test_and_publish.yml

name: Test & Publish

on:
  push:
    branches: 
      - master
      - develop
    paths-ignore:
      - "docs/**"
  pull_request:
    branches:
      - master
      - develop
    paths-ignore:
      - "docs/**"
jobs:
  unit_tests:
    runs-on: ubuntu-latest
    strategy:
      matrix:
        python-version: [ '3.8', '3.9', '3.10']

    steps:
    - uses: actions/checkout@v4
    
    - name: Setup python ${{ matrix.python-version }}
      uses: actions/setup-python@v4.7.1
      with:
        python-version: ${{ matrix.python-version }}

    - name: Setup poetry
      run: |
        python -V
        python -m pip install poetry

    - name: Check pre-commit status
      run: |
        poetry install -v
        poetry run pre-commit run --all-files -c .github/pre-commit-config.yaml

    - name: Test with tox
      run: |
        pip install tox-pip-version tox-gh-actions "tox<4.0.0"
        tox -v

    - name: Store coverage reports
      uses: actions/upload-artifact@v3
      with:
        name: coverage-${{ matrix.python-version }}
        path: coverage.xml
        if-no-files-found: error

  sonarcloud:
    runs-on: ubuntu-latest
    needs: unit_tests
    steps:

    - uses: actions/checkout@v4
      with:
        fetch-depth: 0

    - uses: actions/download-artifact@v3
      with:
        name: coverage-3.9
        path: .

    - name: SonarCloud Scan
      uses: sonarsource/sonarcloud-github-action@master
      with:
        projectBaseDir: ${{ github.workspace }}
      env:
        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        SONAR_TOKEN: ${{ secrets.SONARCLOUD_TOKEN }}

  codeql:
    runs-on: ubuntu-latest
    needs: unit_tests
    permissions:
      actions: read
      contents: read
      security-events: write

    steps:
      - name: Checkout repository
        uses: actions/checkout@v4

      # Initializes the CodeQL tools for scanning.
      - name: Initialize CodeQL
        uses: github/codeql-action/init@v2
        with:
          languages: python

      - name: Autobuild
        uses: github/codeql-action/autobuild@v2

      - name: Perform CodeQL Analysis
        uses: github/codeql-action/analyze@v2

  e2e_tests:
    runs-on: ubuntu-latest
    timeout-minutes: 60
    needs: [unit_tests, sonarcloud]
    strategy:
      matrix:
        e2e_case: ["standard", "grouping"]
    steps:
      - uses: actions/checkout@v4

      - name: Setup python
        uses: actions/setup-python@v4.7.1
        with:
          python-version: 3.8

      - name: Setup poetry
        run: |
          python -V
          python -m pip install poetry

      - name: Build the package
        run: |
          poetry build -f sdist

      - name: Initialize kedro spaceflights project
        # kedro 0.18.1 is on purpose here, due to https://github.com/kedro-org/kedro-starters/issues/99
        run: |
          pip install $(find "./dist" -name "*.tar.gz")
          kedro new --starter spaceflights --config tests/e2e/${{ matrix.e2e_case }}/starter-config.yml --verbose

      - name: Install project dependencies
        working-directory: ./spaceflights
        run: |
          find "../dist" -name "*.tar.gz" | xargs -I@ cp @ kedro-vertexai.tar.gz
          echo -e "\n./kedro-vertexai.tar.gz\n" >> src/requirements.txt
          echo -e "kedro-docker\n" >> src/requirements.txt
          sed -i '/kedro-telemetry/d' src/requirements.txt
          echo $(cat src/requirements.txt)
          pip install -r src/requirements.txt

      - name: Init and update configuration
        working-directory: ./spaceflights
        run: |
          kedro docker init
          sed -i 's/\(COPY src\/requirements.txt.*\)$/\1\nCOPY kedro-vertexai.tar.gz ./g' Dockerfile
          echo "!data/01_raw" >> .dockerignore
          kedro vertexai init gid-ml-ops-sandbox europe-west4
          cp ../tests/e2e/${{ matrix.e2e_case }}/catalog.yml conf/base/catalog.yml
          cp ../tests/e2e/${{ matrix.e2e_case }}/vertexai.yml conf/base/vertexai.yml
          # Introducing tagging to pipelines
          if [[ "${{ matrix.e2e_case }}" == "grouping" ]]; then
            mv ../tests/e2e/${{ matrix.e2e_case }}/pipeline_data_processing.py src/spaceflights/pipelines/data_processing/pipeline.py
            mv ../tests/e2e/${{ matrix.e2e_case }}/pipeline_data_science.py src/spaceflights/pipelines/data_science/pipeline.py
          fi

