test-language-pdf2parquet.yml

#
# DO NOT EDIT THIS FILE: it is generated from test-transform.template,  Edit there and run make to change these files
#
name: Test - transforms/language/pdf2parquet

on:
    workflow_dispatch:
    push:
        branches:
            - "dev"
            - "releases/**"
        tags:
            - "*"
        paths:
            - "transforms/language/pdf2parquet/**"
            - "data-processing-lib/**"
            - "!transforms/language/pdf2parquet/**/kfp_ray/**" # This is/will be tested in separate workflow
            - "!data-processing-lib/**/test/**"
            - "!data-processing-lib/**/test-data/**"
            - "!**.md"
            - "!**/doc/**"
            - "!**/images/**"
            - "!**.gitignore"
    pull_request:
        branches:
            - "dev"
            - "releases/**"
        paths:
            - "transforms/language/pdf2parquet/**"
            - "data-processing-lib/**"
            - "!transforms/language/pdf2parquet/**/kfp_ray/**" # This is/will be tested in separate workflow
            - "!data-processing-lib/**/test/**"
            - "!data-processing-lib/**/test-data/**"
            - "!**.md"
            - "!**/doc/**"
            - "!**/images/**"
            - "!**.gitignore"

jobs:
    check_if_push_image:
        # 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" >> "$GITHUB_OUTPUT"
    test-src:
        runs-on: ubuntu-22.04
        steps:
            - name: Checkout
              uses: actions/checkout@v4
            - name: Free up space in github runner
              # Free space as indicated here : https://github.com/actions/runner-images/issues/2840#issuecomment-790492173
              run: |
                  df -h
                  sudo rm -rf "/usr/local/share/boost"
                  sudo rm -rf "$AGENT_TOOLSDIRECTORY"
                  sudo rm -rf /usr/share/dotnet /opt/ghc /usr/local/lib/android /usr/local/share/powershell /usr/share/swift /usr/local/.ghcup
                  sudo docker rmi $(docker image ls -aq) >/dev/null 2>&1 || true
                  df -h
            - name: Test transform source in transforms/language/pdf2parquet
              run: |
                  if [ -e "transforms/language/pdf2parquet/Makefile" ]; then
                      make -C transforms/language/pdf2parquet DOCKER=docker test-src
                  else
                      echo "transforms/language/pdf2parquet/Makefile not found - source testing disabled for this transform."
                  fi
    test-image:
        needs: [check_if_push_image]
        runs-on: ubuntu-22.04
        timeout-minutes: 120
        env:
            DOCKER_REGISTRY_USER: ${{ secrets.DOCKER_REGISTRY_USER }}
            DOCKER_REGISTRY_KEY: ${{ secrets.DOCKER_REGISTRY_KEY }}
        steps:
            - name: Checkout
              uses: actions/checkout@v4
            - name: Free up space in github runner
              # Free space as indicated here : https://github.com/actions/runner-images/issues/2840#issuecomment-790492173
              run: |
                  df -h
                  sudo rm -rf /opt/ghc
                  sudo rm -rf "/usr/local/share/boost"
                  sudo rm -rf "$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 transform image in transforms/language/pdf2parquet
              run: |
                  if [ -e "transforms/language/pdf2parquet/Makefile" ]; then
                      if [ -d "transforms/language/pdf2parquet/spark" ]; then
                          make -C data-processing-lib/spark DOCKER=docker image
                      fi
                      make -C transforms/language/pdf2parquet DOCKER=docker test-image
                  else
                      echo "transforms/language/pdf2parquet/Makefile not found - testing disabled for this transform."
                  fi
            - 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_image.outputs.publish_images == 'true'
              run: |
                  if [ -e "transforms/language/pdf2parquet/Makefile" ]; then
                      make -C transforms/language/pdf2parquet publish
                  else
                      echo "transforms/language/pdf2parquet/Makefile not found - publishing disabled for this transform."
                  fi