pyproject.toml

[build-system]
requires = ["uv_build>=0.12.5,<0.13"]
build-backend = "uv_build"

[project]
name = "ethnicolr2"
version = "0.3.3"
description = "Predict Race/Ethnicity Based on Sequence of Characters in the Name"
readme = "README.md"
authors = [
  { name = "Rajshekar", email = "rajshekar.ch@gmail.com" },
  { name = "Suriyan", email = "suriyant@gmail.com" },
  { name = "Gaurav Sood", email = "gsood07@gmail.com" }
]
license = "MIT"
license-files = ["LICENSE"]
classifiers = [
    "Development Status :: 4 - Beta",
    "Intended Audience :: Science/Research",
    "Intended Audience :: Developers",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3.12",
    "Programming Language :: Python :: 3.13",
    "Programming Language :: Python :: 3.14",
    "Topic :: Scientific/Engineering :: Information Analysis",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
    "Topic :: Software Development :: Libraries :: Python Modules",
    "Topic :: Text Processing :: Linguistic",
    "Operating System :: OS Independent",
]
keywords = ["race", "ethnicity", "names", "demographics", "machine-learning", "census", "pytorch", "lstm"]
requires-python = ">=3.12"
dependencies = [
    "click>=8.0.0",
    "pandas>=1.3.0",
    "torch==2.13.0",
    "joblib==1.6.0",
    "tqdm==4.70.0",
    "scikit-learn==1.9.0",
    "huggingface-hub>=1.27.0",
    "pyarrow>=14.0.0",
]

[project.urls]
"Homepage" = "https://appeler.github.io/ethnicolr2/"
"Documentation" = "https://appeler.github.io/ethnicolr2/"
"Repository" = "https://github.com/appeler/ethnicolr2"
"Bug Tracker" = "https://github.com/appeler/ethnicolr2/issues"
"Changelog" = "https://github.com/appeler/ethnicolr2/blob/main/CHANGELOG.md"
"Model" = "https://huggingface.co/gojiberries/ethnicolr2"

[dependency-groups]
dev = ["ruff>=0.7.0", "pre-commit>=3.0.0", "pydoclint", "pyright", "pandas-stubs", "types-tqdm"]
test = ["coverage", "pytest", "pytest-cov>=6", "numpy>=1.25.2"]
docs = [
    "sphinx",
    "furo",
    "sphinx-autodoc-typehints",
    "myst-parser",
    "linkify-it-py",
    "sphinx-design",
]

[project.scripts]
census_ln = "ethnicolr2.census_ln:main"
pred_fl_full_name = "ethnicolr2.pred_fl_fn_lstm:main"
pred_fl_last_name = "ethnicolr2.pred_fl_ln_lstm:main"
pred_census_last_name = "ethnicolr2.pred_cen_ln_lstm:main"
ethnicolr2_download_models = "ethnicolr2._setup_hooks:download_cli"


# Testing configuration
[tool.pytest.ini_options]
testpaths = ["tests"]
python_files = "test_*.py"
addopts = "--verbose"
markers = ["live: reaches the Hugging Face Hub"]

# Code quality and formatting tools

[tool.ruff]
line-length = 88
target-version = "py312"
exclude = [
    ".git",
    "__pycache__",
    "build",
    "dist",
    ".venv",
    "docs/source/examples"
]

[tool.ruff.lint]
select = [
    "E",   # pycodestyle errors
    "W",   # pycodestyle warnings
    "F",   # pyflakes
    "I",   # isort
    "B",   # flake8-bugbear
    "C4",  # flake8-comprehensions
    "UP",  # pyupgrade
]
ignore = [
    "E501",  # line too long (handled by formatter)
    "B008",  # do not perform function calls in argument defaults
]

[tool.ruff.lint.per-file-ignores]
"__init__.py" = ["F401"]
"tests/*" = ["S101"]

[tool.uv.build-backend]
module-name = "ethnicolr2"
module-root = "src"

# Type checking configuration
[tool.pyright]
include = ["src/ethnicolr2"]
exclude = ["**/node_modules", "**/__pycache__", ".venv", "venv", "build", "dist"]
strict = ["src/ethnicolr2"]
reportMissingTypeStubs = false
reportUnknownMemberType = false  # For external libraries without stubs
reportUnknownVariableType = false  # For pandas/torch operations
reportUnknownParameterType = false  # For external library parameters
reportUnknownArgumentType = false  # For external library arguments
pythonVersion = "3.12"
pythonPlatform = "All"

# Docstring linting configuration
[tool.pydoclint]
style = "google"
exclude = ["tests/", ".venv/", "venv/", "docs/source/examples/"]
arg-type-hints-in-signature = true
arg-type-hints-in-docstring = false
skip-checking-short-docstrings = false

# Dependency analysis configuration
[tool.deptry]
# Exclude documentation examples, virtual environment, and test files that use numpy
exclude = ["docs/source/examples/", ".venv/", "venv/", "tests/test_input_edge_cases.py", "tests/test_validation.py"]

# Package name mappings for packages with different import vs install names
[tool.deptry.package_module_name_map]
"linkify-it-py" = ["linkify_it_py"]

# Known external dependencies for documentation examples (not part of the main package)
[tool.deptry.per_rule_ignores]
DEP001 = ["docs/source/examples/"]  # Allow missing dependencies in documentation examples
DEP002 = ["scikit-learn"]  # scikit-learn is needed for model compatibility (joblib files)
DEP003 = ["docs/source/examples/"]  # Allow transitive dependencies in documentation examples
DEP004 = ["tests/test_input_edge_cases.py", "tests/test_validation.py"]  # Allow test dependencies in test files

[tool.codespell]
# The census tables are surnames, not prose. codespell reported 1,800 findings
# here, essentially all of them real names it mistook for misspellings, which
# drowned the handful of genuine typos in the source. Auto-"correcting" a name
# would also silently corrupt the data these models are trained on.
skip = "*.csv,*.parquet,*.joblib,./src/ethnicolr2/data,./docs/build,./.venv,uv.lock"

[tool.preen]
link_ignore = [
    # Alive, but not from a GitHub runner. Both surname tables answer 200 from
    # a workstation; from Actions egress the request fails, and it has been
    # failing CI on main since 2026-08-24 for a page that has not moved. The
    # README that cites them is the right place for those citations.
    "census\\.gov/topics/population/genealogy/",
]