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

[project]
name = "sumy"
version = "0.12.0"
description = "Module for automatic summarization of text documents and HTML pages."
readme = "README.md"
license = { text = "Apache License, Version 2.0" }
authors = [
    { name = "Mišo Belica", email = "miso.belica@gmail.com" }
]
requires-python = ">=3.8"
keywords = [
    "data mining",
    "automatic summarization",
    "data reduction",
    "web-data extraction",
    "NLP",
    "natural language processing",
    "latent semantic analysis",
    "LSA",
    "TextRank",
    "LexRank",
]
classifiers = [
    "Development Status :: 4 - Beta",
    "Intended Audience :: Developers",
    "Intended Audience :: Education",
    "License :: OSI Approved :: Apache Software License",
    "Natural Language :: Chinese (Simplified)",
    "Natural Language :: Czech",
    "Natural Language :: English",
    "Natural Language :: French",
    "Natural Language :: German",
    "Natural Language :: Hebrew",
    "Natural Language :: Italian",
    "Natural Language :: Japanese",
    "Natural Language :: Polish",
    "Natural Language :: Portuguese",
    "Natural Language :: Slovak",
    "Natural Language :: Spanish",
    "Natural Language :: Swedish",
    "Natural Language :: Ukrainian",
    "Natural Language :: Greek",
    "Natural Language :: Arabic",
    "Natural Language :: Thai",
    "Topic :: Education",
    "Topic :: Internet",
    "Topic :: Scientific/Engineering :: Information Analysis",
    "Topic :: Text Processing :: Filters",
    "Topic :: Text Processing :: Linguistic",
    "Topic :: Text Processing :: Markup :: HTML",
    "Operating System :: OS Independent",
    "Programming Language :: Python",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3.8",
    "Programming Language :: Python :: 3.9",
    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Programming Language :: Python :: 3.13",
    "Programming Language :: Python :: 3.14",
    "Programming Language :: Python :: Implementation :: CPython",
    "Programming Language :: Python :: Implementation :: PyPy",
]
dependencies = [
    "docopt-ng>=0.6.1",
    "breadability>=0.1.20",
    "lxml-html-clean",  # Required by breadability (lxml.html.clean was moved to separate package)
    "requests>=2.7.0",
    "pycountry>=18.2.23",
    "nltk>=3.0.2",
    "setuptools>=65.0.0",  # Required by breadability for pkg_resources
]

[project.optional-dependencies]
LSA = ["numpy"]
LexRank = ["numpy"]
Japanese = ["tinysegmenter"]
Chinese = ["jieba"]
Korean = ["konlpy"]
Hebrew = ["hebrew_tokenizer"]
Greek = ["greek-stemmer-pos"]
Arabic = ["pyarabic"]
Thai = ["pythainlp"]
Polish = ["pystempel"]

[dependency-groups]
dev = [
    "pytest>=3.0.0",
    "pytest-cov",
    "codecov",
    "invoke",
]

[project.scripts]
sumy = "sumy.__main__:main"
sumy_eval = "sumy.evaluation.__main__:main"

[project.urls]
Homepage = "https://github.com/miso-belica/sumy"
Repository = "https://github.com/miso-belica/sumy"

[tool.hatch.build.targets.wheel]
packages = ["sumy"]

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

[tool.bumpversion]
current_version = "0.12.0"
commit = false
tag = false

[[tool.bumpversion.files]]
filename = "pyproject.toml"
search = 'version = "{current_version}"'
replace = 'version = "{new_version}"'

[[tool.bumpversion.files]]
filename = "sumy/__init__.py"

[[tool.bumpversion.files]]
filename = "tasks.py"

[tool.isort]
multi_line_output = 5

[tool.ruff]
target-version = "py38"
line-length = 120

# Exclude a variety of commonly ignored directories.
exclude = [
    ".bzr",
    ".direnv",
    ".eggs",
    ".git",
    ".hg",
    ".mypy_cache",
    ".nox",
    ".pants.d",
    ".ruff_cache",
    ".svn",
    ".tox",
    ".venv",
    "__pypackages__",
    "_build",
    "buck-out",
    "build",
    "dist",
    "node_modules",
    "venv",
]

[tool.ruff.lint]
# Never enforce `E501` (line length violations).
ignore = ["E501"]

# Ignore `E402` (import violations) in all `__init__.py` files, and in `_compat.py`.
[tool.ruff.lint.per-file-ignores]
"__init__.py" = ["F401"]
"_compat.py" = ["F401"]

[tool.flake8]
ignore = ["S001", "D100"]
max-line-length = 160
inline-quotes = "double"
multiline-quotes = "double"
docstring-quotes = "double"