add Spark 3.5 on JDK 17

.github/workflows/dockerhub_ci.yml

@@ -21,115 +21,125 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        # Specify which tags to build
-        DOCKER_TAG: ["3.4.0,3.4,latest", "3.3.2,3.3", "3.1.3,3.1", "3.0.3,3.0", "2.4.8,2.4"]
+        image:
+          -
+            SPARK_VERSION: "3.5.3"
+            OPENJDK_VERSION: "17"
+            HADOOP_VERSION: "3"
+            LATEST: "true"
+          -
+            SPARK_VERSION: "3.4.4"
+            OPENJDK_VERSION: "11"
+            HADOOP_VERSION: "3"
+            LATEST: "false"
+          -
+            SPARK_VERSION: "3.3.4"
+            OPENJDK_VERSION: "11"
+            HADOOP_VERSION: "3"
+            LATEST: "false"
+          -
+            SPARK_VERSION: "3.1.3"
+            OPENJDK_VERSION: "11"
+            HADOOP_VERSION: "3.2"
+            LATEST: "false"
+          -
+            SPARK_VERSION: "3.0.3"
+            OPENJDK_VERSION: "11"
+            HADOOP_VERSION: "3.2"
+            LATEST: "false"
+          -
+            SPARK_VERSION: "2.4.8"
+            OPENJDK_VERSION: "8"
+            HADOOP_VERSION: "2.7"
+            LATEST: "false"
 
     timeout-minutes: 30
     steps:
       - name: Checkout code
-        uses: actions/checkout@v2
-
-      - name: Parse args
-        id: args
-        run: |
-            DOCKER_TAG="${{ matrix.DOCKER_TAG }}"
-
-            # Manipulate DOCKER_TAG to create build args
-            SPARK_MAJOR_VERSION=${DOCKER_TAG:0:1}
-            SPARK_MAJOR_MINOR_VERSION=${DOCKER_TAG:0:3}
-            if [[ ${SPARK_MAJOR_MINOR_VERSION} = "3.3" || ${SPARK_MAJOR_MINOR_VERSION} = "3.4" || ${DOCKER_TAG} == "latest" ]]; then
-                OPENJDK_VERSION=11
-                HADOOP_VERSION=3
-            elif [ ${SPARK_MAJOR_VERSION} = "3" ]; then
-                OPENJDK_VERSION=11
-                HADOOP_VERSION=3.2
-            else
-                OPENJDK_VERSION=8
-                HADOOP_VERSION=2.7
-            fi
-
-            BUILD_ARGS="OPENJDK_VERSION=${OPENJDK_VERSION}
-                        HADOOP_VERSION=${HADOOP_VERSION}
-                        SPARK_VERSION=${DOCKER_TAG%%,*}"
-
-            # No modification needed beyond this point
-            BUILD_ARGS="${BUILD_ARGS//'%'/'%25'}"
-            BUILD_ARGS="${BUILD_ARGS//$'\n'/'%0A'}"
-            BUILD_ARGS="${BUILD_ARGS//$'\r'/'%0D'}"
-
-            echo "::set-output name=build_args::$BUILD_ARGS"
-
-      - name: Prepare
-        id: prep
-        run: |
-            DOCKER_TAG="${{ matrix.DOCKER_TAG }}"
-            DOCKER_IMAGE_NAME="$DOCKER_REPO:${DOCKER_TAG%%,*}"
-            echo ::set-output name=image_name::${DOCKER_IMAGE_NAME}
-
-            TAGS="$DOCKER_REPO:${DOCKER_TAG//,/,$DOCKER_REPO:}"
-            echo ::set-output name=tags::${TAGS}
-
-            echo ::set-output name=created::$(date -u +'%Y-%m-%dT%H:%M:%SZ')
+        uses: actions/checkout@v4
 
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v2
+        uses: docker/setup-qemu-action@v3
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v2
+        id: setup-buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Generate image metadata
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: "${{ env.DOCKER_REPO }}"
+          flavor: |
+            latest=${{ matrix.image.LATEST }}
+            prefix=
+            suffix=
+          tags: |
+            type=semver,pattern={{version}},value=${{ matrix.image.SPARK_VERSION }}
+            type=semver,pattern={{major}}.{{minor}},value=${{ matrix.image.SPARK_VERSION }}
+          labels: |
+            org.opencontainers.image.source=${{ github.event.repository.clone_url }}
+            org.opencontainers.image.revision=${{ github.sha }}
+            org.opencontainers.image.vendor=Xebia Data, https://xebia.com/
+            org.opencontainers.image.description=An Apache Spark Docker image.
 
