consolidate attribute filtering to match non-english and url encoded values (#22002)

Author: hawkeye217

frigate/api/event.py

@@ -69,6 +69,25 @@
 router = APIRouter(tags=[Tags.events])
 
 
+def _build_attribute_filter_clause(attributes: str):
+    filtered_attributes = [
+        attr.strip() for attr in attributes.split(",") if attr.strip()
+    ]
+    attribute_clauses = []
+
+    for attr in filtered_attributes:
+        attribute_clauses.append(Event.data.cast("text") % f'*:"{attr}"*')
+
+        escaped_attr = json.dumps(attr, ensure_ascii=True)[1:-1]
+        if escaped_attr != attr:
+            attribute_clauses.append(Event.data.cast("text") % f'*:"{escaped_attr}"*')
+
+    if not attribute_clauses:
+        return None
+
+    return reduce(operator.or_, attribute_clauses)
+
+
 @router.get(
     "/events",
     response_model=list[EventResponse],
@@ -193,14 +212,9 @@ def events(
 
     if attributes != "all":
         # Custom classification results are stored as data[model_name] = result_value
-        filtered_attributes = attributes.split(",")
-        attribute_clauses = []
-
-        for attr in filtered_attributes:
-            attribute_clauses.append(Event.data.cast("text") % f'*:"{attr}"*')
-
-        attribute_clause = reduce(operator.or_, attribute_clauses)
-        clauses.append(attribute_clause)
+        attribute_clause = _build_attribute_filter_clause(attributes)
+        if attribute_clause is not None:
+            clauses.append(attribute_clause)
 
     if recognized_license_plate != "all":
         filtered_recognized_license_plates = recognized_license_plate.split(",")
@@ -508,7 +522,7 @@ def events_search(
     cameras = params.cameras
     labels = params.labels
     sub_labels = params.sub_labels
-    attributes = params.attributes
+    attributes = unquote(params.attributes)
     zones = params.zones
     after = params.after
     before = params.before
@@ -607,13 +621,9 @@ def events_search(
 
     if attributes != "all":
         # Custom classification results are stored as data[model_name] = result_value
-        filtered_attributes = attributes.split(",")
-        attribute_clauses = []
-
-        for attr in filtered_attributes:
-            attribute_clauses.append(Event.data.cast("text") % f'*:"{attr}"*')
-
-        event_filters.append(reduce(operator.or_, attribute_clauses))
+        attribute_clause = _build_attribute_filter_clause(attributes)
+        if attribute_clause is not None:
+            event_filters.append(attribute_clause)
 
     if zones != "all":
         zone_clauses = []

frigate/test/http_api/test_http_event.py

@@ -168,6 +168,57 @@ def test_get_event_list_sort_start_time(self):
             assert events[0]["id"] == id
             assert events[1]["id"] == id2
 
+    def test_get_event_list_match_multilingual_attribute(self):
+        event_id = "123456.zh"
+        attribute = "中文标签"
+
+        with AuthTestClient(self.app) as client:
+            super().insert_mock_event(event_id, data={"custom_attr": attribute})
+
+            events = client.get("/events", params={"attributes": attribute}).json()
+            assert len(events) == 1
+            assert events[0]["id"] == event_id
+
+            events = client.get(
+                "/events", params={"attributes": "%E4%B8%AD%E6%96%87%E6%A0%87%E7%AD%BE"}
+            ).json()
+            assert len(events) == 1
+            assert events[0]["id"] == event_id
+
+    def test_events_search_match_multilingual_attribute(self):
+        event_id = "123456.zh.search"
+        attribute = "中文标签"
+        mock_embeddings = Mock()
+        mock_embeddings.search_thumbnail.return_value = [(event_id, 0.05)]
+
+        self.app.frigate_config.semantic_search.enabled = True
+        self.app.embeddings = mock_embeddings
+
+        with AuthTestClient(self.app) as client:
+            super().insert_mock_event(event_id, data={"custom_attr": attribute})
+
+            events = client.get(
+                "/events/search",
+                params={
+                    "search_type": "similarity",
+                    "event_id": event_id,
+                    "attributes": attribute,
+                },
+            ).json()
+            assert len(events) == 1
+            assert events[0]["id"] == event_id
+
+            events = client.get(
+                "/events/search",
+                params={
+                    "search_type": "similarity",
+                    "event_id": event_id,
+                    "attributes": "%E4%B8%AD%E6%96%87%E6%A0%87%E7%AD%BE",
+                },
+            ).json()
+            assert len(events) == 1
+            assert events[0]["id"] == event_id
+
     def test_get_good_event(self):
         id = "123456.random"