ruff.toml

# Ruff configuration for TPack
# See: https://docs.astral.sh/ruff/configuration/

# General settings
line-length = 88
target-version = "py313"

[lint]
# Enable comprehensive rule sets
select = [
  "E",    # pycodestyle errors
  "W",    # pycodestyle warnings  
  "F",    # pyflakes
  "I",    # isort (import sorting)
  "N",    # pep8-naming
  "UP",   # pyupgrade (modernize Python code)
  "YTT",  # flake8-2020 (sys.version_info comparisons)
  "S",    # flake8-bandit (security)
  "BLE",  # flake8-blind-except
  "B",    # flake8-bugbear
  "A",    # flake8-builtins
  "COM",  # flake8-commas
  "C4",   # flake8-comprehensions
  "DTZ",  # flake8-datetimez
  "EM",   # flake8-errmsg
  "FA",   # flake8-future-annotations
  "ISC",  # flake8-implicit-str-concat
  "ICN",  # flake8-import-conventions
  "G",    # flake8-logging-format
  "INP",  # flake8-no-pep420
  "PIE",  # flake8-pie
  "T20",  # flake8-print
  "PT",   # flake8-pytest-style
  "Q",    # flake8-quotes
  "RSE",  # flake8-raise
  "RET",  # flake8-return
  "SLF",  # flake8-self
  "SIM",  # flake8-simplify
  "TID",  # flake8-tidy-imports
  "TCH",  # flake8-type-checking
  "ARG",  # flake8-unused-arguments
  "PTH",  # flake8-use-pathlib
  "ERA",  # eradicate (remove commented code)
  "PD",   # pandas-vet (pandas best practices)
  "PGH",  # pygrep-hooks
  "PL",   # pylint
  "TRY",  # tryceratops
  "FLY",  # flynt (f-string conversion)
  "NPY",  # numpy-specific rules
  "PERF", # performance anti-patterns
  "RUF",  # ruff-specific rules
]

# Disable specific rules that might be too strict for this project
ignore = [
  "E501",    # Line too long (handled by formatter)
  "COM812",  # Trailing comma missing (conflicts with formatter)
  "ISC001",  # Single line implicit string concatenation (conflicts with formatter)
  "S101",    # Use of assert (common in data science/testing)
  "T201",    # Print statements (common in CLI tools)
  "G004",    # Logging f-string (sometimes clearer than .format())
  "EM101",   # String literal in exception (sometimes clearer)
  "EM102",   # f-string in exception (sometimes clearer)
  "TRY003",  # Long exception messages (sometimes necessary)
  "PLR0913", # Too many arguments (common in data science functions)
  "PLR0915", # Too many statements (common in CLI/data processing)
  "PLR2004", # Magic value comparison (common with ML hyperparameters)
  "PD901",   # df as variable name (very common in pandas)
  "S603",    # subprocess without shell=True check (context-dependent)
  "S607",    # subprocess with shell=True (context-dependent)
  "ARG001",  # Unused function argument (common with interface implementations)
  "ARG002",  # Unused method argument (common with interface implementations)
]

# Per-file-type ignores
[lint.per-file-ignores]
# Test files
"test_*.py" = ["S101", "PLR2004", "ARG001", "ARG002"]
"**/test_*.py" = ["S101", "PLR2004", "ARG001", "ARG002"]
"tests/**/*.py" = ["S101", "PLR2004", "ARG001", "ARG002"]

# CLI scripts can have print statements and sys.exit
"src/bin/*.py" = ["T201", "PLR0912", "PLR0915"]

# Evaluation scripts often have complex logic and many arguments
"src/evaluators/*.py" = ["PLR0913", "PLR0912", "C901"]
"src/reports/*.py" = ["PLR0913", "PLR0912"]

# Compressor implementations may be complex
"src/compressors/**/*.py" = ["PLR0913", "PLR0912", "C901"]

[lint.isort]
# Import sorting configuration
known-first-party = ["src"]
known-local-folder = ["src"]
lines-after-imports = 2
split-on-trailing-comma = true
combine-as-imports = true

# Group imports: standard library, third-party, first-party, local
section-order = [
  "future",
  "standard-library",
  "third-party",
  "first-party",
  "local-folder",
]

[lint.pylint]
# Pylint-specific settings
max-args = 8        # Allow up to 8 arguments (data science functions)
max-branches = 15   # Allow more complex branching logic
max-returns = 8     # Allow multiple return points
max-statements = 60 # Allow longer functions for data processing

[lint.mccabe]
# Complexity checking
max-complexity = 12 # Allow moderately complex functions

[format]
# Formatting settings (compatible with Black)
quote-style = "double"
indent-style = "space"
line-ending = "auto"

# Format docstrings
docstring-code-format = true
docstring-code-line-length = 72

[lint.flake8-quotes]
# Consistent quote usage
inline-quotes = "double"
multiline-quotes = "double"

[lint.flake8-builtins]
# Allow some common builtin shadows in data science contexts
builtins-ignorelist = ["id", "input", "filter", "map"]

[lint.flake8-import-conventions]
# Standard import aliases
[lint.flake8-import-conventions.aliases]
"pandas" = "pd"
"numpy" = "np"
"matplotlib.pyplot" = "plt"
"seaborn" = "sns"

[lint.flake8-type-checking]
# Type checking imports
runtime-evaluated-base-classes = ["pydantic.BaseModel"]