Fix for inability to read some parquet files (issue #816) #218
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Test Data Processing libs and (Optionally) Push base DPK images | |
| on: | |
| workflow_dispatch: | |
| push: | |
| branches: | |
| - "dev" | |
| - "releases/**" | |
| tags: | |
| - "*" | |
| paths: | |
| # Note: the transform workflows are expected to trigger when data-processing-lib/** changes | |
| - ".make.*" | |
| - "data-processing-lib/**" | |
| - "!data-processing-lib/**.md" | |
| - "!data-processing-lib/**/doc/**" | |
| - "!data-processing-lib/**/.gitignore" | |
| pull_request: | |
| branches: | |
| - "dev" | |
| - "releases/**" | |
| paths: | |
| # Note: the transform workflows are expected to trigger when data-processing-lib/** changes | |
| - ".make.*" | |
| - "data-processing-lib/**" | |
| - "!data-processing-lib/**.md" | |
| - "!data-processing-lib/**/doc/**" | |
| - "!data-processing-lib/**/.gitignore" | |
| # taken from https://stackoverflow.com/questions/66335225/how-to-cancel-previous-runs-in-the-pr-when-you-push-new-commitsupdate-the-curre | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }} | |
| cancel-in-progress: true | |
| jobs: | |
| check_if_push_images: | |
| # check whether the Docker images should be pushed to the remote repository | |
| # The images are pushed if it is a merge to dev branch or a new tag is created. | |
| # The latter being part of the release process. | |
| # The images tag is derived from the value of the DOCKER_IMAGE_VERSION variable set in the .make.versions file. | |
| runs-on: ubuntu-22.04 | |
| outputs: | |
| publish_images: ${{ steps.version.outputs.publish_images }} | |
| steps: | |
| - id: version | |
| run: | | |
| publish_images='false' | |
| if [[ ${GITHUB_REF} == refs/heads/dev && ${GITHUB_EVENT_NAME} != 'pull_request' && ${GITHUB_REPOSITORY} == IBM/data-prep-kit ]] ; | |
| then | |
| publish_images='true' | |
| fi | |
| if [[ ${GITHUB_REF} == refs/tags/* && ${GITHUB_REPOSITORY} == IBM/data-prep-kit ]] ; | |
| then | |
| publish_images='true' | |
| fi | |
| echo "publish_images=$publish_images" >> "$GITHUB_OUTPUT" | |
| test-python-lib: | |
| runs-on: ubuntu-22.04 | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@v4 | |
| - name: Test data-processing-lib/python | |
| run: | | |
| make -C data-processing-lib/python DOCKER=docker venv test | |
| test-ray-lib: | |
| runs-on: ubuntu-22.04 | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@v4 | |
| - name: Test data-processing-lib/ray | |
| run: | | |
| make -C data-processing-lib/ray DOCKER=docker venv test | |
| test-spark-lib: | |
| runs-on: ubuntu-22.04 | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@v4 | |
| - name: Test data-processing-lib/spark | |
| run: | | |
| make -C data-processing-lib/spark DOCKER=docker venv test | |
| test-data-processing-lib-images: | |
| needs: [check_if_push_images] | |
| if: needs.check_if_push_images.outputs.publish_images == 'true' | |
| runs-on: ubuntu-22.04 | |
| env: | |
| DOCKER_REGISTRY_USER: ${{ secrets.DOCKER_REGISTRY_USER }} | |
| DOCKER_REGISTRY_KEY: ${{ secrets.DOCKER_REGISTRY_KEY }} | |
| timeout-minutes: 30 | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@v4 | |
| - name: Free up space in github runner | |
| # Free space as indicated here : https://github.com/actions/runner-images/issues/2840#issuecomment-790492173 | |
| run: | | |
| df -h | |
| sudo rm -rf "/usr/local/share/boost" | |
| sudo rm -rf "$AGENT_TOOLSDIRECTORY" | |
| sudo rm -rf /usr/share/dotnet /opt/ghc /usr/local/lib/android /usr/local/share/powershell /usr/share/swift /usr/lib/jvm /usr/local/.ghcup | |
| sudo docker rmi $(docker image ls -aq) >/dev/null 2>&1 || true | |
| df -h | |
| - name: Test Code Transform Images | |
| run: | | |
| make -C data-processing-lib/spark DOCKER=docker image | |
| - name: | |
| Print space | |
| # Free space as indicated here : https://github.com/actions/runner-images/issues/2840#issuecomment-790492173 | |
| run: | | |
| df -h | |
| docker images | |
| - name: Publish images | |
| if: needs.check_if_push_images.outputs.publish_images == 'true' | |
| run: | | |
| make -C data-processing-lib/spark publish-image |