scripts/report_hashes.py hinzugefügt

scripts/report_hashes.py

@@ -0,0 +1,92 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Script: scripts/report_hashes.py — Übersicht & Lücken bei Mehrfach-Hashes
+Version: 1.0.0
+Datum: 2025-09-10
+
+Funktion
+--------
+Listet je Note die vorhandenen Einträge im Feld `hashes` (Signaturen: <mode>:<source>:<normalize>)
+und meldet fehlende Soll-Keys. Eignet sich als CI-Check.
+
+Optionen
+--------
+--prefix TEXT              Collection-Prefix (CLI überschreibt ENV)
+--require K [K ...]        Zusätzliche Soll-Keys (Default: body|frontmatter|full:parsed:canonical)
+--fail-on-missing          Exitcode 2, wenn fehlende Keys gefunden werden
+
+Beispiele
+---------
+    python3 -m scripts.report_hashes --prefix mindnet
+    python3 -m scripts.report_hashes --require frontmatter:raw:none --fail-on-missing
+"""
+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.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()