sqlfluff-lint-bash-changed-files.yml

# Original source: https://github.com/sqlfluff/sqlfluff-github-actions/blob/main/menu_of_workflows/surfline/sqlfluff_lint_dbt_models.yml
name: SQLFluff lint dbt data models

on:
  push:
    branches:
    - main
  pull_request:
    branches:
    - main

jobs:
  sqlfluff-lint-models:
    name: Lint dbt models using SQLFluff
    runs-on: ${{ matrix.os }}
    strategy:
      fail-fast: false
      matrix:
        os: ['ubuntu-latest']
        python-version: ['3.12']

    steps:
      - name: Checkout branch
        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
        with:
          fetch-depth: 0 

      - name: Setup Python
        uses: actions/setup-python@42375524e23c412d93fb67b49958b491fce71c38 # v5.4.0
        with:
          python-version: ${{ matrix.python-version }}
          cache: 'pip'

      - name: Install Python packages or restore cache
        run: pip install -r requirements.txt

      - name: Get all changed model SQL files
        id: changed-files-models
        run: |
          # Define array of files to exclude
          EXCLUDE_FILES=(
            "models/utils/date_spine.sql"
          )
          # Define include pattern for SQL files
          INCLUDE_PATTERN="models/.*\.sql$"

          if [ "${{ github.event_name }}" == "pull_request" ]; then
            # For pull requests, compare with the base branch
            git fetch origin ${{ github.base_ref }}
            CHANGED_FILES=$(git diff --name-only origin/${{ github.base_ref }}..HEAD | grep -E "$INCLUDE_PATTERN" || true)
          else
            # For pushes, compare with the previous commit
            CHANGED_FILES=$(git diff --name-only HEAD^ HEAD | grep -E "$INCLUDE_PATTERN" || true)
          fi

          # Filter out excluded files
          for EXCLUDE_FILE in "${EXCLUDE_FILES[@]}"; do
            CHANGED_FILES=$(echo "$CHANGED_FILES" | grep -v "$EXCLUDE_FILE" || true)
          done

          # Set outputs
          echo "all_changed_files=${CHANGED_FILES}" >> $GITHUB_OUTPUT
          if [ -n "$CHANGED_FILES" ]; then
            echo "any_changed=true" >> $GITHUB_OUTPUT
          else
            echo "any_changed=false" >> $GITHUB_OUTPUT
          fi

      - name: Lint dbt models
        if: steps.changed-files-models.outputs.any_changed == 'true'
        shell: bash -l {0}
        run: |
          sqlfluff lint --format github-annotation-native --annotation-level failure ${{ steps.changed-files-models.outputs.all_changed_files }}