first commit

Author: jaesung-rode

.github/workflows/tests.yml

@@ -0,0 +1,128 @@
+name: Tests
+
+on:
+  push:
+    branches: [ main, develop ]
+  pull_request:
+    branches: [ main, develop ]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.8", "3.9", "3.10"]
+
+    steps:
+    - uses: actions/checkout@v3
+    
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v4
+      with:
+        python-version: ${{ matrix.python-version }}
+        
+    - name: Cache pip packages
+      uses: actions/cache@v3
+      with:
+        path: ~/.cache/pip
+        key: ${{ runner.os }}-pip-${{ hashFiles('requirements.txt') }}
+        restore-keys: |
+          ${{ runner.os }}-pip-
+          
+    - name: Install system dependencies
+      run: |
+        sudo apt-get update
+        sudo apt-get install -y ffmpeg
+        
+    - name: Install Python dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install -r requirements.txt
+        pip install pytest pytest-cov pytest-xdist
+        
+    - name: Run unit tests
+      run: |
+        pytest tests/unit -v --cov=pipeline --cov=utils --cov-report=xml --cov-report=term-missing
+        
+    - name: Run integration tests
+      run: |
+        pytest tests/integration -v -m "not slow"
+        
+    - name: Upload coverage reports
+      uses: codecov/codecov-action@v3
+      with:
+        file: ./coverage.xml
+        flags: unittests
+        name: codecov-umbrella
+        
+  lint:
+    runs-on: ubuntu-latest
+    
+    steps:
+    - uses: actions/checkout@v3
+    
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: "3.9"
+        
+    - name: Install linting tools
+      run: |
+        python -m pip install --upgrade pip
+        pip install flake8 black isort mypy
+        
+    - name: Run flake8
+      run: |
+        flake8 pipeline utils --max-line-length=100 --extend-ignore=E203,W503
+        
+    - name: Check black formatting
+      run: |
+        black --check pipeline utils tests
+        
+    - name: Check import sorting
+      run: |
+        isort --check-only pipeline utils tests
+        
+    - name: Run mypy type checking
+      run: |
+        mypy pipeline utils --ignore-missing-imports
+        
+  docs:
+    runs-on: ubuntu-latest
+    
+    steps:
+    - uses: actions/checkout@v3
+    
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: "3.9"
+        
+    - name: Install documentation tools
+      run: |
+        python -m pip install --upgrade pip
+        pip install sphinx sphinx-rtd-theme
+        
+    - name: Build documentation
+      run: |
+        cd docs || mkdir docs
+        echo "Documentation build would go here"
+        
+  security:
+    runs-on: ubuntu-latest
+    
+    steps:
+    - uses: actions/checkout@v3
+    
+    - name: Run Trivy vulnerability scanner
+      uses: aquasecurity/trivy-action@master
+      with:
+        scan-type: 'fs'
+        scan-ref: '.'
+        format: 'sarif'
+        output: 'trivy-results.sarif'
+        
+    - name: Upload Trivy scan results
+      uses: github/codeql-action/upload-sarif@v2
+      with:
+        sarif_file: 'trivy-results.sarif'

.gitignore

@@ -0,0 +1,174 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+Pipfile.lock
+
+# PEP 582
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# Project specific
+data/intermediate/
+data/temp/
+data/output/
+logs/
+*.pkl
+*.h5
+*.hdf5
+*.mp4
+*.wav
+*.avi
+*.mov
+*.pth
+*.pt
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Temporary files
+tmp/
+temp/
+*.tmp
+*.bak
+
+# Model weights (too large for git)
+models/
+weights/
+
+
+# Personal notes
+notes.txt
+TODO.txt
+
+# Credentials
+*.key
+*.pem
+config/secrets.yaml
+
+movie/
+1/
+exp/
+.claude/

Makefile

@@ -0,0 +1,83 @@
+# Makefile for Character-Aware Audiovisual Subtitle Pipeline
+
+.PHONY: help install test test-unit test-integration lint format clean docs run
+
+help:
+	@echo "Available commands:"
+	@echo "  make install          Install dependencies"
+	@echo "  make test            Run all tests"
+	@echo "  make test-unit       Run unit tests only"
+	@echo "  make test-integration Run integration tests only"
+	@echo "  make lint            Run linting checks"
+	@echo "  make format          Format code"
+	@echo "  make clean           Clean temporary files"
+	@echo "  make docs            Build documentation"
+	@echo "  make run             Run pipeline with default settings"
+
+install:
+	pip install -r requirements.txt
+	pip install -e .
+
+test:
+	pytest tests/ -v --cov=pipeline --cov=utils --cov-report=term-missing
+
+test-unit:
+	pytest tests/unit -v --cov=pipeline --cov=utils --cov-report=term-missing
+
+test-integration:
+	pytest tests/integration -v -m "not slow"
+
+test-slow:
+	pytest tests/ -v -m "slow"
+
+lint:
+	flake8 pipeline utils tests --max-line-length=100 --extend-ignore=E203,W503
+	mypy pipeline utils --ignore-missing-imports
+	black --check pipeline utils tests
+	isort --check-only pipeline utils tests
+
+format:
+	black pipeline utils tests
+	isort pipeline utils tests
+
+clean:
+	find . -type f -name "*.pyc" -delete
+	find . -type d -name "__pycache__" -delete
+	find . -type d -name "*.egg-info" -exec rm -rf {} +
+	rm -rf .coverage
+	rm -rf htmlcov
+	rm -rf .pytest_cache
+	rm -rf .mypy_cache
+	rm -rf data/intermediate/*
+	rm -rf data/temp/*
+
+docs:
+	@echo "Documentation generation not implemented yet"
+
+run:
+	python run_pipeline.py
+
+run-episode:
+	@echo "Usage: make run-episode EPISODE=Seinfeld_03x01"
+	python run_pipeline.py --episodes $(EPISODE)
+
+run-sequential:
+	python run_pipeline.py --sequential
+
+run-cleanup:
+	python run_pipeline.py --cleanup
+
+# Development helpers
+dev-setup:
+	pip install -r requirements.txt
+	pip install pytest pytest-cov pytest-xdist
+	pip install flake8 black isort mypy
+	pip install pre-commit
+	pre-commit install
+
+# Docker support (optional)
+docker-build:
+	docker build -t ca-subtitle-pipeline .
+
+docker-run:
+	docker run -v $(PWD)/data:/app/data ca-subtitle-pipeline