Merge branch 'master' into master

kanavnarula · Oct 22, 2024 · 35847e7 · 35847e7
2 parents 332015f + cdb23ac
commit 35847e7
Show file tree

Hide file tree

Showing 745 changed files with 30,693 additions and 18,105 deletions.
diff --git a/.github/workflows/airflow-plugin.yml b/.github/workflows/airflow-plugin.yml
@@ -54,6 +54,9 @@ jobs:
           - python-version: "3.11"
             extra_pip_requirements: "apache-airflow~=2.9.3 -c https://raw.githubusercontent.com/apache/airflow/constraints-2.9.3/constraints-3.11.txt"
             extra_pip_extras: plugin-v2
+          - python-version: "3.11"
+            extra_pip_requirements: "apache-airflow~=2.10.2 -c https://raw.githubusercontent.com/apache/airflow/constraints-2.10.2/constraints-3.11.txt"
+            extra_pip_extras: plugin-v2
       fail-fast: false
     steps:
       - name: Set up JDK 17

diff --git a/.github/workflows/build-and-test.yml b/.github/workflows/build-and-test.yml
@@ -67,17 +67,16 @@ jobs:
           timezoneLinux: ${{ matrix.timezone }}
       - name: Check out the repo
         uses: acryldata/sane-checkout-action@v3
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.10"
+          cache: pip
       - name: Set up JDK 17
         uses: actions/setup-java@v4
         with:
           distribution: "zulu"
           java-version: 17
       - uses: gradle/actions/setup-gradle@v3
-      - uses: actions/setup-python@v5
-        if: ${{ needs.setup.outputs.ingestion_change == 'true' }}
-        with:
-          python-version: "3.10"
-          cache: pip
       - name: Gradle build (and test) for NOT metadata ingestion
         if: ${{  matrix.command == 'except_metadata_ingestion' && needs.setup.outputs.backend_change == 'true' }}
         run: |

