Lars
e93bab6ea7
All checks were successful
Deploy mindnet to llm-node / deploy (push) Successful in 4s
127 lines
3.7 KiB
Python
127 lines
3.7 KiB
Python
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
FILE: scripts/report_hashes.py
|
|
VERSION: 2.1.0 (2025-12-15)
|
|
STATUS: Active
|
|
COMPATIBILITY: v2.9.1 (Post-WP14/WP-15b)
|
|
|
|
Zweck:
|
|
-------
|
|
Erstellt Übersicht über Hash-Signaturen in Note-Payloads.
|
|
Meldet fehlende Soll-Keys für Multi-Hash Change Detection.
|
|
|
|
Funktionsweise:
|
|
---------------
|
|
1. Lädt alle Notes aus {prefix}_notes
|
|
2. Prüft für jede Note das `hashes` Feld
|
|
3. Vergleicht vorhandene Keys mit Soll-Keys
|
|
4. Meldet fehlende Keys pro Note
|
|
|
|
Ergebnis-Interpretation:
|
|
------------------------
|
|
- Ausgabe: JSON mit Hash-Übersicht
|
|
* notes_total: Anzahl geprüfter Notizen
|
|
* notes_with_missing: Anzahl Notizen mit fehlenden Keys
|
|
* missing_keys: Liste fehlender Keys pro Note
|
|
- Exit-Code 0: Keine fehlenden Keys (oder --fail-on-missing nicht gesetzt)
|
|
- Exit-Code 2: Fehlende Keys gefunden (nur mit --fail-on-missing)
|
|
|
|
Verwendung:
|
|
-----------
|
|
- CI/CD-Validierung der Hash-Integrität
|
|
- Audit nach Migrationen
|
|
- Prüfung der Change Detection Funktionalität
|
|
|
|
Hinweise:
|
|
---------
|
|
- Multi-Hash Format: <mode>:<source>:<normalize>
|
|
- Standard Soll-Keys: body:parsed:canonical, full:parsed:canonical
|
|
- Kann zusätzliche Keys via --require anfordern
|
|
|
|
Aufruf:
|
|
-------
|
|
python3 -m scripts.report_hashes --prefix mindnet
|
|
python3 -m scripts.report_hashes --require frontmatter:raw:none --fail-on-missing
|
|
|
|
Parameter:
|
|
----------
|
|
--prefix TEXT Collection-Präfix (überschreibt ENV COLLECTION_PREFIX)
|
|
--require KEY ... Zusätzliche Soll-Keys (Default: body:parsed:canonical, full:parsed:canonical)
|
|
--fail-on-missing Exit-Code 2, wenn fehlende Keys gefunden werden
|
|
|
|
Änderungen:
|
|
-----------
|
|
v2.1.0 (2025-12-15): Dokumentation aktualisiert
|
|
v1.0.0 (2025-09-10): Initial Release
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import argparse
|
|
import json
|
|
import os
|
|
from typing import List, Dict, Any
|
|
|
|
from qdrant_client.http import models as rest
|
|
from app.core.database.qdrant import QdrantConfig, get_client
|
|
|
|
def collections(prefix: str):
|
|
return f"{prefix}_notes", f"{prefix}_chunks", f"{prefix}_edges"
|
|
|
|
def _scroll_all(client, collection: str):
|
|
out = []
|
|
nextp = None
|
|
while True:
|
|
pts, nextp = client.scroll(collection_name=collection, with_payload=True, with_vectors=False, limit=256, offset=nextp)
|
|
if not pts:
|
|
break
|
|
out.extend(pts)
|
|
if nextp is None:
|
|
break
|
|
return out
|
|
|
|
def main():
|
|
ap = argparse.ArgumentParser()
|
|
ap.add_argument("--prefix", help="Collection-Prefix (überschreibt ENV COLLECTION_PREFIX)")
|
|
ap.add_argument("--require", nargs="+", help="Zusätzliche Soll-Keys <mode>:<source>:<normalize>")
|
|
ap.add_argument("--fail-on-missing", action="store_true", help="Exitcode 2 bei fehlenden Keys")
|
|
args = ap.parse_args()
|
|
|
|
cfg = QdrantConfig.from_env()
|
|
if args.prefix:
|
|
cfg.prefix = args.prefix.strip()
|
|
client = get_client(cfg)
|
|
|
|
notes_col, _, _ = collections(cfg.prefix)
|
|
pts = _scroll_all(client, notes_col)
|
|
|
|
required = set(args.require or [])
|
|
required |= {
|
|
"body:parsed:canonical",
|
|
"frontmatter:parsed:canonical",
|
|
"full:parsed:canonical",
|
|
}
|
|
|
|
missing_total = 0
|
|
for p in pts:
|
|
pl = p.payload or {}
|
|
nid = pl.get("note_id")
|
|
hashes = pl.get("hashes") or {}
|
|
present = set(hashes.keys())
|
|
missing = sorted(list(required - present))
|
|
obj = {
|
|
"note_id": nid,
|
|
"present_count": len(present),
|
|
"missing": missing,
|
|
}
|
|
print(json.dumps(obj, ensure_ascii=False))
|
|
missing_total += len(missing)
|
|
|
|
if args.fail_on_missing and missing_total > 0:
|
|
raise SystemExit(2)
|
|
|
|
print(json.dumps({"summary_missing_total": missing_total}))
|
|
|
|
if __name__ == "__main__":
|
|
main()
|