Chore: enable flake8-comprehensions (C4) ruff rules

C4 is part of ruff 0.16's expanded default rule set and is almost
entirely autofixable, making it a low-risk first step towards
adopting the new defaults.

pyproject.toml

@@ -186,6 +186,7 @@ line-ending = "lf"
 # https://docs.astral.sh/ruff/rules/
 select = [ "E4", "E7", "E9", "F" ]
 extend-select = [
+  "C4",   # https://docs.astral.sh/ruff/rules/#flake8-comprehensions-c4
   "COM",  # https://docs.astral.sh/ruff/rules/#flake8-commas-com
   "DJ",   # https://docs.astral.sh/ruff/rules/#flake8-django-dj
   "EXE",  # https://docs.astral.sh/ruff/rules/#flake8-executable-exe

src/documents/filters.py

@@ -734,7 +734,7 @@ class CustomFieldQueryParser:
         )
 
         # Check if any of the requested IDs are missing.
-        missing_ids = set(value) - set(link.document_id for link in links)
+        missing_ids = set(value) - {link.document_id for link in links}
         if missing_ids:
             # The result should be an empty set in this case.
             return Q(id__in=[])

src/documents/search/_query.py

@@ -240,7 +240,7 @@ def parse_user_query(
             DEFAULT_SEARCH_FIELDS,
             field_boosts=_FIELD_BOOSTS,
             # (prefix=True, distance=1, transposition_cost_one=True) — edit-distance fuzziness
-            fuzzy_fields={f: (True, 1, True) for f in DEFAULT_SEARCH_FIELDS},
+            fuzzy_fields=dict.fromkeys(DEFAULT_SEARCH_FIELDS, (True, 1, True)),
         )
         # 0.1 boost keeps fuzzy hits ranked below exact matches (intentional)
         clauses.append((tantivy.Occur.Should, tantivy.Query.boost_query(fuzzy, 0.1)))

src/documents/serialisers.py

@@ -433,7 +433,7 @@ class OwnedObjectSerializer(
             return set()
 
         ctype = ContentType.objects.get_for_model(first_obj)
-        object_pks = list(obj.pk for obj in objects)
+        object_pks = [obj.pk for obj in objects]
         pk_type = type(first_obj.pk)
 
         def get_pks_for_permission_type(model):
@@ -2056,13 +2056,12 @@ class BulkEditSerializer(
             for doc in docs:
                 if "-" in doc:
                     pages.append(
-                        [
-                            x
-                            for x in range(
+                        list(
+                            range(
                                 int(doc.split("-")[0]),
                                 int(doc.split("-")[1]) + 1,
-                            )
-                        ],
+                            ),
+                        ),
                     )
                 else:
                     pages.append([int(doc)])

src/documents/tests/test_api_bulk_edit.py

@@ -1003,8 +1003,8 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
             for correspondent in response.data[field]:
                 self.assertEqual(correspondent["document_count"], 0)
             self.assertCountEqual(
-                map(lambda c: c["id"], response.data[field]),
-                map(lambda c: c["id"], Entity.objects.values("id")),
+                (c["id"] for c in response.data[field]),
+                (c["id"] for c in Entity.objects.values("id")),
             )
 
     def test_api_selection_data(self) -> None:

src/documents/tests/test_api_profile.py

@@ -18,8 +18,8 @@ class MockOpenIDProvider:
 
     def get_brands(self):
         default_servers = [
-            dict(id="yahoo", name="Yahoo", openid_url="http://me.yahoo.com"),
-            dict(id="hyves", name="Hyves", openid_url="http://hyves.nl"),
+            {"id": "yahoo", "name": "Yahoo", "openid_url": "http://me.yahoo.com"},
+            {"id": "hyves", "name": "Hyves", "openid_url": "http://hyves.nl"},
         ]
         return default_servers
 

src/documents/views.py

@@ -1478,13 +1478,12 @@ class DocumentViewSet(
             with get_date_parser() as date_parser:
                 gen = date_parser.parse(doc.filename, doc.content)
                 dates = sorted(
-                    {
-                        i
-                        for i in itertools.islice(
+                    set(
+                        itertools.islice(
                             gen,
                             settings.NUMBER_OF_SUGGESTED_DATES,
-                        )
-                    },
+                        ),
+                    ),
                 )
 
         resp_data = {
@@ -4135,7 +4134,7 @@ class UiSettingsView(GenericAPIView[Any]):
             user_resp["last_name"] = user.last_name
 
         # strip <app_label>.
-        roles = map(lambda perm: re.sub(r"^\w+.", "", perm), user.get_all_permissions())
+        roles = (re.sub(r"^\w+.", "", perm) for perm in user.get_all_permissions())
         return Response(
             {
                 "user": user_resp,

src/paperless/tests/settings/test_db_cache.py

@@ -114,17 +114,17 @@ def test_cache_hit_when_enabled() -> None:
     assert settings.CACHALOT_TIMEOUT == 1
 
     # Read a table to populate the cache
-    list(list(Tag.objects.values_list("id", flat=True)))
+    list(Tag.objects.values_list("id", flat=True))
 
     # Invalidate the cache then read the database, there should be DB hit
     invalidate_db_cache()
     with CaptureQueriesContext(connection) as ctx:
-        list(list(Tag.objects.values_list("id", flat=True)))
+        list(Tag.objects.values_list("id", flat=True))
     assert len(ctx)
 
     # Doing the same request again should hit the cache, not the DB
     with CaptureQueriesContext(connection) as ctx:
-        list(list(Tag.objects.values_list("id", flat=True)))
+        list(Tag.objects.values_list("id", flat=True))
     assert not len(ctx)
 
     # Wait the end of TTL
@@ -133,7 +133,7 @@ def test_cache_hit_when_enabled() -> None:
 
     # Read the DB again. The DB should be hit because the cache has expired
     with CaptureQueriesContext(connection) as ctx:
-        list(list(Tag.objects.values_list("id", flat=True)))
+        list(Tag.objects.values_list("id", flat=True))
     assert len(ctx)
 
     # Invalidate the cache at the end of test
@@ -149,7 +149,7 @@ def test_cache_is_disabled_by_default() -> None:
     # Read the table multiple times: the DB should always be hit without cache
     for _ in range(3):
         with CaptureQueriesContext(connection) as ctx:
-            list(list(Tag.objects.values_list("id", flat=True)))
+            list(Tag.objects.values_list("id", flat=True))
         assert len(ctx)
 
     # Invalidate the cache at the end of test