       - name: Build image
-        uses: docker/build-push-action@v4
+        id: docker-build
+        uses: docker/build-push-action@v6
         with:
          context: .
          file: ./Dockerfile
          push: false
          load: true
-         tags: ${{ steps.prep.outputs.tags }}
+         tags: ${{ steps.meta.outputs.tags }}
          build-args: |
-           ${{ steps.args.outputs.build_args }}
-         labels: |
-           org.opencontainers.image.source=${{ github.event.repository.clone_url }}
-           org.opencontainers.image.created=${{ steps.prep.outputs.created }}
-           org.opencontainers.image.revision=${{ github.sha }}
+           HADOOP_VERSION=${{ matrix.image.HADOOP_VERSION }}
+           OPENJDK_VERSION=${{ matrix.image.OPENJDK_VERSION }}
+           SPARK_VERSION=${{ matrix.image.SPARK_VERSION }}
+         labels: ${{ steps.meta.outputs.labels }}
+         annotations: ${{ steps.meta.outputs.annotations }}
 
       - name: Test image
-        env:
-            IMAGE_NAME: ${{ steps.prep.outputs.image_name }}
         run: |
-            if [[ -f "docker-compose.test.yml" ]]; then
-                docker-compose --file docker-compose.test.yml build
-                docker-compose --file docker-compose.test.yml run sut
-            fi
+          IMAGE_NAME="godatadriven/spark:${{ matrix.image.SPARK_VERSION }}"
+          TEST_IMAGE_NAME="spark-image-tests:${{ matrix.image.SPARK_VERSION }}"
+          docker build \
+            --file tests/Dockerfile \
+            --build-arg IMAGE_NAME="${IMAGE_NAME}" \
+            --tag "${TEST_IMAGE_NAME}" \
+            ./tests/
+
+          docker run --rm "${TEST_IMAGE_NAME}"
 
       - name: Login to DockerHub
         if: github.ref == 'refs/heads/master'
-        uses: docker/login-action@v1 
+        uses: docker/login-action@v3
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB }}
 
       - name: Push image
         # Build and push because of multi platform build
         if: github.ref == 'refs/heads/master'
-        uses: docker/build-push-action@v4
+        uses: docker/build-push-action@v6
         with:
          context: .
          file: ./Dockerfile
          push: true
          provenance: false
          sbom: false
-         tags: ${{ steps.prep.outputs.tags }}
+         tags: ${{ steps.meta.outputs.tags }}
          build-args: |
-           ${{ steps.args.outputs.build_args }}
-         labels: |
-           org.opencontainers.image.source=${{ github.event.repository.clone_url }}
-           org.opencontainers.image.created=${{ steps.prep.outputs.created }}
-           org.opencontainers.image.revision=${{ github.sha }}
+           HADOOP_VERSION=${{ matrix.image.HADOOP_VERSION }}
+           OPENJDK_VERSION=${{ matrix.image.OPENJDK_VERSION }}
+           SPARK_VERSION=${{ matrix.image.SPARK_VERSION }}
+         labels: ${{ steps.meta.outputs.labels }}
+         annotations: ${{ steps.meta.outputs.annotations }}
          platforms: linux/amd64,linux/arm64
 
       - name: Report Status
         if: always() && github.ref == 'refs/heads/master'
-        uses: ravsamhq/notify-slack-action@master
+        uses: ravsamhq/notify-slack-action@v2
         with:
           status: ${{ job.status }}
           notify_when: 'failure'

Dockerfile

@@ -9,11 +9,11 @@ LABEL org.label-schema.name="Apache Spark ${SPARK_VERSION}" \
       org.label-schema.build-date=$BUILD_DATE \
       org.label-schema.version=$SPARK_VERSION      
 
-ENV SPARK_HOME /usr/spark
+ENV SPARK_HOME=/usr/spark
 ENV PATH="/usr/spark/bin:/usr/spark/sbin:${PATH}"
 
 RUN apt-get update && \
-    apt-get install -y wget netcat procps libpostgresql-jdbc-java && \
+    apt-get install -y wget netcat-openbsd procps libpostgresql-jdbc-java && \
     wget -q "http://archive.apache.org/dist/spark/spark-${SPARK_VERSION}/spark-${SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz" && \
     tar xzf "spark-${SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz" && \
     rm "spark-${SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz" && \