Dateien nach "app/core" hochladen

app/core/derive_edges.py

@@ -8,8 +8,7 @@ Zweck:
 - Unterstützt "typed inline relations":
     * [[rel:KIND | Target]]
     * [[rel:KIND Target]]
-    * rel: KIND [[Target]]            (1 Ziel)
+    * rel: KIND [[Target]]
-    * rel: KIND [[T1]] [[T2]] ...     (NEU: mehrere Ziele in einer Zeile)
 - Unterstützt Obsidian-Callouts:
     * > [!edge] KIND: [[Target]] [[Target2]] ...
 Kompatibilität:
@@ -143,68 +142,35 @@ _WIKILINK_RE = re.compile(r"\[\[(?:[^\|\]]+\|)?([a-zA-Z0-9_\-#:. ]+)\]\]")
 #   [[rel:KIND Target]]
 _REL_PIPE  = re.compile(r"\[\[\s*rel:(?P<kind>[a-z_]+)\s*\|\s*(?P<target>[^\]]+?)\s*\]\]", re.IGNORECASE)
 _REL_SPACE = re.compile(r"\[\[\s*rel:(?P<kind>[a-z_]+)\s+(?P<target>[^\]]+?)\s*\]\]",   re.IGNORECASE)
-#   rel: KIND [[Target]]   (ein Ziel)
+#   rel: KIND [[Target]]   (reines Textmuster)
-_REL_TEXT_SINGLE  = re.compile(r"rel\s*:\s*(?P<kind>[a-z_]+)\s*\[\[\s*(?P<target>[^\]]+?)\s*\]\]", re.IGNORECASE)
+_REL_TEXT  = re.compile(r"rel\s*:\s*(?P<kind>[a-z_]+)\s*\[\[\s*(?P<target>[^\]]+?)\s*\]\]", re.IGNORECASE)
-#   rel: KIND [[T1]] [[T2]] ...  (NEU: mehrere Ziele)
-_REL_TEXT_MULTI   = re.compile(r"rel\s*:\s*(?P<kind>[a-z_]+)\s*(?P<targets>(?:\[\[[^\]]+\]\]\s*){1,})", re.IGNORECASE)
-
-# Re-Use für mehrfaches Extrahieren der Wikilinks am Stück
-_WIKILINKS_IN_LINE = re.compile(r"\[\[([^\]]+)\]\]")
 
 def _extract_typed_relations(text: str) -> Tuple[List[Tuple[str,str]], str]:
     """
     Gibt Liste (kind, target) zurück und den Text mit entfernten getypten Relation-Links,
     damit die generische Wikilink-Erkennung sie nicht doppelt zählt.
-    Unterstützt Varianten:
+    Unterstützt drei Varianten:
       - [[rel:KIND | Target]]
       - [[rel:KIND Target]]
       - rel: KIND [[Target]]
-      - rel: KIND [[T1]] [[T2]] ...
     """
     pairs: List[Tuple[str,str]] = []
-
+    def _collect(m):
-    def _collect_pipe(m):
         k = (m.group("kind") or "").strip().lower()
         t = (m.group("target") or "").strip()
         if k and t:
             pairs.append((k, t))
         return ""  # Link entfernen
 
-    def _collect_space(m):
+    text = _REL_PIPE.sub(_collect, text)
-        k = (m.group("kind") or "").strip().lower()
+    text = _REL_SPACE.sub(_collect, text)
-        t = (m.group("target") or "").strip()
+    text = _REL_TEXT.sub(_collect, text)
-        if k and t:
-            pairs.append((k, t))
-        return ""
-
-    def _collect_text_multi(m):
-        k = (m.group("kind") or "").strip().lower()
-        targets = m.group("targets") or ""
-        if k and targets:
-            for t in _WIKILINKS_IN_LINE.findall(targets):
-                t = t.strip()
-                if t:
-                    pairs.append((k, t))
-        return ""
-
-    def _collect_text_single(m):
-        k = (m.group("kind") or "").strip().lower()
-        t = (m.group("target") or "").strip()
-        if k and t:
-            pairs.append((k, t))
-        return ""
-
-    # Reihenfolge wichtig: zuerst MULTI, dann SINGLE, dann die [[rel:...]]-Varianten
-    text = _REL_TEXT_MULTI.sub(_collect_text_multi, text)
-    text = _REL_TEXT_SINGLE.sub(_collect_text_single, text)
-    text = _REL_PIPE.sub(_collect_pipe, text)
-    text = _REL_SPACE.sub(_collect_space, text)
-
     return pairs, text
 
 # Obsidian Callout Parser
 _CALLOUT_START = re.compile(r"^\s*>\s*\[!edge\]\s*(.*)$", re.IGNORECASE)
 _REL_LINE      = re.compile(r"^(?P<kind>[a-z_]+)\s*:\s*(?P<targets>.+?)\s*$", re.IGNORECASE)
+_WIKILINKS_IN_LINE = re.compile(r"\[\[([^\]]+)\]\]")
 
 def _extract_callout_relations(text: str) -> Tuple[List[Tuple[str,str]], str]:
     """
@@ -283,7 +249,7 @@ def build_edges_for_note(
     - belongs_to:   für jeden Chunk   (chunk -> note)
     - next / prev:  zwischen aufeinanderfolgenden Chunks
     - references:   pro Chunk aus window/text (via Wikilinks)
-    - typed inline relations: [[rel:KIND | Target]] / [[rel:KIND Target]] / rel: KIND [[Target]] / rel: KIND [[T1]] [[T2]] ...
+    - typed inline relations: [[rel:KIND | Target]] / [[rel:KIND Target]] / rel: KIND [[Target]]
     - Obsidian Callouts: > [!edge] KIND: [[Target]] [[Target2]]
     - optional note-scope references/backlinks: dedupliziert über alle Chunk-Funde + note_level_references
     - typenbasierte Default-Kanten (edge_defaults) je gefundener Referenz
@@ -321,14 +287,14 @@ def build_edges_for_note(
             "provenance": "rule",
             "rule_id": "structure:order",
             "confidence": 0.95,
-        })))
+        }))
         edges.append(_edge("prev", "chunk", b_id, a_id, note_id, {
             "chunk_id": b_id,
             "edge_id": _mk_edge_id("prev", b_id, a_id, "chunk", "structure:order"),
             "provenance": "rule",
             "rule_id": "structure:order",
             "confidence": 0.95,
-        })))
+        }))
 
     # 3) references + typed inline + callouts + defaults (chunk-scope)
     reg = _load_types_registry()
@@ -341,7 +307,7 @@ def build_edges_for_note(
             continue
         raw = _chunk_text_for_refs(ch)
 
-        # 3a) typed inline relations (inkl. MULTI-Variante)
+        # 3a) typed inline relations
         typed, remainder = _extract_typed_relations(raw)
         for kind, target in typed:
             kind = kind.strip().lower()
@@ -449,7 +415,7 @@ def build_edges_for_note(
                     edges.append(_edge(rel, "note", r, note_id, note_id, {
                         "edge_id": _mk_edge_id(rel, r, note_id, "note", f"edge_defaults:{note_type}:{rel}"),
                         "provenance": "rule",
-                        "rule_id": f"edge_defaults:{note_type}:{rel}"),
+                        "rule_id": f"edge_defaults:{note_type}:{rel}",
                         "confidence": 0.7,
                     }))