From 1a879d48277f41aa7de2488b04f57b2e518ad95b Mon Sep 17 00:00:00 2001
From: Tarik Moussa <tarikmoussa@MacBookAir.fritz.box>
Date: Thu, 18 Jun 2026 09:17:43 +0200
Subject: [PATCH] feat(quality): clean LaTeX accents/ties + word-boundary
 truncation in section titles

Polish _clean_title for R-F: strip accent/escape macros (backslash-quote o to o, backslash-amp), convert tilde ties to spaces, and truncate at a word boundary so stored section titles read cleanly (mobius invariance, colin de verdiere). Tests added; ruff + mypy clean.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---
 codex/quality.py              | 14 +++++++++-----
 tests/quality/test_quality.py | 13 +++++++++++++
 2 files changed, 22 insertions(+), 5 deletions(-)

diff --git a/codex/quality.py b/codex/quality.py
index c2f1b94..7dc21f8 100644
--- a/codex/quality.py
+++ b/codex/quality.py
@@ -113,14 +113,18 @@ def classify_section(text: str) -> str:
 def _clean_title(title: str) -> str:
     """Normalize a LaTeX ``\\section`` title for use as a section label.
 
-    Strips LaTeX commands (``\\emph`` …) and ``{}$``, drops leading section
-    numbering (``3.2 ``), collapses whitespace, lower-cases, and truncates to
-    60 chars so the stored ``section`` value is a clean, comparable string.
+    Strips LaTeX word-commands (``\\emph`` …), accent/escape macros (``\\"o`` →
+    ``o``, ``\\&``), ``~`` ties and ``{}$``, drops leading section numbering
+    (``3.2 ``), collapses whitespace, lower-cases, and truncates to 60 chars at a
+    word boundary so the stored ``section`` value is a clean, comparable string.
     """
-    t = re.sub(r"\\[a-zA-Z]+\*?", " ", title)  # LaTeX commands
+    t = title.replace("~", " ")  # LaTeX non-breaking tie → space
+    t = re.sub(r"\\[a-zA-Z]+\*?", " ", t)  # word-commands: \emph, \mathcal …
+    t = re.sub(r"\\[^a-zA-Z]", "", t)  # accent/escape macros: \"o → o, \', \`, \&
     t = re.sub(r"[{}$]", "", t)  # braces / math delimiters
     t = re.sub(r"^\s*\d+(?:\.\d+)*\.?\s*", "", t)  # leading numbering "3.2 "
-    return " ".join(t.split()).strip().lower()[:60]
+    t = " ".join(t.split()).strip().lower()
+    return t[:60].rsplit(" ", 1)[0] if len(t) > 60 else t
 
 
 def section_label(title: str | None, content: str) -> str:
diff --git a/tests/quality/test_quality.py b/tests/quality/test_quality.py
index 2cfa631..4895c30 100644
--- a/tests/quality/test_quality.py
+++ b/tests/quality/test_quality.py
@@ -257,6 +257,19 @@ class TestCleanTitle:
     def test_collapses_and_lowercases(self):
         assert _clean_title("  Rigidity   Results  ") == "rigidity results"
 
+    def test_strips_accent_macros(self):
+        assert _clean_title(r"M\"obius Invariance") == "mobius invariance"
+
+    def test_strips_ties_and_accents(self):
+        assert _clean_title(r"Colin~de~Verdi\`ere") == "colin de verdiere"
+
+    def test_truncates_at_word_boundary(self):
+        long = "alpha beta gamma delta epsilon zeta eta theta iota kappa lambda mu nu omega"
+        out = _clean_title(long)
+        assert len(out) <= 60
+        assert not out.endswith(" ")
+        assert long.lower().startswith(out)  # whole words from the start, no partial tail
+
 
 class TestSectionLabel:
     def test_title_maps_to_controlled_bucket(self):