Merge branch 'master' into master

.dockerignore

@@ -1,6 +1,11 @@
 **/node_modules/
-datahub-frontend/build/
-metadata-ingestion/venv/
+*/build/
+*/*/build/
+**/venv/
+**/.tox/
+**/.mypy_cache/
+**/.pytest_cache/
+**/__pycache__/
 out
 **/*.class
 # Have to copy gradle/wrapper/gradle-wrapper.jar, can't exclude ALL jars

.github/actions/ci-optimization/action.yml

@@ -0,0 +1,92 @@
+name: 'Identify CI Optimizations'
+description: 'Determine if code changes are specific to certain modules.'
+
+outputs:
+  frontend-only:
+    description: "Frontend only change"
+    value: ${{ steps.filter.outputs.frontend == 'true' && steps.filter.outputs.ingestion == 'false' && steps.filter.outputs.backend == 'false' }}
+  ingestion-only:
+    description: "Ingestion only change"
+    value: ${{ steps.filter.outputs.frontend == 'false' && steps.filter.outputs.ingestion == 'true' && steps.filter.outputs.backend == 'false' }}
+  backend-only:
+    description: "Backend only change"
+    value: ${{ steps.filter.outputs.frontend == 'false' && steps.filter.outputs.ingestion == 'false' && steps.filter.outputs.backend == 'true' }}
+  backend-change:
+    description: "Backend code has changed"
+    value: ${{ steps.filter.outputs.backend == 'true' }}
+  ingestion-change:
+    description: "Ingestion code has changed"
+    value: ${{ steps.filter.outputs.ingestion == 'true' }}
+  ingestion-base-change:
+    description: "Ingestion base image docker image has changed"
+    value: ${{ steps.filter.outputs.ingestion-base == 'true' }}
+  frontend-change:
+    description: "Frontend code has changed"
+    value: ${{ steps.filter.outputs.frontend == 'true' }}
+  docker-change:
+    description: "Docker code has changed"
+    value: ${{ steps.filter.outputs.docker == 'true' }}
+  kafka-setup-change:
+    description: "Kafka setup docker change"
+    value: ${{ steps.filter.outputs.kafka-setup == 'true' }}
+  mysql-setup-change:
+    description: "Mysql setup docker change"
+    value: ${{ steps.filter.outputs.mysql-setup == 'true' }}
+  postgres-setup-change:
+    description: "Postgres setup docker change"
+    value: ${{ steps.filter.outputs.postgres-setup == 'true' }}
+  elasticsearch-setup-change:
+    description: "Elasticsearch setup docker change"
+    value: ${{ steps.filter.outputs.elasticsearch-setup == 'true' }}
+  smoke-test-change:
+    description: "Smoke test change"
+    value: ${{ steps.filter.outputs.smoke-test == 'true' }}
+runs:
+  using: "composite"
+  steps:
+    - uses: dorny/paths-filter@v2
+      id: filter
+      with:
+        filters: |
+          frontend:
+            - "datahub-frontend/**"
+            - "datahub-web-react/**"
+            - "smoke-test/tests/cypress/**"
+            - "docker/datahub-frontend/**"
+          ingestion:
+            - "metadata-ingestion-modules/**"
+            - "metadata-ingestion/**"
+            - "metadata-models/**"
+            - "smoke-test/**"
+            - "docker/datahub-ingestion**"
+          ingestion-base:
+            - "docker/datahub-ingestion-base/**"
+          docker:
+            - "docker/**"
+          backend:
+            - ".github/**"
+            - "metadata-models/**"
+            - "datahub-upgrade/**"
+            - "entity-registry/**"
+            - "li-utils/**"
+            - "metadata-auth/**"
+            - "metadata-dao-impl/**"
+            - "metadata-events/**"
+            - "metadata-io/**"
+            - "metadata-jobs/**"
+            - "metadata-service/**"
+            - "metadata-utils/**"
+            - "metadata-operation-context/**"
+            - "datahub-graphql-core/**"
+            - "smoke-test/**"
+            - "docker/**"
+          kafka-setup:
+            - "docker/kafka-setup/**"
+          mysql-setup:
+            - "docker/mysql-setup/**"
+          postgres-setup:
+            - "docker/postgres-setup/**"
+          elasticsearch-setup:
+            - "docker/elasticsearch-setup/**"
+          smoke-test:
+            - "smoke-test/**"

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

@@ -20,7 +20,7 @@ inputs:
     required: false
 
   images:
-    # e.g. linkedin/datahub-gms
+    # e.g. acryldata/datahub-gms
     description: "List of Docker images to use as base name for tags"
     required: true
   build-args:
@@ -55,7 +55,7 @@ runs:
 
     # 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
+      uses: docker/build-push-action@v5
       if: ${{ inputs.publish != 'true' }}
       with:
         context: ${{ inputs.context }}
@@ -70,27 +70,36 @@ runs:
         push: false
         cache-from: type=registry,ref=${{ 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
+      uses: docker/setup-qemu-action@v3
       if: ${{ inputs.publish == 'true' }}
     - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@v2
+      uses: docker/setup-buildx-action@v3
       if: ${{ inputs.publish == 'true' }}
     - name: Login to DockerHub
-      uses: docker/login-action@v2
+      uses: docker/login-action@v3
       if: ${{ inputs.publish == 'true' }}
       with:
         username: ${{ inputs.username }}
         password: ${{ inputs.password }}
     - name: Build and Push Multi-Platform image
-      uses: docker/build-push-action@v3
+      uses: docker/build-push-action@v5
       if: ${{ inputs.publish == 'true' }}
       with:
         context: ${{ inputs.context }}

.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/check_python_package.py

@@ -0,0 +1,33 @@
+import setuptools
+import os
+
+folders = ["./smoke-test/tests"]
+
+for folder in folders:
+    print(f"Checking folder {folder}")
+    packages = [i for i in setuptools.find_packages(folder) if "cypress" not in i]
+    namespace_packages = [
+        i for i in setuptools.find_namespace_packages(folder) if "cypress" not in i
+    ]
+
+    print("Packages found:", packages)
+    print("Namespace packages found:", namespace_packages)
+
+    in_packages_not_namespace = set(packages) - set(namespace_packages)
+    in_namespace_not_packages = set(namespace_packages) - set(packages)
+
+    if in_packages_not_namespace:
+        print(f"Packages not in namespace packages: {in_packages_not_namespace}")
+    if in_namespace_not_packages:
+        print(f"Namespace packages not in packages: {in_namespace_not_packages}")
+        for pkg in in_namespace_not_packages:
+            pkg_path = os.path.join(folder, pkg.replace(".", os.path.sep))
+            print(f"Contents of {pkg_path}:")
+            print(os.listdir(pkg_path))
+
+    assert (
+        len(in_packages_not_namespace) == 0
+    ), f"Found packages in {folder} that are not in namespace packages: {in_packages_not_namespace}"
+    assert (
+        len(in_namespace_not_packages) == 0
+    ), f"Found namespace packages in {folder} that are not in packages: {in_namespace_not_packages}"

.github/scripts/docker_helpers.sh

@@ -12,13 +12,29 @@ 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/\(.*\),\1-slim,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/\(.*\),\1-full,g' -e 's,refs/pull/\([0-9]*\).*,pr\1-full,g'),${SHORT_SHA}-full
 }
 
 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')
+    echo $(echo ${GITHUB_REF} | sed -e "s,refs/heads/${MAIN_BRANCH},1!0.0.0+docker.${SHORT_SHA},g" -e 's,refs/tags/v\(.*\),1!\1+docker,g' -e 's,refs/pull/\([0-9]*\).*,1!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/\(.*\),\1-slim,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/\(.*\),\1-full,g' -e 's,refs/pull/\([0-9]*\).*,pr\1-full,g')
+}

.github/workflows/airflow-plugin.yml

@@ -0,0 +1,104 @@
+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:
+          # Note: this should be kept in sync with tox.ini.
+          - 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~=2.4.3"
+            extra_pip_extras: plugin-v2,test-airflow24
+          - python-version: "3.10"
+            extra_pip_requirements: 'apache-airflow~=2.6.3 -c https://raw.githubusercontent.com/apache/airflow/constraints-2.6.3/constraints-3.10.txt'
+            extra_pip_extras: plugin-v2
+          - python-version: "3.10"
+            extra_pip_requirements: 'apache-airflow~=2.7.3 -c https://raw.githubusercontent.com/apache/airflow/constraints-2.7.3/constraints-3.10.txt'
+            extra_pip_extras: plugin-v2
+          - python-version: "3.10"
+            extra_pip_requirements: 'apache-airflow~=2.8.1 -c https://raw.githubusercontent.com/apache/airflow/constraints-2.8.1/constraints-3.10.txt'
+            extra_pip_extras: plugin-v2
+          - 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
+      fail-fast: false
+    steps:
+      - name: Set up JDK 17
+        uses: actions/setup-java@v3
+        with:
+          distribution: "zulu"
+          java-version: 17
+      - uses: gradle/actions/setup-gradle@v3
+      - uses: acryldata/sane-checkout-action@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:build
+      - 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
+            !**/binary/**
+      - name: Upload coverage to Codecov
+        if: always()
+        uses: codecov/codecov-action@v3
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+          directory: .
+          fail_ci_if_error: false
+          flags: airflow,airflow-${{ matrix.extra_pip_extras }}
+          name: pytest-airflow-${{ matrix.python-version }}-${{ matrix.extra_pip_requirements }}
+          verbose: true
+
+  event-file:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Upload
+        uses: actions/upload-artifact@v3
+        with:
+          name: Event File
+          path: ${{ github.event_path }}