Initial OSV mirror

scripts/validate.py

@@ -0,0 +1,20 @@
+#!/usr/bin/env python3
+import json
+import sys
+from pathlib import Path
+root = Path(__file__).resolve().parents[1]
+state_file = root / 'state/sync.json'
+if not state_file.exists():
+    sys.exit('No OSV sync state')
+state = json.loads(state_file.read_text())
+for ecosystem, metadata in state.get('ecosystems', {}).items():
+    files = list((root / 'data' / ecosystem).glob('*.json'))
+    if len(files) < 1:
+        sys.exit(f'Empty ecosystem: {ecosystem}')
+    # Files are checked on import; spot-check retained data here to avoid reparsing millions.
+    for path in files[:10]:
+        item = json.loads(path.read_text())
+        if item.get('id') != path.stem:
+            sys.exit(f'Invalid {path}')
+    print(ecosystem, len(files), 'records')
+print('Validation OK')