Enable more ruff rules

ee/billing/quota_limiting.py

@@ -327,17 +327,17 @@ def update_all_org_billing_quotas(
     period_start, period_end = period
 
     # Clickhouse is good at counting things so we count across all teams rather than doing it one by one
-    all_data = dict(
-        teams_with_event_count_in_period=convert_team_usage_rows_to_dict(
+    all_data = {
+        "teams_with_event_count_in_period": convert_team_usage_rows_to_dict(
             get_teams_with_billable_event_count_in_period(period_start, period_end)
         ),
-        teams_with_recording_count_in_period=convert_team_usage_rows_to_dict(
+        "teams_with_recording_count_in_period": convert_team_usage_rows_to_dict(
             get_teams_with_recording_count_in_period(period_start, period_end)
         ),
-        teams_with_rows_synced_in_period=convert_team_usage_rows_to_dict(
+        "teams_with_rows_synced_in_period": convert_team_usage_rows_to_dict(
             get_teams_with_rows_synced_in_period(period_start, period_end)
         ),
-    )
+    }
 
     teams: Sequence[Team] = list(
         Team.objects.select_related("organization")

ee/billing/test/test_quota_limiting.py

@@ -440,15 +440,15 @@ def test_set_org_usage_summary_updates_correctly(self):
         }
         self.organization.save()
 
-        new_usage = dict(
-            events={"usage": 100, "limit": 100},
-            recordings={"usage": 2, "limit": 100},
-            rows_synced={"usage": 6, "limit": 100},
-            period=[
+        new_usage = {
+            "events": {"usage": 100, "limit": 100},
+            "recordings": {"usage": 2, "limit": 100},
+            "rows_synced": {"usage": 6, "limit": 100},
+            "period": [
                 "2021-01-01T00:00:00Z",
                 "2021-01-31T23:59:59Z",
             ],
-        )
+        }
 
         assert set_org_usage_summary(self.organization, new_usage=new_usage)
 
@@ -468,15 +468,15 @@ def test_set_org_usage_summary_does_nothing_if_the_same(self):
         }
         self.organization.save()
 
-        new_usage = dict(
-            events={"usage": 99, "limit": 100},
-            recordings={"usage": 1, "limit": 100},
-            rows_synced={"usage": 5, "limit": 100},
-            period=[
+        new_usage = {
+            "events": {"usage": 99, "limit": 100},
+            "recordings": {"usage": 1, "limit": 100},
+            "rows_synced": {"usage": 5, "limit": 100},
+            "period": [
                 "2021-01-01T00:00:00Z",
                 "2021-01-31T23:59:59Z",
             ],
-        )
+        }
 
         assert not set_org_usage_summary(self.organization, new_usage=new_usage)
 

ee/clickhouse/materialized_columns/analyze.py

@@ -58,7 +58,7 @@ def group_on_events_properties(self, group_type_index: int, team_id: str) -> Set
 
     def _get_properties(self, query, team_id) -> Set[str]:
         rows = sync_execute(query, {"team_id": team_id})
-        return set(name for name, _ in rows)
+        return {name for name, _ in rows}
 
 
 class Query:

ee/clickhouse/models/test/test_property.py

@@ -1773,18 +1773,16 @@ def clean_up_materialised_columns():
 @freeze_time("2021-04-01T01:00:00.000Z")
 def test_prop_filter_json_extract(test_events, clean_up_materialised_columns, property, expected_event_indexes, team):
     query, params = prop_filter_json_extract(property, 0, allow_denormalized_props=False)
-    uuids = list(
-        sorted(
-            [
-                str(uuid)
-                for (uuid,) in sync_execute(
-                    f"SELECT uuid FROM events WHERE team_id = %(team_id)s {query}",
-                    {"team_id": team.pk, **params},
-                )
-            ]
-        )
+    uuids = sorted(
+        [
+            str(uuid)
+            for (uuid,) in sync_execute(
+                f"SELECT uuid FROM events WHERE team_id = %(team_id)s {query}",
+                {"team_id": team.pk, **params},
+            )
+        ]
     )
-    expected = list(sorted([test_events[index] for index in expected_event_indexes]))
+    expected = sorted([test_events[index] for index in expected_event_indexes])
 
     assert len(uuids) == len(expected)  # helpful when diagnosing assertion failure below
     assert uuids == expected
@@ -1801,18 +1799,16 @@ def test_prop_filter_json_extract_materialized(
 
     assert "JSONExtract" not in query
 
-    uuids = list(
-        sorted(
-            [
-                str(uuid)
-                for (uuid,) in sync_execute(
-                    f"SELECT uuid FROM events WHERE team_id = %(team_id)s {query}",
-                    {"team_id": team.pk, **params},
-                )
-            ]
-        )
+    uuids = sorted(
+        [
+            str(uuid)
+            for (uuid,) in sync_execute(
+                f"SELECT uuid FROM events WHERE team_id = %(team_id)s {query}",
+                {"team_id": team.pk, **params},
+            )
+        ]
     )
-    expected = list(sorted([test_events[index] for index in expected_event_indexes]))
+    expected = sorted([test_events[index] for index in expected_event_indexes])
 
     assert uuids == expected
 
@@ -1837,18 +1833,16 @@ def test_prop_filter_json_extract_person_on_events_materialized(
     )
     assert "JSON" not in query
 
