app/core/derive_edges.py aktualisiert

app/core/derive_edges.py

@@ -1,4 +1,25 @@
-# app/core/derive_edges.py
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Name:        app/core/derive_edges.py
+Version:     v1.1.0 (2025-09-05)
+
+Kurzbeschreibung:
+  Leitet Edges aus Wikilinks ([[...]]) ab.
+  - Unterstützt Auflösung über note_id, Title-Slug, File-Slug.
+  - Erzeugt Edges:
+      * "references" (Note->Note) + "backlink" (inverse)
+      * "references_at" (Chunk->Note) mit seq = chunk_index
+  - **NEU**: pro Match ein Occurrence-Zähler 'occ' für eindeutige Edge-IDs.
+
+Kompatibilität:
+  - Vorherige Payload-Felder bleiben erhalten.
+  - Zusätzliche Felder: 'seq' für Volltext ("body"), 'occ' überall.
+
+Changelog:
+  v1.1.0: 'occ' eingeführt; 'references' erhalten jetzt seq="body".
+"""
+
 from __future__ import annotations
 import re
 import unicodedata
@@ -54,42 +75,46 @@ def derive_wikilink_edges(note_payload: dict, chunks_payloads: List[dict], note_
     edges: List[dict] = []
     source_note_id = note_payload["note_id"]
 
-    def _make_edge(kind: str, src: str, tgt: str, seq=None, extra: dict|None=None):
+    def _make_edge(kind: str, src: str, tgt: str, seq=None, occ=None, extra: dict|None=None):
         e = {"edge_id": None, "kind": kind, "source_id": src, "target_id": tgt}
         if seq is not None:
             e["seq"] = seq
+        if occ is not None:
+            e["occ"] = occ
         if extra:
             e.update(extra)
         return e
 
-    # Links im Volltext (falls vorhanden)
+    # Links im Volltext (gesamter Body)
     fulltext = note_payload.get("fulltext") or note_payload.get("body") or ""
     if fulltext:
-        for m in WIKILINK_RE.finditer(fulltext):
+        for k, m in enumerate(WIKILINK_RE.finditer(fulltext), start=1):
             raw_target, heading, alias = m.groups()
             target_id, how = resolve_target(raw_target, note_index)
             extra = {"raw": raw_target, "alias": alias, "heading": heading, "resolution": how}
             if target_id:
-                edges.append(_make_edge("references", source_note_id, target_id, extra=extra))
-                edges.append(_make_edge("backlink",  target_id,      source_note_id, extra=extra))
+                edges.append(_make_edge("references", source_note_id, target_id, seq="body", occ=k, extra=extra))
+                edges.append(_make_edge("backlink",  target_id,      source_note_id, seq="body", occ=k, extra=extra))
             else:
                 extra["status"] = "unresolved"
                 extra["target_label"] = raw_target
-                edges.append(_make_edge("references", source_note_id, raw_target, extra=extra))
+                edges.append(_make_edge("references", source_note_id, raw_target, seq="body", occ=k, extra=extra))
 
     # Links in Chunks (wenn übergeben)
     for i, ch in enumerate(chunks_payloads, start=1):
         txt = ch.get("text") or ch.get("content") or ""
         if not txt:
             continue
+        occ = 0
         for m in WIKILINK_RE.finditer(txt):
+            occ += 1
             raw_target, heading, alias = m.groups()
             target_id, how = resolve_target(raw_target, note_index)
             extra = {"raw": raw_target, "alias": alias, "heading": heading, "resolution": how}
             if target_id:
-                edges.append(_make_edge("references_at", ch["chunk_id"], target_id, seq=i, extra=extra))
+                edges.append(_make_edge("references_at", ch["chunk_id"], target_id, seq=i, occ=occ, extra=extra))
             else:
                 extra["status"] = "unresolved"
                 extra["target_label"] = raw_target
-                edges.append(_make_edge("references_at", ch["chunk_id"], raw_target, seq=i, extra=extra))
+                edges.append(_make_edge("references_at", ch["chunk_id"], raw_target, seq=i, occ=occ, extra=extra))
     return edges