Merge branch 'master' into origin/ColumnLevelLineageAndPathCypressTest

datahub-project · Oct 19, 2023 · a716752 · a716752
2 parents dc18479 + 75b36c4
commit a716752
Show file tree

Hide file tree

Showing 1,057 changed files with 41,271 additions and 11,320 deletions.
diff --git a/.github/scripts/docker_helpers.sh b/.github/scripts/docker_helpers.sh
@@ -15,10 +15,26 @@ function get_tag {
     echo $(echo ${GITHUB_REF} | sed -e "s,refs/heads/${MAIN_BRANCH},${MAIN_BRANCH_TAG}\,${SHORT_SHA},g" -e 's,refs/tags/,,g' -e 's,refs/pull/\([0-9]*\).*,pr\1,g')
 }
 
+function get_tag_slim {
+    echo $(echo ${GITHUB_REF} | sed -e "s,refs/heads/${MAIN_BRANCH},${MAIN_BRANCH_TAG}-slim\,${SHORT_SHA}-slim,g" -e 's,refs/tags/,,g' -e 's,refs/pull/\([0-9]*\).*,pr\1-slim,g')
+}
+
+function get_tag_full {
+    echo $(echo ${GITHUB_REF} | sed -e "s,refs/heads/${MAIN_BRANCH},${MAIN_BRANCH_TAG}-full\,${SHORT_SHA}-full,g" -e 's,refs/tags/,,g' -e 's,refs/pull/\([0-9]*\).*,pr\1-full,g')
+}
+
 function get_python_docker_release_v {
     echo $(echo ${GITHUB_REF} | sed -e "s,refs/heads/${MAIN_BRANCH},0.0.0+docker.${SHORT_SHA},g" -e 's,refs/tags/v\(.*\),\1+docker,g' -e 's,refs/pull/\([0-9]*\).*,0.0.0+docker.pr\1,g')
 }
 
 function get_unique_tag {
     echo $(echo ${GITHUB_REF} | sed -e "s,refs/heads/${MAIN_BRANCH},${SHORT_SHA},g" -e 's,refs/tags/,,g' -e 's,refs/pull/\([0-9]*\).*,pr\1,g')
+}
+
+function get_unique_tag_slim {
+    echo $(echo ${GITHUB_REF} | sed -e "s,refs/heads/${MAIN_BRANCH},${SHORT_SHA}-slim,g" -e 's,refs/tags/,,g' -e 's,refs/pull/\([0-9]*\).*,pr\1-slim,g')
+}
+
+function get_unique_tag_full {
+    echo $(echo ${GITHUB_REF} | sed -e "s,refs/heads/${MAIN_BRANCH},${SHORT_SHA}-full,g" -e 's,refs/tags/,,g' -e 's,refs/pull/\([0-9]*\).*,pr\1-full,g')
 }
diff --git a/.github/workflows/airflow-plugin.yml b/.github/workflows/airflow-plugin.yml
@@ -10,7 +10,7 @@ on:
       - "metadata-models/**"
   pull_request:
     branches:
-      - master
+      - "**"
     paths:
       - ".github/**"
       - "metadata-ingestion-modules/airflow-plugin/**"
@@ -32,16 +32,21 @@ jobs:
     strategy:
       matrix:
         include:
-          - python-version: "3.7"
-            extraPythonRequirement: "apache-airflow~=2.1.0"
-          - python-version: "3.7"
-            extraPythonRequirement: "apache-airflow~=2.2.0"
+          - python-version: "3.8"
+            extra_pip_requirements: "apache-airflow~=2.1.4"
+            extra_pip_extras: plugin-v1
+          - python-version: "3.8"
+            extra_pip_requirements: "apache-airflow~=2.2.4"
+            extra_pip_extras: plugin-v1
           - python-version: "3.10"
-            extraPythonRequirement: "apache-airflow~=2.4.0"
+            extra_pip_requirements: "apache-airflow~=2.4.0"
+            extra_pip_extras: plugin-v2
           - python-version: "3.10"
-            extraPythonRequirement: "apache-airflow~=2.6.0"
+            extra_pip_requirements: "apache-airflow~=2.6.0"
+            extra_pip_extras: plugin-v2
           - python-version: "3.10"
-            extraPythonRequirement: "apache-airflow>2.6.0"
+            extra_pip_requirements: "apache-airflow>=2.7.0"
+            extra_pip_extras: plugin-v2
       fail-fast: false
     steps:
       - uses: actions/checkout@v3
@@ -51,13 +56,13 @@ jobs:
           cache: "pip"
       - name: Install dependencies
         run: ./metadata-ingestion/scripts/install_deps.sh
-      - name: Install airflow package and test  (extras ${{ matrix.extraPythonRequirement }})
-        run: ./gradlew -Pextra_pip_requirements='${{ matrix.extraPythonRequirement }}' :metadata-ingestion-modules:airflow-plugin:lint :metadata-ingestion-modules:airflow-plugin:testQuick
+      - name: Install airflow package and test (extras ${{ matrix.extra_pip_requirements }})
+        run: ./gradlew -Pextra_pip_requirements='${{ matrix.extra_pip_requirements }}' -Pextra_pip_extras='${{ matrix.extra_pip_extras }}' :metadata-ingestion-modules:airflow-plugin:lint :metadata-ingestion-modules:airflow-plugin:testQuick
       - name: pip freeze show list installed
         if: always()
         run: source metadata-ingestion-modules/airflow-plugin/venv/bin/activate && pip freeze
       - uses: actions/upload-artifact@v3
-        if: ${{ always() && matrix.python-version == '3.10' && matrix.extraPythonRequirement == 'apache-airflow>2.6.0' }}
+        if: ${{ always() && matrix.python-version == '3.10' && matrix.extra_pip_requirements == 'apache-airflow>=2.7.0' }}
         with:
           name: Test Results (Airflow Plugin ${{ matrix.python-version}})
           path: |

diff --git a/.github/workflows/build-and-test.yml b/.github/workflows/build-and-test.yml
@@ -8,7 +8,7 @@ on:
       - "**.md"
   pull_request:
     branches:
-      - master
+      - "**"
     paths-ignore:
       - "docs/**"
       - "**.md"
@@ -24,17 +24,12 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        command:
-          [
-            "./gradlew build -x :metadata-ingestion:build -x :metadata-ingestion:check -x docs-website:build -x :metadata-integration:java:spark-lineage:test -x :metadata-io:test -x :metadata-ingestion-modules:airflow-plugin:build -x :datahub-frontend:build -x :datahub-web-react:build --parallel",
-            "./gradlew :datahub-frontend:build :datahub-web-react:build --parallel",
-            "./gradlew :metadata-ingestion-modules:airflow-plugin:build --parallel"
-          ]
-        timezone:
-          [
-            "UTC",
-            "America/New_York",
+        command: [
+            # metadata-ingestion and airflow-plugin each have dedicated build jobs
+            "except_metadata_ingestion",
+            "frontend"
           ]
+        timezone: ["UTC", "America/New_York"]
     runs-on: ubuntu-latest
     timeout-minutes: 60
     steps:
@@ -51,10 +46,17 @@ jobs:
           java-version: 11
       - uses: actions/setup-python@v4
         with:
-          python-version: "3.7"
-      - name: Gradle build (and test)
+          python-version: "3.10"
+          cache: pip
+      - name: Gradle build (and test) for metadata ingestion
+        # we only need the timezone runs for frontend tests
+        if: ${{  matrix.command == 'except_metadata_ingestion' && matrix.timezone == 'America/New_York' }}
+        run: |
+          ./gradlew build -x :metadata-ingestion:build -x :metadata-ingestion:check -x docs-website:build -x :metadata-integration:java:spark-lineage:test -x :metadata-io:test -x :metadata-ingestion-modules:airflow-plugin:build -x :metadata-ingestion-modules:airflow-plugin:check -x :datahub-frontend:build -x :datahub-web-react:build --parallel
+      - name: Gradle build (and test) for frontend
+        if: ${{  matrix.command == 'frontend' }}
         run: |
-          ${{ matrix.command }}
+          ./gradlew :datahub-frontend:build :datahub-web-react:build --parallel
         env:
           NODE_OPTIONS: "--max-old-space-size=3072"
       - uses: actions/upload-artifact@v3
@@ -81,7 +83,7 @@ jobs:
       - uses: actions/checkout@v3
       - uses: actions/setup-python@v4
         with:
-          python-version: "3.7"
+          python-version: "3.10"
       - name: Download YQ
         uses: chrisdickinson/[email protected]
         with:

diff --git a/.github/workflows/check-datahub-jars.yml b/.github/workflows/check-datahub-jars.yml
@@ -10,7 +10,7 @@ on:
       - "**.md"
   pull_request:
     branches:
-      - master
+      - "**"
     paths-ignore:
       - "docker/**"
       - "docs/**"
@@ -28,12 +28,7 @@ jobs:
       max-parallel: 1
       fail-fast: false
       matrix:
-        command:
-          [
-            "datahub-client",
-            "datahub-protobuf",
-            "spark-lineage"
-          ]
+        command: ["datahub-client", "datahub-protobuf", "spark-lineage"]
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3

diff --git a/.github/workflows/close-stale-issues.yml b/.github/workflows/close-stale-issues.yml
@@ -18,7 +18,9 @@ jobs:
           days-before-issue-stale: 30
           days-before-issue-close: 30
           stale-issue-label: "stale"
-          stale-issue-message: "This issue is stale because it has been open for 30 days with no activity. If you believe this is still an issue on the latest DataHub release please leave a comment with the version that you tested it with. If this is a question/discussion please head to https://slack.datahubproject.io. For feature requests please use https://feature-requests.datahubproject.io"
+          stale-issue-message:
+            "This issue is stale because it has been open for 30 days with no activity. If you believe this is still an issue on the latest DataHub release please leave a comment with the version that you tested it with. If this is a question/discussion please head to https://slack.datahubproject.io.\
+            \ For feature requests please use https://feature-requests.datahubproject.io"
           close-issue-message: "This issue was closed because it has been inactive for 30 days since being marked as stale."
           days-before-pr-stale: -1
           days-before-pr-close: -1

diff --git a/.github/workflows/code-checks.yml b/.github/workflows/code-checks.yml
@@ -10,7 +10,7 @@ on:
       - ".github/workflows/code-checks.yml"
   pull_request:
     branches:
-      - master
+      - "**"
     paths:
       - "metadata-io/**"
       - "datahub-web-react/**"
@@ -21,17 +21,12 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
 
-
 jobs:
   code_check:
     strategy:
       fail-fast: false
       matrix:
-        command:
-          [
-            "check_event_type.py",
-            "check_policies.py"
-          ]
+        command: ["check_event_type.py", "check_policies.py"]
     name: run code checks
     runs-on: ubuntu-latest
     steps:
@@ -43,5 +38,5 @@ jobs:
         with:
           python-version: "3.10"
       - name: run check ${{ matrix.command }}
-        run: |
-          python .github/scripts/${{ matrix.command }}
+        run: |-
+          python .github/scripts/${{ matrix.command }}
diff --git a/.github/workflows/docker-ingestion-smoke.yml b/.github/workflows/docker-ingestion-smoke.yml
@@ -3,8 +3,6 @@ on:
   release:
     types: [published]
   push:
-    branches:
-      - master
     paths:
       - "docker/datahub-ingestion-base/**"
       - "smoke-test/**"

diff --git a/.github/workflows/docker-postgres-setup.yml b/.github/workflows/docker-postgres-setup.yml
@@ -8,7 +8,7 @@ on:
       - ".github/workflows/docker-postgres-setup.yml"
   pull_request:
     branches:
-      - master
+      - "**"
     paths:
       - "docker/postgres-setup/**"
       - ".github/workflows/docker-postgres-setup.yml"
@@ -61,4 +61,3 @@ jobs:
           context: .
           file: ./docker/postgres-setup/Dockerfile
           platforms: linux/amd64,linux/arm64
-
diff --git a/.github/workflows/docker-unified.yml b/.github/workflows/docker-unified.yml
@@ -8,7 +8,7 @@ on:
       - "**.md"
   pull_request:
     branches:
-      - master
+      - "**"
     paths-ignore:
       - "docs/**"
       - "**.md"
@@ -54,11 +54,11 @@ jobs:
         run: |
           source .github/scripts/docker_helpers.sh
           echo "tag=$(get_tag)" >> $GITHUB_OUTPUT
-          echo "slim_tag=$(get_tag)-slim" >> $GITHUB_OUTPUT
-          echo "full_tag=$(get_tag)-full" >> $GITHUB_OUTPUT
+          echo "slim_tag=$(get_tag_slim)" >> $GITHUB_OUTPUT
+          echo "full_tag=$(get_tag_full)" >> $GITHUB_OUTPUT
           echo "unique_tag=$(get_unique_tag)" >> $GITHUB_OUTPUT
-          echo "unique_slim_tag=$(get_unique_tag)-slim" >> $GITHUB_OUTPUT
-          echo "unique_full_tag=$(get_unique_tag)-full" >> $GITHUB_OUTPUT
+          echo "unique_slim_tag=$(get_unique_tag_slim)" >> $GITHUB_OUTPUT
+          echo "unique_full_tag=$(get_unique_tag_full)" >> $GITHUB_OUTPUT
           echo "python_release_version=$(get_python_docker_release_v)" >> $GITHUB_OUTPUT
       - name: Check whether publishing enabled
         id: publish
@@ -459,7 +459,7 @@ jobs:
           platforms: linux/amd64,linux/arm64/v8
       - name: Compute DataHub Ingestion (Base) Tag
         id: tag
-        run: echo "tag=${{ steps.filter.outputs.datahub-ingestion-base == 'true' && needs.setup.outputs.tag || 'head' }}" >> $GITHUB_OUTPUT
+        run: echo "tag=${{ steps.filter.outputs.datahub-ingestion-base == 'true' && needs.setup.outputs.unique_tag || 'head' }}" >> $GITHUB_OUTPUT
   datahub_ingestion_base_slim_build:
     name: Build and Push DataHub Ingestion (Base-Slim) Docker Image
     runs-on: ubuntu-latest
@@ -501,7 +501,7 @@ jobs:
           platforms: linux/amd64,linux/arm64/v8
       - name: Compute DataHub Ingestion (Base-Slim) Tag
         id: tag
-        run: echo "tag=${{ steps.filter.outputs.datahub-ingestion-base == 'true' && needs.setup.outputs.unique_slim_tag || 'head' }}" >> $GITHUB_OUTPUT
+        run: echo "tag=${{ steps.filter.outputs.datahub-ingestion-base == 'true' && needs.setup.outputs.unique_slim_tag || 'head-slim' }}" >> $GITHUB_OUTPUT
   datahub_ingestion_base_full_build:
     name: Build and Push DataHub Ingestion (Base-Full) Docker Image
     runs-on: ubuntu-latest
@@ -524,14 +524,14 @@ jobs:
         if: ${{ needs.setup.outputs.publish != 'true' &&  steps.filter.outputs.datahub-ingestion-base == 'true' }}
         with:
           image: ${{ env.DATAHUB_INGESTION_BASE_IMAGE }}:${{ steps.filter.outputs.datahub-ingestion-base == 'true' && needs.setup.outputs.unique_tag || 'head' }}
-      - name: Build and push Base-Full Image
+      - name: Build and push (Base-Full) Image
         if: ${{ steps.filter.outputs.datahub-ingestion-base == 'true' }}
         uses: ./.github/actions/docker-custom-build-and-push
         with:
           target: full-install
           images: |
             ${{ env.DATAHUB_INGESTION_BASE_IMAGE }}
-          tags: ${{ needs.setup.outputs.unique_full_tag }}
+          tags: ${{ needs.setup.outputs.full_tag }}
           username: ${{ secrets.ACRYL_DOCKER_USERNAME }}
           password: ${{ secrets.ACRYL_DOCKER_PASSWORD }}
           build-args: |
@@ -545,7 +545,6 @@ jobs:
         id: tag
         run: echo "tag=${{ steps.filter.outputs.datahub-ingestion-base == 'true' && needs.setup.outputs.unique_full_tag || 'head' }}" >> $GITHUB_OUTPUT
 
-
   datahub_ingestion_slim_build:
     name: Build and Push DataHub Ingestion Docker Images
     runs-on: ubuntu-latest
@@ -567,13 +566,13 @@ jobs:
             datahub-ingestion:
               - 'docker/datahub-ingestion/**'
       - name: Build codegen
-        if: ${{ steps.filter.outputs.datahub-ingestion-base == 'true' || steps.filter.outputs.datahub-ingestion == 'true' }}
+        if: ${{ steps.filter.outputs.datahub-ingestion-base == 'true' || steps.filter.outputs.datahub-ingestion == 'true' || needs.setup.outputs.publish }}
         run: ./gradlew :metadata-ingestion:codegen
       - name: Download Base Image
         uses: ishworkh/docker-image-artifact-download@v1
         if: ${{ needs.setup.outputs.publish != 'true' && steps.filter.outputs.datahub-ingestion-base == 'true' }}
         with:
-          image: ${{ env.DATAHUB_INGESTION_BASE_IMAGE }}:${{ steps.filter.outputs.datahub-ingestion-base == 'true' && needs.setup.outputs.unique_slim_tag || 'head' }}
+          image: ${{ env.DATAHUB_INGESTION_BASE_IMAGE }}:${{ steps.filter.outputs.datahub-ingestion-base == 'true' && needs.setup.outputs.unique_slim_tag || 'head-slim' }}
       - name: Build and push Slim Image
         if: ${{ steps.filter.outputs.datahub-ingestion-base == 'true' || steps.filter.outputs.datahub-ingestion == 'true' || needs.setup.outputs.publish }}
         uses: ./.github/actions/docker-custom-build-and-push
@@ -583,7 +582,7 @@ jobs:
             ${{ env.DATAHUB_INGESTION_IMAGE }}
           build-args: |
             BASE_IMAGE=${{ env.DATAHUB_INGESTION_BASE_IMAGE }}
-            DOCKER_VERSION=${{ steps.filter.outputs.datahub-ingestion-base == 'true' && needs.setup.outputs.unique_slim_tag || 'head' }}
+            DOCKER_VERSION=${{ steps.filter.outputs.datahub-ingestion-base == 'true' && needs.setup.outputs.unique_slim_tag || 'head-slim' }}
             RELEASE_VERSION=${{ needs.setup.outputs.python_release_version }}
             APP_ENV=slim
           tags: ${{ needs.setup.outputs.slim_tag }}
@@ -595,7 +594,7 @@ jobs:
           platforms: linux/amd64,linux/arm64/v8
       - name: Compute Tag
         id: tag
-        run: echo "tag=${{ (steps.filter.outputs.datahub-ingestion-base == 'true' || steps.filter.outputs.datahub-ingestion == 'true') && needs.setup.outputs.unique_slim_tag || 'head' }}" >> $GITHUB_OUTPUT
+        run: echo "tag=${{ (steps.filter.outputs.datahub-ingestion-base == 'true' || steps.filter.outputs.datahub-ingestion == 'true') && needs.setup.outputs.unique_slim_tag || 'head-slim' }}" >> $GITHUB_OUTPUT
   datahub_ingestion_slim_scan:
     permissions:
       contents: read # for actions/checkout to fetch code
@@ -650,13 +649,13 @@ jobs:
             datahub-ingestion:
               - 'docker/datahub-ingestion/**'
       - name: Build codegen
-        if: ${{ steps.filter.outputs.datahub-ingestion-base == 'true' || steps.filter.outputs.datahub-ingestion == 'true' }}
+        if: ${{ steps.filter.outputs.datahub-ingestion-base == 'true' || steps.filter.outputs.datahub-ingestion == 'true' || needs.setup.outputs.publish }}
         run: ./gradlew :metadata-ingestion:codegen
       - name: Download Base Image
         uses: ishworkh/docker-image-artifact-download@v1
         if: ${{ needs.setup.outputs.publish != 'true' && steps.filter.outputs.datahub-ingestion-base == 'true' }}
         with:
-          image: ${{ env.DATAHUB_INGESTION_BASE_IMAGE }}:${{ steps.filter.outputs.datahub-ingestion-base == 'true' && needs.setup.outputs.unique_full_tag || 'head' }}
+          image: ${{ env.DATAHUB_INGESTION_BASE_IMAGE }}:${{ steps.filter.outputs.datahub-ingestion-base == 'true' && needs.setup.outputs.unique_tag || 'head' }}
       - name: Build and push Full Image
         if: ${{ steps.filter.outputs.datahub-ingestion-base == 'true' || steps.filter.outputs.datahub-ingestion == 'true' || needs.setup.outputs.publish }}
         uses: ./.github/actions/docker-custom-build-and-push
@@ -666,9 +665,9 @@ jobs:
             ${{ env.DATAHUB_INGESTION_IMAGE }}
           build-args: |
             BASE_IMAGE=${{ env.DATAHUB_INGESTION_BASE_IMAGE }}
-            DOCKER_VERSION=${{ steps.filter.outputs.datahub-ingestion-base == 'true' && needs.setup.outputs.unique_full_tag || 'head' }}
+            DOCKER_VERSION=${{ steps.filter.outputs.datahub-ingestion-base == 'true' && needs.setup.outputs.unique_tag || 'head' }}
             RELEASE_VERSION=${{ needs.setup.outputs.python_release_version }}
-          tags: ${{ needs.setup.outputs.unique_full_tag }}
+          tags: ${{ needs.setup.outputs.tag }}
           username: ${{ secrets.ACRYL_DOCKER_USERNAME }}
           password: ${{ secrets.ACRYL_DOCKER_PASSWORD }}
           publish: ${{ needs.setup.outputs.publish }}
@@ -677,7 +676,7 @@ jobs:
           platforms: linux/amd64,linux/arm64/v8
       - name: Compute Tag (Full)
         id: tag
-        run: echo "tag=${{ (steps.filter.outputs.datahub-ingestion-base == 'true' || steps.filter.outputs.datahub-ingestion == 'true') && needs.setup.outputs.unique_full_tag || 'head' }}" >> $GITHUB_OUTPUT
+        run: echo "tag=${{ (steps.filter.outputs.datahub-ingestion-base == 'true' || steps.filter.outputs.datahub-ingestion == 'true') && needs.setup.outputs.unique_tag || 'head' }}" >> $GITHUB_OUTPUT
   datahub_ingestion_full_scan:
     permissions:
       contents: read # for actions/checkout to fetch code
@@ -809,8 +808,8 @@ jobs:
           DATAHUB_VERSION: ${{ needs.setup.outputs.unique_tag }}
           DATAHUB_ACTIONS_IMAGE: ${{ env.DATAHUB_INGESTION_IMAGE }}
           ACTIONS_VERSION: ${{ needs.datahub_ingestion_slim_build.outputs.tag }}
-          ACTIONS_EXTRA_PACKAGES: 'acryl-datahub-actions[executor]==0.0.13 acryl-datahub-actions==0.0.13 acryl-datahub==0.10.5'
-          ACTIONS_CONFIG: 'https://raw.githubusercontent.com/acryldata/datahub-actions/main/docker/config/executor.yaml'
+          ACTIONS_EXTRA_PACKAGES: "acryl-datahub-actions[executor]==0.0.13 acryl-datahub-actions==0.0.13 acryl-datahub==0.10.5"
+          ACTIONS_CONFIG: "https://raw.githubusercontent.com/acryldata/datahub-actions/main/docker/config/executor.yaml"
         run: |
           ./smoke-test/run-quickstart.sh
       - name: sleep 60s

diff --git a/.github/workflows/documentation.yml b/.github/workflows/documentation.yml
@@ -3,7 +3,7 @@ name: documentation
 on:
   pull_request:
     branches:
-      - master
+      - "**"
   push:
     branches:
       - master