pyproject.toml

[build-system]
requires = ["setuptools>=72.1"]
build-backend = "setuptools.build_meta"

[project]
name = "sf-hamilton"
dynamic = ["version"]
description = "Hamilton, the micro-framework for creating dataframes."
readme = "README.md"
requires-python = ">=3.8, <4"
license = {text = "BSD-3-Clause"}
keywords = ["hamilton"]
authors = [
    { name = "Stefan Krawczyk", email = "stefan@dagworks.io" },
    { name = "Elijah ben Izzy", email = "elijah@dagworks.io" },
]
classifiers = [
    "Development Status :: 5 - Production/Stable",
    "Intended Audience :: Developers",
    "Natural Language :: English",
    "License :: OSI Approved :: BSD License",
    "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",
]
dependencies = [
    "numpy",
    "pandas",
    "typing_extensions > 4.0.0",
    "typing_inspect",
]

[project.optional-dependencies]
cli = ["typer"]
dask = ["dask[complete]"]  # commonly you'll want everything.
dask-array = ["dask[array]"]
dask-core = ["dask-core"]
dask-dataframe = ["dask[dataframe]"]
dask-diagnostics = ["dask[diagnostics]"]
dask-distributed = ["dask[distributed]"]
datadog = ["ddtrace"]
dev = [
  "pre-commit",
  "ruff==0.5.7", # this should match `.pre-commit-config.yaml`
]
diskcache = ["diskcache"]
docs = [
  "sf-hamilton[dev]",
  "alabaster>=0.7,<0.8,!=0.7.5", # read the docs pins
  "commonmark==0.9.1", # read the docs pins
  "dask-expr",
  "dask[distributed]",
  "ddtrace",
  "diskcache",
  # required for all the plugins
  "dlt",
  # furo -- install from main for now until the next release is out:
  "furo @ git+https://github.com/pradyunsg/furo@main",
  "gitpython", # Required for parsing git info for generation of data-adapter docs
  "grpcio-status",
  "lightgbm",
  "lxml",
  "lz4",
  "mlflow",
  "mock==1.0.1", # read the docs pins
  "myst-nb",
  "narwhals",
  "numpy < 2.0.0",
  "pandera",
  "pillow",
  "polars",
  "pyarrow >= 1.0.0",
  "pydantic >=2.0",
  "pyspark",
    "openlineage-python",
  "PyYAML",
  "ray",
  "readthedocs-sphinx-ext<2.3", # read the docs pins
  "recommonmark==0.5.0", # read the docs pins
  "scikit-learn",
  "slack-sdk",
  "sphinx", # unpinned because myst-parser doesn't break anymore
  "sphinx-autobuild",
  "sphinx-rtd-theme", # read the docs pins
  "sphinx-simplepdf",
  "sphinx-sitemap",
  "tqdm",
  "xgboost",
]
experiments = [
  "fastapi",
  "fastui",
  "uvicorn",
]
lsp = ["sf-hamilton-lsp"]
openlineage = ["openlineage-python"]
packaging = [
  "build",
]
pandera = ["pandera"]
pydantic = ["pydantic>=2.0"]
pyspark = [
  # we have to run these dependencies because Spark does not check to ensure the right target was called
  "pyspark[pandas_on_spark,sql]"
]
ray = ["ray>=2.0.0", "pyarrow"]
sdk = ["sf-hamilton-sdk"]
slack = ["slack-sdk"]
test = [
  "connectorx",
  "dask",
  "dask-expr; python_version >= '3.9'",
  "datasets", # huggingface datasets
  "diskcache",
  "dlt",
  "fsspec",
  "graphviz",
  "kaleido",
  "kedro",
  "lancedb",
  "lightgbm",
  "lxml",
  "lz4",
  "matplotlib",
  "mlflow",
  "networkx",
  "openpyxl", # for excel data loader
  "pandera",
  "plotly",
  "polars",
  "pyarrow",
  "pydantic >=2.0",
  "pyreadstat", # for SPSS data loader
  "pytest",
  "pytest-asyncio",
  "pytest-cov",
  "PyYAML",
  "scikit-learn",
  "sqlalchemy==1.4.49; python_version == '3.7.*'",
  "sqlalchemy; python_version >= '3.8'",
  "typer",
  "xgboost",
  "xlsx2csv", # for excel data loader
  "xlsxwriter",  # Excel export requires 'xlsxwriter'
]
tqdm = ["tqdm"]
ui = ["sf-hamilton-ui"]
vaex = ["vaex"]
visualization = ["graphviz", "networkx"]

[project.entry-points.console_scripts]
h_experiments = "hamilton.plugins.h_experiments.__main__:main"
hamilton = "hamilton.cli.__main__:cli"
hamilton-admin-build-ui = "hamilton.admin:build_ui"
hamilton-admin-build-and-publish = "hamilton.admin:build_and_publish"
hamilton-disable-autoload-extensions = "hamilton.registry:config_disable_autoload"
hamilton-enable-autoload-extensions = "hamilton.registry:config_enable_autoload"

[project.urls]
homepage = "https://www.tryhamilton.dev/"
documentation = "https://hamilton.dagworks.io/en/latest/"
changelog = "https://github.com/DAGWorks-Inc/hamilton/releases"
issues = "https://github.com/dagworks-inc/hamilton/issues"
source = "https://github.com/dagworks-inc/hamilton"
slack = "https://join.slack.com/t/hamilton-opensource/shared_invite/zt-2niepkra8-DGKGf_tTYhXuJWBTXtIs4g"

#[tool.mypy]
#exclude = []

#[tool.pytest.ini_options]
#pythonpath = []
#testpaths = []

[tool.ruff]
line-length = 100
target-version = "py38"  # Must include only the earliest supported version

[tool.ruff.format]
docstring-code-format = false
exclude = [
    "docs/*",
]

[tool.ruff.lint]
extend-select = [
    "B",   # flake8-bugbear rules
#    "C4",  # Helps you write better list/set/dict comprehensions.
    "E",   # pycodestyle errors
    "F",   # pyflakes
#    "FA",  # Verifies files use from __future__ import annotations if a type is used in the module that can be rewritten using PEP 563.
    "FURB",# Refurbishing and modernizing Python codebases
#    "G",   # flake8-logging-format rules
    "I",   # isort
    "ISC", # Encourage correct string literal concatenation.
    "LOG", # Checks for issues using the standard library logging module.
#    "N",   # Check PEP-8 naming conventions
#    "NPY", # Linting rules for numpy
#    "PERF",# Linting rules for performance
#    "PIE", # flake8-pie rules
#    "PT",  # flake8-pytest-style rules
#    "PYI", # Linting rules for type annotations.
    "Q",   # Linting rules for quites
#    "RUF", # Unused noqa directive
#    "SIM", # Linting rules for simplicity
#    "T20", # Check for Print statements in python files.
    "TCH", # Move type-only imports to a type-checking block.
    "TID", # Helps you write tidier imports.
#    "TRY", # Prevent exception handling anti-patterns
#    "UP",  # pyupgrade
    "W",   # pycodestyle warnings
]
extend-ignore = [
    "ISC001", # Checks for implicitly concatenated strings on a single line.
    "T201",
    "TRY003",
    "E203", # whitespace before ':'
    "E402", # module level import not at top of file
    "E501", # line too long
    "E721", # Use `is` and `is not` for type comparisons, or `isinstance()` for isinstance checks
    "W605", # invalid escape sequence
    "TCH001" # TYPE_CHECKING block for first-class imports -- this is a bit ugly for the hamilton codebase
]
exclude = [
    "docs/*",
    "**/business_logic.py",
]

[tool.ruff.lint.isort]
known-local-folder = ["tests"]
known-first-party = ["hamilton*"]

[tool.ruff.lint.per-file-ignores]
"tests/**/*.py" = [
    "S101", # asserts allowed in tests...
    "ARG", # Unused function args -> fixtures nevertheless are functionally relevant...
    "FBT", # Don't care about booleans as positional arguments in tests, e.g. via @pytest.mark.parametrize()
]
"__init__.py" = ["F401"]

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

[tool.setuptools.packages.find]
include = ["hamilton", "hamilton.*"]
exclude = ["*tests*"]

[tool.setuptools.package-data]
hamilton = ["*.json", "*.md", "*.txt"]