pyproject.toml

[tool.poetry]
name = "dataverse-metadata-crawler"
version = "0.1.1"
description = "A Python CLI tool for bulk extracting and exporting metadata from Dataverse repositories' collections to JSON and CSV formats."
authors = ["Ken Lui <kenlh.lui@utoronto.ca>"]
license = "MIT"
readme = "README.md"
package-mode = false

[tool.poetry.dependencies]
python = "^3.10"
httpx = "^0.27.2"
orjson = "^3.10.14"
asyncio = "^3.4.3"
jmespath = "^1.0.1"
typer = "^0.13.1"
rich-argparse = "^1.6.0"
jinja2 = "^3.1.4"
ipykernel = "^6.29.5"
pandas = "^2.2.3"
python-dotenv = "^1.0.1"
pydataverse = "^0.3.4"
numpy = "^2.2.1"
json2 = "^0.9.0"


[tool.poetry.group.dev.dependencies]
ipykernel = "^6.29.5"

[build-system]
requires = ["poetry-core"]
build-backend = "poetry.core.masonry.api"

[tool.ruff]
# General settings
line-length = 120
indent-width = 4
ignore = ["T201"]  # Ignore print statements globally

[tool.ruff.format]
quote-style = "single"
indent-style = "space"
skip-magic-trailing-comma = false
line-ending = "auto"

[tool.ruff.lint]
# Enable pycodestyle (`E`) and Pyflakes (`F`) codes by default.
select = [
    "E",   # pycodestyle errors
    "F",   # Pyflakes
    "W",   # pycodestyle warnings
    "C90", # mccabe
    "I",   # isort
    "N",   # pep8-naming
    "D",   # pydocstring
    "UP",  # pyupgrade
    "ANN", # flake8-annotations
    "B",   # flake8-bugbear
    "C4",  # flake8-comprehensions
    "DTZ", # flake8-datetimez
    "EM",  # flake8-errmsg
    "G",   # flake8-logging-format
    "PIE", # flake8-pie
    "T20", # flake8-print
    "Q",   # flake8-quotes
    "RSE", # flake8-raise
    "RET", # flake8-return
    "SIM", # flake8-simplify
    "PTH", # flake8-use-pathlib
    "PL",  # Pylint
]

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

[tool.ruff.lint.isort]
force-single-line = true
lines-after-imports = 2
known-first-party = ["my_package"]

[tool.ruff.lint.flake8-quotes]
docstring-quotes = "double"
inline-quotes = "single"

[tool.ruff.lint.pylint]
max-args = 6  # Google suggests keeping functions focused
max-locals = 15
max-statements = 50

[tool.ruff.lint.mccabe]
max-complexity = 10  # Google suggests keeping functions simple

[tool.ruff.lint.per-file-ignores]
# Ignore some rules in tests
"test_*.py" = ["D", "ANN"]
# Ignore some rules in __init__.py files
"__init__.py" = ["F401"]
# Ignore long line warnings in main.py
"dvmeta/main.py" = ["E501", "W505"]  

[tool.ruff.lint.pep8-naming]
# Google style guide naming conventions
classmethod-decorators = ["classmethod"]
staticmethod-decorators = ["staticmethod"]

[tool.ruff.lint.pycodestyle]
max-doc-length = 120