pyproject.toml

[project]
name = "verso"
version = "0.1.0"
description = "High-performance document extraction to markdown/json. Extract text, tables, images from PDFs with layout detection and structure preservation."
readme = "README.md"
requires-python = ">=3.10"
license = { text = "MIT" }
authors = [{ name = "verso contributors" }]
maintainers = [{ name = "verso contributors" }]
keywords = [
    "pdf",
    "markdown",
    "extraction",
    "ocr",
    "document",
    "layout",
    "mcp",
    "mlx",
    "text-extraction",
    "pdf-parser",
    "document-ai",
]
classifiers = [
    "Development Status :: 4 - Beta",
    "Intended Audience :: Developers",
    "Intended Audience :: Science/Research",
    "License :: OSI Approved :: MIT License",
    "Operating System :: OS Independent",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Programming Language :: Python :: 3.13",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
    "Topic :: Text Processing :: Markup :: Markdown",
    "Topic :: Software Development :: Libraries :: Python Modules",
    "Typing :: Typed",
]

dependencies = [
    "click>=8.0",
    "pillow>=9.0",
    "pymupdf>=1.24.0",
]

[project.optional-dependencies]
# alternative pdf backend (slower but more permissive license)
pdftext = [
    "pypdfium2>=4.0",
    "pdftext>=0.3.0",
]
# office document support
office = [
    "python-docx>=0.8",
    "python-pptx>=0.6",
    "openpyxl>=3.0",
]
# html/epub support
html = [
    "beautifulsoup4>=4.9",
    "markdownify>=0.11",
    "ebooklib>=0.18",
]
# ocr for scanned documents
ocr = [
    "surya-ocr>=0.4",
]
# layout detection models
layout = [
    "surya-ocr>=0.4",
]
# deep learning models
ml = [
    "torch>=2.0",
    "transformers>=4.30",
    "onnxruntime>=1.16",
]
# llm integration
llm = [
    "openai>=1.0",
]
# mcp server for claude desktop
mcp = [
    "mcp>=1.0",
]
# apple silicon optimization
mlx = [
    "mlx>=0.10",
    "mlx-vlm>=0.1",
]
# convenience bundles
apple = [
    "verso[mlx,mcp]",
]
cpu = [
    "verso[pdftext,office,html,ocr]",
]
full = [
    "verso[pdftext,office,html,ocr,layout,ml,llm,mcp]",
]
# development
dev = [
    "pytest>=7.0",
    "pytest-cov>=4.0",
    "pytest-asyncio>=0.21",
    "ruff>=0.4",
    "mypy>=1.0",
    "types-Pillow>=10.0",
    "pre-commit>=3.0",
]
# documentation
docs = [
    "mkdocs>=1.5",
    "mkdocs-material>=9.0",
    "mkdocstrings[python]>=0.24",
]

[project.scripts]
verso = "verso.cli:cli"
verso-mcp = "verso.mcp_server:main"

[project.urls]
Homepage = "https://github.com/example/verso"
Documentation = "https://github.com/example/verso#readme"
Repository = "https://github.com/example/verso"
Changelog = "https://github.com/example/verso/blob/main/CHANGELOG.md"
Issues = "https://github.com/example/verso/issues"

[build-system]
requires = ["hatchling>=1.21"]
build-backend = "hatchling.build"

[tool.hatch.version]
path = "src/verso/__init__.py"

[tool.hatch.build.targets.sdist]
include = [
    "/src",
    "/tests",
    "/README.md",
    "/CHANGELOG.md",
    "/LICENSE",
]

[tool.hatch.build.targets.wheel]
packages = ["src/verso"]

[tool.ruff]
line-length = 88
target-version = "py310"
src = ["src", "tests"]

[tool.ruff.lint]
select = [
    "E",      # pycodestyle errors
    "F",      # pyflakes
    "I",      # isort
    "W",      # pycodestyle warnings
    "UP",     # pyupgrade
    "B",      # flake8-bugbear
    "C4",     # flake8-comprehensions
    "SIM",    # flake8-simplify
]
ignore = [
    "E501",   # line too long (handled by formatter)
    "B008",   # function call in default argument
    "SIM108", # ternary instead of if-else
]

[tool.ruff.lint.isort]
known-first-party = ["verso"]

[tool.ruff.format]
quote-style = "double"
indent-style = "space"

[tool.mypy]
python_version = "3.10"
strict = true
warn_return_any = true
warn_unused_ignores = true
ignore_missing_imports = true
exclude = [
    "tests/",
    "research/",
]

[tool.pytest.ini_options]
testpaths = ["tests"]
python_files = ["test_*.py"]
python_functions = ["test_*"]
asyncio_mode = "auto"
addopts = [
    "-ra",
    "--strict-markers",
    "--strict-config",
]
markers = [
    "slow: marks tests as slow (deselect with '-m \"not slow\"')",
    "integration: marks tests as integration tests",
]
filterwarnings = [
    "ignore::DeprecationWarning",
    "ignore::PendingDeprecationWarning",
]

[tool.coverage.run]
source = ["src/verso"]
branch = true
omit = [
    "*/tests/*",
    "*/__pycache__/*",
]

[tool.coverage.report]
exclude_lines = [
    "pragma: no cover",
    "def __repr__",
    "raise NotImplementedError",
    "if TYPE_CHECKING:",
    "if __name__ == .__main__.:",
]