pyproject.toml

[build-system]
requires = ["setuptools>=48", "setuptools_scm[toml]>=6.3.1"]
build-backend = "setuptools.build_meta"

[project]
name = "datachain"
description = "Wrangle unstructured AI data at scale"
readme = "README.rst"
license = {text = "Apache-2.0"}
authors = [{name = "Dmitry Petrov", email = "support@dvc.org"}]
classifiers = [
  "Programming Language :: Python :: 3",
  "Programming Language :: Python :: 3.9",
  "Programming Language :: Python :: 3.10",
  "Programming Language :: Python :: 3.11",
  "Programming Language :: Python :: 3.12",
  "Development Status :: 2 - Pre-Alpha"
]
requires-python = ">=3.9"
dynamic = ["version"]
dependencies = [
  "pyyaml",
  "tomlkit",
  "tqdm",
  "numpy>=1,<3",
  "pandas>=2.0.0",
  "pyarrow",
  "typing-extensions",
  "python-dateutil>=2",
  "attrs>=21.3.0",
  "s3fs>=2024.2.0",
  "gcsfs>=2024.2.0",
  "adlfs>=2024.2.0",
  "dvc-data>=3.10,<4",
  "dvc-objects>=4,<6",
  "shtab>=1.3.4,<2",
  "sqlalchemy>=2",
  "multiprocess==0.70.16",
  "cloudpickle",
  "orjson>=3.10.5",
  "pydantic>=2,<3",
  "jmespath>=1.0",
  "datamodel-code-generator>=0.25",
  "Pillow>=10.0.0,<12",
  "msgpack>=1.0.4,<2",
  "psutil",
  "huggingface_hub",
  "iterative-telemetry>=0.0.9",
  "platformdirs",
  "dvc-studio-client>=0.21,<1"
]

[project.optional-dependencies]
docs = [
  "mkdocs>=1.5.2",
  "mkdocs-gen-files>=0.5.0",
  "mkdocs-material>=9.3.1",
  "mkdocs-section-index>=0.3.6",
  "mkdocstrings-python>=1.6.3",
  "mkdocs-literate-nav>=0.6.1"
]
torch = [
  "torch>=2.1.0",
  "torchvision",
  "transformers>=4.36.0"
]
remote = [
  "lz4",
  "requests>=2.22.0"
]
vector = [
  "usearch"
]
hf = [
  "numba>=0.60.0",
  "datasets[audio,vision]>=2.21.0"
]
tests = [
  "datachain[torch,remote,vector,hf]",
  "pytest>=8,<9",
  "pytest-sugar>=0.9.6",
  "pytest-cov>=4.1.0",
  "pytest-mock>=3.12.0",
  "pytest-servers[all]>=0.5.7",
  "pytest-benchmark[histogram]",
  "pytest-xdist>=3.3.1",
  "virtualenv",
  "dulwich",
  "hypothesis",
  "open_clip_torch",
  "aiotools>=1.7.0",
  "requests-mock",
  "scipy"
]
dev = [
  "datachain[docs,tests]",
  "mypy==1.13.0",
  "types-python-dateutil",
  "types-pytz",
  "types-PyYAML",
  "types-requests"
]
examples = [
  "datachain[tests]",
  "numpy>=1,<2",
  "defusedxml",
  "accelerate",
  "unstructured[pdf,embed-huggingface]<0.16.0",
  "pdfplumber==0.11.4",
  "huggingface_hub[hf_transfer]",
  "onnx==1.16.1"
]

[project.urls]
Documentation = "https://datachain.dvc.ai"
Issues = "https://github.com/iterative/datachain/issues"
Source = "https://github.com/iterative/datachain"

[project.scripts]
datachain = "datachain.cli:main"

[tool.setuptools.packages.find]
exclude = ["tests", "tests.*"]
where = ["src"]
namespaces = false

[tool.setuptools_scm]

[tool.pytest.ini_options]
addopts = "-rfEs -m 'not examples' --benchmark-skip"
markers = [
  "e2e: End-to-end tests",
  "examples: All examples",
  "computer_vision: Computer vision examples",
  "get_started: Get started examples",
  "llm_and_nlp: LLM and NLP examples",
  "multimodal: Multimodal examples"
]
filterwarnings = [
  "error::pandas.errors.PerformanceWarning",
  "error::pydantic.warnings.PydanticDeprecatedSince20",
  "error::pytest_mock.PytestMockWarning",
  "error::pytest.PytestCollectionWarning",
  "error::sqlalchemy.exc.SADeprecationWarning",
  "ignore::DeprecationWarning:timm.*",
  "ignore::DeprecationWarning:botocore.auth",
  "ignore::DeprecationWarning:datasets.utils._dill",
  "ignore::DeprecationWarning:librosa.core.intervals",
  "ignore:Field name .* shadows an attribute in parent:UserWarning"  # datachain.lib.feature
]

