Red Queen
5e4191578a
- SearchSourceBuilder: deterministischer Vault->Source-Snapshot (read-only), atomar (temp->validate->fsync->replace), Secret-Scan fail-closed - verify_integrity: exakte object_id/path Set-Equality (stale Source kann nie APPLIED), Canary implizit ueber erwartetes Objekt-Set - apply_commit: Source-Build+Verification vor Rebuild; VERIFYING_SEARCH-Resume (kein Doppel-Rebuild) — C5E-Replay-Crash-Fall abgedeckt - Fix: source_object_count ist keine 0-Fehlerbedingung (echter Defekt) - SearchSourceBuildError + RC_SEARCH_SOURCE_BUILD_FAILURE (Human Gate) - c4b: source_path env-konfigurierbar, indexed_object_ids/paths Read-Back - Testsuite: 17 neue Tests (Test-Plan A-O + Realistic C4-Integration)
41 lines
1.4 KiB
Python
41 lines
1.4 KiB
Python
"""
|
|
TOLARIA SEARCH SERVICE — Rebuild CLI (C4B)
|
|
================================================================
|
|
Baut den Keyword/Metadata-Index aus dem Forgejo-SoT-Source-JSON neu (DERIVED,
|
|
vollständig wegwerfbar + rebuildbar). Kein pgvector, keine Vector-Extension.
|
|
"""
|
|
import json
|
|
import sys
|
|
import os
|
|
|
|
sys.path.insert(0, os.path.dirname(__file__))
|
|
from search_api import TolariaSearch
|
|
|
|
INDEX_JSON = os.path.join(os.path.dirname(__file__), "data", "search_index.json")
|
|
|
|
|
|
def main():
|
|
import argparse
|
|
p = argparse.ArgumentParser(description="TOLARIA SEARCH rebuild")
|
|
p.add_argument("--source", default=os.path.join(os.path.dirname(__file__), "index_source.json"))
|
|
p.add_argument("--head", default=None)
|
|
p.add_argument("--no-secret-filter", action="store_true")
|
|
args = p.parse_args()
|
|
|
|
engine = TolariaSearch(index_path=INDEX_JSON)
|
|
res = engine.rebuild_from_source(args.source, head=args.head,
|
|
secret_filter=not args.no_secret_filter)
|
|
print(json.dumps({
|
|
"status": "rebuilt",
|
|
"indexed": res["indexed"],
|
|
"blocked": res["blocked"],
|
|
"index_path": INDEX_JSON,
|
|
"supported_modes": ["exact", "keyword", "metadata"],
|
|
"source_head": engine.source_head,
|
|
"indexed_object_ids": engine.indexed_object_ids,
|
|
"indexed_paths": engine.indexed_paths,
|
|
}, ensure_ascii=False, indent=2))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|