pyproject.toml

[build-system]
build-backend = "hatchling.build"
requires = [ "hatchling" ]

[project]
name = "gget"
version = "0.30.9"
description = "Efficient querying of genomic databases."
readme = "README.md"
keywords = [ "gget" ]
license = "BSD-2-Clause"
license-files = [ "LICENSE" ]
maintainers = [
  { name = "Laura Luebbert", email = "lauralubbert@gmail.com" },
]
authors = [
  { name = "Laura Luebbert", email = "lauralubbert@gmail.com" },
]
requires-python = ">=3.12"
classifiers = [
  "Environment :: Console",
  "Framework :: Jupyter",
  "Intended Audience :: Science/Research",
  "Operating System :: OS Independent",
  "Programming Language :: Python :: 3 :: Only",
  "Programming Language :: Python :: 3.12",
  "Programming Language :: Python :: 3.13",
  "Programming Language :: Python :: 3.14",
  "Topic :: Scientific/Engineering :: Bio-Informatics",
  "Topic :: Utilities",
]
dependencies = [
  "beautifulsoup4>=4.10",
  "ipython",
  "ipywidgets",
  "lxml",
  "matplotlib",
  "mysql-connector-python>=8.0.32",
  "numpy>=1.17.2",
  "pandas>=1",
  "requests>=2.22",
  "tqdm",
]
# Optional feature dependency for `gget cellxgene` (install: pip install gget[cellxgene]).
# No wheels for the newest Python versions yet (e.g. 3.14 via tiledbsoma).
# scanpy>=1.10 is pinned defensively, not because gget uses scanpy directly,
# but because tiledbsoma (cellxgene-census's dep) declares only `scanpy>=1.9.2`.
# Under certain resolver paths uv lands on scanpy 1.9.8, which transitively
# pins numba 0.53.1 and llvmlite 0.36.x — both of which only support Python 3.6-3.9.
optional-dependencies.cellxgene = [ "cellxgene-census", "scanpy>=1.10" ]
# https://docs.pypi.org/project_metadata/#project-urls
urls.Documentation = "https://pachterlab.github.io/gget"
urls.Homepage = "https://github.com/pachterlab/gget"
urls.Source = "https://github.com/pachterlab/gget"
scripts.gget = "gget.main:main"

[dependency-groups]
dev = [ "pre-commit" ]
test = [
  "bravado==11.0.3",
  "coverage>=7",
  "mypy==1.13",
  "mypy-baseline==0.7.4",
  "openai<=0.28.1",
  "pandas-stubs==3.0.3.260530",
  "parameterized==0.9",
  "pytest>=7",
  "pytest-cov>=6.2.1",
  "pytest-xdist>=3",
  "types-beautifulsoup4==4.12.0.20250516",
  "types-requests==2.33.0.20260518",
  "types-tqdm==4.68.0.20260608",
]

[tool.hatch]
build.targets.wheel.packages = [ "gget" ]
envs.default.installer = "uv"
envs.hatch-test.matrix = [
  { python = [ "3.12", "3.13", "3.14" ] },
]
# cellxgene-census (the `cellxgene` extra) has no wheels for the newest Python
# versions yet (e.g. 3.14 via tiledbsoma), so install it only where available;
# the gget cellxgene test skips itself when the dependency is absent.
envs.hatch-test.overrides.matrix.python.features = [
  { value = "cellxgene", if = [ "3.12", "3.13" ] },
]
# pyproject.toml is the single source of truth for the environments CI tests:
# the workflow reads this matrix via `hatch env show --json`.
envs.hatch-test.default-args = [ "-n", "auto", "tests" ]
envs.hatch-test.dependency-groups = [ "test" ]

[tool.ruff]
line-length = 120
src = [ "gget" ]
extend-include = [ "*.ipynb" ]
format.docstring-code-format = true
lint.select = [
  "B",      # flake8-bugbear
  "BLE",    # flake8-blind-except
  "C4",     # flake8-comprehensions
  "D",      # pydocstyle
  "E",      # Error detected by Pycodestyle
  "F",      # Errors detected by Pyflakes
  "I",      # isort
  "RUF100", # Report unused noqa directives
  "TID",    # flake8-tidy-imports
  "UP",     # pyupgrade
  "W",      # Warning detected by Pycodestyle
]
lint.ignore = [
  "B008", # Errors from function calls in argument defaults. These are fine when the result is immutable.
  "D100", # Missing docstring in public module
  "D104", # Missing docstring in public package
  "D105", # __magic__ methods are often self-explanatory, allow missing docstrings
  "D107", # Missing docstring in __init__
  # Disable one in each pair of mutually incompatible rules
  "D203", # We don’t want a blank line before a class docstring
  "D213", # <> We want docstrings to start immediately after the opening triple quote
  "D400", # first line should end with a period [Bug: doesn’t work with single-line docstrings]
  "D401", # First line should be in imperative mood; try rephrasing
  "E501", # line too long -> we accept long comment lines; formatter gets rid of long code lines
  "E731", # Do not assign a lambda expression, use a def -> lambda expression assignments are convenient
  "E741", # allow I, O, l as variable names -> I is the identity matrix
]
lint.per-file-ignores."*/__init__.py" = [ "F401" ]
lint.per-file-ignores."docs/*" = [ "I" ]
lint.per-file-ignores."tests/*" = [ "D" ]
lint.pydocstyle.convention = "numpy"

[tool.mypy]
files = [ "gget" ]
# `gget/constants.py` (module) coexists with `gget/constants/` (data dir, no
# __init__.py). Mypy's default namespace-package discovery treats the data dir
# as a namespace package and clashes with the module of the same name, so we
# disable namespace packages.
namespace_packages = false
ignore_missing_imports = true
follow_imports = "silent"
python_version = "3.12"
disallow_any_generics = false
disallow_untyped_defs = false
check_untyped_defs = false
warn_redundant_casts = true
warn_unused_ignores = true
show_error_codes = true

[tool.pytest]
ini_options.testpaths = [ "tests" ]
ini_options.addopts = [ "-ra" ]

[tool.coverage]
run.omit = [
  "**/test_*.py",
  "gget/main.py",
]
run.source = [ "gget" ]

# mypy-baseline grandfathers the pre-existing type errors so the pre-commit
# mypy hook only fails on NEW errors. Refresh after fixing some with:
#   mypy gget | mypy-baseline sync
[tool.mypy-baseline]
baseline_path = ".mypy-baseline.txt"
# Ignore mypy `note:` lines in the baseline. Notes are non-actionable context
# attached to errors, and mypy emits slightly different notes across platforms
# (the baseline is generated on macOS; CI runs on Linux), which would otherwise
# show up as spurious "new" violations.
ignore_categories = [ "note" ]