Initial Builder

2026-11-10 21:56:33 +01:00
commit dd8b159ff5
8 changed files with 267 additions and 0 deletions
@@ -0,0 +1,113 @@
+#!/usr/bin/env python3
+"""Build compact CVE SQLite plus optionally incremental row-level delta (CVE slice)."""
+import argparse
+import base64
+import datetime as dt
+import hashlib
+import json
+import sqlite3
+import zlib
+from pathlib import Path
+import subprocess
+
+SCHEMA = '''CREATE TABLE cve (
+    cve_id TEXT PRIMARY KEY,
+    state TEXT NOT NULL,
+    date_updated TEXT,
+    affected BLOB NOT NULL,
+    row_hash TEXT NOT NULL
+) WITHOUT ROWID;
+CREATE INDEX idx_cve_state ON cve(state);'''
+
+def encode_record(doc):
+    meta = doc['cveMetadata']
+    cna = doc.get('containers', {}).get('cna', {})
+    # Preserve entire CNA affected array as structured JSON. Do NOT infer ranges.
+    affected = json.dumps(cna.get('affected', []), sort_keys=True, separators=(',', ':'), ensure_ascii=False).encode('utf-8')
+    blob = zlib.compress(affected, level=9)
+    row = (meta['cveId'], meta.get('state', 'UNKNOWN'), meta.get('dateUpdated'), blob)
+    digest = hashlib.sha256(json.dumps([row[0], row[1], row[2]], separators=(',', ':')).encode() + blob).hexdigest()
+    return (*row, digest)
+
+def fingerprint(conn):
+    h = hashlib.sha256()
+    for cve_id, row_hash in conn.execute('SELECT cve_id,row_hash FROM cve ORDER BY cve_id'):
+        h.update(cve_id.encode() + b'\x00' + row_hash.encode() + b'\n')
+    return h.hexdigest()
+
+def export_zstd(path, output):
+    with output.open('wb') as dst:
+        subprocess.run(['zstd', '-q', '-12', '-c', str(path)], stdout=dst, check=True)
+
+def main():
+    ap = argparse.ArgumentParser()
+    ap.add_argument('--source', type=Path, required=True, help='vuln-cve/data')
+    ap.add_argument('--output', type=Path, default=Path('dist'))
+    ap.add_argument('--previous', type=Path, help='previous SQLite master.db')
+    ap.add_argument('--source-revision', default='unknown')
+    args = ap.parse_args()
+    args.output.mkdir(parents=True, exist_ok=True)
+    db = args.output / 'master.db'
+    db.unlink(missing_ok=True)
+    current = sqlite3.connect(db)
+    current.executescript(SCHEMA)
+    count = 0
+    for path in sorted(args.source.rglob('CVE-*.json')):
+        with path.open(encoding='utf-8') as fh:
+            doc = json.load(fh)
+        if doc.get('cveMetadata', {}).get('cveId') != path.stem:
+            raise ValueError(f'CVE metadata mismatch at {path}')
+        current.execute('INSERT INTO cve VALUES (?,?,?,?,?)', encode_record(doc))
+        count += 1
+        if count % 5000 == 0:
+            current.commit()
+    if count == 0:
+        raise RuntimeError('No CVE records, refusing empty release')
+    current.commit()
+    current.execute('VACUUM')
+    current.commit()
+    current_hash = fingerprint(current)
+    previous_hash = None
+    changed = removed = 0
+    if args.previous:
+        prev = sqlite3.connect(f'file:{args.previous.resolve()}?mode=ro', uri=True)
+        previous_hash = fingerprint(prev)
+        old = {row[0]: row[1] for row in prev.execute('SELECT cve_id,row_hash FROM cve')}
+        delta_file = args.output / 'delta.jsonl.zst'
+        plain_delta = args.output / 'delta.jsonl'
+        with plain_delta.open('w', encoding='utf-8') as out:
+            header = {'type': 'header', 'format': 1, 'base': previous_hash, 'target': current_hash}
+            out.write(json.dumps(header) + '\n')
+            for id, state, date, blob, row_hash in current.execute('SELECT * FROM cve ORDER BY cve_id'):
+                old_hash = old.pop(id, None)
+                if old_hash != row_hash:
+                    change = {'type': 'upsert', 'id': id, 'state': state, 'updated': date, 'affected_b64': base64.b64encode(blob).decode(), 'hash': row_hash}
+                    out.write(json.dumps(change, separators=(',', ':')) + '\n')
+                    changed += 1
+            for id in sorted(old):
+                out.write(json.dumps({'type': 'delete', 'id': id}) + '\n')
+                removed += 1
+        export_zstd(plain_delta, delta_file)
+        plain_delta.unlink()
+        prev.close()
+    export_zstd(db, args.output / 'master.db.zst')
+    manifest = {
+        'format': 1,
+        'schema': 'cve-index-v1',
+        'built_at': dt.datetime.now(dt.timezone.utc).isoformat(),
+        'sources': {'cve': args.source_revision},
+        'records': count,
+        'content_sha256': current_hash,
+        'previous_content_sha256': previous_hash,
+        'upserts': changed,
+        'deletions': removed,
+        'artifacts': {},
+    }
+    for f in sorted(args.output.glob('*.zst')):
+        manifest['artifacts'][f.name] = {'sha256': hashlib.sha256(f.read_bytes()).hexdigest(), 'bytes': f.stat().st_size}
+    (args.output / 'manifest.json').write_text(json.dumps(manifest, indent=2) + '\n')
+    print(json.dumps(manifest, indent=2))
+    current.close()
+
+if __name__ == '__main__':
+    main()