pyproject.toml

[tool.poetry]
name = "text-dedup"
version = "0.4.0"
description = ""
authors = ["Chenghao Mou <mouchenghao@gmail.com>"]
license = "Apache 2.0"
readme = "README.md"

[tool.poetry.dependencies]
python = "^3.10"
numpy = ">=1.26.4"
tqdm = ">=4.64.1"
datasets = ">=2.17.0"
scipy = ">=1.10.1"
xxhash = ">=3.0.0"
pybloom-live = ">=4.0.0"
bitarray = ">=2.6.2"
pyspark = ">=3.3.1"
regex = ">=2023.5.5"
urllib3 = "<=2.0"
sphinxcontrib-bibtex = ">=2.5.0"
zstandard = ">=0.21.0"
ftfy = ">=6.1.1"
setuptools = ">=69.1.0"
psutil = ">=5.9.8"
fire = "^0.6.0"
click = "^8.1.7"
click-option-group = "^0.5.6"
rich = "^13.7.1"
unisim = "^0.0.1"
tensorflow = "^2.16.1"

[tool.poetry.group.dev.dependencies]
pre-commit = "^3.6.2"
insegel = "^1.3.1"
pytest = "^8.0.2"
coverage = "^7.4.3"
ruff = "^0.3.2"
tabulate = "^0.9.0"
scikit-learn = "^1.4.1.post1"

[build-system]
requires = ["poetry-core"]
build-backend = "poetry.core.masonry.api"

[tool.ruff]
exclude = [
    ".bzr",
    ".direnv",
    ".eggs",
    ".git",
    ".git-rewrite",
    ".hg",
    ".ipynb_checkpoints",
    ".mypy_cache",
    ".nox",
    ".pants.d",
    ".pyenv",
    ".pytest_cache",
    ".pytype",
    ".ruff_cache",
    ".svn",
    ".tox",
    ".venv",
    ".vscode",
    "__pypackages__",
    "_build",
    "buck-out",
    "build",
    "dist",
    "node_modules",
    "site-packages",
    "venv",
]
line-length = 120
indent-width = 4
target-version = "py310"

[tool.ruff.lint]
# Enable Pyflakes (`F`) and a subset of the pycodestyle (`E`)  codes by default.
# Unlike Flake8, Ruff doesn't enable pycodestyle warnings (`W`) or
# McCabe complexity (`C901`) by default.
select = ["E4", "E7", "E9", "F", "I"]
ignore = []
fixable = ["ALL"]
unfixable = []

[tool.ruff.lint.isort]
force-single-line = true

[tool.ruff.format]
quote-style = "double"
indent-style = "space"
skip-magic-trailing-comma = false
line-ending = "auto"

[tool.coverage.run]
branch = true
omit = ["tests/*"]

[tool.coverage.report]
ignore_errors = true