pyproject.toml

[build-system]
requires = ["setuptools>=61.0", "wheel"]
build-backend = "setuptools.build_meta"
[project]
name = "epubs-accessibility"
version = "2.0.0"
description = "Comprehensive toolkit for enhancing document accessibility"
authors = [{name = "Broderick Schipp", email = "schipp0@purdue.edu"}]
license = "MIT"
readme = "README.md"
requires-python = ">=3.9"
classifiers = [
    "Development Status :: 4 - Beta",
    "Environment :: Console",
    "Intended Audience :: Science/Research",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3.9",
    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Topic :: Scientific/Engineering :: Image Processing",
    "Topic :: Text Processing :: Markup :: XML",
    "Topic :: Multimedia :: Graphics :: Graphics Conversion",
]
# Core dependencies (always required)
dependencies = [
    # PDF Processing (Critical Path)
    "PyMuPDF>=1.23.0,<1.25.0",
    "pikepdf>=8.3.0,<9.0.0",
    "pdf2image>=1.16.3,<2.0.0",
    "pdfplumber>=0.7.0,<1.0.0",
    
    # OCR Processing (Critical for enhancement pipeline)
    "ocrmypdf>=16.0.0,<17.0.0",
    
    # Image Processing
    "Pillow>=10.0.0,<11.0.0",
    "opencv-python-headless>=4.8.0,<5.0.0",  # headless for better server compatibility
    "scikit-image>=0.21.0,<1.0.0",
    "numpy>=1.24.0,<2.0.0",
    
