update

backend/textkit.py

@@ -56,11 +56,14 @@ def _resolve_title(idx: dict[str, int], t: str) -> int | None:
 
 
 def _norm_dash(s: str) -> str:
-    """Space-surrounded dash variants (en/em/figure/bar/hyphen) → uniform separator ' — '.
+    """Dash variants (en/em/figure/bar) with whitespace on AT LEAST ONE side → uniform separator ' — '.
     Some models (especially non-western ones) use an en-dash "–" instead of the em-dash; without
-    normalization the ` — ` split fails entirely and the whole entry becomes the title.
-    The ASCII hyphen "-" is left untouched (otherwise it would split formulas like "n - 1")."""
-    return re.sub(r"\s+[‒–—―‐]\s+", " — ", s)
+    normalization the ` — ` split fails entirely and the whole entry becomes the title. A one-sided
+    space ("Titel —Beschreibung" / "Titel— Beschreibung") also breaks the split and leaks the source
+    filename into the description — so a dash with a space on either side is repaired too. The ASCII
+    hyphen "-" is deliberately NOT in the class (would split "n - 1"/"3-SAT"); requiring ≥1 surrounding
+    space keeps glued compounds like "Backtracking—Verfahren" and number ranges like "12–15" untouched."""
+    return re.sub(r"\s*[‒–—―]\s+|\s+[‒–—―]\s*", " — ", s)
 
 
 def _parse_selection(text: str) -> dict[int, str]: