mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-10-26 21:26:39 +00:00
0e9690493d
* fix(scripts): keep sync_labels.py from crashing on non-UTF-8 stdio The ✓ / ✗ status glyphs and the em dash in the Done line crashed the sync with UnicodeEncodeError whenever stdout was redirected on a host whose stdio encoding cannot represent them (Windows code pages, POSIX C locale, PYTHONIOENCODING=ascii) — after `gh label create --force` had already run, leaving a half-applied sync and a traceback. gh's UTF-8 diagnostics were additionally decoded with the host locale, mangling failure messages. Closes #7389. - Reconfigure stdout/stderr in main(): UTF-8 with backslashreplace when redirected, backslashreplace only on consoles. - Decode the gh subprocess as UTF-8 with errors="replace", matching scripts/support_bundle.py's _run_command. - Add backend/tests/test_sync_labels_script.py: hermetic offline cases (stub yaml, stub gh) running the real script under PYTHONIOENCODING=ascii for the success path, a UTF-8 gh failure, and --dry-run. All three go red on the unfixed script. * style(tests): fix sync-labels regression lint * docs(scripts): document label sync encoding policy --------- Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
108 lines
3.6 KiB
Python
108 lines
3.6 KiB
Python
#!/usr/bin/env python3
|
|
"""Sync GitHub labels from the declarative source of truth.
|
|
|
|
Reads ``.github/labels.yml`` and creates/updates each label via the GitHub CLI
|
|
(``gh label create --force``). Sync is additive/update-only: labels not listed
|
|
in the file are left untouched (never deleted).
|
|
|
|
Usage:
|
|
uv run --with pyyaml python scripts/sync_labels.py [--repo OWNER/NAME] [--dry-run]
|
|
|
|
Requires the ``gh`` CLI to be installed and authenticated (or ``GH_TOKEN`` set,
|
|
as in CI). When ``--repo`` is omitted, ``gh`` uses the current repository.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import argparse
|
|
import subprocess
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
try:
|
|
import yaml
|
|
except ModuleNotFoundError: # pragma: no cover - guidance for local runs
|
|
sys.exit(
|
|
"PyYAML is required. Run via:\n"
|
|
" uv run --with pyyaml python scripts/sync_labels.py"
|
|
)
|
|
|
|
LABELS_FILE = Path(__file__).resolve().parent.parent / ".github" / "labels.yml"
|
|
|
|
|
|
def load_labels(path: Path) -> list[dict[str, str]]:
|
|
data = yaml.safe_load(path.read_text(encoding="utf-8")) or {}
|
|
labels = data.get("labels")
|
|
if not isinstance(labels, list) or not labels:
|
|
sys.exit(f"No labels found in {path}")
|
|
for label in labels:
|
|
if not isinstance(label, dict) or "name" not in label:
|
|
sys.exit(f"Invalid label entry (missing 'name'): {label!r}")
|
|
return labels
|
|
|
|
|
|
def sync_label(label: dict[str, str], repo: str | None, dry_run: bool) -> bool:
|
|
name = str(label["name"])
|
|
color = str(label.get("color", "ededed")).lstrip("#")
|
|
description = str(label.get("description", ""))
|
|
|
|
cmd = ["gh", "label", "create", name, "--color", color, "--force"]
|
|
if description:
|
|
cmd += ["--description", description]
|
|
if repo:
|
|
cmd += ["--repo", repo]
|
|
|
|
if dry_run:
|
|
print(f"[dry-run] {' '.join(cmd)}")
|
|
return True
|
|
|
|
# gh emits UTF-8; decoding with the host locale mangles (or crashes on)
|
|
# failure messages containing non-ASCII on cp1252/cp936/C-locale hosts.
|
|
result = subprocess.run(cmd, capture_output=True, encoding="utf-8", errors="replace")
|
|
if result.returncode != 0:
|
|
print(f" ✗ {name}: {result.stderr.strip()}", file=sys.stderr)
|
|
return False
|
|
print(f" ✓ {name}")
|
|
return True
|
|
|
|
|
|
def main() -> int:
|
|
# The status glyphs (✓ / ✗) must survive hosts whose stdio encoding cannot
|
|
# represent them (Windows code pages, POSIX C locale): the crash happens
|
|
# after `gh label create --force` has already run, leaving a half-applied
|
|
# sync and a traceback instead of a status line.
|
|
for stream in (sys.stdout, sys.stderr):
|
|
if not hasattr(stream, "reconfigure"):
|
|
continue
|
|
if stream.isatty():
|
|
stream.reconfigure(errors="backslashreplace")
|
|
else:
|
|
stream.reconfigure(encoding="utf-8", errors="backslashreplace")
|
|
|
|
parser = argparse.ArgumentParser(description=__doc__)
|
|
parser.add_argument("--repo", help="Target repository as OWNER/NAME")
|
|
parser.add_argument(
|
|
"--dry-run",
|
|
action="store_true",
|
|
help="Print the gh commands without executing them",
|
|
)
|
|
args = parser.parse_args()
|
|
|
|
labels = load_labels(LABELS_FILE)
|
|
target = args.repo or "(current repository)"
|
|
print(f"Syncing {len(labels)} labels to {target}")
|
|
|
|
failures = sum(
|
|
0 if sync_label(label, args.repo, args.dry_run) else 1 for label in labels
|
|
)
|
|
|
|
if failures:
|
|
print(f"\n{failures} label(s) failed to sync", file=sys.stderr)
|
|
return 1
|
|
print(f"\nDone — {len(labels)} labels in sync.")
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
raise SystemExit(main())
|