    # OCR
    "pytesseract>=0.3.10,<1.0.0",
    
    # Data Processing
    "pandas>=1.5.0,<3.0.0",
    "scipy>=1.7.0,<2.0.0",
    "tqdm>=4.66.0,<5.0.0",
    
    # Configuration and Environment
    "pyyaml>=6.0.0,<7.0.0",
    "python-decouple>=3.6,<4.0",
    
    # CLI and User Interface
    "typer>=0.12.0,<1.0.0",
    "rich>=13.0.0,<14.0.0",
    
    # Utilities
    "pathlib-mate>=1.0.0,<2.0.0",
    "python-magic>=0.4.27,<1.0.0",
    
    # Performance monitoring
    "psutil>=5.9.0,<6.0.0",
]
[project.optional-dependencies]
# Document format support
docs = [
    "python-docx>=1.0.0,<2.0.0",
    "python-pptx>=0.6.21,<1.0.0",
    "openpyxl>=3.0.7,<4.0.0",
    "python-xmp-toolkit>=2.0.2,<3.0.0",
    "reportlab>=4.0.0,<5.0.0",  # For test PDF generation
]
# Machine Learning and AI features (Heavy dependencies)
ml = [
    "torch>=2.0.0,<3.0.0",
    "transformers>=4.49.0,<5.0.0",
    "huggingface-hub>=0.20.0,<1.0.0",
    "anthropic>=0.18.0,<1.0.0",
    "scikit-learn>=1.3.0,<2.0.0",
    "joblib>=1.3.0,<2.0.0",
    "numpy>=1.24.0,<2.0.0",
    "scipy>=1.7.0,<2.0.0",
    # Phase 2B: Advanced Caching & ML Optimization
    "faiss-cpu>=1.7.4,<2.0.0",  # High-performance similarity search
]
# Apple Silicon optimizations
apple = [
    "mlx-vlm>=0.0.3,<1.0.0",
]
# Web scraping capabilities
web = [
    "selenium>=4.0.0,<5.0.0",
    "requests>=2.28.0,<3.0.0",
    "beautifulsoup4>=4.11.0,<5.0.0",
    "urllib3>=1.26.0,<3.0.0",
]
# Development dependencies
dev = [
    "pytest>=7.0.0,<8.0.0",
    "pytest-cov>=4.0.0,<5.0.0",
    "pytest-mock>=3.10.0,<4.0.0",
    "pytest-xdist>=3.0.0,<4.0.0",
    "black>=23.0.0,<24.0.0",
    "isort>=5.12.0,<6.0.0",
    "flake8>=6.0.0,<7.0.0",
    "mypy>=1.0.0,<2.0.0",
    "pre-commit>=3.0.0,<4.0.0",
    "coverage>=7.0.0,<8.0.0",
    "bandit>=1.7.0,<2.0.0",  # Security linting
    "safety>=2.3.0,<3.0.0",  # Dependency vulnerability scanning
]
# Testing dependencies (lighter than dev)
test = [
    "pytest>=7.0.0,<8.0.0",
    "pytest-cov>=4.0.0,<5.0.0",
    "pytest-mock>=3.10.0,<4.0.0",
    "pytest-xdist>=3.0.0,<4.0.0",
    "hypothesis>=6.0.0,<7.0.0",    # Property-based testing
    "factory-boy>=3.2.0,<4.0.0",  # Test fixtures
    "reportlab>=4.0.0,<5.0.0",    # For test PDF generation
]
# All optional dependencies combined (for convenience)
all = [
    "python-docx>=1.0.0,<2.0.0",
    "python-pptx>=0.6.21,<1.0.0",
    "openpyxl>=3.0.7,<4.0.0",
    "python-xmp-toolkit>=2.0.2,<3.0.0",
    "selenium>=4.0.0,<5.0.0",
    "requests>=2.28.0,<3.0.0",
    "beautifulsoup4>=4.11.0,<5.0.0",
    "reportlab>=4.0.0,<5.0.0",
]
[project.scripts]
# Simplified CLI entry point (Stage 2 & 3 complete)
epubs = "src.processor.main_simple:app"
# Scraper CLI (functional component)
epubs-scrape = "src.scraper.purdue_downloader:main"
[project.urls]
Homepage = "https://github.com/schipp0/ePubs_Main"
Repository = "https://github.com/schipp0/ePubs_Main"
Documentation = "https://epubs-accessibility.readthedocs.io"
"Bug Tracker" = "https://github.com/schipp0/ePubs_Main/issues"
[tool.setuptools.packages.find]
# All code now lives in src/ directory
where = ["src"]
exclude = ["venv*", "test_venv*", "build*", "dist*", "*.egg-info*", "temp_processing*", "logs*", "archive*"]
[tool.setuptools.package-data]
"*" = [
    "config/*.yaml", 
    "config/**/*.yaml",
    "resources/*",
    "resources/**/*",
    "*.md",
    "*.txt",
]
# Testing configuration
[tool.pytest.ini_options]
minversion = "7.0"
addopts = [
    "-ra",
    "-q", 
    "--strict-markers",
    "--strict-config",
    "--cov=src.processor",
    "--cov=src.scraper",
    "--cov-report=term-missing",
    "--cov-report=html:htmlcov",
    "--cov-report=xml",
    "--junit-xml=test-results.xml",
]
testpaths = ["tests"]
python_files = ["test_*.py", "*_test.py"]
python_classes = ["Test*"]
python_functions = ["test_*"]
markers = [
    "slow: marks tests as slow (deselect with '-m \"not slow\"')",
    "integration: marks tests as integration tests",
    "unit: marks tests as unit tests",
    "ocr: marks tests that require OCR engine",
    "gpu: marks tests that require GPU",
    "macos: marks tests as macOS specific",
    "windows: marks tests as Windows specific",
    "linux: marks tests as Linux specific",
]
# Code formatting with Black
[tool.black]
line-length = 88
target-version = ['py39', 'py310', 'py311', 'py312']
include = '\.pyi?$'
extend-exclude = '''
/(
  # directories
  \.eggs
  | \.git
  | \.hg
  | \.mypy_cache
  | \.tox
  | \.venv
  | venv
  | _build
  | buck-out
  | build
  | dist
  | archived
)/
'''
# Import sorting with isort
[tool.isort]
profile = "black"
multi_line_output = 3
line_length = 88
known_first_party = ["src"]
known_third_party = [
    "numpy", "pandas", "PIL", "cv2", "pytesseract", 
    "pikepdf", "fitz", "yaml", "click", "rich"
]
sections = ["FUTURE", "STDLIB", "THIRDPARTY", "FIRSTPARTY", "LOCALFOLDER"]
# Type checking with mypy
[tool.mypy]
python_version = "3.9"
warn_return_any = true
warn_unused_configs = true
warn_redundant_casts = true
warn_unused_ignores = true
disallow_any_generics = true
disallow_subclassing_any = true
disallow_untyped_calls = true
disallow_untyped_defs = true
disallow_incomplete_defs = true
check_untyped_defs = true
disallow_untyped_decorators = true
no_implicit_optional = true
warn_no_return = true
warn_unreachable = true
strict_equality = true
[[tool.mypy.overrides]]
module = [
    "cv2.*",
    "pytesseract.*",
    "fitz.*",
    "pikepdf.*",
    "pdf2image.*",
    "mlx_vlm.*",
]
ignore_missing_imports = true
# Coverage configuration
[tool.coverage.run]
source = ["src/processor", "src/scraper"]
omit = [
    "*/tests/*",
    "*/test_*",
    "*/conftest.py",
    "*/venv/*",
    "*/build/*",
    "*/dist/*",
    "*/temp_processing/*",
    "*/logs/*",
    "*/archive/*",
]
[tool.coverage.report]
exclude_lines = [
    "pragma: no cover",
    "def __repr__",
    "if self.debug:",
    "if settings.DEBUG",
    "raise AssertionError",
    "raise NotImplementedError",
    "if 0:",
    "if __name__ == .__main__.:",
    "class .*\\bProtocol\\):",
    "@(abc\\.)?abstractmethod",
]
show_missing = true
skip_covered = false
# Flake8 configuration
[tool.flake8]
max-line-length = 88
extend-ignore = [
    "E203",  # whitespace before ':'
    "E501",  # line too long (handled by black)
    "W503",  # line break before binary operator
]
exclude = [
    ".git",
    "__pycache__",
    "build",
    "dist",
    ".venv",
    "venv",
    ".eggs",
    "*.egg",
    "archived",
]
max-complexity = 10
# Security scanning with bandit