Fix: Make some natural keyword date searches timezone-aware (#10416)

src/documents/index.py

@@ -2,10 +2,12 @@ from __future__ import annotations
 
 import logging
 import math
+import re
 from collections import Counter
 from contextlib import contextmanager
 from datetime import datetime
 from datetime import time
+from datetime import timedelta
 from datetime import timezone
 from shutil import rmtree
 from typing import TYPE_CHECKING
@@ -13,6 +15,8 @@ from typing import Literal
 
 from django.conf import settings
 from django.utils import timezone as django_timezone
+from django.utils.timezone import get_current_timezone
+from django.utils.timezone import now
 from guardian.shortcuts import get_users_with_perms
 from whoosh import classify
 from whoosh import highlight
@@ -344,6 +348,7 @@ class LocalDateParser(English):
 class DelayedFullTextQuery(DelayedQuery):
     def _get_query(self) -> tuple:
         q_str = self.query_params["query"]
+        q_str = rewrite_natural_date_keywords(q_str)
         qp = MultifieldParser(
             [
                 "content",
@@ -450,3 +455,37 @@ def get_permissions_criterias(user: User | None = None) -> list:
                 query.Term("viewer_id", str(user.id)),
             )
     return user_criterias
+
+
+def rewrite_natural_date_keywords(query_string: str) -> str:
+    """
+    Rewrites natural date keywords (e.g. added:today or added:"yesterday") to UTC range syntax for Whoosh.
+    """
+
+    tz = get_current_timezone()
+    local_now = now().astimezone(tz)
+
+    today = local_now.date()
+    yesterday = today - timedelta(days=1)
+
+    ranges = {
+        "today": (
+            datetime.combine(today, time.min, tzinfo=tz),
+            datetime.combine(today, time.max, tzinfo=tz),
+        ),
+        "yesterday": (
+            datetime.combine(yesterday, time.min, tzinfo=tz),
+            datetime.combine(yesterday, time.max, tzinfo=tz),
+        ),
+    }
+
+    pattern = r"(\b(?:added|created))\s*:\s*[\"']?(today|yesterday)[\"']?"
+
+    def repl(m):
+        field, keyword = m.group(1), m.group(2)
+        start, end = ranges[keyword]
+        start_str = start.astimezone(timezone.utc).strftime("%Y%m%d%H%M%S")
+        end_str = end.astimezone(timezone.utc).strftime("%Y%m%d%H%M%S")
+        return f"{field}:[{start_str} TO {end_str}]"
+
+    return re.sub(pattern, repl, query_string)

src/documents/tests/test_index.py

@@ -1,6 +1,11 @@
+from datetime import datetime
 from unittest import mock
 
+from django.contrib.auth.models import User
 from django.test import TestCase
+from django.test import override_settings
+from django.utils.timezone import get_current_timezone
+from django.utils.timezone import timezone
 
 from documents import index
 from documents.models import Document
@@ -90,3 +95,35 @@ class TestAutoComplete(DirectoriesMixin, TestCase):
             _, kwargs = mocked_update_doc.call_args
 
             self.assertIsNone(kwargs["asn"])
+
+    @override_settings(TIME_ZONE="Pacific/Auckland")
+    def test_added_today_respects_local_timezone_boundary(self):
+        tz = get_current_timezone()
+        fixed_now = datetime(2025, 7, 20, 15, 0, 0, tzinfo=tz)
+
+        # Fake a time near the local boundary (1 AM NZT = 13:00 UTC on previous UTC day)
+        local_dt = datetime(2025, 7, 20, 1, 0, 0).replace(tzinfo=tz)
+        utc_dt = local_dt.astimezone(timezone.utc)
+
+        doc = Document.objects.create(
+            title="Time zone",
+            content="Testing added:today",
+            checksum="edgecase123",
+            added=utc_dt,
+        )
+
+        with index.open_index_writer() as writer:
+            index.update_document(writer, doc)
+
+        superuser = User.objects.create_superuser(username="testuser")
+        self.client.force_login(superuser)
+
+        with mock.patch("documents.index.now", return_value=fixed_now):
+            response = self.client.get("/api/documents/?query=added:today")
+            results = response.json()["results"]
+            self.assertEqual(len(results), 1)
+            self.assertEqual(results[0]["id"], doc.id)
+
+            response = self.client.get("/api/documents/?query=added:yesterday")
+            results = response.json()["results"]
+            self.assertEqual(len(results), 0)