Kfp workflow for html2parquet #173
Workflow file for this run
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/build KFP | |
| on: | |
| workflow_dispatch: | |
| push: | |
| branches: | |
| - "dev" | |
| - "releases/**" | |
| tags: | |
| - "*" | |
| paths: | |
| - ".make.*" | |
| - "kfp/**" | |
| - "!kfp/**.md" | |
| - "!kfp/**/test/**" | |
| - "!kfp/**/doc/**" | |
| - "data-processing-lib/**" | |
| - "!data-processing-lib/**.md" | |
| - "!data-processing-lib/**/.gitignore" | |
| - "!data-processing-lib/**/test/**" | |
| - "!data-processing-lib/**/test-data/**" | |
| - "!**.md" | |
| - "!**/doc/**" | |
| - "!**/images/**" | |
| - "!**/.gitignore" | |
| pull_request: | |
| branches: | |
| - "dev" | |
| - "releases/**" | |
| paths: | |
| - ".make.*" | |
| - "kfp/**" | |
| - "!kfp/**/test/**" | |
| - "!kfp/**.md" | |
| - "!kfp/**/doc/**" | |
| - "data-processing-lib/**" | |
| - "!data-processing-lib/**/test/**" | |
| - "!data-processing-lib/**/test-data/**" | |
| - "!data-processing-lib/**.md" | |
| - "!data-processing-lib/**/doc/**" | |
| - "!data-processing-lib/**/.gitignore" | |
| - "!**.md" | |
| - "!**/doc/**" | |
| - "!**/images/**" | |
| - "!**/.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 | |
| env: | |
| KFP_BLACK_LIST: "doc_chunk-ray,pdf2parquet-ray,pii_redactor" | |
| 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" >> "$GITHUB_OUTPUT" | |
| test-kfp-v1: | |
| runs-on: ubuntu-22.04 | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@v4 | |
| - name: Free up space in github runner | |
| # Free space as indicated here : https://github.com/actions/runner-images/issues/2840#issuecomment-790492173 | |
| run: | | |
| df -h | |
| sudo rm -rf "/usr/local/share/boost" | |
| sudo rm -rf "$AGENT_TOOLSDIRECTORY" | |
| sudo rm -rf /usr/share/dotnet /opt/ghc /usr/local/lib/android /usr/local/share/powershell /usr/share/swift /usr/lib/jvm /usr/local/.ghcup | |
| sudo docker rmi $(docker image ls -aq) >/dev/null 2>&1 || true | |
| df -h | |
| - name: Test KFP libs (shared and v1) and run a workflow | |
| timeout-minutes: 120 | |
| run: | | |
| export REPOROOT=$PWD | |
| export K8S_SETUP_SCRIPTS=$PWD/scripts/k8s-setup | |
| source $K8S_SETUP_SCRIPTS/requirements.env | |
| export PATH=$PATH:/tmp/ | |
| curl -Lo /tmp/kind https://kind.sigs.k8s.io/dl/v${KIND_VERSION}/kind-linux-amd64 | |
| chmod 777 /tmp/kind | |
| curl -fsSL -o /tmp/get_helm.sh https://raw.githubusercontent.com/helm/helm/master/scripts/get-helm-3 | |
| chmod 700 /tmp/get_helm.sh | |
| HELM_INSTALL_DIR=/tmp/ /tmp/get_helm.sh -v v${HELM_VERSION} --no-sudo | |
| chmod 777 /tmp/helm | |
| curl -L https://dl.k8s.io/release/v${KUBECTL_VERSION}/bin/linux/amd64/kubectl -o /tmp/kubectl | |
| chmod 777 /tmp/kubectl | |
| curl https://dl.min.io/client/mc/release/linux-amd64/mc --create-dirs -o /tmp/mc | |
| chmod +x /tmp/mc | |
| export DEPLOY_KUBEFLOW=1 | |
| make -C $K8S_SETUP_SCRIPTS setup | |
| make -C kfp/kfp_support_lib test | |
| source $K8S_SETUP_SCRIPTS/common.sh | |
| while : | |
| do | |
| dir=("code" "universal" "language") && index=$(($RANDOM % ${#dir[@]})) && subdirs=${dir[$index]} && transforms=($(find transforms/$subdirs -type d -maxdepth 1 -mindepth 1 )) | |
| set -- "${transforms[@]}" && transforms=("$@") && size=${#transforms[@]} && index=$(($RANDOM % $size)) | |