-    uuids = list(
-        sorted(
-            [
-                str(uuid)
-                for (uuid,) in sync_execute(
-                    f"SELECT uuid FROM events WHERE team_id = %(team_id)s {query}",
-                    {"team_id": team.pk, **params},
-                )
-            ]
-        )
+    uuids = sorted(
+        [
+            str(uuid)
+            for (uuid,) in sync_execute(
+                f"SELECT uuid FROM events WHERE team_id = %(team_id)s {query}",
+                {"team_id": team.pk, **params},
+            )
+        ]
     )
-    expected = list(sorted([test_events[index] for index in expected_event_indexes]))
+    expected = sorted([test_events[index] for index in expected_event_indexes])
 
     assert uuids == expected
 

ee/clickhouse/queries/column_optimizer.py

@@ -22,7 +22,7 @@ class EnterpriseColumnOptimizer(FOSSColumnOptimizer):
     @cached_property
     def group_types_to_query(self) -> Set[GroupTypeIndex]:
         used_properties = self.used_properties_with_type("group")
-        return set(cast(GroupTypeIndex, group_type_index) for _, _, group_type_index in used_properties)
+        return {cast(GroupTypeIndex, group_type_index) for _, _, group_type_index in used_properties}
 
     @cached_property
     def group_on_event_columns_to_query(self) -> Set[ColumnName]:

ee/clickhouse/queries/experiments/utils.py

@@ -31,7 +31,7 @@ def requires_flag_warning(filter: Filter, team: Team) -> bool:
             events.add(entity.id)
 
     entity_query = f"AND event IN %(events_list)s"
-    entity_params = {"events_list": sorted(list(events))}
+    entity_params = {"events_list": sorted(events)}
 
     events_result = sync_execute(
         f"""

ee/clickhouse/queries/funnels/funnel_correlation.py

@@ -587,7 +587,7 @@ def _get_funnel_step_names(self):
             elif entity.id is not None:
                 events.add(entity.id)
 
-        return sorted(list(events))
+        return sorted(events)
 
     def _run(self) -> Tuple[List[EventOddsRatio], bool]:
         """

ee/migrations/0012_migrate_tags_v2.py

@@ -40,7 +40,7 @@ def forwards(apps, schema_editor):
         )
         event_definitions = iter(event_definition_paginator.get_page(event_definition_page))
         for tags, team_id, event_definition_id in event_definitions:
-            unique_tags = set(tagify(t) for t in tags if isinstance(t, str) and t.strip() != "")
+            unique_tags = {tagify(t) for t in tags if isinstance(t, str) and t.strip() != ""}
             for tag in unique_tags:
                 temp_tag = Tag(name=tag, team_id=team_id)
                 createables.append(
@@ -71,7 +71,7 @@ def forwards(apps, schema_editor):
         )
         property_definitions = iter(property_definition_paginator.get_page(property_definition_page))
         for tags, team_id, property_definition_id in property_definitions:
-            unique_tags = set(tagify(t) for t in tags if isinstance(t, str) and t.strip() != "")
+            unique_tags = {tagify(t) for t in tags if isinstance(t, str) and t.strip() != ""}
             for tag in unique_tags:
                 temp_tag = Tag(name=tag, team_id=team_id)
                 createables.append(

ee/tasks/test/subscriptions/subscriptions_test_factory.py

@@ -7,13 +7,13 @@
 
 
 def create_subscription(**kwargs: Any) -> Subscription:
-    payload = dict(
-        target_type="email",
-        target_value="[email protected],[email protected]",
-        frequency="daily",
-        interval=1,
-        start_date=datetime(2022, 1, 1, 9, 0).replace(tzinfo=ZoneInfo("UTC")),
-    )
+    payload = {
+        "target_type": "email",
+        "target_value": "[email protected],[email protected]",
+        "frequency": "daily",
+        "interval": 1,
+        "start_date": datetime(2022, 1, 1, 9, 0).replace(tzinfo=ZoneInfo("UTC")),
+    }
 
