pyproject.toml

[project]
name = "bicleaner-hardrules"
version = "2.10.6"
authors = [
    { name="Prompsit Language Engineering", email="info@prompsit.com" },
]
maintainers = [
    { name="Jaume Zaragoza", email="jzaragoza@prompsit.com" },
]
description = "Pre-filtering step for obvious noise based on rules, poor language based on general language modelling and vulgar language based on specific language modelling"
readme = "README.md"
requires-python = ">=3.8"
dependencies = [
    "regex",
    "PyYAML",
    "pytest",
    "toolwrapper>=1.0,<=3",
    "joblib",
    "sacremoses==0.0.53",
    "fasttext-wheel==0.9.2",
    "fastspell==0.11.1",
    "huggingface-hub>=0.15,<0.23",
]
classifiers = [
    "Environment :: Console",
    "Intended Audience :: Science/Research",
    "Programming Language :: Python :: 3.7",
    "Programming Language :: Python :: 3.8",
    "Programming Language :: Python :: 3.9",
    "Programming Language :: Python :: 3.10",
    "License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
    "Operating System :: POSIX :: Linux",
    "Topic :: Text Processing :: Linguistic",
    "Topic :: Software Development :: Libraries :: Python Modules",
    "Topic :: Text Processing :: Filters"
]

[build-system]
requires = [
    "setuptools>=45.0,<66",
    "cmake>=3.18",
    "scikit-build==0.16.6",
    "ninja",
]
build-backend = "setuptools.build_meta"

[project.scripts]
bicleaner-hardrules = "hardrules.bicleaner_hardrules:main"

[project.urls]
"HomePage" = "https://github.com/bitextor/bicleaner-hardrules"
"Prompsit Language Engineering" =  "http://www.prompsit.com"
"Paracrawl" = "https://paracrawl.eu/"
"MaCoCu" = "https://macocu.eu"
"HPLT Project" = "https://hplt-project.org"