Fix (beta): restore v2 (Whoosh) advanced-search query compatibility (#13010)

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>

src/documents/tests/search/test_query.py

@@ -13,7 +13,6 @@ import time_machine
 
 from documents.search._query import _date_only_range
 from documents.search._query import _datetime_range
-from documents.search._query import _rewrite_compact_date
 from documents.search._query import build_permission_filter
 from documents.search._query import normalize_query
 from documents.search._query import parse_simple_text_highlight_query
@@ -21,6 +20,7 @@ from documents.search._query import parse_user_query
 from documents.search._query import rewrite_natural_date_keywords
 from documents.search._schema import build_schema
 from documents.search._tokenizer import register_tokenizers
+from documents.search._translate import InvalidDateQuery
 
 if TYPE_CHECKING:
     from django.contrib.auth.base_user import AbstractBaseUser
@@ -405,12 +405,14 @@ class TestWhooshQueryRewriting:
         assert lo == "2023-12-01T05:00:00Z"
         assert hi == "2023-12-02T05:00:00Z"
 
-    def test_8digit_invalid_date_passes_through_unchanged(self) -> None:
-        assert rewrite_natural_date_keywords("added:20231340", UTC) == "added:20231340"
-
-    def test_compact_14digit_invalid_date_passes_through_unchanged(self) -> None:
-        # Month=13 makes datetime() raise ValueError; the token must be left as-is
-        assert _rewrite_compact_date("20231300120000") == "20231300120000"
+    def test_8digit_invalid_date_raises(self) -> None:
+        # The translation pipeline raises InvalidDateQuery for unparsable dates
+        # (e.g. month=13) so the API can surface a 400 telling the user the date
+        # is malformed instead of silently returning zero results.
+        with pytest.raises(InvalidDateQuery) as exc_info:
+            rewrite_natural_date_keywords("added:20231340", UTC)
+        assert exc_info.value.field == "added"
+        assert exc_info.value.value == "20231340"
 
 
 class TestParseUserQuery:
@@ -463,6 +465,67 @@ class TestParseUserQuery:
     ) -> None:
         assert isinstance(parse_user_query(query_index, raw_query, UTC), tantivy.Query)
 
+    @pytest.mark.parametrize(
+        "raw_query",
+        [
+            # Partial date scalar (year only)
+            pytest.param("created:2020", id="created_year_scalar"),
+            # 8-digit compact date range in brackets
+            pytest.param(
+                "created:[20200101 TO 20201231]",
+                id="created_8digit_bracket_range",
+            ),
+            # Comma-separated field + date range (Whoosh v2 multi-clause syntax)
+            pytest.param(
+                "title:x,created:[2020 TO 2021]",
+                id="title_comma_created_range",
+            ),
+            # Field alias: type -> document_type
+            pytest.param("type:invoice", id="type_alias"),
+            # Multi-word date keyword
+            pytest.param("created:previous week", id="created_previous_week"),
+            # Full ISO datetime range
+            pytest.param(
+                "created:[2026-01-01T00:00:00Z TO 2026-06-01T00:00:00Z]",
+                id="created_iso_range",
+            ),
+            # Comma-separated ISO ranges (Whoosh v2 syntax)
+            pytest.param(
+                "created:[2026-01-01T00:00:00Z TO 2026-06-01T00:00:00Z],"
+                "added:[2026-05-01T00:00:00Z TO 2026-06-01T00:00:00Z]",
+                id="comma_iso_ranges",
+            ),
+        ],
+    )
+    def test_advanced_search_queries_do_not_raise(
+        self,
+        query_index: tantivy.Index,
+        raw_query: str,
+    ) -> None:
+        """
+        End-to-end: queries that the frontend sends must parse without raising.
+
+        This tests the full pipeline: translate_query -> tantivy parse_query.
+        Equivalent to asserting HTTP 200 (not 400) for each query form.
+        """
+        with time_machine.travel(datetime(2026, 6, 15, 12, 0, tzinfo=UTC), tick=False):
+            assert isinstance(
+                parse_user_query(query_index, raw_query, UTC),
+                tantivy.Query,
+            )
+
+    def test_invalid_date_propagates_not_swallowed(
+        self,
+        query_index: tantivy.Index,
+    ) -> None:
+        # parse_user_query falls back to the raw query on unexpected translation
+        # errors, but an InvalidDateQuery is intentional and must propagate so the
+        # view can return a 400 instead of silently parsing the raw (invalid) date.
+        with pytest.raises(InvalidDateQuery) as exc_info:
+            parse_user_query(query_index, "created:202023", UTC)
+        assert exc_info.value.field == "created"
+        assert exc_info.value.value == "202023"
+
 
 class TestYearRangeRewriting:
     """Whoosh-style year-only date ranges must be rewritten to ISO 8601."""
@@ -542,11 +605,16 @@ class TestYearRangeRewriting:
         assert rewrite_natural_date_keywords(original, UTC) == original
 
     def test_8digit_in_brackets_not_matched_as_year_range(self) -> None:
-        # [YYYYMMDD TO YYYYMMDD] has 8-digit values - must not be caught by year rewriter
+        # [YYYYMMDD TO YYYYMMDD]: the translation layer converts 8-digit bounds to
+        # ISO day ranges. 20200101 -> 2020-01-01T00:00:00Z (lo of that day);
+        # 20201231 -> the ceil of Dec 31 = 2021-01-01T00:00:00Z (exclusive end).
+        # This is the correct and accepted behavior: old compact form becomes a
+        # proper Tantivy-parseable ISO range.
         original = "created:[20200101 TO 20201231]"
         result = rewrite_natural_date_keywords(original, UTC)
-        assert "20200101" in result or "2020-01-01" in result
-        assert "20201231" in result or "2020-12-31" in result
+        lo, hi = _range(result, "created")
+        assert lo == "2020-01-01T00:00:00Z"
+        assert hi == "2021-01-01T00:00:00Z"
 
 
 class TestNonDateFieldsNotRewritten:
@@ -606,6 +674,16 @@ class TestNormalizeQuery:
     def test_normalize_expands_comma_separated_tags(self) -> None:
         assert normalize_query("tag:foo,bar") == "tag:foo AND tag:bar"
 
+    def test_normalize_comma_between_range_expressions(self) -> None:
+        # Comma-separated field range expressions (Whoosh v2 syntax) must be
+        # converted to AND so Tantivy does not receive an invalid comma.
+        q = "created:[2026-01-01T00:00:00Z TO 2026-06-01T00:00:00Z],added:[2026-05-01T00:00:00Z TO 2026-06-01T00:00:00Z]"
+        assert normalize_query(q) == (
+            "created:[2026-01-01T00:00:00Z TO 2026-06-01T00:00:00Z]"
+            " AND "
+            "added:[2026-05-01T00:00:00Z TO 2026-06-01T00:00:00Z]"
+        )
+
     def test_normalize_expands_three_values(self) -> None:
         assert normalize_query("tag:foo,bar,baz") == "tag:foo AND tag:bar AND tag:baz"