pyproject.toml

[project]
name = "microdata-lab"
version = "0.1.0"
description = "Zero-manual-download public microdata acquisition, cataloging, analysis, and visualization"
readme = "README.md"
requires-python = ">=3.11"
license = "Apache-2.0"
dependencies = [
  "duckdb>=1.3.0",
  "filelock>=3.18.0",
  "httpx>=0.28.1",
  "numpy>=2.2.0",
  "pandas>=2.2.3",
  "platformdirs>=4.3.8",
  "pydantic>=2.11.7",
  "pyarrow>=19.0.0",
  "python-dotenv>=1.1.1",
  "pyreadstat>=1.2.8",
  "pyyaml>=6.0.2",
  "rich>=14.0.0",
  "scipy>=1.14.0",
  "selectolax>=0.3.31",
  "statsmodels>=0.14.0",
  "typer>=0.16.0",
  "openpyxl>=3.1.5",
  "curl-cffi>=0.16.0",
]

[project.optional-dependencies]
docs = ["pypdf>=5.6.0"]
dev = [
  "mypy>=1.16.0",
  "pandas-stubs>=2.2.3",
  "pillow>=11.0.0",
  "pytest>=8.4.0",
  "pytest-cov>=6.2.0",
  "respx>=0.22.0",
  "ruff>=0.12.0",
  "types-pyyaml>=6.0.12.20250516",
]

[project.scripts]
microdata = "microdata_lab.cli:app"

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

[tool.hatch.build.targets.wheel]
packages = ["src/microdata_lab"]

[tool.pytest.ini_options]
addopts = "-q --strict-markers"
testpaths = ["tests"]

[tool.ruff]
target-version = "py311"
line-length = 100

[tool.ruff.lint]
select = ["E", "F", "I", "B", "UP", "SIM", "RUF"]
# The project uses typographic punctuation intentionally in chart copy,
# docstrings, and publication notes. These rules mistake that copy for
# ambiguous identifiers; they do not improve runtime correctness here.
ignore = ["RUF001", "RUF002", "RUF003"]

[tool.ruff.lint.per-file-ignores]
"src/microdata_lab/cli.py" = ["B008"]
"analyses/*/estimate.py" = ["E501"]

[tool.mypy]
python_version = "3.11"
strict = true
packages = ["microdata_lab"]

[[tool.mypy.overrides]]
module = ["pyarrow", "pyarrow.*"]
ignore_missing_imports = true

[dependency-groups]
dev = [
    "types-openpyxl>=3.1.5.20260724",
]