fix: file pipeline status reporting and websocket updates (#589)

* feat: use file pipeline for upload and reprocess action

* fix: make file pipeline correctly report status events

* fix: duplication of transcripts_controller

* fix: tests

* test: fix file upload test

* test: fix reprocess

* fix: also patch from main_file_pipeline

(how patch is done is dependent of file import unfortunately)

server/tests/conftest.py

@@ -178,6 +178,63 @@ async def dummy_diarization():
         yield
 
 
+@pytest.fixture
+async def dummy_file_transcript():
+    from reflector.processors.file_transcript import FileTranscriptProcessor
+    from reflector.processors.types import Transcript, Word
+
+    class TestFileTranscriptProcessor(FileTranscriptProcessor):
+        async def _transcript(self, data):
+            return Transcript(
+                text="Hello world. How are you today?",
+                words=[
+                    Word(start=0.0, end=0.5, text="Hello", speaker=0),
+                    Word(start=0.5, end=0.6, text=" ", speaker=0),
+                    Word(start=0.6, end=1.0, text="world", speaker=0),
+                    Word(start=1.0, end=1.1, text=".", speaker=0),
+                    Word(start=1.1, end=1.2, text=" ", speaker=0),
+                    Word(start=1.2, end=1.5, text="How", speaker=0),
+                    Word(start=1.5, end=1.6, text=" ", speaker=0),
+                    Word(start=1.6, end=1.8, text="are", speaker=0),
+                    Word(start=1.8, end=1.9, text=" ", speaker=0),
+                    Word(start=1.9, end=2.1, text="you", speaker=0),
+                    Word(start=2.1, end=2.2, text=" ", speaker=0),
+                    Word(start=2.2, end=2.5, text="today", speaker=0),
+                    Word(start=2.5, end=2.6, text="?", speaker=0),
+                ],
+            )
+
+    with patch(
+        "reflector.processors.file_transcript_auto.FileTranscriptAutoProcessor.__new__"
+    ) as mock_auto:
+        mock_auto.return_value = TestFileTranscriptProcessor()
+        yield
+
+
+@pytest.fixture
+async def dummy_file_diarization():
+    from reflector.processors.file_diarization import (
+        FileDiarizationOutput,
+        FileDiarizationProcessor,
+    )
+    from reflector.processors.types import DiarizationSegment
+
+    class TestFileDiarizationProcessor(FileDiarizationProcessor):
+        async def _diarize(self, data):
+            return FileDiarizationOutput(
+                diarization=[
+                    DiarizationSegment(start=0.0, end=1.1, speaker=0),
+                    DiarizationSegment(start=1.2, end=2.6, speaker=1),
+                ]
+            )
+
+    with patch(
+        "reflector.processors.file_diarization_auto.FileDiarizationAutoProcessor.__new__"
+    ) as mock_auto:
+        mock_auto.return_value = TestFileDiarizationProcessor()
+        yield
+
+
 @pytest.fixture
 async def dummy_transcript_translator():
     from reflector.processors.transcript_translator import TranscriptTranslatorProcessor
@@ -238,9 +295,13 @@ async def dummy_storage():
     with (
         patch("reflector.storage.base.Storage.get_instance") as mock_storage,
         patch("reflector.storage.get_transcripts_storage") as mock_get_transcripts,
+        patch(
+            "reflector.pipelines.main_file_pipeline.get_transcripts_storage"
+        ) as mock_get_transcripts2,
     ):
         mock_storage.return_value = dummy
         mock_get_transcripts.return_value = dummy
+        mock_get_transcripts2.return_value = dummy
         yield
 
 
@@ -260,7 +321,10 @@ def celery_config():
 
 @pytest.fixture(scope="session")
 def celery_includes():
-    return ["reflector.pipelines.main_live_pipeline"]
+    return [
+        "reflector.pipelines.main_live_pipeline",
+        "reflector.pipelines.main_file_pipeline",
+    ]
 
