minimum_pre_commit_version: 2.15.0

exclude: ^LICENSES/|\.(html|csv|svg)$

# reserve "manual" for relatively slow hooks which we still want to run in CI

default_stages: [

commit,

merge-commit,

push,

prepare-commit-msg,

commit-msg,

post-checkout,

post-commit,

post-merge,

post-rewrite

]

ci:

autofix_prs: false

autoupdate_schedule: monthly

# manual stage hooks

skip: [pyright, mypy]

repos:

- repo: https://github.com/astral-sh/ruff-pre-commit

rev: v0.5.0

hooks:

- id: ruff

args: [--exit-non-zero-on-fix]

- id: ruff

# TODO: remove autofixe-only rules when they are checked by ruff

name: ruff-selected-autofixes

alias: ruff-selected-autofixes

files: ^pandas

exclude: ^pandas/tests

args: [--select, "ANN001,ANN2", --fix-only, --exit-non-zero-on-fix]

- id: ruff-format

exclude: ^scripts

- repo: https://github.com/jendrikseipp/vulture

rev: 'v2.11'

hooks:

- id: vulture

entry: python scripts/run_vulture.py

pass_filenames: true

require_serial: false

- repo: https://github.com/codespell-project/codespell

rev: v2.3.0

hooks:

- id: codespell

types_or: [python, rst, markdown, cython, c]

additional_dependencies: [tomli]

- repo: https://github.com/MarcoGorelli/cython-lint

rev: v0.16.2

hooks:

- id: cython-lint

- id: double-quote-cython-strings

- repo: https://github.com/pre-commit/pre-commit-hooks

rev: v4.6.0

hooks:

- id: check-case-conflict

- id: check-toml

- id: check-xml

- id: check-yaml

exclude: ^ci/meta.yaml$

- id: end-of-file-fixer

exclude: \.txt$

- id: mixed-line-ending

args: [--fix=auto]

exclude: ^pandas/tests/io/parser/data/utf16_ex.txt$

- id: fix-byte-order-marker

- id: fix-encoding-pragma

args: [--remove]

- id: trailing-whitespace

args: [--markdown-linebreak-ext=md]

- repo: https://github.com/PyCQA/isort

rev: 5.13.2

hooks:

- id: isort

- repo: https://github.com/asottile/pyupgrade

rev: v3.16.0

hooks:

- id: pyupgrade

args: [--py310-plus]

- repo: https://github.com/pre-commit/pygrep-hooks

rev: v1.10.0

hooks:

- id: rst-backticks

- id: rst-directive-colons

types: [text] # overwrite types: [rst]

types_or: [python, rst]

- id: rst-inline-touching-normal

types: [text] # overwrite types: [rst]

types_or: [python, rst]

- repo: https://github.com/sphinx-contrib/sphinx-lint

rev: v0.9.1

hooks:

- id: sphinx-lint

args: ["--enable", "all", "--disable", "line-too-long"]

- repo: https://github.com/pre-commit/mirrors-clang-format

rev: v18.1.8

hooks:

- id: clang-format

files: ^pandas/_libs/src|^pandas/_libs/include

args: [-i]

types_or: [c, c++]

- repo: local

hooks:

- id: pyright

# note: assumes python env is setup and activated

name: pyright

entry: pyright

language: node

pass_filenames: false

types: [python]

stages: [manual]

additional_dependencies: &pyright_dependencies

- pyright@1.1.352

- id: pyright

# note: assumes python env is setup and activated

name: pyright reportGeneralTypeIssues

entry: pyright -p pyright_reportGeneralTypeIssues.json --level warning

language: node

pass_filenames: false

types: [python]

stages: [manual]

additional_dependencies: *pyright_dependencies

- id: mypy

# note: assumes python env is setup and activated

name: mypy

entry: mypy

language: system

pass_filenames: false

types: [python]

stages: [manual]

- id: mypy

# note: assumes python env is setup and activated

# note: requires pandas dev to be installed

name: mypy (stubtest)

entry: python

language: system

pass_filenames: false

types: [pyi]

args: [scripts/run_stubtest.py]

stages: [manual]

- id: inconsistent-namespace-usage

name: 'Check for inconsistent use of pandas namespace'

entry: python scripts/check_for_inconsistent_pandas_namespace.py

exclude: ^pandas/core/interchange/

language: python

types: [python]

- id: unwanted-patterns

name: Unwanted patterns

language: pygrep

entry: |

(?x)

# outdated annotation syntax

\#\ type:\ (?!ignore)

# foo._class__ instead of type(foo)

|\.__class__

# Numpy

|from\ numpy\ import\ random

|from\ numpy\.random\ import

# Incorrect code-block / IPython directives

|\.\.\ code-block\ ::

|\.\.\ ipython\ ::

# directive should not have a space before ::

|\.\.\ \w+\ ::

# Check for deprecated messages without sphinx directive

|(DEPRECATED|DEPRECATE|Deprecated)(:|,|\.)

# builtin filter function

|(?<!def)[\(\s]filter\(

types_or: [python, cython, rst]

exclude: ^doc/source/development/code_style\.rst # contains examples of patterns to avoid

- id: incorrect-backticks

name: Check for backticks incorrectly rendering because of missing spaces

language: pygrep

entry: '[a-zA-Z0-9]\`\`?[a-zA-Z0-9]'

types: [rst]

files: ^doc/source/

- id: seed-check-asv

name: Check for unnecessary random seeds in asv benchmarks

language: pygrep

entry: 'np\.random\.seed'

files: ^asv_bench/benchmarks

exclude: ^asv_bench/benchmarks/pandas_vb_common\.py

- id: unwanted-patterns-in-tests

name: Unwanted patterns in tests

language: pygrep

entry: |

(?x)

# imports from pandas._testing instead of `import pandas._testing as tm`

from\ pandas\._testing\ import

|from\ pandas\ import\ _testing\ as\ tm

# pandas.testing instead of tm

|pd\.testing\.

# pd.api.types instead of from pandas.api.types import ...

|(pd|pandas)\.api\.types\.

# np.array_equal

|(numpy|np)\.array_equal

# pytest raises without context

|\s\ pytest.raises

# Unseeded numpy default_rng

|default_rng\(\)

files: ^pandas/tests/

types_or: [python, cython, rst]

- id: unwanted-patterns-in-cython

name: Unwanted patterns in Cython code

language: pygrep

entry: |

(?x)

# `<type>obj` as opposed to `<type> obj`

[a-zA-Z0-9*]>[ ]

types: [cython]

- id: pip-to-conda

name: Generate pip dependency from conda

language: python

entry: python scripts/generate_pip_deps_from_conda.py

files: ^(environment.yml|requirements-dev.txt)$

pass_filenames: false

additional_dependencies: [tomli, pyyaml]

- id: title-capitalization

name: Validate correct capitalization among titles in documentation

entry: python scripts/validate_rst_title_capitalization.py

language: python

types: [rst]

files: ^doc/source/(development|reference)/

- id: unwanted-patterns-private-function-across-module

name: Check for use of private functions across modules

language: python

entry: python scripts/validate_unwanted_patterns.py --validation-type="private_function_across_module"

types: [python]

exclude: ^(asv_bench|pandas/tests|doc)/

- id: unwanted-patterns-private-import-across-module

name: Check for import of private attributes across modules

language: python

entry: python scripts/validate_unwanted_patterns.py --validation-type="private_import_across_module"

types: [python]

exclude: |

(?x)

^(asv_bench|pandas/tests|doc)/

|scripts/validate_min_versions_in_sync\.py$

- id: unwanted-patterns-strings-with-misplaced-whitespace

name: Check for strings with misplaced spaces

language: python

entry: python scripts/validate_unwanted_patterns.py --validation-type="strings_with_wrong_placed_whitespace"

types_or: [python, cython]

- id: unwanted-patterns-nodefault-used-not-only-for-typing

name: Check that `pandas._libs.lib.NoDefault` is used only for typing

language: python

entry: python scripts/validate_unwanted_patterns.py --validation-type="nodefault_used_not_only_for_typing"

types: [python]

- id: no-return-exception

name: Use raise instead of return for exceptions

language: pygrep

entry: 'return [A-Za-z]+(Error|Exit|Interrupt|Exception|Iteration)'

files: ^pandas/

types: [python]

exclude: ^pandas/tests/

- id: pandas-errors-documented

name: Ensure pandas errors are documented in doc/source/reference/testing.rst

entry: python scripts/pandas_errors_documented.py

language: python

files: ^pandas/errors/__init__.py$

- id: pg8000-not-installed-CI

name: Check for pg8000 not installed on CI for test_pg8000_sqlalchemy_passthrough_error

language: pygrep

entry: 'pg8000'

files: ^ci/deps

types: [yaml]

- id: validate-min-versions-in-sync

name: Check minimum version of dependencies are aligned

entry: python -m scripts.validate_min_versions_in_sync

language: python

files: ^(ci/deps/actions-.*-minimum_versions\.yaml|pandas/compat/_optional\.py)$

additional_dependencies: [tomli, pyyaml]

pass_filenames: false

- id: validate-errors-locations

name: Validate errors locations

description: Validate errors are in appropriate locations.

entry: python scripts/validate_exception_location.py

language: python

files: ^pandas/

exclude: ^(pandas/_libs/|pandas/tests/|pandas/errors/__init__.py$|pandas/_version.py)

types: [python]

- id: check-test-naming

name: check that test names start with 'test'

entry: python -m scripts.check_test_naming

types: [python]

files: ^pandas/tests

language: python

- id: sort-whatsnew-items

name: sort whatsnew entries alphabetically

entry: python -m scripts.sort_whatsnew_note

types: [rst]

language: python

files: ^doc/source/whatsnew/v

exclude: ^doc/source/whatsnew/v(0|1|2\.0\.0)