190 lines
3.5 KiB
TOML
190 lines
3.5 KiB
TOML
[build-system]
|
|
requires = ["setuptools>=68", "wheel"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
|
|
[project]
|
|
name = "omniread"
|
|
version = "0.0.1"
|
|
description = "Composable content ingestion framework with pluggable scrapers and parsers for HTML, PDF, and structured data"
|
|
readme = "README.md"
|
|
requires-python = ">=3.10"
|
|
license = { text = "MIT" }
|
|
|
|
authors = [
|
|
{ name = "Aetos Skia", email = "dev@aetoskia.com" }
|
|
]
|
|
maintainers = [
|
|
{ name = "Aetos Skia", email = "dev@aetoskia.com" }
|
|
]
|
|
|
|
|
|
keywords = [
|
|
"scraping",
|
|
"parsing",
|
|
"content-ingestion",
|
|
"html",
|
|
"pdf",
|
|
"document-processing",
|
|
"pipeline",
|
|
"typed",
|
|
]
|
|
|
|
classifiers = [
|
|
"Development Status :: 3 - Alpha",
|
|
"Intended Audience :: Developers",
|
|
"License :: OSI Approved :: MIT License",
|
|
"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 :: Software Development :: Libraries :: Python Modules",
|
|
"Topic :: Internet :: WWW/HTTP",
|
|
"Topic :: Text Processing",
|
|
"Typing :: Typed",
|
|
]
|
|
|
|
|
|
dependencies = [
|
|
"requests>=2.31.0",
|
|
"beautifulsoup4>=4.12.0",
|
|
"pypdf>=4.0.0",
|
|
"openpyxl>=3.1.0",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
dev = [
|
|
"pytest>=8.0.0",
|
|
"pytest-asyncio>=0.21.0",
|
|
"pytest-cov>=4.1.0",
|
|
"black>=23.0.0",
|
|
"ruff>=0.3.0",
|
|
"mypy>=1.8.0",
|
|
"build>=1.0.0",
|
|
"twine>=4.0.0",
|
|
"pre-commit>=3.4.0",
|
|
"doc-forge[mcp,mkdocs]>=0.0.6",
|
|
]
|
|
|
|
docs = [
|
|
"mkdocs>=1.5.0",
|
|
"mkdocs-material>=9.5.0",
|
|
"mkdocstrings[python]>=0.24.0",
|
|
]
|
|
|
|
all = [
|
|
"omniread[dev,docs]",
|
|
]
|
|
|
|
|
|
[project.urls]
|
|
Homepage = "https://git.aetoskia.com/aetos/omniread"
|
|
Documentation = "https://git.aetoskia.com/aetos/omniread#readme"
|
|
Repository = "https://git.aetoskia.com/aetos/omniread.git"
|
|
Issues = "https://git.aetoskia.com/aetos/omniread/issues"
|
|
Versions = "https://git.aetoskia.com/aetos/omniread/tags"
|
|
|
|
|
|
[tool.setuptools]
|
|
packages = { find = { include = ["omniread*"] } }
|
|
|
|
[tool.setuptools.package-data]
|
|
omniread = ['py.typed', '\.pyi?$']
|
|
|
|
|
|
[tool.pytest.ini_options]
|
|
testpaths = ["tests"]
|
|
asyncio_mode = "auto"
|
|
python_files = ["test_*.py"]
|
|
python_classes = ["Test*"]
|
|
python_functions = ["test_*"]
|
|
addopts = [
|
|
"--strict-markers",
|
|
"--strict-config",
|
|
"--cov=omniread",
|
|
"--cov-report=term-missing",
|
|
"--cov-report=html",
|
|
"--cov-report=xml",
|
|
]
|
|
|
|
|
|
[tool.black]
|
|
line-length = 88
|
|
target-version = ["py310", "py311", "py312", "py313"]
|
|
include = '\.pyi?$'
|
|
extend-exclude = '''
|
|
/(
|
|
\.eggs
|
|
| \.git
|
|
| \.hg
|
|
| \.mypy_cache
|
|
| \.tox
|
|
| \.venv
|
|
| build
|
|
| dist
|
|
)/
|
|
'''
|
|
|
|
|
|
[tool.ruff]
|
|
line-length = 88
|
|
target-version = "py310"
|
|
|
|
[tool.ruff.lint]
|
|
select = [
|
|
"E",
|
|
"W",
|
|
"F",
|
|
"I",
|
|
"B",
|
|
"C4",
|
|
"UP",
|
|
]
|
|
ignore = [
|
|
"E501",
|
|
"B008",
|
|
"C901",
|
|
]
|
|
|
|
[tool.ruff.lint.per-file-ignores]
|
|
"__init__.py" = ["F401", "I001"]
|
|
"tests/*" = ["B008"]
|
|
|
|
|
|
[tool.mypy]
|
|
python_version = "3.10"
|
|
strict = true
|
|
exclude = [
|
|
"tests/",
|
|
]
|
|
files = ["omniread"]
|
|
|
|
[[tool.mypy.overrides]]
|
|
module = [
|
|
"requests.*",
|
|
"bs4.*",
|
|
"lxml.*",
|
|
"pypdf.*",
|
|
"openpyxl.*",
|
|
]
|
|
ignore_missing_imports = true
|
|
|
|
|
|
[tool.coverage.run]
|
|
source = ["omniread"]
|
|
omit = [
|
|
"*/tests/*",
|
|
"*/test_*.py",
|
|
]
|
|
|
|
[tool.coverage.report]
|
|
exclude_lines = [
|
|
"pragma: no cover",
|
|
"def __repr__",
|
|
"if __name__ == .__main__.:",
|
|
"raise AssertionError",
|
|
"raise NotImplementedError",
|
|
"if TYPE_CHECKING:",
|
|
"@abstractmethod",
|
|
] |