diff --git a/.github/workflows/contributor-open-pr-comment.yml b/.github/workflows/contributor-open-pr-comment.yml
@@ -0,0 +1,42 @@
+name: PR Comment
+
+on:
+  pull_request:
+    types: [opened]
+
+permissions:
+  pull-requests: write
+
+jobs:
+  post-pr-opened-comment:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+
+      - name: Get and Format Username (PR only)
+        if: github.event_name == 'pull_request'
+        run: |
+          formatted_username=$(echo "${{ github.event.pull_request.user.login }}" | tr '[:upper:]' '[:lower:]' | sed 's/ /-/g')
+          echo "FORMATTED_USERNAME=$formatted_username" >> $GITHUB_ENV
+
+      - name: Create Comment (PR only)
+        if: github.event_name == 'pull_request'
+        uses: actions/github-script@v6
+        with:
+          script: |
+            if (context.payload.pull_request) {
+              const prUser = process.env.FORMATTED_USERNAME;
+              const url = `https://contributors.datahubproject.io/${prUser}`;
+              const body = `Hello @${prUser} :smile: \n\n Thank you so much for opening a pull request!\n\n![Image](https://contributors.datahubproject.io/api/og?userId=${{ github.event.pull_request.user.login }})\nYou can check out your contributor card and see all your past stats [here](${url})!`;
+                         
+              // Create a comment on the PR
+              await github.rest.issues.createComment({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: context.payload.pull_request.number,
+                body: body
+              });
+            } else {
+              console.log('Not a pull request event.');
+            }
diff --git a/.github/workflows/docker-unified.yml b/.github/workflows/docker-unified.yml
@@ -186,9 +186,11 @@ jobs:
         with:
           image: ${{ env.DATAHUB_GMS_IMAGE }}:${{ needs.setup.outputs.unique_tag }}
       - name: Run Trivy vulnerability scanner
-        uses: aquasecurity/trivy-action@0.8.0
+        uses: aquasecurity/trivy-action@0.26.0
         env:
           TRIVY_OFFLINE_SCAN: true
+          TRIVY_DB_REPOSITORY: public.ecr.aws/aquasecurity/trivy-db:2,ghcr.io/aquasecurity/trivy-db:2
+          TRIVY_JAVA_DB_REPOSITORY: public.ecr.aws/aquasecurity/trivy-java-db:1,ghcr.io/aquasecurity/trivy-java-db:1
         with:
           image-ref: ${{ env.DATAHUB_GMS_IMAGE }}:${{ needs.setup.outputs.unique_tag }}
           format: "template"
@@ -250,9 +252,11 @@ jobs:
         with:
           image: ${{ env.DATAHUB_MAE_CONSUMER_IMAGE }}:${{ needs.setup.outputs.unique_tag }}
       - name: Run Trivy vulnerability scanner
-        uses: aquasecurity/trivy-action@0.8.0
+        uses: aquasecurity/trivy-action@0.26.0
         env:
           TRIVY_OFFLINE_SCAN: true
+          TRIVY_DB_REPOSITORY: public.ecr.aws/aquasecurity/trivy-db:2,ghcr.io/aquasecurity/trivy-db:2
+          TRIVY_JAVA_DB_REPOSITORY: public.ecr.aws/aquasecurity/trivy-java-db:1,ghcr.io/aquasecurity/trivy-java-db:1
         with:
           image-ref: ${{ env.DATAHUB_MAE_CONSUMER_IMAGE }}:${{ needs.setup.outputs.unique_tag }}
           format: "template"
@@ -314,9 +318,11 @@ jobs:
         with:
           image: ${{ env.DATAHUB_MCE_CONSUMER_IMAGE }}:${{ needs.setup.outputs.unique_tag }}
       - name: Run Trivy vulnerability scanner
-        uses: aquasecurity/trivy-action@0.8.0
+        uses: aquasecurity/trivy-action@0.26.0
         env:
           TRIVY_OFFLINE_SCAN: true
+          TRIVY_DB_REPOSITORY: public.ecr.aws/aquasecurity/trivy-db:2,ghcr.io/aquasecurity/trivy-db:2
+          TRIVY_JAVA_DB_REPOSITORY: public.ecr.aws/aquasecurity/trivy-java-db:1,ghcr.io/aquasecurity/trivy-java-db:1
         with:
           image-ref: ${{ env.DATAHUB_MCE_CONSUMER_IMAGE }}:${{ needs.setup.outputs.unique_tag }}
           format: "template"
@@ -378,9 +384,11 @@ jobs:
         with:
           image: ${{ env.DATAHUB_UPGRADE_IMAGE }}:${{ needs.setup.outputs.unique_tag }}
       - name: Run Trivy vulnerability scanner
-        uses: aquasecurity/trivy-action@0.8.0
+        uses: aquasecurity/trivy-action@0.26.0
         env:
           TRIVY_OFFLINE_SCAN: true
+          TRIVY_DB_REPOSITORY: public.ecr.aws/aquasecurity/trivy-db:2,ghcr.io/aquasecurity/trivy-db:2
+          TRIVY_JAVA_DB_REPOSITORY: public.ecr.aws/aquasecurity/trivy-java-db:1,ghcr.io/aquasecurity/trivy-java-db:1
         with:
           image-ref: ${{ env.DATAHUB_UPGRADE_IMAGE }}:${{ needs.setup.outputs.unique_tag }}
           format: "template"
@@ -444,9 +452,11 @@ jobs:
         with:
           image: ${{ env.DATAHUB_FRONTEND_IMAGE }}:${{ needs.setup.outputs.unique_tag }}
       - name: Run Trivy vulnerability scanner
-        uses: aquasecurity/trivy-action@0.8.0
+        uses: aquasecurity/trivy-action@0.26.0
         env:
           TRIVY_OFFLINE_SCAN: true
+          TRIVY_DB_REPOSITORY: public.ecr.aws/aquasecurity/trivy-db:2,ghcr.io/aquasecurity/trivy-db:2
+          TRIVY_JAVA_DB_REPOSITORY: public.ecr.aws/aquasecurity/trivy-java-db:1,ghcr.io/aquasecurity/trivy-java-db:1
         with:
           image-ref: ${{ env.DATAHUB_FRONTEND_IMAGE }}:${{ needs.setup.outputs.unique_tag }}
           format: "template"
@@ -480,6 +490,41 @@ jobs:
           context: .
           file: ./docker/kafka-setup/Dockerfile
           platforms: linux/amd64,linux/arm64/v8
+  kafka_setup_scan:
+    permissions:
+      contents: read # for actions/checkout to fetch code
+      security-events: write # for github/codeql-action/upload-sarif to upload SARIF results
+      actions: read # only required for a private repository by github/codeql-action/upload-sarif to get the Action run status
+    name: "[Monitoring] Scan Kafka Setup images for vulnerabilities"
+    runs-on: ubuntu-latest
+    needs: [ setup, kafka_setup_build ]
+    if: ${{ needs.setup.outputs.kafka_setup_change == 'true' || (needs.setup.outputs.publish == 'true' || needs.setup.outputs.pr-publish == 'true') }}
+    steps:
+      - name: Checkout # adding checkout step just to make trivy upload happy
+        uses: acryldata/sane-checkout-action@v3
+      - name: Download image
+        uses: ishworkh/docker-image-artifact-download@v1
+        if: ${{ needs.setup.outputs.publish != 'true' && needs.setup.outputs.pr-publish != 'true' }}
+        with:
+          image: ${{ env.DATAHUB_KAFKA_SETUP_IMAGE }}:${{ needs.setup.outputs.unique_tag }}
+      - name: Run Trivy vulnerability scanner
+        uses: aquasecurity/[email protected]
+        env:
+          TRIVY_OFFLINE_SCAN: true
+          TRIVY_DB_REPOSITORY: public.ecr.aws/aquasecurity/trivy-db:2,ghcr.io/aquasecurity/trivy-db:2
+          TRIVY_JAVA_DB_REPOSITORY: public.ecr.aws/aquasecurity/trivy-java-db:1,ghcr.io/aquasecurity/trivy-java-db:1
+        with:
+          image-ref: ${{ env.DATAHUB_KAFKA_SETUP_IMAGE }}:${{ needs.setup.outputs.unique_tag }}
+          format: "template"
+          template: "@/contrib/sarif.tpl"
+          output: "trivy-results.sarif"
+          severity: "CRITICAL,HIGH"
+          ignore-unfixed: true
+          vuln-type: "os,library"
+      - name: Upload Trivy scan results to GitHub Security tab
+        uses: github/codeql-action/upload-sarif@v2
+        with:
+          sarif_file: "trivy-results.sarif"
 
