.ruff.toml

# --- ruff -------------------------------------------------------------------
preview = false  # do not use unstable rules/fixes
# # Assumed Python version
# target-version = "py39" # managed in [project]requires-python above

# file selection
extend-exclude = [
  '.ci',
  '.pytest_cache',
  'docs',
  '*.egg-info',
  '.ipynb_checkpoints',
  '.env',
  '.envrc',
  '.git',
  '.nox',
  '.tox',
]
extend-include = ["*.ipynb"]

# Autofix behavior
fix = true

# Line options
indent-width = 4
line-length = 119

# Directories with source code; allow relative imports
src = ["src", "notebooks", "tests"]

# Group output violations by file
output-format = "grouped"


[format]
indent-style = "space"
line-ending = "auto"
quote-style = "double"
skip-magic-trailing-comma = false
docstring-code-format = true


[lint]
exclude = ["*.pyi"]

select = [
  'A', # flake8 builtins
  'B', # flake8 bugbear
  'C4', # flake8 comprehensions
  'C90', # mccabe
  'D', # pydocstyle
  'E', # pycodestyle
  'F', # pyflakes
  'I', # isort
  'N', # pep8-naming
  # 'PTH', # flake8-use-pathlib
  'Q',  # flake8-quotes
  'S',  # bandit
  'SIM',  # flake8-simplify
  'TRY',  # tryceratops
  'W', # pycodestyle
  # 'T20', # flake8 print
]

ignore = [
  "B905",  # zip strict=True; remove once python <3.10 support is dropped.
  "D100",  # do not require module-level docstrings
  "D104",  # do not require package docstrings
  "D107",  # do not require docstrings in __init__ files
  # "D205",  # don't require linebreak after docstring (ruff vs black conflict)
  "D206",  # redundant w formatter
  "D300",  # redundant w formatter
  "E111",  # redundant w formatter
  "E114",  # redundant w formatter
  "E117",  # redundant w formatter
  "E501",  # line too long
  "F401",  # unused import
  "F403",  # import *
  "F405",  # defined from import *
  # "F541",  # f-string missing placeholders
  "N999",  # allow "invalid" module names due to jinja templates
  "Q000",  # redundant w formatter
  "Q001",  # redundant w formatter
  "Q002",  # redundant w formatter
  "Q003",  # redundant w formatter
  # "S101",  # assert
  "S311",  # allow psuedorandom generators (we use for stats)
  "SIM105",  # allow except: pass
  "TRY003",  # Avoid specifying messages outside exception class; overly strict, especially for ValueError
  "TRY201",  # Allow raise without exception name (align with Sonarlint)
  "W191",  # redundant w formatter
  # "W503",  # not in ruff
  "COM812",  # redundant w formatter
  "COM819",  # redundant w formatter
  "ISC001",  # redundant w formatter
  "ISC002",  # redundant w formatter
]

# Avoid trying to fix extension types:
unfixable = ["B"]

[lint.per-file-ignores]
# # Ignore `E402` (import violations) in all `__init__.py` files,
# # and in `path/to/file.py`.
# "__init__.py" = ["E402"]
# "path/to/file.py" = ["E402"]
".ci/*" = ["D"]
"docs/*" = ["D"]
"notebooks/*" = ["B018", "D", "S"]
"tests/*" = ["D", "S101", "S301"]


# --- ruff plugins --------------------
[lint.flake8-bugbear]
extend-immutable-calls = [
    "chr",
    "typer.Argument",
    "typer.Option",
]

[lint.isort]
combine-as-imports = true
detect-same-package = true
extra-standard-library = ["yaml"]
force-sort-within-sections = true
force-to-top = ["src", "torch"]
# forced-separate = ["scipy", "sklearn", "statsmodels", "torch"]
relative-imports-order = "closest-to-furthest"

known-local-folder = ["src"] # for relative imports
section-order = ["future", "standard-library", "third-party", "sci", "torch", "plot", "first-party", "local-folder"]

[lint.isort.sections]
"sci" = ["numpy", "pandas", "scipy", "sklearn", "statsmodels"]
"torch" = ["datasets", "lightning", "torch", "torch*", "tokenizers", "transformers", "sentence-transformers"]
"llm" = ["langchain*", "llama-index*", "semantic_kernel"]
"plot" = ["cmcrameri", "matplotlib", "plotly", "plotnine", "seaborn"]

[lint.mccabe]
max-complexity = 18

[lint.pep8-naming]
ignore-names = []

[lint.pydocstyle]
convention = "numpy"