Fix: Restrict date query rewrites to date or datetime fields only (#12864)

src/documents/search/_query.py

@@ -52,7 +52,7 @@ _DATE_KEYWORD_PATTERN = "|".join(
 )
 
 _FIELD_DATE_RE = regex.compile(
-    rf"""(?P<field>\w+)\s*:\s*(?:
+    rf"""(?<!\w)(?P<field>created|modified|added)\s*:\s*(?:
     (?P<quote>["'])(?P<quoted>{_DATE_KEYWORD_PATTERN})(?P=quote)
     |
     (?P<bare>{_DATE_KEYWORD_PATTERN})(?![\w-])
@@ -69,10 +69,13 @@ _WHOOSH_REL_RANGE_RE = regex.compile(
     r"\[-(?P<n>\d+)\s+(?P<unit>second|minute|hour|day|week|month|year)s?\s+to\s+now\]",
     regex.IGNORECASE,
 )
-# Whoosh-style 8-digit date: field:YYYYMMDD — field-aware so timezone can be applied correctly
-_DATE8_RE = regex.compile(r"(?P<field>\w+):(?P<date8>\d{8})\b")
+# Whoosh-style 8-digit date: field:YYYYMMDD — field-aware so timezone can be applied correctly.
+# Scoped to date fields only; numeric fields (asn, id, page_count, ...) must not be rewritten.
+_DATE8_RE = regex.compile(
+    r"(?<!\w)(?P<field>created|modified|added):(?P<date8>\d{8})\b",
+)
 _YEAR_RANGE_RE = regex.compile(
-    r"(?P<field>\w+):\[(?P<y1>\d{4})\s+TO\s+(?P<y2>\d{4})\]",
+    r"(?<!\w)(?P<field>created|modified|added):\[(?P<y1>\d{4})\s+TO\s+(?P<y2>\d{4})\]",
     regex.IGNORECASE,
 )
 _SIMPLE_QUERY_TOKEN_RE = regex.compile(r"\S+")

src/documents/tests/search/test_query.py

@@ -541,6 +541,45 @@ class TestYearRangeRewriting:
         assert "20201231" in result or "2020-12-31" in result
 
 
+class TestNonDateFieldsNotRewritten:
+    """Date rewriters must only fire on the date fields (created/modified/added).
+
+    Integer fields like asn/id/page_count and unknown fields would otherwise be
+    rewritten into date ranges and rejected by Tantivy as type mismatches.
+    """
+
+    @pytest.mark.parametrize(
+        "query",
+        [
+            pytest.param("asn:20240101", id="asn_8digit"),
+            pytest.param("id:20240101", id="id_8digit"),
+            pytest.param("page_count:12345678", id="page_count_8digit"),
+            pytest.param("num_notes:20231201", id="num_notes_8digit"),
+        ],
+    )
+    def test_8digit_on_integer_field_passes_through_unchanged(self, query: str) -> None:
+        assert rewrite_natural_date_keywords(query, EASTERN) == query
+
+    @pytest.mark.parametrize(
+        "query",
+        [
+            pytest.param("asn:[2000 TO 2024]", id="asn_year_range"),
+            pytest.param("id:[2000 TO 2024]", id="id_year_range"),
+            pytest.param("page_count:[2000 TO 2024]", id="page_count_year_range"),
+        ],
+    )
+    def test_year_range_on_integer_field_passes_through_unchanged(
+        self,
+        query: str,
+    ) -> None:
+        assert rewrite_natural_date_keywords(query, UTC) == query
+
+    def test_unknown_field_keyword_passes_through_unchanged(self) -> None:
+        # foobar is not a date field: 'foobar:today' must not become a date range,
+        # which Tantivy would otherwise reject as an unknown/typed field.
+        assert rewrite_natural_date_keywords("foobar:today", UTC) == "foobar:today"
+
+
 class TestPassthrough:
     """Queries without field prefixes or unrelated content pass through unchanged."""