Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

CI: Follow-up PR for SDM workflow #85

Merged
merged 2 commits into from
Nov 22, 2024
Merged

Conversation

aaronsteers
Copy link
Contributor

@aaronsteers aaronsteers commented Nov 22, 2024

Creating this PR to fix any issues and follow-up from:

Manual tests confirmed:

Summary by CodeRabbit

  • New Features

    • Enhanced version handling for the Source-Declarative-Manifest (SDM) connector during DockerHub publishing.
    • Introduced default versioning to streamline the build process.
  • Bug Fixes

    • Improved validation logic for version settings to ensure successful workflow exits under specific conditions.
  • Chores

    • Updated conditions for checking existing tags and building Docker images to enhance reliability.

@aaronsteers aaronsteers changed the title failover to '0.0.0dev0' if version not set Follow-up PR for SDM workflow Nov 22, 2024
@aaronsteers aaronsteers marked this pull request as ready for review November 22, 2024 19:57
Copy link
Contributor

coderabbitai bot commented Nov 22, 2024

📝 Walkthrough
📝 Walkthrough

Walkthrough

The modifications to the .github/workflows/publish_sdm_connector.yml file enhance the workflow for publishing the Source-Declarative-Manifest (SDM) connector to DockerHub. Key updates include the introduction of a default version for the package build step, improved version validation logic, and adjustments to the Docker image publishing process to ensure proper handling of versioning and tag checks.

Changes

File Path Change Summary
.github/workflows/publish_sdm_connector.yml - Default version '0.0.0dev0' used if VERSION is not set.
- Enhanced validation to exit if both detected and input versions are empty.
- Adjusted DockerHub tag checks to ensure non-empty tags before proceeding.
- Conditions added for version checks and dry run mode during image build and push.

Possibly related issues

Possibly related PRs

Suggested labels

ci

Suggested reviewers

  • ChristoGrab

📜 Recent review details

Configuration used: CodeRabbit UI
Review profile: CHILL

📥 Commits

Reviewing files that changed from the base of the PR and between 47c9341 and f858db2.

📒 Files selected for processing (1)
  • .github/workflows/publish_sdm_connector.yml (2 hunks)
🚧 Files skipped from review as they are similar to previous changes (1)
  • .github/workflows/publish_sdm_connector.yml

Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?

❤️ Share
🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

‼️ IMPORTANT
Auto-reply has been disabled for this repository in the CodeRabbit settings. The CodeRabbit bot will not respond to your replies unless it is explicitly tagged.

  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai generate unit testing code for this file.
    • @coderabbitai modularize this function.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read src/utils.ts and generate unit testing code.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

  • You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
  • Please see the configuration documentation for more information.
  • If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

Copy link
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 0

🧹 Outside diff range and nitpick comments (2)
.github/workflows/publish_sdm_connector.yml (2)

Line range hint 134-146: Simplify the tag existence check

The tag check has a few potential improvements:

  1. The empty tag error seems misplaced since we already check if: env.VERSION != ''
  2. We could extract the tag into a variable at the job level for reuse

Would you consider this refactor?

       - name: "Check for existing tag (version: ${{ env.VERSION || 'none' }} )"
         if: env.VERSION != ''
         run: |
-          tag="airbyte/source-declarative-manifest:${{ env.VERSION }}"
-          if [ -z "$tag" ]; then
-            echo "Error: VERSION is not set. Ensure the tag follows the format 'refs/tags/vX.Y.Z'."
-            exit 1
-          fi
+          tag="airbyte/source-declarative-manifest:${{ env.VERSION }}"
           echo "Checking if tag '$tag' exists on DockerHub..."
           if DOCKER_CLI_EXPERIMENTAL=enabled docker manifest inspect "$tag" > /dev/null 2>&1; then
             echo "The tag '$tag' already exists on DockerHub. Skipping publish."
             exit 1
           fi
           echo "No existing tag '$tag' found. Proceeding with publish."
+          echo "DOCKER_TAG=${tag}" >> $GITHUB_ENV

Line range hint 148-190: Consider using a matrix strategy for build configurations

I notice we have three similar build-push steps with identical platform configurations. What if we used a matrix strategy to reduce duplication? Here's a thought:

      - name: Set up build matrix
        id: matrix
        run: |
          tags=()
          if [ -z "$VERSION" ]; then
            tags+=("${{ github.sha }}")
          else
            tags+=("$VERSION")
            if [ "$IS_PRERELEASE" = "false" ]; then
              tags+=("latest")
            fi
          fi
          echo "tags=${tags[@]}" >> $GITHUB_OUTPUT

      - name: Build and push
        if: github.event.inputs.dry_run == 'false'
        uses: docker/build-push-action@v5
        with:
          context: .
          platforms: linux/amd64,linux/arm64
          push: true
          tags: airbyte/source-declarative-manifest:${{ matrix.tag }}
        strategy:
          matrix:
            tag: ${{ fromJson(steps.matrix.outputs.tags) }}

This would make the workflow more maintainable and easier to extend with new architectures or tags. What are your thoughts on this approach? 🤔

📜 Review details

Configuration used: CodeRabbit UI
Review profile: CHILL

📥 Commits

Reviewing files that changed from the base of the PR and between e52bde4 and 47c9341.

📒 Files selected for processing (1)
  • .github/workflows/publish_sdm_connector.yml (1 hunks)
🔇 Additional comments (1)
.github/workflows/publish_sdm_connector.yml (1)

81-81: Consider documenting the default version behavior

Hey! I notice we're using '0.0.0dev0' as a default version. While this is a good safeguard, what do you think about:

  1. Adding a comment explaining when this default is used?
  2. Ensuring it follows semver format (maybe '0.0.0-dev.0')?

wdyt? 🤔

Let's check if this version format is consistent with other parts of the codebase:

Also applies to: 85-85

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant