pyproject.toml

[build-system]
requires = ["setuptools", "wheel", "pybind11", "setuptools-rust"]
build-backend = "setuptools.build_meta"

[project]
name = "datumaro"
dynamic = ["version"]
description = "Dataset Management Framework (Datumaro)"
maintainers = [
    { name = "Intel Open Edge Platform" },
]
license-files = ["LICENSE"]
readme = "README.md"
requires-python = ">=3.10,<3.15"
classifiers = [
    "Programming Language :: Python :: 3",
    "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",
    "Operating System :: OS Independent",
]
dependencies = [
    "attrs>=25.3",  # attrs doesn't follow semantic versioning
    "cachetools~=7.0",
    "defusedxml~=0.7",
    "imagesize~=2.0",
    "json-stream~=2.4",
    "lxml~=6.0",
    "numpy~=2.2",
    "opencv-python-headless~=4.11",
    "orjson~=3.10",
    "pandas~=2.3",
    "pillow~=12.0",
    "pyarrow~=24.0",
    "pycocotools~=2.0",
    "PyYAML~=6.0",
    "ruamel.yaml~=0.19.1",
    "shapely~=2.1",
    "tqdm~=4.67",
    "typing_extensions~=4.15",
]

[project.scripts]
datum = "datumaro.cli.__main__:main"

[project.urls]
Homepage = "https://github.com/open-edge-platform/datumaro"

[project.optional-dependencies]
dev = [
    "ruff",
    "prek"
]

test = [
    "pytest>=5.3.5",
    "pytest-cov>=4.0.0",
    "pytest-stress",
    "pytest-html",
    "coverage",
    "pytest-csv",
    "dill",
    "tifffile",
]

docs = [
    "markupsafe==3.0.3",
    "nbconvert>=7.2.3",
    "ipython==8.39.0",
    "sphinx==7.4.7",
    "pydata-sphinx-theme==0.17.1",
    "sphinx-copybutton",
    "sphinx-autoapi",
    "myst-parser",
    "nbsphinx",
    "jupyter",
    "jupytext",
    "pandoc",
    "sphinx-design",
    "sphinx-toolbox",
]

# Tensorflow support
# Exclude Tensorflow from Python 3.13 as it is not supported yet
# Also exclude TensorFlow from the MacOS checks due to the following issue:
# https://github.com/tensorflow/tensorflow/issues/98563
tf = [
    "tensorflow; python_version < '3.13' and sys_platform != 'darwin'",
]
# TODO: Reenable tfds
#tfds = [
#    "tensorflow-datasets; python_version < '3.13' and sys_platform != 'darwin'",
#    "absl-py>=0.12.0; python_version < '3.13' and sys_platform != 'darwin'",
#]

# PyTorch support
torch = ["torch>=2.9", "torchvision>=0.24"]

# Kaggle download support
kaggle = ["kaggle"]

# NDR, mpii file format, missing value detection in tabular data
scipy = ["scipy"]

# Tabular data processing
nlp = ["nltk", "tokenizers", "portalocker"]

# Comparator
tabulate = ["tabulate"]

# Any dependencies needed by the CLI
# 2.3 has an unlisted dependency on PyTorch, which we don't need
cli = ["tensorboardX>=1.8,!=2.3", "tabulate", "scipy", "matplotlib>=3.3.1"]

# Visualizer
visualizer = ["matplotlib>=3.3.1"]

# NYU Depth Dataset v2 file format
h5py = ["h5py>=3.15.0"]

# BraTS file format
nibabel = ["nibabel>=3.2.1"]

# AVA dataset
protobuf = ["protobuf"]

experimental = ["polars~=1.35"]

[tool.setuptools]
package-dir = {"" = "src"}
include-package-data = true
zip-safe = false

[tool.setuptools.packages.find]
where = ["src"]
include = ["datumaro*"]

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

[tool.pybind11.ext_modules]
"datumaro._capi" = { sources = ["src/datumaro/capi/pybind.cpp"], extra_compile_args = ["-O3"] }

