.pre-commit-config.yaml

repos:
  - repo: https://github.com/pre-commit/pre-commit-hooks
    rev: v4.4.0
    hooks:
      - id: check-yaml
        args:
          - --unsafe
      - id: check-json
      - id: end-of-file-fixer
      - id: trailing-whitespace
      - id: check-merge-conflict
      - id: detect-aws-credentials
        args: [--allow-missing-credentials]
  - repo: https://github.com/charliermarsh/ruff-pre-commit
    rev: v0.1.6
    hooks:
      - id: ruff
        args: [--show-source, --fix]
      - id: ruff-format
  - repo: https://github.com/codespell-project/codespell
    rev: v2.2.4
    hooks:
      - id: codespell
        types_or: [rst, markdown]
        files: docs
  - repo: https://github.com/pre-commit/mirrors-mypy
    rev: v1.1.1
    hooks:
      - id: mypy
        args: [--warn-unused-configs]
        additional_dependencies:
          # Type stubs
          - pandas-stubs==v1.5.3.230321
          - types-requests
          - numpy
  - repo: https://github.com/pre-commit/mirrors-prettier
    rev: v2.7.1
    hooks:
      - id: prettier
        types: [yaml]
  - repo: https://github.com/adrienverge/yamllint.git
    rev: v1.28.0
    hooks:
      - id: yamllint
        args: []
  - repo: local
    hooks:
      - name: Dbt deps
        id: dbt-deps
        language: system
        entry: poetry run dbt deps --project-dir transform
        always_run: false
        pass_filenames: false
        types: [sql]
  # Note: for SQLFluff we don't use the default pre-commit hook for a few reasons:
  #   1. dbt cloud looks for config in the dbt project directory, so we put it in
  #      transform/, however sqlfluff requires the templater config to be in the
  #      current working directory. So we have to cd to transform/ to properly set the
  #      templater config.
  #   2. Some machines (such as ODI Macs) seem to struggle with sqlfluff's
  #      multiprocessing implementation, so we force it to be single-process.
  #   3. The pre-commit managed python environment can be difficult to install,
  #      especially due to issues with pyarrow being brought in by Snowflake.
  #      This keep things more predictable by using the poetry.lock environment.
  - repo: local
    hooks:
      - id: sqlfluff
        name: sqlfluff
        language: system
        description: "Lints sql files with `SQLFluff`"
        types: [sql]
        require_serial: true
        entry: >
          poetry run python -c "import os, subprocess; os.chdir('transform');
          subprocess.run(['sqlfluff', 'fix', '--force', '--processes', '1',
          '--nocolor', '--show-lint-violations', '--disable-progress-bar'],
          check=True, )"