Fix (dev): retain backwards compatibility with natural-date keywords in tantivy (#12602)

This commit is contained in:
shamoon
2026-04-20 08:26:33 -07:00
committed by GitHub
parent 750a2723a2
commit 20aa0937e8
4 changed files with 187 additions and 70 deletions
+66 -33
View File
@@ -81,45 +81,38 @@ class TestCreatedDateField:
),
pytest.param(
"created",
"this_week",
"2026-03-23T00:00:00Z",
"2026-03-30T00:00:00Z",
id="this_week_mon_sun",
),
pytest.param(
"created",
"last_week",
"previous week",
"2026-03-16T00:00:00Z",
"2026-03-23T00:00:00Z",
id="last_week",
id="previous_week",
),
pytest.param(
"created",
"this_month",
"this month",
"2026-03-01T00:00:00Z",
"2026-04-01T00:00:00Z",
id="this_month",
),
pytest.param(
"created",
"last_month",
"previous month",
"2026-02-01T00:00:00Z",
"2026-03-01T00:00:00Z",
id="last_month",
id="previous_month",
),
pytest.param(
"created",
"this_year",
"this year",
"2026-01-01T00:00:00Z",
"2027-01-01T00:00:00Z",
id="this_year",
),
pytest.param(
"created",
"last_year",
"previous year",
"2025-01-01T00:00:00Z",
"2026-01-01T00:00:00Z",
id="last_year",
id="previous_year",
),
],
)
@@ -141,7 +134,7 @@ class TestCreatedDateField:
def test_this_month_december_wraps_to_next_year(self) -> None:
# December: next month must roll over to January 1 of next year
lo, hi = _range(
rewrite_natural_date_keywords("created:this_month", UTC),
rewrite_natural_date_keywords("created:this month", UTC),
"created",
)
assert lo == "2026-12-01T00:00:00Z"
@@ -151,12 +144,21 @@ class TestCreatedDateField:
def test_last_month_january_wraps_to_previous_year(self) -> None:
# January: last month must roll back to December 1 of previous year
lo, hi = _range(
rewrite_natural_date_keywords("created:last_month", UTC),
rewrite_natural_date_keywords("created:previous month", UTC),
"created",
)
assert lo == "2025-12-01T00:00:00Z"
assert hi == "2026-01-01T00:00:00Z"
@time_machine.travel(datetime(2026, 7, 15, 12, 0, tzinfo=UTC), tick=False)
def test_previous_quarter(self) -> None:
lo, hi = _range(
rewrite_natural_date_keywords('created:"previous quarter"', UTC),
"created",
)
assert lo == "2026-04-01T00:00:00Z"
assert hi == "2026-07-01T00:00:00Z"
def test_unknown_keyword_raises(self) -> None:
with pytest.raises(ValueError, match="Unknown keyword"):
_date_only_range("bogus_keyword", UTC)
@@ -202,40 +204,34 @@ class TestDateTimeFields:
id="yesterday",
),
pytest.param(
"this_week",
"2026-03-23T00:00:00Z",
"2026-03-30T00:00:00Z",
id="this_week",
),
pytest.param(
"last_week",
"previous week",
"2026-03-16T00:00:00Z",
"2026-03-23T00:00:00Z",
id="last_week",
id="previous_week",
),
pytest.param(
"this_month",
"this month",
"2026-03-01T00:00:00Z",
"2026-04-01T00:00:00Z",
id="this_month",
),
pytest.param(
"last_month",
"previous month",
"2026-02-01T00:00:00Z",
"2026-03-01T00:00:00Z",
id="last_month",
id="previous_month",
),
pytest.param(
"this_year",
"this year",
"2026-01-01T00:00:00Z",
"2027-01-01T00:00:00Z",
id="this_year",
),
pytest.param(
"last_year",
"previous year",
"2025-01-01T00:00:00Z",
"2026-01-01T00:00:00Z",
id="last_year",
id="previous_year",
),
],
)
@@ -254,17 +250,54 @@ class TestDateTimeFields:
@time_machine.travel(datetime(2026, 12, 15, 12, 0, tzinfo=UTC), tick=False)
def test_this_month_december_wraps_to_next_year(self) -> None:
# December: next month wraps to January of next year
lo, hi = _range(rewrite_natural_date_keywords("added:this_month", UTC), "added")
lo, hi = _range(rewrite_natural_date_keywords("added:this month", UTC), "added")
