Update internal 0.12.1

.dockerignore

@@ -1,6 +1,7 @@
 **/node_modules/
-datahub-frontend/build/
-metadata-ingestion/venv/
+*/build/
+*/*/build/
+*/venv/
 out
 **/*.class
 # Have to copy gradle/wrapper/gradle-wrapper.jar, can't exclude ALL jars

.github/actions/docker-custom-build-and-push/action.yml

@@ -30,6 +30,9 @@ inputs:
     # e.g. latest,head,sha12345
     description: "List of tags to use for the Docker image"
     required: true
+  target:
+    description: "Sets the target stage to build"
+    required: false
 outputs:
   image_tag:
     description: "Docker image tags"
@@ -49,7 +52,7 @@ runs:
         # add git short SHA as Docker tag
         tag-custom: ${{ inputs.tags }}
         tag-custom-only: true
-    
+
     # Code for testing the build when not pushing to Docker Hub.
     - name: Build and Load image for testing (if not publishing)
       uses: docker/build-push-action@v3
@@ -62,14 +65,26 @@ runs:
         platforms: linux/amd64
         build-args: ${{ inputs.build-args }}
         tags: ${{ steps.docker_meta.outputs.tags }}
+        target: ${{ inputs.target }}
         load: true
         push: false
+        cache-from: type=registry,ref=${{ steps.docker_meta.outputs.tags }}
+        cache-to: type=inline
+    - name: Single Tag
+      if: ${{ inputs.publish != 'true' }}
+      shell: bash
+      run: |
+        TAGS="""
+        ${{ steps.docker_meta.outputs.tags }}
+        """
+        echo "SINGLE_TAG=$(echo $TAGS | tr '\n' ' ' | awk -F' ' '{ print $1 }')" >> $GITHUB_OUTPUT
+      id: single_tag
     - name: Upload image locally for testing (if not publishing)
       uses: ishworkh/docker-image-artifact-upload@v1
       if: ${{ inputs.publish != 'true' }}
       with:
-        image: ${{ steps.docker_meta.outputs.tags }}
-    
+        image: ${{ steps.single_tag.outputs.SINGLE_TAG }}
+
     # Code for building multi-platform images and pushing to Docker Hub.
     - name: Set up QEMU
       uses: docker/setup-qemu-action@v2
@@ -92,6 +107,9 @@ runs:
         platforms: ${{ inputs.platforms }}
         build-args: ${{ inputs.build-args }}
         tags: ${{ steps.docker_meta.outputs.tags }}
+        target: ${{ inputs.target }}
         push: true
+        cache-from: type=registry,ref=${{ steps.docker_meta.outputs.tags }}
+        cache-to: type=inline
 
     # TODO add code for vuln scanning?

.github/scripts/check_policies.py

@@ -20,7 +20,7 @@
     elif urn == "urn:li:dataHubPolicy:editor-platform-policy":
         editor_platform_policy_privileges = policy["info"]["privileges"]
     elif urn == "urn:li:dataHubPolicy:7":
-        all_user_platform_policy_privilges = policy["info"]["privileges"]
+        all_user_platform_policy_privileges = policy["info"]["privileges"]
     try:
         doc_type = policy["info"]["type"]
         privileges = policy["info"]["privileges"]
@@ -54,10 +54,22 @@
 )
 assert len(diff_policies) == 0, f"Missing privileges for root user are {diff_policies}"
 
-diff_policies = set(editor_platform_policy_privileges).difference(
-    set(all_user_platform_policy_privilges)
-)
-assert "MANAGE_POLICIES" not in all_user_platform_policy_privilges
-assert (
-    len(diff_policies) == 0
-), f"Missing privileges for all user policies are {diff_policies}"
+# All users privileges checks
+assert "MANAGE_POLICIES" not in all_user_platform_policy_privileges
+assert "MANAGE_USERS_AND_GROUPS" not in all_user_platform_policy_privileges
+assert "MANAGE_SECRETS" not in all_user_platform_policy_privileges
+assert "MANAGE_USER_CREDENTIALS" not in all_user_platform_policy_privileges
+assert "MANAGE_ACCESS_TOKENS" not in all_user_platform_policy_privileges
+assert "EDIT_ENTITY" not in all_user_platform_policy_privileges
+assert "DELETE_ENTITY" not in all_user_platform_policy_privileges
+
+# Editor checks
+assert "MANAGE_POLICIES" not in editor_platform_policy_privileges
+assert "MANAGE_USERS_AND_GROUPS" not in editor_platform_policy_privileges
+assert "MANAGE_SECRETS" not in editor_platform_policy_privileges
+assert "MANAGE_USER_CREDENTIALS" not in editor_platform_policy_privileges
+assert "MANAGE_ACCESS_TOKENS" not in editor_platform_policy_privileges
+# These don't prevent a user from modifying entities they are an asset owner of, i.e. their own profile info
+assert "EDIT_CONTACT_INFO" not in editor_platform_policy_privileges
+assert "EDIT_USER_PROFILE" not in editor_platform_policy_privileges
+assert "EDIT_ENTITY_OWNERS" not in editor_platform_policy_privileges

.github/scripts/docker_helpers.sh

@@ -12,7 +12,15 @@ export SHORT_SHA=$(get_short_sha)
 echo "SHORT_SHA: $SHORT_SHA"
 
 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')
+    echo $(echo ${GITHUB_REF} | sed -e "s,refs/heads/${MAIN_BRANCH},${MAIN_BRANCH_TAG},g" -e 's,refs/tags/,,g' -e 's,refs/pull/\([0-9]*\).*,pr\1,g'),${SHORT_SHA}
+}
+
+function get_tag_slim {
+    echo $(echo ${GITHUB_REF} | sed -e "s,refs/heads/${MAIN_BRANCH},${MAIN_BRANCH_TAG}-slim,g" -e 's,refs/tags/,,g' -e 's,refs/pull/\([0-9]*\).*,pr\1-slim,g'),${SHORT_SHA}-slim
+}
+
+function get_tag_full {
+    echo $(echo ${GITHUB_REF} | sed -e "s,refs/heads/${MAIN_BRANCH},${MAIN_BRANCH_TAG}-full,g" -e 's,refs/tags/,,g' -e 's,refs/pull/\([0-9]*\).*,pr\1-full,g'),${SHORT_SHA}-full
 }
 
 function get_python_docker_release_v {
@@ -21,4 +29,12 @@ function get_python_docker_release_v {
 
 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')
 }

.github/workflows/airflow-plugin.yml

@@ -0,0 +1,90 @@
+name: Airflow Plugin
+on:
+  push:
+    branches:
+      - master
+    paths:
+      - ".github/workflows/airflow-plugin.yml"
+      - "metadata-ingestion-modules/airflow-plugin/**"
+      - "metadata-ingestion/**"
+      - "metadata-models/**"
+  pull_request:
+    branches:
+      - "**"
+    paths:
+      - ".github/workflows/airflow-plugin.yml"
+      - "metadata-ingestion-modules/airflow-plugin/**"
+      - "metadata-ingestion/**"
+      - "metadata-models/**"
+  release:
+    types: [published]
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  airflow-plugin:
+    runs-on: ubuntu-latest
+    env:
+      SPARK_VERSION: 3.0.3
+      DATAHUB_TELEMETRY_ENABLED: false
+    strategy:
+      matrix:
+        include:
+          - 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"
+            extra_pip_requirements: "apache-airflow~=2.4.0"
+            extra_pip_extras: plugin-v2
+          - python-version: "3.10"
+            extra_pip_requirements: "apache-airflow~=2.6.0"
+            extra_pip_extras: plugin-v2
+          - python-version: "3.10"
+            extra_pip_requirements: "apache-airflow>=2.7.0"
+            extra_pip_extras: plugin-v2
+      fail-fast: false
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: "pip"
+      - name: Install dependencies
+        run: ./metadata-ingestion/scripts/install_deps.sh
+      - 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.extra_pip_requirements == 'apache-airflow>=2.7.0' }}
+        with:
+          name: Test Results (Airflow Plugin ${{ matrix.python-version}})
+          path: |
+            **/build/reports/tests/test/**
+            **/build/test-results/test/**
+            **/junit.*.xml
+      - name: Upload coverage to Codecov
+        if: always()
+        uses: codecov/codecov-action@v3
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+          directory: .
+          fail_ci_if_error: false
+          flags: airflow-${{ matrix.python-version }}-${{ matrix.extraPythonRequirement }}
+          name: pytest-airflow
+          verbose: true
+
+  event-file:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Upload
+        uses: actions/upload-artifact@v3
+        with:
+          name: Event File
+          path: ${{ github.event_path }}

.github/workflows/build-and-test.yml

@@ -8,7 +8,7 @@ on:
       - "**.md"
   pull_request:
     branches:
-      - master
+      - "**"
     paths-ignore:
       - "docs/**"
       - "**.md"
@@ -24,37 +24,37 @@ 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:
       - uses: szenius/set-timezone@v1.0
         with:
           timezoneLinux: ${{ matrix.timezone }}
-      - uses: actions/checkout@v3
-        with:
-          fetch-depth: 800
+      - uses: hsheth2/sane-checkout-action@v1
       - name: Set up JDK 11
         uses: actions/setup-java@v3
         with:
           distribution: "zulu"
           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 +81,7 @@ jobs:
       - uses: actions/checkout@v3
       - uses: actions/setup-python@v4
         with:
-          python-version: "3.7"
+          python-version: "3.10"
       - name: Download YQ
         uses: chrisdickinson/setup-yq@v1.0.1
         with:

.github/workflows/check-datahub-jars.yml

@@ -4,17 +4,13 @@ on:
   push:
     branches:
       - master
-    paths-ignore:
-      - "docker/**"
-      - "docs/**"
-      - "**.md"
+    paths:
+      - "metadata-integration"
   pull_request:
     branches:
-      - master
-    paths-ignore:
-      - "docker/**"
-      - "docs/**"
-      - "**.md"
+      - "**"
+    paths:
+      - "metadata-integration"
   release:
     types: [published]
 
@@ -28,25 +24,18 @@ 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
-        with:
-          fetch-depth: 800
+      - uses: hsheth2/sane-checkout-action@v1
       - name: Set up JDK 11
         uses: actions/setup-java@v3
         with:
           distribution: "zulu"
           java-version: 11
       - uses: actions/setup-python@v4
         with:
-          python-version: "3.7"
+          python-version: "3.10"
       - name: check ${{ matrix.command }} jar
         run: |
           ./gradlew :metadata-integration:java:${{ matrix.command }}:build --info

.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