   mysql_setup_build:
     name: Build and Push DataHub MySQL Setup Docker Image
@@ -501,6 +546,41 @@ jobs:
           context: .
           file: ./docker/mysql-setup/Dockerfile
           platforms: linux/amd64,linux/arm64/v8
+  mysql_setup_scan:
+    permissions:
+      contents: read # for actions/checkout to fetch code
+      security-events: write # for github/codeql-action/upload-sarif to upload SARIF results
+      actions: read # only required for a private repository by github/codeql-action/upload-sarif to get the Action run status
+    name: "[Monitoring] Scan MySQL Setup images for vulnerabilities"
+    runs-on: ubuntu-latest
+    needs: [ setup, mysql_setup_build ]
+    if: ${{ needs.setup.outputs.mysql_setup_change == 'true' || (needs.setup.outputs.publish == 'true' || needs.setup.outputs.pr-publish == 'true') }}
+    steps:
+      - name: Checkout # adding checkout step just to make trivy upload happy
+        uses: acryldata/sane-checkout-action@v3
+      - name: Download image
+        uses: ishworkh/docker-image-artifact-download@v1
+        if: ${{ needs.setup.outputs.publish != 'true' && needs.setup.outputs.pr-publish != 'true' }}
+        with:
+          image: ${{ env.DATAHUB_MYSQL_SETUP_IMAGE }}:${{ needs.setup.outputs.unique_tag }}
+      - name: Run Trivy vulnerability scanner
+        uses: aquasecurity/[email protected]
+        env:
+          TRIVY_OFFLINE_SCAN: true
+          TRIVY_DB_REPOSITORY: public.ecr.aws/aquasecurity/trivy-db:2,ghcr.io/aquasecurity/trivy-db:2
+          TRIVY_JAVA_DB_REPOSITORY: public.ecr.aws/aquasecurity/trivy-java-db:1,ghcr.io/aquasecurity/trivy-java-db:1
+        with:
+          image-ref: ${{ env.DATAHUB_MYSQL_SETUP_IMAGE }}:${{ needs.setup.outputs.unique_tag }}
+          format: "template"
+          template: "@/contrib/sarif.tpl"
+          output: "trivy-results.sarif"
+          severity: "CRITICAL,HIGH"
+          ignore-unfixed: true
+          vuln-type: "os,library"
+      - name: Upload Trivy scan results to GitHub Security tab
+        uses: github/codeql-action/upload-sarif@v2
+        with:
+          sarif_file: "trivy-results.sarif"
 
   elasticsearch_setup_build:
     name: Build and Push DataHub Elasticsearch Setup Docker Image
@@ -522,6 +602,41 @@ jobs:
           context: .
           file: ./docker/elasticsearch-setup/Dockerfile
           platforms: linux/amd64,linux/arm64/v8
+  elasticsearch_setup_scan:
+    permissions:
+      contents: read # for actions/checkout to fetch code
+      security-events: write # for github/codeql-action/upload-sarif to upload SARIF results
+      actions: read # only required for a private repository by github/codeql-action/upload-sarif to get the Action run status
+    name: "[Monitoring] Scan ElasticSearch setup images for vulnerabilities"
+    runs-on: ubuntu-latest
+    needs: [ setup, elasticsearch_setup_build ]
+    if: ${{ needs.setup.outputs.elasticsearch_setup_change == 'true' || (needs.setup.outputs.publish == 'true' || needs.setup.outputs.pr-publish == 'true' ) }}
+    steps:
+      - name: Checkout # adding checkout step just to make trivy upload happy
+        uses: acryldata/sane-checkout-action@v3
+      - name: Download image
+        uses: ishworkh/docker-image-artifact-download@v1
+        if: ${{ needs.setup.outputs.publish != 'true' && needs.setup.outputs.pr-publish != 'true' }}
+        with:
+          image: ${{ env.DATAHUB_ELASTIC_SETUP_IMAGE }}:${{ needs.setup.outputs.unique_tag }}
+      - name: Run Trivy vulnerability scanner
+        uses: aquasecurity/[email protected]
+        env:
+          TRIVY_OFFLINE_SCAN: true
+          TRIVY_DB_REPOSITORY: public.ecr.aws/aquasecurity/trivy-db:2,ghcr.io/aquasecurity/trivy-db:2
+          TRIVY_JAVA_DB_REPOSITORY: public.ecr.aws/aquasecurity/trivy-java-db:1,ghcr.io/aquasecurity/trivy-java-db:1
+        with:
+          image-ref: ${{ env.DATAHUB_ELASTIC_SETUP_IMAGE }}:${{ needs.setup.outputs.unique_tag }}
+          format: "template"
+          template: "@/contrib/sarif.tpl"
+          output: "trivy-results.sarif"
+          severity: "CRITICAL,HIGH"
+          ignore-unfixed: true
+          vuln-type: "os,library"
+      - name: Upload Trivy scan results to GitHub Security tab
+        uses: github/codeql-action/upload-sarif@v2
+        with:
+          sarif_file: "trivy-results.sarif"
 