 
 @pytest.fixture
@@ -302,7 +366,7 @@ async def fake_transcript_with_topics(tmpdir, client):
     transcript = await transcripts_controller.get_by_id(tid)
     assert transcript is not None
 
-    await transcripts_controller.update(transcript, {"status": "finished"})
+    await transcripts_controller.update(transcript, {"status": "ended"})
 
     # manually copy a file at the expected location
     audio_filename = transcript.audio_mp3_filename

server/tests/test_transcripts_audio_download.py

@@ -19,7 +19,7 @@ async def fake_transcript(tmpdir, client):
     transcript = await transcripts_controller.get_by_id(tid)
     assert transcript is not None
 
-    await transcripts_controller.update(transcript, {"status": "finished"})
+    await transcripts_controller.update(transcript, {"status": "ended"})
 
     # manually copy a file at the expected location
     audio_filename = transcript.audio_mp3_filename

server/tests/test_transcripts_process.py

@@ -29,10 +29,10 @@ async def client(app_lifespan):
 @pytest.mark.asyncio
 async def test_transcript_process(
     tmpdir,
-    whisper_transcript,
     dummy_llm,
     dummy_processors,
-    dummy_diarization,
+    dummy_file_transcript,
+    dummy_file_diarization,
     dummy_storage,
     client,
 ):
@@ -56,8 +56,8 @@ async def test_transcript_process(
     assert response.status_code == 200
     assert response.json()["status"] == "ok"
 
-    # wait for processing to finish (max 10 minutes)
-    timeout_seconds = 600  # 10 minutes
+    # wait for processing to finish (max 1 minute)
+    timeout_seconds = 60
     start_time = time.monotonic()
     while (time.monotonic() - start_time) < timeout_seconds:
         # fetch the transcript and check if it is ended
@@ -75,9 +75,10 @@ async def test_transcript_process(
     )
     assert response.status_code == 200
     assert response.json()["status"] == "ok"
+    await asyncio.sleep(2)
 
-    # wait for processing to finish (max 10 minutes)
-    timeout_seconds = 600  # 10 minutes
+    # wait for processing to finish (max 1 minute)
+    timeout_seconds = 60
     start_time = time.monotonic()
     while (time.monotonic() - start_time) < timeout_seconds:
         # fetch the transcript and check if it is ended
@@ -99,4 +100,4 @@ async def test_transcript_process(
     response = await client.get(f"/transcripts/{tid}/topics")
     assert response.status_code == 200
     assert len(response.json()) == 1
-    assert "want to share" in response.json()[0]["transcript"]
+    assert "Hello world. How are you today?" in response.json()[0]["transcript"]

server/tests/test_transcripts_upload.py

@@ -12,7 +12,8 @@ async def test_transcript_upload_file(
     tmpdir,
     dummy_llm,
     dummy_processors,
-    dummy_diarization,
+    dummy_file_transcript,
+    dummy_file_diarization,
     dummy_storage,
     client,
 ):
@@ -36,8 +37,8 @@ async def test_transcript_upload_file(
     assert response.status_code == 200
     assert response.json()["status"] == "ok"
 
-    # wait the processing to finish (max 10 minutes)
-    timeout_seconds = 600  # 10 minutes
+    # wait the processing to finish (max 1 minute)
+    timeout_seconds = 60
     start_time = time.monotonic()
     while (time.monotonic() - start_time) < timeout_seconds:
         # fetch the transcript and check if it is ended
@@ -47,7 +48,7 @@ async def test_transcript_upload_file(
             break
         await asyncio.sleep(1)
     else:
-        pytest.fail(f"Processing timed out after {timeout_seconds} seconds")
+        return pytest.fail(f"Processing timed out after {timeout_seconds} seconds")
 
     # check the transcript is ended
     transcript = resp.json()
@@ -59,4 +60,4 @@ async def test_transcript_upload_file(
     response = await client.get(f"/transcripts/{tid}/topics")
     assert response.status_code == 200
     assert len(response.json()) == 1
-    assert "want to share" in response.json()[0]["transcript"]
+    assert "Hello world. How are you today?" in response.json()[0]["transcript"]