pyproject.toml

[project]
name = "tokenlearn"
description = "Pre-train Static Embedders"
readme = "README.md"
requires-python = ">=3.9"
authors = [{name = "Thomas van Dongen", email = "thomas123@live.nl"}, { name = "Stéphan Tulkens", email = "stephantul@gmail.com"}]
dynamic = ["version"]

classifiers = [
    "Development Status :: 4 - Beta",
    "Intended Audience :: Developers",
    "Intended Audience :: Science/Research",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
    "Topic :: Software Development :: Libraries",
    "License :: OSI Approved :: MIT License",
    "Programming Language :: Python :: 3 :: Only",
    "Programming Language :: Python :: 3.9",
    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Natural Language :: English",
]

dependencies = [
    "model2vec[distill]>=0.3.0",
    "sentence-transformers",
    "torch",
    "datasets",
    "more-itertools>=10.5.0",
]

[build-system]
requires = ["setuptools>=64", "setuptools_scm>=8"]
build-backend = "setuptools.build_meta"

[project.optional-dependencies]
dev = [
    "black",
    "ipython",
    "mypy",
    "pre-commit",
    "pytest",
    "pytest-coverage",
    "ruff",
]

[project.urls]
"Homepage" = "https://github.com/MinishLab"
"Bug Reports" = "https://github.com/MinishLab/tokenlearn/issues"
"Source" = "https://github.com/MinishLab/tokenlearn"

[tool.ruff]
exclude = [".venv/"]
line-length = 120
target-version = "py310"

[tool.ruff.lint]
select = [
    # Annotations: Enforce type annotations
    "ANN",
    # Complexity: Enforce a maximum cyclomatic complexity
    "C90",
    # Pydocstyle: Enforce docstrings
    "D",
    # Isort: Enforce import order
    "I",
    # Numpy: Enforce numpy style
    "NPY",
    # Print: Forbid print statements
    "T20",
]
ignore = [
    # Allow self and cls to be untyped, and allow Any type
    "ANN101", "ANN102", "ANN401",
    # Pydocstyle ignores
    "D100", "D101", "D104", "D203", "D212", "D401",
    # Allow use of f-strings in logging
    "G004"
]

[tool.pydoclint]
style = "sphinx"
exclude = "test_"
allow-init-docstring = true
arg-type-hints-in-docstring = false
check-return-types = false
require-return-section-when-returning-nothing = false

[tool.mypy]
python_version = "3.10"
warn_unused_configs = true
ignore_missing_imports = true

[tool.setuptools]
packages = ["tokenlearn"]

[tool.setuptools_scm]
# can be empty if no extra settings are needed, presence enables setuptools_scm

[tool.setuptools.dynamic]
version = {attr = "tokenlearn.version.__version__"}