From caaa1cd01a5ea597bd72af223248292b180e3392 Mon Sep 17 00:00:00 2001 From: Sleeps Date: Thu, 8 Oct 2026 10:31:24 +0100 Subject: [PATCH] Cover blended caption text and semantic search results --- tests/test_search_service.py | 93 ++++++++++++++++++++++++++++++++++++ 1 file changed, 93 insertions(+) diff --git a/tests/test_search_service.py b/tests/test_search_service.py index 54a4786..9879b80 100644 --- a/tests/test_search_service.py +++ b/tests/test_search_service.py @@ -92,6 +92,7 @@ class SearchServiceTests(unittest.TestCase): ) service._embedder = FakeEmbedder() # type: ignore[assignment] service.meili = Mock() + service.meili.search_caption_text.return_value = {"hits": []} service.meili.search_vector.return_value = { "hits": [ { @@ -252,6 +253,7 @@ class SearchServiceTests(unittest.TestCase): ) service._embedder = FakeEmbedder() # type: ignore[assignment] service.meili = Mock() + service.meili.search_caption_text.return_value = {"hits": []} service.meili.search_vector.side_effect = [ {"hits": first_hits}, {"hits": expanded_hits}, @@ -276,6 +278,97 @@ class SearchServiceTests(unittest.TestCase): SearchService.SCENES_PER_ITEM, ) + + def test_exact_caption_matches_are_reserved_without_losing_semantic_hits(self) -> None: + with tempfile.TemporaryDirectory() as tmp: + db_path = Path(tmp) / "scenes.sqlite3" + init_db(db_path) + with connect(db_path) as con: + for number in range(1, 4): + con.execute( + """ + INSERT INTO media ( + id, source_path, title, content_sha256, + size_bytes, mtime_ns, interval_ms, model_id, + embedding_dim, source_kind, jellyfin_item_id, + jellyfin_library_id, jellyfin_item_type + ) + VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?) + """, + ( + f"media-{number}", f"/media/movie-{number}.mkv", + f"Movie {number}", f"hash-{number}", 1, 0, + 10000, "model", 2, "jellyfin", + f"jf-{number}", "lib-1", "Movie", + ), + ) + con.execute( + """ + INSERT INTO frames ( + id, media_id, frame_number, timestamp_ms, + thumb_path, embedding_f16 + ) VALUES (?, ?, ?, ?, ?, ?) + """, + ( + f"frame-{number}", f"media-{number}", + 0, 0, f"/tmp/frame-{number}.jpg", + pack_vector(np.asarray([1.0, 0.0], dtype=np.float32)), + ), + ) + + def hit(number: int, *, caption: str | None = None) -> dict: + return { + "id": f"frame-{number}", + "jellyfin_item_id": f"jf-{number}", + "jellyfin_item_type": "Movie", + "title": f"Movie {number}", + "caption": caption, + "_rankingScore": 0.7, + } + + service = SearchService( + db_path=db_path, + meili_url="http://meili.test", + meili_master_key="key", + meili_index="scenes", + model_id="model", + device="cpu", + semantic_ratio=0.8, + ) + service._embedder = FakeEmbedder() # type: ignore[assignment] + service.meili = Mock() + service.meili.search_vector.return_value = { + "hits": [hit(1), hit(2), hit(3)], + } + service.meili.search_caption_text.return_value = { + "hits": [ + hit(3, caption="A red umbrella in the rain"), + hit(2, caption="A red umbrella by the street"), + hit(1, caption="A red umbrella on a table"), + ], + } + + result = service.search( + "red umbrella", scene_limit=3, item_limit=3, + ) + + self.assertEqual(result["caption_text_item_count"], 2) + self.assertEqual(result["item_count"], 3) + self.assertEqual( + [item["jellyfin_item_id"] for item in result["items"]], + ["jf-3", "jf-2", "jf-1"], + ) + self.assertEqual( + [item["caption_text_match"] for item in result["items"]], + [True, True, False], + ) + self.assertEqual(result["candidate_scene_count"], 3) + service.meili.search_caption_text.assert_called_once_with( + "red umbrella", + 20, + filter_expression='source_kind = "jellyfin"', + ) + def test_health_does_not_load_embedding_model(self) -> None: with tempfile.TemporaryDirectory() as tmp: db_path = Path(tmp) / "scenes.sqlite3"