0} дня назад" @@ -208,7 +226,6 @@ "{0} года назад" ], "in \\1 day": [ - "через {0} д", "через {0} день", "через {0} дн", "через {0} дня" @@ -258,13 +275,7 @@ "name": "ru-MD" }, "ru-UA": { - "name": "ru-UA", - "am": [ - "am" - ], - "pm": [ - "pm" - ] + "name": "ru-UA" } } } \ No newline at end of file diff --git a/dateparser_data/cldr_language_data/date_translation_data/rw.json b/dateparser_data/cldr_language_data/date_translation_data/rw.json index 8b4dda315..df9c8f795 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/rw.json +++ b/dateparser_data/cldr_language_data/date_translation_data/rw.json @@ -19,7 +19,7 @@ ], "may": [ "gic", - "gicuransi" + "gicurasi" ], "june": [ "kam", @@ -96,7 +96,8 @@ "day" ], "hour": [ - "hour" + "hour", + "hr" ], "minute": [ "minute" diff --git a/dateparser_data/cldr_language_data/date_translation_data/rwk.json b/dateparser_data/cldr_language_data/date_translation_data/rwk.json index 21b5e41a7..44a4766e7 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/rwk.json +++ b/dateparser_data/cldr_language_data/date_translation_data/rwk.json @@ -95,6 +95,7 @@ "mfiri" ], "hour": [ + "hr", "saa" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/saq.json b/dateparser_data/cldr_language_data/date_translation_data/saq.json index a84ade947..415843f4e 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/saq.json +++ b/dateparser_data/cldr_language_data/date_translation_data/saq.json @@ -96,6 +96,7 @@ "mpari" ], "hour": [ + "hr", "saai" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/sbp.json b/dateparser_data/cldr_language_data/date_translation_data/sbp.json index acd44b6cc..322243561 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/sbp.json +++ b/dateparser_data/cldr_language_data/date_translation_data/sbp.json @@ -96,6 +96,7 @@ "lusiku" ], "hour": [ + "hr", "ilisala" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/se.json b/dateparser_data/cldr_language_data/date_translation_data/se.json index 95e57a715..85604aed5 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/se.json +++ b/dateparser_data/cldr_language_data/date_translation_data/se.json @@ -100,7 +100,8 @@ "beaivi" ], "hour": [ - "diibmu" + "diibmu", + "diibmur" ], "minute": [ "minuhtta" @@ -214,47 +215,151 @@ "locale_specific": { "se-FI": { "name": "se-FI", + "date_order": "DMY", + "april": [ + "cuoŋ" + ], "monday": [ - "vuossárgga" + "má", + "mánnodat" ], "tuesday": [ - "maŋŋebárgga" + "di", + "disdat" ], "wednesday": [ - "gaskavahku" + "ga" ], "thursday": [ - "duorastaga" + "du", + "duorastat" ], "friday": [ - "bearjadaga" + "be" ], "saturday": [ - "lávvardaga" + "lá", + "lávvordat" + ], + "sunday": [ + "so" ], "year": [ "j", "jahki" ], + "month": [ + "m" + ], "week": [ + "v(k)", "vahkku" ], + "day": [ + "b" + ], + "hour": [ + "dmu" + ], + "minute": [ + "min" + ], + "second": [ + "sek" + ], "relative-type": { + "0 hour ago": [ + "dán diimmu" + ], + "0 minute ago": [ + "dán minuhta" + ], + "0 month ago": [ + "dán mánu" + ], + "0 second ago": [ + "dál" + ], + "0 week ago": [ + "dán vahku" + ], "0 year ago": [ "dán jagi" ], + "1 month ago": [ + "mannan mánu" + ], + "1 week ago": [ + "mannan vahku" + ], "1 year ago": [ - "mannan jagi" + "diibmá" + ], + "in 1 month": [ + "boahtte mánu" + ], + "in 1 week": [ + "boahtte vahku" ], "in 1 year": [ "boahtte jagi" ] }, "relative-type-regex": { + "\\1 day ago": [ + "{0} beaivve dás ovdal" + ], + "\\1 hour ago": [ + "{0} diibmu áigi", + "{0} diimmu áigi", + "{0} dmu áigi" + ], + "\\1 minute ago": [ + "{0} min áigi", + "{0} minuhta áigi", + "{0} minuhtta áigi" + ], + "\\1 month ago": [ + "{0} mánnu dás ovdal", + "{0} mánu dás ovdal" + ], + "\\1 second ago": [ + "{0} sek áigi", + "{0} sekunda áigi", + "{0} sekundda áigi" + ], + "\\1 week ago": [ + "{0} vahkku dás ovdal", + "{0} vahku dás ovdal" + ], "\\1 year ago": [ - "{0} jagi árat" + "{0} j dás ovdal", + "{0} jagi dás ovdal" + ], + "in \\1 day": [ + "{0} beaivve siste" + ], + "in \\1 hour": [ + "{0} diimmu siste", + "{0} dmu siste" + ], + "in \\1 minute": [ + "{0} min siste", + "{0} minuhta siste" + ], + "in \\1 month": [ + "{0} mánu geahčen", + "{0} mánu siste" + ], + "in \\1 second": [ + "{0} sek siste", + "{0} sekundda siste" + ], + "in \\1 week": [ + "{0} vahku geahčen" ], "in \\1 year": [ + "{0} j siste", "{0} jagi siste" ] } diff --git a/dateparser_data/cldr_language_data/date_translation_data/seh.json b/dateparser_data/cldr_language_data/date_translation_data/seh.json index f1792f055..dfa1f8ac7 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/seh.json +++ b/dateparser_data/cldr_language_data/date_translation_data/seh.json @@ -96,7 +96,8 @@ "ntsiku" ], "hour": [ - "hora" + "hora", + "hr" ], "minute": [ "minuto" diff --git a/dateparser_data/cldr_language_data/date_translation_data/ses.json b/dateparser_data/cldr_language_data/date_translation_data/ses.json index f935764d8..84b55e215 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ses.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ses.json @@ -94,7 +94,8 @@ "zaari" ], "hour": [ - "guuru" + "guuru", + "hr" ], "minute": [ "miniti" diff --git a/dateparser_data/cldr_language_data/date_translation_data/sg.json b/dateparser_data/cldr_language_data/date_translation_data/sg.json index 52cc1c08b..3b5a31060 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/sg.json +++ b/dateparser_data/cldr_language_data/date_translation_data/sg.json @@ -96,6 +96,7 @@ "lâ" ], "hour": [ + "hr", "ngbonga" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/shi-Latn.json b/dateparser_data/cldr_language_data/date_translation_data/shi-Latn.json index 61c968311..00ad2c008 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/shi-Latn.json +++ b/dateparser_data/cldr_language_data/date_translation_data/shi-Latn.json @@ -96,6 +96,7 @@ "ass" ], "hour": [ + "hr", "tasragt" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/shi-Tfng.json b/dateparser_data/cldr_language_data/date_translation_data/shi-Tfng.json index 22b1473c0..f0d3b2f0b 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/shi-Tfng.json +++ b/dateparser_data/cldr_language_data/date_translation_data/shi-Tfng.json @@ -96,6 +96,7 @@ "ⴰⵙⵙ" ], "hour": [ + "hr", "ⵜⴰⵙⵔⴰⴳⵜ" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/shi.json b/dateparser_data/cldr_language_data/date_translation_data/shi.json index 5124c2d72..8888bf0b7 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/shi.json +++ b/dateparser_data/cldr_language_data/date_translation_data/shi.json @@ -96,6 +96,7 @@ "ⴰⵙⵙ" ], "hour": [ + "hr", "ⵜⴰⵙⵔⴰⴳⵜ" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/si.json b/dateparser_data/cldr_language_data/date_translation_data/si.json index 7e7194dc5..3162d529a 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/si.json +++ b/dateparser_data/cldr_language_data/date_translation_data/si.json @@ -92,16 +92,13 @@ "දිනය" ], "hour": [ - "පැ", "පැය" ], "minute": [ - "මි", "මිනි", "මිනිත්තුව" ], "second": [ - "ත", "තත්", "තත්පරය" ], diff --git a/dateparser_data/cldr_language_data/date_translation_data/sk.json b/dateparser_data/cldr_language_data/date_translation_data/sk.json index b8b883979..bf184ecc3 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/sk.json +++ b/dateparser_data/cldr_language_data/date_translation_data/sk.json @@ -110,7 +110,8 @@ ], "hour": [ "h", - "hodina" + "hodina", + "hodiny" ], "minute": [ "min", @@ -131,12 +132,14 @@ "v tejto minúte" ], "0 month ago": [ + "tento mes", "tento mesiac" ], "0 second ago": [ "teraz" ], "0 week ago": [ + "tento týž", "tento týždeň" ], "0 year ago": [ @@ -146,9 +149,11 @@ "včera" ], "1 month ago": [ + "minulý mes", "minulý mesiac" ], "1 week ago": [ + "minulý týž", "minulý týždeň" ], "1 year ago": [ @@ -158,9 +163,11 @@ "zajtra" ], "in 1 month": [ + "budúci mes", "budúci mesiac" ], "in 1 week": [ + "budúci týž", "budúci týždeň" ], "in 1 year": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/sl.json b/dateparser_data/cldr_language_data/date_translation_data/sl.json index 77a66432d..d2cdef9a3 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/sl.json +++ b/dateparser_data/cldr_language_data/date_translation_data/sl.json @@ -100,7 +100,8 @@ ], "hour": [ "h", - "ura" + "ura", + "ure" ], "minute": [ "min", @@ -122,12 +123,14 @@ "to minuto" ], "0 month ago": [ + "ta mes", "ta mesec" ], "0 second ago": [ "zdaj" ], "0 week ago": [ + "ta ted", "ta teden" ], "0 year ago": [ @@ -137,9 +140,13 @@ "včeraj" ], "1 month ago": [ + "prej mes", + "prejšnji mes", "prejšnji mesec" ], "1 week ago": [ + "prej ted", + "prejšnji ted", "prejšnji teden" ], "1 year ago": [ @@ -149,9 +156,13 @@ "jutri" ], "in 1 month": [ + "nasl mes", + "naslednji mes", "naslednji mesec" ], "in 1 week": [ + "nasl ted", + "naslednji ted", "naslednji teden" ], "in 1 year": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/smn.json b/dateparser_data/cldr_language_data/date_translation_data/smn.json index debf7b9b4..8eaadfd75 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/smn.json +++ b/dateparser_data/cldr_language_data/date_translation_data/smn.json @@ -103,7 +103,8 @@ "day" ], "hour": [ - "hour" + "hour", + "tiijmeh" ], "minute": [ "minute" diff --git a/dateparser_data/cldr_language_data/date_translation_data/sn.json b/dateparser_data/cldr_language_data/date_translation_data/sn.json index f306903cf..b1e28d11d 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/sn.json +++ b/dateparser_data/cldr_language_data/date_translation_data/sn.json @@ -96,7 +96,8 @@ "zuva" ], "hour": [ - "awa" + "awa", + "hr" ], "minute": [ "mineti" diff --git a/dateparser_data/cldr_language_data/date_translation_data/so.json b/dateparser_data/cldr_language_data/date_translation_data/so.json index 850727fc2..d7463da9e 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/so.json +++ b/dateparser_data/cldr_language_data/date_translation_data/so.json @@ -3,152 +3,244 @@ "date_order": "DMY", "january": [ "bisha koobaad", - "kob" + "jan", + "jannaayo" ], "february": [ "bisha labaad", - "lab" + "feb", + "febraayo" ], "march": [ "bisha saddexaad", - "sad" + "maarso", + "mar" ], "april": [ - "afr", + "abr", + "abriil", "bisha afraad" ], "may": [ "bisha shanaad", - "sha" + "may" ], "june": [ "bisha lixaad", - "lix" + "jun", + "juun" ], "july": [ "bisha todobaad", - "tod" + "lul", + "luuliyo" ], "august": [ "bisha sideedaad", - "sid" + "ogosto", + "ogs" ], "september": [ "bisha sagaalaad", - "sag" + "seb", + "sebteembar" ], "october": [ "bisha tobnaad", - "tob" + "okt", + "oktoobar" ], "november": [ "bisha kow iyo tobnaad", - "kit" + "nof", + "noofeembar" ], "december": [ "bisha laba iyo tobnaad", - "lit" + "dis", + "diseembar" ], "monday": [ "isn", "isniin" ], "tuesday": [ - "tal", - "talaado" + "talaado", + "tldo" ], "wednesday": [ - "arb", - "arbaco" + "arbaco", + "arbc" ], "thursday": [ - "kha", - "khamiis" + "khamiis", + "khms" ], "friday": [ - "jim", - "jimco" + "jimco", + "jmc" ], "saturday": [ - "sab", - "sabti" + "sabti", + "sbti" ], "sunday": [ "axad", "axd" ], "am": [ - "sn" + "am", + "gh" ], "pm": [ - "gn" + "gd" ], "year": [ - "year" + "sannad", + "snd" ], "month": [ - "month" + "bil" ], "week": [ - "week" + "tdbd", + "toddobaad" ], "day": [ - "day" + "maalin", + "mln" ], "hour": [ - "hour" + "saacad", + "saacado", + "scd" ], "minute": [ - "minute" + "daqiiqad", + "dqqd" ], "second": [ - "second" + "ilbiriqsi", + "ilbrqsi" ], "relative-type": { "0 day ago": [ "maanta" ], "0 hour ago": [ - "this hour" + "saacadan" ], "0 minute ago": [ - "this minute" + "daqiiqadan" ], "0 month ago": [ - "this month" + "bishan" ], "0 second ago": [ - "now" + "imika", + "iminka" ], "0 week ago": [ - "this week" + "toddobaadkan", + "usbuucan" ], "0 year ago": [ - "this year" + "sannadkan" ], "1 day ago": [ "shalay" ], "1 month ago": [ - "last month" + "bishii hore" ], "1 week ago": [ - "last week" + "toddobaadkii hore" ], "1 year ago": [ - "last year" + "sannadkii hore", + "sannadkii la soo dhaafay" ], "in 1 day": [ "berri" ], "in 1 month": [ - "next month" + "bisha danbe" ], "in 1 week": [ - "next week" + "toddobaadka danbe" ], "in 1 year": [ - "next year" + "sannadka danbe", + "sannadka xiga" + ] + }, + "relative-type-regex": { + "\\1 day ago": [ + "{0} maalin kahor", + "{0} maalmood kahor", + "{0} mlmd khr", + "{0} mln khr" + ], + "\\1 hour ago": [ + "{0} saacad kahor", + "{0} saacadood kahor", + "{0} scd khr" + ], + "\\1 minute ago": [ + "{0} daqiiqad kahor", + "{0} daqiiqadood kahor", + "{0} dqqd khr" + ], + "\\1 month ago": [ + "{0} bil kahor", + "{0} bil khr", + "{0} bilood kahor" + ], + "\\1 second ago": [ + "{0} ilbiriqsi kahor", + "{0} ilbrqsi khr" + ], + "\\1 week ago": [ + "{0} tdbd khr", + "{0} toddobaad kahor" + ], + "\\1 year ago": [ + "{0} sannad kahor", + "{0} sannadood kahor", + "{0} snd khr" + ], + "in \\1 day": [ + "{0} maalin", + "{0} maalmood", + "{0} mlmd", + "{0} mln" + ], + "in \\1 hour": [ + "{0} saacad", + "{0} saacadood", + "{0} scd" + ], + "in \\1 minute": [ + "{0} daqiidadood", + "{0} daqiiqad", + "{0} dqqd" + ], + "in \\1 month": [ + "{0} bil", + "{0} bilood" + ], + "in \\1 second": [ + "{0} ilbiriqsi", + "{0} ilbrqsi" + ], + "in \\1 week": [ + "{0} tdbd", + "{0} toddobaad" + ], + "in \\1 year": [ + "{0} sannad", + "{0} sannadood", + "{0} snd" ] }, "locale_specific": { diff --git a/dateparser_data/cldr_language_data/date_translation_data/sq.json b/dateparser_data/cldr_language_data/date_translation_data/sq.json index 5ac218ed4..655499e53 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/sq.json +++ b/dateparser_data/cldr_language_data/date_translation_data/sq.json @@ -25,11 +25,11 @@ "qershor" ], "july": [ - "kor", + "korr", "korrik" ], "august": [ - "gsh", + "gush", "gusht" ], "september": [ @@ -78,10 +78,12 @@ ], "am": [ "e paradites", - "paradite" + "paradite", + "pd" ], "pm": [ "e pasdites", + "md", "pasdite" ], "year": [ @@ -127,7 +129,8 @@ "këtë javë" ], "0 year ago": [ - "këtë vit" + "këtë vit", + "sivjet" ], "1 day ago": [ "dje" @@ -139,7 +142,8 @@ "javën e kaluar" ], "1 year ago": [ - "vitin e kaluar" + "vitin e kaluar", + "vjet" ], "in 1 day": [ "nesër" @@ -151,6 +155,7 @@ "javën e ardhshme" ], "in 1 year": [ + "mot", "vitin e ardhshëm" ] }, diff --git a/dateparser_data/cldr_language_data/date_translation_data/sr-Cyrl.json b/dateparser_data/cldr_language_data/date_translation_data/sr-Cyrl.json index b894802e0..36d465c4e 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/sr-Cyrl.json +++ b/dateparser_data/cldr_language_data/date_translation_data/sr-Cyrl.json @@ -75,10 +75,10 @@ "недеља" ], "am": [ - "пре подне" + "am" ], "pm": [ - "по подне" + "pm" ], "year": [ "г", @@ -86,12 +86,10 @@ "година" ], "month": [ - "м", "мес", "месец" ], "week": [ - "н", "нед", "недеља" ], @@ -101,6 +99,7 @@ ], "hour": [ "сат", + "сати", "ч" ], "minute": [ @@ -123,39 +122,54 @@ "овог минута" ], "0 month ago": [ + "овог мес", "овог месеца" ], "0 second ago": [ "сада" ], "0 week ago": [ + "ове н", + "ове нед", "ове недеље" ], "0 year ago": [ + "ове г", + "ове год", "ове године" ], "1 day ago": [ "јуче" ], "1 month ago": [ + "прошлог мес", "прошлог месеца" ], "1 week ago": [ + "прошле н", + "прошле нед", "прошле недеље" ], "1 year ago": [ + "прошле г", + "прошле год", "прошле године" ], "in 1 day": [ "сутра" ], "in 1 month": [ + "следећег мес", "следећег месеца" ], "in 1 week": [ + "следеће н", + "следеће нед", "следеће недеље" ], "in 1 year": [ + "следеће г", + "следеће год", "следеће године" ] }, @@ -240,14 +254,11 @@ "locale_specific": { "sr-Cyrl-BA": { "name": "sr-Cyrl-BA", - "september": [ - "септ" - ], - "tuesday": [ - "ут" + "monday": [ + "понедјељак" ], "wednesday": [ - "ср", + "сри", "сриједа" ], "sunday": [ @@ -255,18 +266,110 @@ ], "am": [ "прије подне" - ] + ], + "pm": [ + "по подне" + ], + "month": [ + "мјес", + "мјесец" + ], + "week": [ + "седм", + "седмица" + ], + "relative-type": { + "0 month ago": [ + "овог мјес", + "овог мјесеца" + ], + "0 week ago": [ + "ове с", + "ове седм", + "ове седмице" + ], + "1 month ago": [ + "прошлог мјес", + "прошлог мјесеца" + ], + "1 week ago": [ + "прошле с", + "прошле седм", + "прошле седмице" + ], + "in 1 month": [ + "сљедећег м", + "сљедећег мјес", + "сљедећег мјесеца" + ], + "in 1 week": [ + "сљедеће с", + "сљедеће седм", + "сљедеће седмице" + ], + "in 1 year": [ + "сљедеће г", + "сљедеће год", + "сљедеће године" + ] + }, + "relative-type-regex": { + "\\1 day ago": [ + "прије {0} д", + "прије {0} дана" + ], + "\\1 hour ago": [ + "прије {0} сата", + "прије {0} сати", + "прије {0} ч" + ], + "\\1 minute ago": [ + "прије {0} мин", + "прије {0} минута" + ], + "\\1 month ago": [ + "прије {0} м", + "прије {0} мјес", + "прије {0} мјесеца", + "прије {0} мјесеци" + ], + "\\1 second ago": [ + "прије {0} с", + "прије {0} сек", + "прије {0} секунде", + "прије {0} секунди" + ], + "\\1 week ago": [ + "прије {0} с", + "прије {0} седм", + "прије {0} седмица", + "прије {0} седмице" + ], + "\\1 year ago": [ + "прије {0} г", + "прије {0} год", + "прије {0} година", + "прије {0} године" + ], + "in \\1 month": [ + "за {0} мјес", + "за {0} мјесец", + "за {0} мјесеци" + ], + "in \\1 week": [ + "за {0} с", + "за {0} седм", + "за {0} седмица", + "за {0} седмицу" + ] + } }, "sr-Cyrl-ME": { "name": "sr-Cyrl-ME", "september": [ "септ" ], - "tuesday": [ - "ут" - ], "wednesday": [ - "ср", "сриједа" ], "sunday": [ @@ -274,18 +377,15 @@ ], "am": [ "прије подне" + ], + "pm": [ + "по подне" ] }, "sr-Cyrl-XK": { "name": "sr-Cyrl-XK", "september": [ "септ" - ], - "tuesday": [ - "ут" - ], - "wednesday": [ - "ср" ] } } diff --git a/dateparser_data/cldr_language_data/date_translation_data/sr-Latn.json b/dateparser_data/cldr_language_data/date_translation_data/sr-Latn.json index 74ce8fd02..46321b6e1 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/sr-Latn.json +++ b/dateparser_data/cldr_language_data/date_translation_data/sr-Latn.json @@ -75,10 +75,10 @@ "nedelja" ], "am": [ - "pre podne" + "am" ], "pm": [ - "po podne" + "pm" ], "year": [ "g", @@ -86,12 +86,10 @@ "godina" ], "month": [ - "m", "mes", "mesec" ], "week": [ - "n", "ned", "nedelja" ], @@ -101,6 +99,7 @@ ], "hour": [ "sat", + "sati", "č" ], "minute": [ @@ -123,39 +122,54 @@ "ovog minuta" ], "0 month ago": [ + "ovog mes", "ovog meseca" ], "0 second ago": [ "sada" ], "0 week ago": [ + "ove n", + "ove ned", "ove nedelje" ], "0 year ago": [ + "ove g", + "ove god", "ove godine" ], "1 day ago": [ "juče" ], "1 month ago": [ + "prošlog mes", "prošlog meseca" ], "1 week ago": [ + "prošle n", + "prošle ned", "prošle nedelje" ], "1 year ago": [ + "prošle g", + "prošle god", "prošle godine" ], "in 1 day": [ "sutra" ], "in 1 month": [ + "sledećeg mes", "sledećeg meseca" ], "in 1 week": [ + "sledeće n", + "sledeće ned", "sledeće nedelje" ], "in 1 year": [ + "sledeće g", + "sledeće god", "sledeće godine" ] }, @@ -240,14 +254,11 @@ "locale_specific": { "sr-Latn-BA": { "name": "sr-Latn-BA", - "september": [ - "sept" - ], - "tuesday": [ - "ut" + "monday": [ + "ponedjeljak" ], "wednesday": [ - "sr", + "sri", "srijeda" ], "sunday": [ @@ -255,18 +266,110 @@ ], "am": [ "prije podne" - ] + ], + "pm": [ + "po podne" + ], + "month": [ + "mjes", + "mjesec" + ], + "week": [ + "sedm", + "sedmica" + ], + "relative-type": { + "0 month ago": [ + "ovog mjes", + "ovog mjeseca" + ], + "0 week ago": [ + "ove s", + "ove sedm", + "ove sedmice" + ], + "1 month ago": [ + "prošlog mjes", + "prošlog mjeseca" + ], + "1 week ago": [ + "prošle s", + "prošle sedm", + "prošle sedmice" + ], + "in 1 month": [ + "sljedećeg m", + "sljedećeg mjes", + "sljedećeg mjeseca" + ], + "in 1 week": [ + "sljedeće s", + "sljedeće sedm", + "sljedeće sedmice" + ], + "in 1 year": [ + "sljedeće g", + "sljedeće god", + "sljedeće godine" + ] + }, + "relative-type-regex": { + "\\1 day ago": [ + "prije {0} d", + "prije {0} dana" + ], + "\\1 hour ago": [ + "prije {0} sata", + "prije {0} sati", + "prije {0} č" + ], + "\\1 minute ago": [ + "prije {0} min", + "prije {0} minuta" + ], + "\\1 month ago": [ + "prije {0} m", + "prije {0} mjes", + "prije {0} mjeseca", + "prije {0} mjeseci" + ], + "\\1 second ago": [ + "prije {0} s", + "prije {0} sek", + "prije {0} sekunde", + "prije {0} sekundi" + ], + "\\1 week ago": [ + "prije {0} s", + "prije {0} sedm", + "prije {0} sedmica", + "prije {0} sedmice" + ], + "\\1 year ago": [ + "prije {0} g", + "prije {0} god", + "prije {0} godina", + "prije {0} godine" + ], + "in \\1 month": [ + "za {0} mjes", + "za {0} mjesec", + "za {0} mjeseci" + ], + "in \\1 week": [ + "za {0} s", + "za {0} sedm", + "za {0} sedmica", + "za {0} sedmicu" + ] + } }, "sr-Latn-ME": { "name": "sr-Latn-ME", "september": [ "sept" ], - "tuesday": [ - "ut" - ], "wednesday": [ - "sr", "srijeda" ], "sunday": [ @@ -274,18 +377,15 @@ ], "am": [ "prije podne" + ], + "pm": [ + "po podne" ] }, "sr-Latn-XK": { "name": "sr-Latn-XK", "september": [ "sept" - ], - "tuesday": [ - "ut" - ], - "wednesday": [ - "sr" ] } } diff --git a/dateparser_data/cldr_language_data/date_translation_data/sr.json b/dateparser_data/cldr_language_data/date_translation_data/sr.json index 2ce5041b7..0a0b444f2 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/sr.json +++ b/dateparser_data/cldr_language_data/date_translation_data/sr.json @@ -75,10 +75,10 @@ "недеља" ], "am": [ - "пре подне" + "am" ], "pm": [ - "по подне" + "pm" ], "year": [ "г", @@ -86,12 +86,10 @@ "година" ], "month": [ - "м", "мес", "месец" ], "week": [ - "н", "нед", "недеља" ], @@ -101,6 +99,7 @@ ], "hour": [ "сат", + "сати", "ч" ], "minute": [ @@ -123,39 +122,54 @@ "овог минута" ], "0 month ago": [ + "овог мес", "овог месеца" ], "0 second ago": [ "сада" ], "0 week ago": [ + "ове н", + "ове нед", "ове недеље" ], "0 year ago": [ + "ове г", + "ове год", "ове године" ], "1 day ago": [ "јуче" ], "1 month ago": [ + "прошлог мес", "прошлог месеца" ], "1 week ago": [ + "прошле н", + "прошле нед", "прошле недеље" ], "1 year ago": [ + "прошле г", + "прошле год", "прошле године" ], "in 1 day": [ "сутра" ], "in 1 month": [ + "следећег мес", "следећег месеца" ], "in 1 week": [ + "следеће н", + "следеће нед", "следеће недеље" ], "in 1 year": [ + "следеће г", + "следеће год", "следеће године" ] }, diff --git a/dateparser_data/cldr_language_data/date_translation_data/sv.json b/dateparser_data/cldr_language_data/date_translation_data/sv.json index 89d971787..89dbd3c23 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/sv.json +++ b/dateparser_data/cldr_language_data/date_translation_data/sv.json @@ -99,6 +99,7 @@ "hour": [ "h", "tim", + "timmar", "timme" ], "minute": [ @@ -113,7 +114,8 @@ ], "relative-type": { "0 day ago": [ - "i dag" + "i dag", + "idag" ], "0 hour ago": [ "denna timme" @@ -122,8 +124,8 @@ "denna minut" ], "0 month ago": [ - "denna mån", - "denna månad" + "den här månaden", + "denna mån" ], "0 second ago": [ "nu" @@ -136,7 +138,8 @@ "i år" ], "1 day ago": [ - "i går" + "i går", + "igår" ], "1 month ago": [ "förra mån", @@ -150,7 +153,8 @@ "i fjol" ], "in 1 day": [ - "i morgon" + "i morgon", + "imorgon" ], "in 1 month": [ "nästa mån", @@ -178,19 +182,19 @@ "−{0} h" ], "\\1 minute ago": [ - "för {0} min sedan", + "för {0} min sen", "för {0} minut sedan", "för {0} minuter sedan", "−{0} min" ], "\\1 month ago": [ - "för {0} mån sedan", + "för {0} mån sen", "för {0} månad sedan", "för {0} månader sedan", "−{0} mån" ], "\\1 second ago": [ - "för {0} sek sedan", + "för {0} s sen", "för {0} sekund sedan", "för {0} sekunder sedan", "−{0} s" @@ -203,6 +207,7 @@ ], "\\1 year ago": [ "för {0} år sedan", + "för {0} år sen", "−{0} år" ], "in \\1 day": [ @@ -244,8 +249,7 @@ "name": "sv-AX" }, "sv-FI": { - "name": "sv-FI", - "date_order": "DMY" + "name": "sv-FI" } } } \ No newline at end of file diff --git a/dateparser_data/cldr_language_data/date_translation_data/sw.json b/dateparser_data/cldr_language_data/date_translation_data/sw.json index 760d8a5f6..27b3bc67e 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/sw.json +++ b/dateparser_data/cldr_language_data/date_translation_data/sw.json @@ -70,11 +70,9 @@ "jumapili" ], "am": [ - "am", - "asubuhi" + "am" ], "pm": [ - "mchana", "pm" ], "year": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/ta.json b/dateparser_data/cldr_language_data/date_translation_data/ta.json index cf3692fb4..214f78241 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ta.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ta.json @@ -74,6 +74,7 @@ "ஞாயிறு" ], "am": [ + "am", "முற்பகல்" ], "pm": [ @@ -98,7 +99,8 @@ ], "hour": [ "ம", - "மணி" + "மணி", + "மணிநேரங்கள்" ], "minute": [ "நிமி", @@ -189,7 +191,7 @@ "{0} வா முன்", "{0} வார முன்", "{0} வாரங்களுக்கு முன்", - "{0} வாரத்திற்கு முன்பு" + "{0} வாரத்திற்கு முன்" ], "\\1 year ago": [ "{0} ஆ முன்", diff --git a/dateparser_data/cldr_language_data/date_translation_data/te.json b/dateparser_data/cldr_language_data/date_translation_data/te.json index cd42b1c92..5383409fd 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/te.json +++ b/dateparser_data/cldr_language_data/date_translation_data/te.json @@ -92,15 +92,15 @@ "వారము" ], "day": [ - "ది", - "దినం" + "దినం", + "రోజు" ], "hour": [ "గం", - "గంట" + "గంట", + "గంటలు" ], "minute": [ - "ని", "నిమి", "నిమిషము" ], @@ -128,6 +128,8 @@ "ఈ వారం" ], "0 year ago": [ + "ఈ సం", + "ఈ సంవ", "ఈ సంవత్సరం" ], "1 day ago": [ @@ -140,6 +142,8 @@ "గత వారం" ], "1 year ago": [ + "గత సం", + "గత సంవ", "గత సంవత్సరం" ], "in 1 day": [ @@ -152,6 +156,8 @@ "తదుపరి వారం" ], "in 1 year": [ + "తదుపరి సం", + "తదుపరి సంవ", "తదుపరి సంవత్సరం" ] }, @@ -209,7 +215,8 @@ "in \\1 second": [ "{0} సెక లో", "{0} సెకనులో", - "{0} సెకన్లలో" + "{0} సెకన్లలో", + "{0} సెకలో" ], "in \\1 week": [ "{0} వారంలో", @@ -217,6 +224,7 @@ ], "in \\1 year": [ "{0} సంలో", + "{0} సంల్లో", "{0} సంవత్సరంలో", "{0} సంవత్సరాల్లో" ] diff --git a/dateparser_data/cldr_language_data/date_translation_data/teo.json b/dateparser_data/cldr_language_data/date_translation_data/teo.json index def3c9aa7..746fa5e16 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/teo.json +++ b/dateparser_data/cldr_language_data/date_translation_data/teo.json @@ -96,7 +96,8 @@ "aparan" ], "hour": [ - "esaa" + "esaa", + "hr" ], "minute": [ "idakika" diff --git a/dateparser_data/cldr_language_data/date_translation_data/th.json b/dateparser_data/cldr_language_data/date_translation_data/th.json index b0e2e20b9..c46029fb2 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/th.json +++ b/dateparser_data/cldr_language_data/date_translation_data/th.json @@ -78,9 +78,11 @@ "อา" ], "am": [ + "am", "ก่อนเที่ยง" ], "pm": [ + "pm", "หลังเที่ยง" ], "year": [ @@ -100,7 +102,6 @@ "ชั่วโมง" ], "minute": [ - "น", "นาที" ], "second": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/ti.json b/dateparser_data/cldr_language_data/date_translation_data/ti.json index 11ea5f0ee..a519add75 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ti.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ti.json @@ -52,7 +52,6 @@ "ሰኑይ" ], "tuesday": [ - "ሠሉስ", "ሰሉ", "ሰሉስ" ], @@ -62,8 +61,7 @@ ], "thursday": [ "ሓሙ", - "ሓሙስ", - "ኃሙስ" + "ሓሙስ" ], "friday": [ "ዓር", @@ -78,77 +76,124 @@ "ሰንበት" ], "am": [ - "ንጉሆ ሰዓተ" + "ቅቀ" ], "pm": [ - "ድሕር ሰዓት" + "ድቀ" ], "year": [ - "year" + "ዓመት" ], "month": [ - "month" + "ወርሒ" ], "week": [ - "week" + "ሰሙን" ], "day": [ - "day" + "መዓልቲ" ], "hour": [ - "hour" + "hr", + "ሰዓት" ], "minute": [ - "minute" + "ደቒ", + "ደቒቕ" ], "second": [ - "second" + "ካልኢት" ], "relative-type": { "0 day ago": [ - "today" + "ሎሚ" ], "0 hour ago": [ - "this hour" + "ኣብዚ ሰዓት" ], "0 minute ago": [ - "this minute" + "ኣብዚ ደቒቕ" ], "0 month ago": [ - "this month" + "ህሉው ወርሒ" ], "0 second ago": [ - "now" + "ሕጂ" ], "0 week ago": [ - "this week" + "ህሉው ሰሙን" ], "0 year ago": [ - "this year" + "ሎሚ ዓመት" ], "1 day ago": [ - "yesterday" + "ትማሊ" ], "1 month ago": [ - "last month" + "ዝሓለፈ ወርሒ" ], "1 week ago": [ - "last week" + "ዝሓለፈ ሰሙን" ], "1 year ago": [ - "last year" + "ዓሚ" ], "in 1 day": [ - "tomorrow" + "ጽባሕ" ], "in 1 month": [ - "next month" + "ዝመጽእ ወርሒ" ], "in 1 week": [ - "next week" + "ዝመጽእ ሰሙን" ], "in 1 year": [ - "next year" + "ንዓመታ" + ] + }, + "relative-type-regex": { + "\\1 day ago": [ + "ቅድሚ {0} መዓልቲ", + "ኣብ {0} መዓልቲ" + ], + "\\1 hour ago": [ + "ቅድሚ {0} ሰዓት" + ], + "\\1 minute ago": [ + "ቅድሚ {0} ደቒቕ" + ], + "\\1 month ago": [ + "ቅድሚ {0} ወርሒ" + ], + "\\1 second ago": [ + "ቅድሚ {0} ካልኢት" + ], + "\\1 week ago": [ + "ቅድሚ {0} ሰሙን" + ], + "\\1 year ago": [ + "ቅድሚ {0} ዓ" + ], + "in \\1 day": [ + "ኣብ {0} መዓልቲ" + ], + "in \\1 hour": [ + "ኣብ {0} ሰዓት" + ], + "in \\1 minute": [ + "ኣብ {0} ደቒቕ" + ], + "in \\1 month": [ + "ኣብ {0} ወርሒ" + ], + "in \\1 second": [ + "ኣብ {0} ካልኢት" + ], + "in \\1 week": [ + "ኣብ {0} ሰሙን" + ], + "in \\1 year": [ + "ኣብ {0} ዓ" ] }, "locale_specific": { diff --git a/dateparser_data/cldr_language_data/date_translation_data/to.json b/dateparser_data/cldr_language_data/date_translation_data/to.json index 65b8a6029..bb0ac0a4d 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/to.json +++ b/dateparser_data/cldr_language_data/date_translation_data/to.json @@ -33,8 +33,9 @@ "'aokosi" ], "september": [ - "sep", - "sepitema" + "sepitema", + "sēp", + "sēpitema" ], "october": [ "'oka", @@ -77,81 +78,98 @@ "sāpate" ], "am": [ - "am", "hengihengi", "hh" ], "pm": [ "ea", - "efiafi", - "pm" + "efiafi" ], "year": [ + "t", "ta'u" ], "month": [ + "mh", "māhina" ], "week": [ + "ui", "uike" ], "day": [ + "'a", "'aho" ], "hour": [ + "h", "houa" ], "minute": [ + "m", "miniti" ], "second": [ + "s", "sekoni" ], "relative-type": { "0 day ago": [ - "'ahó ni" + "'ahó ni", + "'ani" ], "0 hour ago": [ - "this hour" + "ko e houa 'eni" ], "0 minute ago": [ - "this minute" + "ko e miniti 'eni" ], "0 month ago": [ + "mhni", "māhiná ni" ], "0 second ago": [ "taimí ni" ], "0 week ago": [ - "uiké ni" + "uiké ni", + "uini" ], "0 year ago": [ - "ta'ú ni" + "ta'ú ni", + "tni" ], "1 day ago": [ + "'ane", "'aneafi" ], "1 month ago": [ + "mh'osi", "māhina kuo'osi" ], "1 week ago": [ + "ui'osi", "uike kuo'osi" ], "1 year ago": [ + "t'osi", "ta'u kuo'osi" ], "in 1 day": [ + "'apo", "'apongipongi" ], "in 1 month": [ + "mhha'u", "māhina kaha'u" ], "in 1 week": [ + "uiha'u", "uike kaha'u" ], "in 1 year": [ - "ta'u kaha'u" + "ta'u kaha'u", + "tha'u" ] }, "relative-type-regex": { diff --git a/dateparser_data/cldr_language_data/date_translation_data/tr.json b/dateparser_data/cldr_language_data/date_translation_data/tr.json index a913750d6..fcb835640 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/tr.json +++ b/dateparser_data/cldr_language_data/date_translation_data/tr.json @@ -125,7 +125,8 @@ "şimdi" ], "0 week ago": [ - "bu hafta" + "bu hafta", + "bu hf" ], "0 year ago": [ "bu yıl" @@ -137,7 +138,8 @@ "geçen ay" ], "1 week ago": [ - "geçen hafta" + "geçen hafta", + "geçen hf" ], "1 year ago": [ "geçen yıl" @@ -149,7 +151,8 @@ "gelecek ay" ], "in 1 week": [ - "gelecek hafta" + "gelecek hafta", + "gelecek hf" ], "in 1 year": [ "gelecek yıl" diff --git a/dateparser_data/cldr_language_data/date_translation_data/twq.json b/dateparser_data/cldr_language_data/date_translation_data/twq.json index 4b6409a72..780cb5333 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/twq.json +++ b/dateparser_data/cldr_language_data/date_translation_data/twq.json @@ -94,7 +94,8 @@ "zaari" ], "hour": [ - "guuru" + "guuru", + "hr" ], "minute": [ "miniti" diff --git a/dateparser_data/cldr_language_data/date_translation_data/tzm.json b/dateparser_data/cldr_language_data/date_translation_data/tzm.json index 1c1d4561d..69ec3fcb7 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/tzm.json +++ b/dateparser_data/cldr_language_data/date_translation_data/tzm.json @@ -96,6 +96,7 @@ "ass" ], "hour": [ + "hr", "tasragt" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/ug.json b/dateparser_data/cldr_language_data/date_translation_data/ug.json index ffe747a90..a2e1a3b76 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ug.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ug.json @@ -86,6 +86,7 @@ "كۈن" ], "hour": [ + "hr", "سائەت" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/uk.json b/dateparser_data/cldr_language_data/date_translation_data/uk.json index e0f1e321f..df31cb436 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/uk.json +++ b/dateparser_data/cldr_language_data/date_translation_data/uk.json @@ -17,19 +17,16 @@ "березня" ], "april": [ - "кві", "квіт", "квітень", "квітня" ], "may": [ - "тра", "трав", "травень", "травня" ], "june": [ - "чер", "черв", "червень", "червня" @@ -40,7 +37,6 @@ "липня" ], "august": [ - "сер", "серп", "серпень", "серпня" @@ -51,19 +47,16 @@ "вересня" ], "october": [ - "жов", "жовт", "жовтень", "жовтня" ], "november": [ - "лис", "лист", "листопад", "листопада" ], "december": [ - "гру", "груд", "грудень", "грудня" @@ -78,6 +71,7 @@ ], "wednesday": [ "середа", + "середу", "ср" ], "thursday": [ @@ -85,15 +79,18 @@ "чт" ], "friday": [ + "п'ятницю", "п'ятниця", "пт" ], "saturday": [ "сб", - "субота" + "субота", + "суботу" ], "sunday": [ "нд", + "неділю", "неділя" ], "am": [ @@ -107,10 +104,12 @@ "рік" ], "month": [ + "м", "міс", "місяць" ], "week": [ + "т", "тиж", "тиждень" ], @@ -120,7 +119,8 @@ ], "hour": [ "год", - "година" + "година", + "години" ], "minute": [ "хв", @@ -141,6 +141,7 @@ "цієї хвилини" ], "0 month ago": [ + "цього міс", "цього місяця" ], "0 second ago": [ @@ -150,36 +151,43 @@ "цього тижня" ], "0 year ago": [ - "цього року" + "цього року", + "цьогоріч" ], "1 day ago": [ "учора" ], "1 month ago": [ + "мин міс", "минулого місяця" ], "1 week ago": [ + "мин тижня", "минулого тижня" ], "1 year ago": [ + "минулого року", "торік" ], "in 1 day": [ "завтра" ], "in 1 month": [ + "наст міс", "наступного місяця" ], "in 1 week": [ + "наст тижня", "наступного тижня" ], "in 1 year": [ + "наст р", + "наст року", "наступного року" ] }, "relative-type-regex": { "\\1 day ago": [ - "{0} д тому", "{0} день тому", "{0} дн тому", "{0} дня тому" @@ -215,7 +223,7 @@ "{0} рік тому" ], "in \\1 day": [ - "за {0} д", + "за {0} дн", "через {0} день", "через {0} дн", "через {0} дня" diff --git a/dateparser_data/cldr_language_data/date_translation_data/ur.json b/dateparser_data/cldr_language_data/date_translation_data/ur.json index 1d263702d..604b29163 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/ur.json +++ b/dateparser_data/cldr_language_data/date_translation_data/ur.json @@ -38,7 +38,7 @@ "دسمبر" ], "monday": [ - "سوموار" + "پیر" ], "tuesday": [ "منگل" @@ -78,7 +78,8 @@ "دن" ], "hour": [ - "گھنٹہ" + "گھنٹہ", + "گھنٹے" ], "minute": [ "منٹ" @@ -97,6 +98,7 @@ "اس منٹ" ], "0 month ago": [ + "اس ماہ", "اس مہینہ" ], "0 second ago": [ @@ -112,10 +114,12 @@ "گزشتہ کل" ], "1 month ago": [ - "پچھلے مہینہ" + "پچھلے مہینہ", + "گزشتہ ماہ" ], "1 week ago": [ - "پچھلے ہفتہ" + "پچھلے ہفتہ", + "گزشتہ ہفتے" ], "1 year ago": [ "گزشتہ سال" @@ -124,10 +128,13 @@ "آئندہ کل" ], "in 1 month": [ + "اگلا مہینہ", + "اگلے ماہ", "اگلے مہینہ" ], "in 1 week": [ - "اگلے ہفتہ" + "اگلے ہفتہ", + "اگلے ہفتے" ], "in 1 year": [ "اگلے سال" @@ -167,7 +174,6 @@ ], "in \\1 hour": [ "{0} گھنٹوں میں", - "{0} گھنٹہ میں", "{0} گھنٹے میں" ], "in \\1 minute": [ @@ -192,21 +198,9 @@ "locale_specific": { "ur-IN": { "name": "ur-IN", - "monday": [ - "پیر" - ], "relative-type": { - "0 month ago": [ - "اس ماہ" - ], - "1 month ago": [ - "گزشتہ ماہ" - ], "1 week ago": [ "گزشتہ ہفتہ" - ], - "in 1 month": [ - "اگلے ماہ" ] }, "relative-type-regex": { diff --git a/dateparser_data/cldr_language_data/date_translation_data/uz-Arab.json b/dateparser_data/cldr_language_data/date_translation_data/uz-Arab.json index d72c229cf..a45ecc889 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/uz-Arab.json +++ b/dateparser_data/cldr_language_data/date_translation_data/uz-Arab.json @@ -94,7 +94,8 @@ "day" ], "hour": [ - "hour" + "hour", + "hr" ], "minute": [ "minute" diff --git a/dateparser_data/cldr_language_data/date_translation_data/uz-Cyrl.json b/dateparser_data/cldr_language_data/date_translation_data/uz-Cyrl.json index 24f46bebd..5154d79b2 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/uz-Cyrl.json +++ b/dateparser_data/cldr_language_data/date_translation_data/uz-Cyrl.json @@ -93,6 +93,7 @@ "кун" ], "hour": [ + "hr", "соат" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/uz-Latn.json b/dateparser_data/cldr_language_data/date_translation_data/uz-Latn.json index f1a957bfb..701beabe1 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/uz-Latn.json +++ b/dateparser_data/cldr_language_data/date_translation_data/uz-Latn.json @@ -116,12 +116,14 @@ "shu daqiqada" ], "0 month ago": [ + "bu oy", "shu oy" ], "0 second ago": [ "hozir" ], "0 week ago": [ + "bu hafta", "shu hafta" ], "0 year ago": [ @@ -138,7 +140,7 @@ "o‘tgan hafta" ], "1 year ago": [ - "o'tgan yil", + "o‘'tgan yil", "o‘tgan yil" ], "in 1 day": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/uz.json b/dateparser_data/cldr_language_data/date_translation_data/uz.json index 220e5cf7e..5c0cdae17 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/uz.json +++ b/dateparser_data/cldr_language_data/date_translation_data/uz.json @@ -116,12 +116,14 @@ "shu daqiqada" ], "0 month ago": [ + "bu oy", "shu oy" ], "0 second ago": [ "hozir" ], "0 week ago": [ + "bu hafta", "shu hafta" ], "0 year ago": [ @@ -138,7 +140,7 @@ "o‘tgan hafta" ], "1 year ago": [ - "o'tgan yil", + "o‘'tgan yil", "o‘tgan yil" ], "in 1 day": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/vun.json b/dateparser_data/cldr_language_data/date_translation_data/vun.json index 821accca1..91754d8b7 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/vun.json +++ b/dateparser_data/cldr_language_data/date_translation_data/vun.json @@ -95,6 +95,7 @@ "mfiri" ], "hour": [ + "hr", "saa" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/wae.json b/dateparser_data/cldr_language_data/date_translation_data/wae.json index 11f6f0837..347c280b8 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/wae.json +++ b/dateparser_data/cldr_language_data/date_translation_data/wae.json @@ -96,7 +96,8 @@ "tag" ], "hour": [ - "schtund" + "schtund", + "stunde" ], "minute": [ "mínütta" diff --git a/dateparser_data/cldr_language_data/date_translation_data/xog.json b/dateparser_data/cldr_language_data/date_translation_data/xog.json index b2eb9eaa5..9a06bb987 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/xog.json +++ b/dateparser_data/cldr_language_data/date_translation_data/xog.json @@ -96,7 +96,8 @@ "olunaku" ], "hour": [ - "essawa" + "essawa", + "hr" ], "minute": [ "edakiika" diff --git a/dateparser_data/cldr_language_data/date_translation_data/yav.json b/dateparser_data/cldr_language_data/date_translation_data/yav.json index 2dec2f135..aad395626 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/yav.json +++ b/dateparser_data/cldr_language_data/date_translation_data/yav.json @@ -96,6 +96,7 @@ "puɔ́sɛ́" ], "hour": [ + "hr", "kisikɛl," ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/yi.json b/dateparser_data/cldr_language_data/date_translation_data/yi.json index c193cd56f..fc6b4f77c 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/yi.json +++ b/dateparser_data/cldr_language_data/date_translation_data/yi.json @@ -85,6 +85,7 @@ "טאָג" ], "hour": [ + "hr", "שעה" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/yo.json b/dateparser_data/cldr_language_data/date_translation_data/yo.json index 656657a63..54a0defce 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/yo.json +++ b/dateparser_data/cldr_language_data/date_translation_data/yo.json @@ -3,75 +3,106 @@ "date_order": "DMY", "january": [ "oṣù ṣẹ́rẹ́", + "ṣẹ́", + "ṣẹ́r", "ṣẹ́rẹ́" ], "february": [ "oṣù èrèlè", + "èr", + "èrèl", "èrèlè" ], "march": [ "oṣù ẹrẹ̀nà", + "ẹr", + "ẹrẹ̀n", "ẹrẹ̀nà" ], "april": [ "oṣù ìgbé", + "ìg", + "ìgb", "ìgbé" ], "may": [ "oṣù ẹ̀bibi", + "ẹ̀b", + "ẹ̀bi", "ẹ̀bibi" ], "june": [ "oṣù òkúdu", + "òk", + "òkú", "òkúdu" ], "july": [ + "ag", + "agẹ", "agẹmọ", "oṣù agẹmọ" ], "august": [ "oṣù ògún", + "òg", + "ògú", "ògún" ], "september": [ + "ow", + "owe", "owewe", "oṣù owewe" ], "october": [ "oṣù ọ̀wàrà", + "ọ̀w", + "ọ̀wà", "ọ̀wàrà" ], "november": [ + "bé", + "bél", "bélú", "oṣù bélú" ], "december": [ "oṣù ọ̀pẹ̀", + "ọ̀p", + "ọ̀pẹ", "ọ̀pẹ̀" ], "monday": [ + "aj", "ajé", "ọjọ́ ajé" ], "tuesday": [ + "ìsẹ́g", "ìsẹ́gun", "ọjọ́ ìsẹ́gun" ], "wednesday": [ + "ọjọ́r", "ọjọ́rú" ], "thursday": [ + "ọjọ́b", "ọjọ́bọ" ], "friday": [ + "ẹt", "ẹtì", "ọjọ́ ẹtì" ], "saturday": [ + "àbám", "àbámẹ́ta", "ọjọ́ àbámẹ́ta" ], "sunday": [ + "àìk", "àìkú", "ọjọ́ àìkú" ], @@ -85,15 +116,17 @@ "ọdún" ], "month": [ - "osù" + "osù", + "oṣù" ], "week": [ - "ọ̀sè" + "ọ̀sẹ̀" ], "day": [ "ọjọ́" ], "hour": [ + "wkt", "wákàtí" ], "minute": [ @@ -113,40 +146,43 @@ "this minute" ], "0 month ago": [ - "this month" + "oṣù yìí" ], "0 second ago": [ "now" ], "0 week ago": [ - "this week" + "ọ̀sẹ̀ yìí" ], "0 year ago": [ - "this year" + "ọdún yìí", + "ọdúnǹí" ], "1 day ago": [ "àná" ], "1 month ago": [ - "last month" + "óṣù tó kọjá" ], "1 week ago": [ - "last week" + "ọ̀sẹ̀ tó kọjá" ], "1 year ago": [ - "last year" + "èṣín", + "ọdún tó kọjá" ], "in 1 day": [ "ọ̀la" ], "in 1 month": [ - "next month" + "óṣù tó ń bọ̀," ], "in 1 week": [ - "next week" + "ọ́sẹ̀ tó ń bọ̀" ], "in 1 year": [ - "next year" + "àmọ́dún", + "ọdún tó ńbọ̀" ] }, "locale_specific": { @@ -154,6 +190,8 @@ "name": "yo-BJ", "january": [ "oshù shɛ́rɛ́", + "shɛ́", + "shɛ́r", "shɛ́rɛ́" ], "february": [ @@ -161,6 +199,8 @@ ], "march": [ "oshù ɛrɛ̀nà", + "ɛr", + "ɛrɛ̀n", "ɛrɛ̀nà" ], "april": [ @@ -168,12 +208,15 @@ ], "may": [ "oshù ɛ̀bibi", + "ɛ̀b", + "ɛ̀bi", "ɛ̀bibi" ], "june": [ "oshù òkúdu" ], "july": [ + "agɛ", "agɛmɔ", "oshù agɛmɔ" ], @@ -185,6 +228,8 @@ ], "october": [ "oshù ɔ̀wàrà", + "ɔ̀w", + "ɔ̀wà", "ɔ̀wàrà" ], "november": [ @@ -192,23 +237,29 @@ ], "december": [ "oshù ɔ̀pɛ̀", + "ɔ̀p", + "ɔ̀pɛ", "ɔ̀pɛ̀" ], "monday": [ "ɔjɔ́ ajé" ], "tuesday": [ + "ìsɛ́g", "ìsɛ́gun", "ɔjɔ́ ìsɛ́gun" ], "wednesday": [ + "ɔjɔ́r", "ɔjɔ́rú" ], "thursday": [ + "ɔjɔ́b", "ɔjɔ́bɔ" ], "friday": [ "ɔjɔ́ ɛtì", + "ɛt", "ɛtì" ], "saturday": [ @@ -227,8 +278,11 @@ "year": [ "ɔdún" ], + "month": [ + "oshù" + ], "week": [ - "ɔ̀sè" + "ɔ̀sɛ̀" ], "day": [ "ɔjɔ́" @@ -240,8 +294,38 @@ "ìsɛ́jú ààyá" ], "relative-type": { + "0 month ago": [ + "oshù yìí" + ], + "0 week ago": [ + "ɔ̀sɛ̀ yìí" + ], + "0 year ago": [ + "ɔdún yìí", + "ɔdúnǹí" + ], + "1 month ago": [ + "óshù tó kɔjá" + ], + "1 week ago": [ + "ɔ̀sɛ̀ tó kɔjá" + ], + "1 year ago": [ + "èshín", + "ɔdún tó kɔjá" + ], "in 1 day": [ "ɔ̀la" + ], + "in 1 month": [ + "óshù tó ń bɔ̀," + ], + "in 1 week": [ + "ɔ́sɛ̀ tó ń bɔ̀" + ], + "in 1 year": [ + "àmɔ́dún", + "ɔdún tó ńbɔ̀" ] } } diff --git a/dateparser_data/cldr_language_data/date_translation_data/yue.json b/dateparser_data/cldr_language_data/date_translation_data/yue.json index f6e9b0923..922a8d819 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/yue.json +++ b/dateparser_data/cldr_language_data/date_translation_data/yue.json @@ -38,32 +38,25 @@ "12月" ], "monday": [ - "星期一", - "週一" + "星期一" ], "tuesday": [ - "星期二", - "週二" + "星期二" ], "wednesday": [ - "星期三", - "週三" + "星期三" ], "thursday": [ - "星期四", - "週四" + "星期四" ], "friday": [ - "星期五", - "週五" + "星期五" ], "saturday": [ - "星期六", - "週六" + "星期六" ], "sunday": [ - "星期日", - "週日" + "星期日" ], "am": [ "上午" diff --git a/dateparser_data/cldr_language_data/date_translation_data/zgh.json b/dateparser_data/cldr_language_data/date_translation_data/zgh.json index 39cfb14c1..ed0eb0e72 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/zgh.json +++ b/dateparser_data/cldr_language_data/date_translation_data/zgh.json @@ -96,6 +96,7 @@ "ⴰⵙⵙ" ], "hour": [ + "hr", "ⵜⴰⵙⵔⴰⴳⵜ" ], "minute": [ diff --git a/dateparser_data/cldr_language_data/date_translation_data/zh-Hant.json b/dateparser_data/cldr_language_data/date_translation_data/zh-Hant.json index f6a313957..cf6f7b9b2 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/zh-Hant.json +++ b/dateparser_data/cldr_language_data/date_translation_data/zh-Hant.json @@ -212,9 +212,6 @@ "1 day ago": [ "昨日" ], - "1 month ago": [ - "上月" - ], "1 week ago": [ "上星期" ], @@ -224,9 +221,6 @@ "in 1 day": [ "明日" ], - "in 1 month": [ - "下月" - ], "in 1 week": [ "下星期" ], @@ -253,7 +247,7 @@ ], "\\1 week ago": [ "{0} 星期前", - "{0}週前" + "{0}星期前" ], "\\1 year ago": [ "{0}年前" @@ -276,7 +270,7 @@ ], "in \\1 week": [ "{0} 星期後", - "{0}週後" + "{0}星期後" ], "in \\1 year": [ "{0}年後" @@ -311,9 +305,6 @@ "1 day ago": [ "昨日" ], - "1 month ago": [ - "上月" - ], "1 week ago": [ "上星期" ], @@ -323,9 +314,6 @@ "in 1 day": [ "明日" ], - "in 1 month": [ - "下月" - ], "in 1 week": [ "下星期" ], @@ -352,7 +340,7 @@ ], "\\1 week ago": [ "{0} 星期前", - "{0}週前" + "{0}星期前" ], "\\1 year ago": [ "{0}年前" @@ -375,7 +363,7 @@ ], "in \\1 week": [ "{0} 星期後", - "{0}週後" + "{0}星期後" ], "in \\1 year": [ "{0}年後" diff --git a/dateparser_data/cldr_language_data/date_translation_data/zu.json b/dateparser_data/cldr_language_data/date_translation_data/zu.json index 3dc90ca99..5a1daccc4 100644 --- a/dateparser_data/cldr_language_data/date_translation_data/zu.json +++ b/dateparser_data/cldr_language_data/date_translation_data/zu.json @@ -3,8 +3,7 @@ "date_order": "MDY", "january": [ "jan", - "januwari", - "umasingana" + "januwari" ], "february": [ "feb", @@ -97,6 +96,7 @@ "usuku" ], "hour": [ + "amahora", "ihora" ], "minute": [ diff --git a/dateparser_data/settings.py b/dateparser_data/settings.py index edf3c4a71..bc2480295 100644 --- a/dateparser_data/settings.py +++ b/dateparser_data/settings.py @@ -1,3 +1,5 @@ +from dateparser._parts_of_day import PartsOfDay + default_parsers = [ "timestamp", "relative-time", @@ -9,6 +11,7 @@ # Date order "DATE_ORDER": "MDY", "PREFER_LOCALE_DATE_ORDER": True, + "STRICT_DATE_ORDER": "none", # Timezone related "TIMEZONE": "local", "TO_TIMEZONE": False, @@ -24,6 +27,7 @@ "SKIP_TOKENS": ["t"], "NORMALIZE": True, "DEFAULT_LANGUAGES": [], + "USE_GIVEN_LANGUAGE_ORDER": False, # Optional language detection "LANGUAGE_DETECTION_CONFIDENCE_THRESHOLD": 0.5, # Time span settings @@ -32,6 +36,8 @@ "DEFAULT_DAYS_IN_MONTH": 30, # Other settings "RETURN_TIME_AS_PERIOD": False, + "PARTS_OF_DAY": PartsOfDay(), "PARSERS": default_parsers, + "IGNORE_SURROUNDING_TEXT": False, "CACHE_SIZE_LIMIT": 1000, } diff --git a/dateparser_data/supplementary_language_data/date_translation_data/af.yaml b/dateparser_data/supplementary_language_data/date_translation_data/af.yaml new file mode 100644 index 000000000..115674aaa --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/af.yaml @@ -0,0 +1,10 @@ +second: + - sek +relative-type: + 0 week ago: + - vandeesweek +relative-type-regex: + \1 second ago: + - (\d+[.,]?\d*) sek gelede + in \1 second: + - oor (\d+[.,]?\d*) sek diff --git a/dateparser_data/supplementary_language_data/date_translation_data/am.yaml b/dateparser_data/supplementary_language_data/date_translation_data/am.yaml new file mode 100644 index 000000000..0f1c379ed --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/am.yaml @@ -0,0 +1,6 @@ +january: + - ጃንዩ + - ጃንዩወሪ +february: + - ፌብሩ + - ፌብሩወሪ diff --git a/dateparser_data/supplementary_language_data/date_translation_data/ar.yaml b/dateparser_data/supplementary_language_data/date_translation_data/ar.yaml index 3c31b7223..aa5442b98 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/ar.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/ar.yaml @@ -1,13 +1,27 @@ -sentence_splitter_group : 6 +locale_specific: + ar-IQ: + october: + - تشرین الأول +sentence_splitter_group: 6 skip: ["الساعة", "في", "مساءً", "هـ"] +june: + - يونيه + - يونية +july: + - يوليه + - يولية + monday: - الإثنين +friday: + - الجمعه year: - عام - سنة + - السنه month: - شهر week: @@ -22,6 +36,7 @@ minute: - دقائق second: - ثانية + - ثانيه ago: - منذ @@ -42,3 +57,13 @@ relative-type: - ساعتين 1 hour ago: - ساعة واحدة + +simplifications: + # The numeral "1" is optional: a bare unit means "1 unit" ago + - '(?<=(قبل|منذ)\s+)أسبوع\b': '1 أسبوع' + - '(?<=(قبل|منذ)\s+)شهر\b': '1 شهر' + - '(?<=(قبل|منذ)\s+)سنة\b': '1 سنة' + - '(?<=(قبل|منذ)\s+)يوم\b': '1 يوم' + - '(?<=(قبل|منذ)\s+)ساعة\b': '1 ساعة' + - '(?<=(قبل|منذ)\s+)دقيقة\b': '1 دقيقة' + - '(?<=(قبل|منذ)\s+)ثانية\b': '1 ثانية' diff --git a/dateparser_data/supplementary_language_data/date_translation_data/as.yaml b/dateparser_data/supplementary_language_data/date_translation_data/as.yaml new file mode 100644 index 000000000..bbb2ca974 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/as.yaml @@ -0,0 +1,42 @@ +thursday: + - বৃহষ্পতি + - বৃহষ্পতিবাৰ +sunday: + - ৰবি +may: + - মে +september: + - সেপ্ট +november: + - নভে +december: + - ডিসে +am: + - পূৰ্বাহ্ণ +pm: + - অপৰাহ্ণ +relative-type: + 0 hour ago: + - this hour + 0 minute ago: + - this minute + 0 month ago: + - this month + 0 second ago: + - now + 0 week ago: + - this week + 0 year ago: + - this year + 1 month ago: + - last month + 1 week ago: + - last week + 1 year ago: + - last year + in 1 month: + - next month + in 1 week: + - next week + in 1 year: + - next year diff --git a/dateparser_data/supplementary_language_data/date_translation_data/az-Latn.yaml b/dateparser_data/supplementary_language_data/date_translation_data/az-Latn.yaml new file mode 100644 index 000000000..f992f847b --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/az-Latn.yaml @@ -0,0 +1,4 @@ +june: + - i̇yun +july: + - i̇yul diff --git a/dateparser_data/supplementary_language_data/date_translation_data/az.yaml b/dateparser_data/supplementary_language_data/date_translation_data/az.yaml new file mode 100644 index 000000000..f992f847b --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/az.yaml @@ -0,0 +1,4 @@ +june: + - i̇yun +july: + - i̇yul diff --git a/dateparser_data/supplementary_language_data/date_translation_data/be.yaml b/dateparser_data/supplementary_language_data/date_translation_data/be.yaml index fba72dd8f..3becfda2c 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/be.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/be.yaml @@ -1,6 +1,11 @@ +relative-type-regex: + \1 day ago: + - (\d+[.,]?\d*) д таму + in \1 day: + - праз (\d+[.,]?\d*) д skip: ["каля", "у", "і", "ў"] -sentence_splitter_group : 1 +sentence_splitter_group: 1 monday: - Пнд @@ -90,3 +95,9 @@ simplifications: - некалькі секунд: 44 секунды - некалькі хвілін: 2 хвіліны - (\d+[.,]?\d*)\s*гадзін\s(\d+[.,]?\d*)\s*хвілін: \1:\2 + + # The numeral "1" is optional: a bare unit means "1 unit" ago + - '(?<=[^\d]\s+|^)тыдзень(?=\s+таму)': '1 тыдзень' + - '(?<=[^\d]\s+|^)месяц(?=\s+таму)': '1 месяц' + - '(?<=[^\d]\s+|^)год(?=\s+таму)': '1 год' + - '(?<=[^\d]\s+|^)дзень(?=\s+таму)': '1 дзень' diff --git a/dateparser_data/supplementary_language_data/date_translation_data/bg.yaml b/dateparser_data/supplementary_language_data/date_translation_data/bg.yaml index f8388135b..3f84ae506 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/bg.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/bg.yaml @@ -1,6 +1,6 @@ skip: ["върху", "до", "на", "около", "от", "под"] -sentence_splitter_group : 1 +sentence_splitter_group: 1 monday: - пон @@ -29,6 +29,7 @@ year: month: - мес - месеци + - м week: - с - сед @@ -60,6 +61,7 @@ relative-type: - след 1 десетилетие 1 week ago: - преди седмица + - миналата седмица 2 day ago: - онзи ден 1 day ago: @@ -78,3 +80,6 @@ simplifications: - един: '1' - два: '2' - три: '3' + + # The numeral "1" is optional: a bare unit means "1 unit" ago + - '(?<=преди\s+)месец\b': '1 месец' diff --git a/dateparser_data/supplementary_language_data/date_translation_data/bn.yaml b/dateparser_data/supplementary_language_data/date_translation_data/bn.yaml index e2a169010..d689886ab 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/bn.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/bn.yaml @@ -1,6 +1,11 @@ +thursday: + - বৃহষ্পতিবার +relative-type-regex: + \1 minute ago: + - (\d+[.,]?\d*) মিনিট পূর্বে skip: ["ই", "এবং", "টা", "প্রায়", "লা", "শে"] -sentence_splitter_group : 3 +sentence_splitter_group: 3 january: - জানুয়ারি diff --git a/dateparser_data/supplementary_language_data/date_translation_data/br.yaml b/dateparser_data/supplementary_language_data/date_translation_data/br.yaml new file mode 100644 index 000000000..08e7da7eb --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/br.yaml @@ -0,0 +1,7 @@ +december: + - ker +relative-type: + 0 hour ago: + - this hour + 0 minute ago: + - this minute diff --git a/dateparser_data/supplementary_language_data/date_translation_data/brx.yaml b/dateparser_data/supplementary_language_data/date_translation_data/brx.yaml new file mode 100644 index 000000000..4c71c74db --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/brx.yaml @@ -0,0 +1,60 @@ +wednesday: + - बुद + - बुदबार +thursday: + - बिसथि + - बिसथिबार +saturday: + - सुनि + - सुनिबार +february: + - फेब्रुवारी +march: + - मार्स +april: + - एफ्रिल +july: + - जुलाइ +august: + - आगस्थ +september: + - सेबथेज्ब़र +october: + - अखथबर +november: + - नबेज्ब़र +december: + - दिसेज्ब़र +week: + - सबथा/हबथा +hour: + - रिंगा +minute: + - मिनिथ +second: + - सेखेन्द +relative-type: + 0 hour ago: + - this hour + 0 minute ago: + - this minute + 0 month ago: + - this month + 0 second ago: + - now + 0 week ago: + - this week + 0 year ago: + - this year + 1 month ago: + - last month + 1 week ago: + - last week + 1 year ago: + - last year + in 1 month: + - next month + in 1 week: + - next week + in 1 year: + - next year diff --git a/dateparser_data/supplementary_language_data/date_translation_data/bs-Cyrl.yaml b/dateparser_data/supplementary_language_data/date_translation_data/bs-Cyrl.yaml new file mode 100644 index 000000000..aee54b750 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/bs-Cyrl.yaml @@ -0,0 +1,149 @@ +august: + - авг + - август +am: + - пријеподне +pm: + - послијеподне + +monday: + - понедјељак + - понедељак + +sunday: + - недјеља + - недеља + +year: + - г + - год + - годинa + +month: + - мј + - мјесец + - мјесеци + - мјесеца + - месец + +week: + - сед + - седмица + - седмице + - недеља + +hour: + - сат + - час + +minute: + - мин + - минута + +second: + - с + - сек + - секунда + +relative-type: + 0 hour ago: + - овај сат + - this hour + 0 minute ago: + - ова минута + - this minute + 0 month ago: + - овај мјесец + - овог месеца + 0 second ago: + - сада + - now + 0 week ago: + - ове седмице + - ове недеље + 1 month ago: + - прошли мјесец + - прошлог месеца + 1 week ago: + - прошле седмице + - прошле недеље + in 1 month: + - сљедећи мјесец + - следећег месеца + in 1 week: + - сљедеће седмице + - следеће недеље + in 1 year: + - сљедеће године + - следеће године + +relative-type-regex: + \1 day ago: + - прије (\d+[.,]?\d*) дан + - прије (\d+[.,]?\d*) дана + - пре (\d+[.,]?\d*) дан + - пре (\d+[.,]?\d*) дана + \1 hour ago: + - прије (\d+[.,]?\d*) сат + - прије (\d+[.,]?\d*) сати + - пре (\d+[.,]?\d*) сат + - пре (\d+[.,]?\d*) сати + \1 minute ago: + - прије (\d+[.,]?\d*) мин + - прије (\d+[.,]?\d*) минута + - прије (\d+[.,]?\d*) минуту + - пре (\d+[.,]?\d*) минут + - пре (\d+[.,]?\d*) минута + \1 month ago: + - прије (\d+[.,]?\d*) мј + - прије (\d+[.,]?\d*) мјесец + - прије (\d+[.,]?\d*) мјесеца + - прије (\d+[.,]?\d*) мјесеци + - пре (\d+[.,]?\d*) месец + - пре (\d+[.,]?\d*) месеци + \1 second ago: + - прије (\d+[.,]?\d*) сек + - прије (\d+[.,]?\d*) секунда + - прије (\d+[.,]?\d*) секунду + - пре (\d+[.,]?\d*) секунд + - пре (\d+[.,]?\d*) секунди + \1 week ago: + - прије (\d+[.,]?\d*) сед + - прије (\d+[.,]?\d*) седмица + - прије (\d+[.,]?\d*) седмице + - прије (\d+[.,]?\d*) седмицу + - пре (\d+[.,]?\d*) недеља + - пре (\d+[.,]?\d*) недељу + \1 year ago: + - прије (\d+[.,]?\d*) г + - прије (\d+[.,]?\d*) год + - прије (\d+[.,]?\d*) година + - прије (\d+[.,]?\d*) годину + - пре (\d+[.,]?\d*) година + - пре (\d+[.,]?\d*) годину + + in \1 minute: + - за (\d+[.,]?\d*) мин + - за (\d+[.,]?\d*) минута + - за (\d+[.,]?\d*) минуту + in \1 month: + - за (\d+[.,]?\d*) мј + - за (\d+[.,]?\d*) мјесец + - за (\d+[.,]?\d*) мјесеца + - за (\d+[.,]?\d*) мјесеци + - за (\d+[.,]?\d*) месец + - за (\d+[.,]?\d*) месеци + in \1 second: + - за (\d+[.,]?\d*) сек + - за (\d+[.,]?\d*) секунда + - за (\d+[.,]?\d*) секунду + in \1 week: + - за (\d+[.,]?\d*) сед + - за (\d+[.,]?\d*) седмица + - за (\d+[.,]?\d*) седмицу + - за (\d+[.,]?\d*) седмице + - за (\d+[.,]?\d*) недеља + - за (\d+[.,]?\d*) недељу + in \1 year: + - за (\d+[.,]?\d*) г + - за (\d+[.,]?\d*) год diff --git a/dateparser_data/supplementary_language_data/date_translation_data/bs-Latn.yaml b/dateparser_data/supplementary_language_data/date_translation_data/bs-Latn.yaml new file mode 100644 index 000000000..28a5480b0 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/bs-Latn.yaml @@ -0,0 +1,3 @@ +august: + - avg + - avgust diff --git a/dateparser_data/supplementary_language_data/date_translation_data/bs.yaml b/dateparser_data/supplementary_language_data/date_translation_data/bs.yaml new file mode 100644 index 000000000..28a5480b0 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/bs.yaml @@ -0,0 +1,3 @@ +august: + - avg + - avgust diff --git a/dateparser_data/supplementary_language_data/date_translation_data/ca.yaml b/dateparser_data/supplementary_language_data/date_translation_data/ca.yaml index 49dd68f5a..b5ed1f2ff 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/ca.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/ca.yaml @@ -23,7 +23,14 @@ relative-type: - la setmana vinent - la pròxima setmana - la propera setmana + - setm vinent + 1 month ago: + - mes passat + 1 week ago: + - setm passada + in 1 month: + - mes vinent simplifications: - una: '1' - un: '1' diff --git a/dateparser_data/supplementary_language_data/date_translation_data/ce.yaml b/dateparser_data/supplementary_language_data/date_translation_data/ce.yaml new file mode 100644 index 000000000..0200c7c82 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/ce.yaml @@ -0,0 +1,21 @@ +monday: + - оршотан де +tuesday: + - шинарин де +wednesday: + - кхаарин де +thursday: + - еарин де +friday: + - пӏераскан де +saturday: + - шот де +sunday: + - кӏиранан де +relative-type: + 0 hour ago: + - this hour + 0 minute ago: + - this minute + 0 second ago: + - now diff --git a/dateparser_data/supplementary_language_data/date_translation_data/chr.yaml b/dateparser_data/supplementary_language_data/date_translation_data/chr.yaml new file mode 100644 index 000000000..e4d3aea1c --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/chr.yaml @@ -0,0 +1,16 @@ +relative-type-regex: + \1 hour ago: + - ꮎꮏ (\d+[.,]?\d*) ꮡꮯ ꮵꭸꮢ + \1 minute ago: + - ꮎꮏ (\d+[.,]?\d*) ꭲꮿꮤ ꮵꭸꮢ + - ꮎꮏ (\d+[.,]?\d*) ꭲꮿꮤꮼꮝꮤꮕ ꮵꭸꮢ + \1 month ago: + - ꮎꮏ (\d+[.,]?\d*) ꭷꮈ ꮵꭸꮢ + - ꮎꮏ (\d+[.,]?\d*) ꭷꮈꭲ ꮵꭸꮢ + - ꮎꮏ (\d+[.,]?\d*) ꮧꭷꮈꭲ ꮵꭸꮢ + \1 week ago: + - ꮎꮏ (\d+[.,]?\d*) ꭲᏻꮎꮩꮣꮖꮝꮧ ꮵꭸꮢ + - ꮎꮏ (\d+[.,]?\d*) ꮢꮎ ꮵꭸꮢ + - ꮎꮏ (\d+[.,]?\d*) ꮢꮎꮩꮣꮖꮝꮧ ꮵꭸꮢ + \1 year ago: + - ꮎꮏ (\d+[.,]?\d*) ꭴꮥ ꮵꭸꮢ diff --git a/dateparser_data/supplementary_language_data/date_translation_data/cs.yaml b/dateparser_data/supplementary_language_data/date_translation_data/cs.yaml index 610478020..645607161 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/cs.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/cs.yaml @@ -1,4 +1,5 @@ -skip: ["přibližně", "v"] +skip: ["přibližně", "v", "ve", "přibližně", "asi", "zhruba", "cca", "kolem", "okolo", "někdy"] + sentence_splitter_group : 1 @@ -9,32 +10,56 @@ tuesday: wednesday: - Stř - Středu + - Středy thursday: - Čtv friday: - Pát + - Pátku saturday: - Sob - Sobotu + - Soboty sunday: - Ned - Neděli +january: + - lednu february: - únr + - únoru +march: + - březnu +april: + - dubnu +may: + - květnu june: - Čer + - červnu july: - Črc + - červenci - črv - +august: + - srpnu +october: + - říjnu +december: + - prosinci year: - roků - roky + - let + - léta + - lety month: - měsíců - měsíce - měsícem + - měsícemi + - měsícema week: - týdnů - týdny @@ -42,32 +67,193 @@ week: day: - dnů - dny + - dnem + - dní + hour: - hodin - hodiny - hodinou - hodinu - hodinami + - hodinama minute: - minut + - minutu + - minutou - minutami - minuty + - minutama second: - sekundy - sekund + - sekundu + - sekundou + - sekundami - vteřina + - vteřinu + - vteřinou - vteřin - vteřiny + - vteřinami ago: - před in: - - ve - - v + # "v" and "ve" is literal translations, but in context of time cz works diferently and uses "za". + - za relative-type: 2 day ago: - předevčírem + 3 day ago: + - předpředevčírem + in 1 day: + - zítřek + - zítřka + in 2 day: + - pozítří + in 3 day: + - popozítří + 0 second ago: + - teď hned + - teď + - okamžitě + - právě teď + +relative-type-regex: + \1 decade ago: + - před (\d+[.,]?\d*) desetiletími + - před (\d+[.,]?\d*) dekádami + - před (\d+[.,]?\d*) dekádou + - před (\d+[.,]?\d*) desetiletím + in \1 decade: + - za (\d+[.,]?\d*) desetiletí + - za (\d+[.,]?\d*) dekád + - za (\d+[.,]?\d*) dekády + - za (\d+[.,]?\d*) dekádu + \1 century ago: + - před (\d+[.,]?\d*) staletími + - před (\d+[.,]?\d*) stoletími + - před (\d+[.,]?\d*) stoletím + in \1 century: + - za (\d+[.,]?\d*) staletí + - za (\d+[.,]?\d*) století simplifications: - - teď: 0 sekunda + # 12-hour modificators + - (o )?půlnoc(i|í)?: 0:00 + - ráno: AM + - dopoledne: AM + - odpoledne: PM + - (pod)?večer: PM + + + # Synonyms + - budoucí(ho)?: příští + - nadcházející(ho)?: příští + - tenhle: tento + - tohle: tento + - letos: tento rok + - vloni: minulý rok + - loni: minulý rok + + # Numbers (Normal) + - jed(en|na|no|ním|ným|nou|noho|né|ný): '1' + - dv(a|ě|ou|ěma): '2' + - tř(i|ech|em|emi): '3' + - čty(r|ř)(i|ech|em|mi): '4' + - pět(i)?: '5' + - šest(i)?: '6' + - sed(u)?m(i)?: '7' + - osm(i)?: '8' + - devět|devíti: '9' + - deset(i)?: '10' + - jedenáct(i)?: '11' + - dvanáct(i)?: '12' + - čtrnáct(i)?: '14' + - dvacet(i)?: '20' + - třicet(i)?: '30' + + # Numbers (Ordinal) + - první(ho|mu|m)?: '1.' + - druh(ý|á|é|ého|ému|ým|ou|ýho): '2.' + - třet(í|ího|ímu|ím): '3.' + - čtvrt(ý|á|é|ého|ému|ým|ou|ýho): '4.' + - pát(ý|á|é|ého|ému|ým|ou|ýho): '5.' + - šest(ý|á|é|ého|ému|ým|ou|ýho): '6.' + - sedm(ý|á|é|ého|ému|ým|ou|ýho): '7.' + - osm(ý|á|é|ého|ému|ým|ou|ýho): '8.' + - devát(ý|á|é|ého|ému|ým|ou|ýho): '9.' + - desát(ý|á|é|ého|ému|ým|ou|ýho): '10.' + - jedenáct(ý|á|ého|ému|ým|ou|ýho|é): '11.' + - dvanáct(ý|á|ého|ému|ým|ou|ýho|é): '12.' + - čtrnáct(ý|á|ého|ému|ým|ou|ýho|é): '14.' + - dvacát(ý|á|ého|ému|ým|ou|ýho|é): '20.' + - třicát(ý|á|ého|ému|ým|ou|ýho|é): '30.' + + # Variant of "1" in places, where czechs would not use the nuber. (e.g. "za 1 hodinu" vs "za hodinu") + - '(?<=(za|před)\s)hodin(u|ou)\b': '1 hodinu' + - '(?<=(za|před)\s)minut(u|ou)\b': '1 minutu' + - '(?<=(za|před)\s)(?:vteřin(u|ou)|sekund(u|ou))\b': '1 sekundu' + - '(?<=(za|před)\s)týdn(em)\b': '1 týden' + - '(?<=(za|před)\s)měsíc(em)\b': '1 měsíc' + - '(?<=(za|před)\s)rok(em)\b': '1 rok' + - '(?<=(za|před)\s)(?:denem|dnem|den)\b': '1 den' + # The numeral "1" is optional: "před týden" means "před 1 týden" + - '(?<=před\s)týden\b': '1 týden' + - '(?<=před\s)měsíc\b': '1 měsíc' + - '(?<=před\s)rok\b': '1 rok' + # Accusative forms used with "za" (e.g. "za týden" = "in a week") + - '(?<=za\s)týden\b': '1 týden' + - '(?<=za\s)měsíc\b': '1 měsíc' + - '(?<=za\s)rok\b': '1 rok' + + # Fractions of hours (For relative time) + - 'čtvrt\s*hodin(y|u)': 15 minut + - 'čtvrt\s*hodinou': 15 minutami + - 'půl\s*hodin(y|u)': 30 minut + - 'půl\s*hodinou': 30 minutami + - 'tři\s*čtvrtě\s*hodin(y|u)': 45 minut + - 'tři\s*čtvrtě\s*hodinou': 45 minutami + + + # Fraction variant of absolute time + - 'čtvrt na 1\.?': '12:15' + - 'čtvrt na 2\.?': '1:15' + - 'čtvrt na 3\.?': '2:15' + - 'čtvrt na 4\.?': '3:15' + - 'čtvrt na 5\.?': '4:15' + - 'čtvrt na 6\.?': '5:15' + - 'čtvrt na 7\.?': '6:15' + - 'čtvrt na 8\.?': '7:15' + - 'čtvrt na 9\.?': '8:15' + - 'čtvrt na 10\.?': '9:15' + - 'čtvrt na 11\.?': '10:15' + - 'čtvrt na 12\.?': '11:15' + + - 'půl 1\.?': '12:30' + - 'půl 2\.?': '1:30' + - 'půl 3\.?': '2:30' + - 'půl 4\.?': '3:30' + - 'půl 5\.?': '4:30' + - 'půl 6\.?': '5:30' + - 'půl 7\.?': '6:30' + - 'půl 8\.?': '7:30' + - 'půl 9\.?': '8:30' + - 'půl 10\.?': '9:30' + - 'půl 11\.?': '10:30' + - 'půl 12\.?': '11:30' + + - 'tři\s*čtvrtě na 1\.?': '12:45' + - 'tři\s*čtvrtě na 2\.?': '1:45' + - 'tři\s*čtvrtě na 3\.?': '2:45' + - 'tři\s*čtvrtě na 4\.?': '3:45' + - 'tři\s*čtvrtě na 5\.?': '4:45' + - 'tři\s*čtvrtě na 6\.?': '5:45' + - 'tři\s*čtvrtě na 7\.?': '6:45' + - 'tři\s*čtvrtě na 8\.?': '7:45' + - 'tři\s*čtvrtě na 9\.?': '8:45' + - 'tři\s*čtvrtě na 10\.?': '9:45' + - 'tři\s*čtvrtě na 11\.?': '10:45' + - 'tři\s*čtvrtě na 12\.?': '11:45' diff --git a/dateparser_data/supplementary_language_data/date_translation_data/cy.yaml b/dateparser_data/supplementary_language_data/date_translation_data/cy.yaml new file mode 100644 index 000000000..501338c41 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/cy.yaml @@ -0,0 +1,2 @@ +day: + - dydd diff --git a/dateparser_data/supplementary_language_data/date_translation_data/da.yaml b/dateparser_data/supplementary_language_data/date_translation_data/da.yaml index 9d8dbcea4..2448417b4 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/da.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/da.yaml @@ -1,6 +1,15 @@ -skip: ["cirka", "d.", "kl", "kl."] +tuesday: + - tir +thursday: + - tor +relative-type: + 0 hour ago: + - i den kommende time + 0 minute ago: + - i det kommende minut +skip: ["cirka", "d.", "den", "kl", "kl."] -sentence_splitter_group : 1 +sentence_splitter_group: 1 month: - måneder @@ -27,10 +36,15 @@ relative-type-regex: \1 minute ago: - for (\d+[.,]?\d*)\s*m - for (\d+[.,]?\d*) minutter + - for (\d+[.,]?\d*) min siden \1 second ago: - for (\d+[.,]?\d*)\s*s - for (\d+[.,]?\d*) sekunder + - for (\d+[.,]?\d*) sek siden + \1 month ago: + - for (\d+[.,]?\d*) md siden + - for (\d+[.,]?\d*) mdr siden simplifications: - en: '1' - et: '1' diff --git a/dateparser_data/supplementary_language_data/date_translation_data/de.yaml b/dateparser_data/supplementary_language_data/date_translation_data/de.yaml index fd2372e3a..3d3159cc4 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/de.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/de.yaml @@ -1,6 +1,10 @@ +am: + - vorm +pm: + - nachm skip: ["etwa", "uhr", "um", "und"] -sentence_splitter_group : 1 +sentence_splitter_group: 1 monday: - Mon diff --git a/dateparser_data/supplementary_language_data/date_translation_data/dsb.yaml b/dateparser_data/supplementary_language_data/date_translation_data/dsb.yaml new file mode 100644 index 000000000..80bb9285f --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/dsb.yaml @@ -0,0 +1,9 @@ +relative-type: + 0 hour ago: + - this hour + 0 minute ago: + - this minute + 1 month ago: + - slědny mjasec + 1 week ago: + - slědny tyźeń diff --git a/dateparser_data/supplementary_language_data/date_translation_data/el.yaml b/dateparser_data/supplementary_language_data/date_translation_data/el.yaml new file mode 100644 index 000000000..d3fa5578a --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/el.yaml @@ -0,0 +1,14 @@ +hour: + - ώρ +relative-type: + 0 hour ago: + - αυτήν την ώρα + 0 minute ago: + - αυτό το λεπτό + 0 week ago: + - αυτήν την εβδομάδα +relative-type-regex: + \1 hour ago: + - πριν από (\d+[.,]?\d*) ώρ + in \1 hour: + - σε (\d+[.,]?\d*) ώρ diff --git a/dateparser_data/supplementary_language_data/date_translation_data/en.yaml b/dateparser_data/supplementary_language_data/date_translation_data/en.yaml index 9e888f388..624128e04 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/en.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/en.yaml @@ -1,4 +1,4 @@ -skip: ["about", "ad", "and", "at", "by", "just", "m", "nd", "of", "on", "rd", "st", "th", "the"] +skip: ["about", "ad", "and", "at", "by", "from", "just", "m", "nd", "of", "on", "rd", "st", "th", "the"] pertain: ["of"] sentence_splitter_group : 1 @@ -54,6 +54,19 @@ second: - seconds - secs +early_morning: + - early morning + - small hours + - wee hours +morning: + - morning +afternoon: + - afternoon +evening: + - evening +night: + - night + ago: - ago - before @@ -76,20 +89,29 @@ relative-type: - till date relative-type-regex: + in \1 week: + - in {0} weeks time + - "in {0} weeks' time" in \1 decade: - in (\d+[.,]?\d*) decades? \1 decade ago: - (\d+[.,]?\d*) decades? ago simplifications: + - (\d+[.,]?\d*)\s*mons?\b: \1 month - an: '1' - a: '1' - (?:12\s+)?noon: '12:00' - (?:12\s+)?midnight: '00:00' + - tonight: today night + - last night: yesterday night + - this ((?:early )?morning|afternoon|evening|night): today \1 + - in the ((?:early )?morning|afternoon|evening|night|small hours|wee hours): \1 - (\d+[.,]?\d*)h(\d+[.,]?\d*): \1:\2 - - (?<=from\s+)now: in + - from\s+now: in - less than 1 minute ago: 45 second ago - - (\d+[.,]?\d*) (decade|year|month|week|day|hour|minute|second)s? later: in \1 \2 + - (\d+(?:st|nd|rd|th)) day: \1 + - (\d+[.,]?\d*|one|two|three|four|five|six|seven|eight|nine|ten|eleven|twelve) (decade|year|month|week|day|hour|minute|second)s? later: in \1 \2 - one: '1' - two: '2' - three: '3' @@ -102,3 +124,8 @@ simplifications: - ten: '10' - eleven: '11' - twelve: '12' + +locale_specific: + en-US: + name: en-US + date_order: MDY diff --git a/dateparser_data/supplementary_language_data/date_translation_data/es.yaml b/dateparser_data/supplementary_language_data/date_translation_data/es.yaml index e83ef7a55..da79c96e6 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/es.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/es.yaml @@ -1,7 +1,66 @@ skip: ["a las", "cerca", "de", "del", "en", "y"] pertain: ["de", "del"] +locale_specific: + es-419: + september: + - sep + es-AR: + september: + - sep + es-BO: + september: + - sep + es-BR: + september: + - sep + es-BZ: + september: + - sep + es-CL: + september: + - sep + es-CO: + september: + - sep + es-CR: + september: + - sep + es-CU: + september: + - sep + es-DO: + september: + - sep + es-EC: + september: + - sep + es-GT: + september: + - sep + es-HN: + september: + - sep + es-MX: + relative-type-regex: + in \1 minute: + - en (\d+[.,]?\d*) min + es-NI: + september: + - sep + es-PA: + september: + - sep + es-PR: + september: + - sep + es-SV: + september: + - sep + es-US: + september: + - sep -sentence_splitter_group : 2 +sentence_splitter_group: 2 monday: - Lu @@ -36,6 +95,10 @@ minute: second: - segundos +early_morning: + - de madrugada + - madrugada + ago: - hace in: @@ -46,5 +109,7 @@ relative-type: - anteayer simplifications: + - esta madrugada: hoy madrugada + - (?:de|por|en) la madrugada: madrugada - una: '1' - un: '1' diff --git a/dateparser_data/supplementary_language_data/date_translation_data/eu.yaml b/dateparser_data/supplementary_language_data/date_translation_data/eu.yaml new file mode 100644 index 000000000..73ff8a013 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/eu.yaml @@ -0,0 +1,13 @@ +relative-type: + 0 month ago: + - hilabete hau + 0 week ago: + - aste hau + 1 month ago: + - aurreko hilabetea + 1 week ago: + - aurreko astea + in 1 month: + - hurrengo hilabetea + in 1 week: + - hurrengo astea diff --git a/dateparser_data/supplementary_language_data/date_translation_data/fa.yaml b/dateparser_data/supplementary_language_data/date_translation_data/fa.yaml index eb938a5e5..06986fe1a 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/fa.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/fa.yaml @@ -1,4 +1,7 @@ -sentence_splitter_group : 6 +relative-type: + 1 month ago: + - ماه پیش +sentence_splitter_group: 6 tuesday: - سهشنبه diff --git a/dateparser_data/supplementary_language_data/date_translation_data/ff.yaml b/dateparser_data/supplementary_language_data/date_translation_data/ff.yaml new file mode 100644 index 000000000..f93beebd6 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/ff.yaml @@ -0,0 +1,7 @@ +locale_specific: + ff-CM: + name: ff-CM + ff-GN: + name: ff-GN + ff-MR: + name: ff-MR diff --git a/dateparser_data/supplementary_language_data/date_translation_data/fi.yaml b/dateparser_data/supplementary_language_data/date_translation_data/fi.yaml index 71e5fd24f..c39d777cd 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/fi.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/fi.yaml @@ -1,4 +1,4 @@ -skip: [":n"] +skip: [":n", "klo"] sentence_splitter_group : 1 @@ -76,3 +76,10 @@ relative-type: simplifications: - (\d+[.,]?\d*) (sekunnin|sekuntin|minuutin|tunnin|päivän|viikon|kuukauden|vuoden) (päästä|kuluttua): \3 \1 \2 + + # The numeral "1" is optional: a bare unit means "1 unit" ago + - '(?<=[^\d]\s+|^)viikko(?=\s+sitten)': '1 viikko' + - '(?<=[^\d]\s+|^)kuukausi(?=\s+sitten)': '1 kuukausi' + - '(?<=[^\d]\s+|^)vuosi(?=\s+sitten)': '1 vuosi' + - '(?<=[^\d]\s+|^)päivä(?=\s+sitten)': '1 päivä' + - '(?<=[^\d]\s+|^)tunti(?=\s+sitten)': '1 tunti' diff --git a/dateparser_data/supplementary_language_data/date_translation_data/fil.yaml b/dateparser_data/supplementary_language_data/date_translation_data/fil.yaml new file mode 100644 index 000000000..de34e0e6a --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/fil.yaml @@ -0,0 +1,5 @@ +relative-type-regex: + \1 hour ago: + - (\d+[.,]?\d*) oras nakalipas + \1 second ago: + - (\d+[.,]?\d*) seg nakalipas diff --git a/dateparser_data/supplementary_language_data/date_translation_data/fr.yaml b/dateparser_data/supplementary_language_data/date_translation_data/fr.yaml index 6e469ee5c..acd8f96f0 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/fr.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/fr.yaml @@ -1,6 +1,13 @@ +relative-type-regex: + \1 hour ago: + - il y a (\d+[.,]?\d*)h + \1 minute ago: + - il y a (\d+[.,]?\d*)min + in \1 hour: + - dans (\d+[.,]?\d*)h skip: ["environ", "er", "et", "le", "à"] -sentence_splitter_group : 1 +sentence_splitter_group: 1 monday: - lu diff --git a/dateparser_data/supplementary_language_data/date_translation_data/ga.yaml b/dateparser_data/supplementary_language_data/date_translation_data/ga.yaml new file mode 100644 index 000000000..9caaa2ac5 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/ga.yaml @@ -0,0 +1,11 @@ +am: + - am +pm: + - pm +relative-type: + 0 year ago: + - an bhl seo + - an bhliain seo +relative-type-regex: + in \1 year: + - i gceann (\d+[.,]?\d*) bhliain diff --git a/dateparser_data/supplementary_language_data/date_translation_data/gd.yaml b/dateparser_data/supplementary_language_data/date_translation_data/gd.yaml new file mode 100644 index 000000000..a98389fdc --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/gd.yaml @@ -0,0 +1,5 @@ +relative-type: + 0 hour ago: + - this hour + 0 minute ago: + - this minute diff --git a/dateparser_data/supplementary_language_data/date_translation_data/gl.yaml b/dateparser_data/supplementary_language_data/date_translation_data/gl.yaml new file mode 100644 index 000000000..12f9d59d2 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/gl.yaml @@ -0,0 +1,47 @@ +year: + - a +month: + - m +day: + - d +relative-type: + 0 hour ago: + - nesta hora + 0 minute ago: + - neste minuto + 0 month ago: + - este m + 1 month ago: + - m pasado + 1 week ago: + - sem pasada + 1 year ago: + - ano pasado + in 1 month: + - m seguinte + in 1 week: + - sem seguinte + in 1 year: + - seguinte ano +relative-type-regex: + \1 day ago: + - hai (\d+[.,]?\d*) d + \1 month ago: + - hai (\d+[.,]?\d*) m + \1 year ago: + - hai (\d+[.,]?\d*) a + in \1 day: + - en (\d+[.,]?\d*) d + in \1 month: + - en (\d+[.,]?\d*) m + in \1 year: + - en (\d+[.,]?\d*) a + +early_morning: + - de madrugada + - na madrugada + - pola madrugada + - madrugada + +simplifications: + - esta madrugada: hoxe madrugada diff --git a/dateparser_data/supplementary_language_data/date_translation_data/gu.yaml b/dateparser_data/supplementary_language_data/date_translation_data/gu.yaml new file mode 100644 index 000000000..95469fa2b --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/gu.yaml @@ -0,0 +1,3 @@ +relative-type-regex: + \1 year ago: + - (\d+[.,]?\d*) વર્ષ પહેલા diff --git a/dateparser_data/supplementary_language_data/date_translation_data/ha.yaml b/dateparser_data/supplementary_language_data/date_translation_data/ha.yaml new file mode 100644 index 000000000..adf846938 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/ha.yaml @@ -0,0 +1,29 @@ +am: + - am +pm: + - pm +relative-type: + 0 hour ago: + - this hour + 0 minute ago: + - this minute + 0 month ago: + - this month + 0 second ago: + - now + 0 week ago: + - this week + 0 year ago: + - this year + 1 month ago: + - last month + 1 week ago: + - last week + 1 year ago: + - last year + in 1 month: + - next month + in 1 week: + - next week + in 1 year: + - next year diff --git a/dateparser_data/supplementary_language_data/date_translation_data/he.yaml b/dateparser_data/supplementary_language_data/date_translation_data/he.yaml index dcb4fab94..ce96acfb9 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/he.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/he.yaml @@ -1,4 +1,9 @@ -sentence_splitter_group : 1 +relative-type-regex: + \1 day ago: + - לפני (\d+[.,]?\d*) ימ׳ + in \1 day: + - בעוד (\d+[.,]?\d*) ימ׳ +sentence_splitter_group: 1 skip: ["ב-", "בסביבות", "בערך", "בקירוב", "בשעה", "ה-"] @@ -121,3 +126,11 @@ simplifications: - אחה"צ: pm - לפנות ערב: pm - בערב: pm + + # The numeral "1" is optional: a bare unit means "1 unit" ago + - '(?<=לפני\s+)שבוע\b': '1 שבוע' + - '(?<=לפני\s+)חודש\b': '1 חודש' + - '(?<=לפני\s+)שנה\b': '1 שנה' + - '(?<=לפני\s+)יום\b': '1 יום' + - '(?<=לפני\s+)שעה\b': '1 שעה' + - '(?<=לפני\s+)דקה\b': '1 דקה' diff --git a/dateparser_data/supplementary_language_data/date_translation_data/hi.yaml b/dateparser_data/supplementary_language_data/date_translation_data/hi.yaml index 4047c7e8a..bf4e9392a 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/hi.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/hi.yaml @@ -1,6 +1,12 @@ +minute: + - मि +am: + - पूर्वाह्न +pm: + - अपराह्न skip: ["के", "को", "बजे", "सन्", "से"] -sentence_splitter_group : 3 +sentence_splitter_group: 3 september: - सितम्बर @@ -24,6 +30,7 @@ day: - दिवस hour: - घंटे + - घं ago: - पहले @@ -47,3 +54,15 @@ relative-type-regex: - (\d+[.,]?\d*) दशक पहले + \1 hour ago: + - (\d+[.,]?\d*) घं पहले + \1 minute ago: + - (\d+[.,]?\d*) मि पहले + \1 second ago: + - (\d+[.,]?\d*) से पहले + in \1 hour: + - (\d+[.,]?\d*) घं में + in \1 minute: + - (\d+[.,]?\d*) मि में + in \1 second: + - (\d+[.,]?\d*) से में diff --git a/dateparser_data/supplementary_language_data/date_translation_data/hr.yaml b/dateparser_data/supplementary_language_data/date_translation_data/hr.yaml index 1749baffd..97cee4390 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/hr.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/hr.yaml @@ -143,3 +143,12 @@ relative-type-regex: simplifications: - podne: '12:00' - ponoć: '00:00' + + # The numeral "1" is optional: a bare unit means "1 unit" ago + - '(?<=prije\s+)tjedan(\s+dana)?': '1 tjedan' + - '(?<=prije\s+)mjesec(\s+dana)?': '1 mjesec' + - '(?<=prije\s+)godinu(\s+dana)?': '1 godinu' + - '(?<=prije\s+)sat(\s+vremena)?': '1 sat' + - '(?<=prije\s+)dan\b': '1 dan' + - '(?<=prije\s+)minutu': '1 minutu' + - '(?<=prije\s+)sekundu': '1 sekundu' diff --git a/dateparser_data/supplementary_language_data/date_translation_data/hsb.yaml b/dateparser_data/supplementary_language_data/date_translation_data/hsb.yaml new file mode 100644 index 000000000..a98389fdc --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/hsb.yaml @@ -0,0 +1,5 @@ +relative-type: + 0 hour ago: + - this hour + 0 minute ago: + - this minute diff --git a/dateparser_data/supplementary_language_data/date_translation_data/hy.yaml b/dateparser_data/supplementary_language_data/date_translation_data/hy.yaml new file mode 100644 index 000000000..d6fe69e29 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/hy.yaml @@ -0,0 +1,9 @@ +am: + - կա +pm: + - կհ +relative-type: + 0 second ago: + - այժմ + 1 month ago: + - անցյալ ամիս diff --git a/dateparser_data/supplementary_language_data/date_translation_data/id.yaml b/dateparser_data/supplementary_language_data/date_translation_data/id.yaml index d02ada75c..05c13c00b 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/id.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/id.yaml @@ -1,12 +1,13 @@ skip: ["pukul", "tanggal", "yang"] -sentence_splitter_group : 1 +sentence_splitter_group: 1 sunday: - Ahad august: - Agu + - agt september: - Sept @@ -29,6 +30,8 @@ relative-type: 0 second ago: - baru saja + in 1 month: + - bulan berikutnya relative-type-regex: \1 week ago: - (\d+[.,]?\d*) minggu lalu diff --git a/dateparser_data/supplementary_language_data/date_translation_data/ig.yaml b/dateparser_data/supplementary_language_data/date_translation_data/ig.yaml new file mode 100644 index 000000000..146090270 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/ig.yaml @@ -0,0 +1,34 @@ +sunday: + - mbọsị ụka + - ụka +april: + - eprel +second: + - nkejinta +relative-type: + 0 hour ago: + - this hour + 0 minute ago: + - this minute + 0 month ago: + - this month + 0 second ago: + - now + 0 week ago: + - this week + 0 year ago: + - this year + 1 day ago: + - nnyaafụ + 1 month ago: + - last month + 1 week ago: + - last week + 1 year ago: + - last year + in 1 month: + - next month + in 1 week: + - next week + in 1 year: + - next year diff --git a/dateparser_data/supplementary_language_data/date_translation_data/is.yaml b/dateparser_data/supplementary_language_data/date_translation_data/is.yaml new file mode 100644 index 000000000..633d07c0a --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/is.yaml @@ -0,0 +1,7 @@ +day: + - d +relative-type: + 0 hour ago: + - this hour + 0 minute ago: + - this minute diff --git a/dateparser_data/supplementary_language_data/date_translation_data/it.yaml b/dateparser_data/supplementary_language_data/date_translation_data/it.yaml index 100f41217..e10f98656 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/it.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/it.yaml @@ -1,6 +1,6 @@ -skip: ["circa", "e"] +skip: ["circa", "e", "alle"] -sentence_splitter_group : 1 +sentence_splitter_group: 1 year: - anni @@ -14,8 +14,10 @@ hour: - ore minute: - minuti + - m second: - secondi + - sec ago: - fa @@ -27,4 +29,5 @@ relative-type: - altro ieri simplifications: - - (\d+[.,]?\d*)\s+ora: \1 ore + - (\d+[.,]?\d*)\s+ora: \1 ore + - \bun[' ]ora\b: 1 ore diff --git a/dateparser_data/supplementary_language_data/date_translation_data/ja.yaml b/dateparser_data/supplementary_language_data/date_translation_data/ja.yaml index 604d907b7..3305b1815 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/ja.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/ja.yaml @@ -1,6 +1,6 @@ no_word_spacing: "True" -sentence_splitter_group : 4 +sentence_splitter_group: 4 skip: ["約"] @@ -78,10 +78,16 @@ relative-type: in 2 day: - 明後日 + in 1 month: + - 翌月 + in 1 week: + - 翌週 + in 1 year: + - 翌年 simplifications: - - (\d+[.,]?\d*)年(?:\s+)?(\d+[.,]?\d*)月(?:\s+)?(\d+[.,]?\d*)日: \1-\2-\3 + - (\d+[.,]?\d*)\s*年\s*(\d+[.,]?\d*)\s*月\s*(\d+[.,]?\d*)\s*日: \1-\2-\3 - (\d+[.,]?\d*)月(?:\s+)?(\d+[.,]?\d*)日: \1-\2 - - (\d+[.,]?\d*)時(?:\s+)?(\d+[.,]?\d*)分(?:\s+)?(\d+[.,]?\d*)秒: \1:\2:\3 - - (\d+[.,]?\d*)時(?:\s+)?(\d+[.,]?\d*)分: \1:\2 - - (\d+[.,]?\d*)時$: \1:00 + - (\d+[.,]?\d*)\s*時\s*(\d+[.,]?\d*)\s*分\s*(\d+[.,]?\d*)\s*秒: \1:\2:\3 + - (\d+[.,]?\d*)\s*時\s*(\d+[.,]?\d*)\s*分: \1:\2 + - (\d+[.,]?\d*)\s*時$: \1:00 - 正午: '12:00' diff --git a/dateparser_data/supplementary_language_data/date_translation_data/ka.yaml b/dateparser_data/supplementary_language_data/date_translation_data/ka.yaml index 6736b5b54..6d3642179 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/ka.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/ka.yaml @@ -1,6 +1,8 @@ +pm: + - შუადღ შემდეგ skip: ["და", "დაახლოებით", "ზე", "ის"] -sentence_splitter_group : 1 +sentence_splitter_group: 1 year: - წლის diff --git a/dateparser_data/supplementary_language_data/date_translation_data/kea.yaml b/dateparser_data/supplementary_language_data/date_translation_data/kea.yaml new file mode 100644 index 000000000..863153037 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/kea.yaml @@ -0,0 +1,11 @@ +saturday: + - sabadu +relative-type: + 0 hour ago: + - this hour + 0 minute ago: + - this minute + 0 second ago: + - now + in 1 day: + - manha diff --git a/dateparser_data/supplementary_language_data/date_translation_data/kl.yaml b/dateparser_data/supplementary_language_data/date_translation_data/kl.yaml new file mode 100644 index 000000000..87e4bf430 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/kl.yaml @@ -0,0 +1,29 @@ +sunday: + - sab + - sabaat +january: + - januari +february: + - feb + - februari +march: + - martsi +april: + - aprili +may: + - maji +june: + - juni +july: + - juli +august: + - augustusi +september: + - sep + - septemberi +october: + - oktoberi +november: + - novemberi +december: + - decemberi diff --git a/dateparser_data/supplementary_language_data/date_translation_data/ko.yaml b/dateparser_data/supplementary_language_data/date_translation_data/ko.yaml new file mode 100644 index 000000000..3f0688071 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/ko.yaml @@ -0,0 +1,14 @@ +relative-type: + 0 day ago: + - 금일 + 1 day ago: + - 작일 + in 1 day: + - 명일 + +relative-type-regex: + \1 month ago: + - (\d+[.,]?\d*)달 전 + in \1 month: + - (\d+[.,]?\d*)달 후 + diff --git a/dateparser_data/supplementary_language_data/date_translation_data/kok.yaml b/dateparser_data/supplementary_language_data/date_translation_data/kok.yaml new file mode 100644 index 000000000..6463f6771 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/kok.yaml @@ -0,0 +1,78 @@ +monday: + - सोम + - सोमवार +tuesday: + - मंगळ +wednesday: + - बुध +thursday: + - गुरु + - गुरुवार +friday: + - शुक्र + - शुक्रवार +saturday: + - शनि + - शनिवार +sunday: + - आदित्यवार + - रवि +april: + - एप्रिल +july: + - जुलै +august: + - ओगस्ट +september: + - सेप्टेंबर +october: + - ओक्टोबर +year: + - year +month: + - month +week: + - week +day: + - day +hour: + - hour +minute: + - minute +second: + - second +am: + - मपू +pm: + - मनं +relative-type: + 0 day ago: + - today + 0 hour ago: + - this hour + 0 minute ago: + - this minute + 0 month ago: + - this month + 0 second ago: + - now + 0 week ago: + - this week + 0 year ago: + - this year + 1 day ago: + - yesterday + 1 month ago: + - last month + 1 week ago: + - last week + 1 year ago: + - last year + in 1 day: + - tomorrow + in 1 month: + - next month + in 1 week: + - next week + in 1 year: + - next year diff --git a/dateparser_data/supplementary_language_data/date_translation_data/ks.yaml b/dateparser_data/supplementary_language_data/date_translation_data/ks.yaml new file mode 100644 index 000000000..ddc642713 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/ks.yaml @@ -0,0 +1,34 @@ +monday: + - ژٔنٛدرٕروار + - ژٔنٛدٕروار +tuesday: + - بوٚموار +thursday: + - برٛٮ۪سوار +may: + - میٔ +month: + - رٮ۪تھ +hour: + - گٲنٛٹہٕ +second: + - سٮ۪کَنڑ +relative-type: + 0 month ago: + - this month + 0 week ago: + - this week + 0 year ago: + - this year + 1 month ago: + - last month + 1 week ago: + - last week + 1 year ago: + - last year + in 1 month: + - next month + in 1 week: + - next week + in 1 year: + - next year diff --git a/dateparser_data/supplementary_language_data/date_translation_data/ky.yaml b/dateparser_data/supplementary_language_data/date_translation_data/ky.yaml new file mode 100644 index 000000000..1261bedd9 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/ky.yaml @@ -0,0 +1,3 @@ +relative-type: + in 1 day: + - эртеӊ diff --git a/dateparser_data/supplementary_language_data/date_translation_data/lo.yaml b/dateparser_data/supplementary_language_data/date_translation_data/lo.yaml new file mode 100644 index 000000000..896078855 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/lo.yaml @@ -0,0 +1,3 @@ +relative-type-regex: + in \1 minute: + - (\d+[.,]?\d*) ໃນອີກ 0 ນາທີ diff --git a/dateparser_data/supplementary_language_data/date_translation_data/lt.yaml b/dateparser_data/supplementary_language_data/date_translation_data/lt.yaml new file mode 100644 index 000000000..c77401aae --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/lt.yaml @@ -0,0 +1,9 @@ +simplifications: + # The numeral "1" is optional: a bare unit means "1 unit" ago + - '(?<=prieš\s+)savaitę\b': '1 savaitę' + - '(?<=prieš\s+)mėnesį\b': '1 mėnesį' + - '(?<=prieš\s+)metus\b': '1 metus' + - '(?<=prieš\s+)dieną\b': '1 dieną' + - '(?<=prieš\s+)valandą\b': '1 valandą' + - '(?<=prieš\s+)minutę\b': '1 minutę' + - '(?<=prieš\s+)sekundę\b': '1 sekundę' diff --git a/dateparser_data/supplementary_language_data/date_translation_data/lv.yaml b/dateparser_data/supplementary_language_data/date_translation_data/lv.yaml new file mode 100644 index 000000000..195cab331 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/lv.yaml @@ -0,0 +1,9 @@ +simplifications: + # The numeral "1" is optional: a bare unit means "1 unit" ago + - '(?<=pirms\s+)nedēļas\b': '1 nedēļas' + - '(?<=pirms\s+)mēneša\b': '1 mēneša' + - '(?<=pirms\s+)gada\b': '1 gada' + - '(?<=pirms\s+)dienas\b': '1 dienas' + - '(?<=pirms\s+)stundas\b': '1 stundas' + - '(?<=pirms\s+)minūtes\b': '1 minūtes' + - '(?<=pirms\s+)sekundes\b': '1 sekundes' diff --git a/dateparser_data/supplementary_language_data/date_translation_data/mk.yaml b/dateparser_data/supplementary_language_data/date_translation_data/mk.yaml new file mode 100644 index 000000000..a7f82b3e0 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/mk.yaml @@ -0,0 +1,24 @@ +tuesday: + - вт +september: + - септ +november: + - ноем +am: + - претпладне +pm: + - попладне +relative-type: + 1 year ago: + - минатата година + in 1 year: + - следната година + +simplifications: + # The numeral "1" is optional: a bare unit means "1 unit" ago + - '(?<=пред\s+)седмица\b': '1 седмица' + - '(?<=пред\s+)месец\b': '1 месец' + - '(?<=пред\s+)година\b': '1 година' + - '(?<=пред\s+)ден\b': '1 ден' + - '(?<=пред\s+)час\b': '1 час' + - '(?<=пред\s+)минута\b': '1 минута' diff --git a/dateparser_data/supplementary_language_data/date_translation_data/mn.yaml b/dateparser_data/supplementary_language_data/date_translation_data/mn.yaml new file mode 100644 index 000000000..896f91244 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/mn.yaml @@ -0,0 +1,13 @@ +june: + - зургадугаар сар +july: + - долдугаар сар +week: + - 7х +relative-type-regex: + \1 week ago: + - (\d+[.,]?\d*) 7х-ийн өмнө + in \1 day: + - (\d+[.,]?\d*) өдөрт + in \1 week: + - (\d+[.,]?\d*) 7х-ийн дараа diff --git a/dateparser_data/supplementary_language_data/date_translation_data/mr.yaml b/dateparser_data/supplementary_language_data/date_translation_data/mr.yaml new file mode 100644 index 000000000..ae6202bce --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/mr.yaml @@ -0,0 +1,4 @@ +am: + - मपू +pm: + - मउ diff --git a/dateparser_data/supplementary_language_data/date_translation_data/ms.yaml b/dateparser_data/supplementary_language_data/date_translation_data/ms.yaml new file mode 100644 index 000000000..896d9c2ea --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/ms.yaml @@ -0,0 +1,7 @@ +relative-type: + 0 week ago: + - mng ini + 1 week ago: + - mng lepas + in 1 week: + - mng depan diff --git a/dateparser_data/supplementary_language_data/date_translation_data/mt.yaml b/dateparser_data/supplementary_language_data/date_translation_data/mt.yaml new file mode 100644 index 000000000..c7391ae42 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/mt.yaml @@ -0,0 +1,14 @@ +relative-type: + 0 hour ago: + - this hour + 0 minute ago: + - this minute + 0 second ago: + - now + 1 day ago: + - ilbieraħ + 1 year ago: + - is-sena li għaddiet +relative-type-regex: + \1 year ago: + - (\d+[.,]?\d*) snin ilu diff --git a/dateparser_data/supplementary_language_data/date_translation_data/nb.yaml b/dateparser_data/supplementary_language_data/date_translation_data/nb.yaml index 70518b040..18853f703 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/nb.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/nb.yaml @@ -1,9 +1,19 @@ +skip: ["cirka", "d.", "kl", "kl."] + +sentence_splitter_group: 1 + +month: + - måneder week: - uker day: - dager hour: - timer +minute: + - minutter +second: + - sekunder ago: - siden @@ -11,5 +21,20 @@ in: - om relative-type-regex: - \1 day ago: - - for (\d+[.,]?\d*) dager siden \ No newline at end of file + \1 day ago: + - for (\d+[.,]?\d*) dager siden + + \1 year ago: + - –(\d+[.,]?\d*) år +simplifications: + - en: '1' + - ett: '1' + - to: '2' + - tre: '3' + - fire: '4' + - fem: '5' + - seks: '6' + - sju: '7' + - åtte: '8' + - ni: '9' + - ti: '10' diff --git a/dateparser_data/supplementary_language_data/date_translation_data/ne.yaml b/dateparser_data/supplementary_language_data/date_translation_data/ne.yaml new file mode 100644 index 000000000..8c883c9d3 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/ne.yaml @@ -0,0 +1,18 @@ +may: + - मई +year: + - बर्ष +relative-type: + 0 hour ago: + - यो घडीमा + 0 second ago: + - अब + in 1 week: + - आउने हप्ता + in 1 year: + - अर्को वर्ष +relative-type-regex: + \1 second ago: + - (\d+[.,]?\d*) सेकेण्ड पहिले + in \1 second: + - (\d+[.,]?\d*) सेकेण्डमा diff --git a/dateparser_data/supplementary_language_data/date_translation_data/nn.yaml b/dateparser_data/supplementary_language_data/date_translation_data/nn.yaml new file mode 100644 index 000000000..d7aeb8543 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/nn.yaml @@ -0,0 +1,61 @@ +am: + - formiddag +pm: + - ettermiddag +relative-type: + 0 hour ago: + - this hour + 0 minute ago: + - this minute + 0 month ago: + - this month + 0 second ago: + - now + 0 week ago: + - this week + 0 year ago: + - this year + 1 month ago: + - last month + 1 week ago: + - last week + 1 year ago: + - last year + in 1 month: + - next month + in 1 week: + - next week + in 1 year: + - next year +relative-type-regex: + \1 day ago: + - for (\d+[.,]?\d*) døgn siden + \1 hour ago: + - for (\d+[.,]?\d*) time siden + - for (\d+[.,]?\d*) timer siden + \1 minute ago: + - for (\d+[.,]?\d*) minutt siden + - for (\d+[.,]?\d*) minutter siden + \1 month ago: + - for (\d+[.,]?\d*) måned siden + - for (\d+[.,]?\d*) måneder siden + \1 second ago: + - for (\d+[.,]?\d*) sekund siden + - for (\d+[.,]?\d*) sekunder siden + \1 week ago: + - for (\d+[.,]?\d*) uke siden + - for (\d+[.,]?\d*) uker siden + \1 year ago: + - for (\d+[.,]?\d*) år siden + in \1 hour: + - om (\d+[.,]?\d*) timer + in \1 minute: + - om (\d+[.,]?\d*) minutter + in \1 month: + - om (\d+[.,]?\d*) måned + - om (\d+[.,]?\d*) måneder + in \1 second: + - om (\d+[.,]?\d*) sekunder + in \1 week: + - om (\d+[.,]?\d*) uke + - om (\d+[.,]?\d*) uker diff --git a/dateparser_data/supplementary_language_data/date_translation_data/or.yaml b/dateparser_data/supplementary_language_data/date_translation_data/or.yaml new file mode 100644 index 000000000..25ee94973 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/or.yaml @@ -0,0 +1,45 @@ +year: + - year +month: + - month +week: + - week +day: + - day +hour: + - hour +minute: + - minute +second: + - second +relative-type: + 0 day ago: + - today + 0 hour ago: + - this hour + 0 minute ago: + - this minute + 0 month ago: + - this month + 0 second ago: + - now + 0 week ago: + - this week + 0 year ago: + - this year + 1 day ago: + - yesterday + 1 month ago: + - last month + 1 week ago: + - last week + 1 year ago: + - last year + in 1 day: + - tomorrow + in 1 month: + - next month + in 1 week: + - next week + in 1 year: + - next year diff --git a/dateparser_data/supplementary_language_data/date_translation_data/pl.yaml b/dateparser_data/supplementary_language_data/date_translation_data/pl.yaml index 609c8412a..a83262207 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/pl.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/pl.yaml @@ -1,4 +1,7 @@ -sentence_splitter_group : 1 +relative-type-regex: + \1 month ago: + - –(\d+[.,]?\d*) mies +sentence_splitter_group: 1 skip: ["i", "o", "r.", "roku", "w"] @@ -163,3 +166,12 @@ simplifications: - przedwczoraj: 2 dnia temu - jutro: za 1 dnia - pojutrze: za 2 dnia + + # The numeral "1" is optional: a bare unit means "1 unit" ago + - '(?<=[^\d]\s+|^)tydzień(?=\s+temu)': '1 tydzień' + - '(?<=[^\d]\s+|^)miesiąc(?=\s+temu)': '1 miesiąc' + - '(?<=[^\d]\s+|^)rok(?=\s+temu)': '1 rok' + - '(?<=[^\d]\s+|^)dzień(?=\s+temu)': '1 dzień' + - '(?<=[^\d]\s+|^)godzinę(?=\s+temu)': '1 godzinę' + - '(?<=[^\d]\s+|^)minutę(?=\s+temu)': '1 minutę' + - '(?<=[^\d]\s+|^)sekundę(?=\s+temu)': '1 sekundę' diff --git a/dateparser_data/supplementary_language_data/date_translation_data/ps.yaml b/dateparser_data/supplementary_language_data/date_translation_data/ps.yaml new file mode 100644 index 000000000..1a5a33d94 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/ps.yaml @@ -0,0 +1,57 @@ +monday: + - دوشنبه +tuesday: + - سه‌شنبه +wednesday: + - چهارشنبه +thursday: + - پنجشنبه +saturday: + - شنبه +sunday: + - یکشنبه +year: + - year +month: + - month +week: + - week +day: + - day +hour: + - hour +minute: + - minute +second: + - second +relative-type: + 0 day ago: + - today + 0 hour ago: + - this hour + 0 minute ago: + - this minute + 0 month ago: + - this month + 0 second ago: + - now + 0 week ago: + - this week + 0 year ago: + - this year + 1 day ago: + - yesterday + 1 month ago: + - last month + 1 week ago: + - last week + 1 year ago: + - last year + in 1 day: + - tomorrow + in 1 month: + - next month + in 1 week: + - next week + in 1 year: + - next year diff --git a/dateparser_data/supplementary_language_data/date_translation_data/pt.yaml b/dateparser_data/supplementary_language_data/date_translation_data/pt.yaml index 48952b704..9157c9729 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/pt.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/pt.yaml @@ -1,7 +1,14 @@ +relative-type-regex: + \1 minute ago: + - há (\d+[.,]?\d*) mins + in \1 minute: + - em (\d+[.,]?\d*) mins + in \1 second: + - em (\d+[.,]?\d*) segs skip: ["cerca", "de", "e", "às"] pertain: ["de"] -sentence_splitter_group : 1 +sentence_splitter_group: 1 monday: - Segunda @@ -31,8 +38,16 @@ hour: - horas minute: - minutos + - m second: - segundos + - s + +early_morning: + - de madrugada + - na madrugada + - pela madrugada + - madrugada ago: - atrás @@ -45,6 +60,7 @@ relative-type: - anteontem simplifications: + - esta madrugada: hoje madrugada - uma: '1' - um: '1' - alguns segundos: 44 segundos diff --git a/dateparser_data/supplementary_language_data/date_translation_data/qu.yaml b/dateparser_data/supplementary_language_data/date_translation_data/qu.yaml new file mode 100644 index 000000000..fdf6188f3 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/qu.yaml @@ -0,0 +1,65 @@ +january: + - qul + - qulla puquy +february: + - hat + - hatun puquy +march: + - pau + - pauqar waray +april: + - ayr + - ayriwa +may: + - aym + - aymuray +june: + - int + - inti raymi +july: + - ant + - anta sitwa +august: + - qha + - qhapaq sitwa +september: + - uma + - uma raymi +october: + - kan + - kantaray +november: + - aya + - ayamarq'a +december: + - kap + - kapaq raymi +relative-type: + 0 day ago: + - today + 0 hour ago: + - this hour + 0 minute ago: + - this minute + 0 month ago: + - this month + 0 week ago: + - this week + 0 year ago: + - this year + 1 day ago: + - yesterday + 1 month ago: + - last month + 1 week ago: + - last week + 1 year ago: + - last year + in 1 day: + - tomorrow + in 1 month: + - next month + in 1 week: + - next week + in 1 year: + - next year diff --git a/dateparser_data/supplementary_language_data/date_translation_data/rm.yaml b/dateparser_data/supplementary_language_data/date_translation_data/rm.yaml new file mode 100644 index 000000000..93081f9ca --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/rm.yaml @@ -0,0 +1,9 @@ +day: + - tag +relative-type: + 0 year ago: + - this year + 1 year ago: + - last year + in 1 year: + - next year diff --git a/dateparser_data/supplementary_language_data/date_translation_data/ro.yaml b/dateparser_data/supplementary_language_data/date_translation_data/ro.yaml index f8767b40e..dd2e3c61d 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/ro.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/ro.yaml @@ -1,6 +1,13 @@ +relative-type-regex: + \1 day ago: + - acum (\d+[.,]?\d*) zile + in \1 day: + - peste (\d+[.,]?\d*) zile + in \1 year: + - peste (\d+[.,]?\d*) ani skip: ["de", "la"] -sentence_splitter_group : 1 +sentence_splitter_group: 1 wednesday: - Mi diff --git a/dateparser_data/supplementary_language_data/date_translation_data/ru.yaml b/dateparser_data/supplementary_language_data/date_translation_data/ru.yaml index a9d6b0557..2d2878fc0 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/ru.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/ru.yaml @@ -1,6 +1,15 @@ +am: + - дп +pm: + - пп +relative-type-regex: + \1 day ago: + - (\d+[.,]?\d*) д назад + in \1 day: + - через (\d+[.,]?\d*) д skip: ["в", "во", "и", "около", "примерно"] -sentence_splitter_group : 1 +sentence_splitter_group: 1 monday: - пнд @@ -71,6 +80,8 @@ relative-type: in 3 day: - послепослезавтра + 0 hour ago: + - в этом часе simplifications: - од(ин|на|ну|ни|ной|ною|но|ного|ному|ним|нем): '1' - перв(ой|ого|ому|ым|ом|ая|ую|ое|ые|ых|ыми): '1' diff --git a/dateparser_data/supplementary_language_data/date_translation_data/rw.yaml b/dateparser_data/supplementary_language_data/date_translation_data/rw.yaml new file mode 100644 index 000000000..9fcb71d19 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/rw.yaml @@ -0,0 +1,2 @@ +may: + - gicuransi diff --git a/dateparser_data/supplementary_language_data/date_translation_data/se.yaml b/dateparser_data/supplementary_language_data/date_translation_data/se.yaml new file mode 100644 index 000000000..ba69fb3cf --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/se.yaml @@ -0,0 +1,20 @@ +locale_specific: + se-FI: + monday: + - vuossárgga + tuesday: + - maŋŋebárgga + wednesday: + - gaskavahku + thursday: + - duorastaga + friday: + - bearjadaga + saturday: + - lávvardaga + relative-type: + 1 year ago: + - mannan jagi + relative-type-regex: + \1 year ago: + - (\d+[.,]?\d*) jagi árat diff --git a/dateparser_data/supplementary_language_data/date_translation_data/si.yaml b/dateparser_data/supplementary_language_data/date_translation_data/si.yaml new file mode 100644 index 000000000..4242f07fa --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/si.yaml @@ -0,0 +1,6 @@ +hour: + - පැ +minute: + - මි +second: + - ත diff --git a/dateparser_data/supplementary_language_data/date_translation_data/sl.yaml b/dateparser_data/supplementary_language_data/date_translation_data/sl.yaml new file mode 100644 index 000000000..c6c74df34 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/sl.yaml @@ -0,0 +1,9 @@ +simplifications: + # The numeral "1" is optional: a bare unit means "1 unit" ago + - '(?<=pred\s+)tednom\b': '1 tednom' + - '(?<=pred\s+)mesecem\b': '1 mesecem' + - '(?<=pred\s+)letom\b': '1 letom' + - '(?<=pred\s+)dnevom\b': '1 dnevom' + - '(?<=pred\s+)uro\b': '1 uro' + - '(?<=pred\s+)minuto\b': '1 minuto' + - '(?<=pred\s+)sekundo\b': '1 sekundo' diff --git a/dateparser_data/supplementary_language_data/date_translation_data/so.yaml b/dateparser_data/supplementary_language_data/date_translation_data/so.yaml new file mode 100644 index 000000000..f62f88c4a --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/so.yaml @@ -0,0 +1,77 @@ +tuesday: + - tal +wednesday: + - arb +thursday: + - kha +friday: + - jim +saturday: + - sab +january: + - kob +february: + - lab +march: + - sad +april: + - afr +may: + - sha +june: + - lix +july: + - tod +august: + - sid +september: + - sag +october: + - tob +november: + - kit +december: + - lit +year: + - year +month: + - month +week: + - week +day: + - day +hour: + - hour +minute: + - minute +second: + - second +am: + - sn +pm: + - gn +relative-type: + 0 hour ago: + - this hour + 0 minute ago: + - this minute + 0 month ago: + - this month + 0 second ago: + - now + 0 week ago: + - this week + 0 year ago: + - this year + 1 month ago: + - last month + 1 week ago: + - last week + 1 year ago: + - last year + in 1 month: + - next month + in 1 week: + - next week + in 1 year: + - next year diff --git a/dateparser_data/supplementary_language_data/date_translation_data/sq.yaml b/dateparser_data/supplementary_language_data/date_translation_data/sq.yaml new file mode 100644 index 000000000..4ae8bf635 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/sq.yaml @@ -0,0 +1,4 @@ +july: + - kor +august: + - gsh diff --git a/dateparser_data/supplementary_language_data/date_translation_data/sr-Cyrl.yaml b/dateparser_data/supplementary_language_data/date_translation_data/sr-Cyrl.yaml new file mode 100644 index 000000000..43f0301b1 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/sr-Cyrl.yaml @@ -0,0 +1,26 @@ +month: + - м +week: + - н +am: + - пре подне +pm: + - по подне +locale_specific: + sr-Cyrl-BA: + tuesday: + - ут + wednesday: + - ср + september: + - септ + sr-Cyrl-ME: + tuesday: + - ут + wednesday: + - ср + sr-Cyrl-XK: + tuesday: + - ут + wednesday: + - ср diff --git a/dateparser_data/supplementary_language_data/date_translation_data/sr-Latn.yaml b/dateparser_data/supplementary_language_data/date_translation_data/sr-Latn.yaml new file mode 100644 index 000000000..c547b6eeb --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/sr-Latn.yaml @@ -0,0 +1,26 @@ +month: + - m +week: + - n +am: + - pre podne +pm: + - po podne +locale_specific: + sr-Latn-BA: + tuesday: + - ut + wednesday: + - sr + september: + - sept + sr-Latn-ME: + tuesday: + - ut + wednesday: + - sr + sr-Latn-XK: + tuesday: + - ut + wednesday: + - sr diff --git a/dateparser_data/supplementary_language_data/date_translation_data/sr.yaml b/dateparser_data/supplementary_language_data/date_translation_data/sr.yaml new file mode 100644 index 000000000..fca5ee98c --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/sr.yaml @@ -0,0 +1,8 @@ +month: + - м +week: + - н +am: + - пре подне +pm: + - по подне diff --git a/dateparser_data/supplementary_language_data/date_translation_data/sv.yaml b/dateparser_data/supplementary_language_data/date_translation_data/sv.yaml index 9bd0b2ad4..83ae7aed7 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/sv.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/sv.yaml @@ -1,6 +1,13 @@ +relative-type-regex: + \1 minute ago: + - för (\d+[.,]?\d*) min sedan + \1 month ago: + - för (\d+[.,]?\d*) mån sedan + \1 second ago: + - för (\d+[.,]?\d*) sek sedan skip: ["den", "på"] -sentence_splitter_group : 1 +sentence_splitter_group: 1 monday: - Månd @@ -59,6 +66,9 @@ relative-type: in 1 day: - imorgon + 0 month ago: + - denna månad simplifications: + - (\d+):[ae]\b: \1 - en: '1' - två: '2' diff --git a/dateparser_data/supplementary_language_data/date_translation_data/sw.yaml b/dateparser_data/supplementary_language_data/date_translation_data/sw.yaml new file mode 100644 index 000000000..97ee0433e --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/sw.yaml @@ -0,0 +1,4 @@ +am: + - asubuhi +pm: + - mchana diff --git a/dateparser_data/supplementary_language_data/date_translation_data/ta.yaml b/dateparser_data/supplementary_language_data/date_translation_data/ta.yaml new file mode 100644 index 000000000..464ca9d0b --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/ta.yaml @@ -0,0 +1,3 @@ +relative-type-regex: + \1 week ago: + - (\d+[.,]?\d*) வாரத்திற்கு முன்பு diff --git a/dateparser_data/supplementary_language_data/date_translation_data/te.yaml b/dateparser_data/supplementary_language_data/date_translation_data/te.yaml new file mode 100644 index 000000000..bea41b68c --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/te.yaml @@ -0,0 +1,4 @@ +day: + - ది +minute: + - ని diff --git a/dateparser_data/supplementary_language_data/date_translation_data/th.yaml b/dateparser_data/supplementary_language_data/date_translation_data/th.yaml index 7047680a7..70557eae8 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/th.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/th.yaml @@ -1,4 +1,6 @@ -sentence_splitter_group : 5 +minute: + - น +sentence_splitter_group: 5 skip: ["น.", "เมื่อ ", "เวลา"] @@ -66,8 +68,11 @@ ago: - แต่ก่อน - มาแล้ว - ก่อน + - ที่แล้ว + - ที่ผ่านมา in: - ใน + - อีก simplifications: - วันนี้: 0 วัน diff --git a/dateparser_data/supplementary_language_data/date_translation_data/ti.yaml b/dateparser_data/supplementary_language_data/date_translation_data/ti.yaml new file mode 100644 index 000000000..49c487948 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/ti.yaml @@ -0,0 +1,53 @@ +tuesday: + - ሠሉስ +thursday: + - ኃሙስ +year: + - year +month: + - month +week: + - week +day: + - day +hour: + - hour +minute: + - minute +second: + - second +am: + - ንጉሆ ሰዓተ +pm: + - ድሕር ሰዓት +relative-type: + 0 day ago: + - today + 0 hour ago: + - this hour + 0 minute ago: + - this minute + 0 month ago: + - this month + 0 second ago: + - now + 0 week ago: + - this week + 0 year ago: + - this year + 1 day ago: + - yesterday + 1 month ago: + - last month + 1 week ago: + - last week + 1 year ago: + - last year + in 1 day: + - tomorrow + in 1 month: + - next month + in 1 week: + - next week + in 1 year: + - next year diff --git a/dateparser_data/supplementary_language_data/date_translation_data/to.yaml b/dateparser_data/supplementary_language_data/date_translation_data/to.yaml new file mode 100644 index 000000000..25b3b3940 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/to.yaml @@ -0,0 +1,11 @@ +september: + - sep +am: + - am +pm: + - pm +relative-type: + 0 hour ago: + - this hour + 0 minute ago: + - this minute diff --git a/dateparser_data/supplementary_language_data/date_translation_data/uk.yaml b/dateparser_data/supplementary_language_data/date_translation_data/uk.yaml index 9bfae097f..f4bfe2b55 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/uk.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/uk.yaml @@ -39,10 +39,23 @@ sunday: march: - берез +april: + - кві +may: + - тра +june: + - чер +august: + - сер september: - верес +october: + - жов november: - листоп + - лис +december: + - гру year: - р @@ -146,12 +159,16 @@ relative-type: - післязавтра relative-type-regex: + \1 day ago: + - (\d+[.,]?\d*) д тому \1 hour ago: - (\d+[.,]?\d*) година тому \1 minute ago: - (\d+[.,]?\d*) хвилина тому \1 second ago: - (\d+[.,]?\d*) секунда тому + in \1 day: + - за (\d+[.,]?\d*) д simplifications: - од(на|ну|ні|ної|нієї|ин|ній): '1' @@ -185,4 +202,10 @@ simplifications: - кілька секунд: 44 секунди - кілька хвилин: 2 хвилини - опів на: 30 хвилин - - за чверть: 15 хвилин \ No newline at end of file + - за чверть: 15 хвилин + + # The numeral "1" is optional: a bare unit means "1 unit" ago + - '(?<=[^\d]\s+|^)тиждень(?=\s+тому)': '1 тиждень' + - '(?<=[^\d]\s+|^)місяць(?=\s+тому)': '1 місяць' + - '(?<=[^\d]\s+|^)рік(?=\s+тому)': '1 рік' + - '(?<=[^\d]\s+|^)день(?=\s+тому)': '1 день' diff --git a/dateparser_data/supplementary_language_data/date_translation_data/ur.yaml b/dateparser_data/supplementary_language_data/date_translation_data/ur.yaml new file mode 100644 index 000000000..8a799fa15 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/ur.yaml @@ -0,0 +1,5 @@ +monday: + - سوموار +relative-type-regex: + in \1 hour: + - (\d+[.,]?\d*) گھنٹہ میں diff --git a/dateparser_data/supplementary_language_data/date_translation_data/uz-Latn.yaml b/dateparser_data/supplementary_language_data/date_translation_data/uz-Latn.yaml new file mode 100644 index 000000000..666e50391 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/uz-Latn.yaml @@ -0,0 +1,3 @@ +relative-type: + 1 year ago: + - o'tgan yil diff --git a/dateparser_data/supplementary_language_data/date_translation_data/uz.yaml b/dateparser_data/supplementary_language_data/date_translation_data/uz.yaml new file mode 100644 index 000000000..666e50391 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/uz.yaml @@ -0,0 +1,3 @@ +relative-type: + 1 year ago: + - o'tgan yil diff --git a/dateparser_data/supplementary_language_data/date_translation_data/vi.yaml b/dateparser_data/supplementary_language_data/date_translation_data/vi.yaml index ee4552e69..68b768b14 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/vi.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/vi.yaml @@ -19,22 +19,40 @@ sunday: january: - Tháng một + - tháng 01 + - thg 01 february: - Tháng hai + - tháng 02 + - thg 02 march: - Tháng ba + - tháng 03 + - thg 03 april: - Tháng tư + - tháng 04 + - thg 04 may: - Tháng năm + - tháng 05 + - thg 05 june: - Tháng sáu + - tháng 06 + - thg 06 july: - Tháng bảy + - tháng 07 + - thg 07 august: - Tháng tám + - tháng 08 + - thg 08 september: - Tháng chín + - tháng 09 + - thg 09 october: - Tháng mười november: diff --git a/dateparser_data/supplementary_language_data/date_translation_data/yo.yaml b/dateparser_data/supplementary_language_data/date_translation_data/yo.yaml new file mode 100644 index 000000000..26076d8fe --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/yo.yaml @@ -0,0 +1,25 @@ +week: + - ọ̀sè +relative-type: + 0 month ago: + - this month + 0 week ago: + - this week + 0 year ago: + - this year + 1 month ago: + - last month + 1 week ago: + - last week + 1 year ago: + - last year + in 1 month: + - next month + in 1 week: + - next week + in 1 year: + - next year +locale_specific: + yo-BJ: + week: + - ɔ̀sè diff --git a/dateparser_data/supplementary_language_data/date_translation_data/yue.yaml b/dateparser_data/supplementary_language_data/date_translation_data/yue.yaml index 9af8bed55..cf666fcdd 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/yue.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/yue.yaml @@ -1,3 +1,17 @@ +monday: + - 週一 +tuesday: + - 週二 +wednesday: + - 週三 +thursday: + - 週四 +friday: + - 週五 +saturday: + - 週六 +sunday: + - 週日 no_word_spacing: "True" -sentence_splitter_group : 4 +sentence_splitter_group: 4 diff --git a/dateparser_data/supplementary_language_data/date_translation_data/zh-Hant.yaml b/dateparser_data/supplementary_language_data/date_translation_data/zh-Hant.yaml index 9af8bed55..dffd770bf 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/zh-Hant.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/zh-Hant.yaml @@ -1,3 +1,26 @@ +locale_specific: + zh-Hant-HK: + relative-type: + 1 month ago: + - 上月 + in 1 month: + - 下月 + relative-type-regex: + \1 week ago: + - (\d+[.,]?\d*)週前 + in \1 week: + - (\d+[.,]?\d*)週後 + zh-Hant-MO: + relative-type: + 1 month ago: + - 上月 + in 1 month: + - 下月 + relative-type-regex: + \1 week ago: + - (\d+[.,]?\d*)週前 + in \1 week: + - (\d+[.,]?\d*)週後 no_word_spacing: "True" -sentence_splitter_group : 4 +sentence_splitter_group: 4 diff --git a/dateparser_data/supplementary_language_data/date_translation_data/zh.yaml b/dateparser_data/supplementary_language_data/date_translation_data/zh.yaml index 75252c017..ce9882d7b 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/zh.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/zh.yaml @@ -47,10 +47,10 @@ relative-type: simplifications: - 半小时前: 30分前 - - (?:中午|下午|(?:晚上?))(?:\s*)(\d+[.,]?\d*)(?:\s*):(?:\s+|:)?(\d+[.,]?\d*): \1:\2 pm - - (?:上午|早上|凌晨)(?:\s*)(\d+[.,]?\d*)(?:\s*):(?:\s+|:)?(\d+[.,]?\d*): \1:\2 am + - (?:中午|下午|(?:晚上?))(?:\s*)(\d+[.,]?\d*)(?:\s*):(?:\s+|:)?(\d+[.,]?\d*(?::\d+[.,]?\d*)?): \1:\2 pm + - (?:上午|早上|凌晨)(?:\s*)(\d+[.,]?\d*)(?:\s*):(?:\s+|:)?(\d+[.,]?\d*(?::\d+[.,]?\d*)?): \1:\2 am - 中午: '12:00' - - (\d+[.,]?\d*)年(?:\s+)?(\d+[.,]?\d*)月(?:\s+)?(\d+[.,]?\d*)日(?:\s+)?(\d+[.,]?\d*)时(?:\s+)?(\d+[.,]?\d*)分: \1-\2-\3 \4:\5 - - (\d+[.,]?\d*)年(?:\s+)?(\d+[.,]?\d*)月(?:\s+)?(\d{1,2})(?:日)?(?:\s+)?(\d{1,2})(?:点|:)(\d{1,2}): \1-\2-\3 \4:\5 - - (\d+[.,]?\d*)年(?:\s+)?(\d+[.,]?\d*)月(?:\s+)?(\d{1,2})(?:日)?: \1-\2-\3 + - (\d+[.,]?\d*)\s*年\s*(\d+[.,]?\d*)\s*月\s*(\d+[.,]?\d*)\s*日\s*(\d+[.,]?\d*)\s*时\s*(\d+[.,]?\d*)\s*分: \1-\2-\3 \4:\5 + - (\d+[.,]?\d*)\s*年\s*(\d+[.,]?\d*)\s*月\s*(\d{1,2})\s*(?:日)?\s*(\d{1,2})\s*(?:点|:)\s*(\d{1,2}): \1-\2-\3 \4:\5 + - (\d+[.,]?\d*)\s*年\s*(\d+[.,]?\d*)\s*月\s*(\d{1,2})\s*(?:日)?: \1-\2-\3 - (\d+[.,]?\d*)月(?=.*[前后]): \1 月 diff --git a/dateparser_data/supplementary_language_data/date_translation_data/zu.yaml b/dateparser_data/supplementary_language_data/date_translation_data/zu.yaml new file mode 100644 index 000000000..f7d5b27c4 --- /dev/null +++ b/dateparser_data/supplementary_language_data/date_translation_data/zu.yaml @@ -0,0 +1,2 @@ +january: + - umasingana diff --git a/dateparser_scripts/article_dates.py b/dateparser_scripts/article_dates.py new file mode 100644 index 000000000..e99506894 --- /dev/null +++ b/dateparser_scripts/article_dates.py @@ -0,0 +1,194 @@ +import argparse +import csv +import io +import os +import random +import re +import sys +import urllib.request +import zipfile +from collections import Counter, defaultdict +from collections.abc import Callable, Iterable +from datetime import datetime +from functools import cache +from multiprocessing import Pool +from pathlib import Path +from typing import NamedTuple, TextIO + +from dateparser.data.languages_info import language_order +from dateparser.date import DateDataParser +from dateparser.search import search_dates + +URL = ( + "https://github.com/scrapinghub/dateparser/files/6532578/" + "article_date_sample_Oct_2020_Mar_2021_public.csv.zip" +) +"""Dataset shared in #928: 300k article publication dates collected from the +web between October 2020 and March 2021.""" + +COLLECTION_END = datetime(2021, 4, 1) +"""No publication date in the dataset can be later than this, so later parsed +dates are wrong, and relative dates are resolved against it.""" + +SETTINGS = {"RELATIVE_BASE": COLLECTION_END} + + +class Result(NamedTuple): + text: str + language: str + date: datetime | None + hinted: datetime | None + locale: str | None + found: bool + error: str | None + + +PROBLEMS: dict[str, Callable[[Result], bool]] = { + "error": lambda r: r.error is not None, + "unparsed": lambda r: r.date is None, + "searchable": lambda r: r.found, + "future": lambda r: ( + r.date is not None and r.date.replace(tzinfo=None) > COLLECTION_END + ), + "hint-dependent": lambda r: r.hinted is not None and r.hinted != r.date, + "misdetected": lambda r: ( + r.hinted is not None + and r.locale is not None + and re.search(r"[^\W\d_]{2}", r.text) is not None + and r.locale.split("-")[0] != r.language + ), +} +"""Checks run on every row. See CONTRIBUTING.rst for what each one means.""" + + +def cache_path() -> Path: + root = os.environ.get("XDG_CACHE_HOME") or Path.home() / ".cache" + return Path(root) / "dateparser" / URL.rsplit("/", 1)[1] + + +def load(path: Path) -> Counter[tuple[str, str]]: + """Return a Counter of (text, language) pairs, downloading the dataset + to *path* first if missing.""" + if not path.exists(): + path.parent.mkdir(parents=True, exist_ok=True) + print(f"Downloading {URL} to {path}", file=sys.stderr) + urllib.request.urlretrieve(URL, path) + with zipfile.ZipFile(path) as archive: + (name,) = archive.namelist() + with archive.open(name) as f: + rows = csv.DictReader(io.TextIOWrapper(f, encoding="utf-8")) + return Counter( + (row["datePublishedRaw"], row["articleLanguage"]) for row in rows + ) + + +@cache +def parser(language: str | None = None) -> DateDataParser: + return DateDataParser(languages=[language] if language else None, settings=SETTINGS) + + +def evaluate(item: tuple[str, str]) -> Result: + text, language = item + result = Result(text, language, None, None, None, False, None) + try: + data = parser().get_date_data(text) + result = result._replace(date=data.date_obj, locale=data.locale) + if language in language_order: + hinted = parser(language).get_date_data(text).date_obj + result = result._replace(hinted=hinted) + if data.date_obj is None: + found = search_dates(text, settings=SETTINGS) is not None + result = result._replace(found=found) + except Exception as exception: + result = result._replace(error=f"{type(exception).__name__}: {exception}") + return result + + +def shape(text: str) -> str: + """Return *text* with digits replaced by 9 and words by a, so that + strings written in the same format share a shape.""" + return re.sub(r"[^\W\d_]+", "a", re.sub(r"\d", "9", text)) + + +def report( + results: list[Result], + counts: Counter[tuple[str, str]], + top: int, + examples: int, + out: TextIO, +) -> None: + total = sum(counts.values()) + hits = {name: [r for r in results if check(r)] for name, check in PROBLEMS.items()} + + def weight(rs: Iterable[Result]) -> int: + return sum(counts[r.text, r.language] for r in rs) + + print(f"{total} rows, {len(results)} distinct\n", file=out) + for name, rs in hits.items(): + print(f"{name}: {weight(rs)} ({weight(rs) / total:.1%})", file=out) + + by_language = defaultdict(list) + for r in results: + by_language[r.language].append(r) + print(f"\n{'language':>8} {'rows':>7}", *(f"{n:>14}" for n in hits), file=out) + ranked = sorted(by_language.items(), key=lambda item: -weight(item[1])) + for language, rs in ranked[:top]: + rows = weight(rs) + cells = (f"{weight(filter(PROBLEMS[n], rs)) / rows:>14.1%}" for n in hits) + print(f"{language or '-':>8} {rows:>7}", *cells, file=out) + + for name, rs in hits.items(): + groups = defaultdict(list) + for r in rs: + groups[shape(r.text)].append(r) + ranked = sorted(groups.items(), key=lambda item: -weight(item[1])) + print(f"\n== {name}: top shapes", file=out) + for s, group in ranked[:top]: + print(f"{weight(group):>7} {s!r}", file=out) + for r in group[:examples]: + print( + f" {r.language or '-':>3} {r.text!r} -> {r.date}" + f" (hinted: {r.hinted}, detected: {r.locale}" + f"{', ' + r.error if r.error else ''})", + file=out, + ) + + +def main(argv: list[str] | None = None) -> None: + arg_parser = argparse.ArgumentParser( + description="Evaluate dateparser against the dataset from #928." + ) + arg_parser.add_argument("--data", type=Path, default=cache_path()) + arg_parser.add_argument("--sample", type=int, help="evaluate this many random rows") + arg_parser.add_argument("--language", help="only rows in this language") + arg_parser.add_argument( + "--top", type=int, default=15, help="how many languages and shapes to list" + ) + arg_parser.add_argument("--examples", type=int, default=3) + arg_parser.add_argument("--jobs", type=int, default=os.cpu_count()) + arg_parser.add_argument( + "--output", + type=Path, + help="write one line per distinct row, to compare runs with diff", + ) + args = arg_parser.parse_args(argv) + + counts = load(args.data) + if args.language is not None: + counts = Counter({k: n for k, n in counts.items() if k[1] == args.language}) + if args.sample: + rows = random.Random(0).sample(list(counts.elements()), args.sample) # noqa: S311 + counts = Counter(rows) + items = sorted(counts) + with Pool(args.jobs) as pool: + results = pool.map(evaluate, items, chunksize=100) + + report(results, counts, args.top, args.examples, sys.stdout) + if args.output: + with args.output.open("w", encoding="utf-8") as f: + for r in results: + print(*(repr(v) for v in r), sep="\t", file=f) + + +if __name__ == "__main__": + main() diff --git a/dateparser_scripts/get_cldr_data.py b/dateparser_scripts/get_cldr_data.py index 6e227c819..8fe764c8c 100644 --- a/dateparser_scripts/get_cldr_data.py +++ b/dateparser_scripts/get_cldr_data.py @@ -1,12 +1,12 @@ import json -import os import shutil -from collections import OrderedDict +from pathlib import Path +from typing import Any import regex as re from dateparser_scripts.order_languages import _get_language_locale_dict -from dateparser_scripts.utils import get_dict_difference, get_raw_data +from dateparser_scripts.utils import CLDR_JSON_DIR, get_dict_difference, get_raw_data APOSTROPHE_LOOK_ALIKE_CHARS = [ "\N{RIGHT SINGLE QUOTATION MARK}", # '\u2019' @@ -30,10 +30,8 @@ PM_PATTERN = re.compile(r"^\s*[Pp]\s*\.?\s*[Mm]\s*\.?\s*$") PARENTHESIS_PATTERN = re.compile(r"[\(\)]") -cldr_dates_full_dir = "../raw_data/cldr_dates_full/main/" - -def _filter_relative_string(relative_string): +def _filter_relative_string(relative_string: object) -> bool | re.Match[str] | None: return ( isinstance(relative_string, str) and RELATIVE_PATTERN.search(relative_string) @@ -41,25 +39,34 @@ def _filter_relative_string(relative_string): ) -def _filter_month_name(month_name): +def _filter_month_name(month_name: str) -> bool: return not DEFAULT_MONTH_PATTERN.match(month_name) -def _retrieve_locale_data(locale): - ca_gregorian_file = cldr_dates_full_dir + locale + "/ca-gregorian.json" - dateFields_file = cldr_dates_full_dir + locale + "/dateFields.json" - with open(ca_gregorian_file) as f: - cldr_gregorian_data = json.load(f, object_pairs_hook=OrderedDict) +def _retrieve_locale_data(locale: str) -> dict[str, Any]: # noqa: PLR0915 + def load(scope: str, file_id: str) -> Any: + file_path = ( + CLDR_JSON_DIR + / "cldr-json" + / f"cldr-{scope}-full" + / "main" + / locale + / f"{file_id}.json" + ) + with file_path.open() as f: + return json.load(f) - with open(dateFields_file) as g: - cldr_datefields_data = json.load(g, object_pairs_hook=OrderedDict) + cldr_gregorian_data = load("dates", "ca-gregorian") + cldr_datefields_data = load("dates", "dateFields") + _units = load("units", "units") gregorian_dict = cldr_gregorian_data["main"][locale]["dates"]["calendars"][ "gregorian" ] date_fields_dict = cldr_datefields_data["main"][locale]["dates"]["fields"] + units = _units["main"][locale]["units"]["long"] - json_dict = OrderedDict() + json_dict: dict[str, Any] = {} field_keys_1 = ["stand-alone", "format"] field_keys_2 = [ @@ -82,8 +89,10 @@ def _retrieve_locale_data(locale): except AttributeError: date_format_string = gregorian_dict["dateFormats"]["short"]["_value"].upper() + date_order_match = DATE_ORDER_PATTERN.search(date_format_string) + assert date_order_match is not None json_dict["date_order"] = DATE_ORDER_PATTERN.sub( - r"\1\2\3", DATE_ORDER_PATTERN.search(date_format_string).group() + r"\1\2\3", date_order_match.group() ) json_dict["january"] = list( @@ -287,12 +296,15 @@ def _retrieve_locale_data(locale): json_dict["day"] = [date_fields_dict[key]["displayName"] for key in day_keys] json_dict["hour"] = [date_fields_dict[key]["displayName"] for key in hour_keys] + hour_unit = units["duration-hour"]["displayName"] + if hour_unit not in json_dict["hour"]: + json_dict["hour"].append(hour_unit) json_dict["minute"] = [date_fields_dict[key]["displayName"] for key in minute_keys] json_dict["second"] = [date_fields_dict[key]["displayName"] for key in second_keys] - json_dict["relative-type"] = OrderedDict() + json_dict["relative-type"] = {} json_dict["relative-type"]["1 year ago"] = [ date_fields_dict[key]["relative-type--1"] for key in year_keys @@ -354,7 +366,7 @@ def _retrieve_locale_data(locale): date_fields_dict[key]["relative-type-0"] for key in second_keys ] - json_dict["relative-type-regex"] = OrderedDict() + json_dict["relative-type-regex"] = {} json_dict["relative-type-regex"]["in \\1 year"] = list( filter( @@ -513,54 +525,52 @@ def _retrieve_locale_data(locale): return json_dict -def _clean_string(given_string): +def _clean_string(given_string: str) -> str: given_string = RE_SANITIZE_APOSTROPHE.sub("'", given_string) given_string = given_string.replace(".", "") given_string = given_string.lower() return " ".join(given_string.split()) -def _clean_dict(json_dict): +def _clean_dict(json_dict: dict[str, Any]) -> dict[str, Any]: """Remove duplicates and sort""" for key, value in json_dict.items(): if isinstance(value, list): - json_dict[key] = sorted(OrderedDict.fromkeys(map(_clean_string, value))) + json_dict[key] = sorted(dict.fromkeys(map(_clean_string, value))) elif isinstance(value, dict): - json_dict[key] = OrderedDict(sorted(value.items())) + json_dict[key] = dict(sorted(value.items())) json_dict[key] = _clean_dict(json_dict[key]) - return OrderedDict(filter(lambda x: x[1], json_dict.items())) + return dict(filter(lambda x: x[1], json_dict.items())) -def main(): +def main() -> None: get_raw_data() language_locale_dict = _get_language_locale_dict() - parent_directory = "../dateparser_data/cldr_language_data" - directory = "../dateparser_data/cldr_language_data/date_translation_data/" - if not os.path.isdir(parent_directory): - os.mkdir(parent_directory) - if os.path.isdir(directory): + parent_directory = Path("../dateparser_data/cldr_language_data") + directory = parent_directory / "date_translation_data" + parent_directory.mkdir(exist_ok=True) + if directory.is_dir(): shutil.rmtree(directory) - os.mkdir(directory) + directory.mkdir() for language in language_locale_dict: json_language_dict = _clean_dict(_retrieve_locale_data(language)) - locale_specific_dict = OrderedDict() + locale_specific_dict: dict[str, dict[str, Any]] = {} locales_list = language_locale_dict[language] for locale in locales_list: json_locale_dict = _clean_dict(_retrieve_locale_data(locale)) locale_specific_dict[locale] = _clean_dict( get_dict_difference(json_language_dict, json_locale_dict) ) - json_language_dict["locale_specific"] = OrderedDict( + json_language_dict["locale_specific"] = dict( sorted(locale_specific_dict.items()) ) - filename = directory + language + ".json" - print("writing " + filename) + filename = directory / f"{language}.json" + print(f"writing {filename}") json_string = json.dumps( json_language_dict, indent=4, separators=(",", ": "), ensure_ascii=False ).encode("utf-8") - with open(filename, "wb") as f: - f.write(json_string) + filename.write_bytes(json_string) if __name__ == "__main__": diff --git a/dateparser_scripts/order_languages.py b/dateparser_scripts/order_languages.py index 39fa6affe..f23ecf3c9 100644 --- a/dateparser_scripts/order_languages.py +++ b/dateparser_scripts/order_languages.py @@ -1,29 +1,182 @@ +import contextlib import json import os -from collections import OrderedDict +from collections.abc import Iterable, Mapping +from pathlib import Path import regex as re import requests from parsel import Selector -from dateparser_scripts.utils import get_raw_data +from dateparser_scripts.utils import CLDR_JSON_DIR, get_raw_data -os.chdir(os.path.dirname(os.path.abspath(__file__))) +os.chdir(Path(__file__).resolve().parent) # Languages with insufficient translation data are excluded avoid_languages = {"cu", "kkj", "nds", "prg", "tk", "vai", "vai-Latn", "vai-Vaii", "vo"} +# Locales that CLDR 44 introduced but which dateparser does not enable yet: enabling +# them expands language auto-detection (and, for many, requires supplementary data), +# so they are handled separately from this data refresh to keep the supported set +# stable. This keeps the generated data limited to the locales already shipped. +cldr_44_new_languages = { + "aa", + "ab", + "an", + "ann", + "apc", + "arn", + "az-Arab", + "ba", + "bal", + "bal-Arab", + "bal-Latn", + "be-tarask", + "bew", + "bgc", + "bgn", + "bho", + "blo", + "blt", + "bm-Nkoo", + "bss", + "byn", + "ca-ES-valencia", + "cad", + "cch", + "ccp", + "ceb", + "cho", + "cic", + "co", + "csw", + "cv", + "doi", + "dv", + "el-polyton", + "en-Dsrt", + "en-Shaw", + "ff-Adlm", + "ff-Latn", + "frr", + "gaa", + "gez", + "gn", + "ha-Arab", + "hi-Latn", + "hnj", + "hnj-Hmnp", + "ia", + "ie", + "io", + "iu", + "iu-Latn", + "jbo", + "jv", + "kaj", + "kcg", + "ken", + "kgp", + "kpe", + "ks-Arab", + "ks-Deva", + "ku", + "kxv", + "kxv-Deva", + "kxv-Latn", + "kxv-Orya", + "kxv-Telu", + "la", + "lij", + "lmo", + "mai", + "mdf", + "mi", + "mic", + "mn-Mong", + "mni", + "mni-Beng", + "mni-Mtei", + "moh", + "ms-Arab", + "mus", + "myv", + "no", + "nqo", + "nr", + "nso", + "nv", + "ny", + "oc", + "osa", + "pap", + "pcm", + "pis", + "quc", + "raj", + "rhg", + "rhg-Rohg", + "rif", + "sa", + "sat", + "sat-Deva", + "sat-Olck", + "sc", + "scn", + "sd", + "sd-Arab", + "sd-Deva", + "sdh", + "shn", + "sid", + "skr", + "sma", + "smj", + "sms", + "ss", + "ssy", + "st", + "su", + "su-Latn", + "syr", + "szl", + "tg", + "tig", + "tn", + "tok", + "tpi", + "trv", + "trw", + "ts", + "tt", + "tyv", + "und", + "ve", + "vec", + "vmw", + "wa", + "wal", + "wbp", + "wo", + "xh", + "xnr", + "yrl", + "yue-Hans", + "yue-Hant", + "za", +} +avoid_languages |= cldr_44_new_languages -def _get_language_locale_dict(): - cldr_dates_full_dir = "../raw_data/cldr_dates_full/main/" - available_locale_names = os.listdir(cldr_dates_full_dir) + +def _get_language_locale_dict() -> dict[str, list[str]]: + cldr_dates_full_dir = CLDR_JSON_DIR / "cldr-json/cldr-dates-full/main/" + available_locale_names = [path.name for path in cldr_dates_full_dir.iterdir()] available_language_names = [ shortname for shortname in available_locale_names if not re.search(r"-[A-Z0-9]+$", shortname) ] - available_language_names.remove("root") - language_locale_dict = {} + language_locale_dict: dict[str, list[str]] = {} for language_name in available_language_names: language_locale_dict[language_name] = [] for locale_name in available_locale_names: @@ -31,13 +184,12 @@ def _get_language_locale_dict(): language_locale_dict[language_name].append(locale_name) for language in avoid_languages: - if language in language_locale_dict: - del language_locale_dict[language] + language_locale_dict.pop(language, None) return language_locale_dict -def _get_language_order(language_locale_dict): - def get_most_common_locales(): +def _get_language_order(language_locale_dict: Mapping[str, list[str]]) -> list[str]: + def get_most_common_locales() -> list[str]: # Order from https://w3techs.com/technologies/overview/content_language # Last updated on 03.10.2022 old_common_locales = [ @@ -82,7 +234,7 @@ def get_most_common_locales(): ] response = requests.get( - "https://w3techs.com/technologies/overview/content_language" + "https://w3techs.com/technologies/overview/content_language", timeout=60 ) sel = Selector(text=response.text) if response.ok: @@ -106,15 +258,17 @@ def get_most_common_locales(): return old_common_locales return new_most_common_locales - territory_info_file = "../raw_data/cldr_core/supplemental/territoryInfo.json" - with open(territory_info_file) as f: + territory_info_file = ( + CLDR_JSON_DIR / "cldr-json/cldr-core/supplemental/territoryInfo.json" + ) + with territory_info_file.open() as f: territory_content = json.load(f) territory_info_data = territory_content["supplemental"]["territoryInfo"] - language_population_dict = {} + language_population_dict: dict[str, float] = {} for territory in territory_info_data: population = int(territory_info_data[territory]["_population"]) - try: + with contextlib.suppress(Exception): lang_dict = territory_info_data[territory]["languagePopulation"] for language in lang_dict: language_population = ( @@ -124,8 +278,6 @@ def get_most_common_locales(): language_population_dict[language] += language_population else: language_population_dict[language] = language_population - except Exception: - pass most_common_locales = get_most_common_locales() language_order_with_duplicates = most_common_locales + sorted( @@ -135,17 +287,19 @@ def get_most_common_locales(): ) language_order = sorted( set(language_order_with_duplicates), - key=lambda x: language_order_with_duplicates.index(x), + key=language_order_with_duplicates.index, ) - for index in range(0, len(language_order)): + for index in range(len(language_order)): language_order[index] = re.sub(r"_", r"-", language_order[index]) cldr_languages = language_locale_dict.keys() - supplementary_date_directory = ( + supplementary_date_directory = Path( "../dateparser_data/supplementary_language_data/date_translation_data" ) - supplementary_languages = [x[:-5] for x in os.listdir(supplementary_date_directory)] + supplementary_languages = [ + path.stem for path in supplementary_date_directory.iterdir() + ] available_languages = set(cldr_languages).union(set(supplementary_languages)) language_order = [ shortname for shortname in language_order if shortname in available_languages @@ -159,11 +313,10 @@ def get_most_common_locales(): else: remaining_languages.append(language) language_order = language_order + sorted(remaining_languages) - language_order = list(map(str, language_order)) - return language_order + return list(map(str, language_order)) -def generate_language_map(language_order): +def generate_language_map(language_order: Iterable[str]) -> dict[str, list[str]]: data = {} for lang in sorted(language_order): if "-" not in lang: @@ -173,22 +326,20 @@ def generate_language_map(language_order): return data -def main(): +def main() -> None: get_raw_data() language_locale_dict = _get_language_locale_dict() language_order = _get_language_order(language_locale_dict) - parent_directory = "../dateparser/data/" - filename = "../dateparser/data/languages_info.py" - if not os.path.isdir(parent_directory): - os.mkdir(parent_directory) + parent_directory = Path("../dateparser/data") + parent_directory.mkdir(exist_ok=True) language_order_string = "language_order = " + json.dumps( language_order, separators=(",", ": "), indent=4 ) - complete_language_locale_dict = OrderedDict() + complete_language_locale_dict = {} for key in language_order: - if key in language_locale_dict.keys(): + if key in language_locale_dict: complete_language_locale_dict[key] = sorted(language_locale_dict[key]) else: complete_language_locale_dict[key] = [] @@ -209,8 +360,7 @@ def main(): + language_locale_dict_string + "\n" ) - with open(filename, "w") as f: - f.write(languages_info_string) + (parent_directory / "languages_info.py").write_text(languages_info_string) if __name__ == "__main__": diff --git a/dateparser_scripts/tz_abbreviation_conflicts.py b/dateparser_scripts/tz_abbreviation_conflicts.py new file mode 100644 index 000000000..0711ced38 --- /dev/null +++ b/dateparser_scripts/tz_abbreviation_conflicts.py @@ -0,0 +1,202 @@ +"""Cross-check dateparser's timezone-abbreviation table against the tz database. + +Many timezone abbreviations are genuinely ambiguous: several IANA tz database +zones use the same letters for different UTC offsets ("CST" is both US Central +Standard Time and China Standard Time). The tz database provides no preferred +answer for those, so ``dateparser/timezones.py`` keeps one arbitrary offset per +abbreviation, originally taken from a Wikipedia scrape. + +Some abbreviations are *not* ambiguous, though: every zone the tz database +names with those letters agrees on a single UTC offset. When dateparser's table +disagrees with that offset, its value is not "another valid reading" -- no zone +goes by that name at that offset. That was the case for "BST", which resolved +to +11 although the only zones named "BST" today are the UK ones, at +1 (see +#1321 and #1322). This script finds every such case generically, so the table +can be kept in sync without a one-off patch per abbreviation. + +Two kinds of conflict are reported: + +``unambiguous`` + The tz database maps the abbreviation to exactly one offset and dateparser + disagrees. The tz database offset should be preferred. +``unsupported`` + The tz database maps the abbreviation to several offsets and dateparser's + value is none of them. There is no single offset to prefer, so this needs a + human decision, but the current value is still unsupported by any zone. + +Zone data comes from ``pytz``, which is already a dateparser dependency and +bundles its own copy of the tz database. That keeps results identical on every +platform, unlike the standard library ``zoneinfo`` module, whose data comes +from the operating system and is missing entirely on Windows unless the +separate ``tzdata`` package is installed. + +What this can and cannot see +---------------------------- + +Only the abbreviations the tz database still prints are checked, around 50 of +the 400-odd in dateparser's table. The rest are invisible here and are left to +dateparser: + +* Modern tz database releases name a zone after its offset ("+11", "-0930") + unless the abbreviation is in common English use, so a zone can drop out of + this comparison without the abbreviation falling out of use. "BST" for + Bougainville is exactly that: the zone now prints "+11". What the check + really shows is that no zone *is named* "BST" at +11 any more, which is the + practical question for a parser. +* Abbreviations no zone uses in the reference window at all, such as ``AHST`` + or ``LMT``, are kept by dateparser so that historical text still parses. +* pytz ships ``MET`` as a copy of ``CET``, so it prints "CET"/"CEST" and the + ``MET``/``MEST`` abbreviations never reach this comparison. + +Run it to print a report; it exits non-zero when it finds anything:: + + python -m dateparser_scripts.tz_abbreviation_conflicts +""" + +from collections.abc import Collection, Mapping +from datetime import datetime +from typing import NamedTuple + +import pytz +import regex as re + +from dateparser.timezones import timezone_info_list + +# Years sampled to determine what an abbreviation means *today*. Both bounds +# are load-bearing, and the window is pinned deliberately, like the CLDR +# version in ``dateparser_scripts/utils.py``. +# +# The upper bound stays in settled years: the tz database records future +# daylight-saving rules as predictions that change between releases, so +# sampling them would make the result depend on the installed tz database +# version rather than on real usage. +# +# The lower bound keeps retired meanings out. Slide this window forward when +# refreshing the table, and do not widen it backwards: reaching further back +# re-admits abbreviations the tz database has since dropped and reports them as +# if they were current. Reaching back to 1999 picks up Guam's old "GST", which +# would report dateparser's "GST" (+4, Gulf Standard Time) as an unambiguous +# conflict against +10, even though Guam has used "ChST" since 2000. +REFERENCE_YEARS = range(2021, 2026) + +# Sampling January, April, July and October catches both the standard-time and +# the daylight-saving abbreviation of every zone, in either hemisphere. +REFERENCE_MONTHS = (1, 4, 7, 10) + +# The tz database uses names such as "+11" or "-0930" for zones that have no +# real abbreviation. They are not abbreviations, and dateparser matches numeric +# offsets through separate UTC/GMT patterns, so they are ignored here. +_NUMERIC_ZONE_NAME = re.compile(r"[+-]\d{2,4}") + + +class Conflict(NamedTuple): + abbreviation: str + kind: str + dateparser_offset: int + tz_database_offsets: list[int] + + +def static_tz_abbreviations() -> dict[str, int]: + """Return ``{abbreviation: offset_in_seconds}`` as dateparser resolves it. + + A few abbreviations are listed more than once in ``timezone_info_list`` + (``LMT`` appears four times with four different offsets). Only the first + entry can ever win: ``build_tz_offsets`` keeps the table order and + ``pop_tz_offset_from_string`` returns the first pattern that matches. So + the first entry, not the set of all of them, is what this comparison has + to use -- otherwise a wrong first entry would be masked by a correct later + one. + + Keys are upper-cased because dateparser matches abbreviations + case-insensitively, so a differently-cased entry such as ``ChST`` is the + same abbreviation and has to be compared as one. + """ + effective: dict[str, int] = {} + for group in timezone_info_list: + for name, offset in group["timezones"]: + effective.setdefault(name.upper(), offset) + return effective + + +def tz_database_abbreviations() -> dict[str, set[int]]: + """Return ``{abbreviation: {offset_in_seconds, ...}}`` from the tz database. + + Every zone is sampled, including the deprecated aliases (``US/Pacific``, + ``Asia/Calcutta``) that ``pytz.all_timezones`` lists alongside canonical + zones. Aliases resolve to the same rules as the zones they link to, so they + only ever repeat offsets a canonical zone already contributed; including + them costs nothing and keeps the scan independent of how pytz classifies + any individual zone. + """ + samples = [ + datetime(year, month, 15, 12, 0, 0) + for year in REFERENCE_YEARS + for month in REFERENCE_MONTHS + ] + abbreviations: dict[str, set[int]] = {} + for zone_name in pytz.all_timezones: + zone = pytz.timezone(zone_name) + for naive in samples: + localized = zone.localize(naive) + abbreviation = localized.tzname() + if not abbreviation or _NUMERIC_ZONE_NAME.fullmatch(abbreviation): + continue + utcoffset = localized.utcoffset() + assert utcoffset is not None + offset = int(utcoffset.total_seconds()) + abbreviations.setdefault(abbreviation.upper(), set()).add(offset) + return abbreviations + + +def find_conflicts( + static: Mapping[str, int] | None = None, + tz_database: Mapping[str, Collection[int]] | None = None, +) -> list[Conflict]: + """Return the sorted list of :class:`Conflict` between both tables. + + ``static`` and ``tz_database`` default to the real tables and are only + meant to be passed in by the tests. + + Abbreviations the tz database no longer uses at all are skipped: dateparser + deliberately keeps obsolete abbreviations such as ``AHST`` or ``LMT`` so + that historical text still parses, and the tz database has nothing to say + about them. + """ + static = static_tz_abbreviations() if static is None else static + tz_database = tz_database_abbreviations() if tz_database is None else tz_database + + conflicts = [] + for abbreviation, tz_database_offsets in tz_database.items(): + if abbreviation not in static: + continue + dateparser_offset = static[abbreviation] + if dateparser_offset in tz_database_offsets: + continue + kind = "unambiguous" if len(tz_database_offsets) == 1 else "unsupported" + conflicts.append( + Conflict(abbreviation, kind, dateparser_offset, sorted(tz_database_offsets)) + ) + return sorted(conflicts) + + +def main() -> int: + found = find_conflicts() + if not found: + print( + "No conflicts: every abbreviation dateparser shares with the tz " + "database resolves to an offset some zone actually uses." + ) + return 0 + for conflict in found: + if conflict.kind == "unambiguous": + detail = f"the tz database only ever uses {conflict.tz_database_offsets[0]}" + else: + detail = f"no zone uses it; options are {conflict.tz_database_offsets}" + print( + f"{conflict.abbreviation}: dateparser uses {conflict.dateparser_offset}, {detail}" + ) + return 1 + + +if __name__ == "__main__": + raise SystemExit(main()) diff --git a/dateparser_scripts/update_supported_languages_and_locales.py b/dateparser_scripts/update_supported_languages_and_locales.py index 53d5d8c45..358105e2d 100755 --- a/dateparser_scripts/update_supported_languages_and_locales.py +++ b/dateparser_scripts/update_supported_languages_and_locales.py @@ -1,12 +1,13 @@ #!/usr/bin/env python3 -import os +from collections.abc import Mapping, Sequence +from pathlib import Path from tempfile import TemporaryFile from dateparser.data.languages_info import language_locale_dict -def to_string(data): +def to_string(data: Mapping[str, Sequence[str]]) -> str: result = "" language_column_width = 18 for language in sorted(data): @@ -14,18 +15,16 @@ def to_string(data): locales = data[language] if locales: result += " " * (language_column_width - len(language)) - result += ", ".join("'{}'".format(locale) for locale in sorted(locales)) + result += ", ".join(f"'{locale}'" for locale in sorted(locales)) result += "\n" return result -def main(): - readme_path = os.path.join( - os.path.dirname(__file__), "..", "docs", "supported_locales.rst" - ) +def main() -> None: + readme_path = Path(__file__).parent.parent / "docs" / "supported_locales.rst" new_data = to_string(language_locale_dict) temporary_file = TemporaryFile("w+") - with open(readme_path) as readme_file: + with readme_path.open() as readme_file: delimiter = "============ ================================================================\n" delimiters_seen = 0 is_inside_table = False @@ -39,7 +38,7 @@ def main(): if is_inside_table: temporary_file.write(new_data) temporary_file.seek(0) - with open(readme_path, "w") as readme_file: + with readme_path.open("w") as readme_file: readme_file.write(temporary_file.read()) temporary_file.close() diff --git a/dateparser_scripts/utils.py b/dateparser_scripts/utils.py index a8ba6d1c5..9b6e1a9ac 100644 --- a/dateparser_scripts/utils.py +++ b/dateparser_scripts/utils.py @@ -1,42 +1,26 @@ -import os import shutil -from collections import OrderedDict +from pathlib import Path +from typing import Any from git import Repo +CLDR_JSON_DIR = (Path(__file__).parent / "../cldr-json").resolve() -def get_raw_data(): - cldr_version = "31.0.1" - raw_data_directory = "../raw_data" - cldr_data = { - "dates_full": { - "url": "https://github.com/unicode-cldr/cldr-dates-full.git", - "dir": "{}/cldr_dates_full/".format(raw_data_directory), - }, - "core": { - "url": "https://github.com/unicode-cldr/cldr-core.git", - "dir": "{}/cldr_core/".format(raw_data_directory), - }, - "rbnf": { - "url": "https://github.com/unicode-cldr/cldr-rbnf.git", - "dir": "{}/cldr_rbnf/".format(raw_data_directory), - }, - } +def get_raw_data() -> None: + cldr_version = "44.1.0" + url = "https://github.com/unicode-org/cldr-json.git" + if CLDR_JSON_DIR.is_dir(): + shutil.rmtree(CLDR_JSON_DIR) - if os.path.isdir(raw_data_directory): - # remove current raw data - shutil.rmtree(raw_data_directory) - os.mkdir(raw_data_directory) + print(f"Clonning {url} @ {cldr_version} on {CLDR_JSON_DIR}...") + Repo.clone_from(url, CLDR_JSON_DIR, branch=cldr_version, depth=1) - for name, data in cldr_data.items(): - print('Clonning "{}" from: {}'.format(name, data["url"])) - repo = Repo.clone_from(data["url"], data["dir"], branch="master") - repo.git.co(cldr_version) - -def get_dict_difference(parent_dict, child_dict): - difference_dict = OrderedDict() +def get_dict_difference( + parent_dict: dict[str, Any], child_dict: dict[str, Any] +) -> dict[str, Any]: + difference_dict = {} for key, child_value in child_dict.items(): parent_value = parent_dict.get(key) child_specific_value = None @@ -53,8 +37,10 @@ def get_dict_difference(parent_dict, child_dict): return difference_dict -def combine_dicts(primary_dict, supplementary_dict): - combined_dict = OrderedDict() +def combine_dicts( + primary_dict: dict[str, Any], supplementary_dict: dict[str, Any] +) -> dict[str, Any]: + combined_dict = {} for key, value in primary_dict.items(): if key in supplementary_dict: if isinstance(value, list): @@ -64,10 +50,8 @@ def combine_dicts(primary_dict, supplementary_dict): else: combined_dict[key] = supplementary_dict[key] else: - combined_dict[key] = primary_dict[key] - remaining_keys = [ - key for key in supplementary_dict.keys() if key not in primary_dict.keys() - ] + combined_dict[key] = value + remaining_keys = [key for key in supplementary_dict if key not in primary_dict] for key in remaining_keys: combined_dict[key] = supplementary_dict[key] return combined_dict diff --git a/dateparser_scripts/write_complete_data.py b/dateparser_scripts/write_complete_data.py index 903b8f383..fb954569a 100644 --- a/dateparser_scripts/write_complete_data.py +++ b/dateparser_scripts/write_complete_data.py @@ -1,7 +1,7 @@ import json -import os import shutil -from collections import OrderedDict +from pathlib import Path +from typing import Any import regex as re from ruamel.yaml import YAML @@ -9,69 +9,112 @@ from dateparser_scripts.order_languages import avoid_languages from dateparser_scripts.utils import combine_dicts -cldr_date_directory = "../dateparser_data/cldr_language_data/date_translation_data/" -supplementary_directory = "../dateparser_data/supplementary_language_data/" +root = Path(__file__).parent.parent + +cldr_date_directory = root / "dateparser_data/cldr_language_data/date_translation_data" +supplementary_directory = root / "dateparser_data/supplementary_language_data" supplementary_date_directory = ( - "../dateparser_data/supplementary_language_data/date_translation_data/" + root / "dateparser_data/supplementary_language_data/date_translation_data" ) -translation_data_directory = "../dateparser/data/" -date_translation_directory = "../dateparser/data/date_translation_data/" - -os.chdir(os.path.dirname(os.path.abspath(__file__))) +translation_data_directory = root / "dateparser/data" +date_translation_directory = root / "dateparser/data/date_translation_data" cldr_languages = list( - set(map(lambda x: x[:-5], os.listdir(cldr_date_directory))) - avoid_languages + {path.stem for path in cldr_date_directory.iterdir()} - avoid_languages ) -supplementary_languages = [x[:-5] for x in os.listdir(supplementary_date_directory)] +supplementary_languages = [path.stem for path in supplementary_date_directory.iterdir()] all_languages = set(cldr_languages).union(set(supplementary_languages)) RELATIVE_PATTERN = re.compile(r"\{0\}") +POSSESSIVE_DIGIT_PATTERN = re.compile(r"\\d\+\[\.,\]\?\\d\*") + + +def _make_possessive(s: str) -> str: + return POSSESSIVE_DIGIT_PATTERN.sub(r"\\d++[.,]?\\d*+", s) + +def _to_plain_types(obj: Any) -> Any: + """Recursively convert ruamel.yaml CommentedMap/CommentedSeq to plain + dict/list so that json.dumps produces stable output across all + Python versions. -def _modify_relative_data(relative_data): - modified_relative_data = OrderedDict() + Python 3.14 changed the json C encoder to bypass the Python-level + ``__iter__``/``items()`` of dict subclasses and access the underlying C + dict directly. ruamel.yaml's CommentedMap relies on its Python-level + iteration for correct key ordering, so the C shortcut produces a + different (non-deterministic) key order on 3.14. Converting to plain + types before serialisation avoids the issue entirely. + """ + if isinstance(obj, dict): + return {k: _to_plain_types(v) for k, v in obj.items()} + if isinstance(obj, list): + return [_to_plain_types(v) for v in obj] + return obj + + +def _modify_relative_data( + relative_data: dict[str, list[str]], +) -> dict[str, list[str]]: + modified_relative_data = {} for key, value in relative_data.items(): for i, string in enumerate(value): - string = RELATIVE_PATTERN.sub(r"(\\d+[.,]?\\d*)", string) - value[i] = string + value[i] = _make_possessive( + RELATIVE_PATTERN.sub(r"(\\d++[.,]?\\d*+)", string) + ) modified_relative_data[key] = value return modified_relative_data -def _modify_data(language_data): +def _modify_simplifications(simplifications: list[dict[str, Any]]) -> None: + for simplification in simplifications: + for pattern in list(simplification.keys()): + new_pattern = _make_possessive(pattern) + if new_pattern != pattern: + simplification[new_pattern] = simplification.pop(pattern) + + +def _modify_data(language_data: dict[str, Any]) -> None: relative_data = language_data.get("relative-type-regex", {}) relative_data = _modify_relative_data(relative_data) + simplifications = language_data.get("simplifications", []) + _modify_simplifications(simplifications) locale_specific_data = language_data.get("locale_specific", {}) - for _, info in locale_specific_data.items(): + for info in locale_specific_data.values(): locale_relative_data = info.get("relative-type-regex", {}) locale_relative_data = _modify_relative_data(locale_relative_data) -def _get_complete_date_translation_data(language): - cldr_data = {} - supplementary_data = {} +def _get_complete_date_translation_data(language: str) -> dict[str, Any]: + cldr_data: dict[str, Any] = {} + supplementary_data: dict[str, Any] = {} if language in cldr_languages: - with open(cldr_date_directory + language + ".json") as f: - cldr_data = json.load(f, object_pairs_hook=OrderedDict) + with (cldr_date_directory / f"{language}.json").open() as f: + cldr_data = json.load(f) if language in supplementary_languages: - with open(supplementary_date_directory + language + ".yaml") as g: + with (supplementary_date_directory / f"{language}.yaml").open() as g: yaml = YAML() - supplementary_data = OrderedDict(yaml.load(g)) + supplementary_data = dict(yaml.load(g)) complete_data = combine_dicts(cldr_data, supplementary_data) if "name" not in complete_data: complete_data["name"] = language return complete_data -def _write_file(filename, text, mode, in_memory, in_memory_result): +def _write_file( + filename: Path, + text: str | bytes, + mode: str, + in_memory: bool, + in_memory_result: dict[Path, str | bytes], +) -> None: if in_memory: in_memory_result[filename] = text else: - with open(filename, mode) as out: + with Path(filename).open(mode) as out: out.write(text) -def write_complete_data(in_memory=False): +def write_complete_data(in_memory: bool = False) -> dict[Path, str | bytes]: """ This function is responsible of generating the needed py files from the CLDR files (JSON format) and supplementary language data (YAML format). @@ -79,29 +122,29 @@ def write_complete_data(in_memory=False): Use it with in_memory=True to avoid writing real files and getting a dictionary containing the file names and their content (used when testing). """ - in_memory_result = {} + in_memory_result: dict[Path, str | bytes] = {} if not in_memory: - if not os.path.isdir(translation_data_directory): - os.mkdir(translation_data_directory) - if os.path.isdir(date_translation_directory): + translation_data_directory.mkdir(exist_ok=True) + if date_translation_directory.is_dir(): shutil.rmtree(date_translation_directory) - os.mkdir(date_translation_directory) + date_translation_directory.mkdir() - with open(supplementary_directory + "base_data.yaml") as f: + with (supplementary_directory / "base_data.yaml").open() as f: yaml = YAML() base_data = yaml.load(f) for language in all_languages: date_translation_data = _get_complete_date_translation_data(language) date_translation_data = combine_dicts(date_translation_data, base_data) + date_translation_data = _to_plain_types(date_translation_data) _modify_data(date_translation_data) translation_data = json.dumps( date_translation_data, indent=4, separators=(",", ": "), ensure_ascii=False ) out_text = ("info = " + translation_data + "\n").encode("utf-8") _write_file( - date_translation_directory + language + ".py", + date_translation_directory / f"{language}.py", out_text, "wb", in_memory, @@ -110,18 +153,19 @@ def write_complete_data(in_memory=False): init_text = ( "from dateparser.data import date_translation_data\n" - "from .languages_info import language_order, language_locale_dict\n" + "\n" + "from .languages_info import language_locale_dict, language_order\n" ) _write_file( - translation_data_directory + "__init__.py", + translation_data_directory / "__init__.py", init_text, "w", False, in_memory_result, ) _write_file( - date_translation_directory + "__init__.py", "", "w", False, in_memory_result + date_translation_directory / "__init__.py", "", "w", False, in_memory_result ) return in_memory_result diff --git a/docs/conf.py b/docs/conf.py index 3035675d7..66888071a 100755 --- a/docs/conf.py +++ b/docs/conf.py @@ -10,14 +10,13 @@ # file. -import os import sys +from pathlib import Path import dateparser # Get the project root dir, which is the parent dir of this -cwd = os.getcwd() -project_root = os.path.dirname(cwd) +project_root = str(Path.cwd().parent) # Insert the project root dir as the first element in the PYTHONPATH. # This lets us ensure that the source package is imported, and that its @@ -46,7 +45,7 @@ # General information about the project. project = "DateParser" -copyright = "2014, Scrapinghub" +project_copyright = "2014, Scrapinghub" # The version info for the project you're documenting, acts as replacement # for |version| and |release|, also used in various other places throughout diff --git a/docs/custom_language_detection.rst b/docs/custom_language_detection.rst index c20d829c9..6598ac4a8 100644 --- a/docs/custom_language_detection.rst +++ b/docs/custom_language_detection.rst @@ -3,8 +3,7 @@ Custom language detection ========================= `dateparser` allows to customize the language detection behavior by using the ``detect_languages_function`` parameter. -It currently supports two language detection libraries out of the box: `fastText `_ -and `langdetect `_, and allows you to implement your own custom language detection. +It supports the `langdetect `_ library out of the box, and allows you to implement your own custom language detection. .. warning:: @@ -14,51 +13,24 @@ and `langdetect `_, and allows you to i Built-in implementations ======================== -fastText -~~~~~~~~ -Language detection with fastText. - -Import the fastText wrapper and pass it as ``detect_languages_function`` -parameter. Example:: - - >>> from dateparser.custom_language_detection.fasttext import detect_languages - >>> dateparser.parse('12/12/12', detect_languages_function=detect_languages) - -The fastText integration currently supports the large and the small models. -Find more information about `fasttext `__ models. -You can download your model of choice using ``dateparser-download``. - -Downloading small model:: - - >>> dateparser-download --fasttext small - -Downloading large model:: - - >>> dateparser-download --fasttext large - -Deleting all cached models:: - - >>> dateparser-download --clear_cache - -.. note:: - - If no model has been downloaded, the fastText wrapper downloads and uses - the small model by default. - langdetect ~~~~~~~~~~ Language detection with langdetect. -Import the langdetect wrapper and pass it as ``detect_languages_function`` +To use langdetect, first install it:: + + pip install dateparser[langdetect] + +Then import the langdetect wrapper and pass it as ``detect_languages_function`` parameter. Example:: >>> from dateparser.custom_language_detection.langdetect import detect_languages >>> dateparser.parse('12/12/12', detect_languages_function=detect_languages) - .. note:: - From some tests we did, we recommend to use ``fastText`` for faster and more accurate results. + **Deprecated fastText support**: The fastText integration has been removed as the library + is archived and no longer maintained. If you were using fastText, please migrate to langdetect. Custom implementation ===================== diff --git a/docs/dateparser.rst b/docs/dateparser.rst index d28072706..75c32ba27 100644 --- a/docs/dateparser.rst +++ b/docs/dateparser.rst @@ -44,6 +44,14 @@ dateparser.freshness_date_parser module :undoc-members: :show-inheritance: +dateparser.search module +------------------------ + +.. automodule:: dateparser.search + :members: + :undoc-members: + :show-inheritance: + dateparser.timezone_parser module --------------------------------- diff --git a/docs/index.rst b/docs/index.rst index 0159b6adc..d805b246e 100644 --- a/docs/index.rst +++ b/docs/index.rst @@ -2,42 +2,11 @@ dateparser -- python parser for human readable dates ==================================================== -.. image:: https://img.shields.io/pypi/dm/dateparser - :target: https://pypi.python.org/pypi/dateparser - :alt: pypi downloads - -.. image:: https://img.shields.io/pypi/v/dateparser.svg - :target: https://pypi.python.org/pypi/dateparser - :alt: pypi version - -.. image:: https://codecov.io/gh/scrapinghub/dateparser/branch/master/graph/badge.svg - :target: https://codecov.io/gh/scrapinghub/dateparser - :alt: Code Coverage - -.. image:: https://github.com/scrapinghub/dateparser/workflows/Build/badge.svg - :target: https://github.com/scrapinghub/dateparser/actions - :alt: Github Build - -.. image:: https://readthedocs.org/projects/dateparser/badge/?version=latest - :target: http://dateparser.readthedocs.org/en/latest/?badge=latest - :alt: Documentation Status - - -`dateparser` provides modules to easily parse localized dates in almost -any string formats commonly found on web pages. - - -Documentation -============= - -This documentation is built automatically and can be found on -`Read the Docs `_. - - -.. include:: introduction.rst +.. include:: ../README.rst + :start-after: docs-include-marker Indices and tables -================== +------------------ Contents: @@ -45,11 +14,11 @@ Contents: .. toctree:: :maxdepth: 2 - introduction installation usage settings custom_language_detection + performance supported_locales contributing modules diff --git a/docs/installation.rst b/docs/installation.rst index 9148904c9..d80cb9f3c 100644 --- a/docs/installation.rst +++ b/docs/installation.rst @@ -14,4 +14,4 @@ If you want to install from the latest sources, you can do:: $ git clone https://github.com/scrapinghub/dateparser.git $ cd dateparser - $ python setup.py install + $ pip install . diff --git a/docs/introduction.rst b/docs/introduction.rst deleted file mode 100644 index bc3445f8d..000000000 --- a/docs/introduction.rst +++ /dev/null @@ -1,275 +0,0 @@ -========================== -Introduction to dateparser -========================== - - -Features -======== - -* Generic parsing of dates in over 200 language locales plus numerous formats in a language agnostic fashion. -* Generic parsing of relative dates like: ``'1 min ago'``, ``'2 weeks ago'``, ``'3 months, 1 week and 1 day ago'``, ``'in 2 days'``, ``'tomorrow'``. -* Generic parsing of dates with time zones abbreviations or UTC offsets like: ``'August 14, 2015 EST'``, ``'July 4, 2013 PST'``, ``'21 July 2013 10:15 pm +0500'``. -* Date lookup in longer texts. -* Support for non-Gregorian calendar systems. See `Supported Calendars`_. -* Extensive test coverage. - - -Basic Usage -=========== - -The most straightforward way is to use the `dateparser.parse <#dateparser.parse>`_ function, -that wraps around most of the functionality in the module. - -.. automodule:: dateparser - :members: parse - :noindex: - - -Popular Formats ---------------- - - >>> import dateparser - >>> dateparser.parse('12/12/12') - datetime.datetime(2012, 12, 12, 0, 0) - >>> dateparser.parse('Fri, 12 Dec 2014 10:55:50') - datetime.datetime(2014, 12, 12, 10, 55, 50) - >>> dateparser.parse('Martes 21 de Octubre de 2014') # Spanish (Tuesday 21 October 2014) - datetime.datetime(2014, 10, 21, 0, 0) - >>> dateparser.parse('Le 11 Décembre 2014 à 09:00') # French (11 December 2014 at 09:00) - datetime.datetime(2014, 12, 11, 9, 0) - >>> dateparser.parse('13 января 2015 г. в 13:34') # Russian (13 January 2015 at 13:34) - datetime.datetime(2015, 1, 13, 13, 34) - >>> dateparser.parse('1 เดือนตุลาคม 2005, 1:00 AM') # Thai (1 October 2005, 1:00 AM) - datetime.datetime(2005, 10, 1, 1, 0) - -This will try to parse a date from the given string, attempting to -detect the language each time. - -You can specify the language(s), if known, using ``languages`` argument. In this case, given languages are used and language detection is skipped: - - >>> dateparser.parse('2015, Ago 15, 1:08 pm', languages=['pt', 'es']) - datetime.datetime(2015, 8, 15, 13, 8) - -If you know the possible formats of the dates, you can -use the ``date_formats`` argument: - - >>> dateparser.parse('22 Décembre 2010', date_formats=['%d %B %Y']) - datetime.datetime(2010, 12, 22, 0, 0) - - -Relative Dates --------------- - - >>> parse('1 hour ago') - datetime.datetime(2015, 5, 31, 23, 0) - >>> parse('Il ya 2 heures') # French (2 hours ago) - datetime.datetime(2015, 5, 31, 22, 0) - >>> parse('1 anno 2 mesi') # Italian (1 year 2 months) - datetime.datetime(2014, 4, 1, 0, 0) - >>> parse('yaklaşık 23 saat önce') # Turkish (23 hours ago) - datetime.datetime(2015, 5, 31, 1, 0) - >>> parse('Hace una semana') # Spanish (a week ago) - datetime.datetime(2015, 5, 25, 0, 0) - >>> parse('2小时前') # Chinese (2 hours ago) - datetime.datetime(2015, 5, 31, 22, 0) - -.. note:: Testing above code might return different values for you depending on your environment's current date and time. - -.. note:: For `Finnish` language, please specify ``settings={'SKIP_TOKENS': []}`` to correctly parse relative dates. - -OOTB Language Based Date Order Preference ------------------------------------------ - - >>> # parsing ambiguous date - >>> parse('02-03-2016') # assumes english language, uses MDY date order - datetime.datetime(2016, 2, 3, 0, 0) - >>> parse('le 02-03-2016') # detects french, uses DMY date order - datetime.datetime(2016, 3, 2, 0, 0) - -.. note:: Ordering is not locale based, that's why do not expect `DMY` order for UK/Australia English. You can specify date order in that case as follows using :ref:`settings`: - - >>> parse('18-12-15 06:00', settings={'DATE_ORDER': 'DMY'}) - datetime.datetime(2015, 12, 18, 6, 0) - -For more on date order, please look at :ref:`settings`. - - -Timezone and UTC Offset ------------------------ - -By default, `dateparser` returns tzaware `datetime` if timezone is present in date string. Otherwise, it returns a naive `datetime` object. - - >>> parse('January 12, 2012 10:00 PM EST') - datetime.datetime(2012, 1, 12, 22, 0, tzinfo=) - - >>> parse('January 12, 2012 10:00 PM -0500') - datetime.datetime(2012, 1, 12, 22, 0, tzinfo=) - - >>> parse('2 hours ago EST') - datetime.datetime(2017, 3, 10, 15, 55, 39, 579667, tzinfo=) - - >>> parse('2 hours ago -0500') - datetime.datetime(2017, 3, 10, 15, 59, 30, 193431, tzinfo=) - - If date has no timezone name/abbreviation or offset, you can specify it using `TIMEZONE` setting. - - >>> parse('January 12, 2012 10:00 PM', settings={'TIMEZONE': 'US/Eastern'}) - datetime.datetime(2012, 1, 12, 22, 0) - - >>> parse('January 12, 2012 10:00 PM', settings={'TIMEZONE': '+0500'}) - datetime.datetime(2012, 1, 12, 22, 0) - -``TIMEZONE`` option may not be useful alone as it only attaches given timezone to -resultant ``datetime`` object. But can be useful in cases where you want conversions from and to different -timezones or when simply want a tzaware date with given timezone info attached. - - >>> parse('January 12, 2012 10:00 PM', settings={'TIMEZONE': 'US/Eastern', 'RETURN_AS_TIMEZONE_AWARE': True}) - datetime.datetime(2012, 1, 12, 22, 0, tzinfo=) - - - >>> parse('10:00 am', settings={'TIMEZONE': 'EST', 'TO_TIMEZONE': 'EDT'}) - datetime.datetime(2016, 9, 25, 11, 0) - -Some more use cases for conversion of timezones. - - >>> parse('10:00 am EST', settings={'TO_TIMEZONE': 'EDT'}) # date string has timezone info - datetime.datetime(2017, 3, 12, 11, 0, tzinfo=) - - >>> parse('now EST', settings={'TO_TIMEZONE': 'UTC'}) # relative dates - datetime.datetime(2017, 3, 10, 23, 24, 47, 371823, tzinfo=) - -In case, no timezone is present in date string or defined in :ref:`settings`. You can still -return tzaware ``datetime``. It is especially useful in case of relative dates when uncertain -what timezone is relative base. - - >>> parse('2 minutes ago', settings={'RETURN_AS_TIMEZONE_AWARE': True}) - datetime.datetime(2017, 3, 11, 4, 25, 24, 152670, tzinfo=) - -In case, you want to compute relative dates in UTC instead of default system's local timezone, you can use `TIMEZONE` setting. - - >>> parse('4 minutes ago', settings={'TIMEZONE': 'UTC'}) - datetime.datetime(2017, 3, 10, 23, 27, 59, 647248, tzinfo=) - -.. note:: In case, when timezone is present both in string and also specified using :ref:`settings`, string is parsed into tzaware representation and then converted to timezone specified in :ref:`settings`. - - >>> parse('10:40 pm PKT', settings={'TIMEZONE': 'UTC'}) - datetime.datetime(2017, 3, 12, 17, 40, tzinfo=) - - >>> parse('20 mins ago EST', settings={'TIMEZONE': 'UTC'}) - datetime.datetime(2017, 3, 12, 21, 16, 0, 885091, tzinfo=) - -For more on timezones, please look at :ref:`settings`. - - -Incomplete Dates ----------------- - - >>> from dateparser import parse - >>> parse('December 2015') # default behavior - datetime.datetime(2015, 12, 16, 0, 0) - >>> parse('December 2015', settings={'PREFER_DAY_OF_MONTH': 'last'}) - datetime.datetime(2015, 12, 31, 0, 0) - >>> parse('December 2015', settings={'PREFER_DAY_OF_MONTH': 'first'}) - datetime.datetime(2015, 12, 1, 0, 0) - - >>> parse('March') - datetime.datetime(2015, 3, 16, 0, 0) - >>> parse('March', settings={'PREFER_DATES_FROM': 'future'}) - datetime.datetime(2016, 3, 16, 0, 0) - >>> # parsing with preference set for 'past' - >>> parse('August', settings={'PREFER_DATES_FROM': 'past'}) - datetime.datetime(2015, 8, 15, 0, 0) - - >>> import dateparser - >>> dateparser.parse("2015") # default behavior - datetime.datetime(2015, 3, 27, 0, 0) - >>> dateparser.parse("2015", settings={"PREFER_MONTH_OF_YEAR": "last"}) - datetime.datetime(2015, 12, 27, 0, 0) - >>> dateparser.parse("2015", settings={"PREFER_MONTH_OF_YEAR": "first"}) - datetime.datetime(2015, 1, 27, 0, 0) - >>> dateparser.parse("2015", settings={"PREFER_MONTH_OF_YEAR": "current"}) - datetime.datetime(2015, 3, 27, 0, 0) - -You can also ignore parsing incomplete dates altogether by setting `STRICT_PARSING` flag as follows: - - >>> parse('December 2015', settings={'STRICT_PARSING': True}) - None - -For more on handling incomplete dates, please look at :ref:`settings`. - - -Search for Dates in Longer Chunks of Text ------------------------------------------ - -.. warning:: Support for searching dates is really limited and needs a lot of improvement, we look forward to community's contribution to get better on that part. See ":ref:`contributing`". - - -You can extract dates from longer strings of text. They are returned as list of tuples with text chunk containing the date and parsed datetime object. - - -.. automodule:: dateparser.search - :members: search_dates - :noindex: - -Time Span Detection -------------------- - -The `search_dates` function can detect time spans from expressions like "past month", "last week", etc. When `RETURN_TIME_SPAN` is enabled, it returns start and end dates for the detected period. - -.. code-block:: python - - >>> search_dates("Messages from the past month", settings={'RETURN_TIME_SPAN': True}) - [('past month (start)', datetime.datetime(2024, 11, 7, 0, 0)), - ('past month (end)', datetime.datetime(2024, 12, 7, 23, 59, 59, 999999))] - -Advanced Usage -============== -If you need more control over what is being parser check the :ref:`settings` section as well as the :ref:`using-datedataparser` section. - - -Dependencies -============ - -`dateparser` relies on following libraries in some ways: - - * dateutil_'s module ``relativedelta`` for its freshness parser. - * convertdate_ to convert *Jalali* dates to *Gregorian*. - * hijridate_ to convert *Hijri* dates to *Gregorian*. - * tzlocal_ to reliably get local timezone. - * ruamel.yaml_ (optional) for operations on language files. - -.. _dateutil: https://pypi.python.org/pypi/python-dateutil -.. _convertdate: https://pypi.python.org/pypi/convertdate -.. _hijridate: https://pypi.python.org/pypi/hijridate -.. _tzlocal: https://pypi.python.org/pypi/tzlocal -.. _ruamel.yaml: https://pypi.python.org/pypi/ruamel.yaml - -Supported languages and locales -=============================== -You can check the supported locales by visiting the ":ref:`supported-locales`" section. - - -Supported Calendars -=================== - -Apart from the Georgian calendar, `dateparser` supports the `Persian Jalali calendar` and the `Hijri/Islami calendar` - -To be able to use them you need to install the `calendar` extra by typing: - - pip install dateparser[calendars] - - -* Example using the `Persian Jalali calendar`. For more information, refer to `Persian Jalali Calendar `_. - - >>> from dateparser.calendars.jalali import JalaliCalendar - >>> JalaliCalendar('جمعه سی ام اسفند ۱۳۸۷').get_date() - DateData(date_obj=datetime.datetime(2009, 3, 20, 0, 0), period='day', locale=None) - - -* Example using the `Hijri/Islamic Calendar`. For more information, refer to `Hijri Calendar `_. - - >>> from dateparser.calendars.hijri import HijriCalendar - >>> HijriCalendar('17-01-1437 هـ 08:30 مساءً').get_date() - DateData(date_obj=datetime.datetime(2015, 10, 30, 20, 30), period='day', locale=None) - -.. note:: `HijriCalendar` only works with Python ≥ 3.7. diff --git a/docs/performance.rst b/docs/performance.rst new file mode 100644 index 000000000..1e863593e --- /dev/null +++ b/docs/performance.rst @@ -0,0 +1,47 @@ +.. _performance: + +=========== +Performance +=========== + +Limit the languages +------------------- + +By default, the language of each input string is detected among all supported +languages. If you know which languages your input can be in, pass them through +the ``languages`` or ``locales`` parameter: + + >>> import dateparser + >>> dateparser.parse('12 de marzo de 2020', languages=['es']) + datetime.datetime(2020, 3, 12, 0, 0) + +Reuse a parser +-------------- + +:func:`dateparser.parse` creates a new :class:`DateDataParser +` on every call that sets any parameter or +setting. To parse many strings with the same parameters and settings, create a +:class:`DateDataParser ` once and reuse it: + + >>> from dateparser.date import DateDataParser + >>> ddp = DateDataParser(languages=['es'], settings={'PARSERS': ['absolute-time']}) + >>> ddp.get_date_data('12 de marzo de 2020') + DateData(date_obj=datetime.datetime(2020, 3, 12, 0, 0), period='day', locale='es') + +Limit the parsers +----------------- + +Set the ``PARSERS`` :ref:`setting ` to the parsers that your input +needs, as in the example above, which skips relative dates like “3 days ago”. + +Try previous locales first +-------------------------- + +With ``try_previous_locales=True``, a :class:`DateDataParser +` first tries the locales that parsed earlier +strings, which is faster when most strings share a locale: + + >>> ddp = DateDataParser(try_previous_locales=True) + +The result for a string that is valid in more than one locale, e.g. with a +different date order, then depends on the strings parsed before it. diff --git a/docs/settings.rst b/docs/settings.rst index c2d5bd724..166db0972 100644 --- a/docs/settings.rst +++ b/docs/settings.rst @@ -37,6 +37,22 @@ Date Order >>> parse('le 02-03-2016', settings={'DATE_ORDER': 'MDY', 'PREFER_LOCALE_DATE_ORDER': False}) datetime.datetime(2016, 2, 3, 0, 0) # MDY worked! +``STRICT_DATE_ORDER``: defaults to ``'none'``. ``DATE_ORDER`` is a preference: a number that does not fit where the order puts it is read as another part of the date. ``13`` is not a valid month, so it is read as the day where ``MDY`` puts the month, and any number that is not a valid day or month is a valid two-digit year, so ``32`` becomes the year 2032: + + >>> parse('13/12/10', settings={'DATE_ORDER': 'MDY'}) + datetime.datetime(2010, 12, 13, 0, 0) + >>> parse('32 DEC 10', settings={'DATE_ORDER': 'DMY'}) + datetime.datetime(2032, 12, 10, 0, 0) + +Set it to ``'year'`` to read a two-digit year only from the position ``DATE_ORDER`` gives the year, or to ``'all'`` to read the day, month and year only in the order ``DATE_ORDER`` gives. A date string that does not fit then gives ``None``: + + >>> parse('32 DEC 10', settings={'DATE_ORDER': 'DMY', 'STRICT_DATE_ORDER': 'year'}) + >>> parse('13/12/10', settings={'DATE_ORDER': 'MDY', 'STRICT_DATE_ORDER': 'year'}) + datetime.datetime(2010, 12, 13, 0, 0) + >>> parse('13/12/10', settings={'DATE_ORDER': 'MDY', 'STRICT_DATE_ORDER': 'all'}) + +``'year'`` and ``'all'`` raise a ``SettingValidationError`` unless ``DATE_ORDER`` is given too. Only the parts read from numbers are checked, and a four-digit year is read wherever it is, so ``'32 DEC'`` with ``DMY`` is still December 2032. Some dates that are read correctly without the setting are rejected, such as ``'95年12月10日'`` with ``MDY``: once translated, it is ``95-12-10``, with nothing left to mark the year. + Timezone Related Configurations +++++++++++++++++++++++++++++++ @@ -97,7 +113,7 @@ If date string is missing some part, this option ensures consistent results depe datetime.datetime(2016, 3, 16, 0, 0) >>> # parsing with preference set for 'past' >>> parse('August', settings={'PREFER_DATES_FROM': 'past'}) - datetime.datetime(2015, 8, 15, 0, 0) + datetime.datetime(2014, 8, 16, 0, 0) ``RELATIVE_BASE``: allows setting the base datetime to use for interpreting partial or relative date strings. Defaults to the current date and time. @@ -155,6 +171,50 @@ For example, assuming current date is `June 16, 2019`: >>> parse('March 12, 2012', settings={'REQUIRE_PARTS': ['day', 'month', 'year']}) datetime.datetime(2012, 3, 12, 0, 0) +``IGNORE_SURROUNDING_TEXT``: defaults to ``False``. By default, the whole input string +must be a date, so a date wrapped in surrounding text is not parsed. When this setting +is enabled and the whole string could not be parsed as a date, dateparser retries +ignoring the words at the beginning and at the end of the string that the tried +language does not recognize as date-related: + + >>> parse('Actualisé le 17 avril 2019', languages=['fr']) + None + >>> parse('Actualisé le 17 avril 2019', languages=['fr'], settings={'IGNORE_SURROUNDING_TEXT': True}) + datetime.datetime(2019, 4, 17, 0, 0) + >>> parse('Published on 16/04/2019', settings={'IGNORE_SURROUNDING_TEXT': True}) + datetime.datetime(2019, 4, 16, 0, 0) + +Only the edges of the string are affected. An unrecognized word inside the date still +prevents parsing, and strings that can be parsed as a whole are parsed exactly as if +the setting was disabled: + + >>> parse('17 foobar avril 2019', languages=['fr'], settings={'IGNORE_SURROUNDING_TEXT': True}) + None + +Stripping stops at the first token the language *does* recognize, and a number counts +as recognized. So surrounding text that contains a number of its own (an id, a page +number, a count) is not ignored, and the string is not parsed: + + >>> parse('invoice 12345 paid on 3 March 2019', settings={'IGNORE_SURROUNDING_TEXT': True}) + None + +To extract a date out of arbitrary text that does not follow this shape, use +:func:`dateparser.search.search_dates` instead, which scans the whole string rather +than only trimming its edges. + +.. warning:: When this setting is enabled, discarded edge text is dropped even if it + could have changed the meaning of the date, and what remains is parsed as if it + were the whole input. As a result, strings that merely contain date-like words can + produce a date, e.g. ``'Chapter 12 March of the Penguins'``. A recognized timezone is + kept and applied only when it is the last token of the string (e.g. + ``'... 1:21 PM EST'``); a timezone before the date, one followed by further + unrecognized text, or any timezone name the parser does not recognize, is discarded + with the rest of the surrounding text (use + :func:`dateparser.search.search_dates` for such input). Enable this setting only when + the input is expected to contain a date, and consider combining it with + ``STRICT_PARSING`` or ``REQUIRE_PARTS`` to discard remainders that are not complete + dates. + Language Detection ++++++++++++++++++ @@ -163,7 +223,7 @@ Language Detection >>> from dateparser.date import DateDataParser >>> DateDataParser(settings={'SKIP_TOKENS': ['de']}).get_date_data(u'27 Haziran 1981 de') # Turkish (at 27 June 1981) - DateData(date_obj=datetime.datetime(1981, 6, 27, 0, 0), period='day', locale='tr') + DateData(date_obj=datetime.datetime(1981, 6, 27, 0, 0), period='day', locale='tr', parts=('year', 'month', 'day')) ``NORMALIZE``: applies unicode normalization (removing accents, diacritics...) when parsing the words. Defaults to True. @@ -174,16 +234,52 @@ Language Detection datetime.datetime(2015, 12, 4, 0, 0) -Default Languages +Default languages +++++++++++++++++ -``DEFAULT_LANGUAGES``: It is a ``list`` of language codes in ISO 639 that will be used as default -languages for parsing when language detection fails. eg. ["en", "fr"]: +``DEFAULT_LANGUAGES``: a ``list`` of ISO 639 language codes to fall back to +when parsing fails with every other language, i.e. those given through the +``languages`` or ``locales`` arguments of :func:`dateparser.parse` or those +detected. These fallback languages are tried even if the input contains no word +of theirs: >>> from dateparser import parse - >>> parse('3 de marzo de 2020', settings={'DEFAULT_LANGUAGES': ["es"]}) + >>> parse('3 de marzo de 2020', languages=['en']) + >>> parse('3 de marzo de 2020', languages=['en'], settings={'DEFAULT_LANGUAGES': ['es']}) + datetime.datetime(2020, 3, 3, 0, 0) + +It is especially useful with ``detect_languages_function``, to cover input for +which language detection fails. + +Language Order +++++++++++++++ + +``USE_GIVEN_LANGUAGE_ORDER``: defaults to ``False``. By default, the languages and +locales passed through the ``languages`` and ``locales`` arguments are tried in the +order of the most common languages, regardless of the order in which they are given. +Set this to ``True`` to instead try them in the order in which they are given, which +is useful when that order already reflects a preference (for example, the output of a +language detector ordered by confidence): + + >>> import dateparser + >>> dateparser.parse('11/12/2020', languages=['es', 'en']) + datetime.datetime(2020, 11, 12, 0, 0) + >>> dateparser.parse('11/12/2020', languages=['es', 'en'], settings={'USE_GIVEN_LANGUAGE_ORDER': True}) + datetime.datetime(2020, 12, 11, 0, 0) + +It also applies to the languages given through the ``DEFAULT_LANGUAGES`` setting when +they are used as a fallback. -.. note:: When using this setting, these languages will be tried after trying with the detected languages with no success. It is especially useful when using ``detect_languages_function``. +.. note:: This setting only reorders the languages and locales that are given. If + neither ``languages`` nor ``locales`` is provided, it has no effect and the default + order is used: + + >>> dateparser.parse('11/12/2020', settings={'USE_GIVEN_LANGUAGE_ORDER': True}) + datetime.datetime(2020, 11, 12, 0, 0) + +.. note:: This setting does not affect :func:`dateparser.search.search_dates`, which + detects a single most likely language and normalizes the text before parsing, so it + does not use the given language order to disambiguate values such as ``11/12``. Optional language detection +++++++++++++++++++++++++++ @@ -202,7 +298,27 @@ Defaults to ``False``. >>> ddp = DateDataParser(settings={'RETURN_TIME_AS_PERIOD': True}) >>> ddp.get_date_data('vr jan 24, 2014 12:49') - DateData(date_obj=datetime.datetime(2014, 1, 24, 12, 49), period='time', locale='nl') + DateData(date_obj=datetime.datetime(2014, 1, 24, 12, 49), period='time', locale='nl', parts=('year', 'month', 'day', 'time')) + +``PARTS_OF_DAY``: a :class:`~dateparser.PartsOfDay` object that sets the time +to use for each part of the day, e.g. for ``tonight``. Defaults to +``PartsOfDay()``. + +.. versionadded:: VERSION + + >>> from datetime import time + >>> from dateparser import PartsOfDay + >>> ddp = DateDataParser(settings={'PARTS_OF_DAY': PartsOfDay(night=time(22)), 'RETURN_TIME_AS_PERIOD': True}) + >>> ddp.get_date_data('5 January 2026 at night') + DateData(date_obj=datetime.datetime(2026, 1, 5, 22, 0), period='part_of_day', locale='en', part_of_day=) + +.. autoclass:: dateparser.PartsOfDay + :members: + :undoc-members: + +.. autoclass:: dateparser.PartOfDay + :members: + :undoc-members: ``PARSERS``: it is a list of names of parsers to try, allowing to customize which parsers are tried against the input date string, and in which order they are diff --git a/docs/supported_locales.rst b/docs/supported_locales.rst index c2523236b..49b8503cf 100644 --- a/docs/supported_locales.rst +++ b/docs/supported_locales.rst @@ -3,6 +3,12 @@ Supported languages and locales =============================== +The ``region`` argument accepts the region subtag from one of the locale +codes listed below. For example, ``languages=['en'], region='IN'`` uses the +``en-IN`` locale, while ``languages=['fr'], region='CA'`` uses ``fr-CA``. +If you already know the full locale code, pass it directly through +``locales=['en-IN']`` instead. + ============ ================================================================ Language Locales ============ ================================================================ @@ -48,7 +54,7 @@ dz ebu ee 'ee-TG' el 'el-CY' -en 'en-001', 'en-150', 'en-AG', 'en-AI', 'en-AS', 'en-AT', 'en-AU', 'en-BB', 'en-BE', 'en-BI', 'en-BM', 'en-BS', 'en-BW', 'en-BZ', 'en-CA', 'en-CC', 'en-CH', 'en-CK', 'en-CM', 'en-CX', 'en-CY', 'en-DE', 'en-DG', 'en-DK', 'en-DM', 'en-ER', 'en-FI', 'en-FJ', 'en-FK', 'en-FM', 'en-GB', 'en-GD', 'en-GG', 'en-GH', 'en-GI', 'en-GM', 'en-GU', 'en-GY', 'en-HK', 'en-IE', 'en-IL', 'en-IM', 'en-IN', 'en-IO', 'en-JE', 'en-JM', 'en-KE', 'en-KI', 'en-KN', 'en-KY', 'en-LC', 'en-LR', 'en-LS', 'en-MG', 'en-MH', 'en-MO', 'en-MP', 'en-MS', 'en-MT', 'en-MU', 'en-MW', 'en-MY', 'en-NA', 'en-NF', 'en-NG', 'en-NL', 'en-NR', 'en-NU', 'en-NZ', 'en-PG', 'en-PH', 'en-PK', 'en-PN', 'en-PR', 'en-PW', 'en-RW', 'en-SB', 'en-SC', 'en-SD', 'en-SE', 'en-SG', 'en-SH', 'en-SI', 'en-SL', 'en-SS', 'en-SX', 'en-SZ', 'en-TC', 'en-TK', 'en-TO', 'en-TT', 'en-TV', 'en-TZ', 'en-UG', 'en-UM', 'en-VC', 'en-VG', 'en-VI', 'en-VU', 'en-WS', 'en-ZA', 'en-ZM', 'en-ZW' +en 'en-001', 'en-150', 'en-AG', 'en-AI', 'en-AS', 'en-AT', 'en-AU', 'en-BB', 'en-BE', 'en-BI', 'en-BM', 'en-BS', 'en-BW', 'en-BZ', 'en-CA', 'en-CC', 'en-CH', 'en-CK', 'en-CM', 'en-CX', 'en-CY', 'en-DE', 'en-DG', 'en-DK', 'en-DM', 'en-ER', 'en-FI', 'en-FJ', 'en-FK', 'en-FM', 'en-GB', 'en-GD', 'en-GG', 'en-GH', 'en-GI', 'en-GM', 'en-GU', 'en-GY', 'en-HK', 'en-IE', 'en-IL', 'en-IM', 'en-IN', 'en-IO', 'en-JE', 'en-JM', 'en-KE', 'en-KI', 'en-KN', 'en-KY', 'en-LC', 'en-LR', 'en-LS', 'en-MG', 'en-MH', 'en-MO', 'en-MP', 'en-MS', 'en-MT', 'en-MU', 'en-MW', 'en-MY', 'en-NA', 'en-NF', 'en-NG', 'en-NL', 'en-NR', 'en-NU', 'en-NZ', 'en-PG', 'en-PH', 'en-PK', 'en-PN', 'en-PR', 'en-PW', 'en-RW', 'en-SB', 'en-SC', 'en-SD', 'en-SE', 'en-SG', 'en-SH', 'en-SI', 'en-SL', 'en-SS', 'en-SX', 'en-SZ', 'en-TC', 'en-TK', 'en-TO', 'en-TT', 'en-TV', 'en-TZ', 'en-UG', 'en-UM', 'en-US', 'en-VC', 'en-VG', 'en-VI', 'en-VU', 'en-WS', 'en-ZA', 'en-ZM', 'en-ZW' eo es 'es-419', 'es-AR', 'es-BO', 'es-BR', 'es-BZ', 'es-CL', 'es-CO', 'es-CR', 'es-CU', 'es-DO', 'es-EA', 'es-EC', 'es-GQ', 'es-GT', 'es-HN', 'es-IC', 'es-MX', 'es-NI', 'es-PA', 'es-PE', 'es-PH', 'es-PR', 'es-PY', 'es-SV', 'es-US', 'es-UY', 'es-VE' et diff --git a/docs/usage.rst b/docs/usage.rst index 3aa9edf0c..7fe8955a2 100644 --- a/docs/usage.rst +++ b/docs/usage.rst @@ -11,15 +11,14 @@ from the same source. :class:`DateDataParser ` provides an alternate and efficient way to control language detection behavior. -The instance of :class:`DateDataParser ` caches the found -languages and will prioritize them when trying to parse the next string. +See :ref:`performance` for ways to make parsing faster. :class:`dateparser.date.DateDataParser` can also be initialized with known languages: >>> ddp = DateDataParser(languages=['de', 'nl']) >>> ddp.get_date_data('vr jan 24, 2014 12:49') - DateData(date_obj=datetime.datetime(2014, 1, 24, 12, 49), period='day', locale='nl') + DateData(date_obj=datetime.datetime(2014, 1, 24, 12, 49), period='day', locale='nl', parts=('year', 'month', 'day', 'time')) >>> ddp.get_date_data('18.10.14 um 22:56 Uhr') - DateData(date_obj=datetime.datetime(2014, 10, 18, 22, 56), period='day', locale='de') + DateData(date_obj=datetime.datetime(2014, 10, 18, 22, 56), period='day', locale='de', parts=('year', 'month', 'day', 'time')) >>> ddp.get_date_data('11 July 2012') - DateData(date_obj=None, period='day', locale=None) + DateData(date_obj=None, period='day', locale=None, parts=()) diff --git a/fuzzing/dateparser_fuzzer.py b/fuzzing/dateparser_fuzzer.py index b8ca8bf12..13d342bd4 100644 --- a/fuzzing/dateparser_fuzzer.py +++ b/fuzzing/dateparser_fuzzer.py @@ -1,5 +1,4 @@ import sys -from typing import List import atheris from fuzz_helpers import EnhancedFuzzedDataProvider @@ -60,14 +59,14 @@ ] -def _get_format_strings(fdp: EnhancedFuzzedDataProvider) -> List[str]: - format_strings = [] - for _ in range(fdp.ConsumeIntInRange(0, 5)): - format_strings.append(fdp.ConsumeString(1).join(fdp.ConsumeSublist(directives))) - return format_strings +def _get_format_strings(fdp: EnhancedFuzzedDataProvider) -> list[str]: + return [ + fdp.ConsumeString(1).join(fdp.ConsumeSublist(directives)) + for _ in range(fdp.ConsumeIntInRange(0, 5)) + ] -def TestOneInput(data): +def TestOneInput(data: bytes) -> int | None: fdp = EnhancedFuzzedDataProvider(data) settings = { @@ -103,9 +102,10 @@ def TestOneInput(data): ) except re.error: return -1 + return None -def main(): +def main() -> None: atheris.Setup(sys.argv, TestOneInput) atheris.Fuzz() diff --git a/fuzzing/fuzz_helpers.py b/fuzzing/fuzz_helpers.py index 1ed057131..0d928e042 100644 --- a/fuzzing/fuzz_helpers.py +++ b/fuzzing/fuzz_helpers.py @@ -2,29 +2,36 @@ import datetime import io import tempfile -from typing import List, TypeVar +from collections.abc import Iterator +from typing import TypeVar import atheris T = TypeVar("T") -class EnhancedFuzzedDataProvider(atheris.FuzzedDataProvider): +class EnhancedFuzzedDataProvider(atheris.FuzzedDataProvider): # type: ignore[misc] def ConsumeRandomBytes(self) -> bytes: - return self.ConsumeBytes(self.ConsumeIntInRange(0, self.remaining_bytes())) + result: bytes = self.ConsumeBytes( + self.ConsumeIntInRange(0, self.remaining_bytes()) + ) + return result def ConsumeRandomString(self) -> str: - return self.ConsumeUnicodeNoSurrogates( + result: str = self.ConsumeUnicodeNoSurrogates( self.ConsumeIntInRange(0, self.remaining_bytes()) ) + return result def ConsumeRemainingString(self) -> str: - return self.ConsumeUnicodeNoSurrogates(self.remaining_bytes()) + result: str = self.ConsumeUnicodeNoSurrogates(self.remaining_bytes()) + return result def ConsumeRemainingBytes(self) -> bytes: - return self.ConsumeBytes(self.remaining_bytes()) + result: bytes = self.ConsumeBytes(self.remaining_bytes()) + return result - def ConsumeSublist(self, source: List[T]) -> List[T]: + def ConsumeSublist(self, source: list[T]) -> list[T]: """ Returns a shuffled sub-list of the given list of len [1, len(source)] """ @@ -46,26 +53,26 @@ def ConsumeDate(self) -> datetime.datetime: @contextlib.contextmanager def ConsumeMemoryFile( self, all_data: bool = False, as_bytes: bool = True - ) -> io.BytesIO: - if all_data: - file_data = ( - self.ConsumeRemainingBytes() - if as_bytes - else self.ConsumeRemainingString() + ) -> Iterator[io.BytesIO | io.StringIO]: + file: io.BytesIO | io.StringIO + if as_bytes: + file = io.BytesIO( + self.ConsumeRemainingBytes() if all_data else self.ConsumeRandomBytes() ) else: - file_data = ( - self.ConsumeRandomBytes() if as_bytes else self.ConsumeRandomString() + file = io.StringIO( + self.ConsumeRemainingString() + if all_data + else self.ConsumeRandomString() ) - - file = io.BytesIO(file_data) if as_bytes else io.StringIO(file_data) yield file file.close() @contextlib.contextmanager def ConsumeTemporaryFile( self, suffix: str, all_data: bool = False, as_bytes: bool = True - ) -> str: + ) -> Iterator[str]: + file_data: bytes | str if all_data: file_data = ( self.ConsumeRemainingBytes() diff --git a/pyproject.toml b/pyproject.toml index 8b7623422..4b90d315f 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,8 +1,68 @@ +[build-system] +build-backend = "setuptools.build_meta" +requires = [ + "setuptools >= 77.0", +] + +[project] +name = "dateparser" +version = "1.4.3" +description = "Date parsing library designed to parse dates from HTML pages" +authors = [ + { name = "Scrapinghub", email = "opensource@zyte.com" }, +] +license = "BSD-3-Clause" +keywords = ["dateparser"] +classifiers = [ + "Development Status :: 5 - Production/Stable", + "Intended Audience :: Developers", + "Natural Language :: English", + "Programming Language :: Python :: 3", + "Programming Language :: Python :: 3.10", + "Programming Language :: Python :: 3.11", + "Programming Language :: Python :: 3.12", + "Programming Language :: Python :: 3.13", + "Programming Language :: Python :: 3.14", + "Programming Language :: Python :: Implementation :: CPython", +] +requires-python = ">=3.10" +dynamic = ["readme"] + +dependencies = [ + "python-dateutil>=2.7.0", + "pytz>=2024.2", + "regex>=2024.9.11", + "tzlocal>=0.2", +] + +[project.optional-dependencies] +calendars = ["convertdate>=2.2.1", "hijridate"] +langdetect = ["langdetect>=1.0.0"] + +[project.urls] +Source = "https://github.com/scrapinghub/dateparser" +History = "https://dateparser.readthedocs.io/en/latest/history.html" + +[project.scripts] +dateparser-download = "dateparser_cli.cli:entrance" + +[tool.setuptools] +include-package-data = true +zip-safe = false + +[tool.setuptools.packages.find] +namespaces = false +exclude = ["tests", "tests.*"] + [tool.bumpversion] -current_version = "1.2.2" commit = true tag = true +[[tool.bumpversion.files]] +filename = "pyproject.toml" +search = 'version = "{current_version}"' +replace = 'version = "{new_version}"' + [[tool.bumpversion.files]] filename = "dateparser/__init__.py" @@ -12,9 +72,196 @@ search = "\\(unreleased\\)$" replace = "({now:%Y-%m-%d})" regex = true +[[tool.bumpversion.files]] +filename = "SECURITY.md" +parse = """(?P0|[1-9]\\d*)\\.(?P0|[1-9]\\d*)""" +serialize = ["{major}.{minor}"] + +[tool.mypy] +strict = true +mypy_path = "stubs" + +[[tool.mypy.overrides]] +module = [ + "atheris", + "convertdate.*", + "langdetect.*", +] +ignore_missing_imports = true + [tool.ruff] exclude = ["date_translation_data"] +[tool.ruff.lint] +extend-select = [ + # flake8-builtins + "A", + # flake8-async + "ASYNC", + # flake8-bugbear + "B", + # flake8-comprehensions + "C4", + # flake8-commas + "COM", + # pydocstyle + "D", + # pycodestyle + "E4", + "E7", + "E9", + # Pyflakes + "F", + # flake8-future-annotations + "FA", + # flynt + "FLY", + # refurb + "FURB", + # isort + "I", + # flake8-implicit-str-concat + "ISC", + # flake8-logging + "LOG", + # Perflint + "PERF", + # pygrep-hooks + "PGH", + # flake8-pie + "PIE", + # pylint + "PL", + # flake8-pytest-style + "PT", + # flake8-use-pathlib + "PTH", + # flake8-pyi + "PYI", + # flake8-quotes + "Q", + # flake8-return + "RET", + # flake8-raise + "RSE", + # Ruff-specific rules + "RUF", + # flake8-bandit + "S", + # flake8-simplify + "SIM", + # flake8-slots + "SLOT", + # flake8-debugger + "T10", + # flake8-type-checking + "TC", + # flake8-tidy-imports + "TID", + # pyupgrade + "UP", + # pycodestyle warnings + "W", + # flake8-2020 + "YTT", +] +ignore = [ + # Do not catch blind exception + "BLE001", + # Trailing comma missing + "COM812", + # Missing docstring in public module + "D100", + # Missing docstring in public class + "D101", + # Missing docstring in public method + "D102", + # Missing docstring in public function + "D103", + # Missing docstring in public package + "D104", + # Missing docstring in magic method + "D105", + # Missing docstring in public nested class + "D106", + # Missing docstring in __init__ + "D107", + # One-line docstring should fit on one line with quotes + "D200", + # No blank lines allowed after function docstring + "D202", + # 1 blank line required between summary line and description + "D205", + # Multi-line docstring closing quotes should be on a separate line + "D209", + # First line should end with a period + "D400", + # First line should be in imperative mood; try rephrasing + "D401", + # First line should not be the function's "signature" + "D402", + # First word of the first line should be properly capitalized + "D403", + # Naive datetime objects are part of the dateparser API + "DTZ", + # `try`-`except` within a loop incurs performance overhead + "PERF203", + # Too many return statements + "PLR0911", + # Too many arguments in function definition + "PLR0913", + # Too many positional arguments + "PLR0917", + # Magic value used in comparison + "PLR2004", + # String contains ambiguous {}. + "RUF001", + # Docstring contains ambiguous {}. + "RUF002", + # Comment contains ambiguous {}. + "RUF003", + # Use of `assert` detected; needed for mypy + "S101", + # Use a context manager for opening files + "SIM115", + # Yoda condition detected + "SIM300", + # Prefer `TypeError` exception for invalid type + "TRY004", +] + +[tool.ruff.lint.isort] +split-on-trailing-comma = false + [tool.ruff.lint.per-file-ignores] "dateparser/data/__init__.py" = ["F401"] "dateparser/languages/__init__.py" = ["F401"] +"tests/**" = [ + # Skip bandit and allow blocking file I/O in tests + "ASYNC240", + "S", + # Assigning to `os.environ` doesn't clear the environment. + "B003", + # Do not use mutable data structures for argument defaults. + "B006", + # Found useless expression. + "B018", + # No explicit stacklevel argument found. + "B028", + # Within an `except` clause, raise exceptions with `raise ... from` + "B904", + # `for` loop variable overwritten by assignment target + "PLW2901", + # Tests are unittest-based + "PT009", + "PT027", + # Default values of parameterized test parameters are optional parameters + "PT028", + # Mutable class attributes should be annotated with `typing.ClassVar` + "RUF012", + # Use capitalized environment variable + "SIM112", +] + +[tool.ruff.lint.pydocstyle] +convention = "pep257" diff --git a/pytest.ini b/pytest.ini index 1a75689bf..b3e793b2a 100644 --- a/pytest.ini +++ b/pytest.ini @@ -1,4 +1,16 @@ [pytest] -addopts = - --doctest-modules - --assert=plain +testpaths = tests +# Warnings are errors: warning-class problems have repeatedly reached users +# instead of CI (#1246, #1013, #506). The suite emits no warnings at all today. +# When an upstream deprecation turns the suite red, fix it if it comes from +# dateparser, and otherwise add the narrowest possible ignore *after* `error`, +# since the last matching filter wins. +# +# The exemptions below are environmental, not code: tzlocal warns when the host +# has no usable time zone configuration or a stale one, which CI never sees +# because it always sets TZ, and pytest warns when it cannot write its cache. +filterwarnings = + error + ignore:Can not find any timezone configuration:UserWarning + ignore:Timezone offset does not match system offset:UserWarning + ignore::pytest.PytestCacheWarning diff --git a/setup.py b/setup.py index 6be5d3346..f9be80fbe 100644 --- a/setup.py +++ b/setup.py @@ -1,62 +1,16 @@ import re +from pathlib import Path -from setuptools import find_packages, setup +from setuptools import setup -__version__ = re.search( - r"__version__.*\s*=\s*[\"]([^\"]+)[\"]", open("dateparser/__init__.py").read() -).group(1) - -introduction = re.sub( - r":members:.+|..\sautomodule::.+|:class:|:func:|:ref:", - "", - open("docs/introduction.rst", encoding="utf-8").read(), -) +readme = Path("README.rst").read_text(encoding="utf-8") +# Remove `.. raw:: html` blocks, which are not supported by PyPI. +readme = re.sub(r"(?m)^\.\. raw:: html\n(?:^[ \t].*\n|^[ \t]*\n)*?\n\n", "", readme) history = re.sub( - r":mod:|:class:|:func:", "", open("HISTORY.rst", encoding="utf-8").read() + r":mod:|:class:|:func:", "", Path("HISTORY.rst").read_text(encoding="utf-8") ) setup( - name="dateparser", - version=__version__, - description="Date parsing library designed to parse dates from HTML pages", - long_description=introduction + "\n\n" + history, - author="Scrapinghub", - author_email="opensource@zyte.com", - url="https://github.com/scrapinghub/dateparser", - project_urls={ - "History": "https://dateparser.readthedocs.io/en/latest/history.html", - }, - packages=find_packages(exclude=("tests", "tests.*")), - include_package_data=True, - install_requires=[ - "python-dateutil>=2.7.0", - "pytz>=2024.2", - "regex>=2024.9.11", - "tzlocal>=0.2", - ], - entry_points={ - "console_scripts": ["dateparser-download = dateparser_cli.cli:entrance"], - }, - extras_require={ - "calendars": ["convertdate>=2.2.1", "hijridate"], - "fasttext": ["fasttext>=0.9.1", "numpy>=1.22.0,<2"], - "langdetect": ["langdetect>=1.0.0"], - }, - license="BSD", - zip_safe=False, - keywords="dateparser", - python_requires=">=3.10", - classifiers=[ - "Development Status :: 5 - Production/Stable", - "Intended Audience :: Developers", - "License :: OSI Approved :: BSD License", - "Natural Language :: English", - "Programming Language :: Python :: 3", - "Programming Language :: Python :: 3.10", - "Programming Language :: Python :: 3.11", - "Programming Language :: Python :: 3.12", - "Programming Language :: Python :: 3.13", - "Programming Language :: Python :: 3.14", - "Programming Language :: Python :: Implementation :: CPython", - ], + long_description=readme + "\n\n" + history, + long_description_content_type="text/x-rst", ) diff --git a/stubs/parameterized/__init__.pyi b/stubs/parameterized/__init__.pyi new file mode 100644 index 000000000..ce6ca6eb3 --- /dev/null +++ b/stubs/parameterized/__init__.pyi @@ -0,0 +1,21 @@ +from collections.abc import Callable, Iterable +from typing import Any, TypeVar + +_F = TypeVar("_F", bound=Callable[..., Any]) + +class param: + args: tuple[Any, ...] + kwargs: dict[str, Any] + def __init__(self, *args: Any, **kwargs: Any) -> None: ... + +class parameterized: + @classmethod + def expand( + cls, + input: Iterable[Any], # noqa: A002 + name_func: Callable[..., str] | None = None, + doc_func: Callable[..., str | None] | None = None, + skip_on_empty: bool = False, + namespace: dict[str, Any] | None = None, + **legacy: Any, + ) -> Callable[[_F], _F]: ... diff --git a/tests/__init__.py b/tests/__init__.py index 7132fb98c..a19c9d353 100644 --- a/tests/__init__.py +++ b/tests/__init__.py @@ -1,26 +1,36 @@ +from __future__ import annotations + +from typing import TYPE_CHECKING, Any from unittest import TestCase +if TYPE_CHECKING: + from collections.abc import Iterable + from unittest.mock import _patch + class BaseTestCase(TestCase): - def setUp(self): + def setUp(self) -> None: super().setUp() - self.__patches = [] + self.__patches: list[_patch[Any]] = [] - self.error = NotImplemented + self.error: object = NotImplemented - def add_patch(self, patch): + def add_patch(self, patch: _patch[Any]) -> None: patch.start() self.__patches.append(patch) - def tearDown(self): + def tearDown(self) -> None: super().tearDown() for patch in reversed(self.__patches): patch.stop() - def then_error_was_raised(self, error_cls, allowed_substrings=()): + def then_error_was_raised( + self, + error_cls: type[BaseException], + allowed_substrings: Iterable[str] = (), + ) -> None: self.assertIsInstance(self.error, error_cls) self.assertTrue( any(mesg in str(self.error) for mesg in allowed_substrings), - "Didn't found any of the expected messages (%r) -- message was: %r" - % (allowed_substrings, self.error), + f"Didn't found any of the expected messages ({allowed_substrings!r}) -- message was: {self.error!r}", ) diff --git a/tests/benchmarks/__init__.py b/tests/benchmarks/__init__.py new file mode 100644 index 000000000..28b5f402f --- /dev/null +++ b/tests/benchmarks/__init__.py @@ -0,0 +1,41 @@ +"""CodSpeed benchmarks. + +These are only collected when ``pytest-codspeed`` is installed, which is the +case in the dedicated ``benchmark`` tox environment (see ``tox.ini``). In every +other environment they are skipped, so the regular test runs are unaffected. +""" + +import pytest + +pytest.importorskip("pytest_codspeed", reason="Benchmark tests require pytest-codspeed") + +# Relative date strings in the form the freshness parser actually receives them: +# the locale translates the input first, which turns plural units singular +# ("2 hours, 50 minutes ago" -> "2 hour 50 minute ago"). PATTERN only matches +# singular units, so benchmarking the untranslated strings would measure a failed +# scan instead of the real workload. +# +# Each benchmark runs the whole list rather than a single string: CodSpeed's +# simulation mode measures one call, and a lone match on a short string is too +# small a unit of work to be meaningful. +TRANSLATED_RELATIVE_STRINGS = [ + "1 minute ago", + "2 hour 50 minute ago", + "3 day ago", + "in 2 week", + "10.5 year ago", + "1 day 2 hour 3 minute 4 second ago", +] + +# A long run of digits: the input shape that made the relative-date regexes +# backtrack superlinearly before #1335. Deliberately pathological rather than +# realistic -- it is what turns a reintroduced regression into an unmissable +# signal. +# +# The length is chosen so that a regressed run still *finishes and reports*: +# with the old greedy quantifiers this takes ~380ms against ~0.7ms for the +# possessive ones, a ~500x jump that no threshold can miss, while remaining a +# handful of seconds under CodSpeed's instrumentation. The 3200 digits of the +# original #1335 repro would instead need ~20 minutes per benchmark once +# regressed, so the job would time out without ever reporting. +LONG_DIGIT_RUN = "9" * 800 diff --git a/tests/benchmarks/test_benchmark_freshness_date_parser.py b/tests/benchmarks/test_benchmark_freshness_date_parser.py new file mode 100644 index 000000000..fc35bff87 --- /dev/null +++ b/tests/benchmarks/test_benchmark_freshness_date_parser.py @@ -0,0 +1,60 @@ +r"""Benchmarks for :mod:`dateparser.freshness_date_parser`. + +``PATTERN`` matches a number followed by a time unit, and is applied to the whole +input string by ``findall()`` (in ``get_kwargs()``) and by ``sub()`` (in +``_parse_time()``). Until #1335 it spelled the number as the greedy +``\d+[.,]?\d*``, whose adjacent digit quantifiers backtrack without ever +changing the match, so the cost grew superlinearly with the length of a digit +run. #1335 made the quantifiers possessive (``\d++[.,]?\d*+``). +""" + +from __future__ import annotations + +from typing import TYPE_CHECKING + +from dateparser.freshness_date_parser import PATTERN, freshness_date_parser +from tests.benchmarks import LONG_DIGIT_RUN, TRANSLATED_RELATIVE_STRINGS + +if TYPE_CHECKING: + from pytest_codspeed import BenchmarkFixture + + +def test_freshness_pattern_findall(benchmark: BenchmarkFixture) -> None: + def run() -> None: + for date_string in TRANSLATED_RELATIVE_STRINGS: + PATTERN.findall(date_string) + + # Guard against measuring a no-op: were PATTERN to stop matching these + # inputs, the benchmark would get faster instead of failing. + assert PATTERN.findall(TRANSLATED_RELATIVE_STRINGS[-1]) == [ + ("1", "day"), + (" 2", "hour"), + (" 3", "minute"), + (" 4", "second"), + ] + + benchmark(run) + + +def test_freshness_pattern_findall_long_digit_run(benchmark: BenchmarkFixture) -> None: + assert PATTERN.findall(LONG_DIGIT_RUN) == [] + + benchmark(lambda: PATTERN.findall(LONG_DIGIT_RUN)) + + +def test_freshness_pattern_sub_long_digit_run(benchmark: BenchmarkFixture) -> None: + """``_parse_time()`` runs ``PATTERN.sub()`` over the input as well.""" + assert PATTERN.sub("", LONG_DIGIT_RUN) == LONG_DIGIT_RUN + + benchmark(lambda: PATTERN.sub("", LONG_DIGIT_RUN)) + + +def test_freshness_get_kwargs(benchmark: BenchmarkFixture) -> None: + def run() -> None: + for date_string in TRANSLATED_RELATIVE_STRINGS: + freshness_date_parser.get_kwargs(date_string) + + kwargs, _ = freshness_date_parser.get_kwargs(TRANSLATED_RELATIVE_STRINGS[1]) + assert kwargs == {"hours": 2.0, "minutes": 50.0} + + benchmark(run) diff --git a/tests/benchmarks/test_benchmark_languages.py b/tests/benchmarks/test_benchmark_languages.py new file mode 100644 index 000000000..d5c39f635 --- /dev/null +++ b/tests/benchmarks/test_benchmark_languages.py @@ -0,0 +1,40 @@ +r"""Benchmarks for :mod:`dateparser.languages.dictionary`. + +``Dictionary.split()`` first splits the input with a regex built from the +locale's ``relative-type-regex`` entries. Those entries carried the same greedy +``\d+[.,]?\d*`` that #1335 replaced with the possessive ``\d++[.,]?\d*+``, and +because the alternation is applied by ``re.split()`` across the whole input, a +long digit run backtracked quadratically here too. + +The typical-input side of ``Dictionary.split()`` is covered end to end by +``test_benchmark_parse.py``, which reaches it through the real locale objects. +""" + +from __future__ import annotations + +from typing import TYPE_CHECKING + +import dateparser.data.date_translation_data.en as en_data +from dateparser.conf import settings +from dateparser.languages.dictionary import Dictionary +from tests.benchmarks import LONG_DIGIT_RUN + +if TYPE_CHECKING: + from pytest_codspeed import BenchmarkFixture + + +def test_dictionary_split_relative_regex_long_digit_run( + benchmark: BenchmarkFixture, +) -> None: + # Only the compiled relative-split regex is taken from the dictionary, as + # ``tests/test_freshness_date_parser.py`` already does. For English the + # regex a plain Dictionary compiles is identical to the NormalizedDictionary + # one the parser uses, since normalization leaves these strings untouched. + split_relative_regex = Dictionary( + en_data.info, settings + )._get_split_relative_regex_cache() + + # A digit run holds no relative-date string, so it must come back unsplit. + assert split_relative_regex.split(LONG_DIGIT_RUN) == [LONG_DIGIT_RUN] + + benchmark(lambda: split_relative_regex.split(LONG_DIGIT_RUN)) diff --git a/tests/benchmarks/test_benchmark_parse.py b/tests/benchmarks/test_benchmark_parse.py new file mode 100644 index 000000000..2dd41a35b --- /dev/null +++ b/tests/benchmarks/test_benchmark_parse.py @@ -0,0 +1,52 @@ +"""Benchmarks for the public :func:`dateparser.parse` entry point. + +Where the other benchmark modules pin down individual regexes, these cover the +end-to-end cost a caller actually pays, so that a slowdown anywhere in the +parsing pipeline is caught too. +""" + +from __future__ import annotations + +from typing import TYPE_CHECKING + +import dateparser + +if TYPE_CHECKING: + from pytest_codspeed import BenchmarkFixture + +RELATIVE_DATE_STRINGS = [ + "2 hours ago", + "3 days ago", + "in 5 minutes", + "a week ago", + "2 months, 3 weeks ago", +] + +ABSOLUTE_DATE_STRINGS = [ + "2015-06-01", + "June 1, 2015", + "01/06/2015", + "1st of June 2015", + "2015-06-01T13:00:00Z", +] + + +def _benchmark_parse(benchmark: BenchmarkFixture, date_strings: list[str]) -> None: + def run() -> None: + for date_string in date_strings: + dateparser.parse(date_string) + + # Load the locale data and warm the parser caches outside the measurement. + run() + + assert dateparser.parse(date_strings[0]) is not None + + benchmark(run) + + +def test_parse_relative_date_strings(benchmark: BenchmarkFixture) -> None: + _benchmark_parse(benchmark, RELATIVE_DATE_STRINGS) + + +def test_parse_absolute_date_strings(benchmark: BenchmarkFixture) -> None: + _benchmark_parse(benchmark, ABSOLUTE_DATE_STRINGS) diff --git a/tests/test_article_dates.py b/tests/test_article_dates.py new file mode 100644 index 000000000..e98ecff2b --- /dev/null +++ b/tests/test_article_dates.py @@ -0,0 +1,35 @@ +import csv +import io +import zipfile +from pathlib import Path + +import pytest + +from dateparser_scripts import article_dates + + +def test_report(tmp_path: Path, capsys: pytest.CaptureFixture[str]) -> None: + rows = io.StringIO() + writer = csv.writer(rows) + writer.writerow( + ["suffix", "articleLanguage", "webPageLanguages", "datePublishedRaw"] + ) + writer.writerow(["com", "en", "en", "October 22, 2020"]) + writer.writerow(["de", "de", "de", "05.03.2021"]) + writer.writerow(["de", "de", "de", "05.03.2021"]) + writer.writerow(["de", "de", "de", "Stellenangebot vom 04.11.2020"]) + data = tmp_path / "data.zip" + with zipfile.ZipFile(data, "w") as archive: + archive.writestr("data.csv", rows.getvalue()) + output = tmp_path / "output.tsv" + + article_dates.main(["--data", str(data), "--jobs", "1", "--output", str(output)]) + + report = capsys.readouterr().out + assert report.startswith("4 rows, 3 distinct\n") + assert "\nunparsed: 1 (25.0%)\n" in report + assert "\nsearchable: 1 (25.0%)\n" in report + assert "\nfuture: 2 (50.0%)\n" in report + assert "\nhint-dependent: 2 (50.0%)\n" in report + assert "\n 2 '99.99.9999'\n" in report + assert len(output.read_text().splitlines()) == 3 diff --git a/tests/test_clean_api.py b/tests/test_clean_api.py index 4ed18a7b3..146e63fd1 100644 --- a/tests/test_clean_api.py +++ b/tests/test_clean_api.py @@ -1,16 +1,18 @@ -from datetime import date, datetime +from datetime import date, datetime, timedelta +from typing import Any from parameterized import param, parameterized from pytz import utc import dateparser +from dateparser.search import search_dates from tests import BaseTestCase class TestParseFunction(BaseTestCase): - def setUp(self): + def setUp(self) -> None: super().setUp() - self.result = NotImplemented + self.result: datetime | None = NotImplemented @parameterized.expand( [ @@ -19,7 +21,9 @@ def setUp(self): param(date_string="January 25, 2014", expected_date=date(2014, 1, 25)), ] ) - def test_parse_dates_in_different_languages(self, date_string, expected_date): + def test_parse_dates_in_different_languages( + self, date_string: str, expected_date: date + ) -> None: self.when_date_is_parsed_with_defaults(date_string) self.then_parsed_date_is(expected_date) @@ -39,7 +43,9 @@ def test_parse_dates_in_different_languages(self, date_string, expected_date): ), ] ) - def test_parse_dates_with_specific_time(self, date_string, expected_date): + def test_parse_dates_with_specific_time( + self, date_string: str, expected_date: datetime + ) -> None: self.when_date_is_parsed_with_defaults(date_string) self.then_parsed_date_and_time_is(expected_date) @@ -63,8 +69,8 @@ def test_parse_dates_with_specific_time(self, date_string, expected_date): ] ) def test_parse_dates_with_specific_time_and_settings( - self, date_string, expected_date, relative - ): + self, date_string: str, expected_date: datetime, relative: datetime + ) -> None: self.when_date_is_parsed_with_settings( date_string, settings={"RELATIVE_BASE": relative} ) @@ -80,8 +86,8 @@ def test_parse_dates_with_specific_time_and_settings( ] ) def test_dates_which_match_languages_are_parsed( - self, date_string, languages, expected_date - ): + self, date_string: str, languages: list[str] | None, expected_date: date + ) -> None: self.when_date_is_parsed(date_string, languages=languages) self.then_parsed_date_is(expected_date) @@ -91,8 +97,8 @@ def test_dates_which_match_languages_are_parsed( ] ) def test_dates_which_do_not_match_languages_are_not_parsed( - self, date_string, languages - ): + self, date_string: str, languages: list[str] | None + ) -> None: self.when_date_is_parsed(date_string, languages=languages) self.then_date_was_not_parsed() @@ -106,11 +112,27 @@ def test_dates_which_do_not_match_languages_are_not_parsed( ] ) def test_dates_which_match_locales_are_parsed( - self, date_string, locales, expected_date - ): + self, date_string: str, locales: list[str], expected_date: date + ) -> None: self.when_date_is_parsed(date_string, locales=locales) self.then_parsed_date_is(expected_date) + @parameterized.expand( + [ + param(date_string="6 yar 2019", locales=["ff-CM"]), + param(date_string="6 yar 2019", locales=["ff-GN"]), + param(date_string="6 yar 2019", locales=["ff-MR"]), + ] + ) + def test_locales_dropped_in_cldr_44_remain_supported( + self, date_string: str, locales: list[str] + ) -> None: + # ff-CM/ff-GN/ff-MR were standalone locales up to CLDR 31 but were dropped in + # CLDR 44 (regional data moved under ff-Latn). They remain valid locale codes + # and resolve to the base `ff` data, so existing callers keep working. + self.when_date_is_parsed(date_string, locales=locales) + self.then_parsed_date_is(date(2019, 10, 6)) + @parameterized.expand( [ param( @@ -124,8 +146,14 @@ def test_dates_which_match_locales_are_parsed( ] ) def test_dates_parse_utc_offset_does_not_throw( - self, date_string, locales, languages, region, date_formats, expected_date - ): + self, + date_string: str, + locales: list[str], + languages: list[str] | None, + region: str, + date_formats: list[str], + expected_date: datetime, + ) -> None: """ Bug discovered by OSSFuzz that caused an exception in pytz to halt parsing Regression test to ensure that this is not reintroduced @@ -180,31 +208,85 @@ def test_dates_parse_utc_offset_does_not_throw( ] ) def test_dates_which_do_not_match_locales_are_not_parsed( - self, date_string, locales - ): + self, date_string: str, locales: list[str] + ) -> None: self.when_date_is_parsed(date_string, locales=locales) self.then_date_was_not_parsed() - def when_date_is_parsed_with_defaults(self, date_string): + @parameterized.expand( + [ + param(date_string="Oct-23", expected_date=datetime(2023, 10, 1, 0, 0)), + param(date_string="May-23", expected_date=datetime(2023, 5, 1, 0, 0)), + ] + ) + def test_require_parts_month_year_parses_month_year( + self, date_string: str, expected_date: datetime + ) -> None: + # Regression: when year is required, Mon-YY should be interpreted as month-year. + base = datetime(2050, 1, 1, 0, 0) + self.when_date_is_parsed_with_settings( + date_string, + settings={ + "RELATIVE_BASE": base, + "PREFER_DAY_OF_MONTH": "first", + "PREFER_DATES_FROM": "past", + "REQUIRE_PARTS": ["month", "year"], + }, + ) + self.then_parsed_date_and_time_is(expected_date) + + def test_require_parts_does_not_override_explicit_date_order(self) -> None: + # Explicit DATE_ORDER must be respected. + base = datetime(2050, 1, 1, 0, 0) + self.when_date_is_parsed_with_settings( + "Oct-23", + settings={ + "RELATIVE_BASE": base, + "REQUIRE_PARTS": ["month", "year"], + "DATE_ORDER": "MDY", + }, + ) + self.then_date_was_not_parsed() + + def test_require_parts_month_day_parses_month_day(self) -> None: + # If day is required, Mon-XX should remain month-day. + base = datetime(2000, 1, 1, 0, 0) + self.when_date_is_parsed_with_settings( + "Oct-23", + settings={ + "RELATIVE_BASE": base, + "REQUIRE_PARTS": ["month", "day"], + }, + ) + self.then_parsed_date_and_time_is(datetime(2000, 10, 23, 0, 0)) + + def when_date_is_parsed_with_defaults(self, date_string: str) -> None: self.result = dateparser.parse(date_string) - def when_date_is_parsed(self, date_string, languages=None, locales=None): + def when_date_is_parsed( + self, + date_string: str, + languages: list[str] | None = None, + locales: list[str] | None = None, + ) -> None: self.result = dateparser.parse( date_string, languages=languages, locales=locales ) - def when_date_is_parsed_with_settings(self, date_string, settings=None): + def when_date_is_parsed_with_settings( + self, date_string: str, settings: dict[str, Any] | None = None + ) -> None: self.result = dateparser.parse(date_string, settings=settings) def when_date_is_parsed_with_args_and_settings( self, - date_string, - languages=None, - locales=None, - region=None, - date_formats=None, - settings=None, - ): + date_string: str, + languages: list[str] | None = None, + locales: list[str] | None = None, + region: str | None = None, + date_formats: list[str] | None = None, + settings: dict[str, Any] | None = None, + ) -> None: self.result = dateparser.parse( date_string, languages=languages, @@ -214,13 +296,332 @@ def when_date_is_parsed_with_args_and_settings( settings=settings, ) - def then_parsed_date_is(self, expected_date): + def then_parsed_date_is(self, expected_date: date) -> None: self.assertEqual( self.result, datetime.combine(expected_date, datetime.min.time()) ) - def then_parsed_date_and_time_is(self, expected_date): + def then_parsed_date_and_time_is(self, expected_date: datetime) -> None: self.assertEqual(self.result, expected_date) - def then_date_was_not_parsed(self): + def then_date_was_not_parsed(self) -> None: + self.assertIsNone(self.result) + + +class TestIgnoreSurroundingTextSetting(BaseTestCase): + """Tests for the opt-in ``IGNORE_SURROUNDING_TEXT`` setting (issue #518).""" + + def setUp(self) -> None: + super().setUp() + self.result: object = NotImplemented + + @parameterized.expand( + [ + # Issue #518: dates wrapped in harmless extra text. + param( + date_string="Actualisé le 17 avril 2019", + languages=["fr"], + expected_datetime=datetime(2019, 4, 17), + ), + param( + date_string="Publié le 16 avril 2019", + languages=["fr"], + expected_datetime=datetime(2019, 4, 16), + ), + # The behavior is not French-specific. + param( + date_string="Published on 16 April 2019", + languages=["en"], + expected_datetime=datetime(2019, 4, 16), + ), + # Purely numeric dates do not need a month name to survive. + param( + date_string="published 2019-04-16 ok", + languages=["en"], + expected_datetime=datetime(2019, 4, 16), + ), + param( + date_string="xx 16/04/2019 yy", + languages=["en"], + expected_datetime=datetime(2019, 4, 16), + ), + # No language hint is needed: locales are tried as usual. + param( + date_string="Actualisé le 17 avril 2019", + languages=None, + expected_datetime=datetime(2019, 4, 17), + ), + # Strings that parse as a whole are parsed exactly as before. + param( + date_string="le 17 avril 2019", + languages=["fr"], + expected_datetime=datetime(2019, 4, 17), + ), + param( + date_string="17 avril 2019", + languages=["fr"], + expected_datetime=datetime(2019, 4, 17), + ), + ] + ) + def test_dates_with_surrounding_text_are_parsed( + self, date_string: str, languages: list[str] | None, expected_datetime: datetime + ) -> None: + self.when_date_is_parsed( + date_string, + languages=languages, + settings={"IGNORE_SURROUNDING_TEXT": True}, + ) + self.then_parsed_datetime_is(expected_datetime) + + @parameterized.expand( + [ + param(date_string="Actualisé le 17 avril 2019", languages=["fr"]), + param(date_string="Publié le 16 avril 2019", languages=["fr"]), + param(date_string="Published on 16 April 2019", languages=["en"]), + ] + ) + def test_dates_with_surrounding_text_are_not_parsed_by_default( + self, date_string: str, languages: list[str] | None + ) -> None: + self.when_date_is_parsed(date_string, languages=languages) + self.then_date_was_not_parsed() + + @parameterized.expand( + [ + # An unrecognized word inside the date still prevents parsing. + param(date_string="17 foobar avril 2019", languages=["fr"]), + # A string without any date content is still not parsed. + param(date_string="hello world", languages=["en"]), + ] + ) + def test_non_dates_are_not_parsed_even_when_enabled( + self, date_string: str, languages: list[str] | None + ) -> None: + self.when_date_is_parsed( + date_string, + languages=languages, + settings={"IGNORE_SURROUNDING_TEXT": True}, + ) + self.then_date_was_not_parsed() + + def test_surrounding_text_ignored_with_locales_argument(self) -> None: + self.when_date_is_parsed( + "Actualisé le 17 avril 2019", + locales=["fr-CA"], + settings={"IGNORE_SURROUNDING_TEXT": True}, + ) + self.then_parsed_datetime_is(datetime(2019, 4, 17)) + + def test_surrounding_text_ignored_with_region_argument(self) -> None: + self.when_date_is_parsed( + "Actualisé le 17 avril 2019", + languages=["fr"], + region="CA", + settings={"IGNORE_SURROUNDING_TEXT": True}, + ) + self.then_parsed_datetime_is(datetime(2019, 4, 17)) + + def test_surrounding_text_ignored_with_default_languages_setting(self) -> None: + self.when_date_is_parsed( + "Actualisé le 17 avril 2019", + settings={"IGNORE_SURROUNDING_TEXT": True, "DEFAULT_LANGUAGES": ["fr"]}, + ) + self.then_parsed_datetime_is(datetime(2019, 4, 17)) + + def test_surrounding_text_ignored_with_detected_language(self) -> None: + self.when_date_is_parsed( + "Actualisé le 17 avril 2019", + detect_languages_function=lambda text, confidence_threshold: ["fr"], + settings={"IGNORE_SURROUNDING_TEXT": True}, + ) + self.then_parsed_datetime_is(datetime(2019, 4, 17)) + + def test_surrounding_text_ignored_with_date_formats(self) -> None: + self.when_date_is_parsed( + "Published on 16/04/2019", + date_formats=["%d/%m/%Y"], + languages=["en"], + settings={"IGNORE_SURROUNDING_TEXT": True}, + ) + self.then_parsed_datetime_is(datetime(2019, 4, 16)) + + def test_relative_date_with_surrounding_text(self) -> None: + self.when_date_is_parsed( + "asdf 3 hours ago asdf", + languages=["en"], + settings={ + "IGNORE_SURROUNDING_TEXT": True, + "RELATIVE_BASE": datetime(2019, 4, 17, 12, 0), + }, + ) + self.then_parsed_datetime_is(datetime(2019, 4, 17, 9, 0)) + + def test_strict_parsing_rejects_incomplete_remainder(self) -> None: + # The remainder is parsed as if it were the whole input, so settings + # such as STRICT_PARSING apply to it as usual. + self.when_date_is_parsed( + "Page 3", + languages=["en"], + settings={"IGNORE_SURROUNDING_TEXT": True, "STRICT_PARSING": True}, + ) + self.then_date_was_not_parsed() + + def test_surrounding_text_can_turn_non_dates_into_dates(self) -> None: + # Documented caveat: with the setting enabled, a string that merely + # contains date-like words produces a date. + self.when_date_is_parsed( + "Chapter 12 March of the Penguins", + languages=["en"], + settings={ + "IGNORE_SURROUNDING_TEXT": True, + "RELATIVE_BASE": datetime(2026, 7, 27), + }, + ) + self.then_parsed_datetime_is(datetime(2026, 3, 12)) + + def test_search_dates_is_not_affected_by_default(self) -> None: + # search_dates keeps relying on the strict behavior of get_date_data. + self.result = search_dates("Actualisé le 17 avril 2019", languages=["fr"]) + self.assertEqual([("le 17 avril 2019", datetime(2019, 4, 17))], self.result) + + def test_trailing_timezone_is_preserved(self) -> None: + # A recognized timezone at the trailing edge must not be discarded with + # the surrounding text: wrapping a date in extra text yields the same + # instant as parsing the bare date, timezone included. + settings = {"IGNORE_SURROUNDING_TEXT": True, "RETURN_AS_TIMEZONE_AWARE": True} + wrapped = dateparser.parse( + "Updated 23 March 2000 1:21 PM EST", languages=["en"], settings=settings + ) + unwrapped = dateparser.parse( + "23 March 2000 1:21 PM EST", + languages=["en"], + settings={"RETURN_AS_TIMEZONE_AWARE": True}, + ) + assert wrapped is not None + self.assertEqual(timedelta(hours=-5), wrapped.utcoffset()) + self.assertEqual(unwrapped, wrapped) + + @parameterized.expand( + [ + # Abbreviations that are not dictionary words, so they are kept via + # is_timezone_token rather than the plain known-word branch. Their + # names and offsets are chosen not to coincide with a plausible + # local timezone (in particular not UTC or CET), so a reversion of + # the trailing-tz exception is caught on any machine rather than + # only under a non-local timezone. + param( + wrapped="Updated 23 March 2000 1:21 PM PST", + bare="23 March 2000 1:21 PM PST", + tzname="PST", + utcoffset=timedelta(hours=-8), + ), + param( + wrapped="Updated 23 March 2000 1:21 PM JST", + bare="23 March 2000 1:21 PM JST", + tzname="JST", + utcoffset=timedelta(hours=9), + ), + ] + ) + def test_more_trailing_timezones_are_preserved( + self, wrapped: str, bare: str, tzname: str, utcoffset: timedelta + ) -> None: + # Like test_trailing_timezone_is_preserved, for further abbreviations: + # wrapping the date in extra text yields the same tz-aware instant as + # parsing the bare date. The timezone *name* is asserted (not only the + # offset) so the test cannot pass by the dropped timezone happening to + # match the machine's local offset. + settings = {"IGNORE_SURROUNDING_TEXT": True, "RETURN_AS_TIMEZONE_AWARE": True} + wrapped_result = dateparser.parse(wrapped, languages=["en"], settings=settings) + bare_result = dateparser.parse( + bare, languages=["en"], settings={"RETURN_AS_TIMEZONE_AWARE": True} + ) + assert wrapped_result is not None + self.assertEqual(tzname, wrapped_result.tzname()) + self.assertEqual(utcoffset, wrapped_result.utcoffset()) + self.assertEqual(bare_result, wrapped_result) + + def test_parenthesized_trailing_timezone_is_applied(self) -> None: + # A parenthesized trailing timezone is applied end to end. GMT is a + # dictionary token, so the parentheses are split off and it is kept via + # the ordinary known-word branch, not via is_timezone_token (which the + # PST/JST cases above exercise). A parenthesized abbreviation that is + # *not* a dictionary word stays glued to its parentheses and is dropped + # like any other unrecognized edge token, so GMT is used here. + settings = {"IGNORE_SURROUNDING_TEXT": True, "RETURN_AS_TIMEZONE_AWARE": True} + wrapped = dateparser.parse( + "Last updated: 12 March 2019 at 10:30 (GMT)", + languages=["en"], + settings=settings, + ) + bare = dateparser.parse( + "12 March 2019 at 10:30 (GMT)", + languages=["en"], + settings={"RETURN_AS_TIMEZONE_AWARE": True}, + ) + assert wrapped is not None + self.assertEqual("GMT", wrapped.tzname()) + self.assertEqual(timedelta(0), wrapped.utcoffset()) + self.assertEqual(bare, wrapped) + + def test_only_trailing_timezone_is_preserved(self) -> None: + # tz-recognition when stripping edge tokens is deliberately applied to + # the trailing edge only: a timezone that follows the date is kept and + # applied, while the same abbreviation before the date is treated as + # ordinary surrounding text and dropped. + settings = {"IGNORE_SURROUNDING_TEXT": True, "RETURN_AS_TIMEZONE_AWARE": True} + trailing = dateparser.parse( + "23 March 2000 1:21 PM EST", languages=["en"], settings=settings + ) + leading = dateparser.parse( + "EST 23 March 2000 1:21 PM", languages=["en"], settings=settings + ) + without_tz = dateparser.parse( + "23 March 2000 1:21 PM", + languages=["en"], + settings={"RETURN_AS_TIMEZONE_AWARE": True}, + ) + # Trailing EST is applied... + assert trailing is not None + self.assertEqual(timedelta(hours=-5), trailing.utcoffset()) + # ...leading EST is not: the result matches the same string with no + # timezone at all, and does not carry the EST offset. + self.assertEqual(without_tz, leading) + self.assertNotEqual(trailing, leading) + + def test_trailing_timezone_followed_by_more_text_is_dropped(self) -> None: + # Known limitation: a trailing timezone is kept only when it is the + # final token. If unrecognized text follows it, the tokenizer merges + # the two, so the timezone is stripped together with that text and its + # offset is not applied (use search_dates for such input). The date is + # still parsed -- only the timezone is lost. + settings = {"IGNORE_SURROUNDING_TEXT": True, "RETURN_AS_TIMEZONE_AWARE": True} + result = dateparser.parse( + "Updated 23 March 2000 1:21 PM EST reportedly", + languages=["en"], + settings=settings, + ) + assert result is not None + self.assertEqual(datetime(2000, 3, 23, 13, 21), result.replace(tzinfo=None)) + self.assertNotEqual(timedelta(hours=-5), result.utcoffset()) + + def test_leading_numeric_noise_is_not_ignored(self) -> None: + # Documented limitation: stripping stops at the first recognized token, + # and a number counts as recognized, so leading text that contains a + # number of its own blocks parsing. search_dates covers this shape. + self.when_date_is_parsed( + "invoice 12345 paid on 3 March 2019", + languages=["en"], + settings={"IGNORE_SURROUNDING_TEXT": True}, + ) + self.then_date_was_not_parsed() + + def when_date_is_parsed(self, date_string: str, **kwargs: Any) -> None: + self.result = dateparser.parse(date_string, **kwargs) + + def then_parsed_datetime_is(self, expected_datetime: datetime) -> None: + self.assertEqual(expected_datetime, self.result) + + def then_date_was_not_parsed(self) -> None: self.assertIsNone(self.result) diff --git a/tests/test_data.py b/tests/test_data.py index b8c6deae6..30127d11d 100644 --- a/tests/test_data.py +++ b/tests/test_data.py @@ -1,10 +1,13 @@ +from collections.abc import Iterable, Mapping from itertools import chain +from typing import Any import regex as re from parameterized import parameterized -from dateparser.data import language_locale_dict +from dateparser.data.languages_info import language_locale_dict from dateparser.languages import default_loader +from dateparser.languages.locale import Locale from tests import BaseTestCase DEFAULT_MONTH_PATTERN = re.compile(r"^M?\d+$", re.U) @@ -58,6 +61,11 @@ "second", "am", "pm", + "early_morning", + "morning", + "afternoon", + "evening", + "night", "relative-type", "relative-type-regex", "sentence_splitter_group", @@ -109,11 +117,11 @@ ] -def is_invalid_translation(translation): +def is_invalid_translation(translation: object) -> bool: return (not (translation and isinstance(translation, str))) or "." in translation -def is_invalid_month_translation(translation): +def is_invalid_month_translation(translation: object) -> bool | re.Match[str] | None: return ( (not (translation and isinstance(translation, str))) or "." in translation @@ -121,7 +129,7 @@ def is_invalid_month_translation(translation): ) -def is_invalid_am_pm_translation(translation): +def is_invalid_am_pm_translation(translation: object) -> bool | re.Match[str] | None: return ( (not (translation and isinstance(translation, str))) or "." in translation @@ -129,249 +137,251 @@ def is_invalid_am_pm_translation(translation): ) -def is_invalid_simplification(simplification): +def is_invalid_simplification(simplification: object) -> bool: if not isinstance(simplification, dict) or len(simplification) != 1: return True - key, value = list(simplification.items())[0] + key, value = next(iter(simplification.items())) return not isinstance(key, str) or not isinstance(value, str) -def is_invalid_relative_mapping(relative_mapping): +def is_invalid_relative_mapping(relative_mapping: tuple[object, object]) -> bool: key, value = relative_mapping if not (key and value and isinstance(key, str) and isinstance(value, list)): return True - return not all([isinstance(x, str) for x in value]) + return not all(isinstance(x, str) for x in value) -def is_invalid_relative_regex_mapping(relative_regex_mapping): +def is_invalid_relative_regex_mapping( + relative_regex_mapping: tuple[object, object], +) -> bool: key, value = relative_regex_mapping if not (key and value and isinstance(key, str) and isinstance(value, list)): return True - return not all([isinstance(x, str) for x in value]) + return not all(isinstance(x, str) for x in value) class TestLocaleInfo(BaseTestCase): - def setUp(self): + def setUp(self) -> None: super().setUp() - self.info = NotImplemented - self.shortname = NotImplemented + self.info: Mapping[str, Any] = NotImplemented + self.shortname: str = NotImplemented @parameterized.expand(all_locale_params) - def test_extra_keys(self, locale): + def test_extra_keys(self, locale: Locale) -> None: self.given_locale_info(locale) extra_keys = list(set(self.info.keys()) - set(VALID_KEYS)) self.assertFalse( - extra_keys, "Extra keys found for {}: {}".format(self.shortname, extra_keys) + extra_keys, f"Extra keys found for {self.shortname}: {extra_keys}" ) @parameterized.expand(all_locale_params) - def test_necessary_keys(self, locale): + def test_necessary_keys(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_keys_present_in_info(NECESSARY_KEYS) self.then_translations_present_in_info(NECESSARY_KEYS) @parameterized.expand(all_locale_params) - def test_name(self, locale): + def test_name(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_name_is_valid() @parameterized.expand(all_locale_params) - def test_date_order(self, locale): + def test_date_order(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_date_order_is_valid() @parameterized.expand(all_locale_params) - def test_january_translation(self, locale): + def test_january_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_month_translations_are_valid("january") @parameterized.expand(all_locale_params) - def test_february_translation(self, locale): + def test_february_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_month_translations_are_valid("february") @parameterized.expand(all_locale_params) - def test_march_translation(self, locale): + def test_march_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_month_translations_are_valid("march") @parameterized.expand(all_locale_params) - def test_april_translation(self, locale): + def test_april_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_month_translations_are_valid("april") @parameterized.expand(all_locale_params) - def test_may_translation(self, locale): + def test_may_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_month_translations_are_valid("may") @parameterized.expand(all_locale_params) - def test_june_translation(self, locale): + def test_june_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_month_translations_are_valid("june") @parameterized.expand(all_locale_params) - def test_july_translation(self, locale): + def test_july_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_month_translations_are_valid("july") @parameterized.expand(all_locale_params) - def test_august_translation(self, locale): + def test_august_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_month_translations_are_valid("august") @parameterized.expand(all_locale_params) - def test_september_translation(self, locale): + def test_september_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_month_translations_are_valid("september") @parameterized.expand(all_locale_params) - def test_october_translation(self, locale): + def test_october_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_month_translations_are_valid("october") @parameterized.expand(all_locale_params) - def test_november_translation(self, locale): + def test_november_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_month_translations_are_valid("november") @parameterized.expand(all_locale_params) - def test_december_translation(self, locale): + def test_december_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_month_translations_are_valid("december") @parameterized.expand(all_locale_params) - def test_am_translation(self, locale): + def test_am_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_am_pm_translations_are_valid("am") @parameterized.expand(all_locale_params) - def test_pm_translation(self, locale): + def test_pm_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_am_pm_translations_are_valid("pm") @parameterized.expand(all_locale_params) - def test_sunday_translation(self, locale): + def test_sunday_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_translations_are_valid("sunday") @parameterized.expand(all_locale_params) - def test_monday_translation(self, locale): + def test_monday_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_translations_are_valid("monday") @parameterized.expand(all_locale_params) - def test_tuesday_translation(self, locale): + def test_tuesday_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_translations_are_valid("tuesday") @parameterized.expand(all_locale_params) - def test_wednesday_translation(self, locale): + def test_wednesday_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_translations_are_valid("wednesday") @parameterized.expand(all_locale_params) - def test_thursday_translation(self, locale): + def test_thursday_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_translations_are_valid("thursday") @parameterized.expand(all_locale_params) - def test_friday_translation(self, locale): + def test_friday_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_translations_are_valid("friday") @parameterized.expand(all_locale_params) - def test_saturday_translation(self, locale): + def test_saturday_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_translations_are_valid("saturday") @parameterized.expand(all_locale_params) - def test_year_translation(self, locale): + def test_year_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_translations_are_valid("year") @parameterized.expand(all_locale_params) - def test_month_translation(self, locale): + def test_month_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_translations_are_valid("month") @parameterized.expand(all_locale_params) - def test_week_translation(self, locale): + def test_week_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_translations_are_valid("week") @parameterized.expand(all_locale_params) - def test_day_translation(self, locale): + def test_day_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_translations_are_valid("day") @parameterized.expand(all_locale_params) - def test_hour_translation(self, locale): + def test_hour_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_translations_are_valid("hour") @parameterized.expand(all_locale_params) - def test_minute_translation(self, locale): + def test_minute_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_translations_are_valid("minute") @parameterized.expand(all_locale_params) - def test_second_translation(self, locale): + def test_second_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_translations_are_valid("second") @parameterized.expand(all_locale_params) - def test_ago_translation(self, locale): + def test_ago_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_translations_are_valid("ago") @parameterized.expand(all_locale_params) - def test_in_translation(self, locale): + def test_in_translation(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_translations_are_valid("in") @parameterized.expand(all_locale_params) - def test_skip_tokens(self, locale): + def test_skip_tokens(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_skip_pertain_tokens_are_valid("skip") @parameterized.expand(all_locale_params) - def test_pertain_tokens(self, locale): + def test_pertain_tokens(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_skip_pertain_tokens_are_valid("pertain") @parameterized.expand(all_locale_params) - def test_simplifications(self, locale): + def test_simplifications(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_simplifications_are_valid() @parameterized.expand(all_locale_params) - def test_relative_type(self, locale): + def test_relative_type(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_relative_type_is_valid() @parameterized.expand(all_locale_params) - def test_relative_type_regex(self, locale): + def test_relative_type_regex(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_relative_type_regex_is_valid() @parameterized.expand(all_locale_params) - def test_no_word_spacing(self, locale): + def test_no_word_spacing(self, locale: Locale) -> None: self.given_locale_info(locale) self.then_no_word_spacing_is_valid() - def given_locale_info(self, locale): + def given_locale_info(self, locale: Locale) -> None: self.info = locale.info self.shortname = locale.shortname - def then_keys_present_in_info(self, keys_list): + def then_keys_present_in_info(self, keys_list: Iterable[str]) -> None: absent_keys = list(set(keys_list) - set(self.info.keys())) self.assertFalse( absent_keys, "{} not found in locale {}".format(", ".join(absent_keys), self.shortname), ) - def then_translations_present_in_info(self, keys_list): + def then_translations_present_in_info(self, keys_list: Iterable[str]) -> None: no_translation_keys = [key for key in keys_list if not self.info.get(key)] self.assertFalse( no_translation_keys, @@ -380,46 +390,40 @@ def then_translations_present_in_info(self, keys_list): ), ) - def then_name_is_valid(self): + def then_name_is_valid(self) -> None: name = self.info["name"] self.assertIsInstance( name, str, - "Invalid type for name: {} for locale {}".format( - type(name).__name__, self.shortname - ), + f"Invalid type for name: {type(name).__name__} for locale {self.shortname}", ) self.assertEqual( name, self.shortname, - "Invalid name: {} for locale {}".format(name, self.shortname), + f"Invalid name: {name} for locale {self.shortname}", ) - def then_date_order_is_valid(self): + def then_date_order_is_valid(self) -> None: if "date_order" in self.info: date_order = self.info["date_order"] self.assertIsInstance( date_order, str, - "Invalid type for date_order: {} for locale {}".format( - type(date_order).__name__, self.shortname - ), + f"Invalid type for date_order: {type(date_order).__name__} for locale {self.shortname}", ) self.assertIn( date_order, ["DMY", "DYM", "MDY", "MYD", "YDM", "YMD"], - "Invalid date_order {} for {}".format(date_order, self.shortname), + f"Invalid date_order {date_order} for {self.shortname}", ) - def then_month_translations_are_valid(self, month): + def then_month_translations_are_valid(self, month: str) -> None: if month in self.info: month_translations = self.info[month] self.assertIsInstance( month_translations, list, - "Invalid type for {}: {} for locale {}".format( - month, type(month_translations).__name__, self.shortname - ), + f"Invalid type for {month}: {type(month_translations).__name__} for locale {self.shortname}", ) invalid_translations = list( filter(is_invalid_month_translation, month_translations) @@ -431,15 +435,13 @@ def then_month_translations_are_valid(self, month): ), ) - def then_am_pm_translations_are_valid(self, key): + def then_am_pm_translations_are_valid(self, key: str) -> None: if key in self.info: translations_list = self.info[key] self.assertIsInstance( translations_list, list, - "Invalid type for {}: {} for locale {}".format( - key, type(translations_list).__name__, self.shortname - ), + f"Invalid type for {key}: {type(translations_list).__name__} for locale {self.shortname}", ) invalid_translations = list( filter(is_invalid_am_pm_translation, translations_list) @@ -451,15 +453,13 @@ def then_am_pm_translations_are_valid(self, key): ), ) - def then_translations_are_valid(self, key): + def then_translations_are_valid(self, key: str) -> None: if key in self.info: translations_list = self.info[key] self.assertIsInstance( translations_list, list, - "Invalid type for {}: {} for locale {}".format( - key, type(translations_list).__name__, self.shortname - ), + f"Invalid type for {key}: {type(translations_list).__name__} for locale {self.shortname}", ) invalid_translations = list( filter(is_invalid_translation, translations_list) @@ -471,15 +471,13 @@ def then_translations_are_valid(self, key): ), ) - def then_skip_pertain_tokens_are_valid(self, key): + def then_skip_pertain_tokens_are_valid(self, key: str) -> None: if key in self.info: tokens_list = self.info[key] self.assertIsInstance( tokens_list, list, - "Invalid type for {}: {} for locale {}".format( - key, type(tokens_list).__name__, self.shortname - ), + f"Invalid type for {key}: {type(tokens_list).__name__} for locale {self.shortname}", ) invalid_tokens = [ token @@ -493,15 +491,13 @@ def then_skip_pertain_tokens_are_valid(self, key): ), ) - def then_simplifications_are_valid(self): + def then_simplifications_are_valid(self) -> None: if "simplifications" in self.info: simplifications_list = self.info["simplifications"] self.assertIsInstance( simplifications_list, list, - "Invalid type for simplifications: {} for locale {}".format( - type(simplifications_list).__name__, self.shortname - ), + f"Invalid type for simplifications: {type(simplifications_list).__name__} for locale {self.shortname}", ) invalid_simplifications = list( filter(is_invalid_simplification, simplifications_list) @@ -514,15 +510,13 @@ def then_simplifications_are_valid(self): + ", each simplification must be a single string to string mapping", ) - def then_relative_type_is_valid(self): + def then_relative_type_is_valid(self) -> None: if "relative-type" in self.info: relative_type_dict = self.info["relative-type"] self.assertIsInstance( relative_type_dict, dict, - "Invalid type for relative-type: {} for locale {}".format( - type(relative_type_dict).__name__, self.shortname - ), + f"Invalid type for relative-type: {type(relative_type_dict).__name__} for locale {self.shortname}", ) invalid_relative_type = list( filter(is_invalid_relative_mapping, relative_type_dict.items()) @@ -535,15 +529,13 @@ def then_relative_type_is_valid(self): + ", each mapping must be a string to list (of strings) mapping", ) - def then_relative_type_regex_is_valid(self): + def then_relative_type_regex_is_valid(self) -> None: if "relative-type-regex" in self.info: relative_type_dict = self.info["relative-type-regex"] self.assertIsInstance( relative_type_dict, dict, - "Invalid type for relative-type-regex: {} for locale {}".format( - type(relative_type_dict).__name__, self.shortname - ), + f"Invalid type for relative-type-regex: {type(relative_type_dict).__name__} for locale {self.shortname}", ) invalid_relative_type_regex = list( filter(is_invalid_relative_regex_mapping, relative_type_dict.items()) @@ -556,20 +548,16 @@ def then_relative_type_regex_is_valid(self): + ", each mapping must be a string to list (of strings) mapping", ) - def then_no_word_spacing_is_valid(self): + def then_no_word_spacing_is_valid(self) -> None: if "no_word_spacing" in self.info: no_word_spacing = self.info["no_word_spacing"] self.assertIsInstance( no_word_spacing, str, - "Invalid type for no_word_spacing: {} for locale {}".format( - type(no_word_spacing).__name__, self.shortname - ), + f"Invalid type for no_word_spacing: {type(no_word_spacing).__name__} for locale {self.shortname}", ) self.assertIn( no_word_spacing, ["True", "False"], - "Invalid no_word_spacing {} for {}".format( - no_word_spacing, self.shortname - ), + f"Invalid no_word_spacing {no_word_spacing} for {self.shortname}", ) diff --git a/tests/test_date.py b/tests/test_date.py index 249919ae4..8b0aab35f 100644 --- a/tests/test_date.py +++ b/tests/test_date.py @@ -1,13 +1,12 @@ -#!/usr/bin/env python - import datetime as real_datetime import os import unittest -from collections import OrderedDict +from collections.abc import Iterable from datetime import datetime, timedelta from datetime import timezone as dttz from itertools import product from time import tzset +from typing import Any from unittest.mock import Mock, patch import pytest @@ -17,13 +16,14 @@ from dateparser import date from dateparser.conf import Settings from dateparser.date import DateData +from dateparser.languages.locale import Locale from tests import BaseTestCase class TestDateRangeFunction(BaseTestCase): - def setUp(self): + def setUp(self) -> None: super().setUp() - self.result = NotImplemented + self.result: list[datetime] = NotImplemented @parameterized.expand( [ @@ -34,7 +34,9 @@ def setUp(self): ) ] ) - def test_date_range(self, begin, end, expected_length): + def test_date_range( + self, begin: datetime, end: datetime, expected_length: int + ) -> None: self.when_date_range_generated(begin, end) self.then_range_length_is(expected_length) self.then_all_dates_in_range_are_present(begin, end) @@ -64,7 +66,9 @@ def test_date_range(self, begin, end, expected_length): ), ] ) - def test_one_date_for_each_month(self, begin, end, expected_months): + def test_one_date_for_each_month( + self, begin: datetime, end: datetime, expected_months: list[tuple[int, int]] + ) -> None: self.when_date_range_generated(begin, end, months=1) self.then_expected_months_are(expected_months) @@ -79,7 +83,9 @@ def test_one_date_for_each_month(self, begin, end, expected_months): "second", ] ) - def test_should_reject_easily_mistaken_dateutil_arguments(self, invalid_period): + def test_should_reject_easily_mistaken_dateutil_arguments( + self, invalid_period: str + ) -> None: self.when_date_range_generated( begin=datetime(2014, 6, 15), end=datetime(2014, 6, 25), @@ -87,43 +93,47 @@ def test_should_reject_easily_mistaken_dateutil_arguments(self, invalid_period): ) self.then_period_was_rejected(invalid_period) - def when_date_range_generated(self, begin, end, **size): + def when_date_range_generated( + self, begin: datetime, end: datetime, **size: int + ) -> None: try: self.result = list(date.date_range(begin, end, **size)) except Exception as error: self.error = error - def then_expected_months_are(self, expected): + def then_expected_months_are(self, expected: list[tuple[int, int]]) -> None: self.assertEqual(expected, [(d.year, d.month) for d in self.result]) - def then_range_length_is(self, expected_length): + def then_range_length_is(self, expected_length: int) -> None: self.assertEqual(expected_length, len(self.result)) - def then_all_dates_in_range_are_present(self, begin, end): + def then_all_dates_in_range_are_present( + self, begin: datetime, end: datetime + ) -> None: date_under_test = begin while date_under_test < end: self.assertIn(date_under_test, self.result) date_under_test += timedelta(days=1) - def then_range_is_in_ascending_order(self): + def then_range_is_in_ascending_order(self) -> None: for i in range(len(self.result) - 1): self.assertLess(self.result[i], self.result[i + 1]) - def then_period_was_rejected(self, period): - self.then_error_was_raised(ValueError, ["Invalid argument: {}".format(period)]) + def then_period_was_rejected(self, period: str) -> None: + self.then_error_was_raised(ValueError, [f"Invalid argument: {period}"]) class TestGetIntersectingPeriodsFunction(BaseTestCase): - def setUp(self): + def setUp(self) -> None: super().setUp() - self.result = NotImplemented + self.result: list[datetime] = NotImplemented @parameterized.expand( [param(low=datetime(2014, 6, 15), high=datetime(2014, 6, 16), length=1)] ) def test_date_arguments_and_date_range_with_default_post_days( - self, low, high, length - ): + self, low: datetime, high: datetime, length: int + ) -> None: self.when_intersecting_period_calculated(low, high, period_size="day") self.then_all_dates_in_range_are_present(begin=low, end=high) self.then_date_range_length_is(length) @@ -171,8 +181,8 @@ def test_date_arguments_and_date_range_with_default_post_days( ] ) def test_dates_in_intersecting_period_should_use_first_day_when_period_is_month( - self, low, high, expected_results - ): + self, low: datetime, high: datetime, expected_results: list[datetime] + ) -> None: self.when_intersecting_period_calculated(low, high, period_size="month") self.then_results_are(expected_results) @@ -223,8 +233,8 @@ def test_dates_in_intersecting_period_should_use_first_day_when_period_is_month( ] ) def test_dates_in_intersecting_period_should_use_first_month_and_first_day_when_period_is_year( - self, low, high, expected_results - ): + self, low: datetime, high: datetime, expected_results: list[datetime] + ) -> None: self.when_intersecting_period_calculated(low, high, period_size="year") self.then_results_are(expected_results) @@ -278,7 +288,13 @@ def test_dates_in_intersecting_period_should_use_first_month_and_first_day_when_ ), ] ) - def test_periods(self, low, high, period_size, expected_results): + def test_periods( + self, + low: datetime, + high: datetime, + period_size: str, + expected_results: list[datetime], + ) -> None: self.when_intersecting_period_calculated(low, high, period_size=period_size) self.then_results_are(expected_results) @@ -294,7 +310,9 @@ def test_periods(self, low, high, period_size, expected_results): param("some_period"), ] ) - def test_should_reject_easily_mistaken_dateutil_arguments(self, period_size): + def test_should_reject_easily_mistaken_dateutil_arguments( + self, period_size: str + ) -> None: self.when_intersecting_period_calculated( low=datetime(2014, 6, 15), high=datetime(2014, 6, 25), @@ -316,11 +334,15 @@ def test_should_reject_easily_mistaken_dateutil_arguments(self, period_size): ), ] ) - def test_empty_period(self, low, high, period_size): + def test_empty_period( + self, low: datetime, high: datetime, period_size: str + ) -> None: self.when_intersecting_period_calculated(low, high, period_size) self.then_period_is_empty() - def when_intersecting_period_calculated(self, low, high, period_size): + def when_intersecting_period_calculated( + self, low: datetime, high: datetime, period_size: str + ) -> None: try: self.result = list( date.get_intersecting_periods(low, high, period=period_size) @@ -328,26 +350,28 @@ def when_intersecting_period_calculated(self, low, high, period_size): except Exception as error: self.error = error - def then_results_are(self, expected_results): + def then_results_are(self, expected_results: list[datetime]) -> None: self.assertEqual(expected_results, self.result) - def then_date_range_length_is(self, size): + def then_date_range_length_is(self, size: int) -> None: self.assertEqual(size, len(self.result)) - def then_all_dates_in_range_are_present(self, begin, end): + def then_all_dates_in_range_are_present( + self, begin: datetime, end: datetime + ) -> None: date_under_test = begin while date_under_test < end: self.assertIn(date_under_test, self.result) date_under_test += timedelta(days=1) - def then_period_is_empty(self): + def then_period_is_empty(self) -> None: self.assertEqual([], self.result) class TestParseWithFormatsFunction(BaseTestCase): - def setUp(self): + def setUp(self) -> None: super().setUp() - self.result = NotImplemented + self.result: DateData = NotImplemented @parameterized.expand( [ @@ -355,8 +379,8 @@ def setUp(self): ] ) def test_date_with_not_matching_format_is_not_parsed( - self, date_string, date_formats - ): + self, date_string: str, date_formats: list[str] + ) -> None: self.when_date_is_parsed_with_formats(date_string, date_formats) self.then_date_was_not_parsed() @@ -369,12 +393,188 @@ def test_date_with_not_matching_format_is_not_parsed( ), ] ) - def test_should_parse_date(self, date_string, date_formats, expected_result): + def test_should_parse_date( + self, date_string: str, date_formats: list[str], expected_result: datetime + ) -> None: + self.when_date_is_parsed_with_formats(date_string, date_formats) + self.then_date_was_parsed() + self.then_parsed_period_is("day") + self.then_parsed_date_is(expected_result) + + @parameterized.expand( + [ + ("01.24-1", "%W.%y-%w", datetime(2024, 1, 1)), + ("2024-01-1", "%Y-%U-%w", datetime(2024, 1, 8)), + ("2023-00-1", "%Y-%W-%w", datetime(2022, 12, 26)), + ("2024-09-4", "%Y-%W-%u", datetime(2024, 2, 29)), + ("2024-09-Thu", "%Y-%W-%a", datetime(2024, 2, 29)), + ("2024-08-Thursday", "%Y-%U-%A", datetime(2024, 2, 29)), + ("01.2024-1", "%V.%G-%u", datetime(2024, 1, 1)), + ("2019-W01-1", "%G-W%V-%u", datetime(2018, 12, 31)), + ("2020-W53-5", "%G-W%V-%u", datetime(2021, 1, 1)), + ("2020-W53-Fri", "%G-W%V-%a", datetime(2021, 1, 1)), + ("2020-W53-Friday", "%G-W%V-%A", datetime(2021, 1, 1)), + ("2020-W53-5", "%G-W%V-%w", datetime(2021, 1, 1)), + ] + ) + def test_should_preserve_complete_week_date( + self, text: str, fmt: str, expected: datetime + ) -> None: + self.given_now(2026, 9, 15) + for preference in ("first", "last", "current"): + with self.subTest(preference=preference): + settings = { + "RELATIVE_BASE": datetime(2026, 9, 15), + "PREFER_DAY_OF_MONTH": preference, + "PREFER_MONTH_OF_YEAR": preference, + "PARSERS": ["custom-formats"], + } + parsed = date.DateDataParser(settings=settings).get_date_data( + text, date_formats=[fmt] + ) + self.assertEqual(parsed.date_obj, expected) + self.assertEqual(parsed.period, "day") + self.assertEqual( + dateparser.parse(text, date_formats=[fmt], settings=settings), + expected, + ) + + @parameterized.expand( + [ + ("2024-09", "%Y-%W", 2024), + ("2024-1", "%Y-%w", 2024), + ("2024-%W-1", "%Y-%%W-%w", 2024), + ("2024-01-%w", "%Y-%W-%%w", 2024), + ("09-1", "%W-%w", 2026), + ] + ) + def test_incomplete_week_date_keeps_date_preferences( + self, text: str, fmt: str, year: int + ) -> None: + self.given_now(2026, 9, 15) + settings = Settings().replace( + RELATIVE_BASE=datetime(2026, 9, 15), + PREFER_DAY_OF_MONTH="last", + PREFER_MONTH_OF_YEAR="last", + ) + self.when_date_is_parsed_with_formats(text, [fmt], settings) + self.then_parsed_date_is(datetime(year, 12, 31)) + self.then_parsed_period_is("year") + + @parameterized.expand( + [ + ("2024-W01", "%G-W%V"), + ("2024-W01-1", "%Y-W%V-%u"), + ("2024-W01-1", "%G-W%W-%u"), + ("2024-W01-8", "%G-W%V-%u"), + ] + ) + def test_invalid_iso_week_date_is_not_parsed(self, text: str, fmt: str) -> None: + self.when_date_is_parsed_with_formats(text, [fmt]) + self.then_date_was_not_parsed() + + @parameterized.expand( + [ + param( + date_string="2023-100", + date_formats=["%Y-%j"], + expected_result=datetime(2023, 4, 10), + ), + param( + date_string="2024-060", + date_formats=["%Y-%j"], + expected_result=datetime(2024, 2, 29), + ), + param( + date_string="2023 060", + date_formats=["%Y %j"], + expected_result=datetime(2023, 3, 1), + ), + ] + ) + def test_should_parse_day_of_year_format( + self, date_string: str, date_formats: list[str], expected_result: datetime + ) -> None: + """Format %%j (day of year) should correctly set both month and day.""" + self.when_date_is_parsed_with_formats(date_string, date_formats) + self.then_date_was_parsed() + self.then_parsed_period_is("day") + self.then_parsed_date_is(expected_result) + + @parameterized.expand( + [ + param( + date_string="1999001", + date_formats=["%Y%j"], + expected_result=datetime(1999, 1, 1), + ), + param( + date_string="1999050", + date_formats=["%Y%j"], + expected_result=datetime(1999, 2, 19), + ), + param( + date_string="1999032", + date_formats=["%Y%j"], + expected_result=datetime(1999, 2, 1), + ), + param( + date_string="1999059", + date_formats=["%Y%j"], + expected_result=datetime(1999, 2, 28), + ), + param( + date_string="1999060", + date_formats=["%Y%j"], + expected_result=datetime(1999, 3, 1), + ), + param( + date_string="1999365", + date_formats=["%Y%j"], + expected_result=datetime(1999, 12, 31), + ), + param( + date_string="2000060", + date_formats=["%Y%j"], + expected_result=datetime(2000, 2, 29), + ), + param( + date_string="2000366", + date_formats=["%Y%j"], + expected_result=datetime(2000, 12, 31), + ), + ] + ) + def test_should_parse_day_of_year_boundaries( + self, date_string: str, date_formats: list[str], expected_result: datetime + ) -> None: + """Format %%j (day of year) should handle month and leap year edges.""" self.when_date_is_parsed_with_formats(date_string, date_formats) self.then_date_was_parsed() self.then_parsed_period_is("day") self.then_parsed_date_is(expected_result) + @parameterized.expand( + [ + # 366 is only a valid day of year in leap years, and must not be + # rolled over into the next year. + param(date_string="1999366", date_formats=["%Y%j"]), + param(date_string="2023-366", date_formats=["%Y-%j"]), + param(date_string="1900366", date_formats=["%Y%j"]), + param(date_string="2100 366", date_formats=["%Y %j"]), + # Values that are out of the %j range altogether. + param(date_string="1999000", date_formats=["%Y%j"]), + param(date_string="1999367", date_formats=["%Y%j"]), + param(date_string="1999777", date_formats=["%Y%j"]), + ] + ) + def test_should_not_parse_out_of_range_day_of_year( + self, date_string: str, date_formats: list[str] + ) -> None: + """Format %%j (day of year) should reject days the year does not have.""" + self.when_date_is_parsed_with_formats(date_string, date_formats) + self.then_date_was_not_parsed() + @parameterized.expand( [ param( @@ -386,8 +586,12 @@ def test_should_parse_date(self, date_string, date_formats, expected_result): ] ) def test_should_use_current_year_for_dates_without_year( - self, date_string, date_formats, expected_month, expected_day - ): + self, + date_string: str, + date_formats: list[str], + expected_month: int, + expected_day: int, + ) -> None: self.given_now(2015, 2, 4) self.when_date_is_parsed_with_formats(date_string, date_formats) self.then_date_was_parsed() @@ -427,14 +631,14 @@ def test_should_use_current_year_for_dates_without_year( ) def test_should_use_correct_day_from_settings_for_dates_without_day( self, - date_string, - date_formats, - expected_year, - expected_month, - today_day, - prefer_day_of_month, - expected_day, - ): + date_string: str, + date_formats: list[str], + expected_year: int, + expected_month: int, + today_day: int, + prefer_day_of_month: str, + expected_day: int, + ) -> None: self.given_now(2014, 8, today_day) settings_mod = Settings() settings_mod.PREFER_DAY_OF_MONTH = prefer_day_of_month @@ -478,14 +682,14 @@ def test_should_use_correct_day_from_settings_for_dates_without_day( ) def test_should_use_correct_month_from_settings_for_dates_without_month( self, - date_string, - date_formats, - expected_year, - prefer_month_of_year, - current_month, - expected_month, - expected_day, - ): + date_string: str, + date_formats: list[str], + expected_year: int, + prefer_month_of_year: str, + current_month: int, + expected_month: int, + expected_day: int, + ) -> None: self.given_now(2014, current_month, 1) settings_mod = Settings() settings_mod.PREFER_MONTH_OF_YEAR = prefer_month_of_year @@ -513,16 +717,16 @@ def test_should_use_correct_month_from_settings_for_dates_without_month( ) def test_should_use_correct_day_n_month_from_settings_for_dates_without_day_n_month( self, - date_string, - date_formats, - current_day, - current_month, - prefer_day_of_month, - prefer_month_of_year, - expected_year, - expected_month, - expected_day, - ): + date_string: str, + date_formats: list[str], + current_day: int, + current_month: int, + prefer_day_of_month: str, + prefer_month_of_year: str, + expected_year: int, + expected_month: int, + expected_day: int, + ) -> None: self.given_now(2014, current_month, current_day) settings_mod = Settings() settings_mod.PREFER_DAY_OF_MONTH = prefer_day_of_month @@ -534,7 +738,7 @@ def test_should_use_correct_day_n_month_from_settings_for_dates_without_day_n_mo datetime(year=expected_year, month=expected_month, day=expected_day) ) - def given_now(self, year, month, day, **time): + def given_now(self, year: int, month: int, day: int, **time: Any) -> None: now = datetime(year, month, day, **time) datetime_mock = Mock(wraps=datetime) datetime_mock.utcnow = Mock(return_value=now) @@ -544,40 +748,43 @@ def given_now(self, year, month, day, **time): self.add_patch(patch("dateparser.utils.datetime", new=datetime_mock)) def when_date_is_parsed_with_formats( - self, date_string, date_formats, custom_settings=None - ): + self, + date_string: str, + date_formats: Iterable[str], + custom_settings: Settings | None = None, + ) -> None: self.result = date.parse_with_formats( date_string, date_formats, custom_settings or Settings() ) - def then_date_was_not_parsed(self): + def then_date_was_not_parsed(self) -> None: self.assertIsNotNone(self.result) self.assertIsNone(self.result["date_obj"]) - def then_date_was_parsed(self): + def then_date_was_parsed(self) -> None: self.assertIsNotNone(self.result) self.assertIsNotNone(self.result["date_obj"]) - def then_parsed_date_is(self, date_obj): + def then_parsed_date_is(self, date_obj: datetime) -> None: self.assertEqual(date_obj.date(), self.result["date_obj"].date()) - def then_parsed_period_is(self, period): + def then_parsed_period_is(self, period: str) -> None: self.assertEqual(period, self.result["period"]) class TestDateDataParser(BaseTestCase): - def setUp(self): + def setUp(self) -> None: super().setUp() - self.parser = NotImplemented - self.result = NotImplemented - self.multiple_results = NotImplemented + self.parser: date.DateDataParser = NotImplemented + self.result: DateData = NotImplemented + self.multiple_results: list[DateData | Exception] = NotImplemented @parameterized.expand( [ param("10:04am EDT"), ] ) - def test_time_without_date_should_use_today(self, date_string): + def test_time_without_date_should_use_today(self, date_string: str) -> None: self.given_parser(settings={"RELATIVE_BASE": datetime(2020, 7, 19)}) self.when_date_string_is_parsed(date_string) self.then_date_was_parsed() @@ -608,25 +815,22 @@ def test_time_without_date_should_use_today(self, date_string): param("снощи", days_ago=1), ] ) - def test_temporal_nouns_are_parsed(self, date_string, days_ago): + def test_temporal_nouns_are_parsed(self, date_string: str, days_ago: int) -> None: self.given_parser() self.when_date_string_is_parsed(date_string) self.then_date_was_parsed() self.then_date_is_n_days_ago(days=days_ago) - def test_should_not_assume_language_too_early(self): - dates_to_parse = OrderedDict( - [ - ("07/07/2014", datetime(2014, 7, 7).date()), # any language - ("07.jul.2014 | 12:52", datetime(2014, 7, 7).date()), # en, es, pt, nl - ("07.ago.2014 | 12:52", datetime(2014, 8, 7).date()), # es, it, pt - ( - "07.feb.2014 | 12:52", - datetime(2014, 2, 7).date(), - ), # en, de, es, it, nl, ro - ("07.ene.2014 | 12:52", datetime(2014, 1, 7).date()), - ] - ) # es + def test_should_not_assume_language_too_early(self) -> None: + dates_to_parse = { + "07/07/2014": datetime(2014, 7, 7).date(), # any language + "07.jul.2014 | 12:52": datetime(2014, 7, 7).date(), # en, es, pt, nl + "07.ago.2014 | 12:52": datetime(2014, 8, 7).date(), # es, it, pt + "07.feb.2014 | 12:52": datetime( + 2014, 2, 7 + ).date(), # en, de, es, it, nl, ro + "07.ene.2014 | 12:52": datetime(2014, 1, 7).date(), # es + } self.given_parser( restrict_to_languages=["en", "de", "fr", "it", "pt", "nl", "ro", "es", "ru"] @@ -650,26 +854,28 @@ def test_should_not_assume_language_too_early(self): param(date_string="24 януари 2015г.", locale="bg"), ] ) - def test_returned_detected_locale_should_be(self, date_string, locale): + def test_returned_detected_locale_should_be( + self, date_string: str, locale: str + ) -> None: self.given_parser() self.when_date_string_is_parsed(date_string) self.then_detected_locale(locale) - def test_try_previous_locales_false(self): + def test_try_previous_locales_false(self) -> None: self.given_parser(try_previous_locales=False) self.when_date_string_is_parsed("Mañana") # es self.then_detected_locale("es") self.when_date_string_is_parsed("2020-05-01") self.then_detected_locale("en") - def test_try_previous_locales_true(self): + def test_try_previous_locales_true(self) -> None: self.given_parser(try_previous_locales=True) self.when_date_string_is_parsed("Mañana") # es self.then_detected_locale("es") self.when_date_string_is_parsed("2020-05-01") self.then_detected_locale("es") - def test_try_previous_locales_order_deterministic(self): + def test_try_previous_locales_order_deterministic(self) -> None: self.given_parser(try_previous_locales=True) self.when_date_string_is_parsed("Mañana") # es self.then_detected_locale("es") @@ -682,12 +888,47 @@ def test_try_previous_locales_order_deterministic(self): param("2014-10-09T17:57:39+00:00"), ] ) - def test_get_date_data_should_not_strip_timezone_info(self, date_string): + def test_get_date_data_should_not_strip_timezone_info( + self, date_string: str + ) -> None: self.given_parser() self.when_date_string_is_parsed(date_string) self.then_date_was_parsed() self.then_parsed_date_has_timezone() + def test_ignore_surrounding_text_setting_parses_wrapped_date(self) -> None: + # Issue #518: a date wrapped in harmless extra text is parsed when the + # ``IGNORE_SURROUNDING_TEXT`` setting is enabled. + self.given_parser( + restrict_to_languages=["fr"], settings={"IGNORE_SURROUNDING_TEXT": True} + ) + self.when_date_string_is_parsed("Actualisé le 17 avril 2019") + self.then_date_was_parsed() + self.then_parsed_datetime_is(datetime(2019, 4, 17)) + self.then_detected_locale("fr") + self.then_period_is("day") + + def test_get_date_data_ignores_surrounding_text_only_when_enabled(self) -> None: + # The safety property of the ``IGNORE_SURROUNDING_TEXT`` setting: by + # default, ``get_date_data`` keeps requiring the whole string to be a + # date, so language detection and ``search_dates`` are unaffected. + self.given_parser(restrict_to_languages=["fr"]) + self.when_date_string_is_parsed("Actualisé le 17 avril 2019") + self.then_date_was_not_parsed() + + def test_ignore_surrounding_text_with_try_previous_locales(self) -> None: + self.given_parser( + restrict_to_languages=["fr", "en"], + try_previous_locales=True, + settings={"IGNORE_SURROUNDING_TEXT": True}, + ) + self.when_date_string_is_parsed("Actualisé le 17 avril 2019") + self.then_parsed_datetime_is(datetime(2019, 4, 17)) + self.then_previous_locales_is(["fr"]) + self.when_date_string_is_parsed("Publié le 16 avril 2019") + self.then_parsed_datetime_is(datetime(2019, 4, 16)) + self.then_previous_locales_is(["fr"]) + @parameterized.expand( [ param( @@ -712,7 +953,9 @@ def test_get_date_data_should_not_strip_timezone_info(self, date_string): ), ] ) - def test_parse_date_using_format(self, date_string, date_formats, expected_result): + def test_parse_date_using_format( + self, date_string: str, date_formats: list[str], expected_result: datetime + ) -> None: self.given_local_tz_offset(0) self.given_parser() self.when_date_string_is_parsed(date_string, date_formats) @@ -720,6 +963,28 @@ def test_parse_date_using_format(self, date_string, date_formats, expected_resul self.then_period_is("day") self.then_parsed_datetime_is(expected_result) + @parameterized.expand( + [ + param("xxxx junio 2020", ["xxxx %B %Y"], datetime(2020, 6, 1)), + param( + "el 15 de junio de 2020", ["el %d de %B de %Y"], datetime(2020, 6, 15) + ), + param( + "15 ENE, semana 3, 2020", ["%d %b, semana 3, %Y"], datetime(2020, 1, 15) + ), + param("mar, 16 jun 2020", ["%a, %d %b %Y"], datetime(2020, 6, 16)), + ] + ) + def test_parse_date_using_format_with_literal_text( + self, date_string: str, date_formats: list[str], expected_result: datetime + ) -> None: + self.given_parser( + restrict_to_languages=["es"], settings={"PREFER_DAY_OF_MONTH": "first"} + ) + self.when_date_string_is_parsed(date_string, date_formats) + self.then_parsed_datetime_is(expected_result) + self.then_detected_locale("es") + @parameterized.expand( [ param( @@ -730,16 +995,16 @@ def test_parse_date_using_format(self, date_string, date_formats, expected_resul ] ) def test_parsing_date_using_invalid_type_date_format_must_raise_error( - self, date_string, date_formats - ): + self, date_string: str, date_formats: object + ) -> None: self.given_local_tz_offset(0) self.given_parser() - self.when_date_string_is_parsed(date_string, date_formats) + self.when_date_string_is_parsed(date_string, date_formats) # type: ignore[arg-type] self.then_error_was_raised( TypeError, [ "Date formats should be list, tuple or set of strings", - "'{}' object is not iterable".format(type(date_formats).__name__), + f"'{type(date_formats).