     payload.update(kwargs)
     return Subscription.objects.create(**payload)

posthog/api/documentation.py

@@ -250,5 +250,5 @@ def custom_postprocessing_hook(result, generator, request, public):
         **result,
         "info": {"title": "PostHog API", "version": None, "description": ""},
         "paths": paths,
-        "x-tagGroups": [{"name": "All endpoints", "tags": sorted(list(set(all_tags)))}],
+        "x-tagGroups": [{"name": "All endpoints", "tags": sorted(set(all_tags))}],
     }

posthog/api/ingestion_warnings.py

@@ -47,4 +47,4 @@ def _calculate_summaries(warning_events):
         summaries[warning_type]["warnings"].append({"type": warning_type, "timestamp": timestamp, "details": details})
         summaries[warning_type]["count"] += 1
 
-    return list(sorted(summaries.values(), key=lambda summary: summary["lastSeen"], reverse=True))
+    return sorted(summaries.values(), key=lambda summary: summary["lastSeen"], reverse=True)

posthog/api/sharing.py

@@ -122,12 +122,12 @@ def _get_sharing_configuration(self, context: Dict[str, Any]):
         insight = context.get("insight")
         recording = context.get("recording")
 
-        config_kwargs = dict(
-            team_id=self.team_id,
-            insight=insight,
-            dashboard=dashboard,
-            recording=recording,
-        )
+        config_kwargs = {
+            "team_id": self.team_id,
+            "insight": insight,
+            "dashboard": dashboard,
+            "recording": recording,
+        }
 
         try:
             instance = SharingConfiguration.objects.get(**config_kwargs)

posthog/api/test/dashboards/test_dashboard.py

@@ -903,7 +903,7 @@ def test_dashboard_duplication(self):
         self.assertEqual(len(response["tiles"]), len(existing_dashboard.insights.all()))
 
         existing_dashboard_item_id_set = {tile1.pk, tile2.pk}
-        response_item_id_set = set(map(lambda x: x.get("id", None), response["tiles"]))
+        response_item_id_set = {x.get("id", None) for x in response["tiles"]}
         # check both sets are disjoint to verify that the new items' ids are different than the existing items
 
         self.assertTrue(existing_dashboard_item_id_set.isdisjoint(response_item_id_set))

posthog/api/test/dashboards/test_dashboard_text_tiles.py

@@ -164,7 +164,7 @@ def test_can_update_a_single_text_tile_color(self) -> None:
         dashboard_id, dashboard_json = self.dashboard_api.update_text_tile(dashboard_id, updated_tile)
 
         assert len(dashboard_json["tiles"]) == 2
-        assert set((t["id"], t["color"]) for t in dashboard_json["tiles"]) == {
+        assert {(t["id"], t["color"]) for t in dashboard_json["tiles"]} == {
             (tile_ids[0], "purple"),
             (tile_ids[1], None),
         }

posthog/api/test/test_feature_flag.py

@@ -1327,7 +1327,7 @@ def test_create_feature_flag_usage_dashboard(self, mock_capture):
         self.assertEqual(instance.key, "alpha-feature")
 
         dashboard = instance.usage_dashboard
-        tiles = sorted([tile for tile in dashboard.tiles.all()], key=lambda x: x.insight.name)
+        tiles = sorted(dashboard.tiles.all(), key=lambda x: x.insight.name)
 
         self.assertEqual(dashboard.name, "Generated Dashboard: alpha-feature Usage")
         self.assertEqual(
@@ -1421,7 +1421,7 @@ def test_create_feature_flag_usage_dashboard(self, mock_capture):
         instance.refresh_from_db()
 
         dashboard = instance.usage_dashboard
-        tiles = sorted([tile for tile in dashboard.tiles.all()], key=lambda x: x.insight.name)
+        tiles = sorted(dashboard.tiles.all(), key=lambda x: x.insight.name)
 
         self.assertEqual(dashboard.name, "Generated Dashboard: alpha-feature Usage")
         self.assertEqual(

posthog/api/test/test_organization_feature_flag.py

@@ -606,7 +606,7 @@ def connect(parent, child):
         original_cohorts_cache = {}
         for _, cohort in cohorts.items():
             original_cohorts_cache[cohort.id] = cohort
-        original_cohort_ids = {cohort_id for cohort_id in original_cohorts_cache.keys()}
+        original_cohort_ids = set(original_cohorts_cache.keys())
         topologically_sorted_original_cohort_ids = sort_cohorts_topologically(
             original_cohort_ids, original_cohorts_cache
         )

posthog/api/test/test_plugin.py

@@ -804,7 +804,7 @@ def test_transpile_plugin_frontend_source(self, mock_get, mock_reload):
         )
         try:
             PluginSourceFile.objects.get(plugin_id=id)
-            assert False, "Should have thrown DoesNotExist"
+            raise AssertionError("Should have thrown DoesNotExist")
         except PluginSourceFile.DoesNotExist:
             assert True
 

posthog/async_migrations/migrations/0002_events_sample_by.py

@@ -186,13 +186,11 @@ def healthcheck(self):
 
