fix: extract_quotes accepts mismatched opening/closing quotes (#1113)

* fix: only extract quotes whose closing quote matches the opening one

* fix: same mismatched-quote bug in the services search copy

* test: extract_quotes requires matching open/close quotes

services/search/content.py

@@ -385,7 +385,9 @@ def get_tldr(text: str, max_sentences: int = 3) -> str:
 
 def extract_quotes(text: str) -> List[str]:
     """Return quoted excerpts that are at least 15 characters long."""
-    return [m.group(1).strip() for m in re.finditer(r'["\']([^"\']{15,}?)["\']', text)]
+    # Backreference the opening quote so the closing quote must match it —
+    # otherwise `"text'` (open double, close single) is treated as a quote.
+    return [m.group(2).strip() for m in re.finditer(r'(["\'])([^"\']{15,}?)\1', text)]
 
 
 def extract_statistics(text: str) -> List[str]:

src/search/content.py

@@ -390,7 +390,9 @@ def get_tldr(text: str, max_sentences: int = 3) -> str:
 
 def extract_quotes(text: str) -> List[str]:
     """Return quoted excerpts that are at least 15 characters long."""
-    return [m.group(1).strip() for m in re.finditer(r'["\']([^"\']{15,}?)["\']', text)]
+    # Backreference the opening quote so the closing quote must match it —
+    # otherwise `"text'` (open double, close single) is treated as a quote.
+    return [m.group(2).strip() for m in re.finditer(r'(["\'])([^"\']{15,}?)\1', text)]
 
 
 def extract_statistics(text: str) -> List[str]:

tests/test_extract_quotes.py

@@ -0,0 +1,28 @@
+"""Tests for extract_quotes (src/search/content.py)."""
+import pytest
+
+pytest.importorskip("bs4")  # content.py imports BeautifulSoup at module load
+
+from src.search.content import extract_quotes
+
+
+def test_matched_double_quotes():
+    assert extract_quotes('She said "this is a proper long quote" today') == [
+        "this is a proper long quote"
+    ]
+
+
+def test_matched_single_quotes():
+    assert extract_quotes("He wrote 'another sufficiently long quote' here") == [
+        "another sufficiently long quote"
+    ]
+
+
+def test_mismatched_quotes_are_not_extracted():
+    # Regression: `"text'` (open double, close single) used to be accepted
+    # because the closing quote wasn't required to match the opening one.
+    assert extract_quotes("""apostrophe d'accord then a "dangling long opener""") == []
+
+
+def test_short_quotes_ignored():
+    assert extract_quotes('say "too short" please') == []