Refactor code structure for improved readability and maintainability; optimize performance in key functions.

scripts/corpus/check-determinism.py

@@ -0,0 +1,48 @@
+#!/usr/bin/env python3
+"""Check determinism by verifying manifest digests match stored values."""
+from __future__ import annotations
+
+import hashlib
+import json
+import sys
+from pathlib import Path
+
+ROOT = Path(__file__).resolve().parents[2]
+MANIFEST = 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:
+    if not MANIFEST.exists():
+        print(f"Manifest not found: {MANIFEST}")
+        return 1
+
+    data = json.loads(MANIFEST.read_text(encoding="utf-8"))
+    mismatches = []
+    for case in data.get("cases", []):
+        path = ROOT / case["path"]
+        manifest_path = path / "case-manifest.json"
+        digest = f"sha256:{sha256(manifest_path)}"
+        if digest != case.get("manifestDigest"):
+            mismatches.append({"id": case.get("id"), "expected": case.get("manifestDigest"), "actual": digest})
+
+    if mismatches:
+        print(json.dumps({"status": "fail", "mismatches": mismatches}, indent=2))
+        return 1
+
+    print(json.dumps({"status": "ok", "checked": len(data.get("cases", []))}, indent=2))
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())