fix: guard label/text normalizers against None node labels (#1195)

Guards _norm, _norm_label, and _strip_diacritics against None node labels that cause TypeError in unicodedata.normalize(). Fixes #1194. Consistent with existing security.py:270 precedent.

Co-authored-by: freiit <freiit@users.noreply.github.com>

graphify/build.py

@@ -311,8 +311,10 @@ def build(
     return build_from_json(combined, directed=directed, root=root)
 
 
-def _norm_label(label: str) -> str:
+def _norm_label(label: str | None) -> str:
     """Canonical dedup key — Unicode-aware, preserves CJK/word characters."""
+    if not isinstance(label, str):
+        label = "" if label is None else str(label)
     label = unicodedata.normalize("NFKC", label)
     return re.sub(r"[\W_ ]+", " ", label.casefold(), flags=re.UNICODE).strip()
 

graphify/dedup.py

@@ -15,8 +15,10 @@ from rapidfuzz.distance import JaroWinkler
 
 # ── helpers ───────────────────────────────────────────────────────────────────
 
-def _norm(label: str) -> str:
+def _norm(label: str | None) -> str:
     """Lowercase + collapse non-alphanumeric runs to space (Unicode-aware)."""
+    if not isinstance(label, str):
+        label = "" if label is None else str(label)
     label = unicodedata.normalize("NFKC", label)
     return re.sub(r"[\W_]+", " ", label.casefold(), flags=re.UNICODE).strip()
 

graphify/export.py

@@ -102,8 +102,10 @@ def _obsidian_tag(name: str) -> str:
     return re.sub(r"[^a-zA-Z0-9_\-/]", "", name.replace(" ", "_"))
 
 
-def _strip_diacritics(text: str) -> str:
+def _strip_diacritics(text: str | None) -> str:
     import unicodedata
+    if not isinstance(text, str):
+        text = "" if text is None else str(text)
     nfkd = unicodedata.normalize("NFKD", text)
     return "".join(c for c in nfkd if not unicodedata.combining(c))
 

graphify/serve.py

@@ -51,8 +51,10 @@ def _communities_from_graph(G: nx.Graph) -> dict[int, list[str]]:
     return communities
 
 
-def _strip_diacritics(text: str) -> str:
+def _strip_diacritics(text: str | None) -> str:
     import unicodedata
+    if not isinstance(text, str):
+        text = "" if text is None else str(text)
     nfkd = unicodedata.normalize("NFKD", text)
     return "".join(c for c in nfkd if not unicodedata.combining(c))