Configure and run taplo in CI for formatting .toml

[dangotbanned]

Originally posted by @dangotbanned in #643 (comment)

I should've explained this better in the description for (1ea2812)

That commit uses automatic formatting via taplo.
The two non-default configuration options applied were:

align_entries=true

Align entries vertically. Entries that have table headers, comments, or blank lines between them are not aligned.

allowed_blank_lines=1

The maximum amount of consecutive blank lines allowed.

---

taplo can be used via its CLI and as a VSCode extension (Even Better TOML)

I haven't used it in CI before, but it is available on PyPI - so we could run it with uvx?
https://github.com/tamasfe/taplo/blob/a8bc571ee28775e7d5ad84c2ea87cf5b61ab42f5/.github/workflows/releases.yaml#L503-L504

NPM is another option for install

---

@domoritz

If we have a formatter, it should run on the ci as well.

[domoritz]

I haven't heard of it but sounds good. I'd recommend uvx since it's for python.

[dangotbanned]

I haven't heard of it but sounds good. I'd recommend uvx since it's for python.

Great, that sounds like something I can take a stab at

@domoritz would it be worth opening a separate issue for a pyproject.toml?

I've been using one locally for ruff & pyright e.g. (2b1be70), (fbd1be5), (5e779e6)
It would probably be easier to manage uv as a project, and naturally provides a home for other tool configs

Local pyproject.toml

Based on https://github.com/vega/altair/blob/9002472d65875a8486de920e4cc585420efdd276/pyproject.toml#L198-L447

[project]
name = "vega-datasets"
version = "0.1.0"
description = "Add your description here"
readme = "README.md"
requires-python = ">=3.12"
dependencies = [
    "frictionless[json,parquet]>=5.18.0",
    "niquests>=3.11.2",
    "polars>=1.17.1",
]

[dependency-groups]
dev = ["ruff>=0.8.2"]

[tool.ruff]
target-version = "py312"
extend-exclude = [
    "scripts/budget.py",
    "scripts/flights.py",
    "scripts/github.py",
    "scripts/make-unemployment-across-industries.py",
    "scripts/update_countries_json.py",
    "scripts/update_gapminder.py",
    "scripts/weather.py",
    ".venv",
    # TEMPORARY
    # "scripts/build_datapackage.py",
]

[tool.ruff.format]
preview                    = true
docstring-code-format      = true
docstring-code-line-length = 88

[tool.ruff.lint]
preview = true
extend-safe-fixes = [
    # unnecessary-comprehension-in-call
    "C419",
    # unnecessary-dict-comprehension-for-iterable
    "C420",
    # literal-membership
    "PLR6201",
    # unsorted-dunder-all
    "RUF022",
    # trailing-whitespace
    "W291",
    # blank line contains whitespace
    "W293",
    # annotations #
    # ----------- #
    "ANN204",
    "TC",
    "UP006",
    "UP008",
    # pydocstyle #
    # ---------- #
    # fits-on-one-line
    "D200",
    # escape-sequence-in-docstring
    "D301",
    # ends-in-period
    "D400",
    # assign exception msg to variable #
    # -------------------------------- #
    "EM101",
    "EM102",
]
extend-select = [
    # root-logger-call
    "LOG015",
    # refurb
    "FURB",
    # pylint (preview) autofix #
    # ------------------------ #
    # unnecessary-dunder-call 
    "PLC2801",
    # unnecessary-dict-index-lookup
    "PLR1733",
    # unnecessary-list-index-lookup
    "PLR1736",
    # literal-membership
    "PLR6201",
    # unspecified-encoding
    "PLW1514",
]
select = [
    # flake8-annotations
    "ANN",
    # flake8-bugbear
    "B",
    # flake8-comprehensions
    "C4",
    # complex-structure
    "C901",
    # pydocstyle
    "D",
    # multi-line-summary-second-line
    "D213",
    # pycodestyle-error
    "E",
    # flake8-errmsg
    "EM",
    # pyflakes
    "F",
    # flake8-future-annotations
    "FA",
    # flynt
    "FLY",
    # logging-f-string
    "G004",
    # unsorted-imports
    "I001",
    # flake8-logging
    "LOG",
    # flake8-pie
    "PIE",
    # pylint (Convention)
    "PLC",
    # flake8-use-pathlib
    "PTH",
    # unnecessary-type-union
    "PYI055",
    # unnecessary-assign
    "RET504",
    # superfluous-else-return
    "RET505",
    # Ruff-specific rules
    "RUF",
    # flake8-simplify
    "SIM",
    # flake8-type-checking
    "TC",
    # flake8-tidy-imports
    "TID",
    # pyupgrade
    "UP",
    # pycodestyle-warning
    "W",
    # pylint (stable) autofix #
    # ----------------------- #
    # manual-from-import
    "PLR0402",
    # useless-return
    "PLR1711",
    # repeated-equality-comparison
    "PLR1714",
    # collapsible-else-if
    "PLR5501",
    # useless-else-on-loop
    "PLW0120",
    # subprocess-run-without-check
    "PLW1510",
    # nested-min-max
    "PLW3301",
]
ignore = [
    # Whitespace before ':'
    "E203",
    # Line too long
    "E501",
    # mutable-class-default
    "RUF012",
    # pydocstyle/ https://docs.astral.sh/ruff/formatter/#conflicting-lint-rules #
    # ------------------------------------------------------------------------- #
    # undocumented-public-module
    "D100",
    # undocumented-public-class
    "D101",
    # undocumented-public-method  
    "D102",
    # undocumented-public-function  
    "D103",
    # undocumented-public-package   
    "D104",
    # undocumented-magic-method 
    "D105",
    # undocumented-public-init  
    "D107",
    # indent-with-spaces
    "D206",
    # multi-line-summary-first-line ((D213) is the opposite of this)
    "D212",
    # Imperative mood   
    "D401",
    # Blank line after last section 
    "D413",
    # doc-line-too-long
    "W505",
    # Any as annotation
    "ANN401",
]
pydocstyle = { convention = "numpy" }

[tool.ruff.lint.per-file-ignores]
"*/**/*.ipynb" = ["ANN", "F401", "W391"]
"*.ipynb"      = ["ANN", "F401", "W391"]

[tool.ruff.lint.isort]
extra-standard-library  = ["typing_extensions"]
split-on-trailing-comma = false

[tool.pyright]
enableExperimentalFeatures = true
include                    = ["./scripts/build_datapackage.py", "./scripts/flights2.py"]
ignore                     = [".venv", "../../../**/Lib"]
pythonPlatform             = "All"
pythonVersion              = "3.12"
reportUnusedExpression     = "none"
typeCheckingMode           = "basic"