[[tool.setuptools-rust.ext-modules]]
target = "datumaro.rust_api"
path = "rust/Cargo.toml"
binding = "PyO3"

[tool.coverage.run]
branch = true

source = [
    "src/",
]

omit = [
    "src/datumaro/__main__.py",
    "src/datumaro/version.py",
    "tests/*",
]

[tool.cibuildwheel]
# reference docs - https://cibuildwheel.readthedocs.io/en/stable/options/#build-skip
build = "cp310-*_x86_64 cp311-*_x86_64 cp312-*_x86_64 cp313-*_x86_64 cp310-*_amd64 cp311-*_amd64 cp312-*_amd64 cp313-*_amd64 cp310-*_arm64 cp311-*_arm64 cp312-*_arm64 cp313-*_arm64"

[tool.cibuildwheel.linux]
before-all = [
    "curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs -o rustup-init.sh",
    "sh ./rustup-init.sh -y --default-toolchain stable --profile minimal"
]

environment = { PATH="$HOME/.cargo/bin:$PATH" }

[tool.coverage.report]
# Regexes for lines to exclude from consideration
exclude_lines = [
    # Have to re-enable the standard pragma
    'pragma: no cover',

    # Don't complain about missing debug-only code:
    'def __repr__',
    'if\s+[\w\.()]+\.isEnabledFor\(log\.DEBUG\):',

    # Don't complain if tests don't hit defensive assertion code:
    'raise AssertionError',
    'raise NotImplementedError',

    # Don't complain if non-runnable code isn't run:
    'if 0:',
    'if __name__ == .__main__.:',

    # Don't complain for the type checking code:
    'if TYPE_CHECKING:'
]

# don't fail on the code that can be found
ignore_errors = true

skip_empty = true

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

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

extend-exclude = [
    "src/datumaro/plugins/openvino_plugin/samples"
]

[tool.ruff.lint]
select = ["ARG", "E", "F", "I", "N", "UP", "YTT", "ASYNC", "S", "COM", "C4", "FA", "PIE", "PYI", "Q", "RSE", "RET", "SIM",
    "TID", "TC", "PL", "RUF", "C90", "D103", "ANN001", "ANN201", "ANN205", "FAST"]

ignore = ["N801", "N805","N806","N807", "N818", "COM812", "RET503", "SIM108", "SIM105", "PLR2004",
    "RUF010", "TC001",  "RUF012", "PLC0415"]

fixable = ["ALL"]
dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"

[tool.ruff.lint.per-file-ignores]
"*test*.py" = ["S", "ANN", "D", "ARG", "PLR", "N8", "RUF001", "E741", "E4", "F403", "F405"]
"!src/datumaro/experimental/**" = ["S", "ANN", "D", "ARG", "PLR", "PLC0415", "PLW", "C", "UP", "N8", "E741", "E402"]
"__init__.py" = [
    "F4"      # unused-import
]
"src/datumaro/plugins/data_formats/ava/ava_label_pb2.py" = [
    "E501"      # line-too-long
]
"notebooks/**" = [ "E501" ]

[tool.ruff.lint.isort]
split-on-trailing-comma = false
known-local-folder = []

[tool.ruff.lint.pylint]
max-args=7

[tool.ruff.lint.mccabe]
# Unlike Flake8, default to a complexity level of 10.
max-complexity = 10

[tool.nbqa.addopts]
ruff = ["--ignore=E402"]

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

[tool.bandit]
exclude_dirs = [
  '.vscode/',
  '.git/',
  'build/',
  'tests/',
]
tests = [ 'B301', 'B302', 'B303', 'B304', 'B305', 'B306', 'B308', 'B310', 'B311', 'B312', 'B313', 'B314', 'B315', 'B316', 'B317', 'B318', 'B319', 'B321', 'B323', 'B324', 'B401', 'B402', 'B403', 'B404', 'B405', 'B406', 'B407', 'B408', 'B409', 'B411', 'B412', 'B413']