48 lines
1.3 KiB
Python
48 lines
1.3 KiB
Python
#!/usr/bin/env python3
|
|
"""Generate corpus-manifest.json from case directories."""
|
|
from __future__ import annotations
|
|
|
|
import hashlib
|
|
import json
|
|
from datetime import datetime, timezone
|
|
from pathlib import Path
|
|
|
|
ROOT = Path(__file__).resolve().parents[2]
|
|
CORPUS = ROOT / "bench" / "golden-corpus" / "categories"
|
|
OUTPUT = ROOT / "bench" / "golden-corpus" / "corpus-manifest.json"
|
|
|
|
|
|
def sha256(path: Path) -> str:
|
|
h = hashlib.sha256()
|
|
with path.open("rb") as fh:
|
|
while True:
|
|
chunk = fh.read(8192)
|
|
if not chunk:
|
|
break
|
|
h.update(chunk)
|
|
return h.hexdigest()
|
|
|
|
|
|
def main() -> int:
|
|
cases = []
|
|
for case_dir in sorted([p for p in CORPUS.rglob("*") if p.is_dir() and (p / "case-manifest.json").exists()]):
|
|
manifest_path = case_dir / "case-manifest.json"
|
|
cases.append({
|
|
"id": case_dir.name,
|
|
"path": str(case_dir.relative_to(ROOT)).replace("\\", "/"),
|
|
"manifestDigest": f"sha256:{sha256(manifest_path)}",
|
|
})
|
|
|
|
payload = {
|
|
"generatedAt": datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ"),
|
|
"caseCount": len(cases),
|
|
"cases": cases,
|
|
}
|
|
|
|
OUTPUT.write_text(json.dumps(payload, indent=2) + "\n", encoding="utf-8")
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
raise SystemExit(main())
|