Fix sub label filter for non-ascii names (#24953)

* fix sub label filter for non-ascii names

The sub_labels filter lowercased the requested name in Python but the stored value with SQLite's LOWER(), which only folds ASCII. Cyrillic and other non-ASCII names never matched, so filtering by a face name returned no events. Both sides are now lowered in SQLite, which keeps ASCII matching case-insensitive and non-ASCII matching exact.

* cover events/search in sub label filter test

frigate/api/event.py

@@ -199,18 +199,14 @@ def events(
             sub_label_clauses.append(Event.sub_label.is_null())
 
         for label in filtered_sub_labels:
-            lowered = label.lower()
-            sub_label_clauses.append(
-                fn.LOWER(Event.sub_label.cast("text")) == lowered
-            )  # include exact matches (case-insensitive)
+            # SQLite LOWER() only folds ASCII, so lower both sides in SQL to
+            # keep non-ASCII names matching exactly
+            stored = fn.LOWER(Event.sub_label.cast("text"))
+            sub_label_clauses.append(stored == fn.LOWER(label))
 
-            # include this label when part of a list (LIKE is case-insensitive in sqlite for ASCII)
-            sub_label_clauses.append(
-                fn.LOWER(Event.sub_label.cast("text")) % f"*{lowered},*"
-            )
-            sub_label_clauses.append(
-                fn.LOWER(Event.sub_label.cast("text")) % f"*, {lowered}*"
-            )
+            # include this label when part of a list
+            sub_label_clauses.append(stored % fn.LOWER(f"*{label},*"))
+            sub_label_clauses.append(stored % fn.LOWER(f"*, {label}*"))
 
         sub_label_clause = reduce(operator.or_, sub_label_clauses)
         clauses.append(sub_label_clause)
@@ -633,18 +629,14 @@ def events_search(
             sub_label_clauses.append(Event.sub_label.is_null())
 
         for label in filtered_sub_labels:
-            lowered = label.lower()
-            sub_label_clauses.append(
-                fn.LOWER(Event.sub_label.cast("text")) == lowered
-            )  # include exact matches (case-insensitive)
+            # SQLite LOWER() only folds ASCII, so lower both sides in SQL to
+            # keep non-ASCII names matching exactly
+            stored = fn.LOWER(Event.sub_label.cast("text"))
+            sub_label_clauses.append(stored == fn.LOWER(label))
 
-            # include this label when part of a list (LIKE is case-insensitive in sqlite for ASCII)
-            sub_label_clauses.append(
-                fn.LOWER(Event.sub_label.cast("text")) % f"*{lowered},*"
-            )
-            sub_label_clauses.append(
-                fn.LOWER(Event.sub_label.cast("text")) % f"*, {lowered}*"
-            )
+            # include this label when part of a list
+            sub_label_clauses.append(stored % fn.LOWER(f"*{label},*"))
+            sub_label_clauses.append(stored % fn.LOWER(f"*, {label}*"))
 
         event_filters.append(reduce(operator.or_, sub_label_clauses))
 

frigate/test/http_api/test_http_event.py

@@ -485,6 +485,40 @@ class TestHttpApp(BaseTestHttp):
             assert sub_labels
             assert sub_labels == [sub_label]
 
+    def test_get_event_list_filter_sub_labels(self):
+        sub_labels = {
+            "1.cyrillic": "Кузнецова Ира",
+            "2.joined": "Ира, Bob",
+            "3.ascii": "Alice",
+            "4.none": None,
+        }
+        mock_embeddings = Mock()
+        mock_embeddings.search_thumbnail.return_value = [(id, 0.1) for id in sub_labels]
+
+        self.app.frigate_config.semantic_search.enabled = True
+        self.app.embeddings = mock_embeddings
+
+        with AuthTestClient(self.app) as client:
+            for id, sub_label in sub_labels.items():
+                super().insert_mock_event(id)
+                Event.update(sub_label=sub_label).where(Event.id == id).execute()
+
+            search_params = {"search_type": "similarity", "event_id": "1.cyrillic"}
+
+            for path, params in (("/events", {}), ("/events/search", search_params)):
+
+                def ids(query: str) -> set[str]:
+                    events = client.get(
+                        path, params={**params, "sub_labels": query}
+                    ).json()
+                    return {event["id"] for event in events}
+
+                assert ids("Кузнецова Ира") == {"1.cyrillic"}
+                assert ids("Ира") == {"2.joined"}
+                assert ids("bob") == {"2.joined"}
+                assert ids("ALICE") == {"3.ascii"}
+                assert ids("None") == {"4.none"}
+
     ####################################################################################################################
     ###################################  GET /metrics Endpoint   #########################################################
     ####################################################################################################################