app/core/derive_edges.py aktualisiert

app/core/derive_edges.py

@@ -4,6 +4,7 @@ import re
 import unicodedata
 from typing import Dict, List, Tuple
 
+# [[Ziel]], [[Ziel|Alias]], [[Ziel#Heading]], [[Ziel#Heading|Alias]]
 WIKILINK_RE = re.compile(r"\[\[([^\]|#]+)(?:#([^\]|]+))?(?:\|([^\]]+))?\]\]")
 
 def _slug(s: str) -> str:
@@ -13,9 +14,8 @@ def _slug(s: str) -> str:
     s = unicodedata.normalize("NFKD", s)
     s = "".join(ch for ch in s if not unicodedata.combining(ch))
     s = s.replace("\\", "/")
-    s = s.split("/")[-1]  # nur letzter Pfadteil
-    s = s.lower()
-    s = s.replace(" ", "-")
+    s = s.split("/")[-1]
+    s = s.lower().replace(" ", "-")
     s = re.sub(r"[^a-z0-9\-]+", "", s)
     s = re.sub(r"-{2,}", "-", s).strip("-")
     return s
@@ -30,7 +30,7 @@ def build_note_index(notes_payloads: List[dict]) -> Tuple[Dict[str, dict], Dict[
             continue
         by_id[nid] = n
         title = n.get("title", "")
-        path = n.get("path", "")  # z.B. "Ordner/Datei.md"
+        path = n.get("path", "")
         file_slug = _slug(path.split("/")[-1]) if path else ""
         if title:
             by_slug[_slug(title)] = n
@@ -38,14 +38,11 @@ def build_note_index(notes_payloads: List[dict]) -> Tuple[Dict[str, dict], Dict[
             by_file_slug[file_slug] = n
     return by_id, by_slug, by_file_slug
 
-def resolve_target(note_like: str, idx: Tuple[Dict[str,dict],Dict[str,dict],Dict[str,dict]]) -> Tuple[str|None, str]:
-    """
-    Liefert (target_note_id | None, resolution_hint)
-    """
+def resolve_target(note_like: str, idx: Tuple[Dict[str,dict],Dict[str,dict],Dict[str,dict]]):
     by_id, by_slug, by_file_slug = idx
     key = note_like.strip()
     if key in by_id:
-        return key, "by_id"
+        return by_id[key]["note_id"], "by_id"
     s = _slug(key)
     if s in by_slug:
         return by_slug[s]["note_id"], "by_slug"
@@ -54,29 +51,18 @@ def resolve_target(note_like: str, idx: Tuple[Dict[str,dict],Dict[str,dict],Dict
     return None, "unresolved"
 
 def derive_wikilink_edges(note_payload: dict, chunks_payloads: List[dict], note_index) -> List[dict]:
-    """
-    Erzeugt Edges aus [[...]] im Note-Text und in Chunk-Text:
-      - references: source_note -> target_note
-      - backlink:   target_note -> source_note
-      - optional: references_at: source_chunk -> target_note (wo steht der Link?)
-    """
     edges: List[dict] = []
     source_note_id = note_payload["note_id"]
 
-    def _make_edge(kind: str, src: str, tgt: str, seq: int|None=None, extra: dict|None=None) -> dict:
-        e = {
-            "edge_id": None,  # später vergeben (qdrant_points macht robusten Fallback + UUID)
-            "kind": kind,
-            "source_id": src,
-            "target_id": tgt,
-        }
+    def _make_edge(kind: str, src: str, tgt: str, seq=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 extra:
             e.update(extra)
         return e
 
-    # 1) Links im Note-Gesamttext (falls vorhanden)
+    # Links im Volltext (falls vorhanden)
     fulltext = note_payload.get("fulltext") or note_payload.get("body") or ""
     if fulltext:
         for m in WIKILINK_RE.finditer(fulltext):
@@ -85,14 +71,13 @@ def derive_wikilink_edges(note_payload: dict, chunks_payloads: List[dict], note_
             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("backlink",  target_id,      source_note_id, extra=extra))
             else:
-                # Unresolved: referenziere Slug/Raw, markiere Status
                 extra["status"] = "unresolved"
                 extra["target_label"] = raw_target
                 edges.append(_make_edge("references", source_note_id, raw_target, extra=extra))
 
-    # 2) Links in den einzelnen Chunks
+    # 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:
@@ -101,13 +86,10 @@ def derive_wikilink_edges(note_payload: dict, chunks_payloads: List[dict], note_
             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}
-            # optional: chunk→note Referenz (wo steht der Link?)
             if target_id:
                 edges.append(_make_edge("references_at", ch["chunk_id"], target_id, seq=i, extra=extra))
-                # die Note→Note-Kanten sind oben schon generiert; doppelt vermeiden:
             else:
                 extra["status"] = "unresolved"
                 extra["target_label"] = raw_target
                 edges.append(_make_edge("references_at", ch["chunk_id"], raw_target, seq=i, extra=extra))
-
     return edges