Files
TirsvadandClaude Sonnet 5.5 cbb9688ed4 Stabilise the metadata sync workflow and add offline validation
Restructure the script embedded in the scoped sync workflow into testable
functions, fix the invalid `exit 0` (now a successful run with a visible
warning when Gitea returns an invalid push mirror list) and report errors as
`ERROR: <message>` with exit code 1. Zero, several or malformed GitHub mirrors
still fail.

Add pytest-based offline tests (workflow YAML, embedded Python, credential and
mirror parsing, sync flow against a fake API) that run in a virtual
environment, and a validation workflow that runs them on pull requests and
pushes to main. Remove the manual tests/test_.ps1 probe and the duplicate
src/ copy of the workflow. Update the README and record the decisions for
tasks 1 and 3 in MIL-001.

Task: MIL-001#1
Task: MIL-001#2
Task: MIL-001#3
Task: MIL-001#4
Task: MIL-001#5
Task: MIL-001#6
Refs #1
Refs #2
Refs #3
Refs #4
Refs #5
Refs #6

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-03 20:45:57 +08:00

45 lines
1.4 KiB
Python

"""Helpers that read workflow files and the Python embedded in them."""
import re
import textwrap
from pathlib import Path
from typing import Any
REPO_ROOT = Path(__file__).resolve().parent.parent
WORKFLOW_DIRS = (
REPO_ROOT / ".gitea" / "scoped_workflows",
REPO_ROOT / ".gitea" / "workflows",
)
SYNC_WORKFLOW = WORKFLOW_DIRS[0] / "sync-github-metadata.yml"
_HEREDOC = re.compile(
r"^[ \t]*python3 - <<'PY'\r?\n(?P<code>.*?)^[ \t]*PY[ \t]*\r?$",
re.DOTALL | re.MULTILINE,
)
def workflow_files() -> list[Path]:
"""Return every workflow file in the known workflow directories."""
files: list[Path] = []
for directory in WORKFLOW_DIRS:
if directory.is_dir():
files += sorted(directory.glob("*.yml")) + sorted(directory.glob("*.yaml"))
return files
def embedded_python(path: Path) -> list[str]:
"""Return the source of each `python3 - <<'PY'` heredoc in a workflow."""
text = path.read_text(encoding="utf-8")
return [
textwrap.dedent(match.group("code").replace("\r\n", "\n"))
for match in _HEREDOC.finditer(text)
]
def load_sync_module(name: str = "embedded_sync") -> dict[str, Any]:
"""Execute the embedded sync script without running `main`."""
(source,) = embedded_python(SYNC_WORKFLOW)
namespace: dict[str, Any] = {"__name__": name}
exec(compile(source, str(SYNC_WORKFLOW), "exec"), namespace)
return namespace