   datahub_ingestion_base_build:
     name: Build and Push DataHub Ingestion (Base) Docker Image
@@ -645,14 +760,18 @@ jobs:
     needs: [setup, datahub_ingestion_base_slim_build]
     if: ${{ needs.setup.outputs.ingestion_change == 'true' || needs.setup.outputs.publish == 'true' || needs.setup.outputs.pr-publish == 'true' }}
     steps:
+      - name: Check out the repo
+        uses: acryldata/sane-checkout-action@v3
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.10"
+          cache: "pip"
       - name: Set up JDK 17
         uses: actions/setup-java@v4
         with:
           distribution: "zulu"
           java-version: 17
       - uses: gradle/actions/setup-gradle@v3
-      - name: Check out the repo
-        uses: acryldata/sane-checkout-action@v3
       - name: Build codegen
         if: ${{ needs.setup.outputs.ingestion_change == 'true' || needs.setup.outputs.publish == 'true' || needs.setup.outputs.pr-publish =='true' }}
         run: ./gradlew :metadata-ingestion:codegen
@@ -709,9 +828,11 @@ jobs:
         with:
           image: ${{ env.DATAHUB_INGESTION_IMAGE }}:${{ needs.datahub_ingestion_slim_build.outputs.tag }}
       - name: Run Trivy vulnerability scanner Slim Image
-        uses: aquasecurity/trivy-action@0.8.0
+        uses: aquasecurity/trivy-action@0.26.0
         env:
           TRIVY_OFFLINE_SCAN: true
+          TRIVY_DB_REPOSITORY: public.ecr.aws/aquasecurity/trivy-db:2,ghcr.io/aquasecurity/trivy-db:2
+          TRIVY_JAVA_DB_REPOSITORY: public.ecr.aws/aquasecurity/trivy-java-db:1,ghcr.io/aquasecurity/trivy-java-db:1
         with:
           image-ref: ${{ env.DATAHUB_INGESTION_IMAGE }}:${{ needs.datahub_ingestion_slim_build.outputs.tag }}
           format: "template"
@@ -735,14 +856,18 @@ jobs:
     needs: [setup, datahub_ingestion_base_full_build]
     if: ${{ needs.setup.outputs.ingestion_change == 'true' || needs.setup.outputs.publish == 'true' || needs.setup.outputs.pr-publish == 'true' }}
     steps:
+      - name: Check out the repo
+        uses: acryldata/sane-checkout-action@v3
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.10"
+          cache: "pip"
       - name: Set up JDK 17
         uses: actions/setup-java@v4
         with:
           distribution: "zulu"
           java-version: 17
       - uses: gradle/actions/setup-gradle@v3
-      - name: Check out the repo
-        uses: acryldata/sane-checkout-action@v3
       - name: Build codegen
         if: ${{ needs.setup.outputs.ingestion_change == 'true' || needs.setup.outputs.publish == 'true' || needs.setup.outputs.pr-publish == 'true' }}
         run: ./gradlew :metadata-ingestion:codegen
@@ -797,9 +922,11 @@ jobs:
         with:
           image: ${{ env.DATAHUB_INGESTION_IMAGE }}:${{ needs.datahub_ingestion_full_build.outputs.tag }}
       - name: Run Trivy vulnerability scanner Full Image
-        uses: aquasecurity/trivy-action@0.8.0
+        uses: aquasecurity/trivy-action@0.26.0
         env:
           TRIVY_OFFLINE_SCAN: true
+          TRIVY_DB_REPOSITORY: public.ecr.aws/aquasecurity/trivy-db:2,ghcr.io/aquasecurity/trivy-db:2
+          TRIVY_JAVA_DB_REPOSITORY: public.ecr.aws/aquasecurity/trivy-java-db:1,ghcr.io/aquasecurity/trivy-java-db:1
         with:
           image-ref: ${{ env.DATAHUB_INGESTION_IMAGE }}:${{ needs.datahub_ingestion_full_build.outputs.tag }}
           format: "template"
@@ -864,16 +991,16 @@ jobs:
         run: df -h . && docker images
       - name: Check out the repo
         uses: acryldata/sane-checkout-action@v3
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.10"
+          cache: "pip"
       - name: Set up JDK 17
         uses: actions/setup-java@v4
         with:
           distribution: "zulu"
           java-version: 17
       - uses: gradle/actions/setup-gradle@v3
-      - uses: actions/setup-python@v5
-        with:
-          python-version: "3.10"
-          cache: "pip"
       - name: Login to DockerHub
         uses: docker/login-action@v3
         if: ${{ needs.setup.outputs.docker-login == 'true' }}

diff --git a/.github/workflows/metadata-ingestion.yml b/.github/workflows/metadata-ingestion.yml
@@ -26,6 +26,7 @@ concurrency:
 jobs:
   metadata-ingestion:
     runs-on: ubuntu-latest
+    timeout-minutes: 40
     env:
       SPARK_VERSION: 3.3.2
       DATAHUB_TELEMETRY_ENABLED: false