     @cached_property
     def _partitions(self):
-        return list(
-            sorted(
-                row[0]
-                for row in sync_execute(
-                    f"SELECT DISTINCT toUInt32(partition) FROM system.parts WHERE database = %(database)s AND table='{EVENTS_TABLE}'",
-                    {"database": CLICKHOUSE_DATABASE},
-                )
+        return sorted(
+            row[0]
+            for row in sync_execute(
+                f"SELECT DISTINCT toUInt32(partition) FROM system.parts WHERE database = %(database)s AND table='{EVENTS_TABLE}'",
+                {"database": CLICKHOUSE_DATABASE},
             )
         )
 

posthog/async_migrations/migrations/0003_fill_person_distinct_id2.py

@@ -91,4 +91,4 @@ def migrate_team_operation(self, team_id: int):
 
     @cached_property
     def _team_ids(self):
-        return list(sorted(row[0] for row in sync_execute("SELECT DISTINCT team_id FROM person_distinct_id")))
+        return sorted(row[0] for row in sync_execute("SELECT DISTINCT team_id FROM person_distinct_id"))

posthog/async_migrations/setup.py

@@ -42,7 +42,7 @@ def setup_async_migrations(ignore_posthog_version: bool = False):
     4. Populate a dependencies map and in-memory record of migration definitions
     """
 
-    applied_migrations = set(instance.name for instance in get_all_completed_async_migrations())
+    applied_migrations = {instance.name for instance in get_all_completed_async_migrations()}
     unapplied_migrations = set(ALL_ASYNC_MIGRATIONS.keys()) - applied_migrations
 
     for migration_name, migration in ALL_ASYNC_MIGRATIONS.items():

posthog/batch_exports/service.py

@@ -472,7 +472,7 @@ def sync_batch_export(batch_export: BatchExport, created: bool):
         paused=batch_export.paused,
     )
 
-    destination_config_fields = set(field.name for field in fields(workflow_inputs))
+    destination_config_fields = {field.name for field in fields(workflow_inputs)}
     destination_config = {k: v for k, v in batch_export.destination.config.items() if k in destination_config_fields}
 
     temporal = sync_connect()

posthog/caching/test/test_insight_cache.py

@@ -54,7 +54,7 @@ def create_insight_caching_state(
 
 # Reaching into the internals of LocMemCache
 def cache_keys(cache):
-    return set(key.split(":", 2)[-1] for key in cache._cache.keys())
+    return {key.split(":", 2)[-1] for key in cache._cache.keys()}
 
 
 @pytest.mark.django_db

posthog/caching/utils.py

@@ -58,12 +58,12 @@ def active_teams() -> Set[int]:
             return set()
         redis.zadd(
             RECENTLY_ACCESSED_TEAMS_REDIS_KEY,
-            {team: score for team, score in teams_by_recency},
+            dict(teams_by_recency),
         )
         redis.expire(RECENTLY_ACCESSED_TEAMS_REDIS_KEY, IN_A_DAY)
         all_teams = teams_by_recency
 
-    return set(int(team_id) for team_id, _ in all_teams)
+    return {int(team_id) for team_id, _ in all_teams}
 
 
 def stale_cache_invalidation_disabled(team: Team) -> bool:

posthog/clickhouse/system_status.py

@@ -122,7 +122,7 @@ def system_status() -> Generator[SystemStatusRow, None, None]:
         "value": "",
         "subrows": {
             "columns": ["Metric", "Value", "Description"],
-            "rows": list(sorted(system_metrics)),
+            "rows": sorted(system_metrics),
         },
     }
 

posthog/demo/matrix/taxonomy_inference.py

@@ -58,7 +58,7 @@ def infer_taxonomy_for_team(team_id: int) -> Tuple[int, int, int]:
 def _get_events_last_seen_at(team_id: int) -> Dict[str, timezone.datetime]:
     from posthog.client import sync_execute
 
-    return {event: last_seen_at for event, last_seen_at in sync_execute(_GET_EVENTS_LAST_SEEN_AT, {"team_id": team_id})}
+    return dict(sync_execute(_GET_EVENTS_LAST_SEEN_AT, {"team_id": team_id}))
 
 
 def _get_property_types(team_id: int) -> Dict[str, Optional[PropertyType]]: