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.

Sign up for GitHub

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

Jump to bottom

fix(model): bigquery, avoid fetching duplicated fields when fetching it #1054

Merged
merged 1 commit into from
Feb 5, 2025
Merged

fix(model): bigquery, avoid fetching duplicated fields when fetching it #1054

merged 1 commit into from
Feb 5, 2025

Conversation

sebastien-boulle
Copy link
Contributor

@sebastien-boulle sebastien-boulle commented Feb 4, 2025 •
edited by coderabbitai bot
Loading

The issue is present since the implementation of the connector. It's trigger on our bigquery tables because we have partitionned tables.

Indeed the TABLE_OPTIONS view can have multiple entries for each field (in our case the description and the require_partition_filter values) thus with the left join fields were present for each entry in the TABLE_OPTIONS.

So only join of the value that we want i.e. the description.

This was leading to breaking the import of the metadata later because fields were duplicated.

Summary by CodeRabbit

  • Bug Fixes
    • Refined the process that retrieves table descriptions, ensuring that only valid details are included. This update improves the accuracy of metadata displayed for tables in BigQuery.

@sebastien-boulle
fix(model): bigquery, avoid fetching duplicated fields when fetching it
2744bda 
The issue is present since the implementation of the connector.
It's trigger on our bigquery tables because we have partitionned tables.

Indeed the TABLE_OPTIONS view can have multiple entries for each field
(in our case the description and the require_partition_filter values)
thus with the left join fields were present for each entry in the
TABLE_OPTIONS.

So only join of the value that we want i.e. the description.

This was leading to breaking the import of the metadata later because
fields were duplicated.
@coderabbitai coderabbitai
Copy link

coderabbitai bot commented Feb 4, 2025 •
edited
Loading

Walkthrough

The change updates the SQL query in the get_table_list method of the BigQueryMetadata class. The join condition for the TABLE_OPTIONS table now includes an additional filter (OPTION_NAME = 'description'), which refines the data retrieved for the table_description field. No other functional or public API changes were made.

Changes

File Path Summary
ibis-server/.../bigquery.py Modified the SQL join condition in get_table_list to include a filter for OPTION_NAME = 'description'

Possibly related PRs

Suggested labels

bigquery, ibis, python

Suggested reviewers

  • goldmedal

Poem

I'm a rabbit with a coding flair,
Hopping through queries with a gentle air.
SQL joins now filter with refined precision,
Guiding data on its fresh new mission.
Here's to neat changes and smooth revision!
🐰💻

Tip

🌐 Web search-backed reviews and chat
  • We have enabled web search-based reviews and chat for all users. This feature allows CodeRabbit to access the latest documentation and information on the web.
  • You can disable this feature by setting web_search: false in the knowledge_base settings.
  • Please share any feedback in the Discord discussion.
📜 Recent review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between fe58251 and 2744bda.

📒 Files selected for processing (1)
  • ibis-server/app/model/metadata/bigquery.py (1 hunks)
🔇 Additional comments (2)
ibis-server/app/model/metadata/bigquery.py (2)

50-51: LGTM! The join condition fix effectively prevents field duplication.

The added condition table_options.OPTION_NAME = 'description' in the LEFT JOIN correctly addresses the issue of duplicated fields in partitioned tables by ensuring only the description field is fetched from TABLE_OPTIONS.

22-55: Verify the query results in BigQuery.

The SQL query modification looks correct. To ensure it works as expected, please verify that:

  1. The query returns exactly one description per table
  2. No table descriptions are missing after adding the filter

Run this query in BigQuery to validate the results:

✨ Finishing Touches
  • 📝 Generate Docstrings (Beta)

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:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>, please review it.
    • Generate unit testing code for this file.
    • Open a follow-up GitHub issue for this discussion.
  • 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 generate docstrings to generate docstrings for this PR. (Beta)
  • @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.

@github-actions github-actions bot added bigquery ibis python Pull requests that update Python code labels Feb 4, 2025
goldmedal
goldmedal approved these changes Feb 5, 2025
View reviewed changes
Copy link
Contributor

@goldmedal goldmedal left a comment

Choose a reason for hiding this comment

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

Thanks @sebastien-boulle. It makes sense to me. 👍

@goldmedal goldmedal merged commit 3b29a43 into Canner:main Feb 5, 2025
6 of 7 checks passed
@sebastien-boulle sebastien-boulle deleted the fix/bigquery-avoid-duplicate branch February 5, 2025 06:56
@sebastien-boulle
Copy link
Contributor Author

Thanks @sebastien-boulle. It makes sense to me. 👍

Thanks for the review @goldmedal. Should I do the submodule update PR in #canner/wrenai ?

@goldmedal
Copy link
Contributor

Thanks for the review @goldmedal. Should I do the submodule update PR in #canner/wrenai ?

You don't need to do that. This change will be included in the next release. Wren AI will use the latest image directly.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@goldmedal goldmedal goldmedal approved these changes

Assignees
No one assigned
Labels
bigquery ibis python Pull requests that update Python code
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@sebastien-boulle @goldmedal