Skip to content

fix: pick the --run input type from the corpus extension #65

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鈥檒l occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
abrignoni merged 1 commit into from
Aug 10, 2026
Merged

fix: pick the --run input type from the corpus extension #65

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
29 changes: 26 additions & 3 deletions admin/scripts/validate_sample_data.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
and what each produced, for example::

"sample_data": {
"discord_macos": "Discord 0.0.402 macOS | 12940 rows",
"corpus_key": "AppName 1.2.3 | 12940 rows",
}

Those keys are meant to name entries in a corpus registry (`samples.json`),
Expand All @@ -30,7 +30,7 @@
python3 admin/scripts/validate_sample_data.py
python3 admin/scripts/validate_sample_data.py --registry /path/samples.json
python3 admin/scripts/validate_sample_data.py --registry /path/samples.json --verify-hashes
python3 admin/scripts/validate_sample_data.py --registry /path/samples.json --run discord_win_ptb
python3 admin/scripts/validate_sample_data.py --registry /path/samples.json --run corpus_key

The registry path may also be supplied through the ``DLEAPP_SAMPLES``
environment variable. Exit status is 1 if any error was reported; warnings
Expand Down Expand Up @@ -219,6 +219,23 @@ def check_registry(artifacts, registry, registry_path, verify_hashes, report):
f"artifacts cite {len(cited)}")


def input_type_for(source):
"""Map a corpus file's extension to the tool's -t input type.

The registry's match key is spelled "zip" for historical reasons but may
point at any container the tool accepts. Returns None when the extension
names no known type, so the caller reports it instead of guessing.
"""
name = source.name.lower()
if name.endswith((".tar.gz", ".tgz", ".gz")):
return "gz"
if name.endswith(".tar"):
return "tar"
if name.endswith(".zip"):
return "zip"
return None


def run_corpus(registry, registry_path, corpus, report, keep=False):
"""Step 3: parse a corpus and compare produced rows against declared rows."""
entry = registry["samples"].get(corpus)
Expand All @@ -234,9 +251,15 @@ def run_corpus(registry, registry_path, corpus, report, keep=False):
report.error(f"--run '{corpus}' points at a missing file: {source}")
return

input_type = input_type_for(source)
if input_type is None:
report.error(f"--run '{corpus}': cannot pick a -t input type for {source.name}; "
"known extensions are .zip, .tar, .tar.gz, .tgz")
return

output_root = tempfile.mkdtemp(prefix="dleapp-validate-")
folder = "validate_run"
command = [sys.executable, str(REPO_ROOT / "dleapp.py"), "-t", "zip",
command = [sys.executable, str(REPO_ROOT / "dleapp.py"), "-t", input_type,
"-i", str(source), "-o", output_root, "--custom_output_folder", folder]
print(f" running {source.name} ...")
completed = subprocess.run(command, cwd=str(REPO_ROOT),
Expand Down
Loading