.pre-commit-config.yaml

default_language_version:
  python: python3
# Skip the pre-commit check for below directories to have
# a consistency with the official tfrecord preprocessing scripts
exclude: "^(streaming/text/convert/enwiki/)"
repos:
  - repo: https://github.com/astral-sh/ruff-pre-commit
    # Ruff version.
    rev: v0.0.282
    hooks:
      - id: ruff
        args: [--fix, --exit-non-zero-on-fix]
  - repo: https://github.com/google/yapf
    rev: v0.32.0
    hooks:
      - id: yapf
        name: yapf
        description: "A formatter for Python files."
        entry: yapf
        args: [-i, -vv, -p]   # inplace
        language: python
        types: [python]
        additional_dependencies:
          - "toml"
  - repo: https://github.com/pycqa/isort
    hooks:
      - id: isort
    rev: 5.12.0
  - repo: https://github.com/pre-commit/pre-commit-hooks
    rev: v4.3.0
    hooks:
      - id: check-added-large-files
      - id: check-ast
      - id: check-builtin-literals
        args:
          - --no-allow-dict-kwargs
      - id: check-case-conflict
      - id: check-docstring-first
      - id: check-executables-have-shebangs
      - id: check-json
      - id: check-shebang-scripts-are-executable
      - id: pretty-format-json
        args:
          - --autofix
          - --no-sort-keys
          - --indent=4
      - id: check-merge-conflict
      - id: check-symlinks
      - id: check-toml
      - id: check-vcs-permalinks
      - id: check-xml
      - id: check-yaml
      - id: debug-statements
      - id: destroyed-symlinks
      - id: double-quote-string-fixer
      - id: end-of-file-fixer
      - id: fix-byte-order-marker
      - id: mixed-line-ending
      - id: trailing-whitespace
  - repo: https://github.com/Lucas-C/pre-commit-hooks
    rev: v1.3.1
    hooks:
      - id: insert-license
        args:
          - --license-filepath
          - .ci/FILE_HEADER
          - --comment-style
          - "#"
        types: [python]
  - repo: local
    hooks:
      - id: pyright
        name: pyright
        entry: pyright .
        language: node
        types: [python]
        pass_filenames: false
        args: [--warnings]
        additional_dependencies: ["pyright@1.1.256"]
  - repo: https://github.com/myint/docformatter
    rev: v1.5.0
    hooks:
      - id: docformatter
        args: [--in-place, --wrap-summaries=99, --wrap-descriptions=99]
        exclude: "(tests)"
  - repo: https://github.com/PyCQA/pydocstyle
    hooks:
      - id: pydocstyle
        name: pydocstyle
        entry: pydocstyle
        language: python
        types: [python]
        exclude: "(tests|.ci|.github)"
        additional_dependencies:
          - "toml"
    rev: 6.1.1
  - repo: https://github.com/adrienverge/yamllint.git
    rev: v1.28.0
    hooks:
      - id: yamllint
        name: yamllint
        description: This hook runs yamllint.
        entry: yamllint
        language: python
        types: [file, yaml]
  - repo: https://github.com/trufflesecurity/trufflehog.git
    rev: v3.40.0
    hooks:
      - id: trufflehog
        name: secret scan
        entry: trufflehog filesystem ./
        args:
          - --only-verified
          - --fail
          - --exclude-paths=./.github/secrets/exclude.yaml