| transform=$(basename "${transforms[$index]}") | |
| if [ -d ${transforms[$index]}/kfp_ray ] && echo ${KFP_BLACK_LIST} | grep -qv ${transform} ; then | |
| header_text "Running ${transforms[$index]} workflow test" | |
| break | |
| fi | |
| done | |
| make -C ${transforms[$index]} workflow-build | |
| make -C ${transforms[$index]} workflow-test | |
| echo "Run ${transforms[$index]} completed" | |
| test-kfp-v2: | |
| 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/lib/jvm /usr/local/.ghcup | |
| sudo docker rmi $(docker image ls -aq) >/dev/null 2>&1 || true | |
| df -h | |
| - name: Test KFP libs (shared and v2) and run a workflow | |
| timeout-minutes: 120 | |
| run: | | |
| export REPOROOT=$PWD | |
| export K8S_SETUP_SCRIPTS=$PWD/scripts/k8s-setup | |
| source $K8S_SETUP_SCRIPTS/requirements.env | |
| export PATH=$PATH:/tmp/ | |
| curl -Lo /tmp/kind https://kind.sigs.k8s.io/dl/v${KIND_VERSION}/kind-linux-amd64 | |
| chmod 777 /tmp/kind | |
| curl -fsSL -o /tmp/get_helm.sh https://raw.githubusercontent.com/helm/helm/master/scripts/get-helm-3 | |
| chmod 700 /tmp/get_helm.sh | |
| HELM_INSTALL_DIR=/tmp/ /tmp/get_helm.sh -v v${HELM_VERSION} --no-sudo | |
| chmod 777 /tmp/helm | |
| curl -L https://dl.k8s.io/release/v${KUBECTL_VERSION}/bin/linux/amd64/kubectl -o /tmp/kubectl | |
| chmod 777 /tmp/kubectl | |
| curl https://dl.min.io/client/mc/release/linux-amd64/mc --create-dirs -o /tmp/mc | |
| chmod +x /tmp/mc | |
| export DEPLOY_KUBEFLOW=1 | |
| export KFPv2=1 | |
| make -C $K8S_SETUP_SCRIPTS setup | |
| make -C kfp/kfp_support_lib test | |
| source $K8S_SETUP_SCRIPTS/common.sh | |
| while : | |
| do | |
| dir=("code" "universal" "language") && index=$(($RANDOM % ${#dir[@]})) && subdirs=${dir[$index]} && transforms=($(find transforms/$subdirs -type d -maxdepth 1 -mindepth 1 )) | |
| set -- "${transforms[@]}" && transforms=("$@") && size=${#transforms[@]} && index=$(($RANDOM % $size)) | |
| transform=$(basename "${transforms[$index]}") | |
| if [ -d ${transforms[$index]}/kfp_ray ] && echo ${KFP_BLACK_LIST} | grep -qv ${transform} ; then | |
| header_text "Running ${transforms[$index]} workflow test" | |
| break | |
| fi | |
| done | |
| make -C ${transforms[$index]} workflow-build | |
| make -C ${transforms[$index]} workflow-test | |
| header_text "Run ${transforms[$index]} completed" | |
| build-kfp-components: | |
| needs: [check_if_push_images] | |
| runs-on: ubuntu-22.04 | |
| timeout-minutes: 30 | |
| env: | |
| DOCKER_REGISTRY_USER: ${{ secrets.DOCKER_REGISTRY_USER }} | |
| DOCKER_REGISTRY_KEY: ${{ secrets.DOCKER_REGISTRY_KEY }} | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@v4 | |
| - name: Free up space in github runner | |
| # Free space as indicated here : https://github.com/actions/runner-images/issues/2840#issuecomment-790492173 | |
| run: | | |
| df -h | |
| sudo rm -rf "/usr/local/share/boost" | |
| sudo rm -rf "$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: Build | |
| run: | | |
| make -C kfp/kfp_ray_components DOCKER=docker image | |
| make KFPv2=1 -C kfp/kfp_ray_components DOCKER=docker image | |
| - name: Publish images | |
| if: needs.check_if_push_images.outputs.publish_images == 'true' | |
| run: make -C kfp/kfp_ray_components publish |