[tool.coverage.run]
branch = true
source = ["datachain", "tests"]

[tool.coverage.paths]
source = ["src", "*/site-packages"]

[tool.coverage.report]
show_missing = true
exclude_lines = [
  "pragma: no cover",
  "if __name__ == .__main__.:",
  "if typing.TYPE_CHECKING:",
  "if TYPE_CHECKING:",
  "raise NotImplementedError",
  "raise AssertionError",
  "if self.dialect == .sqlite.",
  "@overload"
]

[tool.mypy]
# Error output
show_column_numbers = true
show_error_codes = true
show_error_context = true
show_traceback = true
pretty = true
check_untyped_defs = false
# Warnings
warn_no_return = true
warn_redundant_casts = true
warn_unreachable = true
ignore_missing_imports = true
disable_error_code = "annotation-unchecked"
files = ["src", "tests"]

[tool.codespell]
ignore-words-list = " "
skip = ["CODE_OF_CONDUCT.rst", "examples/**/*.ipynb", "tests/examples/wds_data.py"]

[tool.ruff]
show-fixes = true

[tool.ruff.lint]
preview = true
explicit-preview-rules = true
ignore = [
  "S101",  # assert
  "PLR2004",  # magic-value-comparison
  "PLW2901",  # redefined-loop-name
  "ISC001",  # single-line-implicit-string-concatenation, incompatible with ruff format
  "RET502",  # implicit-return-value
  "RET503",  # implicit-return
  "SIM105",  # suppressible-exception
  "SIM108",  # if-else-block-instead-of-if-exp
  "SIM117",  # multiple-with-statements
  "PERF203",  # perflint - try-except-in-loop, irrelevant for Python>=3.11
  "PERF401",
  "D100",  # undocumented-public-module
  "D205"  # one-blank-line-after-class
]
select = [
  "B",  # flake8-bugbear
  "C4",  # flake8-comprehensions
  "C420",  # unnecessary-dict-comprehension-for-iterable
  "C90",  # mccabe
  "W",  # pycodestyle - Warning
  "E",  # pycodestyle - Error
  "F",  # pyflakes
  "I",  # isort
  "T10",  # flake8-debugger
  "S",  # flake8-bandit
  "PL",  # pylint
  "TCH",  # flake8-type-checking
  "UP",  # pyupgrade
  "N",  # pep8-naming
  "YTT",  # flake8-2020
  "ASYNC",  # flake8-async
  "EXE",  # flake8-executable
  "ISC",  # flake8-implicit-str-concat
  "ICN",  # flake8-import-conventions
  "PIE",  # flake8-pie
  "LOG",  # flake8-logging
  "G",  # flake8-logging-format
  "PYI",  # flake8-pyi
  "Q",  # flake8-quotes
  "SLOT",  # flake8-slots
  "PGH",  # pygrep-hooks
  "FLY",  # flynt
  "PERF",  # perflint
  "TID",  # flake8-tidy-imports
  "RSE",  # flake8-raise
  "INP",  # flake8-no-pep420
  "RUF",  # ruff rules
  "BLE",  # flake8-blind-except
  "SIM",  # flake8-simplify
  "RSE",  # flake8-raise
  "RET",  # flake8-return
  "DTZ",  # flake8-datetimez
  "FURB",  # refurb
  "NPY",  # numpy
  "TRY004",  # type-check-without-type-error
  "TRY201",  # verbose-raise
  "TRY203",  # useless-try-except
  "TRY401",  # verbose-log-message
  "RUF022",  # unsorted-dunder-all
  "RUF023",  # unsorted-dunder-slots
  "RUF027",  # missing-f-string-syntax
  "RUF030",  # assert-with-print-message
  "RUF101",  # redirected-noqa
  "D"  # pydocstyle
]

[tool.ruff.lint.flake8-bugbear]
# Allow default arguments like, e.g., `data: List[str] = fastapi.Query(None)`.
extend-immutable-calls = ["datachain.storage.StorageURI"]

[tool.ruff.lint.flake8-type-checking]
strict = true

[tool.ruff.lint.isort]
known-first-party = ["datachain"]

[tool.ruff.lint.pylint]
max-args = 16
max-branches = 16
max-public-methods = 32
max-statements = 64

[tool.ruff.lint.mccabe]
max-complexity = 15

[tool.ruff.lint.per-file-ignores]
"examples/**" = ["INP001"]
"!src/datachain/lib/dc.py" = ["D"]
"tests/scripts/**" = ["INP001"]
"tests/**" = ["DTZ"]
"tests/examples/wds_data.py" = ["E501"]

[tool.ruff.lint.pydocstyle]
convention = "google"