      - name: Prepare docker env
        uses: docker/setup-buildx-action@v3
        id: buildx
        with:
          install: true

      - name: Build pipeline docker image
        run: |
          cd ./spaceflights
          docker pull gcr.io/gid-ml-ops-sandbox/kedro-vertexai-e2e:${{ matrix.e2e_case }} || true
          docker build --build-arg BASE_IMAGE=python:3.8-buster --tag kedro-vertexai-e2e:${{ matrix.e2e_case }} --load --cache-from=gcr.io/gid-ml-ops-sandbox/kedro-vertexai-e2e:${{ matrix.e2e_case }} .

      - name: Publish docker image to GCR
        uses: mattes/gce-docker-push-action@v1
        with:
          creds: ${{ secrets.GOOGLE_APPLICATION_CREDENTIALS }}
          src: kedro-vertexai-e2e:${{ matrix.e2e_case }}
          dst: gcr.io/gid-ml-ops-sandbox/kedro-vertexai-e2e:${{ matrix.e2e_case }}

      - name: Set up GCP Credentials
        uses: google-github-actions/auth@v1.1.1
        with:
          credentials_json: ${{ secrets.GOOGLE_APPLICATION_CREDENTIALS }}
          create_credentials_file: true
          cleanup_credentials: true

      - name: Run project on vertex pipeline
        run: |
          cd ./spaceflights
          export KEDRO_CONFIG_COMMIT_ID=$GITHUB_SHA
          kedro vertexai run-once --wait-for-completion

  publish:
    if: github.event.pull_request == null && github.ref == 'refs/heads/master'
    needs: [ e2e_tests, codeql ]
    runs-on: ubuntu-latest
    env:
      PYTHON_PACKAGE: kedro_vertexai
    steps:
      - name: Checkout the repo
        uses: actions/checkout@v4
        with:
          fetch-depth: 0  # necessary to enable merging, all the history is needed
      - name: Set up Python 3.8
        uses: actions/setup-python@v4.7.1
        with:
          python-version: "3.8"
      - name: Build package dist from source # A better way will be : https://packaging.python.org/guides/publishing-package-distribution-releases-using-github-actions-ci-cd-workflows/ but pep 517 is still marked as experimental
        run: |
          pip install poetry
          poetry build
      - name:  Merge back to develop  # we have to set the config first on a fresh machine
        run: |
          git config user.name github-actions
          git config user.email github-actions@github.com
          git checkout -b develop --track origin/develop
          git merge master
          git push
      - name: Set dynamically package version as output variable # see https://github.com/actions/create-release/issues/39
        # see https://docs.github.com/en/free-pro-team@latest/actions/reference/workflow-commands-for-github-actions#setting-an-environment-variable
        id: set_package_version
        run: |
          echo "::set-output name=PACKAGE_VERSION::$(cat $PYTHON_PACKAGE/__init__.py | grep -Po  '\d+\.\d+\.\d+')"
      - name: Create temporary file with the body content for the release
        run: |
          grep -Poz "## \[${{steps.set_package_version.outputs.PACKAGE_VERSION}}] - \d{4}-\d{2}-\d{2}[\S\s]+?(?=## \[\d+\.\d+\.\d+\]|\[.+\]:)" CHANGELOG.md > release_body.md
      - name: Create Release # https://github.com/actions/create-release
        id: create_release
        uses: actions/create-release@v1.1.4
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # This token is provided by Actions, you do not need to create your own token
        with:
          tag_name: ${{ steps.set_package_version.outputs.PACKAGE_VERSION }}
          release_name: Release ${{ steps.set_package_version.outputs.PACKAGE_VERSION }}
          body_path: ./release_body.md
          draft: false
          prerelease: false
      - name: Rollback Release in case of run failure
        if: failure() && steps.create_release.outputs.id != ''
        uses: author/action-rollback@stable
        with:
          # Using a known release ID
          release_id: ${{ steps.create_release.outputs.id }}
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
      - name: Publish distribution to PyPI  # official action from python maintainers
        uses: pypa/gh-action-pypi-publish@master
        with:
          user: __token__
          password: ${{ secrets.PYPI_PASSWORD }}
          verbose: true  # trace if the upload fails