up

samples/graph/graph-40k/verify.py

@@ -0,0 +1,58 @@
+#!/usr/bin/env python3
+"""
+Verify graph-40k fixture hashes and counts against manifest.json.
+"""
+from __future__ import annotations
+
+import hashlib
+import json
+import sys
+from pathlib import Path
+from typing import Tuple
+
+
+def sha256(path: Path) -> str:
+    h = hashlib.sha256()
+    with path.open("rb") as f:
+        for chunk in iter(lambda: f.read(8192), b""):
+            h.update(chunk)
+    return h.hexdigest()
+
+
+def count_lines(path: Path) -> int:
+    with path.open("r", encoding="utf-8") as f:
+        return sum(1 for _ in f if _.strip())
+
+
+def verify(manifest_path: Path) -> Tuple[bool, str]:
+    manifest = json.loads(manifest_path.read_text())
+    base = manifest_path.parent
+
+    nodes_path = base / "nodes.ndjson"
+    edges_path = base / "edges.ndjson"
+    overlay_path = base / manifest["overlay"]["path"]
+
+    checks = [
+        ("nodes hash", sha256(nodes_path) == manifest["hashes"]["nodes_ndjson_sha256"]),
+        ("edges hash", sha256(edges_path) == manifest["hashes"]["edges_ndjson_sha256"]),
+        ("overlay hash", sha256(overlay_path) == manifest["hashes"]["overlay_ndjson_sha256"]),
+        ("nodes count", count_lines(nodes_path) == manifest["counts"]["nodes"]),
+        ("edges count", count_lines(edges_path) == manifest["counts"]["edges"]),
+        ("overlay count", count_lines(overlay_path) == manifest["counts"]["overlays"]["policy.overlay.v1"]),
+    ]
+
+    failed = [name for name, ok in checks if not ok]
+    if failed:
+        return False, f"Failed checks: {', '.join(failed)}"
+    return True, "All hashes and counts match manifest."
+
+
+def main() -> int:
+    manifest_path = Path(sys.argv[1]).resolve() if len(sys.argv) > 1 else Path(__file__).resolve().parent / "manifest.json"
+    ok, message = verify(manifest_path)
+    print(message)
+    return 0 if ok else 1
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())