Features

.github/workflows/ci.yml

@@ -5,21 +5,33 @@ on:
   pull_request:
 
 jobs:
-  build:
+  test:
     runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.10", "3.11"]
 
     steps:
       - uses: actions/checkout@v4
 
-      - uses: actions/setup-python@v5
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
         with:
-          python-version: "3.11"
+          python-version: ${{ matrix.python-version }}
+          cache: 'pip'
 
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
           pip install -r requirements.txt
 
-      - name: Check syntax
+      - name: Lint with flake8
         run: |
-          python -m compileall .
+          # Stop the build if there are Python syntax errors or undefined names
+          flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+          # exit-zero treats all errors as warnings
+          flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+
+      - name: Test with pytest
+        run: |
+          pytest tests/ --cov=src --cov-report=xml

.gitignore

@@ -47,6 +47,7 @@ data/
 *.wav
 *.m4a
 *.webm
+*.ogg
 
 # ======================
 # Logs
@@ -76,3 +77,4 @@ Thumbs.db
 .coverage
 htmlcov/
 .pytest_cache/
+coverage.xml

app/app.py

@@ -1,5 +1,8 @@
-import streamlit as st
+import sys
 import os
+sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
+
+import streamlit as st
 from src.ingestion.youtube import fetch_youtube_transcript, download_audio, get_video_info
 from src.ingestion.transcribe import transcribe_audio
 from src.processing.summarize import summarize_text

pytest.ini

@@ -0,0 +1,2 @@
+[pytest]
+pythonpath = .

tests/test_chunking.py

@@ -0,0 +1,26 @@
+import pytest
+from src.processing.chunking import split_text
+
+def test_split_text_empty():
+    assert split_text("") == []
+    assert split_text("   ") == []
+
+def test_split_text_single_short_sentence():
+    text = "This is a short sentence."
+    chunks = split_text(text, max_words=10, overlap=2)
+    assert len(chunks) == 1
+    assert chunks[0] == text
+
+def test_split_text_multiple_sentences():
+    text = "Hello world. This is a test. We should split this well."
+    chunks = split_text(text, max_words=6, overlap=2)
+    assert len(chunks) >= 2
+    # Ensure all words are present across chunks roughly
+
+def test_split_text_long_sentence_fallback():
+    # Sentence without punctuation longer than max_words
+    text = "this is a very long sentence that has no punctuation and just keeps going on and on for many words without stopping so we need to fallback on word splitting"
+    chunks = split_text(text, max_words=10, overlap=2)
+    assert sum(len(c.split()) for c in chunks) >= len(text.split())
+    for chunk in chunks:
+        assert len(chunk.split()) <= 10

tests/test_ingestion.py

@@ -0,0 +1,35 @@
+import pytest
+from unittest.mock import patch, MagicMock
+from src.ingestion.youtube import fetch_youtube_transcript, get_video_info
+
+@patch('src.ingestion.youtube.yt_dlp.YoutubeDL')
+def test_get_video_info(mock_ytdl):
+    mock_instance = MagicMock()
+    mock_ytdl.return_value.__enter__.return_value = mock_instance
+    mock_instance.extract_info.return_value = {
+        'title': 'Test Video',
+        'duration': 120,
+        'channel': 'Test Channel',
+        'subtitles': {'en': {}},
+        'automatic_captions': {}
+    }
+
+    info = get_video_info('http://test.url')
+    assert info is not None
+    assert info['title'] == 'Test Video'
+    assert info['has_manual_subs'] == True
+    assert info['has_auto_subs'] == False
+
+@patch('src.ingestion.youtube.tempfile.TemporaryDirectory')
+@patch('src.ingestion.youtube.yt_dlp.YoutubeDL')
+def test_fetch_youtube_transcript_no_subs(mock_ytdl, mock_temp):
+    mock_instance = MagicMock()
+    mock_ytdl.return_value.__enter__.return_value = mock_instance
+    mock_instance.extract_info.return_value = {
+        'subtitles': {},
+        'automatic_captions': {}
+    }
+
+    transcript, source = fetch_youtube_transcript('http://test.url')
+    assert transcript is None
+    assert source is None