assert lo == "2026-12-01T00:00:00Z"
assert hi == "2027-01-01T00:00:00Z"
@time_machine.travel(datetime(2026, 1, 15, 12, 0, tzinfo=UTC), tick=False)
def test_last_month_january_wraps_to_previous_year(self) -> None:
# January: last month wraps back to December of previous year
lo, hi = _range(rewrite_natural_date_keywords("added:last_month", UTC), "added")
lo, hi = _range(
rewrite_natural_date_keywords("added:previous month", UTC),
"added",
)
assert lo == "2025-12-01T00:00:00Z"
assert hi == "2026-01-01T00:00:00Z"
@pytest.mark.parametrize(
("query", "expected_lo", "expected_hi"),
[
pytest.param(
'added:"previous quarter"',
"2026-04-01T00:00:00Z",
"2026-07-01T00:00:00Z",
id="quoted_previous_quarter",
),
pytest.param(
"added:previous month",
"2026-06-01T00:00:00Z",
"2026-07-01T00:00:00Z",
id="bare_previous_month",
),
pytest.param(
"added:this month",
"2026-07-01T00:00:00Z",
"2026-08-01T00:00:00Z",
id="bare_this_month",
),
],
)
@time_machine.travel(datetime(2026, 7, 15, 12, 0, tzinfo=UTC), tick=False)
def test_legacy_natural_language_aliases(
self,
query: str,
expected_lo: str,
expected_hi: str,
) -> None:
lo, hi = _range(rewrite_natural_date_keywords(query, UTC), "added")
assert lo == expected_lo
assert hi == expected_hi
def test_unknown_keyword_raises(self) -> None:
with pytest.raises(ValueError, match="Unknown keyword"):
_datetime_range("bogus_keyword", UTC)
+45
View File
@@ -3,6 +3,7 @@ from datetime import timedelta
from unittest import mock
import pytest
import time_machine
from dateutil.relativedelta import relativedelta
from django.contrib.auth.models import Group
from django.contrib.auth.models import Permission
@@ -26,6 +27,7 @@ from documents.models import Tag
from documents.models import Workflow
from documents.search import get_backend
from documents.search import reset_backend
from documents.tests.factories import DocumentFactory
from documents.tests.utils import DirectoriesMixin
from paperless_mail.models import MailAccount
from paperless_mail.models import MailRule
@@ -741,6 +743,49 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
# Tantivy rejects unparsable field queries with a 400
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
@override_settings(
TIME_ZONE="UTC",
)
@time_machine.travel(
datetime.datetime(2026, 7, 15, 12, 0, tzinfo=datetime.UTC),
tick=False,
)
def test_search_added_previous_quarter(self) -> None:
"""
GIVEN:
- Documents inside and outside the previous quarter
WHEN:
- Query with the legacy natural-language phrase used by the UI
THEN:
- Previous-quarter documents are returned
"""
d1 = DocumentFactory.create(
title="quarterly statement april",
content="bank statement",
added=datetime.datetime(2026, 4, 10, 12, 0, tzinfo=datetime.UTC),
)
d2 = DocumentFactory.create(
title="quarterly statement june",
content="bank statement",
added=datetime.datetime(2026, 6, 20, 12, 0, tzinfo=datetime.UTC),
)
d3 = DocumentFactory.create(
title="quarterly statement july",
content="bank statement",
added=datetime.datetime(2026, 7, 10, 12, 0, tzinfo=datetime.UTC),
)
backend = get_backend()
backend.add_or_update(d1)
backend.add_or_update(d2)
backend.add_or_update(d3)
response = self.client.get('/api/documents/?query=added:"previous quarter"')
self.assertEqual(response.status_code, status.HTTP_200_OK)
results = response.data["results"]
self.assertEqual({r["id"] for r in results}, {1, 2})
@mock.patch("documents.search._backend.TantivyBackend.autocomplete")
def test_search_autocomplete_limits(self, m) -> None:
"""