update

backend/textkit.py

@@ -32,8 +32,46 @@ def _norm_title(s: str) -> str:
     return s.casefold()
 
 
+# Bracket-aware separator handling: a ' — ' (or a dash that _norm_dash would normalize) INSIDE
+# ()[]{} is part of the title, not a title/description separator. Without this a spaced dash within
+# a math title truncates it: 'Aε-Algorithmus (Güte 1+ε, Laufzeit O(n³)) — …' → 'Aε-Algorithmus (Güte…'.
+_BRACKETS = {"(": ")", "[": "]", "{": "}"}
+_CLOSERS = {v: k for k, v in _BRACKETS.items()}
+
+
+def _unclosed(s: str) -> bool:
+    """True if s has a dangling opening bracket ()[]{} — the symptom of a mid-bracket cut. Extra
+    closers (more ')' than '(') do NOT count; only an unclosed opener signals a truncated title."""
+    depth = 0
+    for c in s:
+        if c in _BRACKETS:
+            depth += 1
+        elif c in _CLOSERS and depth > 0:
+            depth -= 1
+    return depth > 0
+
+
+def _split_top(s: str, sep: str) -> str:
+    """First bracket-depth-0 segment of s split on sep; whole s if sep never occurs at depth 0."""
+    depth = 0
+    for i, c in enumerate(s):
+        if c in _BRACKETS:
+            depth += 1
+        elif c in _CLOSERS and depth > 0:
+            depth -= 1
+        elif depth == 0 and s.startswith(sep, i):
+            return s[:i]
+    return s
+
+
 def _title(entry: str) -> str:
-    return entry.split(" — ")[0].strip() or entry
+    """Title = text before the first TOP-LEVEL ' — '. A separator inside ()[]{} does not split
+    (keeps math titles intact); if the extracted title has an unclosed bracket (malformed source),
+    keep the whole entry rather than emit a truncated title."""
+    title = _split_top(entry, " — ")
+    if _unclosed(title):
+        return entry.strip() or entry
+    return title.strip() or entry
 
 
 def clean_title(s: str) -> str:
@@ -74,6 +112,9 @@ def _resolve_title(idx: dict[str, int], t: str) -> int | None:
     return idx.get(_norm_title(t)) or idx.get(_norm_title(_title(t)))
 
 
+_DASH_SEP_RE = re.compile(r"\s*[‒–—―]\s+|\s+[‒–—―]\s*")
+
+
 def _norm_dash(s: str) -> str:
     """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
@@ -81,8 +122,12 @@ def _norm_dash(s: str) -> str:
     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)
+    space keeps glued compounds like "Backtracking—Verfahren" and number ranges like "12–15" untouched.
+    A qualifying dash INSIDE an open bracket ()[]{} is left untouched — it is part of the title, not a
+    separator (else 'Algorithmus (Güte 1+ε – O(n³)) — …' would split mid-parenthetical)."""
+    def _repl(m):
+        return m.group(0) if _unclosed(s[:m.start()]) else " — "
+    return _DASH_SEP_RE.sub(_repl, s)
 
 
 def _parse_selection(text: str) -> dict[int, str]: