airbyte-ci format: make most inputs optional in run-airbyte-ci (#37683)

alafanechere · web-flow · commit 9c8fd80f2c13 · 2024-04-30T17:42:51.000+02:00
diff --git a/.github/actions/install-airbyte-ci/action.yml b/.github/actions/install-airbyte-ci/action.yml
@@ -36,8 +36,10 @@ runs:
         if [[ "${{ github.ref }}" != "refs/heads/master" ]] && [[ "${{ steps.changes.outputs.pipelines_any_changed }}" == "true" ]]; then
           echo "Making changes to Airbyte CI on a non-master branch. Airbyte-CI will be installed from source."
           echo "install-mode=source" >> $GITHUB_OUTPUT
+          echo "SENTRY_ENVIRONMENT=dev" >> $GITHUB_ENV
         else
           echo "install-mode=binary" >> $GITHUB_OUTPUT
+          echo "SENTRY_ENVIRONMENT=production" >> $GITHUB_ENV
         fi
 
     - name: Install Airbyte CI from binary
diff --git a/.github/actions/run-airbyte-ci/action.yml b/.github/actions/run-airbyte-ci/action.yml
@@ -9,16 +9,16 @@ inputs:
     required: true
   github_token:
     description: "GitHub token"
-    required: true
+    required: false
   dagger_cloud_token:
     description: "Dagger Cloud token"
-    required: true
+    required: false
   docker_hub_username:
     description: "Dockerhub username"
-    required: true
+    required: false
   docker_hub_password:
     description: "Dockerhub password"
-    required: true
+    required: false
   options:
     description: "Options for the subcommand"
     required: false
@@ -93,15 +93,14 @@ runs:
     - name: Get start timestamp
       id: get-start-timestamp
       shell: bash
-      run: echo "name=start-timestamp=$(date +%s)" >> $GITHUB_OUTPUT
-
+      run: echo "start-timestamp=$(date +%s)" >> $GITHUB_OUTPUT
     - name: Docker login
       id: docker-login
       uses: docker/login-action@v3
+      if: ${{ inputs.docker_hub_username != '' && inputs.docker_hub_password != '' }}
       with:
         username: ${{ inputs.docker_hub_username }}
         password: ${{ inputs.docker_hub_password }}
-
     - name: Install Airbyte CI
       id: install-airbyte-ci
       uses: ./.github/actions/install-airbyte-ci
@@ -111,19 +110,19 @@ runs:
     - name: Run airbyte-ci
       id: run-airbyte-ci
       shell: bash
-      run: |
-        airbyte-ci --disable-update-check --disable-dagger-run --is-ci --gha-workflow-run-id=${{ github.run_id }} ${{ inputs.subcommand }} ${{ inputs.options }}
       env:
+        CI: "True"
+        CI_GIT_USER: ${{ github.repository_owner }}
+        CI_PIPELINE_START_TIMESTAMP: ${{ steps.get-start-timestamp.outputs.start-timestamp }}
+        PULL_REQUEST_NUMBER: ${{ github.event.pull_request.number }}
+        # Next environment variables are workflow inputs based and can be set with empty values if the inputs are not required and passed
         CI_CONTEXT: "${{ inputs.context }}"
-        CI_GIT_REPO_URL: ${{ inputs.git_repo_url }}
         CI_GIT_BRANCH: ${{ inputs.git_branch || github.head_ref }}
+        CI_GIT_REPO_URL: ${{ inputs.git_repo_url }}
         CI_GIT_REVISION: ${{ inputs.git_revision || github.sha }}
-        CI_GIT_USER: ${{ github.repository_owner }}
         CI_GITHUB_ACCESS_TOKEN: ${{ inputs.github_token }}
         CI_JOB_KEY: ${{ inputs.ci_job_key }}
-        CI_PIPELINE_START_TIMESTAMP: ${{ steps.get-start-timestamp.outputs.start-timestamp }}
         CI_REPORT_BUCKET_NAME: ${{ inputs.report_bucket_name }}
-        CI: "True"
         DAGGER_CLOUD_TOKEN: "${{ inputs.dagger_cloud_token }}"
         DOCKER_HUB_PASSWORD: ${{ inputs.docker_hub_password }}
         DOCKER_HUB_USERNAME: ${{ inputs.docker_hub_username }}
@@ -133,47 +132,46 @@ runs:
         METADATA_SERVICE_BUCKET_NAME: ${{ inputs.metadata_service_bucket_name }}
         METADATA_SERVICE_GCS_CREDENTIALS: ${{ inputs.metadata_service_gcs_credentials }}
         PRODUCTION: ${{ inputs.production }}
-        PULL_REQUEST_NUMBER: ${{ github.event.pull_request.number }}
         PYTHON_REGISTRY_TOKEN: ${{ inputs.python_registry_token }}
         PYTHON_REGISTRY_URL: ${{ inputs.python_registry_url }}
-        PYTHON_REGISTRY_CHECK_URL: ${{ inputs.python_registry_check_url }}
         S3_BUILD_CACHE_ACCESS_KEY_ID: ${{ inputs.s3_build_cache_access_key_id }}
         S3_BUILD_CACHE_SECRET_KEY: ${{ inputs.s3_build_cache_secret_key }}
         SENTRY_DSN: ${{ inputs.sentry_dsn }}
-        SENTRY_ENVIRONMENT: ${{ steps.determine-install-mode.outputs.install-mode }}
         SLACK_WEBHOOK: ${{ inputs.slack_webhook_url }}
         SPEC_CACHE_BUCKET_NAME: ${{ inputs.spec_cache_bucket_name }}
         SPEC_CACHE_GCS_CREDENTIALS: ${{ inputs.spec_cache_gcs_credentials }}
-    # give the Dagger Engine more time to push cache data to Dagger Cloud
+      run: |
+        airbyte-ci --disable-update-check --disable-dagger-run --is-ci --gha-workflow-run-id=${{ github.run_id }} ${{ inputs.subcommand }} ${{ inputs.options }}
     - name: Stop Engine
       id: stop-engine
       if: always()
       shell: bash
       run: |
         mapfile -t containers < <(docker ps --filter name="dagger-engine-*" -q)
         if [[ "${#containers[@]}" -gt 0 ]]; then
+          # give 5mn to the Dagger Engine to push cache data to Dagger Cloud
           docker stop -t 300 "${containers[@]}";
         fi
 
-    - name: Collect docker logs on failure
-      id: collect-docker-logs
+    - name: Collect dagger engine logs
+      id: collect-dagger-engine-logs
       if: always()
       uses: jwalton/gh-docker-logs@v2
       with:
-        dest: "./docker_logs"
+        dest: "./dagger_engine_logs"
         images: "registry.dagger.io/engine"
 
     - name: Tar logs
       id: tar-logs
       if: always()
       shell: bash
-      run: tar cvzf ./docker_logs.tgz ./docker_logs
+      run: tar cvzf ./dagger_engine_logs.tgz ./dagger_engine_logs
 
     - name: Upload logs to GitHub
-      id: upload-docker-logs
+      id: upload-dagger-engine-logs
       if: always()
       uses: actions/upload-artifact@v4
       with:
-        name: docker_logs.tgz
-        path: ./docker_logs.tgz
+        name: dagger_engine_logs.tgz
+        path: ./dagger_engine_logs.tgz
         retention-days: 7
diff --git a/.github/workflows/community_ci.yml b/.github/workflows/community_ci.yml
@@ -21,6 +21,43 @@ on:
       - "master"
 
 jobs:
+  format_check:
+    # IMPORTANT: This name must match the require check name on the branch protection settings
+    name: "Check for formatting errors"
+    if: github.event.pull_request.head.repo.fork == true
+    environment: community-ci-auto
+    runs-on: community-tooling-test-small
+    timeout-minutes: 30s
+    env:
+      MAIN_BRANCH_NAME: "master"
+    steps:
+      # This checkouts a fork which can contain untrusted code
+      # It's deemed safe as the formatter are not executing any checked out code
+      - name: Checkout fork
+        uses: actions/checkout@v4
+        with:
+          repository: ${{ github.event.pull_request.head.repo.full_name }}
+          ref: ${{ github.event.pull_request.head.sha }}
+          fetch-depth: 1
+
+      # This will sync the .github folder of the main repo with the fork
+      # This allows us to use up to date actions from the main repo
+      - name: Pull .github folder from main repository
+        id: pull_github_folder
+        run: |
+          git remote add main https://github.com/airbytehq/airbyte.git
+          git fetch main ${MAIN_BRANCH_NAME}
+          git checkout main/${MAIN_BRANCH_NAME} -- .github
+
+      - name: Run airbyte-ci format check all
+        # This path refers to the fork .github folder.
+        # We make sure its content is in sync with the main repo .github folder by pulling it in the previous step
+        uses: ./.github/actions/run-airbyte-ci
+        with:
+          context: "pull_request"
+          sentry_dsn: ${{ secrets.SENTRY_AIRBYTE_CI_DSN }}
+          subcommand: "format check all"
+          is_fork: "true"
   connectors_test:
     name: Run connectors tests on fork
     if: github.event.pull_request.head.repo.fork == true
diff --git a/.github/workflows/connectors_tests.yml b/.github/workflows/connectors_tests.yml
@@ -63,7 +63,7 @@ jobs:
     # We only run the Connectors CI job if there are changes to the connectors on a non-forked PR
     # Forked PRs are handled by the community_ci.yml workflow
     # If the condition is not met the job will be skipped (it will not fail)
-    if: needs.changes.outputs.connectors == 'true' && github.event.pull_request.head.repo.fork != true
+    if: (github.event_name == 'pull_request' && needs.changes.outputs.connectors == 'true' && github.event.pull_request.head.repo.fork != true) || github.event_name == 'workflow_dispatch'
     name: Connectors CI
     runs-on: connector-test-large
     timeout-minutes: 360 # 6 hours
diff --git a/.github/workflows/format_check.yml b/.github/workflows/format_check.yml
@@ -30,12 +30,7 @@ jobs:
         continue-on-error: true
         with:
           context: "master"
-          dagger_cloud_token: ${{ secrets.DAGGER_CLOUD_TOKEN_2 }}
-          docker_hub_password: ${{ secrets.DOCKER_HUB_PASSWORD }}
-          docker_hub_username: ${{ secrets.DOCKER_HUB_USERNAME }}
-          gcs_credentials: ${{ secrets.METADATA_SERVICE_PROD_GCS_CREDENTIALS }}
           sentry_dsn: ${{ secrets.SENTRY_AIRBYTE_CI_DSN }}
-          github_token: ${{ secrets.GH_PAT_MAINTENANCE_OCTAVIA }}
           subcommand: "format check all"
 
       - name: Run airbyte-ci format check [PULL REQUEST]
@@ -45,12 +40,7 @@ jobs:
         continue-on-error: false
         with:
           context: "pull_request"
-          dagger_cloud_token: ${{ secrets.DAGGER_CLOUD_TOKEN_2 }}
-          docker_hub_password: ${{ secrets.DOCKER_HUB_PASSWORD }}
-          docker_hub_username: ${{ secrets.DOCKER_HUB_USERNAME }}
-          gcs_credentials: ${{ secrets.METADATA_SERVICE_PROD_GCS_CREDENTIALS }}
           sentry_dsn: ${{ secrets.SENTRY_AIRBYTE_CI_DSN }}
-          github_token: ${{ secrets.GH_PAT_MAINTENANCE_OCTAVIA }}
           subcommand: "format check all"
 
       - name: Run airbyte-ci format check [WORKFLOW DISPATCH]
@@ -60,12 +50,7 @@ jobs:
         continue-on-error: false
         with:
           context: "manual"
-          dagger_cloud_token: ${{ secrets.DAGGER_CLOUD_TOKEN_2 }}
-          docker_hub_password: ${{ secrets.DOCKER_HUB_PASSWORD }}
-          docker_hub_username: ${{ secrets.DOCKER_HUB_USERNAME }}
-          gcs_credentials: ${{ secrets.METADATA_SERVICE_PROD_GCS_CREDENTIALS }}
           sentry_dsn: ${{ secrets.SENTRY_AIRBYTE_CI_DSN }}
-          github_token: ${{ secrets.GH_PAT_MAINTENANCE_OCTAVIA }}
           subcommand: "format check all"
 
       - name: Match GitHub User to Slack User [MASTER]
@@ -77,7 +62,7 @@ jobs:
           GITHUB_API_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Format Failure on Master Slack Channel [MASTER]
-        if: steps.airbyte_ci_format_check_all.outcome == 'failure' && github.ref == 'refs/heads/master'
+        if: steps.airbyte_ci_format_check_all_master.outcome == 'failure' && github.ref == 'refs/heads/master'
         uses: abinoda/slack-action@master
         env:
           SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN_AIRBYTE_TEAM }}
@@ -90,35 +75,3 @@ jobs:
             {\"type\":\"section\",\"text\":{\"type\":\"mrkdwn\",\"text\":\"<@${{ steps.match-github-to-slack-user.outputs.slack_user_ids }}> \n\"}},
             {\"type\":\"section\",\"text\":{\"type\":\"mrkdwn\",\"text\":\" :octavia-shocked: <https://github.com/${{github.repository}}/actions/runs/${{github.run_id}}|View Action Run> :octavia-shocked: \n\"}},
             {\"type\":\"divider\"}]}
-
-  # TODO alafanechere: move it to community_ci.yml and make it use the run-airbyte-ci action
-  format-check-from-forks:
-    # Same-named job as above, in order to ensure 'required checks' pass either way.
-    # This should run all the same checks as above, except not requiring any credentials.
-    name: "Check for formatting errors"
-    if: >
-      github.event.pull_request.head.repo.fork == true
-    runs-on: ubuntu-latest
-    steps:
-      # We have no creds. Ignore docker caching and just run the CLI.
-      - name: Checkout code (Unprivileged)
-        uses: actions/checkout@v4
-        with:
-          ref: ${{ github.event.pull_request.head.ref }}
-          repository: ${{ github.event.pull_request.head.repo.full_name }}
-          fetch-depth: 1
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.10"
-
-      - name: Install Airbyte CI from binary
-        id: install-airbyte-ci-binary
-        shell: bash
-        run: |
-          curl -sSL "https://connectors.airbyte.com/airbyte-ci/releases/ubuntu/latest/airbyte-ci" --output airbyte-ci-bin
-          sudo mv airbyte-ci-bin /usr/local/bin/airbyte-ci
-          sudo chmod +x /usr/local/bin/airbyte-ci
-      - name: Run format checks
-        run: |
-          /usr/local/bin/airbyte-ci --disable-update-check format check all
