Skip to content

Update for Unicode 18.0.0 #79

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
domenic merged 1 commit into from
Oct 4, 2026
Merged

Update for Unicode 18.0.0 #79

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 6 additions & 6 deletions package-lock.json
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

4 changes: 2 additions & 2 deletions package.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,10 +38,10 @@
},
"devDependencies": {
"@domenic/eslint-config": "^4.0.1",
"@unicode/unicode-17.0.0": "^1.6.12",
"@unicode/unicode-18.0.0": "^2.0.7",
"eslint": "^9.35.0",
"globals": "^16.4.0",
"regenerate": "^1.4.2"
},
"unicodeVersion": "17.0.0"
"unicodeVersion": "18.0.0"
}
24 changes: 12 additions & 12 deletions scripts/generateRegexes.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,22 +12,22 @@ main().catch(e => {

async function main() {
const cp = {
Mark: require(`@unicode/unicode-${unicodeVersion}/General_Category/Mark/code-points.js`),
Mark: (await import(`@unicode/unicode-${unicodeVersion}/General_Category/Mark/code-points.mjs`)).default,
JT: await generateUnicodeCodePoints(`https://unicode.org/Public/${unicodeVersion}/ucd/extracted/DerivedJoiningType.txt`, ["L", "R", "D", "T"]),
CombiningClassVirama: (await generateUnicodeCodePoints(`https://unicode.org/Public/${unicodeVersion}/ucd/extracted/DerivedCombiningClass.txt`, ["9"]))["9"],

// https://tools.ietf.org/html/rfc5893#section-1.4
L: require(`@unicode/unicode-${unicodeVersion}/Bidi_Class/Left_To_Right/code-points.js`),
R: require(`@unicode/unicode-${unicodeVersion}/Bidi_Class/Right_To_Left/code-points.js`),
AL: require(`@unicode/unicode-${unicodeVersion}/Bidi_Class/Arabic_Letter/code-points.js`),
EN: require(`@unicode/unicode-${unicodeVersion}/Bidi_Class/European_Number/code-points.js`),
ES: require(`@unicode/unicode-${unicodeVersion}/Bidi_Class/European_Separator/code-points.js`),
ET: require(`@unicode/unicode-${unicodeVersion}/Bidi_Class/European_Terminator/code-points.js`),
AN: require(`@unicode/unicode-${unicodeVersion}/Bidi_Class/Arabic_Number/code-points.js`),
CS: require(`@unicode/unicode-${unicodeVersion}/Bidi_Class/Common_Separator/code-points.js`),
NSM: require(`@unicode/unicode-${unicodeVersion}/Bidi_Class/Nonspacing_Mark/code-points.js`),
BN: require(`@unicode/unicode-${unicodeVersion}/Bidi_Class/Boundary_Neutral/code-points.js`),
ON: require(`@unicode/unicode-${unicodeVersion}/Bidi_Class/Other_Neutral/code-points.js`)
L: (await import(`@unicode/unicode-${unicodeVersion}/Bidi_Class/Left_To_Right/code-points.mjs`)).default,
R: (await import(`@unicode/unicode-${unicodeVersion}/Bidi_Class/Right_To_Left/code-points.mjs`)).default,
AL: (await import(`@unicode/unicode-${unicodeVersion}/Bidi_Class/Arabic_Letter/code-points.mjs`)).default,
EN: (await import(`@unicode/unicode-${unicodeVersion}/Bidi_Class/European_Number/code-points.mjs`)).default,
ES: (await import(`@unicode/unicode-${unicodeVersion}/Bidi_Class/European_Separator/code-points.mjs`)).default,
ET: (await import(`@unicode/unicode-${unicodeVersion}/Bidi_Class/European_Terminator/code-points.mjs`)).default,
AN: (await import(`@unicode/unicode-${unicodeVersion}/Bidi_Class/Arabic_Number/code-points.mjs`)).default,
CS: (await import(`@unicode/unicode-${unicodeVersion}/Bidi_Class/Common_Separator/code-points.mjs`)).default,
NSM: (await import(`@unicode/unicode-${unicodeVersion}/Bidi_Class/Nonspacing_Mark/code-points.mjs`)).default,
BN: (await import(`@unicode/unicode-${unicodeVersion}/Bidi_Class/Boundary_Neutral/code-points.mjs`)).default,
ON: (await import(`@unicode/unicode-${unicodeVersion}/Bidi_Class/Other_Neutral/code-points.mjs`)).default
};

function r(strings, ...regs) {
Expand Down
13 changes: 11 additions & 2 deletions scripts/getLatestTests.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ const { unicodeVersion } = require("../package.json");

// Update this by going to https://github.com/web-platform-tests/wpt/tree/master/url/resources and pressing "y" on the
// keyboard.
const wptSHA = "40fc257a28faf7c378f59185235685ea8684e8f4";
const wptSHA = "13748c36fdf9dd77cd0b34dd6b244256b365ea60";

main().catch(e => {
console.error(e);
Expand All @@ -21,17 +21,26 @@ async function main() {
await Promise.all([
(async () => {
const target = path.resolve(__dirname, "../test/fixtures/IdnaTestV2.txt");
const response = await fetch(`https://unicode.org/Public/idna/${unicodeVersion}/IdnaTestV2.txt`);
const response = await fetch(`https://unicode.org/Public/${unicodeVersion}/idna/IdnaTestV2.txt`);
if (!response.ok) {
throw new Error(`Failed to fetch ${response.url}: ${response.status}`);
}
await fs.writeFile(target, response.body);
})(),
(async () => {
const target = path.resolve(__dirname, "../test/fixtures/toascii.json");
const response = await fetch(`https://github.com/web-platform-tests/wpt/raw/${wptSHA}/url/resources/toascii.json`);
if (!response.ok) {
throw new Error(`Failed to fetch ${response.url}: ${response.status}`);
}
await fs.writeFile(target, response.body);
})(),
(async () => {
const target = path.resolve(__dirname, "../test/fixtures/IdnaTestV2ToASCII.json");
const response = await fetch(`https://github.com/web-platform-tests/wpt/raw/${wptSHA}/url/resources/IdnaTestV2.json`);
if (!response.ok) {
throw new Error(`Failed to fetch ${response.url}: ${response.status}`);
}
await fs.writeFile(target, response.body);
})()
]);
Expand Down
10 changes: 10 additions & 0 deletions test/toascii.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,6 +32,11 @@ describe("ToASCII", () => {
continue;
}

// The URL Standard bypasses IDNA processing for ASCII domains.
if (/^[\x00-\x7F]*$/u.test(testCase.input)) {
continue;
}

let description = testCase.input;
if (testCase.comment) {
description += ` (${testCase.comment})`;
Expand All @@ -54,6 +59,11 @@ describe("ToASCII via IdnaTestV2.json in wpt", () => {
continue;
}

// The URL Standard bypasses IDNA processing for ASCII domains.
if (/^[\x00-\x7F]*$/u.test(testCase.input)) {
continue;
}

let description = testCase.input;
if (testCase.comment) {
description += ` (${testCase.comment})`;
Expand Down
Loading