__name__}' object is not iterable", ], ) @@ -753,10 +1018,10 @@ def test_parsing_date_using_invalid_type_date_format_must_raise_error( ] ) def test_parsing_date_using_invalid_type_date_string_must_raise_error( - self, date_string - ): + self, date_string: object + ) -> None: self.given_parser() - self.when_date_string_is_parsed(date_string) + self.when_date_string_is_parsed(date_string) # type: ignore[arg-type] self.then_error_was_raised(TypeError, ["Input type must be str"]) @parameterized.expand( @@ -768,8 +1033,8 @@ def test_parsing_date_using_invalid_type_date_string_must_raise_error( ] ) def test_parse_date_with_timezones_not_using_formats( - self, date_string, expected_result - ): + self, date_string: str, expected_result: datetime + ) -> None: self.given_parser(settings={"TO_TIMEZONE": "UTC"}) self.when_date_string_is_parsed(date_string) self.then_date_was_parsed() @@ -787,8 +1052,8 @@ def test_parse_date_with_timezones_not_using_formats( ] ) def test_parse_date_with_timezones_using_formats_ignore_timezone( - self, date_string, date_formats, expected_result - ): + self, date_string: str, date_formats: list[str], expected_result: datetime + ) -> None: self.given_local_tz_offset(0) self.given_parser() self.when_date_string_is_parsed(date_string, date_formats) @@ -805,8 +1070,8 @@ def test_parse_date_with_timezones_using_formats_ignore_timezone( ] ) def test_should_parse_with_no_break_space_in_dates( - self, date_string, expected_result - ): + self, date_string: str, expected_result: datetime + ) -> None: self.given_parser() self.when_date_string_is_parsed(date_string) self.then_date_was_parsed() @@ -829,7 +1094,9 @@ def test_should_parse_with_no_break_space_in_dates( ), ] ) - def test_get_date_tuple(self, date_string, expected_result): + def test_get_date_tuple( + self, date_string: str, expected_result: tuple[datetime, str, str] + ) -> None: self.given_parser() self.when_get_date_tuple_is_called(date_string) self.then_returned_tuple_is(expected_result) @@ -866,7 +1133,7 @@ def test_get_date_tuple(self, date_string, expected_result): ), ] ) - def test_short_weekday_names(self, date_string, expected): + def test_short_weekday_names(self, date_string: str, expected: datetime) -> None: if "Mo" in date_string: pytest.xfail( "Known bug: 'Mo' is being interpreted as a month instead of a weekday and needs to be fixed." @@ -877,30 +1144,35 @@ def test_short_weekday_names(self, date_string, expected): self.when_date_string_is_parsed(date_string) self.then_parsed_datetime_is(expected) - def given_now(self, year, month, day, **time): + def given_now(self, year: int, month: int, day: int, **time: Any) -> None: now = real_datetime.datetime(year, month, day, **time) # Patch the datetime *class* in each target module class DateParserDateTime(real_datetime.datetime): @classmethod - def now(cls, tz=None): + def now( # type: ignore[override] + cls, tz: real_datetime.tzinfo | None = None + ) -> real_datetime.datetime: return now.replace(tzinfo=tz) if tz else now @classmethod - def utcnow(cls): + def utcnow(cls) -> real_datetime.datetime: # type: ignore[override] return now @classmethod - def today(cls): + def today(cls) -> real_datetime.datetime: # type: ignore[override] return now self.add_patch(patch("dateparser.date.datetime", DateParserDateTime)) self.add_patch(patch("dateparser.parser.datetime", DateParserDateTime)) + self.add_patch(patch("dateparser.utils.datetime", DateParserDateTime)) - def given_parser(self, restrict_to_languages=None, **params): + def given_parser( + self, restrict_to_languages: list[str] | None = None, **params: Any + ) -> None: self.parser = date.DateDataParser(languages=restrict_to_languages, **params) - def given_local_tz_offset(self, offset): + def given_local_tz_offset(self, offset: int) -> None: self.add_patch( patch.object( dateparser.timezone_parser, @@ -909,15 +1181,18 @@ def given_local_tz_offset(self, offset): ) ) - def when_date_string_is_parsed(self, date_string, date_formats=None): + def when_date_string_is_parsed( + self, date_string: str, date_formats: Iterable[str] | None = None + ) -> None: try: self.result = self.parser.get_date_data(date_string, date_formats) except Exception as error: self.error = error - def when_multiple_dates_are_parsed(self, date_strings): + def when_multiple_dates_are_parsed(self, date_strings: Iterable[str]) -> None: self.multiple_results = [] for date_string in date_strings: + result: DateData | Exception try: result = self.parser.get_date_data(date_string) except Exception as error: @@ -925,57 +1200,64 @@ def when_multiple_dates_are_parsed(self, date_strings): finally: self.multiple_results.append(result) - def when_get_date_tuple_is_called(self, date_string): - self.result = self.parser.get_date_tuple(date_string) + def when_get_date_tuple_is_called(self, date_string: str) -> None: + self.date_tuple = self.parser.get_date_tuple(date_string) - def then_date_was_parsed(self): + def then_date_was_parsed(self) -> None: self.assertIsNotNone(self.result["date_obj"]) - def then_date_locale(self): + def then_date_was_not_parsed(self) -> None: + self.assertIsNone(self.result["date_obj"]) + + def then_date_locale(self) -> None: self.assertIsNotNone(self.result["locale"]) - def then_date_is_n_days_ago(self, days): + def then_date_is_n_days_ago(self, days: int) -> None: today = datetime.now().date() expected_date = today - timedelta(days=days) self.assertEqual(expected_date, self.result["date_obj"].date()) - def then_all_results_were_parsed(self): + def then_all_results_were_parsed(self) -> None: self.assertNotIn(None, self.multiple_results) - def then_parsed_dates_are(self, expected_dates): + def then_parsed_dates_are(self, expected_dates: list[real_datetime.date]) -> None: self.assertEqual( expected_dates, - [result["date_obj"].date() for result in self.multiple_results], + [ + result["date_obj"].date() + for result in self.multiple_results + if isinstance(result, DateData) + ], ) - def then_detected_locale(self, locale): + def then_detected_locale(self, locale: str) -> None: self.assertEqual(locale, self.result["locale"]) - def then_period_is(self, day): + def then_period_is(self, day: str) -> None: self.assertEqual(day, self.result["period"]) - def then_parsed_datetime_is(self, expected_datetime): + def then_parsed_datetime_is(self, expected_datetime: datetime) -> None: self.assertEqual(expected_datetime, self.result["date_obj"]) - def then_parsed_date_is(self, expected_date): + def then_parsed_date_is(self, expected_date: real_datetime.date) -> None: self.assertEqual(expected_date, self.result["date_obj"].date()) - def then_parsed_date_has_timezone(self): + def then_parsed_date_has_timezone(self) -> None: self.assertTrue(hasattr(self.result["date_obj"], "tzinfo")) - def then_returned_tuple_is(self, expected_tuple): - self.assertEqual(expected_tuple, self.result) + def then_returned_tuple_is(self, expected_tuple: tuple[datetime, str, str]) -> None: + self.assertEqual(expected_tuple, self.date_tuple) - def then_previous_locales_is(self, expected_list): + def then_previous_locales_is(self, expected_list: list[str]) -> None: self.assertEqual( expected_list, [locale.shortname for locale in self.parser.previous_locales] ) class TestParserInitialization(BaseTestCase): - def setUp(self): + def setUp(self) -> None: super().setUp() - self.parser = NotImplemented + self.parser: date.DateDataParser = NotImplemented @parameterized.expand( [ @@ -983,11 +1265,13 @@ def setUp(self): param(languages={"languages": ["en", "he", "it"]}), ] ) - def test_error_raised_for_invalid_languages_argument(self, languages): - self.when_parser_is_initialized(languages=languages) + def test_error_raised_for_invalid_languages_argument( + self, languages: object + ) -> None: + self.when_parser_is_initialized(languages=languages) # type: ignore[arg-type] self.then_error_was_raised( TypeError, - ["languages argument must be a list (%r given)" % type(languages)], + [f"languages argument must be a list ({type(languages)!r} given)"], ) @parameterized.expand( @@ -996,10 +1280,10 @@ def test_error_raised_for_invalid_languages_argument(self, languages): param(locales={"locales": ["zh-Hant-HK", "ha-NE", "se-SE"]}), ] ) - def test_error_raised_for_invalid_locales_argument(self, locales): - self.when_parser_is_initialized(locales=locales) + def test_error_raised_for_invalid_locales_argument(self, locales: object) -> None: + self.when_parser_is_initialized(locales=locales) # type: ignore[arg-type] self.then_error_was_raised( - TypeError, ["locales argument must be a list (%r given)" % type(locales)] + TypeError, [f"locales argument must be a list ({type(locales)!r} given)"] ) @parameterized.expand( @@ -1008,10 +1292,10 @@ def test_error_raised_for_invalid_locales_argument(self, locales): param(region=150), ] ) - def test_error_raised_for_invalid_region_argument(self, region): - self.when_parser_is_initialized(region=region) + def test_error_raised_for_invalid_region_argument(self, region: object) -> None: + self.when_parser_is_initialized(region=region) # type: ignore[arg-type] self.then_error_was_raised( - TypeError, ["region argument must be str (%r given)" % type(region)] + TypeError, [f"region argument must be str ({type(region)!r} given)"] ) @parameterized.expand( @@ -1023,14 +1307,13 @@ def test_error_raised_for_invalid_region_argument(self, region): ] ) def test_error_raised_for_invalid_try_previous_locales_argument( - self, try_previous_locales - ): - self.when_parser_is_initialized(try_previous_locales=try_previous_locales) + self, try_previous_locales: object + ) -> None: + self.when_parser_is_initialized(try_previous_locales=try_previous_locales) # type: ignore[arg-type] self.then_error_was_raised( TypeError, [ - "try_previous_locales argument must be a boolean (%r given)" - % type(try_previous_locales) + f"try_previous_locales argument must be a boolean ({type(try_previous_locales)!r} given)" ], ) @@ -1042,38 +1325,40 @@ def test_error_raised_for_invalid_try_previous_locales_argument( param(use_given_order=1), ] ) - def test_error_raised_for_invalid_use_given_order_argument(self, use_given_order): + def test_error_raised_for_invalid_use_given_order_argument( + self, use_given_order: object + ) -> None: self.when_parser_is_initialized( - locales=["en", "es"], use_given_order=use_given_order + locales=["en", "es"], + use_given_order=use_given_order, # type: ignore[arg-type] ) self.then_error_was_raised( TypeError, [ - "use_given_order argument must be a boolean (%r given)" - % type(use_given_order) + f"use_given_order argument must be a boolean ({type(use_given_order)!r} given)" ], ) def test_error_is_raised_when_use_given_order_is_True_and_locales_and_languages_is_None( self, - ): + ) -> None: self.when_parser_is_initialized(use_given_order=True) self.then_error_was_raised( ValueError, ["locales or languages must be given if use_given_order is True"], ) - def test_no_error_for_order_with_languages_without_locales(self): + def test_no_error_for_order_with_languages_without_locales(self) -> None: self.when_parser_is_initialized(languages=["en", "fr"], use_given_order=True) def when_parser_is_initialized( self, - languages=None, - locales=None, - region=None, - try_previous_locales=True, - use_given_order=False, - ): + languages: Iterable[str] | None = None, + locales: Iterable[str] | None = None, + region: str | None = None, + try_previous_locales: bool = True, + use_given_order: bool = False, + ) -> None: try: self.parser = date.DateDataParser( languages=languages, @@ -1087,20 +1372,36 @@ def when_parser_is_initialized( class TestSanitizeDate(BaseTestCase): - def test_remove_year_in_russian(self): + def test_remove_year_in_russian(self) -> None: self.assertEqual(date.sanitize_date("2005г."), "2005") self.assertEqual(date.sanitize_date("2005г. 20:37"), "2005 20:37") self.assertEqual(date.sanitize_date("2005 г."), "2005") self.assertEqual(date.sanitize_date("2005 г. 15:24"), "2005 15:24") self.assertEqual(date.sanitize_date("Авг."), "Авг") - def test_sanitize_date_colons(self): + def test_sanitize_date_roman_numeral_years(self) -> None: + self.assertEqual(date.sanitize_date("Anno MDCCXVII."), "Anno 1717") + for date_string in ("MD", "MIXED", "mdccxvii", "MDCLXXXIIX", "CMXCIX"): + self.assertEqual(date.sanitize_date(date_string), date_string) + + def test_sanitize_date_decimal_comma(self) -> None: + self.assertEqual(date.sanitize_date("06:38:49,946"), "06:38:49.946") + self.assertEqual(date.sanitize_date("06:38:49,12 June"), "06:38:49,12 June") + + def test_sanitize_date_colons(self) -> None: self.assertEqual(date.sanitize_date("2019:"), "2019") self.assertEqual(date.sanitize_date("31/07/2019:"), "31/07/2019") + def test_sanitize_date_dash_look_alikes(self) -> None: + for dash in date.DASH_LOOK_ALIKE_CHARS: + self.assertEqual( + date.sanitize_date(f"UTC{dash}06:00"), + "UTC-06:00", + ) + class TestDateLocaleParser(BaseTestCase): - def setUp(self): + def setUp(self) -> None: super().setUp() @parameterized.expand( @@ -1120,13 +1421,13 @@ def setUp(self): ), # wrong format (list) param(date_data=DateData(date_obj=None, period="day")), # date_obj is None param( - date_data=DateData(date_obj="29/05/1994", period="day") + date_data=DateData(date_obj="29/05/1994", period="day") # type: ignore[arg-type] ), # wrong date_obj format ] ) - def test_is_valid_date_data(self, date_data): + def test_is_valid_date_data(self, date_data: object) -> None: self.given_parser( - language=["en"], + language=["en"], # type: ignore[arg-type] date_string="10 jan 2000", date_formats=None, settings=Settings(), @@ -1134,25 +1435,31 @@ def test_is_valid_date_data(self, date_data): self.when_date_object_is_validated(date_data) self.then_date_object_is_invalid() - def given_parser(self, language, date_string, date_formats, settings): + def given_parser( + self, + language: Locale, + date_string: str, + date_formats: Iterable[str] | None, + settings: Settings, + ) -> None: self.parser = date._DateLocaleParser( language, date_string, date_formats, settings ) - def when_date_object_is_validated(self, date_data): + def when_date_object_is_validated(self, date_data: object) -> None: self.is_valid_date_obj = self.parser._is_valid_date_data(date_data) - def then_date_object_is_invalid(self): + def then_date_object_is_invalid(self) -> None: self.assertFalse(self.is_valid_date_obj) class TestTimestampParser(BaseTestCase): - def given_parser(self, **params): + def given_parser(self, **params: Any) -> None: self.parser = date.DateDataParser(**params) - def given_tzstr(self, tzstr): + def given_tzstr(self, tzstr: str | None) -> None: # Save the existing value - self.old_tzstr = os.environ["TZ"] if "TZ" in os.environ else None + self.old_tzstr: str | None = os.environ.get("TZ", None) # Overwrite the value, or remove it if tzstr is not None: @@ -1163,7 +1470,7 @@ def given_tzstr(self, tzstr): # Call tzset tzset() - def reset_tzstr(self): + def reset_tzstr(self) -> None: # If we never set it with given_tzstr, don't bother resetting it if not hasattr(self, "old_tzstr"): return @@ -1180,7 +1487,7 @@ def reset_tzstr(self): # Restore the old timezone behavior tzset() - def test_timestamp_in_milliseconds(self): + def test_timestamp_in_milliseconds(self) -> None: self.assertEqual( date.get_date_from_timestamp("1570308760263", None), datetime.fromtimestamp(1570308760).replace(microsecond=263000), @@ -1195,9 +1502,9 @@ def test_timestamp_in_milliseconds(self): ) ) def test_timestamp_with_different_timestr( - self, timestamp, timezone, to_timezone, tzstr - ): - settings = { + self, timestamp: str, timezone: str, to_timezone: str | None, tzstr: str | None + ) -> None: + settings: dict[str, object] = { "RETURN_AS_TIMEZONE_AWARE": True, "TIMEZONE": timezone, } @@ -1217,7 +1524,7 @@ def test_timestamp_with_different_timestr( self.reset_tzstr() - def test_timestamp_in_microseconds(self): + def test_timestamp_in_microseconds(self) -> None: self.assertEqual( date.get_date_from_timestamp("1570308760263111", None), datetime.fromtimestamp(1570308760).replace(microsecond=263111), @@ -1239,7 +1546,9 @@ def test_timestamp_in_microseconds(self): ), ] ) - def test_timestamp_with_negative(self, input_timestamp, negative, result): + def test_timestamp_with_negative( + self, input_timestamp: str, negative: bool, result: datetime | None + ) -> None: self.assertEqual( date.get_date_from_timestamp(input_timestamp, None, negative=negative), result, @@ -1259,9 +1568,46 @@ def test_timestamp_with_negative(self, input_timestamp, negative, result): param(date_string="1570308760263111222"), ] ) - def test_timestamp_with_wrong_length(self, date_string): + def test_timestamp_with_wrong_length(self, date_string: str) -> None: self.assertEqual(date.get_date_from_timestamp(date_string, None), None) +YMD = ("year", "month", "day") + + +@pytest.mark.parametrize( + ("date_string", "date_formats", "settings", "expected"), + [ + ("2017", None, None, ("year",)), + ("January 2017", None, None, ("year", "month")), + ("22 May", None, None, ("month", "day")), + ("22 May 2017", None, None, YMD), + ("22 May 2017 10:30", None, None, (*YMD, "time")), + ("May 2017 4pm", None, None, ("year", "month", "time")), + ("Monday", None, None, YMD), + ("4pm", None, None, (*YMD, "time")), + ("22/05", ["%d/%m"], None, ("month", "day")), + ("22/05 10:30", ["%d/%m %H:%M"], None, ("month", "day", "time")), + ("20170522", None, {"DATE_ORDER": "YMD", "PARSERS": ["no-spaces-time"]}, YMD), + ("1439251200", None, None, (*YMD, "time")), + ("2 years ago", None, None, ("year",)), + ("3 months ago", None, None, ("year", "month")), + ("yesterday", None, None, YMD), + ("tomorrow 4pm", None, None, (*YMD, "time")), + ("the 1st of last month", None, None, YMD), + ("2 hours ago", None, None, (*YMD, "time")), + ("foo", None, None, ()), + ], +) +def test_parts( + date_string: str, + date_formats: list[str] | None, + settings: dict[str, Any] | None, + expected: tuple[str, ...], +) -> None: + parser = date.DateDataParser(languages=["en"], settings=settings) + assert parser.get_date_data(date_string, date_formats).parts == expected + + if __name__ == "__main__": unittest.main() diff --git a/tests/test_date_data.py b/tests/test_date_data.py index f96d670d2..21f055e04 100644 --- a/tests/test_date_data.py +++ b/tests/test_date_data.py @@ -6,21 +6,19 @@ class TestDateData: - def test_get_item_like_dict(self): + def test_get_item_like_dict(self) -> None: date = datetime(year=5432, month=3, day=1) dd = DateData(date_obj=date, period="day", locale="de") assert dd["date_obj"] == date assert dd["period"] == "day" assert dd["locale"] == "de" - def test_get_item_like_dict_keyerror(self): + def test_get_item_like_dict_keyerror(self) -> None: dd = DateData(date_obj=None, period="day", locale="de") - with pytest.raises(KeyError) as e: - date_obj = dd["date"] - assert e == "date" - assert not date_obj + with pytest.raises(KeyError, match="date"): + dd["date"] - def test_set_item_like_dict(self): + def test_set_item_like_dict(self) -> None: dd = DateData() assert dd.date_obj is None @@ -28,26 +26,25 @@ def test_set_item_like_dict(self): dd["date_obj"] = date assert dd.date_obj == date - def test_set_item_like_dict_keyerror(self): + def test_set_item_like_dict_keyerror(self) -> None: dd = DateData() - with pytest.raises(KeyError) as e: + with pytest.raises(KeyError, match="date"): dd["date"] = datetime(year=5432, month=3, day=1) - assert e == "date" @pytest.mark.parametrize( - "date,period,locale,expected", + ("date", "period", "locale", "expected"), [ ( datetime(year=2020, month=10, day=28), "day", "en", - "DateData(date_obj=datetime.datetime(2020, 10, 28, 0, 0), period='day', locale='en')", + "DateData(date_obj=datetime.datetime(2020, 10, 28, 0, 0), period='day', locale='en', parts=())", ), ( datetime(year=2014, month=5, day=29, hour=3, minute=2), "day", "es", - "DateData(date_obj=datetime.datetime(2014, 5, 29, 3, 2), period='day', locale='es')", + "DateData(date_obj=datetime.datetime(2014, 5, 29, 3, 2), period='day', locale='es', parts=())", ), ( datetime( @@ -61,24 +58,36 @@ def test_set_item_like_dict_keyerror(self): ), "time", "fr", - "DateData(date_obj=datetime.datetime(2028, 7, 31, 3, 2, 12, 601265), period='time', locale='fr')", + "DateData(date_obj=datetime.datetime(2028, 7, 31, 3, 2, 12, 601265), period='time', locale='fr', parts=())", ), ( datetime(year=1994, month=8, day=1), "month", "ca", - "DateData(date_obj=datetime.datetime(1994, 8, 1, 0, 0), period='month', locale='ca')", + "DateData(date_obj=datetime.datetime(1994, 8, 1, 0, 0), period='month', locale='ca', parts=())", ), ( datetime(year=2033, month=10, day=12), "month", None, - "DateData(date_obj=datetime.datetime(2033, 10, 12, 0, 0), period='month', locale=None)", + "DateData(date_obj=datetime.datetime(2033, 10, 12, 0, 0), period='month', locale=None, parts=())", + ), + ( + None, + "day", + None, + "DateData(date_obj=None, period='day', locale=None, parts=())", + ), + ( + None, + "year", + "fr", + "DateData(date_obj=None, period='year', locale='fr', parts=())", ), - (None, "day", None, "DateData(date_obj=None, period='day', locale=None)"), - (None, "year", "fr", "DateData(date_obj=None, period='year', locale='fr')"), ], ) - def test_repr(self, date, period, locale, expected): + def test_repr( + self, date: datetime | None, period: str, locale: str | None, expected: str + ) -> None: dd = DateData(date_obj=date, period=period, locale=locale) assert dd.__repr__() == expected diff --git a/tests/test_date_parser.py b/tests/test_date_parser.py index 654d37777..496fffc82 100644 --- a/tests/test_date_parser.py +++ b/tests/test_date_parser.py @@ -1,13 +1,16 @@ import unittest -from datetime import datetime, timedelta +from collections.abc import Callable +from datetime import datetime, timedelta, timezone, tzinfo from functools import wraps +from typing import Any from unittest.mock import Mock, patch from parameterized import param, parameterized import dateparser.timezone_parser -from dateparser.date import DateDataParser, date_parser -from dateparser.date_parser import DateParser +from dateparser import parse +from dateparser.date import DateData, DateDataParser +from dateparser.date_parser import DateParser, date_parser from dateparser.parser import _parse_absolute from dateparser.timezone_parser import StaticTzInfo from dateparser.utils import normalize_unicode @@ -15,12 +18,12 @@ class TestDateParser(BaseTestCase): - def setUp(self): + def setUp(self) -> None: super().setUp() - self.parser = NotImplemented - self.result = NotImplemented - self.date_parser = NotImplemented - self.date_result = NotImplemented + self.parser: DateDataParser = NotImplemented + self.result: DateData = NotImplemented + self.date_parser: Mock = NotImplemented + self.date_result: tuple[datetime, str | None, tuple[str, ...]] = NotImplemented @parameterized.expand( [ @@ -28,6 +31,7 @@ def setUp(self): param("[Sept] 04, 2014.", datetime(2014, 9, 4)), param("Tuesday Jul 22, 2014", datetime(2014, 7, 22)), param("Tues 9th Aug, 2015", datetime(2015, 8, 9)), + param("the 1st day of March 2015", datetime(2015, 3, 1)), param("10:04am", datetime(2012, 11, 13, 10, 4)), param("Friday", datetime(2012, 11, 9)), param("November 19, 2014 at noon", datetime(2014, 11, 19, 12, 0)), @@ -57,6 +61,7 @@ def setUp(self): param( "Wednesday, 22nd June, 2016, 12.16 pm.", datetime(2016, 6, 22, 12, 16) ), + param("2020/10/9 PM 2:26", datetime(2020, 10, 9, 14, 26)), # French dates param("11 Mai 2014", datetime(2014, 5, 11)), param("11 sept. 2014", datetime(2014, 9, 11)), @@ -149,7 +154,7 @@ def setUp(self): param("Thứ sáu", datetime(2012, 11, 9)), # Friday param( "Tháng Mười Hai 29, 2013, 14:14", datetime(2013, 12, 29, 14, 14) - ), # bpsosrcs.wordpress.com # NOQA + ), # bpsosrcs.wordpress.com param("05 Tháng một 2015 - 03:54 AM", datetime(2015, 1, 5, 3, 54)), # Belarusian dates param("11 траўня", datetime(2012, 5, 11)), @@ -175,6 +180,7 @@ def setUp(self): # Japanese dates param("2016年3月20日(日) 21時40分", datetime(2016, 3, 20, 21, 40)), param("2016年3月20日 21時40分", datetime(2016, 3, 20, 21, 40)), + param("2016 年 3 月 20 日 21 時 40 分", datetime(2016, 3, 20, 21, 40)), # Numeric dates param("06-17-2014", datetime(2014, 6, 17)), param("13/03/2014", datetime(2014, 3, 13)), @@ -190,7 +196,13 @@ def setUp(self): param("2016年6月2911:30", datetime(2016, 6, 29, 11, 30)), param("2016年6月29", datetime(2016, 6, 29, 0, 0)), param("2016年 2月 5日", datetime(2016, 2, 5, 0, 0)), + param("2019 年 10 月 30 日", datetime(2019, 10, 30, 0, 0)), + param("2016 年 6 月 30 日 9 时 30 分", datetime(2016, 6, 30, 9, 30)), param("2016年9月14日晚8:00", datetime(2016, 9, 14, 20, 0)), + param("2020/10/9 下午 02:26:26", datetime(2020, 10, 9, 14, 26, 26)), + param("2020/10/9 上午 02:26:26", datetime(2020, 10, 9, 2, 26, 26)), + # Korean dates + param("2020/10/9 오후 2:26", datetime(2020, 10, 9, 14, 26)), # Bulgarian param("25 ян 2016", datetime(2016, 1, 25, 0, 0)), param("23 декември 2013 15:10:01", datetime(2013, 12, 23, 15, 10, 1)), @@ -214,6 +226,11 @@ def setUp(self): # Finnish dates param("5.7.2018 5.45 ip.", datetime(2018, 7, 5, 17, 45)), param("5 .7 .2018 5.45 ip.", datetime(2018, 7, 5, 17, 45)), + param("28 maalis klo 9:37", datetime(2012, 3, 28, 9, 37)), + param("28 maalis 9:37", datetime(2012, 3, 28, 9, 37)), + param("15 tammi klo 14:30", datetime(2012, 1, 15, 14, 30)), + param("5 kesä klo 18:00", datetime(2012, 6, 5, 18, 0)), + param("12.5.2020 klo 16:45", datetime(2020, 5, 12, 16, 45)), # Croatian dates param("06. travnja 2021.", datetime(2021, 4, 6, 0, 0)), param("13. svibanj 2022.", datetime(2022, 5, 13, 0, 0)), @@ -225,9 +242,19 @@ def setUp(self): param("28. u studenom 2017.", datetime(2017, 11, 28, 0, 0)), param("13. veljače 1999. u podne", datetime(1999, 2, 13, 12, 0)), param("27. siječnja 1994. u ponoć", datetime(1994, 1, 27, 0, 0)), + # Day ranges + param("June 12-14, 2021", datetime(2021, 6, 12, 0, 0)), + param("Jun 12–14 2021", datetime(2021, 6, 12, 0, 0)), + param("12-14 June 2021", datetime(2021, 6, 12, 0, 0)), + param("12.-14. Juni 2021", datetime(2021, 6, 12, 0, 0)), + param("12.-14.06.2021", datetime(2021, 6, 12, 0, 0)), + param("12-14 июня 2021", datetime(2021, 6, 12, 0, 0)), + param("12-12 июня 2021", datetime(2021, 6, 12, 0, 0)), + param("5-5 juin 2021", datetime(2021, 6, 5, 0, 0)), + param("12 - 14 czerwca 2021", datetime(2021, 6, 12, 0, 0)), ] ) - def test_dates_parsing(self, date_string, expected): + def test_dates_parsing(self, date_string: str, expected: datetime) -> None: self.given_parser( settings={"NORMALIZE": False, "RELATIVE_BASE": datetime(2012, 11, 13)} ) @@ -241,7 +268,9 @@ def test_dates_parsing(self, date_string, expected): param("hr", "02/10/2016 u 17:20", datetime(2016, 10, 2, 17, 20)), ] ) - def test_dates_parsing_with_language(self, language, date_string, expected): + def test_dates_parsing_with_language( + self, language: str, date_string: str, expected: datetime + ) -> None: self.given_parser( languages=[language], settings={ @@ -259,7 +288,9 @@ def test_dates_parsing_with_language(self, language, date_string, expected): param("2016020417:10", datetime(2016, 2, 4, 17, 10)), ] ) - def test_dates_parsing_no_spaces(self, date_string, expected): + def test_dates_parsing_no_spaces( + self, date_string: str, expected: datetime + ) -> None: self.given_parser( settings={ "NORMALIZE": False, @@ -272,7 +303,7 @@ def test_dates_parsing_no_spaces(self, date_string, expected): self.then_period_is("day") self.then_date_obj_exactly_is(expected) - def test_stringified_datetime_should_parse_fine(self): + def test_stringified_datetime_should_parse_fine(self) -> None: expected_date = datetime(2012, 11, 13, 10, 15, 5, 330256) self.given_parser(settings={"RELATIVE_BASE": expected_date}) date_string = str(self.parser.get_date_data("today")["date_obj"]) @@ -386,7 +417,7 @@ def test_stringified_datetime_should_parse_fine(self): param("Thứ sáu", datetime(2012, 11, 9)), # Friday param( "Tháng Mười Hai 29, 2013, 14:14", datetime(2013, 12, 29, 14, 14) - ), # bpsosrcs.wordpress.com # NOQA + ), # bpsosrcs.wordpress.com param("05 Tháng một 2015 - 03:54 AM", datetime(2015, 1, 5, 3, 54)), # Belarusian dates param("11 траўня", datetime(2012, 5, 11)), @@ -439,7 +470,9 @@ def test_stringified_datetime_should_parse_fine(self): param("सन् 1989 11 फ़रवरी 09:43", datetime(1989, 2, 11, 9, 43)), ] ) - def test_dates_parsing_with_normalization(self, date_string, expected): + def test_dates_parsing_with_normalization( + self, date_string: str, expected: datetime + ) -> None: self.given_local_tz_offset(0) self.given_parser( settings={"NORMALIZE": True, "RELATIVE_BASE": datetime(2012, 11, 13)} @@ -457,7 +490,9 @@ def test_dates_parsing_with_normalization(self, date_string, expected): param("08/17/14 17:00 (PDT)", datetime(2014, 8, 18, 0, 0)), ] ) - def test_parsing_with_time_zones_and_converting_to_UTC(self, date_string, expected): + def test_parsing_with_time_zones_and_converting_to_UTC( + self, date_string: str, expected: datetime + ) -> None: self.given_parser(settings={"TO_TIMEZONE": "UTC"}) self.when_date_is_parsed(date_string) self.then_date_was_parsed_by_date_parser() @@ -494,8 +529,8 @@ def test_parsing_with_time_zones_and_converting_to_UTC(self, date_string, expect ] ) def test_dateparser_should_return_tzaware_date_when_tz_info_present_in_date_string( - self, date_string, timezone_str, expected - ): + self, date_string: str, timezone_str: str, expected: datetime + ) -> None: self.given_parser() self.when_date_is_parsed(date_string) self.then_date_was_parsed_by_date_parser() @@ -521,8 +556,8 @@ def test_dateparser_should_return_tzaware_date_when_tz_info_present_in_date_stri ] ) def test_dateparser_should_return_date_in_setting_timezone_if_timezone_info_present_in_datestring_and_in_settings( - self, date_string, setting_timezone, expected - ): + self, date_string: str, setting_timezone: str, expected: datetime + ) -> None: self.given_parser(settings={"TIMEZONE": setting_timezone}) self.when_date_is_parsed(date_string) self.then_date_was_parsed_by_date_parser() @@ -541,9 +576,26 @@ def test_dateparser_should_return_date_in_setting_timezone_if_timezone_info_pres "Fri Sep 23 2016 10:34:51 GMT+0800 (CST)", datetime(2016, 9, 23, 2, 34, 51), ), + # RFC 2822 email dates carry a numeric offset plus a redundant, + # equivalent timezone abbreviation in parentheses. + param( + "Thu, 30 May 2024 10:13:10 -0500 (CDT)", + datetime(2024, 5, 30, 15, 13, 10), + ), + param( + "30 May 2024 10:13:10 -0500 CDT", + datetime(2024, 5, 30, 15, 13, 10), + ), + param( + "Mon, 15 Jan 2024 09:30:00 +0000 (UTC)", + datetime(2024, 1, 15, 9, 30, 0), + ), + param("2019-09-28WIB19:17:34+07:00", datetime(2019, 9, 28, 12, 17, 34)), ] ) - def test_parsing_with_utc_offsets(self, date_string, expected): + def test_parsing_with_utc_offsets( + self, date_string: str, expected: datetime + ) -> None: self.given_parser(settings={"TO_TIMEZONE": "utc"}) self.when_date_is_parsed(date_string) self.then_date_was_parsed_by_date_parser() @@ -551,7 +603,7 @@ def test_parsing_with_utc_offsets(self, date_string, expected): self.then_timezone_parsed_is("UTC") self.then_date_obj_exactly_is(expected) - def test_empty_dates_string_is_not_parsed(self): + def test_empty_dates_string_is_not_parsed(self) -> None: self.when_date_is_parsed_by_date_parser("") self.then_error_was_raised(ValueError, ["Empty string"]) @@ -569,9 +621,13 @@ def test_empty_dates_string_is_not_parsed(self): "Unable to parse: 8", ), param("12/09/18567", "Unable to parse: 18567"), + param("5 06 Mar 2009", "Unable to parse: march"), + param("Mar 5 06 2009", "Too many numbers in date string"), + param("6/4/25 0730", "Too many numbers in date string"), + param("6-4-25 0730", "Too many numbers in date string"), ] ) - def test_dates_not_parsed(self, date_string, message): + def test_dates_not_parsed(self, date_string: str, message: str) -> None: self.when_date_is_parsed_by_date_parser(date_string) self.then_error_was_raised(ValueError, message) @@ -591,7 +647,7 @@ def test_dates_not_parsed(self, date_string, message): param("3/3/94", datetime(1994, 3, 3)), ] ) - def test_preferably_past_dates(self, date_string, expected): + def test_preferably_past_dates(self, date_string: str, expected: datetime) -> None: self.given_parser( settings={ "PREFER_DATES_FROM": "past", @@ -616,7 +672,9 @@ def test_preferably_past_dates(self, date_string, expected): param("3/3/94", datetime(2094, 3, 3)), ] ) - def test_preferably_future_dates(self, date_string, expected): + def test_preferably_future_dates( + self, date_string: str, expected: datetime + ) -> None: self.given_local_tz_offset(0) self.given_parser( settings={ @@ -634,8 +692,8 @@ def test_preferably_future_dates(self, date_string, expected): ] ) def test_preferably_future_dates_relative_last_week_of_month( - self, date_string, expected - ): + self, date_string: str, expected: datetime + ) -> None: self.given_local_tz_offset(0) self.given_parser( settings={ @@ -658,7 +716,9 @@ def test_preferably_future_dates_relative_last_week_of_month( param("14:05", datetime(2015, 2, 15, 14, 5)), ] ) - def test_dates_without_preference(self, date_string, expected): + def test_dates_without_preference( + self, date_string: str, expected: datetime + ) -> None: self.given_local_tz_offset(0) self.given_parser( settings={ @@ -678,8 +738,8 @@ def test_dates_without_preference(self, date_string, expected): ] ) def test_preferably_past_dates_leap_year( - self, date_string, relative_base, expected - ): + self, date_string: str, relative_base: datetime, expected: datetime + ) -> None: self.given_parser( settings={"PREFER_DATES_FROM": "past", "RELATIVE_BASE": relative_base} ) @@ -695,8 +755,8 @@ def test_preferably_past_dates_leap_year( ] ) def test_preferably_future_dates_leap_year( - self, date_string, relative_base, expected - ): + self, date_string: str, relative_base: datetime, expected: datetime + ) -> None: self.given_parser( settings={"PREFER_DATES_FROM": "future", "RELATIVE_BASE": relative_base} ) @@ -713,8 +773,8 @@ def test_preferably_future_dates_leap_year( ] ) def test_dates_without_preference_leap_year( - self, date_string, relative_base, expected - ): + self, date_string: str, relative_base: datetime, expected: datetime + ) -> None: self.given_local_tz_offset(0) self.given_parser( settings={ @@ -761,8 +821,11 @@ def test_dates_without_preference_leap_year( ] ) def test_dates_with_day_missing_preferring_current_day_of_month( - self, date_string, today=None, expected=None - ): + self, + date_string: str, + today: datetime | None = None, + expected: datetime | None = None, + ) -> None: self.given_parser( settings={"PREFER_DAY_OF_MONTH": "current", "RELATIVE_BASE": today} ) @@ -805,8 +868,11 @@ def test_dates_with_day_missing_preferring_current_day_of_month( ] ) def test_dates_with_day_missing_preferring_last_day_of_month( - self, date_string, today=None, expected=None - ): + self, + date_string: str, + today: datetime | None = None, + expected: datetime | None = None, + ) -> None: self.given_parser( settings={"PREFER_DAY_OF_MONTH": "last", "RELATIVE_BASE": today} ) @@ -843,8 +909,11 @@ def test_dates_with_day_missing_preferring_last_day_of_month( ] ) def test_dates_with_day_missing_preferring_first_day_of_month( - self, date_string, today=None, expected=None - ): + self, + date_string: str, + today: datetime | None = None, + expected: datetime | None = None, + ) -> None: self.given_parser( settings={"PREFER_DAY_OF_MONTH": "first", "RELATIVE_BASE": today} ) @@ -860,8 +929,8 @@ def test_dates_with_day_missing_preferring_first_day_of_month( ] ) def test_that_day_preference_does_not_affect_dates_with_explicit_day( - self, prefer_day_of_month=None - ): + self, prefer_day_of_month: str | None = None + ) -> None: self.given_parser( settings={ "PREFER_DAY_OF_MONTH": prefer_day_of_month, @@ -872,7 +941,51 @@ def test_that_day_preference_does_not_affect_dates_with_explicit_day( self.then_date_was_parsed_by_date_parser() self.then_date_obj_exactly_is(datetime(2012, 4, 24)) - def test_date_is_parsed_when_skip_tokens_are_supplied(self): + @parameterized.expand( + [ + param("past", "first", datetime(2025, 4, 1)), + param("past", "current", datetime(2025, 4, 4)), + param("past", "last", datetime(2024, 4, 30)), + param("future", "first", datetime(2026, 4, 1)), + param("future", "current", datetime(2026, 4, 4)), + param("future", "last", datetime(2025, 4, 30)), + ] + ) + def test_day_preference_decides_if_current_month_is_past_or_future( + self, prefer_dates_from: str, prefer_day_of_month: str, expected: datetime + ) -> None: + self.given_parser( + settings={ + "PREFER_DATES_FROM": prefer_dates_from, + "PREFER_DAY_OF_MONTH": prefer_day_of_month, + "RELATIVE_BASE": datetime(2025, 4, 4, 12), + } + ) + self.when_date_is_parsed("April") + self.then_date_was_parsed_by_date_parser() + self.then_date_obj_exactly_is(expected) + + @parameterized.expand( + [ + param("past", datetime(2024, 2, 1), datetime(2023, 2, 28)), + param("future", datetime(2024, 3, 1), datetime(2025, 2, 28)), + ] + ) + def test_last_day_of_february_moved_to_another_year( + self, prefer_dates_from: str, today: datetime, expected: datetime + ) -> None: + self.given_parser( + settings={ + "PREFER_DATES_FROM": prefer_dates_from, + "PREFER_DAY_OF_MONTH": "last", + "RELATIVE_BASE": today, + } + ) + self.when_date_is_parsed("February") + self.then_date_was_parsed_by_date_parser() + self.then_date_obj_exactly_is(expected) + + def test_date_is_parsed_when_skip_tokens_are_supplied(self) -> None: self.given_parser( settings={"SKIP_TOKENS": ["de"], "RELATIVE_BASE": datetime(2015, 2, 12)} ) @@ -890,8 +1003,8 @@ def test_date_is_parsed_when_skip_tokens_are_supplied(self): ] ) def test_error_should_be_raised_for_invalid_dates_with_too_large_day_number( - self, date_string, message - ): + self, date_string: str, message: str + ) -> None: self.when_date_is_parsed_by_date_parser(date_string) self.then_error_was_raised( ValueError, ["day is out of range for month", "must be in range", message] @@ -909,11 +1022,16 @@ def test_error_should_be_raised_for_invalid_dates_with_too_large_day_number( languages=["en"], expected=datetime(2015, 5, 2, 10, 20, 19), ), + param( + "2021-04-29T06:38:49,946902974+02:00", + languages=["fr"], + expected=datetime(2021, 4, 29, 6, 38, 49, 946902), + ), ] ) def test_iso_datestamp_format_should_always_parse( - self, date_string, languages, expected - ): + self, date_string: str, languages: list[str], expected: datetime + ) -> None: self.given_local_tz_offset(0) self.given_parser( languages=languages, settings={"PREFER_LOCALE_DATE_ORDER": False} @@ -923,6 +1041,71 @@ def test_iso_datestamp_format_should_always_parse( self.result["date_obj"] = self.result["date_obj"].replace(tzinfo=None) self.then_date_obj_exactly_is(expected) + @parameterized.expand( + [ + param("2017-06-22", languages=["it"], expected=datetime(2017, 6, 22)), + param("2017-06-10", languages=["it"], expected=datetime(2017, 6, 10)), + param("2017-06-22", languages=["fr"], expected=datetime(2017, 6, 22)), + param( + "2015-05-02T10:20:19+0000", + languages=["fr"], + expected=datetime(2015, 5, 2, 10, 20, 19), + ), + ] + ) + def test_iso_datestamp_format_should_parse_with_locale_date_order( + self, date_string: str, languages: list[str], expected: datetime + ) -> None: + # Regression test for #360: dates starting with a four-digit year + # (e.g. ISO 8601 dates) must parse even when the locale date order + # is not year-first (Italian and French use DMY), without needing + # the PREFER_LOCALE_DATE_ORDER=False workaround. + self.given_local_tz_offset(0) + self.given_parser(languages=languages) + self.when_date_is_parsed(date_string) + self.then_date_was_parsed_by_date_parser() + self.result["date_obj"] = self.result["date_obj"].replace(tzinfo=None) + self.then_date_obj_exactly_is(expected) + + @parameterized.expand( + [ + param("2023-11-08", date_order="DMY", expected=datetime(2023, 11, 8)), + param("1960-12-23", date_order="DMY", expected=datetime(1960, 12, 23)), + param("2023-11-08", date_order="MDY", expected=datetime(2023, 11, 8)), + param("2023-11-08", date_order="YDM", expected=datetime(2023, 8, 11)), + ] + ) + def test_year_first_date_with_explicit_date_order( + self, date_string: str, date_order: str, expected: datetime + ) -> None: + self.given_parser(languages=["en"], settings={"DATE_ORDER": date_order}) + self.when_date_is_parsed(date_string) + self.then_date_was_parsed_by_date_parser() + self.then_date_obj_exactly_is(expected) + + @parameterized.expand( + [ + param("05/2020", date_order="DMY", expected=datetime(2020, 5, 1)), + param("5-2020", date_order="YMD", expected=datetime(2020, 5, 1)), + param( + "05/2020 10:00", date_order="YDM", expected=datetime(2020, 5, 28, 10) + ), + param("13/2020", date_order="DMY", expected=datetime(2020, 9, 13)), + ] + ) + def test_month_and_year_with_explicit_date_order( + self, date_string: str, date_order: str, expected: datetime + ) -> None: + self.given_parser( + settings={ + "DATE_ORDER": date_order, + "PREFER_DAY_OF_MONTH": "first", + "RELATIVE_BASE": datetime(2020, 9, 28), + } + ) + self.when_date_is_parsed(date_string) + self.then_date_obj_exactly_is(expected) + @parameterized.expand( [ # Epoch timestamps. @@ -944,7 +1127,7 @@ def test_iso_datestamp_format_should_always_parse( ), ] ) - def test_parse_timestamp(self, date_string, expected): + def test_parse_timestamp(self, date_string: str, expected: datetime) -> None: self.given_local_tz_offset(0) self.given_parser(settings={"TO_TIMEZONE": "UTC"}) self.when_date_is_parsed(date_string) @@ -958,7 +1141,9 @@ def test_parse_timestamp(self, date_string, expected): param("-1015673450000001", expected=datetime(1937, 10, 25, 12, 29, 10, 1)), ] ) - def test_parse_negative_timestamp(self, date_string, expected): + def test_parse_negative_timestamp( + self, date_string: str, expected: datetime + ) -> None: self.given_local_tz_offset(0) self.given_parser( settings={"TO_TIMEZONE": "UTC", "PARSERS": ["negative-timestamp"]} @@ -988,7 +1173,9 @@ def test_parse_negative_timestamp(self, date_string, expected): ), ] ) - def test_parse_timestamp_with_time_as_period(self, date_string, expected): + def test_parse_timestamp_with_time_as_period( + self, date_string: str, expected: datetime + ) -> None: self.given_local_tz_offset(0) self.given_parser( settings={"TO_TIMEZONE": "UTC", "RETURN_TIME_AS_PERIOD": True} @@ -1016,6 +1203,12 @@ def test_parse_timestamp_with_time_as_period(self, date_string, expected): param("²⁹/⁰⁵/²⁰¹⁵", expected=datetime(2015, 5, 29), period="day"), param("₁₅/₀₂/₂₀₂₀", expected=datetime(2020, 2, 15), period="day"), param("₃₁ December", expected=datetime(2015, 12, 31), period="day"), + # Roman numeral years + param("MCMXCIX", expected=datetime(1999, 2, 15), period="year"), + param("M.DC.LXXIX.", expected=datetime(1679, 2, 15), period="year"), + param( + "April MCCCCLXXVIIII", expected=datetime(1479, 4, 15), period="month" + ), # Russian param("1000 год", expected=datetime(1000, 2, 15), period="year"), param("1001 год", expected=datetime(1001, 2, 15), period="year"), @@ -1029,7 +1222,12 @@ def test_parse_timestamp_with_time_as_period(self, date_string, expected): param("2001год", expected=datetime(2001, 2, 15), period="year"), ] ) - def test_extracted_period(self, date_string, expected=None, period=None): + def test_extracted_period( + self, + date_string: str, + expected: datetime | None = None, + period: str | None = None, + ) -> None: self.given_local_tz_offset(0) self.given_parser(settings={"RELATIVE_BASE": datetime(2015, 2, 15, 15, 30)}) self.when_date_is_parsed(date_string) @@ -1048,8 +1246,11 @@ def test_extracted_period(self, date_string, expected=None, period=None): ] ) def test_period_is_time_if_return_time_as_period_setting_applied_and_time_component_present( - self, date_string, expected=None, period=None - ): + self, + date_string: str, + expected: datetime | None = None, + period: str | None = None, + ) -> None: self.given_parser(settings={"RETURN_TIME_AS_PERIOD": True}) self.when_date_is_parsed(date_string) self.then_date_was_parsed_by_date_parser() @@ -1066,8 +1267,11 @@ def test_period_is_time_if_return_time_as_period_setting_applied_and_time_compon ] ) def test_period_is_time_if_return_time_as_period_and_relative_base_settings_applied_and_time_component_present( - self, date_string, expected=None, period=None - ): + self, + date_string: str, + expected: datetime | None = None, + period: str | None = None, + ) -> None: self.given_parser( settings={ "RETURN_TIME_AS_PERIOD": True, @@ -1088,8 +1292,11 @@ def test_period_is_time_if_return_time_as_period_and_relative_base_settings_appl ] ) def test_period_is_day_if_return_time_as_period_setting_applied_and_time_component_is_not_present( - self, date_string, expected=None, period=None - ): + self, + date_string: str, + expected: datetime | None = None, + period: str | None = None, + ) -> None: self.given_parser(settings={"RETURN_TIME_AS_PERIOD": True}) self.when_date_is_parsed(date_string) self.then_date_was_parsed_by_date_parser() @@ -1103,8 +1310,11 @@ def test_period_is_day_if_return_time_as_period_setting_applied_and_time_compone ] ) def test_period_is_day_if_return_time_as_period_setting_not_applied( - self, date_string, expected=None, period=None - ): + self, + date_string: str, + expected: datetime | None = None, + period: str | None = None, + ) -> None: self.given_parser( settings={ "RETURN_TIME_AS_PERIOD": False, @@ -1146,14 +1356,95 @@ def test_period_is_day_if_return_time_as_period_setting_not_applied( expected=datetime(1856, 5, 23, 0, 9, 8), order="DMY", ), + # A day and month that do not fit the date order are swapped. + param("2021-13-01", expected=datetime(2021, 1, 13), order="YMD"), + param("2021-01-13", expected=datetime(2021, 1, 13), order="YDM"), + param("13/01/2021", expected=datetime(2021, 1, 13), order="MDY"), + param("01/13/2021", expected=datetime(2021, 1, 13), order="DMY"), + param("01/13/21", expected=datetime(2021, 1, 13), order="DMY"), + param("13-2021-01", expected=datetime(2021, 1, 13), order="MYD"), + param("01-2021-13", expected=datetime(2021, 1, 13), order="DYM"), + param("13/01/2021", expected=datetime(2021, 1, 13), order="YDM"), + param("01/13/2021", expected=datetime(2021, 1, 13), order="DYM"), + param("12 13 December", expected=datetime(2013, 12, 12), order="DMY"), ] ) - def test_order(self, date_string, expected=None, order=None): + def test_order( + self, + date_string: str, + expected: datetime | None = None, + order: str | None = None, + ) -> None: self.given_parser(settings={"DATE_ORDER": order}) self.when_date_is_parsed(date_string) self.then_date_was_parsed_by_date_parser() self.then_date_obj_exactly_is(expected) + def test_locale_order_is_not_swapped(self) -> None: + self.given_parser(languages=["fr"]) + self.when_date_is_parsed("01/13/2021") + self.then_date_obj_exactly_is(None) + + def test_order_is_not_swapped_with_a_month_name(self) -> None: + self.given_parser(languages=["en"], settings={"DATE_ORDER": "DMY"}) + self.when_date_is_parsed("12/24, Monday 15 March 2021") + self.then_date_obj_exactly_is(None) + + @parameterized.expand( + [ + # Japanese dates without a year: the day must not be read as + # a two-digit year just because the year comes first (#519). + param( + "4月20日 18:10", + expected=datetime(2019, 4, 20, 18, 10), + languages=["ja"], + ), + param( + "3月8日", + expected=datetime(2019, 3, 8, 0, 0), + languages=["ja"], + ), + # The root cause is locale-independent: any year-first date + # order must not consume the day as a year either. + param( + "4-20 18:10", + expected=datetime(2019, 4, 20, 18, 10), + settings={"DATE_ORDER": "YMD"}, + ), + # A number that cannot be a day is still parsed as a year. + param( + "4-99", + expected=datetime(1999, 4, 27, 0, 0), + settings={"DATE_ORDER": "YMD"}, + ), + # Fully specified dates keep their meaning. + param( + "2020年4月20日 18:10", + expected=datetime(2020, 4, 20, 18, 10), + languages=["ja"], + ), + param( + "19年4月20日", + expected=datetime(2019, 4, 20, 0, 0), + languages=["ja"], + ), + ] + ) + def test_two_digit_day_is_not_confused_with_year( + self, + date_string: str, + expected: datetime | None = None, + languages: list[str] | None = None, + settings: dict[str, Any] | None = None, + ) -> None: + self.given_parser( + languages=languages, + settings={"RELATIVE_BASE": datetime(2019, 6, 27), **(settings or {})}, + ) + self.when_date_is_parsed(date_string) + self.then_date_was_parsed_by_date_parser() + self.then_date_obj_exactly_is(expected) + @parameterized.expand( [ param("201508", expected=datetime(2015, 8, 20, 0, 0), order="DYM"), @@ -1161,7 +1452,12 @@ def test_order(self, date_string, expected=None, order=None): param("201108", expected=datetime(2008, 11, 20, 0, 0), order="DMY"), ] ) - def test_order_no_spaces(self, date_string, expected=None, order=None): + def test_order_no_spaces( + self, + date_string: str, + expected: datetime | None = None, + order: str | None = None, + ) -> None: self.given_parser(settings={"DATE_ORDER": order, "PARSERS": ["no-spaces-time"]}) self.when_date_is_parsed(date_string) self.then_date_was_parsed_by_date_parser() @@ -1196,8 +1492,12 @@ def test_order_no_spaces(self, date_string, expected=None, order=None): ] ) def test_if_settings_provided_date_order_is_retained( - self, date_string, expected=None, languages=None, settings=None - ): + self, + date_string: str, + expected: datetime | None = None, + languages: list[str] | None = None, + settings: dict[str, Any] | None = None, + ) -> None: self.given_parser(languages=languages, settings=settings) self.when_date_is_parsed(date_string) self.then_date_was_parsed_by_date_parser() @@ -1214,8 +1514,8 @@ def test_if_settings_provided_date_order_is_retained( ] ) def test_parsing_strings_containing_only_separator_tokens( - self, date_string, expected - ): + self, date_string: str, expected: None + ) -> None: self.given_parser() self.when_date_is_parsed(date_string) self.then_period_is("day") @@ -1266,8 +1566,8 @@ def test_parsing_strings_containing_only_separator_tokens( ] ) def test_prefer_dates_from_with_timezone( - self, date_string, expected, test_settings - ): + self, date_string: str, expected: datetime, test_settings: dict[str, Any] + ) -> None: self.given_parser( settings={ "TO_TIMEZONE": "etc/utc", @@ -1327,8 +1627,13 @@ def test_prefer_dates_from_with_timezone( ] ) def test_dates_with_no_day_or_month( - self, date_string, prefer_day, prefer_month, today=None, expected=None - ): + self, + date_string: str, + prefer_day: str, + prefer_month: str, + today: datetime | None = None, + expected: datetime | None = None, + ) -> None: self.given_parser( settings={ "PREFER_DAY_OF_MONTH": prefer_day, @@ -1340,7 +1645,130 @@ def test_dates_with_no_day_or_month( self.then_date_was_parsed_by_date_parser() self.then_date_obj_exactly_is(expected) - def given_local_tz_offset(self, offset): + def test_dates_with_no_day_or_month_use_same_current_date_for_month_and_day( + self, + ) -> None: + class UtilsDateTime(datetime): + @classmethod + def now(cls, tz: tzinfo | None = None) -> datetime: # type: ignore[override] + return datetime(2026, 6, 1, 12, 0, tzinfo=tz) + + with ( + patch("dateparser.parser._now", return_value=datetime(2026, 5, 31, 12)), + patch("dateparser.utils.datetime", UtilsDateTime), + ): + self.assertEqual(parse("2014"), datetime(2014, 5, 31)) + + @parameterized.expand( + [ + param("Monday", {}, datetime(2023, 11, 6)), + param("Tuesday", {}, datetime(2023, 10, 31)), + param("Tuesday", {"PREFER_DATES_FROM": "future"}, datetime(2023, 11, 7)), + param("Monday", {"PREFER_DATES_FROM": "past"}, datetime(2023, 10, 30)), + param("November 7", {"PREFER_DATES_FROM": "past"}, datetime(2022, 11, 7)), + param("9pm", {"PREFER_DATES_FROM": "past"}, datetime(2023, 11, 5, 21)), + ] + ) + def test_current_date_is_taken_from_timezone( + self, date_string: str, settings: dict[str, Any], expected: datetime + ) -> None: + class UtilsDateTime(datetime): + @classmethod + def now(cls, tz: tzinfo | None = None) -> datetime: # type: ignore[override] + return datetime(2023, 11, 7, 2, 15, tzinfo=timezone.utc).astimezone(tz) + + with patch("dateparser.utils.datetime", UtilsDateTime): + result = parse( + date_string, + settings={ + "TIMEZONE": "America/Chicago", + "RETURN_AS_TIMEZONE_AWARE": False, + **settings, + }, + ) + self.assertEqual(result, expected) + + @parameterized.expand( + [ + param( + "yesterday +1h", + lambda base: base - timedelta(days=1) + timedelta(hours=1), + "Yesterday plus 1 hour", + ), + param( + "yesterday +2h", + lambda base: base - timedelta(days=1) + timedelta(hours=2), + "Yesterday plus 2 hours", + ), + param( + "yesterday +30m", + lambda base: base - timedelta(days=1) + timedelta(minutes=30), + "Yesterday plus 30 minutes", + ), + param( + "yesterday -1h", + lambda base: base - timedelta(days=1) - timedelta(hours=1), + "Yesterday minus 1 hour", + ), + param( + "yesterday -2h", + lambda base: base - timedelta(days=1) - timedelta(hours=2), + "Yesterday minus 2 hours", + ), + param( + "yesterday -30m", + lambda base: base - timedelta(days=1) - timedelta(minutes=30), + "Yesterday minus 30 minutes", + ), + param( + "tomorrow +1h", + lambda base: base + timedelta(days=1) + timedelta(hours=1), + "Tomorrow plus 1 hour", + ), + param( + "tomorrow +3h", + lambda base: base + timedelta(days=1) + timedelta(hours=3), + "Tomorrow plus 3 hours", + ), + param( + "tomorrow -1h", + lambda base: base + timedelta(days=1) - timedelta(hours=1), + "Tomorrow minus 1 hour", + ), + param( + "tomorrow -2h", + lambda base: base + timedelta(days=1) - timedelta(hours=2), + "Tomorrow minus 2 hours", + ), + ] + ) + def test_relative_date_with_time_offset( + self, + date_string: str, + offset_calculator: Callable[[datetime], datetime], + description: str, + ) -> None: + """Ensure +/- signs in time offsets are parsed correctly.""" + base_date = datetime(2026, 1, 19, 12, 0, 0) + expected = offset_calculator(base_date) + + result = parse( + date_string, + settings={ + "RELATIVE_BASE": base_date, + "RETURN_AS_TIMEZONE_AWARE": False, + }, + ) + + self.assertIsNotNone(result, f"Failed to parse: {description}") + assert result is not None + self.assertEqual( + expected, + result, + f"{description}: Expected {expected}, got {result}", + ) + + def given_local_tz_offset(self, offset: int) -> None: self.add_patch( patch.object( dateparser.timezone_parser, @@ -1349,10 +1777,146 @@ def given_local_tz_offset(self, offset): ) ) - def given_parser(self, *args, **kwds): - def collecting_get_date_data(parse): + def test_yesterday_plus_and_minus_expected_values(self) -> None: + """Verify correct time offset calculations for yesterday.""" + # Base: 2026-01-08 21:38:10 + base_date = datetime(2026, 1, 8, 21, 38, 10) + + plus_result = parse( + "yesterday +1h", + settings={"RELATIVE_BASE": base_date, "RETURN_AS_TIMEZONE_AWARE": False}, + ) + minus_result = parse( + "yesterday -1h", + settings={"RELATIVE_BASE": base_date, "RETURN_AS_TIMEZONE_AWARE": False}, + ) + + # Expected: 2026-01-07 22:38:10 (yesterday at same time, plus 1 hour) + expected_plus = datetime(2026, 1, 7, 22, 38, 10) + # Expected: 2026-01-07 20:38:10 (yesterday at same time, minus 1 hour) + expected_minus = datetime(2026, 1, 7, 20, 38, 10) + + self.assertEqual( + expected_plus, + plus_result, + f"'yesterday +1h' should be {expected_plus}, got {plus_result}", + ) + self.assertEqual( + expected_minus, + minus_result, + f"'yesterday -1h' should be {expected_minus}, got {minus_result}", + ) + + @parameterized.expand( + [ + # USE_GIVEN_LANGUAGE_ORDER=True preserves the given order of `languages`. + param( + "11/12/2020", + expected=datetime(2020, 12, 11, 0, 0), + languages=["es", "en"], + settings={"USE_GIVEN_LANGUAGE_ORDER": True}, + ), + param( + "11/12/2020", + expected=datetime(2020, 11, 12, 0, 0), + languages=["en", "es"], + settings={"USE_GIVEN_LANGUAGE_ORDER": True}, + ), + # ... and the given order of `locales`. + param( + "11/12/2020", + expected=datetime(2020, 12, 11, 0, 0), + locales=["es", "en"], + settings={"USE_GIVEN_LANGUAGE_ORDER": True}, + ), + param( + "11/12/2020", + expected=datetime(2020, 11, 12, 0, 0), + locales=["en", "es"], + settings={"USE_GIVEN_LANGUAGE_ORDER": True}, + ), + # Default (False): the most-common-language order is used, regardless + # of the order in which languages/locales are given. + param( + "11/12/2020", + expected=datetime(2020, 11, 12, 0, 0), + languages=["es", "en"], + settings={"USE_GIVEN_LANGUAGE_ORDER": False}, + ), + param( + "11/12/2020", + expected=datetime(2020, 11, 12, 0, 0), + locales=["es", "en"], + settings={"USE_GIVEN_LANGUAGE_ORDER": False}, + ), + # No-op (no error) when no languages/locales are given: there is + # nothing to reorder, so the default order is used. + param( + "11/12/2020", + expected=datetime(2020, 11, 12, 0, 0), + languages=[], + settings={"USE_GIVEN_LANGUAGE_ORDER": True}, + ), + param( + "11/12/2020", + expected=datetime(2020, 11, 12, 0, 0), + languages=None, + settings={"USE_GIVEN_LANGUAGE_ORDER": True}, + ), + ] + ) + def test_use_given_language_order_setting( + self, + date_string: str, + expected: datetime | None = None, + languages: list[str] | None = None, + locales: list[str] | None = None, + settings: dict[str, Any] | None = None, + ) -> None: + self.given_parser(languages=languages, locales=locales, settings=settings) + self.when_date_is_parsed(date_string) + self.then_date_was_parsed_by_date_parser() + self.then_date_obj_exactly_is(expected) + + def test_use_given_order_parameter_still_preserves_order_without_setting( + self, + ) -> None: + # The pre-existing ``use_given_order`` constructor argument must keep working + # on its own (the new setting is OR-ed with it, not a replacement). + self.given_parser(languages=["es", "en"], use_given_order=True) + self.when_date_is_parsed("11/12/2020") + self.then_date_was_parsed_by_date_parser() + self.then_date_obj_exactly_is(datetime(2020, 12, 11, 0, 0)) + + def test_use_given_language_order_setting_fixes_top_level_parse(self) -> None: + # Regression test for https://github.com/scrapinghub/dateparser/issues/770 + # The top-level ``parse`` must honour the given language order through the + # ``USE_GIVEN_LANGUAGE_ORDER`` setting. + self.assertEqual( + datetime(2020, 12, 11, 0, 0), + parse( + "11/12/2020", + languages=["es", "en"], + settings={"USE_GIVEN_LANGUAGE_ORDER": True}, + ), + ) + self.assertEqual( + datetime(2020, 11, 12, 0, 0), + parse( + "11/12/2020", + languages=["en", "es"], + settings={"USE_GIVEN_LANGUAGE_ORDER": True}, + ), + ) + + def given_parser(self, *args: Any, **kwds: Any) -> None: + def collecting_get_date_data( + parse: Callable[..., tuple[datetime, str | None, tuple[str, ...]]], + ) -> Callable[..., tuple[datetime, str | None, tuple[str, ...]]]: @wraps(parse) - def wrapped(*args, **kwargs): + def wrapped( + *args: Any, **kwargs: Any + ) -> tuple[datetime, str | None, tuple[str, ...]]: self.date_result = parse(*args, **kwargs) return self.date_result @@ -1368,29 +1932,623 @@ def wrapped(*args, **kwargs): self.add_patch(patch("dateparser.date.date_parser", new=self.date_parser)) self.parser = DateDataParser(*args, **kwds) - def when_date_is_parsed(self, date_string): + def when_date_is_parsed(self, date_string: str) -> None: self.result = self.parser.get_date_data(date_string) - def when_date_is_parsed_by_date_parser(self, date_string): + def when_date_is_parsed_by_date_parser(self, date_string: str) -> None: try: - self.result = DateParser().parse(date_string, parse_method=_parse_absolute) + DateParser().parse(date_string, parse_method=_parse_absolute) except Exception as error: self.error = error - def then_period_is(self, period): + def then_period_is(self, period: str | None) -> None: self.assertEqual(period, self.result["period"]) - def then_date_obj_exactly_is(self, expected): + def then_date_obj_exactly_is(self, expected: datetime | None) -> None: self.assertEqual(expected, self.result["date_obj"]) - def then_date_was_parsed_by_date_parser(self): + def then_date_was_parsed_by_date_parser(self) -> None: self.assertNotEqual(NotImplemented, self.date_result, "Date was not parsed") self.assertEqual(self.result["date_obj"], self.date_result[0]) - def then_timezone_parsed_is(self, tzstr): + def then_timezone_parsed_is(self, tzstr: str) -> None: self.assertTrue(tzstr in repr(self.result["date_obj"].tzinfo)) self.result["date_obj"] = self.result["date_obj"].replace(tzinfo=None) + @parameterized.expand( + [ + # Test word numbers with "later" + param("two days later", timedelta(days=2), "two days later"), + param("three weeks later", timedelta(weeks=3), "three weeks later"), + param("five hours later", timedelta(hours=5), "five hours later"), + param("ten minutes later", timedelta(minutes=10), "ten minutes later"), + param("seven seconds later", timedelta(seconds=7), "seven seconds later"), + param("twelve days later", timedelta(days=12), "twelve days later"), + # Test numeric values still work + param("2 days later", timedelta(days=2), "2 days later"), + param("5 hours later", timedelta(hours=5), "5 hours later"), + # Test other word numbers with "later" + param("one day later", timedelta(days=1), "one day later"), + param( + "four months later", timedelta(days=122), "four months later (approx)" + ), + param("six years later", timedelta(days=2191), "six years later (approx)"), + # Test pluralization with "later" + param("one days later", timedelta(days=1), "one days later (with plural)"), + param("two day later", timedelta(days=2), "two day later (without plural)"), + ] + ) + def test_word_numbers_with_later( + self, date_string: str, expected_delta: timedelta, description: str + ) -> None: + """Test that word numbers (one, two, three, etc.) work with 'later' pattern.""" + base_date = datetime(2025, 6, 15, 12, 0, 0) + expected = base_date + expected_delta + + result = parse( + date_string, + settings={ + "RELATIVE_BASE": base_date, + "RETURN_AS_TIMEZONE_AWARE": False, + }, + ) + + self.assertIsNotNone(result, f"Failed to parse: {description}") + assert result is not None + if "approx" in description: + # For approximate cases, ensure the result is after the base date + # and not later than the expected upper bound. + self.assertGreater(result, base_date, f"{description}: should be in future") + self.assertLessEqual( + result, + expected, + f"{description}: Expected at most {expected}, got {result}", + ) + else: + self.assertEqual( + expected, + result, + f"{description}: Expected {expected}, got {result}", + ) + + @parameterized.expand( + [ + # Test word numbers with "from now" + param("two days from now", timedelta(days=2), "two days from now"), + param("five hours from now", timedelta(hours=5), "five hours from now"), + param( + "ten minutes from now", timedelta(minutes=10), "ten minutes from now" + ), + # Still works with digits + param("2 days from now", timedelta(days=2), "2 days from now"), + param("5 hours from now", timedelta(hours=5), "5 hours from now"), + ] + ) + def test_word_numbers_advanced( + self, date_string: str, expected_delta: timedelta, description: str + ) -> None: + """Test number parsing with word numbers (1-12) in 'from now' phrases.""" + base_date = datetime(2025, 6, 15, 12, 0, 0) + expected = base_date + expected_delta + + result = parse( + date_string, + settings={ + "RELATIVE_BASE": base_date, + "RETURN_AS_TIMEZONE_AWARE": False, + }, + ) + + self.assertIsNotNone(result, f"Failed to parse: {description}") + assert result is not None + self.assertEqual( + expected, + result, + f"{description}: Expected {expected}, got {result}", + ) + + @parameterized.expand( + [ + # Test PREFER_DATES_FROM='past' with 2-digit year format (Issue #445) + param( + date_string="1/15/64", + date_format="%m/%d/%y", + prefer_from="past", + expected_year=1964, + description="PREFER_DATES_FROM='past' with 2-digit year", + ), + # Test PREFER_DATES_FROM='future' with 2-digit year format + param( + date_string="1/15/64", + date_format="%m/%d/%y", + prefer_from="future", + expected_year=2064, + description="PREFER_DATES_FROM='future' with 2-digit year", + ), + # Test with past date and prefer future + param( + date_string="1/15/24", + date_format="%m/%d/%y", + prefer_from="future", + expected_year=2124, + description="Past date (24) with PREFER_DATES_FROM='future'", + ), + # Test with future date and prefer past + param( + date_string="1/15/35", + date_format="%m/%d/%y", + prefer_from="past", + expected_year=1935, + description="Future date (35) with PREFER_DATES_FROM='past'", + ), + # Test 4-digit year format (should not apply PREFER_DATES_FROM adjustment) + param( + date_string="1/15/2050", + date_format="%m/%d/%Y", + prefer_from="past", + expected_year=2050, + description="4-digit year format ignores PREFER_DATES_FROM", + ), + ] + ) + def test_prefer_dates_from_with_date_formats( + self, + date_string: str, + date_format: str, + prefer_from: str, + expected_year: int, + description: str, + ) -> None: + """Test that PREFER_DATES_FROM setting works with date_formats parameter (Issue #445).""" + result = parse( + date_string, + date_formats=[date_format], + settings={ + "PREFER_DATES_FROM": prefer_from, + "RELATIVE_BASE": datetime(2026, 1, 1), + }, + ) + + self.assertIsNotNone(result, f"Failed to parse: {description}") + assert result is not None + self.assertEqual( + expected_year, + result.year, + f"{description}: Expected year {expected_year}, got {result.year}", + ) + + def test_prefer_dates_from_with_date_formats_and_relative_base(self) -> None: + """Test that PREFER_DATES_FROM respects RELATIVE_BASE with date_formats.""" + # Use a relative base in the past (e.g., 1980-01-01) + # When parsing '1/15/64' with RELATIVE_BASE='1980-01-01' and PREFER_DATES_FROM='past', + # it should be interpreted as 1964 (past relative to 1980) + relative_base = datetime(1980, 1, 1) + result = parse( + "1/15/64", + date_formats=["%m/%d/%y"], + settings={ + "PREFER_DATES_FROM": "past", + "RELATIVE_BASE": relative_base, + }, + ) + + self.assertIsNotNone(result) + assert result is not None + self.assertEqual( + 1964, + result.year, + f"RELATIVE_BASE not respected: Expected 1964, got {result.year}", + ) + + # Now test with a relative base in the future + # When parsing '1/15/64' with RELATIVE_BASE='2020-01-01' and PREFER_DATES_FROM='future', + # it should be interpreted as 2064 (future relative to 2020) + relative_base = datetime(2020, 1, 1) + result = parse( + "1/15/64", + date_formats=["%m/%d/%y"], + settings={ + "PREFER_DATES_FROM": "future", + "RELATIVE_BASE": relative_base, + }, + ) + + self.assertIsNotNone(result) + assert result is not None + self.assertEqual( + 2064, + result.year, + f"RELATIVE_BASE not respected: Expected 2064, got {result.year}", + ) + + def test_prefer_dates_from_with_date_formats_tz_aware_relative_base(self) -> None: + """Test that a tz-aware RELATIVE_BASE does not crash (Bug #1 fix).""" + result = parse( + "1/15/64", + date_formats=["%m/%d/%y"], + settings={ + "PREFER_DATES_FROM": "past", + "RELATIVE_BASE": datetime(1980, 1, 1, tzinfo=timezone.utc), + }, + ) + self.assertIsNotNone(result) + assert result is not None + self.assertEqual(1964, result.year) + + def test_prefer_dates_from_with_date_formats_feb29_non_leap(self) -> None: + """Test that Feb 29 shifted to a non-leap year finds the next valid leap year (Bug #2 fix).""" + # 2/29/00 parses as 2000-02-29; shifting +100 → 2100 which is not a leap year. + # _apply_century_preference finds the next valid leap year: 2104. + result = parse( + "2/29/00", + date_formats=["%m/%d/%y"], + settings={ + "PREFER_DATES_FROM": "future", + "RELATIVE_BASE": datetime(2026, 1, 1), + }, + ) + self.assertIsNotNone(result) + assert result is not None + self.assertEqual(2104, result.year) + self.assertEqual(2, result.month) + self.assertEqual(29, result.day) + + @parameterized.expand( + [ + param(date_string="1999001", expected=datetime(1999, 1, 1)), + param(date_string="1999050", expected=datetime(1999, 2, 19)), + param(date_string="1999365", expected=datetime(1999, 12, 31)), + param(date_string="2000366", expected=datetime(2000, 12, 31)), + ] + ) + def test_day_of_year_is_parsed(self, date_string: str, expected: datetime) -> None: + """Test that %j maps the day of year onto the right date (Issue #271).""" + self.assertEqual(expected, parse(date_string, date_formats=["%Y%j"])) + + @parameterized.expand( + [ + param(date_string="1999366"), # 1999 is not a leap year + param(date_string="1999777"), + ] + ) + def test_out_of_range_day_of_year_is_not_parsed(self, date_string: str) -> None: + """Test that an invalid %j value is not read as another date (Issue #271).""" + self.assertIsNone(parse(date_string, date_formats=["%Y%j"])) + + @parameterized.expand( + [ + param( + date_string="mar, 07 giu 2022 08:56:47 +0200", + date_formats=["%a, %d %b %Y %H:%M:%S %z"], + ), + param(date_string="mar, 07 giu 2022 08:56:47 +0200", date_formats=None), + param(date_string="mar 07 giu 2022 08:56:47 +0200", date_formats=None), + ] + ) + def test_weekday_month_abbreviation_conflict_is_read_as_weekday( + self, date_string: str, date_formats: list[str] | None + ) -> None: + """Italian "mar" abbreviates both "martedì" (Tue) and "marzo" (Mar). When + another, unambiguous month ("giu") is present in the same string, "mar" must + be read as the weekday, comma or not, or the string fails to parse entirely + (Issue #1061).""" + result = parse(date_string, date_formats=date_formats, languages=["it"]) + assert result is not None + self.assertEqual(datetime(2022, 6, 7, 8, 56, 47), result.replace(tzinfo=None)) + + @parameterized.expand( + [ + param(date_string="mar 2022", expected_year=2022, expected_month=3), + param(date_string="mar, 2022", expected_year=2022, expected_month=3), + param( + date_string="mar, 7 2022", + expected_year=2022, + expected_month=3, + expected_day=7, + ), + param( + date_string="mar, 10, 2022", + expected_year=2022, + expected_month=3, + expected_day=10, + ), + ] + ) + def test_weekday_month_abbreviation_conflict_is_read_as_month( + self, + date_string: str, + expected_year: int, + expected_month: int, + expected_day: int | None = None, + ) -> None: + """Without another, unambiguous month elsewhere in the string, the ambiguous + Italian "mar" abbreviation must still be read as the month.""" + result = parse(date_string, languages=["it"]) + assert result is not None + self.assertEqual(expected_year, result.year) + self.assertEqual(expected_month, result.month) + if expected_day is not None: + self.assertEqual(expected_day, result.day) + + @parameterized.expand( + [ + param("mar 5 mar 2019", "it", datetime(2019, 3, 5)), + param("mar, 07 giu 2022 08:56:47", "it", datetime(2022, 6, 7, 8, 56, 47)), + param("seg, 3 fev 2020", "pt", datetime(2020, 2, 3)), + param("luni, 3 mar 2020", "ro", datetime(2020, 3, 3)), + param("3월 5일 2020", "ko", datetime(2020, 3, 5)), + param("mar 2019", "es", datetime(2019, 3, 15)), + ] + ) + def test_word_with_several_meanings( + self, date_string: str, language: str, expected: datetime + ) -> None: + settings = {"RELATIVE_BASE": datetime(2020, 1, 15)} + self.assertEqual( + expected, parse(date_string, languages=[language], settings=settings) + ) + + def test_word_with_several_meanings_with_date_formats(self) -> None: + self.assertEqual( + datetime(2022, 6, 7, 8, 56, 47), + parse( + "mar, 07 giu 2022 08:56:47", + date_formats=["%a, %d %b %Y %H:%M:%S"], + languages=["it"], + ), + ) + + def test_word_with_too_many_meaning_combinations(self) -> None: + self.assertIsNone(parse("mar mar mar mar mar", languages=["it"])) + + @parameterized.expand( + [ + param("32 DEC 10", datetime(2032, 12, 10), order="DMY"), + param("32/12/10", datetime(2032, 10, 12), order="DMY"), + param("12/13/10", datetime(2013, 10, 12), order="DMY"), + param("20 09 29", datetime(2020, 9, 29), order="MYD"), + param("95年12月10日", datetime(1995, 12, 10), order="MDY"), + # A day and a month in each other's place are swapped. + param("13/12/10", datetime(2010, 12, 13), order="MDY"), + param("01/13/21", datetime(2021, 1, 13), order="DMY"), + ] + ) + def test_date_order_is_a_preference_by_default( + self, date_string: str, expected: datetime, order: str + ) -> None: + """Test that without STRICT_DATE_ORDER, a number that does not fit where + DATE_ORDER puts it is read as another part of the date (Issue #868).""" + settings = {"DATE_ORDER": order, "RELATIVE_BASE": datetime(2019, 6, 24)} + self.assertEqual(expected, parse(date_string, settings=settings)) + + @parameterized.expand( + [ + param(*case.args, strict=strict, **case.kwargs) + for strict in ("year", "all") + for case in [ + param(date_string="32 DEC 10", order="DMY"), + param(date_string="00 DEC 10", order="DMY"), + param(date_string="32/12/10", order="DMY"), + param(date_string="32 DEC 10 10:30", order="DMY"), + param(date_string="32 décembre 10", order="DMY"), + param(date_string="DEC 32 10", order="MDY"), + param(date_string="10/32/12", order="MDY"), + param(date_string="40 12", order="DYM"), + # A day or month that the order puts after the year must not be + # read before it either. + param(date_string="10 DEC 32", order="MYD"), + param(date_string="DEC 10 95", order="YMD"), + # The year is the last resort here (#519), but YMD wants it first. + param(date_string="4-99", order="YMD"), + # The same goes for an invalid month, and the day and month are + # not swapped instead: that reading would not be the one + # without the setting. + param(date_string="12/13/10", order="DMY"), + # Translation leaves no marker of the year: "95-12-10". + param(date_string="95年12月10日", order="MDY"), + # Other locales must not read it differently: "ru" translates + # "20 09 29" to "29 29" and would find 2029-06-29. + param(date_string="20 09 29", order="MYD"), + # Nor must the no-spaces parser, which would find 1900-01-01 + # 10:03 in the first, and read 00 as the year in the second. + param( + date_string="10:30 PM 32/12/10", + order="DMY", + settings={"PARSERS": ["absolute-time", "no-spaces-time"]}, + ), + param( + date_string="001210", + order="DMY", + settings={"PARSERS": ["absolute-time", "no-spaces-time"]}, + ), + ] + ] + ) + def test_strict_date_order_rejects_misplaced_year( + self, + date_string: str, + order: str, + strict: str, + settings: dict[str, Any] | None = None, + ) -> None: + """Test that with STRICT_DATE_ORDER, a number that is invalid where + DATE_ORDER puts it is not read as a two-digit year instead, whether only + the year or the whole order is enforced (Issue #868).""" + settings = { + "DATE_ORDER": order, + "STRICT_DATE_ORDER": strict, + "RELATIVE_BASE": datetime(2019, 6, 24), + **(settings or {}), + } + self.assertIsNone(parse(date_string, settings=settings)) + + @parameterized.expand( + [ + param(*case.args, strict=strict, **case.kwargs) + for strict in ("year", "all") + for case in [ + param("31 DEC 10", datetime(2010, 12, 31), order="DMY"), + param("10 DEC 32", datetime(2032, 12, 10), order="DMY"), + # A year after the month is where DMY expects it. + param("DEC 32", datetime(2032, 12, 24), order="DMY"), + # A missing part is not checked. + param("DEC 95", datetime(1995, 12, 24), order="MDY"), + param("12/95", datetime(1995, 12, 24), order="MDY"), + param("13/2020", datetime(2020, 6, 13), order="MDY"), + # A two-digit year is still the last resort (#519). + param("DEC 95", datetime(1995, 12, 24), order="YMD"), + param("5 Dec 99", datetime(1999, 12, 5), order="DYM"), + # A four-digit year cannot be anything else. + param("2010 DEC 10", datetime(2010, 12, 10), order="DMY"), + param("12/2017/10", datetime(2017, 10, 12), order="DMY"), + param("DEC 2017 06", datetime(2017, 12, 6), order="DMY"), + # A date that starts with a four-digit year is read as year, + # month and day (#1419). + param("2017-06-22", datetime(2017, 6, 22), order="DMY"), + param("2017 06 DEC", datetime(2017, 12, 6), order="DMY"), + # A lone number next to a four-digit year is the month (#1472). + param("05/2020", datetime(2020, 5, 24), order="YMD"), + # The end of a range is dropped. + param("12-14 June 2021", datetime(2021, 6, 12), order="MDY"), + param("June 12-14, 2021", datetime(2021, 6, 12), order="MDY"), + param("12-12 June 2021", datetime(2021, 6, 12), order="DMY"), + # YMD asks for the year first, and MYD between month and day. + param("32 DEC 10", datetime(2032, 12, 10), order="YMD"), + param("95 DEC 10", datetime(1995, 12, 10), order="YMD"), + param("95年12月10日", datetime(1995, 12, 10), order="YMD"), + param("DEC 32 10", datetime(2032, 12, 10), order="MYD"), + # A month name is not checked: "12月" is translated to + # "december". + param("95年12月", datetime(1995, 12, 24), order="DMY"), + param("12 13 December", datetime(2013, 12, 12), order="DMY"), + # A word that another language reads as a date part does not + # stop that language: "ago" is August in Spanish. + param("12 ago 2019", datetime(2019, 8, 12), order="DMY"), + # Nor does a word with several meanings stop its other + # meanings: "mar" is Tuesday or March in Spanish. + param( + "mar 13 mar 2010", + datetime(2010, 3, 13), + order="DMY", + languages=["es"], + ), + # Nor does a number that is no date part at all stop the + # no-spaces parser. + param( + "20101231", + datetime(2010, 12, 31), + order="YMD", + settings={"PARSERS": ["absolute-time", "no-spaces-time"]}, + ), + ] + ] + ) + def test_strict_date_order_keeps_valid_dates( + self, + date_string: str, + expected: datetime, + strict: str, + order: str, + languages: list[str] | None = None, + settings: dict[str, Any] | None = None, + ) -> None: + """Test that STRICT_DATE_ORDER does not change dates whose parts are + where DATE_ORDER puts them, or that have no ambiguous number (Issue + #868).""" + settings = { + "DATE_ORDER": order, + "STRICT_DATE_ORDER": strict, + "RELATIVE_BASE": datetime(2019, 6, 24), + **(settings or {}), + } + self.assertEqual( + expected, parse(date_string, languages=languages, settings=settings) + ) + + @parameterized.expand( + [ + param("13/12/10", datetime(2010, 12, 13), order="MDY"), + param("13/12", datetime(2019, 12, 13), order="MDY"), + # Through the retry with the day and month swapped (#1180). + param("01/13/21", datetime(2021, 1, 13), order="DMY"), + param("06/2017/22", datetime(2017, 6, 22), order="DMY"), + # DYM and MYD put the year between the day and the month, so the + # swap changes which of them is read before it. + param("05 95 13", datetime(1995, 5, 13), order="DYM"), + param("13 95 12", datetime(1995, 12, 13), order="MYD"), + param("2017-06-22", datetime(2017, 6, 22), order="YDM"), + # After a four-digit year, the month and day may be swapped too. + param("2017-22-06", datetime(2017, 6, 22), order="DMY"), + # A four-digit year may displace a number read as the year. + param("31 DEC 2010", datetime(2010, 12, 31), order="MYD"), + param("14 12 2021", datetime(2021, 12, 14), order="MYD"), + param("22 2017 06", datetime(2017, 6, 22), order="YDM"), + param("05 2017 12", datetime(2017, 5, 12), order="YDM"), + # A CJK date goes through the same swap retry. + param("10年20月00日", datetime(2000, 10, 20), order="DMY"), + ] + ) + def test_strict_date_order_year_keeps_day_month_swaps( + self, date_string: str, expected: datetime, order: str + ) -> None: + """Test that STRICT_DATE_ORDER="year" enforces the position of the year + only, so a day and a month in each other's place are still swapped + (Issue #868).""" + settings = { + "DATE_ORDER": order, + "STRICT_DATE_ORDER": "year", + "RELATIVE_BASE": datetime(2019, 6, 24), + } + self.assertEqual(expected, parse(date_string, settings=settings)) + + @parameterized.expand( + [ + param(date_string="13/12/10", order="MDY"), + param(date_string="13/12", order="MDY"), + param(date_string="01/13/21", order="DMY"), + param(date_string="06/2017/22", order="DMY"), + param(date_string="05 95 13", order="DYM"), + param(date_string="13 95 12", order="MYD"), + param(date_string="2017-06-22", order="YDM"), + param(date_string="2017-22-06", order="DMY"), + param(date_string="31 DEC 2010", order="MYD"), + param(date_string="14 12 2021", order="MYD"), + param(date_string="22 2017 06", order="YDM"), + param(date_string="05 2017 12", order="YDM"), + # Other locales must not read it either: "zh" would read it as a + # relative date, 10 years and 20 months ago. + param(date_string="10年20月00日", order="DMY"), + ] + ) + def test_strict_date_order_all_rejects_day_month_swaps( + self, date_string: str, order: str + ) -> None: + """Test that STRICT_DATE_ORDER="all" also keeps the day and month where + DATE_ORDER puts them, instead of swapping them when they do not fit + (Issue #868).""" + settings = { + "DATE_ORDER": order, + "STRICT_DATE_ORDER": "all", + "RELATIVE_BASE": datetime(2019, 6, 24), + } + self.assertIsNone(parse(date_string, settings=settings)) + + @parameterized.expand([param(strict="year"), param(strict="all")]) + def test_strict_date_order_does_not_stop_other_parsers(self, strict: str) -> None: + """Test that a reading rejected by STRICT_DATE_ORDER does not keep the + other parsers of the locale from reading the date string (Issue #868).""" + settings = { + "DATE_ORDER": "DMY", + "STRICT_DATE_ORDER": strict, + "PARSERS": ["absolute-time", "relative-time"], + "RELATIVE_BASE": datetime(2019, 6, 24), + } + # The absolute parser would read it as 2032-06-10. + self.assertEqual( + datetime(2019, 6, 22, 15, 50), + parse("32 hours 10 minutes", settings=settings), + ) + if __name__ == "__main__": unittest.main() diff --git a/tests/test_dateparser_data_integrity.py b/tests/test_dateparser_data_integrity.py index 7e58e81d4..62a2cd01c 100644 --- a/tests/test_dateparser_data_integrity.py +++ b/tests/test_dateparser_data_integrity.py @@ -1,3 +1,5 @@ +from pathlib import Path + import pytest pytest.importorskip("ruamel") @@ -5,12 +7,11 @@ from dateparser_scripts.write_complete_data import write_complete_data -def test_dateparser_data_integrity(): +def test_dateparser_data_integrity() -> None: files = write_complete_data(in_memory=True) for filename in files: - with open(filename, "rb") as f: - assert f.read().strip() == files[filename].strip(), ( - 'The content of the file "{}" doesn\'t match the content' - " of the generated file.".format(filename) - ) + assert Path(filename).read_bytes().strip() == files[filename].strip(), ( + f'The content of the file "{filename}" doesn\'t match the content' + " of the generated file." + ) diff --git a/tests/test_fasttext.py b/tests/test_fasttext.py new file mode 100644 index 000000000..0b088074c --- /dev/null +++ b/tests/test_fasttext.py @@ -0,0 +1,8 @@ +import pytest + + +def test_fasttext_is_deprecated() -> None: + with pytest.warns(DeprecationWarning, match="fastText support is deprecated"): + from dateparser.custom_language_detection import fasttext # noqa: PLC0415 + with pytest.raises(ImportError): + fasttext.detect_languages("14 June 2020", 0.0) diff --git a/tests/test_french_republican.py b/tests/test_french_republican.py new file mode 100644 index 000000000..6d304edf8 --- /dev/null +++ b/tests/test_french_republican.py @@ -0,0 +1,87 @@ +import pytest + +pytest.importorskip("convertdate") + +from datetime import datetime + +from parameterized import param, parameterized + +from dateparser.calendars.french_republican import ( + FrenchRepublicanCalendar, + _french_republican_parser, +) +from dateparser.conf import settings +from tests import BaseTestCase + + +class TestFrenchRepublicanCalendar(BaseTestCase): + @parameterized.expand( + [ + param("18 brumaire an VIII", datetime(1799, 11, 9)), + param("1er Vendémiaire an II", datetime(1793, 9, 22)), + param("6 jours complémentaires an iii", datetime(1795, 9, 22)), + param("1 Floréal an. 79", datetime(1871, 4, 21)), + ] + ) + def test_dates(self, date_string: str, expected: datetime) -> None: + date_data = FrenchRepublicanCalendar(date_string).get_date() + assert date_data is not None + self.assertEqual(date_data.date_obj, expected) + self.assertEqual(date_data.period, "day") + self.assertEqual(date_data.parts, ("year", "month", "day")) + + @parameterized.expand( + [ + param("An XIV", datetime(1805, 9, 23), "year", ("year",)), + param("An 3.eme", datetime(1794, 9, 22), "year", ("year",)), + param("An IVme.", datetime(1795, 9, 23), "year", ("year",)), + param( + "Sans-culottides an I", + datetime(1793, 9, 17), + "month", + ("year", "month"), + ), + ] + ) + def test_prefer_first( + self, + date_string: str, + expected: datetime, + period: str, + parts: tuple[str, ...], + ) -> None: + first = settings.replace( + PREFER_DAY_OF_MONTH="first", PREFER_MONTH_OF_YEAR="first" + ) + self.assertEqual( + _french_republican_parser.parse(date_string, first), + (expected, period, parts), + ) + + def test_prefer_current(self) -> None: + current = settings.replace(RELATIVE_BASE=datetime(2026, 9, 29)) + self.assertEqual( + _french_republican_parser.parse("an VIII", current), + (datetime(1799, 9, 29), "year", ("year",)), + ) + + def test_prefer_last(self) -> None: + last = settings.replace(PREFER_DAY_OF_MONTH="last", PREFER_MONTH_OF_YEAR="last") + self.assertEqual( + _french_republican_parser.parse("an III", last), + (datetime(1795, 9, 22), "year", ("year",)), + ) + + @parameterized.expand( + [ + param("31 brumaire an VIII"), + param("6 sansculottides an II"), + param("An 0"), + param("An"), + param("An XIIII"), + param("brumaire"), + param("18 brumaire 1799"), + ] + ) + def test_invalid(self, date_string: str) -> None: + self.assertIsNone(FrenchRepublicanCalendar(date_string).get_date()) diff --git a/tests/test_freshness_date_parser.py b/tests/test_freshness_date_parser.py index 0ba2d60fe..58629945d 100644 --- a/tests/test_freshness_date_parser.py +++ b/tests/test_freshness_date_parser.py @@ -1,38 +1,40 @@ import unittest -from datetime import date, datetime, time, timedelta +from collections.abc import Callable +from datetime import date, datetime, time, timedelta, tzinfo from functools import wraps - -import pytz - -from zoneinfo import ZoneInfo - +from time import monotonic +from typing import Any from unittest.mock import Mock, patch +from zoneinfo import ZoneInfo from dateutil.relativedelta import relativedelta from parameterized import param, parameterized import dateparser -from dateparser.conf import settings -from dateparser.date import DateDataParser, freshness_date_parser +import dateparser.data.date_translation_data.en as en_data +from dateparser.conf import Settings, settings +from dateparser.date import DateData, DateDataParser +from dateparser.freshness_date_parser import PATTERN, freshness_date_parser +from dateparser.languages.dictionary import Dictionary from dateparser.utils import normalize_unicode from tests import BaseTestCase class TestFreshnessDateDataParser(BaseTestCase): - def setUp(self): + def setUp(self) -> None: super().setUp() self.now = datetime(2014, 9, 1, 10, 30) - self.date_string = NotImplemented - self.parser = NotImplemented - self.result = NotImplemented - self.freshness_parser = NotImplemented - self.freshness_result = NotImplemented + self.date_string: str = NotImplemented + self.parser: DateDataParser = NotImplemented + self.result: DateData = NotImplemented + self.freshness_parser: Mock = NotImplemented + self.freshness_result: DateData = NotImplemented self.date = NotImplemented self.time = NotImplemented - settings.TIMEZONE = "utc" + self.add_patch(patch.object(settings, "TIMEZONE", "utc")) - def now_with_timezone(self, tz): + def now_with_timezone(self, tz: tzinfo | None) -> datetime: now = self.now return datetime(now.year, now.month, now.day, now.hour, now.minute, tzinfo=tz) @@ -43,7 +45,9 @@ def now_with_timezone(self, tz): param("yesterday at 11:30", ago={"hours": 23}, period="time"), ] ) - def test_relative_past_dates_with_time_as_period(self, date_string, ago, period): + def test_relative_past_dates_with_time_as_period( + self, date_string: str, ago: dict[str, Any], period: str + ) -> None: self.given_parser(settings={"NORMALIZE": False, "RETURN_TIME_AS_PERIOD": True}) self.given_date_string(date_string) self.when_date_is_parsed() @@ -68,6 +72,13 @@ def test_relative_past_dates_with_time_as_period(self, date_string, ago, period) param("last decade", ago={"years": 10}, period="year"), param("a decade ago", ago={"years": 10}, period="year"), param("100 decades", ago={"years": 1000}, period="year"), + # Regression tests for #1304: an explicit sign on a component is + # preserved when ``decades`` is folded into ``years`` instead of + # being overwritten by the decade's sign. Unsigned components still + # follow the ago/future context. + param("-1 decade", ago={"years": 10}, period="year"), + param("-1 decade 2 years", ago={"years": 12}, period="year"), + param("-1 decade +2 years", ago={"years": 8}, period="year"), param("yesterday", ago={"days": 1}, period="day"), param("the day before yesterday", ago={"days": 2}, period="day"), param("4 days before", ago={"days": 4}, period="day"), @@ -99,7 +110,7 @@ def test_relative_past_dates_with_time_as_period(self, date_string, ago, period) ), # We've fixed .now in setUp param("5000 months ago", ago={"years": 416, "months": 8}, period="month"), param( - "{} months ago".format(2013 * 12 + 8), + f"{2013 * 12 + 8} months ago", ago={"years": 2013, "months": 8}, period="month", ), @@ -116,6 +127,11 @@ def test_relative_past_dates_with_time_as_period(self, date_string, ago, period) period="day", ), param("just now", ago={"seconds": 0}, period="day"), + # now - offset with explicit spaced '-' operator + param("now - 1hour", ago={"hours": 1}, period="day"), + param("now - 2 hours", ago={"hours": 2}, period="day"), + param("now - 30 minutes", ago={"minutes": 30}, period="day"), + param("now - 1 day", ago={"days": 1}, period="day"), # Fix for #291, work till one to twelve only param("nine hours ago", ago={"hours": 9}, period="day"), param("three week ago", ago={"weeks": 3}, period="week"), @@ -533,7 +549,7 @@ def test_relative_past_dates_with_time_as_period(self, date_string, ago, period) param("1000 বছর আগে", ago={"years": 1000}, period="year"), param("5000 মাস আগে", ago={"years": 416, "months": 8}, period="month"), param( - "{} মাস আগে".format(2013 * 12 + 8), + f"{2013 * 12 + 8} মাস আগে", ago={"years": 2013, "months": 8}, period="month", ), @@ -696,6 +712,39 @@ def test_relative_past_dates_with_time_as_period(self, date_string, ago, period) ago={"minutes": 2, "seconds": 45}, period="day", ), + param("před týden", ago={"weeks": 1}, period="week"), + param("před měsíc", ago={"months": 1}, period="month"), + param("před rok", ago={"years": 1}, period="year"), + param("před den", ago={"days": 1}, period="day"), + param("před dnem", ago={"days": 1}, period="day"), + param("před hodinu", ago={"hours": 1}, period="day"), + param("před minutu", ago={"minutes": 1}, period="day"), + param("před sekundu", ago={"seconds": 1}, period="day"), + param("قبل أسبوع", ago={"weeks": 1}, period="week"), # ar + param("قبل ساعة", ago={"hours": 1}, period="day"), # ar + param("тыдзень таму", ago={"weeks": 1}, period="week"), # be + param("год таму", ago={"years": 1}, period="year"), # be + param("преди месец", ago={"months": 1}, period="month"), # bg + param("viikko sitten", ago={"weeks": 1}, period="week"), # fi + param("tunti sitten", ago={"hours": 1}, period="day"), # fi + param("לפני שבוע", ago={"weeks": 1}, period="week"), # he + param("לפני שעה", ago={"hours": 1}, period="day"), # he + param("prije tjedan dana", ago={"weeks": 1}, period="week"), # hr + param("prije mjesec dana", ago={"months": 1}, period="month"), # hr + param("prije sat vremena", ago={"hours": 1}, period="day"), # hr + param("prieš savaitę", ago={"weeks": 1}, period="week"), # lt + param("prieš metus", ago={"years": 1}, period="year"), # lt + param("pirms nedēļas", ago={"weeks": 1}, period="week"), # lv + param("pirms gada", ago={"years": 1}, period="year"), # lv + param("пред седмица", ago={"weeks": 1}, period="week"), # mk + param("пред месец", ago={"months": 1}, period="month"), # mk + param("tydzień temu", ago={"weeks": 1}, period="week"), # pl + param("miesiąc temu", ago={"months": 1}, period="month"), # pl + param("godzinę temu", ago={"hours": 1}, period="day"), # pl + param("pred tednom", ago={"weeks": 1}, period="week"), # sl + param("pred uro", ago={"hours": 1}, period="day"), # sl + param("тиждень тому", ago={"weeks": 1}, period="week"), # uk + param("рік тому", ago={"years": 1}, period="year"), # uk # cy param("5 wythnos yn ôl", ago={"weeks": 5}, period="week"), param( @@ -797,7 +846,7 @@ def test_relative_past_dates_with_time_as_period(self, date_string, ago, period) # kl param("for 6 ulloq unnuarlu siden", ago={"days": 6}, period="day"), # km - param("11 សប្ដាហ៍​មុន", ago={"weeks": 11}, period="week"), + param("11 សប្ដាហ៍\u200bមុន", ago={"weeks": 11}, period="week"), # kn param("15 ಸೆಕೆಂಡುಗಳ ಹಿಂದೆ", ago={"seconds": 15}, period="day"), # ko @@ -907,7 +956,9 @@ def test_relative_past_dates_with_time_as_period(self, date_string, ago, period) param("21 izinsuku ezedlule", ago={"days": 21}, period="day"), ] ) - def test_relative_past_dates(self, date_string, ago, period): + def test_relative_past_dates( + self, date_string: str, ago: dict[str, Any], period: str + ) -> None: self.given_parser(settings={"NORMALIZE": False}) self.given_date_string(date_string) self.when_date_is_parsed() @@ -962,7 +1013,7 @@ def test_relative_past_dates(self, date_string, ago, period): ), # We've fixed .now in setUp param("5000 months ago", ago={"years": 416, "months": 8}, period="month"), param( - "{} months ago".format(2013 * 12 + 8), + f"{2013 * 12 + 8} months ago", ago={"years": 2013, "months": 8}, period="month", ), @@ -1274,6 +1325,8 @@ def test_relative_past_dates(self, date_string, ago, period): }, period="day", ), + param("6 วัน ที่แล้ว", ago={"days": 6}, period="day"), + param("3 เดือน ที่ผ่านมา", ago={"months": 3}, period="month"), # Vietnamese dates param("Hôm nay", ago={"days": 0}, period="day"), param("Hôm qua", ago={"days": 1}, period="day"), @@ -1356,7 +1409,7 @@ def test_relative_past_dates(self, date_string, ago, period): param("1000 বছর আগে", ago={"years": 1000}, period="year"), param("5000 মাস আগে", ago={"years": 416, "months": 8}, period="month"), param( - "{} মাস আগে".format(2013 * 12 + 8), + f"{2013 * 12 + 8} মাস আগে", ago={"years": 2013, "months": 8}, period="month", ), @@ -1614,7 +1667,7 @@ def test_relative_past_dates(self, date_string, ago, period): # kl param("for 6 ulloq unnuarlu siden", ago={"days": 6}, period="day"), # km - param("11 សប្ដាហ៍​មុន", ago={"weeks": 11}, period="week"), + param("11 សប្ដាហ៍\u200bមុន", ago={"weeks": 11}, period="week"), # kn param("15 ಸೆಕೆಂಡುಗಳ ಹಿಂದೆ", ago={"seconds": 15}, period="day"), # ko @@ -1716,7 +1769,9 @@ def test_relative_past_dates(self, date_string, ago, period): param("21 izinsuku ezedlule", ago={"days": 21}, period="day"), ] ) - def test_normalized_relative_dates(self, date_string, ago, period): + def test_normalized_relative_dates( + self, date_string: str, ago: dict[str, Any], period: str + ) -> None: date_string = normalize_unicode(date_string) self.given_parser(settings={"NORMALIZE": True}) self.given_date_string(date_string) @@ -1738,6 +1793,10 @@ def test_normalized_relative_dates(self, date_string, ago, period): param("in 1 decade 12 years", in_future={"years": 22}, period="year"), param("next decade", in_future={"years": 10}, period="year"), param("in a decade", in_future={"years": 10}, period="year"), + # Regression tests for #1304: explicit signs preserved with decades + years + param("+2 years", in_future={"years": 2}, period="year"), + param("in 1 decade +2 years", in_future={"years": 12}, period="year"), + param("+1 decade -2 years", in_future={"years": 8}, period="year"), param("tomorrow", in_future={"days": 1}, period="day"), param("day after tomorrow", in_future={"days": 2}, period="day"), param("after 4 days", in_future={"days": 4}, period="day"), @@ -1783,7 +1842,7 @@ def test_normalized_relative_dates(self, date_string, ago, period): "in 5000 months", in_future={"years": 416, "months": 8}, period="month" ), param( - "in {} months".format(2013 * 12 + 8), + f"in {2013 * 12 + 8} months", in_future={"years": 2013, "months": 8}, period="month", ), @@ -1808,6 +1867,27 @@ def test_normalized_relative_dates(self, date_string, ago, period): param("3 hours later", in_future={"hours": 3}, period="day"), param("4 minutes later", in_future={"minutes": 4}, period="day"), param("5 seconds later", in_future={"seconds": 5}, period="day"), + # from now + param("7 years from now", in_future={"years": 7}, period="year"), + param("6 months from now", in_future={"months": 6}, period="month"), + param("5 weeks from now", in_future={"weeks": 5}, period="week"), + param("4 days from now", in_future={"days": 4}, period="day"), + param("3 hours from now", in_future={"hours": 3}, period="day"), + param("2 minutes from now", in_future={"minutes": 2}, period="day"), + param("1 second from now", in_future={"seconds": 1}, period="day"), + param("five years from now", in_future={"years": 5}, period="year"), + param("a year from now", in_future={"years": 1}, period="year"), + param("an hour from now", in_future={"hours": 1}, period="day"), + param( + "1 year 2 months from now", + in_future={"years": 1, "months": 2}, + period="month", + ), + # now + offset with explicit spaced '+' operator + param("now + 1hour", in_future={"hours": 1}, period="day"), + param("now + 2 hours", in_future={"hours": 2}, period="day"), + param("now + 30 minutes", in_future={"minutes": 30}, period="day"), + param("now + 1 day", in_future={"days": 1}, period="day"), # Fractional units param("in 2.5 hours", in_future={"hours": 2.5}, period="day"), param("in 10.75 minutes", in_future={"minutes": 10.75}, period="day"), @@ -2264,6 +2344,7 @@ def test_normalized_relative_dates(self, date_string, ago, period): # th param("ในอีก 6 นาที", in_future={"minutes": 6}, period="day"), param("ในอีก 3 ปี", in_future={"years": 3}, period="year"), + param("อีก 6 วัน", in_future={"days": 6}, period="day"), # to param("'i he māhina 'e 5", in_future={"months": 5}, period="month"), param("'i he houa 'e 11", in_future={"hours": 11}, period="day"), @@ -2304,7 +2385,9 @@ def test_normalized_relative_dates(self, date_string, ago, period): param("4 週後", in_future={"weeks": 4}, period="week"), ] ) - def test_relative_future_dates(self, date_string, in_future, period): + def test_relative_future_dates( + self, date_string: str, in_future: dict[str, Any], period: str + ) -> None: self.given_parser() self.given_date_string(date_string) self.when_date_is_parsed() @@ -2317,9 +2400,11 @@ def test_relative_future_dates(self, date_string, in_future, period): [ param("15th of Aug, 2014 Diane Bennett"), param("4 heures ago"), + param("the 31st of this month"), + param("the 1st of last month 2 days ago"), ] ) - def test_insane_dates(self, date_string): + def test_insane_dates(self, date_string: str) -> None: self.given_parser() self.given_date_string(date_string) self.when_date_is_parsed() @@ -2330,7 +2415,7 @@ def test_insane_dates(self, date_string): [ param("5000 years ago"), param("2014 years ago"), # We've fixed .now in setUp - param("{} months ago".format(2013 * 12 + 9)), + param(f"{2013 * 12 + 9} months ago"), param("123456789 hour"), param("123456789123 hour"), param("1234567 days"), @@ -2339,7 +2424,7 @@ def test_insane_dates(self, date_string): param("123455678976543 month"), ] ) - def test_dates_not_supported_by_date_time(self, date_string): + def test_dates_not_supported_by_date_time(self, date_string: str) -> None: self.given_parser() self.given_date_string(date_string) self.when_date_is_parsed() @@ -2348,15 +2433,21 @@ def test_dates_not_supported_by_date_time(self, date_string): @parameterized.expand( [ - param("1mon ago"), # 1116 + param("1mon ago", ago={"months": 1}, period="month"), # 1123 + param("2mon ago", ago={"months": 2}, period="month"), # 1123 + param("3mons ago", ago={"months": 3}, period="month"), # 1123 ] ) - def test_known_issues(self, date_string): + def test_known_issues( + self, date_string: str, ago: dict[str, Any], period: str + ) -> None: self.given_parser() self.given_date_string(date_string) self.when_date_is_parsed() self.then_error_was_not_raised() - self.assertEqual(None, self.result["date_obj"]) + self.then_date_was_parsed_by_freshness_parser() + self.then_date_obj_is_exactly_this_time_ago(ago) + self.then_period_is(period) @parameterized.expand( [ @@ -2364,7 +2455,9 @@ def test_known_issues(self, date_string): param("há alguns segundos", boundary={"seconds": 45}, period="day"), ] ) - def test_inexplicit_dates(self, date_string, boundary, period): + def test_inexplicit_dates( + self, date_string: str, boundary: dict[str, int], period: str + ) -> None: self.given_parser() self.given_date_string(date_string) self.when_date_is_parsed() @@ -2389,14 +2482,16 @@ def test_inexplicit_dates(self, date_string, boundary, period): param("tomorrow at 2 PM", date(2014, 9, 2), time(14, 0)), ] ) - def test_freshness_date_with_time(self, date_string, date, time): + def test_freshness_date_with_time( + self, date_string: str, date: date, time: time + ) -> None: self.given_parser() self.given_date_string(date_string) self.when_date_is_parsed() self.then_date_is(date) self.then_time_is(time) - def test_freshness_date_with_time_and_timezone(self): + def test_freshness_date_with_time_and_timezone(self) -> None: self.given_parser(settings={"TIMEZONE": "local"}) self.given_date_string("tomorrow 8:30 CST") self.when_date_is_parsed() @@ -2415,8 +2510,8 @@ def test_freshness_date_with_time_and_timezone(self): ] ) def test_freshness_date_with_pytz_timezones( - self, date_string, timezone, date, time - ): + self, date_string: str, timezone: str, date: date, time: time + ) -> None: self.given_parser(settings={"TIMEZONE": timezone}) self.given_date_string(date_string) self.when_date_is_parsed() @@ -2440,8 +2535,8 @@ def test_freshness_date_with_pytz_timezones( ] ) def test_freshness_date_with_timezone_conversion( - self, date_string, timezone, to_timezone, date, time - ): + self, date_string: str, timezone: str, to_timezone: str, date: date, time: time + ) -> None: self.given_parser( settings={ "TIMEZONE": timezone, @@ -2454,20 +2549,16 @@ def test_freshness_date_with_timezone_conversion( self.then_date_is(date) self.then_time_is(time) - def test_freshness_date_with_to_timezone_setting(self): + def test_freshness_date_with_to_timezone_setting(self) -> None: _settings = settings.replace( - **{ - "TIMEZONE": "local", - "TO_TIMEZONE": "UTC", - "RELATIVE_BASE": datetime(2014, 9, 1, 10, 30), - } + TIMEZONE="local", + TO_TIMEZONE="UTC", + RELATIVE_BASE=datetime(2014, 9, 1, 10, 30), ) parser = dateparser.freshness_date_parser.FreshnessDateDataParser() - timezone = ( - ZoneInfo(key="US/Eastern") if ZoneInfo else pytz.timezone("US/Eastern") - ) - parser.get_local_tz = Mock(return_value=timezone) + timezone = ZoneInfo(key="US/Eastern") + parser.get_local_tz = Mock(return_value=timezone) # type: ignore[method-assign] result = parser.get_date_data("1 minute ago", _settings) result = result["date_obj"] self.assertEqual(result.date(), date(2014, 9, 1)) @@ -2481,8 +2572,8 @@ def test_freshness_date_with_to_timezone_setting(self): ] ) def test_freshness_date_with_timezone_abbreviations( - self, date_string, timezone, date, time - ): + self, date_string: str, timezone: str, date: date, time: time + ) -> None: self.given_parser(settings={"TIMEZONE": timezone}) self.given_date_string(date_string) self.when_date_is_parsed() @@ -2497,8 +2588,8 @@ def test_freshness_date_with_timezone_abbreviations( ] ) def test_freshness_date_with_timezone_utc_offset( - self, date_string, timezone, date, time - ): + self, date_string: str, timezone: str, date: date, time: time + ) -> None: self.given_parser(settings={"TIMEZONE": timezone}) self.given_date_string(date_string) self.when_date_is_parsed() @@ -2536,7 +2627,7 @@ def test_freshness_date_with_timezone_utc_offset( param("1000 years ago", date(1010, 6, 4), time(13, 15)), param("2008 years ago", date(2, 6, 4), time(13, 15)), param("5000 months ago", date(1593, 10, 4), time(13, 15)), - param("{} months ago".format(2008 * 12 + 8), date(1, 10, 4), time(13, 15)), + param(f"{2008 * 12 + 8} months ago", date(1, 10, 4), time(13, 15)), param( "1 year, 1 month, 1 week, 1 day, 1 hour and 1 minute ago", date(2009, 4, 26), @@ -2548,9 +2639,15 @@ def test_freshness_date_with_timezone_utc_offset( param("in 10.75 minutes", date(2010, 6, 4), time(13, 25, 45)), param("in 1.5 days", date(2010, 6, 6), time(1, 15)), param("0,5 hours ago", date(2010, 6, 4), time(12, 45)), + # Day of a relative month + param("the 1st of last month", date(2010, 5, 1), time(13, 15)), + param("the 1st of this month", date(2010, 6, 1), time(13, 15)), + param("30th of next month at 5pm", date(2010, 7, 30), time(17, 0)), ] ) - def test_freshness_date_with_relative_base(self, date_string, date, time): + def test_freshness_date_with_relative_base( + self, date_string: str, date: date, time: time + ) -> None: self.given_parser(settings={"RELATIVE_BASE": datetime(2010, 6, 4, 13, 15)}) self.given_date_string(date_string) self.when_date_is_parsed() @@ -2563,7 +2660,9 @@ def test_freshness_date_with_relative_base(self, date_string, date, time): param("2 years", date(2008, 6, 4), time(13, 15)), ] ) - def test_freshness_date_with_relative_base_past(self, date_string, date, time): + def test_freshness_date_with_relative_base_past( + self, date_string: str, date: date, time: time + ) -> None: self.given_parser( settings={ "PREFER_DATES_FROM": "past", @@ -2581,7 +2680,9 @@ def test_freshness_date_with_relative_base_past(self, date_string, date, time): param("2 years", date(2012, 6, 4), time(13, 15)), ] ) - def test_freshness_date_with_relative_base_future(self, date_string, date, time): + def test_freshness_date_with_relative_base_future( + self, date_string: str, date: date, time: time + ) -> None: self.given_parser( settings={ "PREFER_DATES_FROM": "future", @@ -2593,13 +2694,61 @@ def test_freshness_date_with_relative_base_future(self, date_string, date, time) self.then_date_is(date) self.then_time_is(time) - def given_date_string(self, date_string): + @parameterized.expand( + [ + param("this month", {"PREFER_DAY_OF_MONTH": "first"}, date(2010, 6, 1)), + param("next month", {"PREFER_DAY_OF_MONTH": "last"}, date(2010, 7, 31)), + param("2 months ago", {"PREFER_DAY_OF_MONTH": "last"}, date(2010, 4, 30)), + param("next month", {"PREFER_DAY_OF_MONTH": "current"}, date(2010, 7, 4)), + param("next week", {"PREFER_DAY_OF_MONTH": "first"}, date(2010, 6, 11)), + param( + "last year", + {"PREFER_MONTH_OF_YEAR": "first", "PREFER_DAY_OF_MONTH": "first"}, + date(2009, 1, 1), + ), + param("last year", {"PREFER_MONTH_OF_YEAR": "last"}, date(2009, 12, 4)), + ] + ) + def test_freshness_date_with_prefer_day_and_month( + self, date_string: str, prefer_settings: dict[str, Any], date: date + ) -> None: + self.given_parser( + settings={"RELATIVE_BASE": datetime(2010, 6, 4, 13, 15), **prefer_settings} + ) + self.given_date_string(date_string) + self.when_date_is_parsed() + self.then_date_is(date) + self.then_time_is(time(13, 15)) + + def test_long_digit_run_does_not_hang(self) -> None: + # Possessive quantifiers (\d++[.,]?\d*+) prevent quadratic backtracking. + # Without the fix, PATTERN.findall('9' * 3200) takes ~23 s; with it, ~0.02 s. + long_digits = "9" * 3200 + + start = monotonic() + PATTERN.findall(long_digits) + elapsed = monotonic() - start + self.assertLess(elapsed, 1.0, "PATTERN.findall backtracked on long digit run") + + d = Dictionary(en_data.info, settings) + split_re = d._get_split_relative_regex_cache() + + start = monotonic() + split_re.split(long_digits) + elapsed = monotonic() - start + self.assertLess( + elapsed, 1.0, "split_relative_regex backtracked on long digit run" + ) + + def given_date_string(self, date_string: str) -> None: self.date_string = date_string - def given_parser(self, settings=None): - def collecting_get_date_data(get_date_data): + def given_parser(self, settings: Settings | dict[str, Any] | None = None) -> None: + def collecting_get_date_data( + get_date_data: Callable[..., DateData], + ) -> Callable[..., DateData]: @wraps(get_date_data) - def wrapped(*args, **kwargs): + def wrapped(*args: Any, **kwargs: Any) -> DateData: self.freshness_result = get_date_data(*args, **kwargs) return self.freshness_result @@ -2615,7 +2764,7 @@ def wrapped(*args, **kwargs): self.freshness_parser = Mock(wraps=freshness_date_parser) - dt_mock = Mock(wraps=dateparser.freshness_date_parser.datetime) + dt_mock = Mock(wraps=dateparser.freshness_date_parser.datetime) # type: ignore[attr-defined] dt_mock.now = Mock(side_effect=self.now_with_timezone) self.add_patch(patch("dateparser.freshness_date_parser.datetime", new=dt_mock)) self.add_patch( @@ -2623,43 +2772,47 @@ def wrapped(*args, **kwargs): ) self.parser = DateDataParser(settings=settings) - def when_date_is_parsed(self): + def when_date_is_parsed(self) -> None: try: self.result = self.parser.get_date_data(self.date_string) except Exception as error: self.error = error - def then_date_is(self, date): + def then_date_is(self, date: date) -> None: self.assertEqual(date, self.result["date_obj"].date()) - def then_time_is(self, time): + def then_time_is(self, time: time) -> None: self.assertEqual(time, self.result["date_obj"].time()) - def then_timezone_is(self, timezone): + def then_timezone_is(self, timezone: str) -> None: self.assertEqual(timezone, self.result["date_obj"].tzname()) - def then_period_is(self, period): + def then_period_is(self, period: str) -> None: self.assertEqual(period, self.result["period"]) - def then_date_obj_is_between(self, low_boundary, high_boundary): + def then_date_obj_is_between( + self, low_boundary: datetime, high_boundary: datetime + ) -> None: self.assertGreater(self.result["date_obj"], low_boundary) self.assertLess(self.result["date_obj"], high_boundary) - def then_date_obj_is_exactly_this_time_ago(self, ago): + def then_date_obj_is_exactly_this_time_ago(self, ago: dict[str, Any]) -> None: self.assertEqual(self.now - relativedelta(**ago), self.result["date_obj"]) - def then_date_obj_is_exactly_this_time_in_future(self, in_future): + def then_date_obj_is_exactly_this_time_in_future( + self, in_future: dict[str, Any] + ) -> None: self.assertEqual(self.now + relativedelta(**in_future), self.result["date_obj"]) - def then_date_was_not_parsed(self): + def then_date_was_not_parsed(self) -> None: self.assertIsNone( - self.result["date_obj"], '"%s" should not be parsed' % self.date_string + self.result["date_obj"], f'"{self.date_string}" should not be parsed' ) - def then_date_was_parsed_by_freshness_parser(self): + def then_date_was_parsed_by_freshness_parser(self) -> None: self.assertEqual(self.result, self.freshness_result) - def then_error_was_not_raised(self): + def then_error_was_not_raised(self) -> None: self.assertEqual(NotImplemented, self.error) diff --git a/tests/test_hijri.py b/tests/test_hijri.py index 00b58da61..3e49ebcc2 100644 --- a/tests/test_hijri.py +++ b/tests/test_hijri.py @@ -3,27 +3,38 @@ pytest.importorskip("hijridate") from datetime import datetime +from typing import TYPE_CHECKING from parameterized import param, parameterized from dateparser.calendars.hijri import HijriCalendar +from dateparser.conf import settings from tests import BaseTestCase +if TYPE_CHECKING: + from dateparser.date import DateData + class TestHijriParser(BaseTestCase): - def setUp(self): + def setUp(self) -> None: super().setUp() - self.result = NotImplemented - self.date_string = NotImplemented - self.parser = NotImplemented + self.result: DateData | None = NotImplemented + self.date_string: str = NotImplemented + self.parser: HijriCalendar = NotImplemented self.translated = NotImplemented - def when_date_is_given(self, dt_string, date_formats, languages): + def when_date_is_given( + self, + dt_string: str, + date_formats: list[str] | None, + languages: list[str] | None, + ) -> None: self.date_string = dt_string self.parser = HijriCalendar(dt_string) self.result = self.parser.get_date() - def then_parsed_datetime_is(self, dt): + def then_parsed_datetime_is(self, dt: datetime) -> None: + assert self.result is not None self.assertEqual(dt, self.result["date_obj"]) @parameterized.expand( @@ -58,10 +69,12 @@ def then_parsed_datetime_is(self, dt): ] ) def test_datetime_parsing( - self, dt_string, dt_obj, date_formats=None, languages=None - ): - from dateparser.conf import settings - + self, + dt_string: str, + dt_obj: datetime, + date_formats: list[str] | None = None, + languages: list[str] | None = None, + ) -> None: settings.DATE_ORDER = "DMY" self.when_date_is_given(dt_string, date_formats, languages) self.then_parsed_datetime_is(dt_obj) diff --git a/tests/test_jalali.py b/tests/test_jalali.py index 7511f1661..cc4c137a2 100644 --- a/tests/test_jalali.py +++ b/tests/test_jalali.py @@ -3,6 +3,7 @@ pytest.importorskip("convertdate") from datetime import datetime +from typing import TYPE_CHECKING from parameterized import param, parameterized @@ -10,16 +11,19 @@ from dateparser.calendars.jalali_parser import PersianDate, jalali_parser from tests import BaseTestCase +if TYPE_CHECKING: + from dateparser.date import DateData + class TestPersianDate(BaseTestCase): - def setUp(self): + def setUp(self) -> None: super().setUp() - self.persian_date = NotImplemented + self.persian_date: PersianDate = NotImplemented - def when_date_is_given(self, year, month, day): + def when_date_is_given(self, year: int, month: int, day: int) -> None: self.persian_date = PersianDate(year, month, day) - def then_weekday_is(self, weekday): + def then_weekday_is(self, weekday: int | None) -> None: self.assertEqual(self.persian_date.weekday(), weekday) @parameterized.expand( @@ -28,31 +32,35 @@ def then_weekday_is(self, weekday): param(year=1348, month=2, day=28, weekday=0), param(year=1348, month=3, day=27, weekday=2), param(year=1348, month=4, day=11, weekday=3), + param(year=1348, month=1, day=32, weekday=None), + param(year=1348, month=12, day=31, weekday=None), ] ) - def test_weekday(self, year, month, day, weekday): + def test_weekday( + self, year: int, month: int, day: int, weekday: int | None + ) -> None: self.when_date_is_given(year, month, day) self.then_weekday_is(weekday) class TestJalaliParser(BaseTestCase): - def setUp(self): + def setUp(self) -> None: super().setUp() - self.translated = NotImplemented + self.translated: str = NotImplemented - def when_date_is_given(self, date_string): + def when_date_is_given(self, date_string: str) -> None: self.translated = jalali_parser.to_latin(date_string) - def then_month_is_parsed_as(self, month_name): + def then_month_is_parsed_as(self, month_name: str) -> None: self.assertEqual(month_name, self.translated) - def then_weekday_is_parsed_as(self, weekday): + def then_weekday_is_parsed_as(self, weekday: str) -> None: self.assertEqual(weekday, self.translated) - def then_digit_is_parsed_as(self, digit): + def then_digit_is_parsed_as(self, digit: str) -> None: self.assertEqual(digit, self.translated) - def then_numeral_parsed_is(self, datetime): + def then_numeral_parsed_is(self, datetime: str) -> None: self.assertEqual(datetime, self.translated) @parameterized.expand( @@ -71,7 +79,7 @@ def then_numeral_parsed_is(self, datetime): param(date_string="اسفند", latin="Esfand"), ] ) - def test_replace_months(self, date_string, latin): + def test_replace_months(self, date_string: str, latin: str) -> None: self.when_date_is_given(date_string) self.then_month_is_parsed_as(latin) @@ -86,7 +94,7 @@ def test_replace_months(self, date_string, latin): param(date_string="جمعه", latin="Friday"), ] ) - def test_replace_weekdays(self, date_string, latin): + def test_replace_weekdays(self, date_string: str, latin: str) -> None: self.when_date_is_given(date_string) self.then_weekday_is_parsed_as(latin) @@ -98,7 +106,7 @@ def test_replace_weekdays(self, date_string, latin): param(date_string="۰۵۶۱۲۷۳۸۹۴", latin="0561273894"), ] ) - def test_replace_digits(self, date_string, latin): + def test_replace_digits(self, date_string: str, latin: str) -> None: self.when_date_is_given(date_string) self.then_digit_is_parsed_as(latin) @@ -163,24 +171,27 @@ def test_replace_digits(self, date_string, latin): param(persian="سی و یکم", numeral="31"), ] ) - def test_replace_day_literal_with_numerals(self, persian, numeral): + def test_replace_day_literal_with_numerals( + self, persian: str, numeral: str + ) -> None: self.when_date_is_given(persian) self.then_numeral_parsed_is(numeral) class TestJalaliCalendar(BaseTestCase): - def setUp(self): + def setUp(self) -> None: super().setUp() - self.result = NotImplemented - self.date_string = NotImplemented - self.calendar = NotImplemented + self.result: DateData | None = NotImplemented + self.date_string: str = NotImplemented + self.calendar: JalaliCalendar = NotImplemented - def when_date_is_given(self, date_string): + def when_date_is_given(self, date_string: str) -> None: self.date_string = date_string self.calendar = JalaliCalendar(date_string) self.result = self.calendar.get_date() - def then_date_parsed_is(self, datetime): + def then_date_parsed_is(self, datetime: datetime) -> None: + assert self.result is not None self.assertEqual(datetime, self.result["date_obj"]) @parameterized.expand( @@ -254,6 +265,10 @@ def then_date_parsed_is(self, datetime): ), ] ) - def test_get_date(self, date_string, dt): + def test_get_date(self, date_string: str, dt: datetime) -> None: self.when_date_is_given(date_string) self.then_date_parsed_is(dt) + + def test_get_date_invalid(self) -> None: + self.when_date_is_given("foo") + self.assertIsNone(self.result) diff --git a/tests/test_language_detect.py b/tests/test_language_detect.py index fe82c1db4..350e4b999 100644 --- a/tests/test_language_detect.py +++ b/tests/test_language_detect.py @@ -1,6 +1,6 @@ import pytest -pytest.importorskip("fasttext") +pytest.importorskip("langdetect") import unittest from datetime import datetime @@ -9,62 +9,131 @@ from parameterized import param, parameterized from dateparser import parse -from dateparser.custom_language_detection.fasttext import ( - detect_languages as fast_text_detect_languages, -) from dateparser.custom_language_detection.langdetect import ( detect_languages as lang_detect_detect_languages, ) from dateparser.date import DateDataParser from dateparser.search import search_dates -detect_languages = Mock() -detect_languages.return_value = ["en"] +class LangDetectBasicTest(unittest.TestCase): + """Tests for basic langdetect functionality""" -class CustomLangDetectParserTest(unittest.TestCase): - def check_is_returned_list(self): - self.assertEqual(type(self.result), list) + def test_returns_list(self) -> None: + result = lang_detect_detect_languages("14 June 2020", 0.0) + self.assertIsInstance(result, list) - @parameterized.expand( - [ - param(dt_string="14 June 2020", confidence_threshold=0.0), - param(dt_string="26 July 2021", confidence_threshold=0.0), - ] - ) - def test_custom_language_detect_fast_text(self, dt_string, confidence_threshold): - self.result = fast_text_detect_languages(dt_string, confidence_threshold) - self.check_is_returned_list() + def test_detects_english(self) -> None: + result = lang_detect_detect_languages( + "The meeting is scheduled for Tuesday, July 22, 2014", 0.5 + ) + self.assertIn("en", result) - @parameterized.expand( - [ - param(dt_string="14 June 2020", confidence_threshold=0.0), - ] - ) - def test_custom_language_detect_lang_detect(self, dt_string, confidence_threshold): - self.result = lang_detect_detect_languages(dt_string, confidence_threshold) - self.check_is_returned_list() + def test_detects_spanish(self) -> None: + result = lang_detect_detect_languages( + "La reunión está programada para el martes 22 de julio de 2014", 0.5 + ) + self.assertIn("es", result) - @parameterized.expand( - [ - param(dt_string="10-10-2021", confidence_threshold=0.5), - ] - ) - def test_lang_detect_doesnt_raise_error(self, dt_string, confidence_threshold): - result = lang_detect_detect_languages(dt_string, confidence_threshold) - assert result == [] + def test_detects_french(self) -> None: + result = lang_detect_detect_languages( + "La réunion est prévue pour le mardi 22 juillet 2014", 0.5 + ) + self.assertIn("fr", result) + + def test_detects_german(self) -> None: + result = lang_detect_detect_languages( + "Das Treffen ist für Dienstag, den 22. Juli 2014 geplant", 0.5 + ) + self.assertIn("de", result) + + def test_handles_numeric_only_input(self) -> None: + result = lang_detect_detect_languages("10-10-2021", 0.5) + self.assertEqual(result, []) + + def test_handles_empty_string(self) -> None: + result = lang_detect_detect_languages("", 0.5) + self.assertEqual(result, []) + + def test_confidence_threshold_filters_results(self) -> None: + # With low threshold, should detect language + result_low = lang_detect_detect_languages("14 June 2020", 0.0) + self.assertGreater(len(result_low), 0) + + # With very high threshold, might not detect anything on short strings + result_high = lang_detect_detect_languages("14 June", 0.99) + # Short strings may have uncertain detection, result_high might be empty + self.assertIsInstance(result_high, list) + + +class LangDetectIntegrationTest(unittest.TestCase): + """Tests for langdetect integration with dateparser""" + + def test_parse_with_langdetect_english(self) -> None: + result = parse( + "Tuesday Jul 22, 2014", + detect_languages_function=lang_detect_detect_languages, + ) + self.assertEqual(result, datetime(2014, 7, 22, 0, 0, 0)) + + def test_parse_with_langdetect_spanish(self) -> None: + result = parse( + "martes 22 de julio de 2014", + detect_languages_function=lang_detect_detect_languages, + ) + assert result is not None + self.assertEqual(result.year, 2014) + self.assertEqual(result.month, 7) + self.assertEqual(result.day, 22) + + def test_parse_with_langdetect_french(self) -> None: + result = parse( + "mardi 22 juillet 2014", + detect_languages_function=lang_detect_detect_languages, + ) + assert result is not None + self.assertEqual(result.year, 2014) + self.assertEqual(result.month, 7) + self.assertEqual(result.day, 22) + + def test_datedataparser_with_langdetect(self) -> None: + ddp = DateDataParser(detect_languages_function=lang_detect_detect_languages) + result = ddp.get_date_data("Tuesday Jul 22, 2014") + self.assertEqual(result["date_obj"], datetime(2014, 7, 22, 0, 0, 0)) + + def test_search_dates_with_langdetect(self) -> None: + result = search_dates( + "The event is on January 3, 2017 and ends February 1st", + detect_languages_function=lang_detect_detect_languages, + ) + assert result is not None + self.assertEqual(len(result), 2) + # Check that dates are found + self.assertEqual(result[0][1], datetime(2017, 1, 3, 0, 0)) + self.assertEqual(result[1][1], datetime(2017, 2, 1, 0, 0)) + + def test_parse_without_langdetect_still_works(self) -> None: + # Ensure dateparser works without custom language detection + result = parse("Tuesday Jul 22, 2014") + self.assertEqual(result, datetime(2014, 7, 22, 0, 0, 0)) + + +class MockLangDetectTest(unittest.TestCase): + """Tests with mocked language detection""" # Mock test for parse, search_dates and DateDataParser + result: object + detect_languages = Mock() detect_languages.return_value = ["en"] # parse - def when_date_is_parsed_using_parse(self, dt_string): - self.result = parse(dt_string, detect_languages_function=detect_languages) + def when_date_is_parsed_using_parse(self, dt_string: str) -> None: + self.result = parse(dt_string, detect_languages_function=self.detect_languages) - def then_date_obj_exactly_is(self, expected_date_obj): + def then_date_obj_exactly_is(self, expected_date_obj: object) -> None: self.assertEqual(expected_date_obj, self.result) @parameterized.expand( @@ -72,14 +141,16 @@ def then_date_obj_exactly_is(self, expected_date_obj): param("Tuesday Jul 22, 2014", datetime(2014, 7, 22, 0, 0, 0)), ] ) - def test_custom_language_detect_mock_parse(self, dt_string, expected_date_obj): + def test_custom_language_detect_mock_parse( + self, dt_string: str, expected_date_obj: datetime + ) -> None: self.when_date_is_parsed_using_parse(dt_string) self.then_date_obj_exactly_is(expected_date_obj) # DateDataParser - def when_date_is_parsed_using_with_datedataparser(self, dt_string): - ddp = DateDataParser(detect_languages_function=detect_languages) + def when_date_is_parsed_using_with_datedataparser(self, dt_string: str) -> None: + ddp = DateDataParser(detect_languages_function=self.detect_languages) self.result = ddp.get_date_data(dt_string)["date_obj"] @parameterized.expand( @@ -88,16 +159,16 @@ def when_date_is_parsed_using_with_datedataparser(self, dt_string): ] ) def test_custom_language_detect_mock_datedataparser( - self, dt_string, expected_date_obj - ): + self, dt_string: str, expected_date_obj: datetime + ) -> None: self.when_date_is_parsed_using_with_datedataparser(dt_string) self.then_date_obj_exactly_is(expected_date_obj) # search_date - def when_date_is_parsed_using_with_search_dates(self, dt_string): + def when_date_is_parsed_using_with_search_dates(self, dt_string: str) -> None: self.result = search_dates( - dt_string, detect_languages_function=detect_languages + dt_string, detect_languages_function=self.detect_languages ) @parameterized.expand( @@ -112,7 +183,7 @@ def when_date_is_parsed_using_with_search_dates(self, dt_string): ] ) def test_custom_language_detect_mock_search_dates( - self, dt_string, expected_date_obj - ): + self, dt_string: str, expected_date_obj: list[tuple[str, datetime]] + ) -> None: self.when_date_is_parsed_using_with_search_dates(dt_string) self.then_date_obj_exactly_is(expected_date_obj) diff --git a/tests/test_languages.py b/tests/test_languages.py index 111ef266b..6908054c5 100644 --- a/tests/test_languages.py +++ b/tests/test_languages.py @@ -1,24 +1,31 @@ import logging from datetime import datetime from io import StringIO +from typing import Any +from unittest.mock import patch import pytest from parameterized import param, parameterized from dateparser import parse -from dateparser.conf import apply_settings, settings +from dateparser.conf import Settings, apply_settings, settings from dateparser.date import DateDataParser from dateparser.languages import Locale, default_loader +from dateparser.languages.dictionary import Dictionary from dateparser.languages.validation import LanguageValidator from dateparser.search import search_dates -from dateparser.search.detection import AutoDetectLanguage, ExactLanguages +from dateparser.search.detection import ( + AutoDetectLanguage, + BaseLanguageDetector, + ExactLanguages, +) from dateparser.utils import normalize_unicode from tests import BaseTestCase class TestLocaleTranslation: @pytest.mark.parametrize( - "date_string,expected,locale,keep_formatting", + ("date_string", "expected", "locale", "keep_formatting"), [ ( "December 04, 1999, 11:04:59 PM", @@ -36,7 +43,9 @@ class TestLocaleTranslation: ("23 März 18:37", "23 march 18:37", "de", False), ], ) - def test_keep_formatting(self, date_string, expected, locale, keep_formatting): + def test_keep_formatting( + self, date_string: str, expected: str, locale: str, keep_formatting: bool + ) -> None: result = default_loader.get_locale(locale).translate( date_string=date_string, keep_formatting=keep_formatting, settings=settings ) @@ -45,14 +54,14 @@ def test_keep_formatting(self, date_string, expected, locale, keep_formatting): class TestBundledLanguages(BaseTestCase): - def setUp(self): + def setUp(self) -> None: super().setUp() - self.language = NotImplemented - self.datetime_string = NotImplemented - self.translation = NotImplemented - self.tokens = NotImplemented - self.result = NotImplemented - self.settings = NotImplemented + self.language: Locale = NotImplemented + self.datetime_string: str = NotImplemented + self.translation: str = NotImplemented + self.tokens: list[str] = NotImplemented + self.result: bool = NotImplemented + self.settings: Settings = NotImplemented @parameterized.expand( [ @@ -74,11 +83,12 @@ def setUp(self): param("zh", "周六 2013年04月08日", "saturday 2013-04-08"), param("zh", "下午3:30", "3:30 pm"), param("zh", "凌晨3:30", "3:30 am"), + param("zh", "下午 02:26:26", "02:26:26 pm"), param("zh", "中午", "12:00"), # French param("fr", "20 Février 2012", "20 february 2012"), param("fr", "Mercredi 19 Novembre 2013", "wednesday 19 november 2013"), - param("fr", "18 octobre 2012 à 19 h 21 min", "18 october 2012 19:21"), + param("fr", "18 octobre 2012 à 19 h 21 min", "18 october 2012 19:21"), # German param("de", "29. Juni 2007", "29. june 2007"), param("de", "Montag 5 Januar, 2015", "monday 5 january 2015"), @@ -107,49 +117,64 @@ def setUp(self): param("it", "Giovedi Maggio 29 2013", "thursday may 29 2013"), param("it", "19 Luglio 2013", "19 july 2013"), # Portuguese - param("pt", "22 de dezembro de 2014 às 02:38", "22 december 2014 02:38"), + param("pt", "22 de dezembro de 2014 às 02:38", "22 december 2014 02:38"), # Russian - param("ru", "5 августа 2014 г. в 12:00", "5 august 2014 year. 12:00"), + param("ru", "5 августа 2014 г. в 12:00", "5 august 2014 year. 12:00"), # Turkish param("tr", "2 Ocak 2015 Cuma, 16:49", "2 january 2015 friday 16:49"), # Czech - param("cs", "22. prosinec 2014 v 2:38", "22. december 2014 2:38"), + param( + "cs", "22. prosinec 2014 v 2:38", "22. december 2014 2:38" + ), # Issue #1302: "v" → "in" → cleared, whitespace preserved # Dutch param( "nl", "maandag 22 december 2014 om 2:38", - "monday 22 december 2014 2:38", + "monday 22 december 2014 2:38", ), # Romanian - param("ro", "22 Decembrie 2014 la 02:38", "22 december 2014 02:38"), + param("ro", "22 Decembrie 2014 la 02:38", "22 december 2014 02:38"), # Polish - param("pl", "4 stycznia o 13:50", "4 january 13:50"), - param("pl", "29 listopada 2014 o 08:40", "29 november 2014 08:40"), + param("pl", "4 stycznia o 13:50", "4 january 13:50"), + param( + "pl", "29 listopada 2014 o 08:40", "29 november 2014 08:40" + ), # Issue #1302: "o" removed, whitespace preserved # Ukrainian - param("uk", "30 листопада 2013 о 04:27", "30 november 2013 04:27"), - param("uk", "22 верес 2021 о 07:37", "22 september 2021 07:37"), - param("uk", "28 лютого 2020 року об 11:57", "28 february 2020 year 11:57"), + param("uk", "30 листопада 2013 о 04:27", "30 november 2013 04:27"), + param("uk", "22 верес 2021 о 07:37", "22 september 2021 07:37"), + param("uk", "28 лютого 2020 року об 11:57", "28 february 2020 year 11:57"), param( "uk", "середу, 28 лютого 2020 року об 11:57", - "wednesday 28 february 2020 year 11:57", + "wednesday 28 february 2020 year 11:57", ), param( "uk", "понед, 12 вересня 2022 року об 09:22", - "monday 12 september 2022 year 09:22", + "monday 12 september 2022 year 09:22", ), # Belarusian - param("be", "5 снежня 2015 г. у 12:00", "5 december 2015 year. 12:00"), - param("be", "11 верасня 2015 г. у 12:11", "11 september 2015 year. 12:11"), - param("be", "3 стд 2015 г. у 10:33", "3 january 2015 year. 10:33"), + param("be", "5 снежня 2015 г. у 12:00", "5 december 2015 year. 12:00"), + param("be", "11 верасня 2015 г. у 12:11", "11 september 2015 year. 12:11"), + param("be", "3 стд 2015 г. у 10:33", "3 january 2015 year. 10:33"), # Arabic param("ar", "6 يناير، 2015، الساعة 05:16 مساءً", "6 january 2015 05:16 pm"), param("ar", "7 يناير، 2015، الساعة 11:00 صباحاً", "7 january 2015 11:00 am"), + param("ar", "الجمعه 5 يونيه 2020", "friday 5 june 2020"), + param("ar", "6 يونية 2020", "6 june 2020"), + param("ar", "7 يوليه 2020", "7 july 2020"), + param("ar", "8 يولية 2020", "8 july 2020"), # Vietnamese param("vi", "Thứ Năm, ngày 8 tháng 1 năm 2015", "thursday 8 january 2015"), - param("vi", "Thứ Tư, 07/01/2015 | 22:34", "wednesday 07/01/2015 22:34"), - param("vi", "9 Tháng 1 2015 lúc 15:08", "9 january 2015 15:08"), + param( + "vi", "Thứ Tư, 07/01/2015 | 22:34", "wednesday 07/01/2015 22:34" + ), # Pipe between spaces preserved + param( + "vi", "9 Tháng 1 2015 lúc 15:08", "9 january 2015 15:08" + ), # Issue #1302: "lúc" removed, whitespace preserved + param( + "vi", "21 tháng 09 năm 2025", "21 september 2025" + ), # Issue #1297: zero-padded month "09" # Thai param( "th", @@ -182,11 +207,13 @@ def setUp(self): param("en", "2014-12-12T12:33:39-08:00", "2014-12-12 12:33:39-08:00"), param("en", "2014-10-15T16:12:20+00:00", "2014-10-15 16:12:20+00:00"), param("en", "28 Oct 2014 16:39:01 +0000", "28 october 2014 16:39:01 +0000"), - param("es", "13 Febrero 2015 a las 23:00", "13 february 2015 23:00"), + param("es", "13 Febrero 2015 a las 23:00", "13 february 2015 23:00"), # Danish param("da", "Sep 03 2014", "september 03 2014"), param("da", "fredag, 03 september 2014", "friday 03 september 2014"), - param("da", "fredag d. 3 september 2014", "friday 3 september 2014"), + param( + "da", "fredag d. 3 september 2014", "friday 3 september 2014" + ), # Issue #1302: 'd.' removed, whitespace preserved # Finnish param("fi", "maanantai tammikuu 16, 2015", "monday january 16 2015"), param("fi", "ma tammi 16, 2015", "monday january 16 2015"), @@ -214,6 +241,9 @@ def setUp(self): param("fi", "su joulu 16, 2015", "sunday december 16 2015"), param("fi", "1. tammikuuta, 2016", "1. january 2016"), param("fi", "tiistaina, 27. lokakuuta 2015", "tuesday 27. october 2015"), + param( + "fi", "28 maalis klo 9:37", "28 march 9:37" + ), # Issue #1302: preserve single space # Japanese param("ja", "午後3時", "pm 3:00"), param("ja", "2時", "2:00"), @@ -236,7 +266,7 @@ def setUp(self): # Hebrew param("he", "20 לאפריל 2012", "20 april 2012"), param("he", "יום רביעי ה-19 בנובמבר 2013", "wednesday 19 november 2013"), - param("he", "18 לאוקטובר 2012 בשעה 19:21", "18 october 2012 19:21"), + param("he", "18 לאוקטובר 2012 בשעה 19:21", "18 october 2012 19:21"), param("he", "יום ה' 6/10/2016", "thursday 6/10/2016"), param("he", "חצות", "12 am"), param("he", "1 אחר חצות", "1 am"), @@ -256,6 +286,8 @@ def setUp(self): # Swedish param("sv", "Sept 03 2014", "september 03 2014"), param("sv", "fredag, 03 september 2014", "friday 03 september 2014"), + param("sv", "den 24:e december 2020", " 24 december 2020"), + param("sv", "1:a januari 2021 10:00", "1 january 2021 10:00"), # af param("af", "5 Mei 2017", "5 may 2017"), param( @@ -333,6 +365,17 @@ def setUp(self): # bs-Cyrl param("bs-Cyrl", "2 септембар 2000, четвртак", "2 september 2000 thursday"), param("bs-Cyrl", "1 јули 1987 9:25 поподне", "1 july 1987 9:25 pm"), + param("bs-Cyrl", "1 јули 1987 9:25 послијеподне", "1 july 1987 9:25 pm"), + param( + "bs-Cyrl", + "понедјељак, 1 јули 1987 9:25 пријеподне", + "monday 1 july 1987 9:25 am", + ), + param( + "bs-Cyrl", + "недјеља, 2 септембар 2000 7:00 послијеподне", + "sunday 2 september 2000 7:00 pm", + ), # bs-Latn param("bs-Latn", "23 septembar 1879, petak", "23 september 1879 friday"), param( @@ -483,7 +526,7 @@ def setUp(self): param("hr", "2 ožujak 1980 pet", "2 march 1980 friday"), param("hr", "nedjelja 3 lis 1879", "sunday 3 october 1879"), param("hr", "06. travnja 2021.", "06. april 2021."), - param("hr", "13. svibanj 2022. u 14:34", "13. may 2022. 14:34"), + param("hr", "13. svibanj 2022. u 14:34", "13. may 2022. 14:34"), param("hr", "20. studenoga 2010. @ 07:28", "20. november 2010. 07:28"), param("hr", "13. studenog 1989.", "13. november 1989."), param("hr", "u listopadu 2056.", " october 2056."), @@ -1067,7 +1110,9 @@ def setUp(self): param("zu", "son 23 umasingana 1996", "sunday 23 january 1996"), ] ) - def test_translation(self, shortname, datetime_string, expected_translation): + def test_translation( + self, shortname: str, datetime_string: str, expected_translation: str + ) -> None: self.given_settings() self.given_bundled_language(shortname) self.given_string(datetime_string) @@ -1115,6 +1160,12 @@ def test_translation(self, shortname, datetime_string, expected_translation): param("it", "oggi", "0 day ago"), param("it", "2 settimana fa", "2 week ago"), param("it", "2 anno fa", "2 year ago"), + param("it", "un ora fa", "1 hour ago"), + param("it", "un'ora fa", "1 hour ago"), + param("it", "oggi alle 11:00", "0 day ago 11:00"), + param("it", "oggi 11:00", "0 day ago 11:00"), + # "un'ora" simplification must not corrupt words like "orario" + param("it", "un orario", "un orario"), # Portuguese param("pt", "anteontem", "2 day ago"), param("pt", "ontem", "1 day ago"), @@ -1163,6 +1214,28 @@ def test_translation(self, shortname, datetime_string, expected_translation): param("cs", "40 sekunda", "40 second"), param("cs", "4 týden", "4 week"), param("cs", "14 roků", "14 year"), + param("cs", "20 let", "20 year"), + param("cs", "pět minut", "5 minute"), + param("cs", "před šesti minutami", "6 minute ago"), + param("cs", "sedmého ledna loni", "7. january 1 year ago"), + param("cs", "včera", "1 day ago"), + param("cs", "předevčírem", "2 day ago"), + param("cs", "dnes", "0 day ago"), + param("cs", "teď", "0 second ago"), + param("cs", "před rokem", "ago 1 year"), + param("cs", "prvního ledna 2021 v půl šesté", "1. january 2021 5:30"), + param("cs", "desátého šestý", "10. 6."), + param("cs", "za dvacet let", "in 20 year"), + param("cs", "za čtrnáct dní", "in 14 day"), + param("cs", "čtvrt na tři", "2:15"), + param("cs", "zítra o půlnoci", "in 1 day 0:00"), + param("cs", "v sedum třicet odpoledne", " 7 30 pm"), + param("cs", "za měsíc", "in 1 month"), + param("cs", "za týden", "in 1 week"), + param("cs", "za rok", "in 1 year"), + param("cs", "v lednu", " january"), + param("cs", "v červenci 2020", " july 2020"), + param("cs", "v únoru", " february"), # Chinese param("zh", "昨天", "1 day ago"), param("zh", "前天", "2 day ago"), @@ -1190,13 +1263,17 @@ def test_translation(self, shortname, datetime_string, expected_translation): param("ar", "يومين", "2 day"), param("ar", "أمس", "1 day ago"), param("ar", "4 عام", "4 year"), + param("ar", "4 السنه", "4 year"), + param("ar", "منذ 3 ثانيه", "ago 3 second"), param("ar", "منذ 2 ساعات", "ago 2 hour"), param("ar", "منذ ساعتين", "ago 2 hour"), param("ar", "اليوم السابق", "1 day ago"), param("ar", "اليوم", "0 day ago"), # Polish param("pl", "2 godz.", "2 hour."), - param("pl", "Wczoraj o 07:40", "1 day ago 07:40"), + param( + "pl", "Wczoraj o 07:40", "1 day ago 07:40" + ), # Issue #1302: fixed double space # Vietnamese param("vi", "2 tuần 3 ngày", "2 week 3 day"), param("vi", "21 giờ trước", "21 hour ago"), @@ -1235,10 +1312,10 @@ def test_translation(self, shortname, datetime_string, expected_translation): param("id", "hari ini", "0 day ago"), param("id", "kemarin", "1 day ago"), param("id", "kemarin lusa", "2 day ago"), - param("id", "sehari yang lalu", "1 day ago"), - param("id", "seminggu yang lalu", "1 week ago"), - param("id", "sebulan yang lalu", "1 month ago"), - param("id", "setahun yang lalu", "1 year ago"), + param("id", "sehari yang lalu", "1 day ago"), + param("id", "seminggu yang lalu", "1 week ago"), + param("id", "sebulan yang lalu", "1 month ago"), + param("id", "setahun yang lalu", "1 year ago"), # Finnish param("fi", "1 vuosi sitten", "1 year ago"), param("fi", "2 vuotta sitten", "2 year ago"), @@ -1306,7 +1383,9 @@ def test_translation(self, shortname, datetime_string, expected_translation): param("ja", "明後日", "in 2 day"), # Hebrew param("he", "אתמול", "1 day ago"), - param("he", "אתמול בשעה 3", "1 day ago 3"), + param( + "he", "אתמול בשעה 3", "1 day ago 3" + ), # Issue #1302: "בשעה" removed, whitespace preserved param("he", "היום", "0 day ago"), param("he", "לפני יומיים", "2 day ago"), param("he", "לפני שבועיים", "2 week ago"), @@ -1395,6 +1474,17 @@ def test_translation(self, shortname, datetime_string, expected_translation): param("bs-Cyrl", "следећег месеца", "in 1 month"), param("bs-Cyrl", "прошле године 10:05 пре подне", "1 year ago 10:05 am"), param("bs-Cyrl", "пре 28 недеља", "28 week ago"), + param("bs-Cyrl", "сљедећи мјесец", "in 1 month"), + param("bs-Cyrl", "сљедеће седмице", "in 1 week"), + param("bs-Cyrl", "сљедеће године", "in 1 year"), + param("bs-Cyrl", "прије 4 мјесеца", "4 month ago"), + param("bs-Cyrl", "прије 2 седмице", "2 week ago"), + param("bs-Cyrl", "прошли мјесец", "1 month ago"), + param("bs-Cyrl", "прошле седмице", "1 week ago"), + param("bs-Cyrl", "овај мјесец", "0 month ago"), + param("bs-Cyrl", "ове седмице", "0 week ago"), + param("bs-Cyrl", "за 2 мјесеца", "in 2 month"), + param("bs-Cyrl", "за 3 седмице", "in 3 week"), # bs-Latn param("bs-Latn", "sljedeće godine", "in 1 year"), param("bs-Latn", "prije 4 mjeseci", "4 month ago"), @@ -1405,6 +1495,8 @@ def test_translation(self, shortname, datetime_string, expected_translation): param("bs", "ovaj sat", "0 hour ago"), # ca param("ca", "d'aquí a 22 hores", "in 22 hour"), + # standalone hour unit, added from the CLDR "duration-hour" unit data + param("ca", "2 hores", "2 hour"), param("ca", "fa 17 anys", "17 year ago"), param("ca", "el mes passat", "1 month ago"), param("ca", "la pròxima setmana", "in 1 week"), @@ -1672,7 +1764,7 @@ def test_translation(self, shortname, datetime_string, expected_translation): # km param("km", "ម៉ោងនេះ", "0 hour ago"), param("km", "19 ខែមុន", "19 month ago"), - param("km", "ក្នុង​រយៈ​ពេល 23 ម៉ោង", "in 23 hour"), + param("km", "ក្នុង\u200bរយៈ\u200bពេល 23 ម៉ោង", "in 23 hour"), # kn param("kn", "18 ತಿಂಗಳುಗಳ ಹಿಂದೆ", "18 month ago"), param("kn", "26 ಸೆಕೆಂಡ್‌ನಲ್ಲಿ", "in 26 second"), @@ -1681,6 +1773,11 @@ def test_translation(self, shortname, datetime_string, expected_translation): param("ko", "2분 후", "in 2 minute"), param("ko", "5년 전", "5 year ago"), param("ko", "다음 달", "in 1 month"), + param("ko", "금일", "0 day ago"), + param("ko", "작일", "1 day ago"), + param("ko", "명일", "in 1 day"), + param("ko", "3달 전", "3 month ago"), + param("ko", "2달 후", "in 2 month"), # ksb param("ksb", "keloi", "in 1 day"), param("ksb", "evi eo", "0 day ago"), @@ -1792,6 +1889,13 @@ def test_translation(self, shortname, datetime_string, expected_translation): param("nb", "2 uker siden", "2 week ago"), param("nb", "1 uke siden", "1 week ago"), param("nb", "10 timer siden", "10 hour ago"), + param("nb", "3 måneder siden", "3 month ago"), + param("nb", "2 dager siden", "2 day ago"), + param("nb", "5 uker siden", "5 week ago"), + param("nb", "30 minutter siden", "30 minute ago"), + param("nb", "45 sekunder siden", "45 second ago"), + param("nb", "om 3 uker", "in 3 week"), + param("nb", "om 2 måneder", "in 2 month"), # nd param("nd", "kusasa", "in 1 day"), param("nd", "izolo", "1 day ago"), @@ -2013,8 +2117,8 @@ def test_translation(self, shortname, datetime_string, expected_translation): ] ) def test_freshness_translation( - self, shortname, datetime_string, expected_translation - ): + self, shortname: str, datetime_string: str, expected_translation: str + ) -> None: self.given_settings(settings={"NORMALIZE": False}) # Finnish language use "t" as hour, so empty SKIP_TOKENS. if shortname == "fi": @@ -2302,7 +2406,9 @@ def test_freshness_translation( param("naq", "13 ǃkhanǀgôab 1887", ["13", " ", "ǃkhanǀgôab", " ", "1887"]), ] ) - def test_split(self, shortname, datetime_string, expected_tokens): + def test_split( + self, shortname: str, datetime_string: str, expected_tokens: list[str] + ) -> None: self.given_settings(settings={"NORMALIZE": False}) self.given_bundled_language(shortname) self.given_string(datetime_string) @@ -2333,7 +2439,9 @@ def test_split(self, shortname, datetime_string, expected_tokens): param("bn", "3 সপ্তাহ", strip_timezone=False), ] ) - def test_applicable_languages(self, shortname, datetime_string, strip_timezone): + def test_applicable_languages( + self, shortname: str, datetime_string: str, strip_timezone: bool + ) -> None: self.given_settings() self.given_bundled_language(shortname) self.given_string(datetime_string) @@ -2348,50 +2456,131 @@ def test_applicable_languages(self, shortname, datetime_string, strip_timezone): param("cs", "3 hafta", strip_timezone=False), ] ) - def test_not_applicable_languages(self, shortname, datetime_string, strip_timezone): + def test_not_applicable_languages( + self, shortname: str, datetime_string: str, strip_timezone: bool + ) -> None: self.given_settings() self.given_bundled_language(shortname) self.given_string(datetime_string) self.when_datetime_string_checked_if_applicable(strip_timezone) self.then_language_is_not_applicable() + @parameterized.expand( + [ + # Dates wrapped in text the locale does not recognize (issue #518). + param("fr", "actualisé le 17 avril 2019"), + param("fr", "publié le 16 avril 2019"), + param("en", "published on 16 april 2019"), + param("en", "xx 16/04/2019 yy"), + ] + ) + def test_applicable_languages_when_ignoring_surrounding_text( + self, shortname: str, datetime_string: str + ) -> None: + self.given_settings() + self.given_bundled_language(shortname) + self.given_string(datetime_string) + self.when_datetime_string_checked_if_applicable_ignoring_surrounding_text() + self.then_language_is_applicable() + + @parameterized.expand( + [ + # An unrecognized token inside the date keeps the locale + # inapplicable: only the edges may be ignored. + param("fr", "17 foobar avril 2019"), + # Nothing is left when every token is unrecognized. + param("en", "hello world"), + ] + ) + def test_not_applicable_languages_when_ignoring_surrounding_text( + self, shortname: str, datetime_string: str + ) -> None: + self.given_settings() + self.given_bundled_language(shortname) + self.given_string(datetime_string) + self.when_datetime_string_checked_if_applicable_ignoring_surrounding_text() + self.then_language_is_not_applicable() + + @parameterized.expand( + [ + # The result is the same as translating the date without the + # surrounding text. + param("fr", "actualisé le 17 avril 2019", " 17 april 2019"), + param("en", "published on 16 april 2019", " 16 april 2019"), + param("en", "xx 16/04/2019 yy", "16/04/2019"), + # A recognized timezone at the trailing edge is kept, so the offset + # is not discarded; the result matches the unwrapped translation. + param( + "en", + "updated 23 march 2000 1:21 pm est", + "23 march 2000 1:21 pm est", + ), + ] + ) + def test_translation_when_ignoring_surrounding_text( + self, shortname: str, datetime_string: str, expected_translation: str + ) -> None: + self.given_settings() + self.given_bundled_language(shortname) + self.given_string(datetime_string) + self.when_datetime_string_translated_ignoring_surrounding_text() + self.then_string_translated_to(expected_translation) + @apply_settings - def given_settings(self, settings=None): + def given_settings(self, settings: Settings | dict[str, Any] | None = None) -> None: + assert isinstance(settings, Settings) self.settings = settings - def given_string(self, datetime_string): + def given_string(self, datetime_string: str) -> None: if self.settings.NORMALIZE: datetime_string = normalize_unicode(datetime_string) self.datetime_string = datetime_string - def given_bundled_language(self, shortname): + def given_bundled_language(self, shortname: str) -> None: self.language = default_loader.get_locale(shortname) - def when_datetime_string_translated(self): + def when_datetime_string_translated(self) -> None: self.translation = self.language.translate( self.datetime_string, settings=self.settings ) - def when_datetime_string_splitted(self, keep_formatting=False): + def when_datetime_string_splitted(self, keep_formatting: bool = False) -> None: self.tokens = self.language._get_dictionary(self.settings).split( self.datetime_string ) - def when_datetime_string_checked_if_applicable(self, strip_timezone): + def when_datetime_string_checked_if_applicable(self, strip_timezone: bool) -> None: self.result = self.language.is_applicable( self.datetime_string, strip_timezone, settings=self.settings ) - def then_string_translated_to(self, expected_string): + def when_datetime_string_checked_if_applicable_ignoring_surrounding_text( + self, + ) -> None: + self.result = self.language.is_applicable( + self.datetime_string, + strip_timezone=False, + settings=self.settings, + ignore_surrounding_text=True, + ) + + def when_datetime_string_translated_ignoring_surrounding_text(self) -> None: + self.translation = self.language.translate( + self.datetime_string, + settings=self.settings, + ignore_surrounding_text=True, + ) + + def then_string_translated_to(self, expected_string: str) -> None: self.assertEqual(expected_string, self.translation) - def then_tokens_are(self, expected_tokens): + def then_tokens_are(self, expected_tokens: list[str]) -> None: self.assertEqual(expected_tokens, self.tokens) - def then_language_is_applicable(self): + def then_language_is_applicable(self) -> None: self.assertTrue(self.result) - def then_language_is_not_applicable(self): + def then_language_is_not_applicable(self) -> None: self.assertFalse(self.result) @@ -2400,19 +2589,21 @@ class BaseLanguageDetectorTestCase(BaseTestCase): NOT_DETECTED = object() - def setUp(self): + def setUp(self) -> None: super().setUp() - self.datetime_string = NotImplemented - self.detector = NotImplemented - self.detected_language = NotImplemented - self.known_languages = None + self.datetime_string: str = NotImplemented + self.detector: BaseLanguageDetector = NotImplemented + self.detected_language: object = NotImplemented + self.known_languages: list[Locale] | None = None @parameterized.expand( [ param("1 january 2015", "en"), ] ) - def test_valid_dates_detected(self, datetime_string, expected_language): + def test_valid_dates_detected( + self, datetime_string: str, expected_language: str + ) -> None: self.given_locales(expected_language) self.given_detector() self.given_settings() @@ -2425,7 +2616,7 @@ def test_valid_dates_detected(self, datetime_string, expected_language): param("foo"), ] ) - def test_invalid_dates_not_detected(self, datetime_string): + def test_invalid_dates_not_detected(self, datetime_string: str) -> None: self.given_locales("en") self.given_detector() self.given_settings() @@ -2433,7 +2624,7 @@ def test_invalid_dates_not_detected(self, datetime_string): self.when_searching_for_first_applicable_language() self.then_no_language_was_detected() - def test_invalid_date_after_valid_date_not_detected(self): + def test_invalid_date_after_valid_date_not_detected(self) -> None: self.given_settings() self.given_locales("en") self.given_detector() @@ -2442,7 +2633,7 @@ def test_invalid_date_after_valid_date_not_detected(self): self.when_searching_for_first_applicable_language() self.then_no_language_was_detected() - def test_valid_date_after_invalid_date_detected(self): + def test_valid_date_after_invalid_date_detected(self) -> None: self.given_locales("en") self.given_settings() self.given_detector() @@ -2451,28 +2642,29 @@ def test_valid_date_after_invalid_date_detected(self): self.when_searching_for_first_applicable_language() self.then_language_was_detected("en") - def given_locales(self, *shortnames): + def given_locales(self, *shortnames: str) -> None: self.known_languages = [ default_loader.get_locale(shortname) for shortname in shortnames ] @apply_settings - def given_settings(self, settings=None): + def given_settings(self, settings: Settings | dict[str, Any] | None = None) -> None: + assert isinstance(settings, Settings) self.settings = settings - def given_previously_detected_string(self, datetime_string): + def given_previously_detected_string(self, datetime_string: str) -> None: for _ in self.detector.iterate_applicable_languages( datetime_string, modify=True, settings=self.settings ): break - def given_string(self, datetime_string): + def given_string(self, datetime_string: str) -> None: self.datetime_string = datetime_string - def given_detector(self): + def given_detector(self) -> None: raise NotImplementedError - def when_searching_for_first_applicable_language(self): + def when_searching_for_first_applicable_language(self) -> None: for language in self.detector.iterate_applicable_languages( self.datetime_string, modify=True, settings=self.settings ): @@ -2481,13 +2673,14 @@ def when_searching_for_first_applicable_language(self): else: self.detected_language = self.NOT_DETECTED - def then_language_was_detected(self, shortname): + def then_language_was_detected(self, shortname: str) -> None: self.assertIsInstance( self.detected_language, Locale, "Language was not properly detected" ) + assert isinstance(self.detected_language, Locale) self.assertEqual(shortname, self.detected_language.shortname) - def then_no_language_was_detected(self): + def then_no_language_was_detected(self) -> None: self.assertIs(self.detected_language, self.NOT_DETECTED) @@ -2502,7 +2695,7 @@ class TestExactLanguages(BaseLanguageDetectorTestCase): param("01-01-12", ["en"]), ] ) - def test_exact_languages(self, datetime_string, shortnames): + def test_exact_languages(self, datetime_string: str, shortnames: list[str]) -> None: self.given_settings() self.given_string(datetime_string) self.given_known_languages(shortnames) @@ -2510,25 +2703,27 @@ def test_exact_languages(self, datetime_string, shortnames): self.when_using_exact_languages() self.then_exact_languages_were_filtered(shortnames) - def test_none_raises_value_error(self): + def test_none_raises_value_error(self) -> None: with self.assertRaisesRegex( ValueError, r"language cannot be None for ExactLanguages" ): ExactLanguages(None) @apply_settings - def given_settings(self, settings=None): + def given_settings(self, settings: Settings | dict[str, Any] | None = None) -> None: + assert isinstance(settings, Settings) self.settings = settings - def given_known_languages(self, shortnames): + def given_known_languages(self, shortnames: list[str]) -> None: self.known_languages = [ default_loader.get_locale(shortname) for shortname in shortnames ] - def given_detector(self): + def given_detector(self) -> None: self.assertIsInstance( self.known_languages, list, "Require a list of languages to initialize" ) + assert self.known_languages is not None self.assertGreaterEqual( len(self.known_languages), 1, @@ -2536,27 +2731,29 @@ def given_detector(self): ) self.detector = ExactLanguages(languages=self.known_languages) - def when_using_exact_languages(self): + def when_using_exact_languages(self) -> None: self.exact_languages = self.detector.iterate_applicable_languages( self.datetime_string, modify=True, settings=self.settings ) - def then_exact_languages_were_filtered(self, shortnames): + def then_exact_languages_were_filtered(self, shortnames: list[str]) -> None: self.assertEqual( set(shortnames), {lang.shortname for lang in self.exact_languages} ) class BaseAutoDetectLanguageDetectorTestCase(BaseLanguageDetectorTestCase): - allow_redetection = NotImplemented + allow_redetection: bool = NotImplemented - def given_detector(self): + def given_detector(self) -> None: + assert self.known_languages is not None self.detector = AutoDetectLanguage( languages=self.known_languages, allow_redetection=self.allow_redetection ) @apply_settings - def given_settings(self, settings=None): + def given_settings(self, settings: Settings | dict[str, Any] | None = None) -> None: + assert isinstance(settings, Settings) self.settings = settings @@ -2575,16 +2772,15 @@ class TestAutoDetectLanguageDetectorWithRedetection( class TestLanguageValidatorWhenInvalid(BaseTestCase): - def setUp(self): + def setUp(self) -> None: super().setUp() self.validator = LanguageValidator self.captured_logs = StringIO() - self.validator.get_logger() self.sh = logging.StreamHandler(self.captured_logs) - self.validator.logger.addHandler(self.sh) + self.validator.get_logger().addHandler(self.sh) self.log_list = self.captured_logs.getvalue().split("\n")[0] - def get_log_str(self): + def get_log_str(self) -> str: return self.captured_logs.getvalue().split("\n")[0] @parameterized.expand( @@ -2596,7 +2792,9 @@ def get_log_str(self): ), ] ) - def test_validate_info_when_invalid_type(self, lang_id, lang_info, log_msg): + def test_validate_info_when_invalid_type( + self, lang_id: str, lang_info: object, log_msg: str + ) -> None: result = self.validator.validate_info(lang_id, lang_info) self.assertEqual(log_msg, self.get_log_str()) self.assertFalse(result) @@ -2608,7 +2806,9 @@ def test_validate_info_when_invalid_type(self, lang_id, lang_info, log_msg): param("en", {"name": ""}, log_msg="Language 'en' does not have a name"), ] ) - def test_validate_name_when_invalid(self, lang_id, lang_info, log_msg): + def test_validate_name_when_invalid( + self, lang_id: str, lang_info: dict[str, Any], log_msg: str + ) -> None: result = self.validator._validate_name(lang_id, lang_info) self.assertEqual(log_msg, self.get_log_str()) self.assertFalse(result) @@ -2623,7 +2823,9 @@ def test_validate_name_when_invalid(self, lang_id, lang_info, log_msg): ), ] ) - def test_validate_word_spacing_when_invalid(self, lang_id, lang_info, log_msg): + def test_validate_word_spacing_when_invalid( + self, lang_id: str, lang_info: dict[str, Any], log_msg: str + ) -> None: result = self.validator._validate_word_spacing(lang_id, lang_info) self.assertEqual(log_msg, self.get_log_str()) self.assertFalse(result) @@ -2644,7 +2846,9 @@ def test_validate_word_spacing_when_invalid(self, lang_id, lang_info, log_msg): ), ] ) - def test_validate_skip_list_when_invalid(self, lang_id, lang_info, log_msg): + def test_validate_skip_list_when_invalid( + self, lang_id: str, lang_info: dict[str, Any], log_msg: str + ) -> None: result = self.validator._validate_skip_list(lang_id, lang_info) self.assertEqual(log_msg, self.get_log_str()) self.assertFalse(result) @@ -2654,7 +2858,9 @@ def test_validate_skip_list_when_invalid(self, lang_id, lang_info, log_msg): param("en", {}), ] ) - def test_validate_skip_list_when_absent(self, lang_id, lang_info): + def test_validate_skip_list_when_absent( + self, lang_id: str, lang_info: dict[str, Any] + ) -> None: result = self.validator._validate_skip_list(lang_id, lang_info) self.assertTrue(result) @@ -2672,7 +2878,9 @@ def test_validate_skip_list_when_absent(self, lang_id, lang_info): ), ] ) - def test_validate_pertain_list_when_invalid(self, lang_id, lang_info, log_msg): + def test_validate_pertain_list_when_invalid( + self, lang_id: str, lang_info: dict[str, Any], log_msg: str + ) -> None: result = self.validator._validate_pertain_list(lang_id, lang_info) self.assertEqual(log_msg, self.get_log_str()) self.assertFalse(result) @@ -2682,7 +2890,9 @@ def test_validate_pertain_list_when_invalid(self, lang_id, lang_info, log_msg): param("en", {}), ] ) - def test_validate_pertain_list_when_absent(self, lang_id, lang_info): + def test_validate_pertain_list_when_absent( + self, lang_id: str, lang_info: dict[str, Any] + ) -> None: result = self.validator._validate_pertain_list(lang_id, lang_info) self.assertTrue(result) @@ -2721,7 +2931,9 @@ def test_validate_pertain_list_when_absent(self, lang_id, lang_info): ), ] ) - def test_validate_weekdays_when_invalid(self, lang_id, lang_info, log_msg): + def test_validate_weekdays_when_invalid( + self, lang_id: str, lang_info: dict[str, Any], log_msg: str + ) -> None: result = self.validator._validate_weekdays(lang_id, lang_info) self.assertEqual(log_msg, self.get_log_str()) self.assertFalse(result) @@ -2771,7 +2983,9 @@ def test_validate_weekdays_when_invalid(self, lang_id, lang_info, log_msg): ), ] ) - def test_validate_months_when_invalid(self, lang_id, lang_info, log_msg): + def test_validate_months_when_invalid( + self, lang_id: str, lang_info: dict[str, Any], log_msg: str + ) -> None: result = self.validator._validate_months(lang_id, lang_info) self.assertEqual(log_msg, self.get_log_str()) self.assertFalse(result) @@ -2811,7 +3025,9 @@ def test_validate_months_when_invalid(self, lang_id, lang_info, log_msg): ), ] ) - def test_validate_units_when_invalid(self, lang_id, lang_info, log_msg): + def test_validate_units_when_invalid( + self, lang_id: str, lang_info: dict[str, Any], log_msg: str + ) -> None: result = self.validator._validate_units(lang_id, lang_info) self.assertEqual(log_msg, self.get_log_str()) self.assertFalse(result) @@ -2839,7 +3055,9 @@ def test_validate_units_when_invalid(self, lang_id, lang_info, log_msg): ), ] ) - def test_validate_other_words_when_invalid(self, lang_id, lang_info, log_msg="na"): + def test_validate_other_words_when_invalid( + self, lang_id: str, lang_info: dict[str, Any], log_msg: str = "na" + ) -> None: result = self.validator._validate_other_words(lang_id, lang_info) self.assertEqual(log_msg, self.get_log_str()) self.assertFalse(result) @@ -2849,7 +3067,9 @@ def test_validate_other_words_when_invalid(self, lang_id, lang_info, log_msg="na param("en", {}), ] ) - def test_validate_simplifications_when_absent(self, lang_id, lang_info): + def test_validate_simplifications_when_absent( + self, lang_id: str, lang_info: dict[str, Any] + ) -> None: result = self.validator._validate_simplifications(lang_id, lang_info) self.assertTrue(result) @@ -2903,7 +3123,9 @@ def test_validate_simplifications_when_absent(self, lang_id, lang_info): ), ] ) - def test_validate_simplifications_when_invalid(self, lang_id, lang_info, log_msg): + def test_validate_simplifications_when_invalid( + self, lang_id: str, lang_info: dict[str, Any], log_msg: str + ) -> None: result = self.validator._validate_simplifications(lang_id, lang_info) self.assertEqual(log_msg, self.get_log_str()) self.assertFalse(result) @@ -2925,8 +3147,8 @@ def test_validate_simplifications_when_invalid(self, lang_id, lang_info, log_msg ] ) def test_validate_sentence_splitter_group_when_invalid( - self, lang_id, lang_info, log_msg - ): + self, lang_id: str, lang_info: dict[str, Any], log_msg: str + ) -> None: result = self.validator._validate_sentence_splitter_group(lang_id, lang_info) self.assertEqual(log_msg, self.get_log_str()) self.assertFalse(result) @@ -2940,7 +3162,9 @@ def test_validate_sentence_splitter_group_when_invalid( ), ] ) - def test_validate_extra_keys_when_invalid(self, lang_id, lang_info, log_msg): + def test_validate_extra_keys_when_invalid( + self, lang_id: str, lang_info: dict[str, Any], log_msg: str + ) -> None: result = self.validator._validate_extra_keys(lang_id, lang_info) self.assertEqual(log_msg, self.get_log_str()) self.assertFalse(result) @@ -2956,8 +3180,12 @@ def test_validate_extra_keys_when_invalid(self, lang_id, lang_info, log_msg): ] ) def test_parse_settings_default_languages( - self, date_string, languages, settings, expected - ): + self, + date_string: str, + languages: list[str], + settings: dict[str, Any], + expected: datetime, + ) -> None: result = parse(date_string, languages=languages, settings=settings) assert result == expected @@ -2972,8 +3200,12 @@ def test_parse_settings_default_languages( ] ) def test_date_data_parser_settings_default_languages( - self, date_string, languages, settings, expected - ): + self, + date_string: str, + languages: list[str], + settings: dict[str, Any], + expected: datetime, + ) -> None: ddp = DateDataParser(languages=languages, settings=settings) result = ddp.get_date_data(date_string) assert result.date_obj == expected @@ -2988,8 +3220,11 @@ def test_date_data_parser_settings_default_languages( ] ) def test_search_dates_settings_default_languages( - self, date_string, settings, expected - ): + self, + date_string: str, + settings: dict[str, Any], + expected: list[tuple[str, datetime]], + ) -> None: result = search_dates(date_string, settings=settings) assert result == expected @@ -2997,8 +3232,8 @@ def test_search_dates_settings_default_languages( [param(date_string="RANDOM_WORD ", settings={"DEFAULT_LANGUAGES": ["en"]})] ) def test_parse_settings_default_languages_no_language_detect( - self, date_string, settings - ): + self, date_string: str, settings: dict[str, Any] + ) -> None: result = parse(date_string, settings=settings) assert result is None @@ -3013,7 +3248,42 @@ def test_parse_settings_default_languages_no_language_detect( ] ) def test_parse_settings_default_languages_with_detected_language( - self, date_string, languages, expected, settings - ): + self, + date_string: str, + languages: list[str], + expected: datetime, + settings: dict[str, Any], + ) -> None: result = parse(date_string, languages=languages, settings=settings) assert result == expected + + +class TestNoWordSpacingSecurity: + def test_dictionary_does_not_evaluate_no_word_spacing(self) -> None: + locale_info = { + "name": "Test", + "skip": [], + "pertain": [], + "relative-type": {}, + "relative-type-regex": {}, + "no_word_spacing": "__import__('os').system('echo vulnerable')", + } + + with patch("os.system") as os_system: + Dictionary(locale_info, settings=settings) + + os_system.assert_not_called() + + def test_locale_does_not_evaluate_no_word_spacing(self) -> None: + language_info = { + "name": "Test", + "simplifications": [{"x": "y"}], + "no_word_spacing": "__import__('os').system('echo vulnerable')", + } + + with patch("os.system") as os_system: + locale = Locale("xx", language_info) + simplifications = locale._get_simplifications(settings=settings) + + os_system.assert_not_called() + assert simplifications diff --git a/tests/test_loading.py b/tests/test_loading.py index b79db98f9..40d7bc7bd 100644 --- a/tests/test_loading.py +++ b/tests/test_loading.py @@ -1,22 +1,31 @@ from operator import attrgetter +from typing import TYPE_CHECKING import regex as re from parameterized import param, parameterized -from dateparser.languages.loader import default_loader +from dateparser.languages.loader import LocaleDataLoader, default_loader from tests import BaseTestCase +if TYPE_CHECKING: + from collections import OrderedDict + from collections.abc import Iterator + + from dateparser.languages.locale import Locale + class TestLoading(BaseTestCase): - def setUp(self): + data_loader: LocaleDataLoader + + def setUp(self) -> None: super().setUp() - self.locale_generator = NotImplemented + self.locale_generator: Iterator[Locale] = NotImplemented @classmethod - def setUpClass(cls): + def setUpClass(cls) -> None: cls.data_loader = default_loader - cls.data_loader._loaded_locales = {} - cls.data_loader._loaded_languages = {} + cls.data_loader._loaded_locales.clear() + cls.data_loader._loaded_languages.clear() @parameterized.expand( [ @@ -190,17 +199,67 @@ def setUpClass(cls): ], expected_locales=["shi-Latn", "teo-KE", "ewo", "vun"], ), + param( + given_languages=["en"], + given_locales=None, + given_region="US", + loaded_languages=[ + "en", + "es", + "fr", + "ar", + "asa", + "nl", + "so", + "sr-Latn", + "zgh", + "pt", + "zh-Hant", + "zh-Hans", + "ru", + "ckb", + "sq", + "shi-Latn", + "teo", + "ewo", + "vun", + ], + loaded_locales=[ + "en", + "es", + "fr", + "fr-BF", + "ar-SO", + "asa", + "nl-CW", + "so-KE", + "sr-Latn-XK", + "zgh", + "pt-MO", + "zh-Hant-MO", + "zh-Hans-MO", + "ru-UA", + "ckb-IR", + "sq-XK", + "shi-Latn", + "teo-KE", + "ewo", + "vun", + "en-US", + ], + expected_locales=["en-US"], + ), ] ) def test_loading( self, - given_languages, - given_locales, - given_region, - loaded_languages, - loaded_locales, - expected_locales, - ): + given_languages: list[str] | None, + given_locales: list[str] | None, + given_region: str | None, + loaded_languages: list[str], + loaded_locales: list[str], + expected_locales: list[str], + ) -> None: self.load_data( languages=given_languages, locales=given_locales, region=given_region ) @@ -208,20 +267,25 @@ def test_loading( self.then_loaded_languages_are(loaded_languages) self.then_loaded_locales_are(loaded_locales) - def load_data(self, languages, locales, region): + def load_data( + self, + languages: list[str] | None, + locales: list[str] | None, + region: str | None, + ) -> None: self.locale_generator = self.data_loader.get_locales( languages=languages, locales=locales, region=region, use_given_order=True ) - def then_loaded_languages_are(self, loaded_languages): + def then_loaded_languages_are(self, loaded_languages: list[str]) -> None: self.assertCountEqual( loaded_languages, self.data_loader._loaded_languages.keys() ) - def then_loaded_locales_are(self, loaded_locales): + def then_loaded_locales_are(self, loaded_locales: list[str]) -> None: self.assertCountEqual(loaded_locales, self.data_loader._loaded_locales.keys()) - def then_locales_are_yielded_in_order(self, expected_locales): + def then_locales_are_yielded_in_order(self, expected_locales: list[str]) -> None: self.assertEqual( list(map(attrgetter("shortname"), list(self.locale_generator))), expected_locales, @@ -232,11 +296,11 @@ class TestLocaleDataLoader(BaseTestCase): UNKNOWN_LANGUAGES_EXCEPTION_RE = re.compile(r"Unknown language\(s\): (.+)") UNKNOWN_LOCALES_EXCEPTION_RE = re.compile(r"Unknown locale\(s\): (.+)") - def setUp(self): + def setUp(self) -> None: super().setUp() self.data_loader = default_loader - self.data_loader._loaded_languages = {} - self.data_loader._loaded_locales = {} + self.data_loader._loaded_languages.clear() + self.data_loader._loaded_locales.clear() @parameterized.expand( [ @@ -246,7 +310,7 @@ def setUp(self): param(given_locales=["tl", "nl-SX", "de-BE"]), ] ) - def test_loading_with_given_order(self, given_locales): + def test_loading_with_given_order(self, given_locales: list[str]) -> None: self.load_data(given_locales, use_given_order=True) self.then_locales_are_yielded_in_order(given_locales) @@ -263,7 +327,9 @@ def test_loading_with_given_order(self, given_locales): ), ] ) - def test_loading_without_given_order(self, given_locales, expected_locales): + def test_loading_without_given_order( + self, given_locales: list[str], expected_locales: list[str] + ) -> None: self.load_data(given_locales, use_given_order=False) self.then_locales_are_yielded_in_order(expected_locales) @@ -275,7 +341,7 @@ def test_loading_without_given_order(self, given_locales, expected_locales): param(given_locales=["fr-NE", "ar-SY"]), ] ) - def test_get_locale_map_with_given_order(self, given_locales): + def test_get_locale_map_with_given_order(self, given_locales: list[str]) -> None: self.given_locale_map(locales=given_locales, use_given_order=True) self.then_locale_map_in_order(given_locales) @@ -295,7 +361,9 @@ def test_get_locale_map_with_given_order(self, given_locales): ), ] ) - def test_get_locale_map_without_given_order(self, given_locales, expected_locales): + def test_get_locale_map_without_given_order( + self, given_locales: list[str], expected_locales: list[str] + ) -> None: self.given_locale_map(locales=given_locales, use_given_order=False) self.then_locale_map_in_order(expected_locales) @@ -313,8 +381,8 @@ def test_get_locale_map_without_given_order(self, given_locales, expected_locale ] ) def test_error_raised_for_unknown_languages( - self, given_languages, unknown_languages - ): + self, given_languages: list[str], unknown_languages: list[str] + ) -> None: self.given_locale_map(languages=given_languages) self.then_error_for_unknown_languages_raised(unknown_languages) @@ -330,7 +398,9 @@ def test_error_raised_for_unknown_languages( param(given_locales=["nl-SX", "be-BE", "ca-FR"], unknown_locales=["be-BE"]), ] ) - def test_error_raised_for_unknown_locales(self, given_locales, unknown_locales): + def test_error_raised_for_unknown_locales( + self, given_locales: list[str], unknown_locales: list[str] + ) -> None: self.given_locale_map(locales=given_locales) self.then_error_for_unknown_locales_raised(unknown_locales) @@ -341,7 +411,9 @@ def test_error_raised_for_unknown_locales(self, given_locales, unknown_locales): param(given_locales=["ca-TA", "ca", "fr"]), ] ) - def test_error_raised_for_conflicting_locales(self, given_locales): + def test_error_raised_for_conflicting_locales( + self, given_locales: list[str] + ) -> None: self.given_locale_map(locales=given_locales) self.then_error_was_raised( ValueError, "Locales should not have same language and different region" @@ -354,52 +426,64 @@ def test_error_raised_for_conflicting_locales(self, given_locales): param(given_locales=["af-NA", "da", "af"]), ] ) - def test_conflicting_locales_load_if_allow_conflicting_locales(self, given_locales): + def test_conflicting_locales_load_if_allow_conflicting_locales( + self, given_locales: list[str] + ) -> None: self.load_data( given_locales, use_given_order=True, allow_conflicting_locales=True ) self.then_locales_are_yielded_in_order(given_locales) def load_data( - self, given_locales, use_given_order=False, allow_conflicting_locales=False - ): + self, + given_locales: list[str], + use_given_order: bool = False, + allow_conflicting_locales: bool = False, + ) -> None: self.locale_generator = self.data_loader.get_locales( locales=given_locales, use_given_order=use_given_order, allow_conflicting_locales=allow_conflicting_locales, ) - def given_locale_map(self, languages=None, locales=None, use_given_order=True): + def given_locale_map( + self, + languages: list[str] | None = None, + locales: list[str] | None = None, + use_given_order: bool = True, + ) -> None: try: - self.locale_map = self.data_loader.get_locale_map( + self.locale_map: OrderedDict[str, Locale] = self.data_loader.get_locale_map( languages=languages, locales=locales, use_given_order=use_given_order ) except Exception as error: self.error = error - def then_locales_are_yielded_in_order(self, expected_locales): + def then_locales_are_yielded_in_order(self, expected_locales: list[str]) -> None: self.assertEqual( list(map(attrgetter("shortname"), list(self.locale_generator))), expected_locales, ) - def then_locale_map_in_order(self, expected_locales): + def then_locale_map_in_order(self, expected_locales: list[str]) -> None: self.assertEqual(list(self.locale_map.keys()), expected_locales) - def then_error_for_unknown_languages_raised(self, unknown_languages): + def then_error_for_unknown_languages_raised( + self, unknown_languages: list[str] + ) -> None: self.assertIsInstance(self.error, ValueError) match = self.UNKNOWN_LANGUAGES_EXCEPTION_RE.match(str(self.error)) - self.assertTrue(match) + assert match is not None languages = match.group(1).split(", ") self.assertCountEqual( languages, [repr(unknown_language) for unknown_language in unknown_languages], ) - def then_error_for_unknown_locales_raised(self, unknown_locales): + def then_error_for_unknown_locales_raised(self, unknown_locales: list[str]) -> None: self.assertIsInstance(self.error, ValueError) match = self.UNKNOWN_LOCALES_EXCEPTION_RE.match(str(self.error)) - self.assertTrue(match) + assert match is not None locales = match.group(1).split(", ") self.assertCountEqual( locales, [repr(unknown_locale) for unknown_locale in unknown_locales] diff --git a/tests/test_minguo.py b/tests/test_minguo.py new file mode 100644 index 000000000..60ae84c03 --- /dev/null +++ b/tests/test_minguo.py @@ -0,0 +1,53 @@ +from datetime import datetime + +from parameterized import param, parameterized + +from dateparser.calendars.minguo import MinguoCalendar, _minguo_parser +from dateparser.conf import settings +from tests import BaseTestCase + + +class TestMinguoCalendar(BaseTestCase): + @parameterized.expand( + [ + param("101/05/25", datetime(2012, 5, 25)), + param("民國101年5月25日 08:36", datetime(2012, 5, 25, 8, 36)), + param("99.12.31", datetime(2010, 12, 31)), + param("5/1/2", datetime(1916, 1, 2)), + param("101/2/29", datetime(2012, 2, 29)), + ] + ) + def test_parse(self, date_string: str, expected: datetime) -> None: + date_data = MinguoCalendar(date_string).get_date() + assert date_data is not None + self.assertEqual(date_data.date_obj, expected) + self.assertEqual(date_data.period, "day") + + @parameterized.expand( + [ + param("101-02", datetime(2012, 2, 29), "month", ("year", "month")), + param("110", datetime(2021, 3, 31), "year", ("year",)), + ] + ) + def test_partial( + self, + date_string: str, + expected: datetime, + period: str, + parts: tuple[str, ...], + ) -> None: + current = settings.replace(RELATIVE_BASE=datetime(2026, 3, 31)) + self.assertEqual( + _minguo_parser.parse(date_string, current), (expected, period, parts) + ) + + @parameterized.expand( + [ + param("2012/05/25"), + param("0/1/1"), + param("102/2/29"), + param("101/05/25 08:36 92694"), + ] + ) + def test_invalid(self, date_string: str) -> None: + self.assertIsNone(MinguoCalendar(date_string).get_date()) diff --git a/tests/test_parser.py b/tests/test_parser.py index c1c5f6def..96a80d7c9 100644 --- a/tests/test_parser.py +++ b/tests/test_parser.py @@ -1,9 +1,10 @@ -from datetime import datetime, time import warnings +from datetime import datetime, time +from typing import Any from parameterized import param, parameterized -from dateparser.conf import apply_settings +from dateparser.conf import Settings, apply_settings from dateparser.parser import _no_spaces_parser, _parser, time_parser, tokenizer from tests import BaseTestCase @@ -91,33 +92,35 @@ class TestTokenizer(BaseTestCase): ), ] ) - def test_tokenization(self, date_string, expected_tokens, expected_types): + def test_tokenization( + self, date_string: str, expected_tokens: list[str], expected_types: list[int] + ) -> None: self.given_tokenizer(date_string) self.when_tokenized() self.then_tokens_were(expected_tokens) self.then_token_types_were(expected_types) - def given_tokenizer(self, date_string): + def given_tokenizer(self, date_string: str) -> None: self.tokenizer = tokenizer(date_string) - def when_tokenized(self): - self.result = list(self.tokenizer.tokenize()) + def when_tokenized(self) -> None: + self.result: list[tuple[str, int]] = list(self.tokenizer.tokenize()) - def then_tokens_were(self, expected_tokens): + def then_tokens_were(self, expected_tokens: list[str]) -> None: self.assertEqual([token_type[0] for token_type in self.result], expected_tokens) - def then_token_types_were(self, expected_types): + def then_token_types_were(self, expected_types: list[int]) -> None: self.assertEqual([token_type[1] for token_type in self.result], expected_types) class TestNoSpaceParser(BaseTestCase): - def test_date_with_spaces_is_not_parsed(self): + def test_date_with_spaces_is_not_parsed(self) -> None: datestring = "2013 25 12" self.given_parser() self.given_settings() self.when_date_is_parsed(datestring) self.then_error_was_raised( - ValueError, ["Unable to parse date from: %s" % datestring] + ValueError, [f"Unable to parse date from: {datestring}"] ) @parameterized.expand( @@ -130,7 +133,7 @@ def test_date_with_spaces_is_not_parsed(self): ), ] ) - def test_empty_string_is_not_parsed(self, date_string): + def test_empty_string_is_not_parsed(self, date_string: str) -> None: self.given_parser() self.given_settings() self.when_date_is_parsed(date_string) @@ -146,21 +149,21 @@ def test_empty_string_is_not_parsed(self, date_string): ), ] ) - def test_colons_string_is_not_parsed(self, date_string): + def test_colons_string_is_not_parsed(self, date_string: str) -> None: self.given_parser() self.given_settings() self.when_date_is_parsed(date_string) self.then_error_was_raised( - ValueError, ["Unable to parse date from: %s" % date_string] + ValueError, [f"Unable to parse date from: {date_string}"] ) - def test_date_with_alphabets_is_not_parsed(self): + def test_date_with_alphabets_is_not_parsed(self) -> None: datestring = "12AUG2015" self.given_parser() self.given_settings() self.when_date_is_parsed(datestring) self.then_error_was_raised( - ValueError, ["Unable to parse date from: %s" % datestring] + ValueError, [f"Unable to parse date from: {datestring}"] ) @parameterized.expand( @@ -288,8 +291,12 @@ def test_date_with_alphabets_is_not_parsed(self): ] ) def test_date_are_parsed_in_order_supplied( - self, date_string, expected_date, expected_period, date_order - ): + self, + date_string: str, + expected_date: datetime, + expected_period: str, + date_order: str, + ) -> None: self.given_parser() self.given_settings(settings={"DATE_ORDER": date_order}) self.when_date_is_parsed(date_string) @@ -311,8 +318,8 @@ def test_date_are_parsed_in_order_supplied( ] ) def test_default_order_used_if_date_order_not_supplied( - self, date_string, expected_date, expected_period - ): + self, date_string: str, expected_date: datetime, expected_period: str + ) -> None: self.given_parser() self.given_settings(settings={"DATE_ORDER": ""}) self.when_date_is_parsed(date_string) @@ -351,11 +358,16 @@ def test_default_order_used_if_date_order_not_supplied( expected_date=datetime(1234, 5, 6, 7, 8), expected_period="day", ), + param( + date_string="00592763", + expected_date=datetime(59, 6, 27, 3), + expected_period="day", + ), ] ) def test_best_order_used_if_date_order_not_supplied_to_8_digit_numbers( - self, date_string, expected_date, expected_period - ): + self, date_string: str, expected_date: datetime, expected_period: str + ) -> None: self.given_parser() self.given_settings(settings={"DATE_ORDER": ""}) self.when_date_is_parsed(date_string) @@ -368,12 +380,14 @@ def test_best_order_used_if_date_order_not_supplied_to_8_digit_numbers( param(date_string="987654321234567890123456789", date_order="DMY"), ] ) - def test_error_is_raised_when_date_cannot_be_parsed(self, date_string, date_order): + def test_error_is_raised_when_date_cannot_be_parsed( + self, date_string: str, date_order: str + ) -> None: self.given_parser() self.given_settings(settings={"DATE_ORDER": date_order}) self.when_date_is_parsed(date_string) self.then_error_was_raised( - ValueError, ["Unable to parse date from: {}".format(date_string)] + ValueError, [f"Unable to parse date from: {date_string}"] ) @parameterized.expand( @@ -394,37 +408,42 @@ def test_error_is_raised_when_date_cannot_be_parsed(self, date_string, date_orde param(format_string="%M%S.%f", expected_period="day"), ] ) - def test_get_period_function(self, format_string, expected_period): + def test_get_period_function( + self, format_string: str, expected_period: str + ) -> None: self.given_parser() self.when_get_period_is_called(format_string) self.then_returned_period_is(expected_period) - def given_parser(self): + def given_parser(self) -> None: self.parser = _no_spaces_parser @apply_settings - def given_settings(self, settings=None): + def given_settings(self, settings: Settings | dict[str, Any] | None = None) -> None: + assert isinstance(settings, Settings) self.settings = settings - def when_date_is_parsed(self, date_string): + def when_date_is_parsed(self, date_string: str) -> None: try: - self.result = self.parser.parse(date_string, self.settings) + self.result: tuple[datetime, str, tuple[str, ...]] | str = ( + self.parser.parse(date_string, self.settings) + ) except Exception as error: self.error = error - def when_get_period_is_called(self, format_string): + def when_get_period_is_called(self, format_string: str) -> None: self.result = self.parser._get_period(format_string) - def then_date_exactly_is(self, expected_date): + def then_date_exactly_is(self, expected_date: datetime) -> None: self.assertEqual(self.result[0], expected_date) - def then_period_exactly_is(self, expected_period): + def then_period_exactly_is(self, expected_period: str) -> None: self.assertEqual(self.result[1], expected_period) - def then_date_is_not_parsed(self): + def then_date_is_not_parsed(self) -> None: self.assertIsNone(self.result) - def then_returned_period_is(self, expected_period): + def then_returned_period_is(self, expected_period: str) -> None: self.assertEqual(self.result, expected_period) @@ -438,7 +457,9 @@ class TestParser(BaseTestCase): param(date_string="31/2010"), ] ) - def test_error_is_raised_when_incomplete_dates_given(self, date_string): + def test_error_is_raised_when_incomplete_dates_given( + self, date_string: str + ) -> None: self.given_parser() self.given_settings(settings={"STRICT_PARSING": True}) self.then_error_is_raised_when_date_is_parsed(date_string) @@ -452,7 +473,9 @@ def test_error_is_raised_when_incomplete_dates_given(self, date_string): param(date_string="31/2010"), ] ) - def test_error_is_raised_when_partially_complete_dates_given(self, date_string): + def test_error_is_raised_when_partially_complete_dates_given( + self, date_string: str + ) -> None: self.given_parser() self.given_settings(settings={"REQUIRE_PARTS": ["day", "month", "year"]}) self.then_error_is_raised_when_date_is_parsed(date_string) @@ -464,7 +487,7 @@ def test_error_is_raised_when_partially_complete_dates_given(self, date_string): param(date_string="2010"), ] ) - def test_error_is_raised_when_day_part_missing(self, date_string): + def test_error_is_raised_when_day_part_missing(self, date_string: str) -> None: self.given_parser() self.given_settings(settings={"REQUIRE_PARTS": ["day"]}) self.then_error_is_raised_when_date_is_parsed(date_string) @@ -475,7 +498,7 @@ def test_error_is_raised_when_day_part_missing(self, date_string): param(date_string="31/2010"), ] ) - def test_error_is_raised_when_month_part_missing(self, date_string): + def test_error_is_raised_when_month_part_missing(self, date_string: str) -> None: self.given_parser() self.given_settings(settings={"REQUIRE_PARTS": ["month"]}) self.then_error_is_raised_when_date_is_parsed(date_string) @@ -486,25 +509,44 @@ def test_error_is_raised_when_month_part_missing(self, date_string): param(date_string="March"), ] ) - def test_error_is_raised_when_year_part_missing(self, date_string): + def test_error_is_raised_when_year_part_missing(self, date_string: str) -> None: self.given_parser() self.given_settings(settings={"REQUIRE_PARTS": ["year"]}) self.then_error_is_raised_when_date_is_parsed(date_string) - def given_parser(self): + @parameterized.expand( + [ + param(relative_base=datetime(1, 1, 1), prefer_dates_from="past"), + param(relative_base=datetime(9999, 6, 1), prefer_dates_from="future"), + ] + ) + def test_error_is_raised_when_preferred_year_is_out_of_range( + self, relative_base: datetime, prefer_dates_from: str + ) -> None: + self.given_parser() + self.given_settings( + settings={ + "RELATIVE_BASE": relative_base, + "PREFER_DATES_FROM": prefer_dates_from, + } + ) + self.then_error_is_raised_when_date_is_parsed("March 3") + + def given_parser(self) -> None: self.parser = _parser @apply_settings - def given_settings(self, settings=None): + def given_settings(self, settings: Settings | dict[str, Any] | None = None) -> None: + assert isinstance(settings, Settings) self.settings = settings - def when_date_is_parsed(self, date_string): + def when_date_is_parsed(self, date_string: str) -> None: try: self.parser.parse(date_string, self.settings) except Exception as error: self.error = error - def then_error_is_raised_when_date_is_parsed(self, date_string): + def then_error_is_raised_when_date_is_parsed(self, date_string: str) -> None: with self.assertRaises(ValueError): self.parser.parse(date_string, self.settings) @@ -519,8 +561,8 @@ def then_error_is_raised_when_date_is_parsed(self, date_string): ] ) def test_parser_does_not_raise_ambiguious_date_deprecation_warning( - self, date_string - ): + self, date_string: str + ) -> None: with warnings.catch_warnings(record=True) as w: warnings.simplefilter("always") self.when_date_is_parsed(date_string) @@ -552,7 +594,7 @@ class TestTimeParser(BaseTestCase): param(date_string="14:30:15.330100", timeobj=time(14, 30, 15, 330100)), ] ) - def test_time_is_parsed(self, date_string, timeobj): + def test_time_is_parsed(self, date_string: str, timeobj: time) -> None: self.given_parser() self.when_time_is_parsed(date_string) self.then_time_exactly_is(timeobj) @@ -568,22 +610,22 @@ def test_time_is_parsed(self, date_string, timeobj): param(date_string="2.45 PM"), ] ) - def test_error_is_raised_for_invalid_time_string(self, date_string): + def test_error_is_raised_for_invalid_time_string(self, date_string: str) -> None: self.given_parser() self.when_time_is_parsed(date_string) self.then_error_was_raised( ValueError, - ["{} does not seem to be a valid time string".format(date_string)], + [f"{date_string} does not seem to be a valid time string"], ) - def given_parser(self): + def given_parser(self) -> None: self.parser = time_parser - def when_time_is_parsed(self, datestring): + def when_time_is_parsed(self, datestring: str) -> None: try: - self.result = self.parser(datestring) + self.result: time = self.parser(datestring) except Exception as error: self.error = error - def then_time_exactly_is(self, timeobj): + def then_time_exactly_is(self, timeobj: time) -> None: self.assertEqual(self.result, timeobj) diff --git a/tests/test_parts_of_day.py b/tests/test_parts_of_day.py new file mode 100644 index 000000000..745a872c0 --- /dev/null +++ b/tests/test_parts_of_day.py @@ -0,0 +1,92 @@ +from datetime import datetime, time + +import pytest + +from dateparser import PartOfDay, PartsOfDay, parse +from dateparser.conf import SettingValidationError +from dateparser.date import DateDataParser +from dateparser.search import search_dates + +BASE = datetime(2026, 9, 28, 15, 0) + + +@pytest.mark.parametrize( + ("date_string", "languages", "expected"), + [ + ("tonight", ["en"], datetime(2026, 9, 28, 20, 0)), + ("last night", ["en"], datetime(2026, 9, 27, 20, 0)), + ("this morning", ["en"], datetime(2026, 9, 28, 9, 0)), + ("tomorrow in the afternoon", ["en"], datetime(2026, 9, 29, 15, 0)), + ("monday evening", ["en"], datetime(2026, 9, 28, 18, 0)), + ("yesterday in the small hours", ["en"], datetime(2026, 9, 27, 3, 0)), + ("Sunday, January 4, 2026 at night", ["en"], datetime(2026, 1, 4, 20, 0)), + ("tonight at 11pm", ["en"], datetime(2026, 9, 28, 23, 0)), + ("8 in the evening", ["en"], datetime(2026, 9, 28, 20, 0)), + ("tomorrow at 7:30 in the morning", ["en"], datetime(2026, 9, 29, 7, 30)), + ("12 at night", ["en"], datetime(2026, 9, 28, 0, 0)), + ("2 at night", ["en"], datetime(2026, 9, 28, 2, 0)), + ("January 8 in the evening", ["en"], datetime(2026, 1, 8, 18, 0)), + ("January 8 at 9 in the evening", ["en"], datetime(2026, 1, 8, 21, 0)), + ("2026-01-05 at night", ["en"], datetime(2026, 1, 5, 20, 0)), + ("3 de mayo a las 5 de la madrugada", ["es"], datetime(2026, 5, 3, 5, 0)), + ("esta madrugada", ["es"], datetime(2026, 9, 28, 3, 0)), + ("mañana de madrugada", ["es"], datetime(2026, 9, 29, 3, 0)), + ("ontem de madrugada", ["pt"], datetime(2026, 9, 27, 3, 0)), + ("onte pola madrugada", ["gl"], datetime(2026, 9, 27, 3, 0)), + ("night", ["en"], None), + ("17 in the afternoon", ["en"], None), + ], +) +def test_parse( + date_string: str, languages: list[str], expected: datetime | None +) -> None: + settings = {"RELATIVE_BASE": BASE} + assert parse(date_string, languages=languages, settings=settings) == expected + + +@pytest.mark.parametrize( + ("date_string", "return_time_as_period", "period"), + [ + ("tonight", True, "part_of_day"), + ("tonight", False, "day"), + ("tonight at 11pm", True, "time"), + ], +) +def test_date_data(date_string: str, return_time_as_period: bool, period: str) -> None: + parser = DateDataParser( + settings={"RELATIVE_BASE": BASE, "RETURN_TIME_AS_PERIOD": return_time_as_period} + ) + date_data = parser.get_date_data(date_string) + assert date_data.period == period + assert date_data.part_of_day is PartOfDay.NIGHT + + +def test_date_data_without_part_of_day() -> None: + date_data = DateDataParser().get_date_data("today") + assert date_data.part_of_day is None + assert "part_of_day" not in repr(date_data) + + +def test_setting() -> None: + settings = {"RELATIVE_BASE": BASE, "PARTS_OF_DAY": PartsOfDay(night=time(22, 30))} + assert parse("tonight", settings=settings) == datetime(2026, 9, 28, 22, 30) + + +def test_setting_validation() -> None: + with pytest.raises(SettingValidationError): + parse("tonight", settings={"PARTS_OF_DAY": {"night": time(22)}}) + with pytest.raises(TypeError): + PartsOfDay(night="22:00") # type: ignore[arg-type] + + +def test_search_dates() -> None: + assert search_dates( + "There is a party tonight. It was a dark night.", + languages=["en"], + settings={"RELATIVE_BASE": BASE}, + ) == [("tonight", datetime(2026, 9, 28, 20, 0))] + assert search_dates( + "Llegó a las 5 de la madrugada del 3 de mayo", + languages=["es"], + settings={"RELATIVE_BASE": BASE}, + ) == [("a las 5 de la madrugada del 3 de mayo", datetime(2026, 5, 3, 5, 0))] diff --git a/tests/test_pickle.py b/tests/test_pickle.py index 937517f0c..82354f929 100644 --- a/tests/test_pickle.py +++ b/tests/test_pickle.py @@ -7,26 +7,27 @@ class TestPickle(BaseTestCase): - def test_pickling_basic_parsed_object(self): + def test_pickling_basic_parsed_object(self) -> None: now = parse("now") self.assertIsInstance(now, datetime) pickle_dumps = pickle.dumps(now) self.assertIsInstance(pickle_dumps, bytes) - def test_pickling_parsed_object_with_tz(self): + def test_pickling_parsed_object_with_tz(self) -> None: now_in_utc = parse("now in UTC") self.assertIsInstance(now_in_utc, datetime) + assert now_in_utc is not None self.assertIsInstance(now_in_utc.tzinfo, StaticTzInfo) pickle_dumps = pickle.dumps(now_in_utc) self.assertIsInstance(pickle_dumps, bytes) - def test_unpickling_basic_parsed_object(self): + def test_unpickling_basic_parsed_object(self) -> None: now = parse("now") pickle_dumps = pickle.dumps(now) pickle_loads = pickle.loads(pickle_dumps) self.assertIsInstance(pickle_loads, datetime) - def test_unpickling_parsed_object_with_tz(self): + def test_unpickling_parsed_object_with_tz(self) -> None: now_in_utc = parse("now in UTC") pickle_dumps = pickle.dumps(now_in_utc) pickle_loads = pickle.loads(pickle_dumps) diff --git a/tests/test_search.py b/tests/test_search.py index 7c3b3322e..a422e6847 100644 --- a/tests/test_search.py +++ b/tests/test_search.py @@ -1,5 +1,6 @@ import datetime from datetime import timedelta +from typing import Any import pytz from parameterized import param, parameterized @@ -11,23 +12,26 @@ from dateparser_data.settings import default_parsers from tests import BaseTestCase -today = datetime.datetime.today() +today = datetime.datetime.now() +relative_base = datetime.datetime(2020, 2, 13, 20, 7, 6) class TestTranslateSearch(BaseTestCase): - def setUp(self): + def setUp(self) -> None: super().setUp() self.search_with_detection = DateSearchWithDetection() self.exact_language_search = self.search_with_detection.search - def run_search_dates_function_invalid_languages(self, text, languages, error_type): + def run_search_dates_function_invalid_languages( + self, text: str, languages: object, error_type: type[Exception] + ) -> None: try: - search_dates(text=text, languages=languages) + search_dates(text=text, languages=languages) # type: ignore[arg-type] except Exception as error: self.error = error self.assertIsInstance(self.error, error_type) - def check_error_message(self, message): + def check_error_message(self, message: str) -> None: self.assertEqual(str(self.error), message) @parameterized.expand( @@ -201,7 +205,7 @@ def check_error_message(self, message): param("sv", "fredag, 03 september 2014"), ] ) - def test_search_date_string(self, shortname, datetime_string): + def test_search_date_string(self, shortname: str, datetime_string: str) -> None: result = self.exact_language_search.search( shortname, datetime_string, settings=Settings() )[1][0] @@ -259,8 +263,10 @@ def test_search_date_string(self, shortname, datetime_string): "Krigen i Europa begyndte den 1. september 1939, da Nazi-Tyskland invaderede Polen, " "og endte med Nazi-Tysklands betingelsesløse overgivelse den 8. maj 1945.", [ - ("1. september 1939", datetime.datetime(1939, 9, 1, 0, 0)), - ("8. maj 1945", datetime.datetime(1945, 5, 8, 0, 0)), + # "den" is a Danish skip word (as in "den 8. maj"), so it is + # included in the matched substring, like "de" in Spanish. + ("den 1. september 1939", datetime.datetime(1939, 9, 1, 0, 0)), + ("den 8. maj 1945", datetime.datetime(1945, 5, 8, 0, 0)), ], settings={"RELATIVE_BASE": datetime.datetime(2000, 1, 1)}, ), @@ -558,7 +564,65 @@ def test_search_date_string(self, shortname, datetime_string): ] ) @apply_settings - def test_search_and_parse(self, shortname, string, expected, settings=None): + def test_search_and_parse( + self, + shortname: str, + string: str, + expected: list[tuple[str, datetime.datetime]], + settings: Settings | dict[str, Any] | None = None, + ) -> None: + assert isinstance(settings, Settings) + result = self.exact_language_search.search_parse( + shortname, string, settings=settings + ) + self.assertEqual(result, expected) + + @parameterized.expand( + [ + param( + "en", + "between Friday and Monday", + [ + ("Friday", datetime.datetime(1999, 12, 31, 0, 0)), + ("Monday", datetime.datetime(1999, 12, 27, 0, 0)), + ], + ), + param( + "en", + "Sept 1st and Oct 10th", + [ + ("Sept 1st", datetime.datetime(2000, 9, 1, 0, 0)), + ("Oct 10th", datetime.datetime(2000, 10, 10, 0, 0)), + ], + ), + param( + "es", + "1 de junio de 1998 y 5 de julio de 1999", + [ + ("1 de junio de 1998", datetime.datetime(1998, 6, 1, 0, 0)), + ("5 de julio de 1999", datetime.datetime(1999, 7, 5, 0, 0)), + ], + ), + param( + "de", + "Freitag und Montag", + [ + ("Freitag", datetime.datetime(1999, 12, 31, 0, 0)), + ("Montag", datetime.datetime(1999, 12, 27, 0, 0)), + ], + ), + ] + ) + @apply_settings + def test_search_dates_joined_by_skipped_words( + self, + shortname: str, + string: str, + expected: list[tuple[str, datetime.datetime]], + settings: Settings | dict[str, Any] | None = None, + ) -> None: + assert isinstance(settings, Settings) + settings = settings.replace(RELATIVE_BASE=datetime.datetime(2000, 1, 1)) result = self.exact_language_search.search_parse( shortname, string, settings=settings ) @@ -599,7 +663,7 @@ def test_search_and_parse(self, shortname, string, expected, settings=None): datetime.datetime( 2020, 5, - datetime.datetime.now(tz=datetime.timezone.utc).day, + today.day, 0, 0, ), @@ -609,7 +673,7 @@ def test_search_and_parse(self, shortname, string, expected, settings=None): datetime.datetime( 2020, 7, - datetime.datetime.now(tz=datetime.timezone.utc).day, + today.day, 0, 0, ), @@ -619,7 +683,7 @@ def test_search_and_parse(self, shortname, string, expected, settings=None): datetime.datetime( 2023, 7, - datetime.datetime.now(tz=datetime.timezone.utc).day, + today.day, 0, 0, ), @@ -629,7 +693,7 @@ def test_search_and_parse(self, shortname, string, expected, settings=None): datetime.datetime( 2023, 1, - datetime.datetime.now(tz=datetime.timezone.utc).day, + today.day, 0, 0, tzinfo=pytz.utc, @@ -720,7 +784,14 @@ def test_search_and_parse(self, shortname, string, expected, settings=None): ] ) @apply_settings - def test_relative_base_setting(self, shortname, string, expected, settings=None): + def test_relative_base_setting( + self, + shortname: str, + string: str, + expected: list[tuple[str, datetime.datetime]], + settings: Settings | dict[str, Any] | None = None, + ) -> None: + assert isinstance(settings, Settings) result = self.exact_language_search.search_parse( shortname, string, settings=settings ) @@ -804,7 +875,14 @@ def test_relative_base_setting(self, shortname, string, expected, settings=None) ] ) @apply_settings - def test_splitting_of_not_parsed(self, shortname, string, expected, settings=None): + def test_splitting_of_not_parsed( + self, + shortname: str, + string: str, + expected: list[tuple[str, datetime.datetime]], + settings: Settings | dict[str, Any] | None = None, + ) -> None: + assert isinstance(settings, Settings) result = self.exact_language_search.search_parse( shortname, string, settings=settings ) @@ -971,7 +1049,7 @@ def test_splitting_of_not_parsed(self, shortname, string, expected, settings=Non param("en", "2007"), ] ) - def test_detection(self, shortname, text): + def test_detection(self, shortname: str, text: str) -> None: result = self.search_with_detection.detect_language(text, languages=None) self.assertEqual(result, shortname) @@ -1014,12 +1092,53 @@ def test_detection(self, shortname, text): settings=None, expected=[("DECEMBER 21 19", datetime.datetime(2019, 12, 21, 0, 0))], ), + # Full stops between digits + param( + text="Sampled on 2019-10-19 20:28:35.973000 by the sensor", + languages=None, + settings=None, + expected=[ + ( + "2019-10-19 20:28:35.973000", + datetime.datetime(2019, 10, 19, 20, 28, 35, 973000), + ) + ], + ), + param( + text="test 13.07.2016 test", + languages=None, + settings=None, + expected=[("13.07.2016", datetime.datetime(2016, 7, 13, 0, 0))], + ), param( text="bonjour, pouvez vous me joindre svp par telephone 08 11 58 54 41", languages=None, settings={"STRICT_PARSING": True}, expected=None, ), + param( + text="Date de facture 23 juillet 2020 Condition Redevable livraison FR", + languages=["en", "fr", "es", "pt", "de", "it", "ar"], + settings={"STRICT_PARSING": True}, + expected=[("23 juillet 2020", datetime.datetime(2020, 7, 23, 0, 0))], + ), + param( + text="Bubble -58.5 06 Mar 2009 in need of -43.4 30 Oct 1974", + languages=["en"], + settings={"STRICT_PARSING": True}, + expected=[ + ("06 Mar 2009 in", datetime.datetime(2009, 3, 6, 0, 0)), + ("30 Oct 1974", datetime.datetime(1974, 10, 30, 0, 0)), + ], + ), + param( + text="The conference is June 12-14, 2021 in Boston.", + languages=["en"], + settings=None, + expected=[ + ("June 12-14, 2021 in", datetime.datetime(2021, 6, 12, 0, 0)) + ], + ), param(text="a Americ", languages=None, settings=None, expected=None), # Date with comma and apostrophe param( @@ -1036,10 +1155,162 @@ def test_detection(self, shortname, text): ), ] ) - def test_date_search_function(self, text, languages, settings, expected): + def test_date_search_function( + self, + text: str, + languages: list[str] | None, + settings: dict[str, Any] | None, + expected: list[tuple[str, datetime.datetime]] | None, + ) -> None: result = search_dates(text, languages=languages, settings=settings) self.assertEqual(result, expected) + @parameterized.expand( + [ + # The comma used to be what told the expression and the date apart + param( + text="Today 13 Feb 2020", + languages=["en"], + expected=[ + ("Today", relative_base), + ("13 Feb 2020", datetime.datetime(2020, 2, 13, 0, 0)), + ], + ), + param( + text="Today, 13 Feb 2020", + languages=["en"], + expected=[ + ("Today", relative_base), + ("13 Feb 2020", datetime.datetime(2020, 2, 13, 0, 0)), + ], + ), + # The expression written after the date instead of before it + param( + text="13 Feb 2020 Today", + languages=["en"], + expected=[ + ("13 Feb 2020", datetime.datetime(2020, 2, 13, 0, 0)), + ("Today", relative_base), + ], + ), + # An expression translated into "in 1 day" instead of "0 day ago" + param( + text="Tomorrow 13 Feb 2020", + languages=["en"], + expected=[ + ("Tomorrow", datetime.datetime(2020, 2, 14, 20, 7, 6)), + ("13 Feb 2020", datetime.datetime(2020, 2, 13, 0, 0)), + ], + ), + param( + text="hoy 13 feb 2020", + languages=["es"], + expected=[ + ("hoy", relative_base), + ("13 feb 2020", datetime.datetime(2020, 2, 13, 0, 0)), + ], + ), + # "and" is written by the text but not by its translation, so the + # words left of the expression no longer line up with the ones + # they were translated from + param( + text="Today 13 Feb 2020 and 14 Mar 2021", + languages=["en"], + expected=None, + ), + # "3 days ago" is written as three words and translated into three, + # which the two "tomorrow" adds back: the counts line up although + # the expression was not translated from "3" alone + param( + text="3 days ago tomorrow 13 Feb 2020", + languages=["en"], + expected=None, + ), + # Cutting "today" off would leave "13 feb 2020 before", which is no + # longer a date, so the expression was not written next to one + param( + text="13 feb 2020 before today", + languages=["en"], + expected=None, + ), + ] + ) + def test_search_dates_with_a_relative_expression_next_to_a_date( + self, + text: str, + languages: list[str], + expected: list[tuple[str, datetime.datetime]], + ) -> None: + result = search_dates( + text, languages=languages, settings={"RELATIVE_BASE": relative_base} + ) + self.assertEqual(result, expected) + + @parameterized.expand( + [ + # The word a future expression is written with is what points it + # forward, and reporting it is what tells the two directions apart + param( + text="через 2 часа", + languages=["ru"], + expected=[("через 2 часа", relative_base + timedelta(hours=2))], + ), + # The unit is written next to a comma, which used to keep it from + # being read as the unit of a future expression + param( + text="через 2 часа, пожалуйста", + languages=["ru"], + expected=[("через 2 часа", relative_base + timedelta(hours=2))], + ), + param( + text="Позвони мне через 2 часа, пожалуйста", + languages=["ru"], + expected=[("через 2 часа", relative_base + timedelta(hours=2))], + ), + param( + text="через 3 дня, пожалуйста", + languages=["ru"], + expected=[("через 3 дня", relative_base + timedelta(days=3))], + ), + # A past expression is written with its own word and keeps pointing + # back, comma or not + param( + text="2 часа назад", + languages=["ru"], + expected=[("2 часа назад", relative_base - timedelta(hours=2))], + ), + param( + text="2 часа назад, пожалуйста", + languages=["ru"], + expected=[("2 часа назад", relative_base - timedelta(hours=2))], + ), + # The expression is translated into English before it is parsed, so + # the comma reaches the same code whatever it was written in + param( + text="in 2 hours, please", + languages=["en"], + expected=[("in 2 hours", relative_base + timedelta(hours=2))], + ), + # Not only a comma: any punctuation the translation carries on the + # unit. ``parse`` already reads this one as a future date + param( + text="in three weeks' time", + languages=["en"], + expected=[("in three weeks", relative_base + timedelta(weeks=3))], + ), + ] + ) + def test_search_dates_with_a_relative_expression_reads_its_direction( + self, + text: str, + languages: list[str], + expected: list[tuple[str, datetime.datetime]], + ) -> None: + result = search_dates( + text, languages=languages, settings={"RELATIVE_BASE": relative_base} + ) + self.assertEqual(result, expected) + @parameterized.expand( [ param( @@ -1063,8 +1334,12 @@ def test_date_search_function(self, text, languages, settings, expected): ] ) def test_search_dates_returning_detected_languages_if_requested( - self, text, add_detected_language, expected - ): + self, + text: str, + add_detected_language: bool, + expected: list[tuple[str, datetime.datetime]] + | list[tuple[str, datetime.datetime, str]], + ) -> None: result = search_dates(text, add_detected_language=add_detected_language) self.assertEqual(result, expected) @@ -1073,7 +1348,9 @@ def test_search_dates_returning_detected_languages_if_requested( param(text="19 марта 2001", languages="wrong type: str instead of list"), ] ) - def test_date_search_function_invalid_languages_type(self, text, languages): + def test_date_search_function_invalid_languages_type( + self, text: str, languages: str + ) -> None: self.run_search_dates_function_invalid_languages( text=text, languages=languages, error_type=TypeError ) @@ -1086,13 +1363,15 @@ def test_date_search_function_invalid_languages_type(self, text, languages): param(text="19 марта 2001", languages=["unknown language code"]), ] ) - def test_date_search_function_invalid_language_code(self, text, languages): + def test_date_search_function_invalid_language_code( + self, text: str, languages: list[str] + ) -> None: self.run_search_dates_function_invalid_languages( text=text, languages=languages, error_type=ValueError ) self.check_error_message("Unknown language(s): 'unknown language code'") - def test_search_dates_with_prepositions(self): + def test_search_dates_with_prepositions(self) -> None: """Test `search_dates` for parsing Russian date ranges with prepositions and language detection.""" result = search_dates( "Сервис будет недоступен с 12 января по 30 апреля.", @@ -1201,8 +1480,13 @@ def test_search_dates_with_prepositions(self): ] ) def test_search_dates_multi_word_expression( - self, text, expected_text, expected_day, expected_month, description - ): + self, + text: str, + expected_text: str, + expected_day: int, + expected_month: int, + description: str, + ) -> None: """Test parsing of multi-word date expressions in Russian.""" result = search_dates(text, languages=["ru"]) expected = [ @@ -1215,121 +1499,558 @@ def test_search_dates_multi_word_expression( ] self.assertEqual(result, expected) - def test_search_dates_time_span_past_month(self): - """Test search_dates with 'past month' time span.""" - text = "messages received for the past month" - settings = { - "RETURN_TIME_SPAN": True, - "RELATIVE_BASE": datetime.datetime(2025, 2, 15, 12, 0, 0), - "DEFAULT_DAYS_IN_MONTH": 30, - } - - result = search_dates(text, settings=settings) - - self.assertIsNotNone(result) - self.assertIsInstance(result, list) - if result is not None: - self.assertGreaterEqual(len(result), 2) - - span_results = [r for r in result if "(start)" in r[0] or "(end)" in r[0]] - self.assertEqual(len(span_results), 2) + # A Tuesday, so that the start of the week is neither the base date itself + # nor the day before it under either DEFAULT_START_OF_WEEK value. + TIME_SPAN_BASE = datetime.datetime(2025, 2, 18, 12, 0) - start_result = next(r for r in span_results if "(start)" in r[0]) - end_result = next(r for r in span_results if "(end)" in r[0]) - self.assertEqual(end_result[1], datetime.datetime(2025, 2, 15, 12, 0, 0)) - - expected_start = datetime.datetime(2025, 2, 15, 12, 0, 0) - timedelta( - days=30 - ) - self.assertEqual(start_result[1], expected_start) - - def test_search_dates_time_span_last_week(self): - """Test search_dates with 'last week' time span.""" - text = "messages received last week" - settings = { - "RETURN_TIME_SPAN": True, - "RELATIVE_BASE": datetime.datetime(2025, 2, 18, 12, 0, 0), # Tuesday - "DEFAULT_START_OF_WEEK": "monday", - } - - result = search_dates(text, settings=settings) + @parameterized.expand( + [ + param( + "for the past month", + start=datetime.datetime(2025, 1, 19, 12, 0), + end=datetime.datetime(2025, 2, 18, 12, 0), + ), + param( + "for the past month", + start=datetime.datetime(2025, 1, 21, 12, 0), + end=datetime.datetime(2025, 2, 18, 12, 0), + settings={"DEFAULT_DAYS_IN_MONTH": 28}, + ), + param( + "last week", + start=datetime.datetime(2025, 2, 10, 12, 0), + end=datetime.datetime(2025, 2, 16, 12, 0), + ), + param( + "last week", + start=datetime.datetime(2025, 2, 9, 12, 0), + end=datetime.datetime(2025, 2, 15, 12, 0), + settings={"DEFAULT_START_OF_WEEK": "sunday"}, + ), + param( + "in the past 5 days", + start=datetime.datetime(2025, 2, 13, 12, 0), + end=datetime.datetime(2025, 2, 18, 12, 0), + ), + param( + "previous 3 weeks", + start=datetime.datetime(2025, 1, 28, 12, 0), + end=datetime.datetime(2025, 2, 18, 12, 0), + ), + param( + "during the last 2 months", + start=datetime.datetime(2024, 12, 18, 12, 0), + end=datetime.datetime(2025, 2, 18, 12, 0), + ), + param( + "next month", + start=datetime.datetime(2025, 2, 18, 12, 0), + end=datetime.datetime(2025, 3, 20, 12, 0), + ), + param( + "coming week", + start=datetime.datetime(2025, 2, 24, 12, 0), + end=datetime.datetime(2025, 3, 2, 12, 0), + ), + param( + "coming week", + start=datetime.datetime(2025, 2, 23, 12, 0), + end=datetime.datetime(2025, 3, 1, 12, 0), + settings={"DEFAULT_START_OF_WEEK": "sunday"}, + ), + param( + "in the next 10 days", + start=datetime.datetime(2025, 2, 18, 12, 0), + end=datetime.datetime(2025, 2, 28, 12, 0), + ), + param( + "following 2 weeks", + start=datetime.datetime(2025, 2, 18, 12, 0), + end=datetime.datetime(2025, 3, 4, 12, 0), + ), + param( + "next 6 months", + start=datetime.datetime(2025, 2, 18, 12, 0), + end=datetime.datetime(2025, 8, 18, 12, 0), + ), + ] + ) + def test_search_dates_time_span( + self, + expression: str, + start: datetime.datetime, + end: datetime.datetime, + settings: dict[str, Any] | None = None, + ) -> None: + result = search_dates( + "messages received " + expression, + languages=["en"], + settings={ + "RETURN_TIME_SPAN": True, + "RELATIVE_BASE": self.TIME_SPAN_BASE, + **(settings or {}), + }, + ) + assert result is not None + self.assertEqual( + [item for item in result if item[0].startswith(expression + " (")], + [(expression + " (start)", start), (expression + " (end)", end)], + ) - self.assertIsNotNone(result) - self.assertIsInstance(result, list) - if result is not None: - self.assertGreaterEqual(len(result), 2) + def test_search_dates_time_span_without_a_span_expression(self) -> None: + result = search_dates( + "messages received yesterday", + languages=["en"], + settings={ + "RETURN_TIME_SPAN": True, + "RELATIVE_BASE": self.TIME_SPAN_BASE, + }, + ) + self.assertEqual(result, [("yesterday", datetime.datetime(2025, 2, 17, 12, 0))]) - span_results = [r for r in result if "(start)" in r[0] or "(end)" in r[0]] - self.assertEqual(len(span_results), 2) + def test_search_dates_time_span_disabled_by_default(self) -> None: + result = search_dates( + "messages received for the past month", + languages=["en"], + settings={"RELATIVE_BASE": self.TIME_SPAN_BASE}, + ) + self.assertIsNone(result) - start_result = next(r for r in span_results if "(start)" in r[0]) - end_result = next(r for r in span_results if "(end)" in r[0]) - expected_start = datetime.datetime(2025, 2, 10, 12, 0, 0) - expected_end = datetime.datetime(2025, 2, 16, 12, 0, 0) + def test_search_dates_keeps_an_explicit_date_order_after_the_first_date( + self, + ) -> None: + result = search_dates( + "op 30-05-2027. Deze op 01-11-2026", + languages=["nl"], + settings={"DATE_ORDER": "DMY", "STRICT_PARSING": True}, + ) + self.assertEqual( + result, + [ + ("30-05-2027", datetime.datetime(2027, 5, 30, 0, 0)), + ("01-11-2026", datetime.datetime(2026, 11, 1, 0, 0)), + ], + ) - self.assertEqual(start_result[1], expected_start) - self.assertEqual(end_result[1], expected_end) + @parameterized.expand( + [ + # Every language but vi and hu is searched in its English + # translation, so the dates after the first one were read as MDY + param( + "nl", + "Besteld op 25-12-2020, verzonden op 02-01-2021 en geleverd op 05-01-2021.", + "DMY", + [ + ("25-12-2020", datetime.datetime(2020, 12, 25, 0, 0)), + ("02-01-2021", datetime.datetime(2021, 1, 2, 0, 0)), + ("05-01-2021", datetime.datetime(2021, 1, 5, 0, 0)), + ], + ), + param( + "de", + "Bestellt 25.12.2020, versandt 02.01.2021, geliefert 05.01.2021.", + "DMY", + [ + ("25.12.2020", datetime.datetime(2020, 12, 25, 0, 0)), + ("02.01.2021", datetime.datetime(2021, 1, 2, 0, 0)), + ("05.01.2021", datetime.datetime(2021, 1, 5, 0, 0)), + ], + ), + param( + "fr", + "Commandé 25/12/2020, expédié 02/01/2021, livré 05/01/2021.", + "DMY", + [ + ("25/12/2020", datetime.datetime(2020, 12, 25, 0, 0)), + ("02/01/2021", datetime.datetime(2021, 1, 2, 0, 0)), + ("05/01/2021", datetime.datetime(2021, 1, 5, 0, 0)), + ], + ), + param( + "ru", + "Заказ 25.12.2020, отправка 02.01.2021, доставка 05.01.2021.", + "DMY", + [ + ("25.12.2020", datetime.datetime(2020, 12, 25, 0, 0)), + ("02.01.2021", datetime.datetime(2021, 1, 2, 0, 0)), + ("05.01.2021", datetime.datetime(2021, 1, 5, 0, 0)), + ], + ), + param( + "en", + "Ordered 25/12/2020, shipped 02/01/2021, delivered 05/01/2021.", + "DMY", + [ + ("25/12/2020", datetime.datetime(2020, 12, 25, 0, 0)), + ("02/01/2021", datetime.datetime(2021, 1, 2, 0, 0)), + ("05/01/2021", datetime.datetime(2021, 1, 5, 0, 0)), + ], + ), + # vi and hu are searched in their own locale, whose order is DMY + # and YMD respectively + param( + "vi", + "Đặt hàng 12/25/2020, giao hàng 01/02/2021, nhận hàng 01/05/2021.", + "MDY", + [ + ("12/25/2020", datetime.datetime(2020, 12, 25, 0, 0)), + ("01/02/2021", datetime.datetime(2021, 1, 2, 0, 0)), + ("01/05/2021", datetime.datetime(2021, 1, 5, 0, 0)), + ], + ), + param( + "hu", + "Rendelés 12/25/2020, szállítás 01/02/2021, kézbesítés 01/05/2021.", + "MDY", + [ + ("12/25/2020", datetime.datetime(2020, 12, 25, 0, 0)), + ("01/02/2021", datetime.datetime(2021, 1, 2, 0, 0)), + ("01/05/2021", datetime.datetime(2021, 1, 5, 0, 0)), + ], + ), + param( + "en", + "Ordered 12/25/2020, shipped 01/02/2021, delivered 01/05/2021.", + "MDY", + [ + ("12/25/2020", datetime.datetime(2020, 12, 25, 0, 0)), + ("01/02/2021", datetime.datetime(2021, 1, 2, 0, 0)), + ("01/05/2021", datetime.datetime(2021, 1, 5, 0, 0)), + ], + ), + # With a four-digit year first, any order reads the year first, so + # only a two-digit year tells YMD apart + param( + "en", + "Ordered 20-12-25, shipped 21-01-02, delivered 21-01-05.", + "YMD", + [ + ("20-12-25", datetime.datetime(2020, 12, 25, 0, 0)), + ("21-01-02", datetime.datetime(2021, 1, 2, 0, 0)), + ("21-01-05", datetime.datetime(2021, 1, 5, 0, 0)), + ], + ), + param( + "es", + "Pedido 20/12/25, enviado 21/01/02, entregado 21/01/05.", + "YMD", + [ + ("20/12/25", datetime.datetime(2020, 12, 25, 0, 0)), + ("21/01/02", datetime.datetime(2021, 1, 2, 0, 0)), + ("21/01/05", datetime.datetime(2021, 1, 5, 0, 0)), + ], + ), + param( + "vi", + "Đặt hàng 20/12/25, giao hàng 21/01/02, nhận hàng 21/01/05.", + "YMD", + [ + ("20/12/25", datetime.datetime(2020, 12, 25, 0, 0)), + ("21/01/02", datetime.datetime(2021, 1, 2, 0, 0)), + ("21/01/05", datetime.datetime(2021, 1, 5, 0, 0)), + ], + ), + ] + ) + def test_search_dates_reads_every_date_in_an_explicit_date_order( + self, + language: str, + text: str, + date_order: str, + expected: list[tuple[str, datetime.datetime]], + ) -> None: + for strict_parsing in (False, True): + with self.subTest(strict_parsing=strict_parsing): + result = search_dates( + text, + languages=[language], + settings={ + "DATE_ORDER": date_order, + "STRICT_PARSING": strict_parsing, + }, + ) + self.assertEqual(result, expected) - def test_search_dates_time_span_custom_start_of_week(self): - """Test search_dates with custom start_of_week setting.""" - text = "messages received last week" - settings = { - "RETURN_TIME_SPAN": True, - "RELATIVE_BASE": datetime.datetime(2025, 2, 18, 12, 0, 0), # Tuesday - "DEFAULT_START_OF_WEEK": "sunday", # Custom start of week - } + @parameterized.expand( + [ + param( + "en", + "Ordered 12/25/2020, shipped 01/02/2021, delivered 01/05/2021.", + [ + ("12/25/2020", datetime.datetime(2020, 12, 25, 0, 0)), + ("01/02/2021", datetime.datetime(2021, 1, 2, 0, 0)), + ("01/05/2021", datetime.datetime(2021, 1, 5, 0, 0)), + ], + ), + param( + "vi", + "Đặt hàng 25/12/2020, giao hàng 02/01/2021, nhận hàng 05/01/2021.", + [ + ("25/12/2020", datetime.datetime(2020, 12, 25, 0, 0)), + ("02/01/2021", datetime.datetime(2021, 1, 2, 0, 0)), + ("05/01/2021", datetime.datetime(2021, 1, 5, 0, 0)), + ], + ), + param( + "hu", + "Rendelés 20.12.25, szállítás 21.01.02, kézbesítés 21.01.05.", + [ + ("20.12.25", datetime.datetime(2020, 12, 25, 0, 0)), + ("21.01.02", datetime.datetime(2021, 1, 2, 0, 0)), + ("21.01.05", datetime.datetime(2021, 1, 5, 0, 0)), + ], + ), + ] + ) + def test_search_dates_reads_every_date_in_the_locale_date_order_by_default( + self, + language: str, + text: str, + expected: list[tuple[str, datetime.datetime]], + ) -> None: + # Setting something else must not make the default DATE_ORDER count as + # one set by the caller for the dates after the first one. + for settings in ( + None, + {"STRICT_PARSING": True}, + {"PREFER_DAY_OF_MONTH": "first"}, + ): + with self.subTest(settings=settings): + result = search_dates(text, languages=[language], settings=settings) + self.assertEqual(result, expected) - result = search_dates(text, settings=settings) - self.assertIsNotNone(result) - self.assertIsInstance(result, list) - if result is not None: - self.assertGreaterEqual(len(result), 2) + @parameterized.expand( + [ + # The second date has no year, so it is the year of the first date + # or the next one, as PREFER_DATES_FROM prefers + param( + "en", + "Ordered 25/12/2020, delivered 02/01.", + {"PREFER_DATES_FROM": "future"}, + [ + ("25/12/2020", datetime.datetime(2020, 12, 25, 0, 0)), + ("02/01", datetime.datetime(2021, 1, 2, 0, 0)), + ], + ), + param( + "en", + "Ordered 25/12/2020, delivered 02/01.", + {"PREFER_DATES_FROM": "past"}, + [ + ("25/12/2020", datetime.datetime(2020, 12, 25, 0, 0)), + ("02/01", datetime.datetime(2020, 1, 2, 0, 0)), + ], + ), + # A relative date counts from the date found before it + param( + "en", + "Ordered 25/12/2020. Paid 02/01/2021. Shipped in 3 days. " + "Delivered 10/01/2021.", + {}, + [ + ("25/12/2020", datetime.datetime(2020, 12, 25, 0, 0)), + ("02/01/2021", datetime.datetime(2021, 1, 2, 0, 0)), + ("in 3 days", datetime.datetime(2021, 1, 5, 0, 0)), + ("10/01/2021", datetime.datetime(2021, 1, 10, 0, 0)), + ], + ), + param( + "ru", + "Заказ 25.12.2020. Оплата 02.01.2021. Через 3 дня отправка. " + "Доставка 10.01.2021.", + {}, + [ + ("25.12.2020", datetime.datetime(2020, 12, 25, 0, 0)), + ("02.01.2021", datetime.datetime(2021, 1, 2, 0, 0)), + ("Через 3 дня", datetime.datetime(2021, 1, 5, 0, 0)), + ("10.01.2021", datetime.datetime(2021, 1, 10, 0, 0)), + ], + ), + param( + "nl", + "op 30-05-2027 om 10:00. Deze op 01-11-2026 om 09:30", + {"TIMEZONE": "Europe/Amsterdam", "TO_TIMEZONE": "UTC"}, + [ + ("30-05-2027 om 10:00", datetime.datetime(2027, 5, 30, 8, 0)), + ("01-11-2026 om 09:30", datetime.datetime(2026, 11, 1, 8, 30)), + ], + ), + param( + "nl", + "op 30-05-2027 om 10:00. Deze op 01-11-2026 om 09:30", + {"TIMEZONE": "Europe/Amsterdam", "RETURN_AS_TIMEZONE_AWARE": True}, + [ + ( + "30-05-2027 om 10:00", + datetime.datetime( + 2027, + 5, + 30, + 10, + 0, + tzinfo=datetime.timezone(timedelta(hours=2)), + ), + ), + ( + "01-11-2026 om 09:30", + datetime.datetime( + 2026, + 11, + 1, + 9, + 30, + tzinfo=datetime.timezone(timedelta(hours=1)), + ), + ), + ], + ), + ] + ) + def test_search_dates_keeps_the_other_settings_after_the_first_date( + self, + language: str, + text: str, + settings: dict[str, Any], + expected: list[tuple[str, datetime.datetime]], + ) -> None: + result = search_dates( + text, languages=[language], settings={"DATE_ORDER": "DMY", **settings} + ) + self.assertEqual(result, expected) - span_results = [r for r in result if "(start)" in r[0] or "(end)" in r[0]] - self.assertEqual(len(span_results), 2) + @parameterized.expand( + [ + # 25 cannot be the month, and "all" does not swap it with the day + param("all", "Opened 25/12/2020, closed 12/25/2021."), + # 32 cannot be the day, so it is the year, which DMY puts last + param("year", "Opened 25/12/2020, closed 32/12/10."), + ] + ) + def test_search_dates_keeps_strict_date_order_after_the_first_date( + self, strict: str, text: str + ) -> None: + result = search_dates( + text, + languages=["en"], + settings={"DATE_ORDER": "DMY", "STRICT_DATE_ORDER": strict}, + ) + self.assertEqual( + result, [("25/12/2020", datetime.datetime(2020, 12, 25, 0, 0))] + ) - start_result = next(r for r in span_results if "(start)" in r[0]) - end_result = next(r for r in span_results if "(end)" in r[0]) - expected_start = datetime.datetime(2025, 2, 9, 12, 0, 0) - expected_end = datetime.datetime(2025, 2, 15, 12, 0, 0) - self.assertEqual(start_result[1], expected_start) - self.assertEqual(end_result[1], expected_end) +class TestNgramSearch(BaseTestCase): + def setUp(self) -> None: + super().setUp() + self.search_with_detection = DateSearchWithDetection() - def test_search_dates_time_span_custom_days_in_month(self): - """Test search_dates with custom days_in_month setting.""" - text = "messages received for the past month" - settings = { - "RETURN_TIME_SPAN": True, - "RELATIVE_BASE": datetime.datetime(2025, 2, 15, 12, 0, 0), - "DEFAULT_DAYS_IN_MONTH": 28, # Custom month length - } + @parameterized.expand( + [ + # noise words ("on") are not part of the returned substring and + # trailing punctuation is stripped + param( + "en", + text="The first artificial Earth satellite was launched" + " on 4 October 1957.", + expected=[("4 October 1957", datetime.datetime(1957, 10, 4))], + ), + # all non-overlapping dates are returned, longest match first + param( + "en", + text="The client arrived to the office for the first time" + " in March 3rd, 2004 and got serviced, after a couple of months," + " on May 6th 2004, the customer returned indicating a defect on" + " the part", + expected=[ + ("in March 3rd, 2004 and", datetime.datetime(2004, 3, 3)), + ("May 6th 2004, the", datetime.datetime(2004, 5, 6)), + ], + ), + # bare small numbers are blacklisted and do not produce dates + param("en", text="Chapter 12, page 3", expected=[]), + # French + param( + "fr", + text="Publié le 11 juillet 2016", + expected=[("le 11 juillet 2016", datetime.datetime(2016, 7, 11))], + ), + param( + "fr", + text="Le premier satellite artificiel, lancé le 4 octobre 1957," + " pesait 83 kg", + expected=[("le 4 octobre 1957", datetime.datetime(1957, 10, 4))], + ), + # Russian + param( + "ru", + text="веб-страница обновлена 11 июля 2016 года", + expected=[("11 июля 2016 года", datetime.datetime(2016, 7, 11))], + ), + ] + ) + def test_ngram_search( + self, shortname: str, text: str, expected: list[tuple[str, datetime.datetime]] + ) -> None: + result = self.search_with_detection.search_dates( + text, languages=[shortname], strategy="ngram" + ) + self.assertEqual(result["Language"], shortname) + self.assertEqual(result["Dates"], expected) - result = search_dates(text, settings=settings) + def test_ngram_search_with_relative_base(self) -> None: + result = self.search_with_detection.search_dates( + "posted 10 minutes ago", + languages=["en"], + settings={"RELATIVE_BASE": datetime.datetime(2020, 1, 1, 12, 0)}, + strategy="ngram", + ) + self.assertEqual( + result["Dates"], + [("10 minutes ago", datetime.datetime(2020, 1, 1, 11, 50))], + ) - self.assertIsNotNone(result) - self.assertIsInstance(result, list) - if result is not None: - self.assertGreaterEqual(len(result), 2) + def test_ngram_search_returns_time_spans(self) -> None: + result = self.search_with_detection.search_dates( + "messages received for the past week", + languages=["en"], + settings={ + "RETURN_TIME_SPAN": True, + "RELATIVE_BASE": datetime.datetime(2025, 2, 15, 12, 0), + }, + strategy="ngram", + ) + self.assertEqual( + result["Dates"], + [ + ("for the past week (start)", datetime.datetime(2025, 2, 3, 12, 0)), + ("for the past week (end)", datetime.datetime(2025, 2, 9, 12, 0)), + ], + ) - span_results = [r for r in result if "(start)" in r[0] or "(end)" in r[0]] - self.assertEqual(len(span_results), 2) + def test_search_dates_with_ngram_strategy(self) -> None: + result = search_dates( + "launched on 4 October 1957", languages=["en"], strategy="ngram" + ) + self.assertEqual(result, [("4 October 1957", datetime.datetime(1957, 10, 4))]) - start_result = next(r for r in span_results if "(start)" in r[0]) - end_result = next(r for r in span_results if "(end)" in r[0]) - self.assertEqual(end_result[1], datetime.datetime(2025, 2, 15, 12, 0, 0)) + def test_search_dates_with_ngram_strategy_and_detected_language(self) -> None: + result = search_dates( + "launched on 4 October 1957", + languages=["en"], + strategy="ngram", + add_detected_language=True, + ) + self.assertEqual( + result, [("4 October 1957", datetime.datetime(1957, 10, 4), "en")] + ) - expected_start = datetime.datetime(2025, 2, 15, 12, 0, 0) - timedelta( - days=28 + def test_search_dates_ngram_strategy_returns_none_when_no_dates_found(self) -> None: + self.assertIsNone( + search_dates( + "Hello world nothing here at all", languages=["en"], strategy="ngram" ) - self.assertEqual(start_result[1], expected_start) - - def test_search_dates_time_span_disabled_by_default(self): - """Test that time span functionality is disabled by default.""" - text = "messages received for the past month" - - result = search_dates(text) + ) - if result: - span_results = [r for r in result if "(start)" in r[0] or "(end)" in r[0]] - self.assertEqual(len(span_results), 0) + def test_unknown_strategy_raises_error(self) -> None: + with self.assertRaisesRegex(ValueError, "strategy must be"): + search_dates("4 October 1957", languages=["en"], strategy="unknown") diff --git a/tests/test_settings.py b/tests/test_settings.py index 8fc3550e0..0109483fc 100644 --- a/tests/test_settings.py +++ b/tests/test_settings.py @@ -1,24 +1,26 @@ from datetime import datetime, tzinfo +from typing import Any import pytest from parameterized import param, parameterized from dateparser import DateDataParser, parse -from dateparser.conf import SettingValidationError, apply_settings, settings +from dateparser.conf import Settings, SettingValidationError, apply_settings, settings +from dateparser.search import search_dates from tests import BaseTestCase -def test_function(settings=None): +def test_function(settings: object = None) -> object: return settings class TimeZoneSettingsTest(BaseTestCase): - def setUp(self): + def setUp(self) -> None: super().setUp() - self.given_ds = NotImplemented - self.result = NotImplemented + self.given_ds: str = NotImplemented + self.result: datetime | None = NotImplemented self.timezone = NotImplemented - self.confs = NotImplemented + self.confs: Settings = NotImplemented @parameterized.expand( [ @@ -32,7 +34,7 @@ def setUp(self): param("12 Feb 2015 8:30 PM ACT", datetime(2015, 2, 12, 20, 30), "ACT"), ] ) - def test_should_return_and_assert_tz(self, ds, dt, tz): + def test_should_return_and_assert_tz(self, ds: str, dt: datetime, tz: str) -> None: self.given(ds) self.given_configurations({}) self.when_date_is_parsed() @@ -48,7 +50,9 @@ def test_should_return_and_assert_tz(self, ds, dt, tz): param("12 Feb 2015 8:30 PM", datetime(2015, 2, 12, 20, 30), ""), ] ) - def test_only_return_explicit_timezone(self, ds, dt, tz): + def test_only_return_explicit_timezone( + self, ds: str, dt: datetime, tz: str + ) -> None: self.given(ds) self.given_configurations({}) self.when_date_is_parsed() @@ -79,81 +83,112 @@ def test_only_return_explicit_timezone(self, ds, dt, tz): ), ] ) - def test_should_return_naive_if_RETURN_AS_TIMEZONE_AWARE_IS_FALSE(self, ds, dt): + def test_should_return_naive_if_RETURN_AS_TIMEZONE_AWARE_IS_FALSE( + self, ds: str, dt: datetime + ) -> None: self.given(ds) self.given_configurations({"RETURN_AS_TIMEZONE_AWARE": False}) self.when_date_is_parsed() self.then_date_is(dt) self.then_date_is_not_tz_aware() - def then_timezone_is(self, tzname): - self.assertEqual(self.result.tzinfo.tzname(""), tzname) + def then_timezone_is(self, tzname: str) -> None: + assert self.result is not None + assert self.result.tzinfo is not None + self.assertEqual(self.result.tzinfo.tzname(None), tzname) - def given(self, ds): + def given(self, ds: str) -> None: self.given_ds = ds - def given_configurations(self, confs): + def given_configurations(self, confs: dict[str, Any]) -> None: if "TIMEZONE" not in confs: confs.update({"TIMEZONE": "local"}) self.confs = settings.replace(**confs) - def when_date_is_parsed(self): + def when_date_is_parsed(self) -> None: self.result = parse(self.given_ds, settings=(self.confs or {})) - def then_date_is_tz_aware(self): + def then_date_is_tz_aware(self) -> None: + assert self.result is not None self.assertIsInstance(self.result.tzinfo, tzinfo) - def then_date_is_not_tz_aware(self): + def then_date_is_not_tz_aware(self) -> None: + assert self.result is not None self.assertIsNone(self.result.tzinfo) - def then_date_is(self, date): + def then_date_is(self, date: datetime) -> None: + assert self.result is not None dtc = self.result.replace(tzinfo=None) self.assertEqual(dtc, date) class SettingsTest(BaseTestCase): - def setUp(self): + def setUp(self) -> None: super().setUp() self.default_settings = settings def test_apply_settings_should_return_default_settings_when_no_settings_are_supplied_to_the_decorated_function( self, - ): + ) -> None: test_func = apply_settings(test_function) self.assertEqual(test_func(), self.default_settings) def test_apply_settings_should_return_non_default_settings_when_settings_are_supplied_to_the_decorated_function( self, - ): + ) -> None: test_func = apply_settings(test_function) self.assertNotEqual( test_func(settings={"PREFER_DATES_FROM": "past"}), self.default_settings ) - def test_apply_settings_shouldnt_create_new_settings_when_same_settings_are_supplied_to_the_decorated_function_more_than_once( # noqa E501 + def test_apply_settings_shouldnt_create_new_settings_when_same_settings_are_supplied_to_the_decorated_function_more_than_once( self, - ): + ) -> None: test_func = apply_settings(test_function) settings_once = test_func(settings={"PREFER_DATES_FROM": "past"}) settings_twice = test_func(settings={"PREFER_DATES_FROM": "past"}) self.assertEqual(settings_once, settings_twice) - def test_apply_settings_should_return_default_settings_when_called_with_no_settings_after_once_called_with_settings_supplied_to_the_decorated_function( # noqa E501 + def test_apply_settings_should_return_default_settings_when_called_with_no_settings_after_once_called_with_settings_supplied_to_the_decorated_function( self, - ): + ) -> None: test_func = apply_settings(test_function) settings_once = test_func(settings={"PREFER_DATES_FROM": "past"}) settings_twice = test_func() self.assertNotEqual(settings_once, self.default_settings) self.assertEqual(settings_twice, self.default_settings) + def test_replace_keeps_the_settings_that_the_caller_set(self) -> None: + test_func = apply_settings(test_function) + caller_settings = test_func(settings={"DATE_ORDER": "DMY"}) + assert isinstance(caller_settings, Settings) + replaced = caller_settings.replace(RELATIVE_BASE=datetime(2020, 12, 25)) + # A DATE_ORDER that the caller set wins over the MDY order of the locale. + parser = DateDataParser(languages=["en"], settings=replaced) + self.assertEqual( + datetime(2021, 1, 2), parser.get_date_data("02/01/2021")["date_obj"] + ) + + def test_replace_does_not_count_the_settings_it_copies_as_set_by_the_caller( + self, + ) -> None: + test_func = apply_settings(test_function) + caller_settings = test_func(settings={"PREFER_DATES_FROM": "past"}) + assert isinstance(caller_settings, Settings) + replaced = caller_settings.replace(RELATIVE_BASE=datetime(2020, 12, 25)) + # The default DATE_ORDER, MDY, gives way to the DMY order of the locale. + parser = DateDataParser(languages=["de"], settings=replaced) + self.assertEqual( + datetime(2021, 1, 2), parser.get_date_data("02.01.2021")["date_obj"] + ) + class InvalidSettingsTest(BaseTestCase): - def setUp(self): + def setUp(self) -> None: super().setUp() - def test_error_is_raised_when_none_is_passed_in_settings(self): + def test_error_is_raised_when_none_is_passed_in_settings(self) -> None: test_func = apply_settings(test_function) with self.assertRaisesRegex(TypeError, r"Invalid.*None\}"): test_func(settings={"PREFER_DATES_FROM": None}) @@ -164,7 +199,7 @@ def test_error_is_raised_when_none_is_passed_in_settings(self): with self.assertRaisesRegex(TypeError, r"Invalid.*None\}"): test_func(settings={"TO_TIMEZONE": None}) - def test_error_is_raised_for_invalid_type_settings(self): + def test_error_is_raised_for_invalid_type_settings(self) -> None: test_func = apply_settings(test_function) try: test_func(settings=["current_period", False, "current"]) @@ -175,7 +210,7 @@ def test_error_is_raised_for_invalid_type_settings(self): ["settings can only be either dict or instance of Settings class"], ) - def test_check_settings_wrong_setting_name(self): + def test_check_settings_wrong_setting_name(self) -> None: with self.assertRaisesRegex( SettingValidationError, r".* is not a valid setting" ): @@ -200,17 +235,21 @@ def test_check_settings_wrong_setting_name(self): param("STRICT_PARSING", "true", "", True), param("RETURN_TIME_AS_PERIOD", "false", "", True), param("PREFER_LOCALE_DATE_ORDER", "true", "", False), + param("STRICT_DATE_ORDER", True, "full", "none"), param("NORMALIZE", "true", "", True), param("FUZZY", "true", "", False), param("PREFER_LOCALE_DATE_ORDER", "false", "", True), param("DEFAULT_LANGUAGES", "en", "", ["en"]), + param("USE_GIVEN_LANGUAGE_ORDER", "yes", "", True), param("LANGUAGE_DETECTION_CONFIDENCE_THRESHOLD", "1", "", 0.5), ] ) - def test_check_settings(self, setting, wrong_type, wrong_value, valid_value): + def test_check_settings( + self, setting: str, wrong_type: object, wrong_value: str, valid_value: object + ) -> None: with self.assertRaisesRegex( SettingValidationError, - r'"{}" must be .*, not "{}".'.format(setting, type(wrong_type).__name__), + rf'"{setting}" must be .*, not "{type(wrong_type).__name__}".', ): DateDataParser(settings={setting: wrong_type}) @@ -226,7 +265,7 @@ def test_check_settings(self, setting, wrong_type, wrong_value, valid_value): # check that a valid value doesn't raise an error assert DateDataParser(settings={setting: valid_value}) - def test_check_settings_extra_check_require_parts(self): + def test_check_settings_extra_check_require_parts(self) -> None: with self.assertRaisesRegex( SettingValidationError, r'"REQUIRE_PARTS" setting contains invalid values: time', @@ -238,7 +277,7 @@ def test_check_settings_extra_check_require_parts(self): ): DateDataParser(settings={"REQUIRE_PARTS": ["month", "day", "month"]}) - def test_check_settings_extra_check_parsers(self): + def test_check_settings_extra_check_parsers(self) -> None: with self.assertRaisesRegex( SettingValidationError, r'Found unknown parsers in the "PARSERS" setting: no-spaces', @@ -253,7 +292,7 @@ def test_check_settings_extra_check_parsers(self): settings={"PARSERS": ["absolute-time", "timestamp", "absolute-time"]} ) - def test_check_settings_extra_check_confidence_threshold(self): + def test_check_settings_extra_check_confidence_threshold(self) -> None: with self.assertRaisesRegex( SettingValidationError, r"1.1 is not a valid value for " @@ -262,7 +301,7 @@ def test_check_settings_extra_check_confidence_threshold(self): ): DateDataParser(settings={"LANGUAGE_DETECTION_CONFIDENCE_THRESHOLD": 1.1}) - def test_check_settings_extra_check_default_languages(self): + def test_check_settings_extra_check_default_languages(self) -> None: with self.assertRaisesRegex( SettingValidationError, "Found invalid languages in the 'DEFAULT_LANGUAGES' setting: 'abcd'", @@ -270,8 +309,73 @@ def test_check_settings_extra_check_default_languages(self): DateDataParser(settings={"DEFAULT_LANGUAGES": ["abcd"]}) +class StrictDateOrderSettingsTest(BaseTestCase): + """STRICT_DATE_ORDER enforces the DATE_ORDER that the caller sets, so it + needs one.""" + + @parameterized.expand([param("year"), param("all")]) + def test_strict_date_order_requires_date_order(self, strict: str) -> None: + with self.assertRaisesRegex( + SettingValidationError, + rf'"STRICT_DATE_ORDER": "{strict}" requires the "DATE_ORDER" setting', + ): + DateDataParser(settings={"STRICT_DATE_ORDER": strict}) + + # parse() builds the parser too, whatever the date string. + with self.assertRaises(SettingValidationError): + parse("12/10/95", settings={"STRICT_DATE_ORDER": strict}) + + # The default DATE_ORDER is a preference, but one that the caller sets + # is enforced, even if it is the default one. + assert DateDataParser( + settings={"STRICT_DATE_ORDER": strict, "DATE_ORDER": "MDY"} + ) + + def test_strict_date_order_none_does_not_require_date_order(self) -> None: + assert DateDataParser(settings={"STRICT_DATE_ORDER": "none"}) + self.assertEqual( + datetime(1995, 12, 10), + parse("12/10/95", settings={"STRICT_DATE_ORDER": "none"}), + ) + + @parameterized.expand([param("year"), param("all")]) + def test_strict_date_order_stays_in_force_when_a_parser_is_reused( + self, strict: str + ) -> None: + parser = DateDataParser( + settings={"DATE_ORDER": "DMY", "STRICT_DATE_ORDER": strict} + ) + for _ in range(2): + self.assertIsNone(parser.get_date_data("32 DEC 10")["date_obj"]) + self.assertEqual( + datetime(2010, 12, 31), parser.get_date_data("31 DEC 10")["date_obj"] + ) + + @parameterized.expand([param("year"), param("all")]) + def test_search_dates_does_not_check_the_rebuilt_settings( + self, strict: str + ) -> None: + """Test that search_dates does not raise SettingValidationError for the + settings that it rebuilds for the dates after the first one, which + remember which settings the caller set.""" + text = "Opened 25/12/2020, closed 31/12/2020." + self.assertEqual( + [ + ("25/12/2020", datetime(2020, 12, 25)), + ("31/12/2020", datetime(2020, 12, 31)), + ], + search_dates( + text, + languages=["en"], + settings={"DATE_ORDER": "DMY", "STRICT_DATE_ORDER": strict}, + ), + ) + with self.assertRaises(SettingValidationError): + search_dates(text, languages=["en"], settings={"STRICT_DATE_ORDER": strict}) + + @pytest.mark.parametrize( - "date_string,expected_result", + ("date_string", "expected_result"), [ # Note that these results are "valid" but probably they shouldn't be considered ("2020", datetime(1900, 1, 1, 20, 2)), @@ -280,7 +384,7 @@ def test_check_settings_extra_check_default_languages(self): ("100000", datetime(1900, 1, 1, 10, 0)), ], ) -def test_no_spaces_strict_parsing(date_string, expected_result): +def test_no_spaces_strict_parsing(date_string: str, expected_result: datetime) -> None: parser = DateDataParser( settings={"PARSERS": ["no-spaces-time"], "STRICT_PARSING": False} ) @@ -292,14 +396,13 @@ def test_no_spaces_strict_parsing(date_string, expected_result): assert parser.get_date_data(date_string)["date_obj"] is None -def detect_languages(text, confidence_threshold): +def detect_languages(text: str, confidence_threshold: float) -> list[str]: if confidence_threshold > 0.5: return ["en"] - else: - return ["fr"] + return ["fr"] -def test_confidence_threshold_setting_is_applied(): +def test_confidence_threshold_setting_is_applied() -> None: ddp = DateDataParser( detect_languages_function=detect_languages, settings={"LANGUAGE_DETECTION_CONFIDENCE_THRESHOLD": 0.6}, diff --git a/tests/test_thread_safety.py b/tests/test_thread_safety.py new file mode 100644 index 000000000..ab2620fff --- /dev/null +++ b/tests/test_thread_safety.py @@ -0,0 +1,229 @@ +import contextlib +import sys +import threading +import unittest +from collections.abc import Callable, Iterable +from concurrent.futures import ThreadPoolExecutor +from datetime import datetime +from typing import Literal, TypeVar + +import dateparser.data.date_translation_data.en as en_data +from dateparser.conf import settings as base_settings +from dateparser.date import DateData, DateDataParser +from dateparser.languages.dictionary import Dictionary +from dateparser.languages.locale import Locale +from dateparser.search import search_dates +from dateparser.search.search import DateSearchWithDetection, _ExactLanguageSearch +from tests import BaseTestCase + +_T = TypeVar("_T") +_R = TypeVar("_R") + + +class TestThreadSafety(BaseTestCase): + """Regression tests for thread-safety issues. + + See https://github.com/scrapinghub/dateparser/issues/441, + https://github.com/scrapinghub/dateparser/issues/1291 and + https://github.com/scrapinghub/dateparser/issues/1369. + """ + + def setUp(self) -> None: + super().setUp() + # A tiny thread-switch interval makes the interpreter yield between + # almost every bytecode, so the narrow check-then-read windows that + # cause the races below are exercised reliably instead of only once in + # a blue moon. + self._switch_interval = sys.getswitchinterval() + sys.setswitchinterval(1e-7) + + def tearDown(self) -> None: + sys.setswitchinterval(self._switch_interval) + super().tearDown() + + def _run_concurrently( + self, func: Callable[[_T], _R], args_list: Iterable[_T], workers: int = 32 + ) -> list[_R]: + with ThreadPoolExecutor(max_workers=workers) as executor: + futures = [executor.submit(func, arg) for arg in args_list] + return [future.result() for future in futures] + + def test_dictionary_cache_eviction_concurrently(self) -> None: + # Issue #1291: concurrent population/eviction of the size-limited + # dictionary caches raised intermittent ``KeyError`` because the cache + # was read after a concurrent eviction could remove the entry. + dictionaries = [ + Dictionary( + en_data.info, + base_settings.replace(CACHE_SIZE_LIMIT=1, SKIP_TOKENS=[f"tok{i}"]), + ) + for i in range(24) + ] + + def hammer(index: int) -> bool: + dictionary = dictionaries[index % len(dictionaries)] + for _ in range(50): + dictionary.split("2 days ago") + dictionary.are_tokens_valid(["2", "days", "ago"]) + return True + + results = self._run_concurrently(hammer, range(24)) + self.assertTrue(all(results)) + + def test_settings_date_order_not_mutated_while_parsing(self) -> None: + # The absolute-time parser used to assign the locale-specific date order + # onto the shared Settings object in place (restoring it afterwards), so + # a concurrent parse could observe and use a foreign DATE_ORDER. Here the + # German locale order (DMY) differs from the configured default (MDY); a + # watcher thread asserts the shared setting never changes mid-parse. + parser = DateDataParser( + languages=["de"], settings={"PREFER_LOCALE_DATE_ORDER": True} + ) + baseline = parser._settings.DATE_ORDER + self.assertEqual(baseline, "MDY") + + observed: set[str] = set() + stop = threading.Event() + + def watch() -> None: + while not stop.is_set(): + observed.add(parser._settings.DATE_ORDER) + + def parse(i: int) -> DateData: + return parser.get_date_data( + ["02.03.2014", "2014-03-02", "11.12.2013"][i % 3] + ) + + watcher = threading.Thread(target=watch) + watcher.start() + try: + self._run_concurrently(parse, range(100), workers=16) + finally: + stop.set() + watcher.join() + + self.assertEqual(observed, {baseline}) + + def test_search_does_not_mutate_shared_relative_base(self) -> None: + # search_dates used to assign RELATIVE_BASE onto the shared default + # Settings while resolving relative dates, polluting it for concurrent + # parses/searches. + text = ( + "19 марта 2001. Сегодня был хороший день. " + "2 дня назад был хороший день. Вчера тоже был хороший день." + ) + baseline = base_settings.RELATIVE_BASE + + observed: set[datetime | Literal[False]] = set() + stop = threading.Event() + + def watch() -> None: + while not stop.is_set(): + observed.add(base_settings.RELATIVE_BASE) + + def search( + i: int, + ) -> list[tuple[str, datetime]] | list[tuple[str, datetime, str | None]] | None: + return search_dates(text, languages=["ru"]) + + watcher = threading.Thread(target=watch) + watcher.start() + try: + results = self._run_concurrently(search, range(40), workers=8) + finally: + stop.set() + watcher.join() + + self.assertTrue(all(result is not None for result in results)) + self.assertEqual(observed, {baseline}) + + def test_detect_language_does_not_leave_narrowed_detector_on_instance(self) -> None: + # Issue #1369 site 1: detect_language used to stash a FullTextLanguageDetector + # on the process-wide singleton. _best_language narrows detector.languages + # in place, so a concurrent search_dates can load another call's already- + # narrowed detector and return None or a wrong date. + ds = DateSearchWithDetection() + detected = ds.detect_language("19 марта 2001", languages=["ru", "en"]) + self.assertEqual(detected, "ru") + detector = getattr(ds, "language_detector", None) + if detector is not None: + leftover = [locale.shortname for locale in detector.languages] + self.assertEqual( + set(leftover), + {"ru", "en"}, + "detect_language left a single-use detector narrowed in place " + "on the instance; concurrent search_dates can observe this " + f"(issue #1369). leftover={leftover!r}", + ) + + def test_concurrent_search_dates_does_not_share_language_detector(self) -> None: + # Issue #1369 site 1: the store/load gap is a few bytecodes, so park each + # thread immediately after it stores the detector. Sequential search_dates + # is not a valid RED for this race. + ru_text = "Договор подписан 19 марта 2001 года в Москве" + en_text = "The satellite was launched on 4 October 1957 from Baikonur" + sequential_ru = search_dates(ru_text, languages=["ru"]) + sequential_en = search_dates(en_text, languages=["en"]) + self.assertIsNotNone(sequential_ru) + self.assertIsNotNone(sequential_en) + + slot: dict[str, object] = {} + barrier = threading.Barrier(2, timeout=10) + + def _get(self: DateSearchWithDetection) -> object: + return slot["v"] + + def _set(self: DateSearchWithDetection, value: object) -> None: + slot["v"] = value + with contextlib.suppress(threading.BrokenBarrierError): + barrier.wait() + + DateSearchWithDetection.language_detector = property(_get, _set) # type: ignore[attr-defined] + try: + with ThreadPoolExecutor(max_workers=2) as executor: + ru, en = executor.map( + lambda args: search_dates(args[0], languages=[args[1]]), + [(ru_text, "ru"), (en_text, "en")], + ) + finally: + del DateSearchWithDetection.language_detector # type: ignore[attr-defined] + + self.assertEqual(ru, sequential_ru) + self.assertEqual(en, sequential_en) + + def test_concurrent_search_dates_does_not_share_locale_slot(self) -> None: + # Issue #1369 site 2: _ExactLanguageSearch.self.language is a 1-slot cache + # on the same singleton. Park after get_current_language so a store from + # the other thread lands before translate_search. + ru_text = "Договор подписан 19 марта 2001 года в Москве" + en_text = "The satellite was launched on 4 October 1957 from Baikonur" + sequential_ru = search_dates(ru_text, languages=["ru"]) + sequential_en = search_dates(en_text, languages=["en"]) + self.assertIsNotNone(sequential_ru) + self.assertIsNotNone(sequential_en) + + original = _ExactLanguageSearch.get_current_language + barrier = threading.Barrier(2, timeout=10) + + def patched(self: _ExactLanguageSearch, shortname: str) -> Locale: + result = original(self, shortname) + with contextlib.suppress(threading.BrokenBarrierError): + barrier.wait() + return result + + _ExactLanguageSearch.get_current_language = patched # type: ignore[method-assign] + try: + with ThreadPoolExecutor(max_workers=2) as executor: + ru, en = executor.map( + lambda args: search_dates(args[0], languages=[args[1]]), + [(ru_text, "ru"), (en_text, "en")], + ) + finally: + _ExactLanguageSearch.get_current_language = original # type: ignore[method-assign] + + self.assertEqual(ru, sequential_ru) + self.assertEqual(en, sequential_en) + + +if __name__ == "__main__": + unittest.main() diff --git a/tests/test_timezone_parser.py b/tests/test_timezone_parser.py index 5279fa622..8a58ab468 100644 --- a/tests/test_timezone_parser.py +++ b/tests/test_timezone_parser.py @@ -1,5 +1,7 @@ import datetime as dt from datetime import datetime, timedelta +from types import ModuleType +from typing import ClassVar from unittest import SkipTest from unittest.mock import Mock, patch @@ -10,18 +12,22 @@ from dateparser import parse from dateparser.timezone_parser import ( StaticTzInfo, + convert_to_local_tz, get_local_tz_offset, + is_timezone_token, pop_tz_offset_from_string, + word_is_tz, ) +from dateparser_scripts import tz_abbreviation_conflicts from tests import BaseTestCase class TestTZPopping(BaseTestCase): - def setUp(self): + def setUp(self) -> None: super().setUp() - self.initial_string = self.datetime_string = self.timezone_offset = ( - NotImplemented - ) + self.initial_string: str = NotImplemented + self.datetime_string: str = NotImplemented + self.timezone_offset: timedelta | None = NotImplemented @parameterized.expand( [ @@ -67,7 +73,9 @@ def setUp(self): param("16. srpna 2021 9:59:44 VEČ", 2), ] ) - def test_extracting_valid_offset(self, initial_string, expected_offset): + def test_extracting_valid_offset( + self, initial_string: str, expected_offset: float | None + ) -> None: self.given_string(initial_string) self.when_offset_popped_from_string() self.then_offset_is(expected_offset) @@ -86,44 +94,74 @@ def test_extracting_valid_offset(self, initial_string, expected_offset): "17th October, 2034 @ 01:08 am +0700", "17th October, 2034 @ 01:08 am " ), param("Sep 03 2014 4:32 pm +0630", "Sep 03 2014 4:32 pm "), + param( + "Thu 30 May 2024 10:13:10 -0500 CDT", + "Thu 30 May 2024 10:13:10 ", + ), + param( + "Thu 30 May 2024 10:13:10 CDT -0500", + "Thu 30 May 2024 10:13:10 ", + ), + param("2019-09-28WIB19:17:34+07:00", "2019-09-28 19:17:34"), ] ) - def test_timezone_deleted_from_string(self, initial_string, result_string): + def test_timezone_deleted_from_string( + self, initial_string: str, result_string: str + ) -> None: self.given_string(initial_string) self.when_offset_popped_from_string() self.then_string_modified_to(result_string) - def test_string_not_changed_if_no_timezone(self): + def test_string_not_changed_if_no_timezone(self) -> None: self.given_string("15 May 2004") self.when_offset_popped_from_string() self.then_string_modified_to("15 May 2004") - def given_string(self, string_): + def given_string(self, string_: str) -> None: self.initial_string = string_ - def when_offset_popped_from_string(self): + def when_offset_popped_from_string(self) -> None: self.datetime_string, timezone_offset = pop_tz_offset_from_string( self.initial_string ) - if timezone_offset: - self.timezone_offset = timezone_offset.utcoffset("") + if timezone_offset is not None: + self.timezone_offset = timezone_offset.utcoffset(None) else: self.timezone_offset = timezone_offset - def then_string_modified_to(self, expected_string): + def then_string_modified_to(self, expected_string: str) -> None: self.assertEqual(expected_string, self.datetime_string) - def then_offset_is(self, expected_offset): + def then_offset_is(self, expected_offset: float | None) -> None: delta = ( timedelta(hours=expected_offset) if expected_offset is not None else None ) self.assertEqual(delta, self.timezone_offset) +class TestUnicodeDashOffsets(BaseTestCase): + @parameterized.expand( + [ + param("jan 15th UTC‐06:00", -6), # HYPHEN + param("jan 15th UTC–06:00", -6), # EN DASH + param("jan 15th UTC—06:00", -6), # EM DASH + param("jan 15th UTC−06:00", -6), # MINUS SIGN + param("jan 15th UTC-06:00", -6), # FULLWIDTH HYPHEN-MINUS + param("jan 15th UTC+06:00", 6), + ] + ) + def test_parses_dash_look_alike_offsets( + self, date_string: str, expected_offset_hours: int + ) -> None: + parsed = parse(date_string) + assert parsed is not None + self.assertEqual(parsed.utcoffset(), timedelta(hours=expected_offset_hours)) + + class TestLocalTZOffset(BaseTestCase): - def setUp(self): + def setUp(self) -> None: super().setUp() - self.timezone_offset = NotImplemented + self.timezone_offset: timedelta = NotImplemented @parameterized.expand( [ @@ -134,7 +172,9 @@ def setUp(self): param(utc="2014-10-18 17:41", local="2014-10-18 17:41", offset=0), ] ) - def test_timezone_offset_calculation(self, utc, local, offset): + def test_timezone_offset_calculation( + self, utc: str, local: str, offset: float + ) -> None: try: self.given_time(utc, local) except OverflowError: @@ -142,10 +182,10 @@ def test_timezone_offset_calculation(self, utc, local, offset): self.when_offset_popped_from_string() self.then_offset_is(offset) - def when_offset_popped_from_string(self): + def when_offset_popped_from_string(self) -> None: self.timezone_offset = get_local_tz_offset() - def then_offset_is(self, expected_offset): + def then_offset_is(self, expected_offset: float | None) -> None: delta = ( timedelta(seconds=3600 * expected_offset) if expected_offset is not None @@ -153,8 +193,8 @@ def then_offset_is(self, expected_offset): ) self.assertEqual(delta, self.timezone_offset) - def given_time(self, utc_dt_string, local_dt_string): - datetime_cls = dateparser.timezone_parser.datetime + def given_time(self, utc_dt_string: str, local_dt_string: str) -> None: + datetime_cls = dateparser.timezone_parser.datetime # type: ignore[attr-defined] if not isinstance(datetime_cls, Mock): datetime_cls = Mock(wraps=datetime) utc_dt_obj = datetime.strptime(utc_dt_string, "%Y-%m-%d %H:%M").replace( @@ -162,7 +202,7 @@ def given_time(self, utc_dt_string, local_dt_string): ) local_dt_obj = datetime.strptime(local_dt_string, "%Y-%m-%d %H:%M") - def _dt_now(tz=None): + def _dt_now(tz: dt.tzinfo | None = None) -> datetime: if tz == dt.timezone.utc: return utc_dt_obj return local_dt_obj @@ -172,11 +212,11 @@ def _dt_now(tz=None): class TestTimeZoneConversion(BaseTestCase): - def setUp(self): + def setUp(self) -> None: super().setUp() - self.settings = {} + self.settings: dict[str, str] = {} self.parser = parse - self.result = NotImplemented + self.result: datetime | None = NotImplemented @parameterized.expand( [ @@ -194,27 +234,29 @@ def setUp(self): ), ] ) - def test_timezone_conversion(self, datestring, from_tz, to_tz, expected): + def test_timezone_conversion( + self, datestring: str, from_tz: str, to_tz: str, expected: datetime + ) -> None: self.given_from_timezone(from_tz) self.given_to_timezone(to_tz) self.when_date_is_parsed(datestring) self.then_date_is(expected) - def given_from_timezone(self, timezone): + def given_from_timezone(self, timezone: str) -> None: self.settings["TIMEZONE"] = timezone - def given_to_timezone(self, timezone): + def given_to_timezone(self, timezone: str) -> None: self.settings["TO_TIMEZONE"] = timezone - def when_date_is_parsed(self, datestring): + def when_date_is_parsed(self, datestring: str) -> None: self.result = self.parser(datestring, settings=self.settings) - def then_date_is(self, date): + def then_date_is(self, date: datetime) -> None: self.assertEqual(date, self.result) class TestStaticTzInfo(BaseTestCase): - def setUp(self): + def setUp(self) -> None: super().setUp() @parameterized.expand( @@ -224,19 +266,256 @@ def setUp(self): param(given_date=datetime(2000, 2, 20, tzinfo=timezone("Pacific/Samoa"))), ] ) - def test_localize_raises_error_if_date_has_tzinfo(self, given_date): + def test_localize_raises_error_if_date_has_tzinfo( + self, given_date: datetime + ) -> None: self.timezone_info = StaticTzInfo("UTC\\+00:00", timedelta(0)) self.when_date_is_localized(given_date) self.then_error_was_raised( ValueError, ["Not naive datetime (tzinfo is already set)"] ) - def when_date_is_localized(self, given_date): + def when_date_is_localized(self, given_date: datetime) -> None: try: self.localized_date = self.timezone_info.localize(given_date) except Exception as error: self.error = error - def then_localized_date_is(self, expected_date, expected_tzname): + def then_localized_date_is( + self, expected_date: datetime, expected_tzname: str + ) -> None: self.assertEqual(self.localized_date.date(), expected_date.date()) self.assertEqual(self.localized_date.tzname(), expected_tzname) + + +class TestIsTimezoneToken(BaseTestCase): + """Unit tests for ``is_timezone_token``, used to keep a trailing timezone + when ``IGNORE_SURROUNDING_TEXT`` strips edge tokens.""" + + @parameterized.expand( + [ + param(token="EST", expected=True), + # Already-lowercased and space-padded tokens (as produced by the + # translation pipeline) are recognized too. + param(token="est", expected=True), + param(token=" est", expected=True), + param(token="cet", expected=True), + param(token="pst", expected=True), + param(token="utc", expected=True), + # A longer word that merely starts with a timezone abbreviation must + # not be treated as a timezone. + param(token="actualisé", expected=False), + param(token="ACTUALISÉ", expected=False), + param(token="updated", expected=False), + param(token="", expected=False), + param(token=" ", expected=False), + ] + ) + def test_is_timezone_token(self, token: str, expected: bool) -> None: + self.assertEqual(expected, is_timezone_token(token)) + + def test_anchored_match_unlike_word_is_tz(self) -> None: + # word_is_tz prefix-matches ("ACT" of "ACTUALISÉ"); is_timezone_token is + # anchored, so it does not — this is what keeps a noise word from + # surviving as a timezone when edges are stripped. + self.assertTrue(word_is_tz("ACTUALISÉ")) + self.assertFalse(is_timezone_token("ACTUALISÉ")) + + +class TestTzDatabasePreference(BaseTestCase): + """Tests for #1322: prefer the tz database for conflicting abbreviations. + + ``dateparser/timezones.py`` maps every timezone abbreviation to a single UTC + offset, and unrelated zones often share the same letters. The table was + scraped from Wikipedia, so a few abbreviations ended up with a meaning no tz + database zone has: "BST" resolved to +11, although the only zone named "BST" + today is British Summer Time at +1 (#1321). + + The rule pinned down here is that when the tz database names exactly one + offset for an abbreviation, dateparser has to use it, and when the tz + database names several, dateparser's existing choice is left alone. + + The tests that exercise the comparison itself run against + ``FROZEN_TZ_DATABASE`` so that they keep testing the same logic as the tz + database changes; the two that check dateparser's actual data are the ones + that read the installed tz database. + """ + + # A stand-in for the tz database: "BST"/"HDT" named by one offset each, + # "CST" by three (US Central, Cuba, China). + FROZEN_TZ_DATABASE = { + "BST": {3600}, + "HDT": {-32400}, + "CST": {-21600, -18000, 28800}, + } + + checker: ClassVar[ModuleType] + tz_database: ClassVar[dict[str, set[int]]] + + @classmethod + def setUpClass(cls) -> None: + super().setUpClass() + cls.checker = tz_abbreviation_conflicts + # Sampling every zone takes a moment, so it is done once for the class. + cls.tz_database = tz_abbreviation_conflicts.tz_database_abbreviations() + + def offset_of(self, date_string: str) -> timedelta: + _, timezone_offset = pop_tz_offset_from_string(date_string) + self.assertIsNotNone(timezone_offset, f"no timezone found in {date_string!r}") + assert timezone_offset is not None + return timezone_offset.utcoffset(None) + + @parameterized.expand( + [ + # British Summer Time, the case reported in #1321. + param("13 August 2026 10:00 BST", +1, "BST"), + # Hawaii-Aleutian Daylight Time (America/Adak). The table used + # -9:30, which is what Pacific/Honolulu called "HDT" back when + # Hawaii kept -10:30; no zone has been named that since. + param("13 August 2026 10:00 HDT", -9, "HDT"), + ] + ) + def test_unambiguous_abbreviation_uses_tz_database_offset( + self, date_string: str, expected_offset: float, abbreviation: str + ) -> None: + self.assertEqual(timedelta(hours=expected_offset), self.offset_of(date_string)) + # And the tz database really does name only that one offset. + self.assertEqual({int(expected_offset * 3600)}, self.tz_database[abbreviation]) + + @parameterized.expand( + [ + param("13 August 2026 10:00 BST", +1, "BST"), + param("13 August 2026 10:00 HDT", -9, "HDT"), + ] + ) + def test_unambiguous_abbreviation_parses_end_to_end( + self, date_string: str, expected_offset: float, abbreviation: str + ) -> None: + # The #1321 report as a user would hit it, not just at the popping layer. + parsed = parse(date_string, settings={"RETURN_AS_TIMEZONE_AWARE": True}) + assert parsed is not None + self.assertEqual(timedelta(hours=expected_offset), parsed.utcoffset()) + self.assertEqual(abbreviation, parsed.tzname()) + + @parameterized.expand( + [ + # US Central, but "CST" also names Cuba (-5) and China (+8). + param("13 August 2026 10:00 CST", -6), + # US Central Daylight, but "CDT" also names Cuba (-4). + param("13 August 2026 10:00 CDT", -5), + # Israel, but "IST" also names India (+5:30) and Ireland (+1). + param("13 August 2026 10:00 IST", +2), + # US Pacific, but "PST" also names the Philippines (+8). + param("13 August 2026 10:00 PST", -8), + ] + ) + def test_ambiguous_abbreviation_keeps_its_offset( + self, date_string: str, expected_offset: float + ) -> None: + # These keep the value dateparser has always used. The assertion below + # holds whether or not the abbreviation stays ambiguous: what matters is + # that the retained value is one a real zone uses, not an arbitrary one. + self.assertEqual(timedelta(hours=expected_offset), self.offset_of(date_string)) + abbreviation = date_string.rsplit(" ", 1)[1] + self.assertIn(int(expected_offset * 3600), self.tz_database[abbreviation]) + + def test_table_agrees_with_the_tz_database(self) -> None: + # The generalized check behind #1322: instead of asserting a fixed list + # of abbreviations, ask the tz database about every abbreviation the two + # tables share, so a regression on any of them is caught. + shared = set(self.checker.static_tz_abbreviations()) & set(self.tz_database) + # Without this, the assertion below would also pass if the comparison + # silently stopped covering anything. + self.assertGreater( + len(shared), 40, f"only {len(shared)} abbreviations compared" + ) + conflicts = self.checker.find_conflicts(tz_database=self.tz_database) + self.assertEqual([], conflicts, f"conflicts with the tz database: {conflicts}") + + def test_report_runs_clean(self) -> None: + # Exercises the module's entry point with its real defaults, which the + # test above bypasses by passing the tz database in. + self.assertEqual(0, self.checker.main()) + + def test_reference_years_stay_in_settled_years(self) -> None: + # The tz database records future daylight-saving rules as predictions + # that change between releases, so sampling them would tie the result to + # the installed version rather than to real usage. + self.assertLess(max(self.checker.REFERENCE_YEARS), datetime.now().year) + + def test_pre_fix_offsets_are_reported_as_conflicts(self) -> None: + # Reproduces the bug this change fixes, and keeps the whole-table check + # from passing vacuously: the offsets shipped before #1322 are flagged. + conflicts = self.checker.find_conflicts( + static={"BST": 39600, "HDT": -34200}, + tz_database=self.FROZEN_TZ_DATABASE, + ) + self.assertEqual( + [ + ("BST", "unambiguous", 39600, [3600]), + ("HDT", "unambiguous", -34200, [-32400]), + ], + [tuple(conflict) for conflict in conflicts], + ) + + def test_offset_no_zone_uses_is_reported_even_when_ambiguous(self) -> None: + # "CST" has several meanings, so none of them can be preferred, but +11 + # is not one of them and is still worth reporting. + (conflict,) = self.checker.find_conflicts( + static={"CST": 39600}, tz_database=self.FROZEN_TZ_DATABASE + ) + self.assertEqual("CST", conflict.abbreviation) + self.assertEqual("unsupported", conflict.kind) + self.assertNotIn(39600, conflict.tz_database_offsets) + + @parameterized.expand([param(-21600), param(28800)]) + def test_any_offset_a_zone_really_uses_is_accepted(self, offset: int) -> None: + # Both US Central (-6) and China (+8) are legitimate readings of "CST". + self.assertEqual( + [], + self.checker.find_conflicts( + static={"CST": offset}, tz_database=self.FROZEN_TZ_DATABASE + ), + ) + + def test_abbreviations_outside_the_reference_window_are_ignored(self) -> None: + # dateparser keeps abbreviations no zone is named after any more, such + # as "AHST", so historical text still parses. The tz database says + # nothing about them, so they are skipped rather than reported. + self.assertNotIn("AHST", self.tz_database) + self.assertEqual( + [], + self.checker.find_conflicts( + static={"AHST": -36000}, tz_database=self.FROZEN_TZ_DATABASE + ), + ) + + def test_abbreviations_are_compared_case_insensitively(self) -> None: + # dateparser matches abbreviations regardless of case, so the table's + # "ChST" entry and the tz database's "ChST" are one abbreviation and + # have to meet under the same key. + self.assertIn("CHST", self.checker.static_tz_abbreviations()) + self.assertIn("CHST", self.tz_database) + + def test_numeric_zone_names_are_not_treated_as_abbreviations(self) -> None: + # The tz database names zones that have no established abbreviation + # after their offset, as in "+11" or "-0930". Those are offsets rather + # than identities, and dateparser matches numeric offsets through its + # separate UTC/GMT patterns, so they stay out of this comparison. + self.assertEqual([], [name for name in self.tz_database if name[0] in "+-"]) + self.assertIn("BST", self.tz_database) + + def test_repeated_abbreviation_resolves_to_its_first_entry(self) -> None: + # "LMT" is listed four times with four different offsets. Only the first + # can ever match, so that is the value the comparison has to use; + # checking against all four would hide a wrong first entry. + self.assertEqual( + self.checker.static_tz_abbreviations()["LMT"], + self.offset_of("13 August 2026 10:00 LMT").total_seconds(), + ) + + +class TestConvertToLocalTz(BaseTestCase): + def test_deprecated(self) -> None: + with self.assertWarns(FutureWarning): + convert_to_local_tz(datetime(2020, 1, 1), timedelta(0)) diff --git a/tests/test_utils.py b/tests/test_utils.py index d107a8644..b5cda903c 100644 --- a/tests/test_utils.py +++ b/tests/test_utils.py @@ -1,11 +1,18 @@ +import calendar import itertools +from collections.abc import Callable from datetime import datetime +from unittest.mock import patch import pytest from parameterized import param, parameterized from pytz import UnknownTimeZoneError, utc +from pytz.tzinfo import BaseTzInfo +import dateparser from dateparser.conf import settings +from dateparser.search import search_dates +from dateparser.timezone_parser import StaticTzInfo from dateparser.utils import ( apply_timezone, apply_timezone_from_settings, @@ -16,31 +23,39 @@ localize_timezone, registry, ) +from dateparser.utils.strptime import patch_strptime from tests import BaseTestCase class TestUtils(BaseTestCase): - def setUp(self): + def setUp(self) -> None: super().setUp() - self.date_format = None - self.result = None + self.date_format: str | None = None + self.result: str | None = None - def given_date_format(self, date_format): + def test_patch_strptime_preserves_global_calendar(self) -> None: + before = vars(calendar).copy() + patch_strptime() + self.assertEqual(set(vars(calendar)), set(before)) + for name, value in before.items(): + self.assertIs(getattr(calendar, name), value, name) + + def given_date_format(self, date_format: str) -> None: self.date_format = date_format - def when_date_separator_is_parsed(self): + def when_date_separator_is_parsed(self) -> None: + assert self.date_format is not None self.result = find_date_separator(self.date_format) - def then_date_separator_is(self, sep): + def then_date_separator_is(self, sep: str | None) -> None: self.assertEqual(self.result, sep) @staticmethod - def make_class_without_get_keys(): + def make_class_without_get_keys() -> type: class SomeClass: pass - some_class = SomeClass - return some_class + return SomeClass @parameterized.expand( [ @@ -50,11 +65,16 @@ class SomeClass: ) ] ) - def test_separator_extraction(self, date_format, expected_sep): + def test_separator_extraction(self, date_format: str, expected_sep: str) -> None: self.given_date_format(date_format) self.when_date_separator_is_parsed() self.then_date_separator_is(expected_sep) + def test_separator_extraction_without_separator(self) -> None: + self.given_date_format("%Y") + self.when_date_separator_is_parsed() + self.then_date_separator_is(None) + @parameterized.expand( [ param(datetime(2015, 12, 12), timezone="UTC", zone="UTC"), @@ -62,8 +82,11 @@ def test_separator_extraction(self, date_format, expected_sep): param(datetime(2015, 12, 12, tzinfo=utc), timezone="UTC", zone="UTC"), ] ) - def test_localize_timezone_function(self, date, timezone, zone): + def test_localize_timezone_function( + self, date: datetime, timezone: str, zone: str + ) -> None: tzaware_dt = localize_timezone(date, timezone) + assert isinstance(tzaware_dt.tzinfo, BaseTzInfo) self.assertEqual(tzaware_dt.tzinfo.zone, zone) @parameterized.expand( @@ -72,7 +95,9 @@ def test_localize_timezone_function(self, date, timezone, zone): param(datetime(2015, 12, 12), timezone="Asia/Karach"), ] ) - def test_localize_timezone_function_raise_error(self, date, timezone): + def test_localize_timezone_function_raise_error( + self, date: datetime, timezone: str + ) -> None: self.assertRaises(UnknownTimeZoneError, localize_timezone, date, timezone) @parameterized.expand( @@ -80,9 +105,12 @@ def test_localize_timezone_function_raise_error(self, date, timezone): param(datetime(2015, 12, 12), timezone="UTC+3", zone=r"UTC\+03:00"), ] ) - def test_localize_timezone_function_exception(self, date, timezone, zone): + def test_localize_timezone_function_exception( + self, date: datetime, timezone: str, zone: str + ) -> None: tzaware_dt = localize_timezone(date, timezone) - self.assertEqual(tzaware_dt.tzinfo._StaticTzInfo__name, zone) + assert isinstance(tzaware_dt.tzinfo, StaticTzInfo) + self.assertEqual(tzaware_dt.tzinfo.tzname(None), zone) @parameterized.expand( [ @@ -98,7 +126,9 @@ def test_localize_timezone_function_exception(self, date, timezone, zone): ), ] ) - def test_apply_timezone_function(self, date, timezone, expected): + def test_apply_timezone_function( + self, date: datetime, timezone: str, expected: datetime + ) -> None: result = apply_timezone(date, timezone) result = result.replace(tzinfo=None) self.assertEqual(expected, result) @@ -117,9 +147,11 @@ def test_apply_timezone_function(self, date, timezone, expected): ), ] ) - def test_apply_timezone_from_settings_function(self, date, timezone, expected): + def test_apply_timezone_from_settings_function( + self, date: datetime, timezone: str, expected: datetime + ) -> None: result = apply_timezone_from_settings( - date, settings.replace(**{"TO_TIMEZONE": timezone, "TIMEZONE": "UTC"}) + date, settings.replace(TO_TIMEZONE=timezone, TIMEZONE="UTC") ) self.assertEqual(expected, result) @@ -130,7 +162,9 @@ def test_apply_timezone_from_settings_function(self, date, timezone, expected): ), ] ) - def test_apply_timezone_from_settings_function_none_settings(self, date, expected): + def test_apply_timezone_from_settings_function_none_settings( + self, date: datetime, expected: datetime + ) -> None: result = apply_timezone_from_settings(date, None) self.assertEqual(expected, result) @@ -144,13 +178,15 @@ def test_apply_timezone_from_settings_function_none_settings(self, date, expecte ), ] ) - def test_apply_timezone_from_settings_function_should_return_tz(self, date): + def test_apply_timezone_from_settings_function_should_return_tz( + self, date: datetime + ) -> None: result = apply_timezone_from_settings( - date, settings.replace(**{"RETURN_AS_TIMEZONE_AWARE": True}) + date, settings.replace(RETURN_AS_TIMEZONE_AWARE=True) ) self.assertTrue(bool(result.tzinfo)) - def test_registry_when_get_keys_not_implemented(self): + def test_registry_when_get_keys_not_implemented(self) -> None: cl = self.make_class_without_get_keys() self.assertRaises(NotImplementedError, registry, cl) @@ -173,12 +209,14 @@ def test_registry_when_get_keys_not_implemented(self): param(2300, 12, 31), ] ) - def test_get_last_day_of_month(self, year, month, expected_last_day): + def test_get_last_day_of_month( + self, year: int, month: int, expected_last_day: int + ) -> None: assert get_last_day_of_month(year, month) == expected_last_day @pytest.mark.parametrize( - "year,expected_previous_leap_year", + ("year", "expected_previous_leap_year"), [ (2020, 2016), (2000, 1996), # leap and centurial year @@ -188,12 +226,12 @@ def test_get_last_day_of_month(self, year, month, expected_last_day): (0, -4), # even if this is not a valid year, it is the expected result ], ) -def test_get_previous_leap_year(year, expected_previous_leap_year): +def test_get_previous_leap_year(year: int, expected_previous_leap_year: int) -> None: assert get_previous_leap_year(year) == expected_previous_leap_year @pytest.mark.parametrize( - "year,expected_next_leap_year", + ("year", "expected_next_leap_year"), [ (2020, 2024), (1996, 2000), # leap and centurial year @@ -203,5 +241,25 @@ def test_get_previous_leap_year(year, expected_previous_leap_year): (0, 4), ], ) -def test_get_next_leap_year(year, expected_next_leap_year): +def test_get_next_leap_year(year: int, expected_next_leap_year: int) -> None: assert get_next_leap_year(year) == expected_next_leap_year + + +@pytest.mark.parametrize( + "parse", + [ + lambda: dateparser.parse("4 October 1957"), + lambda: dateparser.parse("yesterday"), + lambda: dateparser.parse("1570308760"), + lambda: search_dates("It was launched on 4 October 1957.", languages=["en"]), + ], +) +def test_broken_local_timezone(parse: Callable[[], object]) -> None: + with ( + patch( + "dateparser.utils.get_localzone", + side_effect=ValueError("ZoneInfo keys may not be absolute paths"), + ), + pytest.raises(RuntimeError, match="Could not determine the local timezone"), + ): + parse() diff --git a/tests/test_utils_strptime.py b/tests/test_utils_strptime.py index 529158af7..6edc58b1c 100644 --- a/tests/test_utils_strptime.py +++ b/tests/test_utils_strptime.py @@ -1,7 +1,7 @@ import locale +import warnings from datetime import datetime from unittest import SkipTest -import warnings from parameterized import param, parameterized @@ -10,31 +10,33 @@ class TestStrptime(BaseTestCase): - def setUp(self): + def setUp(self) -> None: super().setUp() - def given_system_locale_is(self, locale_str): + def given_system_locale_is(self, locale_str: str) -> None: try: locale.setlocale(locale.LC_ALL, locale_str) except locale.Error: - raise SkipTest("Locale {} is not installed".format(locale_str)) + raise SkipTest(f"Locale {locale_str} is not installed") - def when_date_string_is_parsed(self, date_string, fmt): + def when_date_string_is_parsed(self, date_string: str, fmt: str) -> None: try: - self.result = strptime(date_string, fmt) + self.result: datetime | ValueError = strptime(date_string, fmt) except ValueError as e: self.result = e - def when_date_string_is_parsed_using_datetime_strptime(self, date_string, fmt): + def when_date_string_is_parsed_using_datetime_strptime( + self, date_string: str, fmt: str + ) -> None: try: self.result = datetime.strptime(date_string, fmt) except ValueError as e: self.result = e - def then_date_object_is(self, expected): + def then_date_object_is(self, expected: datetime) -> None: assert self.result == expected - def then_date_object_is_instance_of(self, expected): + def then_date_object_is_instance_of(self, expected: type[Exception]) -> None: assert isinstance(self.result, expected) @parameterized.expand( @@ -70,8 +72,8 @@ def then_date_object_is_instance_of(self, expected): ] ) def test_dates_with_months_are_parsed_if_locale_is_non_english( - self, date_string, fmt, expected - ): + self, date_string: str, fmt: str, expected: datetime + ) -> None: self.given_system_locale_is("fr_FR.UTF-8") self.when_date_string_is_parsed(date_string, fmt) self.then_date_object_is(expected) @@ -102,15 +104,15 @@ def test_dates_with_months_are_parsed_if_locale_is_non_english( ] ) def test_dates_with_days_are_parsed_if_locale_is_non_english( - self, date_string, fmt, expected - ): + self, date_string: str, fmt: str, expected: datetime + ) -> None: self.given_system_locale_is("fr_FR.UTF-8") self.when_date_string_is_parsed(date_string, fmt) self.then_date_object_is(expected) def test_parsing_date_should_fail_using_datetime_strptime_if_locale_is_non_english( self, - ): + ) -> None: self.given_system_locale_is("fr_FR.UTF-8") self.when_date_string_is_parsed_using_datetime_strptime( "21 february 2010", "%d %B %Y" @@ -171,7 +173,9 @@ def test_parsing_date_should_fail_using_datetime_strptime_if_locale_is_non_engli ), ] ) - def test_microseconds_are_parsed_correctly(self, date_string, fmt, expected): + def test_microseconds_are_parsed_correctly( + self, date_string: str, fmt: str, expected: datetime + ) -> None: self.when_date_string_is_parsed(date_string, fmt) self.then_date_object_is(expected) @@ -184,8 +188,8 @@ def test_microseconds_are_parsed_correctly(self, date_string, fmt, expected): ] ) def test_dates_with_no_year_do_not_raise_a_deprecation_warning( - self, date_string, fmt - ): + self, date_string: str, fmt: str + ) -> None: with warnings.catch_warnings(record=True) as w: warnings.simplefilter("always") self.when_date_string_is_parsed(date_string, fmt) @@ -233,8 +237,66 @@ def test_dates_with_no_year_do_not_raise_a_deprecation_warning( ) def test_dates_with_no_year_use_the_current_year( self, date_string: str, fmt: str, expected: datetime - ): + ) -> None: self.when_date_string_is_parsed(date_string, fmt) current_year = datetime.today().year expected = expected.replace(year=current_year) self.assertEqual(self.result, expected) + + @parameterized.expand( + [ + param("1999001", "%Y%j", expected=datetime(1999, 1, 1)), + param("1999032", "%Y%j", expected=datetime(1999, 2, 1)), + param("1999050", "%Y%j", expected=datetime(1999, 2, 19)), + param("1999059", "%Y%j", expected=datetime(1999, 2, 28)), + param("1999060", "%Y%j", expected=datetime(1999, 3, 1)), + param("1999365", "%Y%j", expected=datetime(1999, 12, 31)), + param("2000060", "%Y%j", expected=datetime(2000, 2, 29)), + param("2000061", "%Y%j", expected=datetime(2000, 3, 1)), + param("2000366", "%Y%j", expected=datetime(2000, 12, 31)), + param("2400366", "%Y%j", expected=datetime(2400, 12, 31)), + param("2023-100", "%Y-%j", expected=datetime(2023, 4, 10)), + param("2024 366", "%Y %j", expected=datetime(2024, 12, 31)), + param("1999001 12:30", "%Y%j %H:%M", expected=datetime(1999, 1, 1, 12, 30)), + ] + ) + def test_day_of_year_is_parsed( + self, date_string: str, fmt: str, expected: datetime + ) -> None: + self.when_date_string_is_parsed(date_string, fmt) + self.then_date_object_is(expected) + + @parameterized.expand( + [ + # 366 is only a valid day of year in leap years. + param("1999366", "%Y%j"), + param("2023-366", "%Y-%j"), + param("1900366", "%Y%j"), # divisible by 100 but not by 400 + param("2100366", "%Y%j"), + param("2025366 12:30", "%Y%j %H:%M"), + # Values that strptime itself rejects. + param("1999000", "%Y%j"), + param("1999367", "%Y%j"), + param("1999777", "%Y%j"), + ] + ) + def test_day_of_year_out_of_range_is_not_parsed( + self, date_string: str, fmt: str + ) -> None: + self.when_date_string_is_parsed(date_string, fmt) + self.then_date_object_is_instance_of(ValueError) + + @parameterized.expand( + [ + param("%j", "%%j", expected=datetime(1900, 1, 1)), + param("1999%j", "%Y%%j", expected=datetime(1999, 1, 1)), + # A literal "%j" must not be taken for a day of year directive, not + # even when another directive rolls the year over. + param("2023 53 1 %j", "%Y %U %w %%j", expected=datetime(2024, 1, 1)), + ] + ) + def test_escaped_day_of_year_directive_is_a_literal( + self, date_string: str, fmt: str, expected: datetime + ) -> None: + self.when_date_string_is_parsed(date_string, fmt) + self.then_date_object_is(expected) diff --git a/tests/test_whitespace_preservation.py b/tests/test_whitespace_preservation.py new file mode 100644 index 000000000..9620e15d7 --- /dev/null +++ b/tests/test_whitespace_preservation.py @@ -0,0 +1,108 @@ +""" +Tests for issue #1302: Whitespace preservation during translation +""" + +from typing import TYPE_CHECKING + +from parameterized import param, parameterized + +from dateparser.conf import settings +from dateparser.languages import default_loader +from tests import BaseTestCase + +if TYPE_CHECKING: + from dateparser.languages.locale import Locale + + +class TestWhitespacePreservation(BaseTestCase): + """ + Tests to ensure that whitespace is preserved exactly when translating + date strings, even when tokens are removed from the skip list (e.g., "klo" in Finnish). + + Issue #1302: Extra whitespace handling during date translation + """ + + def setUp(self) -> None: + super().setUp() + self.language: Locale = NotImplemented + self.datetime_string: str = NotImplemented + self.translation: str = NotImplemented + self.settings = settings + + @parameterized.expand( + [ + # Finnish: "klo" is a skip word + param("fi", "28 maalis klo 9:37", "28 march 9:37"), + param("fi", "28 maalis klo 9:37", "28 march 9:37"), + param("fi", "28 maalis klo 9:37", "28 march 9:37"), + param("fi", "28 maalis klo 9:37", "28 march 9:37"), + param( + "fi", "tiistaina 27. lokakuuta 2015", "tuesday 27. october 2015" + ), + # Czech: "v" translates to "in", then cleared by _clear_future_words + param("cs", "22. prosinec 2014 v 2:38", "22. december 2014 2:38"), + param("cs", "22. prosinec 2014 v 2:38", "22. december 2014 2:38"), + # Polish: "o" is a skip word + param("pl", "4 stycznia o 13:50", "4 january 13:50"), + param("pl", "29 listopada 2014 o 08:40", "29 november 2014 08:40"), + # Russian: "в" is a skip word + param("ru", "5 августа 2014 г. в 12:00", "5 august 2014 year. 12:00"), + # Ukrainian: "о"/"об" are skip words + param("uk", "30 листопада 2013 о 04:27", "30 november 2013 04:27"), + # Croatian: "u" translates to "in", then cleared + param("hr", "13. svibanj 2022. u 14:34", "13. may 2022. 14:34"), + ] + ) + def test_whitespace_preservation_during_translation( + self, shortname: str, datetime_string: str, expected_translation: str + ) -> None: + """Test that exact whitespace is preserved when translating date strings.""" + self.given_bundled_language(shortname) + self.given_string(datetime_string) + self.when_datetime_string_translated() + self.then_string_translated_to(expected_translation) + + @parameterized.expand( + [ + # Finnish: keep_formatting=True + param("fi", "28 maalis klo 9:37", "28 march 9:37"), + param("fi", "28 maalis klo 9:37", "28 march 9:37"), + param("fi", "28 maalis klo 9:37", "28 march 9:37"), + # Czech: keep_formatting=True + param("cs", "22. prosinec 2014 v 2:38", "22. december 2014 2:38"), + # Polish: keep_formatting=True + param("pl", "4 stycznia o 13:50", "4 january 13:50"), + ] + ) + def test_whitespace_preservation_keep_formatting( + self, shortname: str, datetime_string: str, expected_translation: str + ) -> None: + """Test whitespace preservation with keep_formatting=True.""" + self.given_bundled_language(shortname) + self.given_string(datetime_string) + self.when_datetime_string_translated_keep_formatting() + self.then_string_translated_to(expected_translation) + + def given_bundled_language(self, shortname: str) -> None: + self.language = default_loader.get_locale(shortname) + + def given_string(self, datetime_string: str) -> None: + self.datetime_string = datetime_string + + def when_datetime_string_translated(self) -> None: + self.translation = self.language.translate( + self.datetime_string, settings=self.settings + ) + + def when_datetime_string_translated_keep_formatting(self) -> None: + self.translation = self.language.translate( + self.datetime_string, keep_formatting=True, settings=self.settings + ) + + def then_string_translated_to(self, expected_string: str) -> None: + self.assertEqual( + expected_string, + self.translation, + f"\nExpected: |{expected_string}|\nGot: |{self.translation}|\n" + f"Input: |{self.datetime_string}|", + ) diff --git a/tox.ini b/tox.ini index 05b10493c..524145b48 100644 --- a/tox.ini +++ b/tox.ini @@ -1,5 +1,6 @@ [tox] -envlist = pre-commit,min,min-all,py310,py311,py312,py313,py314,all,scripts,docs,twinedeck +min_version = 4.25.0 +envlist = pre-commit,mypy,min,min-all,py3{10-14},all,scripts,docs,twinecheck,benchmark [base] deps = @@ -13,12 +14,12 @@ deps = atheris; python_version < '3.12' commands = pytest --cov=dateparser --cov-report=xml {posargs: tests} +passenv = TZ [testenv:all] basepython = python3.14 extras = calendars - fasttext langdetect [testenv:min] @@ -29,6 +30,14 @@ deps = pytz==2024.2 regex==2024.9.11 tzlocal==0.2 +# tzlocal 0.2 contains invalid string escapes, which pytest.ini turns into an +# error. Installers that byte-compile, pip included, absorb that warning before +# pytest starts, but the ones that do not turn it into an import-time +# SyntaxError, so ignore that one message for the environments pinned to it. No +# category: it is a DeprecationWarning up to Python 3.11 and a SyntaxWarning +# from 3.12 on. +set_env = + PYTEST_ADDOPTS = -W "ignore:invalid escape sequence" [testenv:min-all] basepython = {[testenv:min]basepython} @@ -38,9 +47,7 @@ deps = convertdate==2.2.1 hijridate==2.3.0 langdetect==1.0.0 - numpy==1.22.0 - # fasttext excluded due to - # https://github.com/facebookresearch/fastText/issues/512 +set_env = {[testenv:min]set_env} [testenv:scripts] deps = @@ -49,6 +56,27 @@ deps = commands = pytest --cov=dateparser --cov-report=xml {posargs:tests/test_dateparser_data_integrity.py} +[testenv:mypy] +basepython = python3.10 +deps = + mypy==2.3.1 + convertdate==2.5.1 + gitpython==3.1.62 + hijridate==2.6.0 + langdetect==1.0.9 + parameterized==0.9.0 + parsel==1.12.0 + pytest==9.1.1 + pytest-codspeed==5.0.3 + ruamel.yaml==0.19.1 + types-python-dateutil==2.9.0.20260807 + types-pytz==2026.4.0.20260926 + types-regex==2026.9.10.20260911 + types-requests==2.33.0.20260906 + tzlocal==5.4.4 +commands = + mypy {posargs:dateparser dateparser_cli dateparser_scripts fuzzing tests} + [testenv:pre-commit] basepython = python3 deps = @@ -73,3 +101,25 @@ deps = commands = python -m build --sdist --wheel twine check dist/* + +# Pinned to a single interpreter: CodSpeed compares measurements across runs, and +# instruction counts are not comparable between Python versions. +[testenv:benchmark] +basepython = python3.13 +deps = + {[base]deps} + pytest-codspeed +# The CodSpeed runner drives pytest-codspeed through CODSPEED_* variables, which +# have to reach the command tox runs for any measurement to happen. +passenv = + *codspeed* + *ci* +# tox picks a random hash seed per run, which would show up as noise in the +# instruction counts CodSpeed compares. +set_env = + PYTHONHASHSEED = 0 +# pytest-codspeed reports a measurement hook that failed to start or stop as a +# RuntimeWarning; pytest.ini would turn that runner glitch into a red CodSpeed +# check that says nothing about dateparser. +commands = + pytest -W "ignore::RuntimeWarning:pytest_codspeed" tests/benchmarks/ --no-cov --codspeed