[fix] Use indirect writemethod for BigQuery writes to actually output partitioned tables.

[david-zlai]

… partitioned tables.

Summary

Checklist

• Added Unit Tests
• Covered by existing CI
• Integration tested
• Documentation update

Summary by CodeRabbit

• Bug Fixes
  • Improved BigQuery data writing method to support partitioned tables by changing the write method from "direct" to "indirect".

[coderabbitai]

Walkthrough

The pull request modifies the writeFormat method in the GcpFormatProvider class, specifically changing the BigQuery write method from "direct" to "indirect". This change addresses an issue with writing partitioned tables, ensuring that the indirect method is used to properly handle partitioned data when writing to BigQuery.

Changes

File	Change Summary
cloud_gcp/src/main/scala/ai/chronon/integrations/cloud_gcp/GcpFormatProvider.scala	Updated writeFormat method to use "indirect" write method for BigQuery, resolving partitioned table output limitations

Possibly related PRs

• feat: introduce BigQueryFormat #146: Initial introduction of the GCPFormatProvider class
• for bigquery table spark jobs, add transient to unblock serialization issues and do not create table when attempting to insert #174: Addressing BigQuery serialization and table creation issues
• fix: handle partition overwrite #206: Handling partition overwrites in BigQuery writes

Suggested Reviewers

• piyush-zlai
• nikhil-zlai
• chewy-zlai

Poem

🚀 Indirect paths we now explore,
Where partitions once hit a wall before,
BigQuery's data flows with grace,
A subtle change in writing's embrace,
Code transforms with wisdom's core! 📊

Warning

Review ran into problems

🔥 Problems

GitHub Actions: Resource not accessible by integration - https://docs.github.com/rest/actions/workflow-runs#list-workflow-runs-for-a-repository.

Please grant the required permissions to the CodeRabbit GitHub App under the organization or repository settings.

---

🪧 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.

[coderabbitai]

Actionable comments posted: 0

🧹 Nitpick comments (1)

cloud_gcp/src/main/scala/ai/chronon/integrations/cloud_gcp/GcpFormatProvider.scala (1)

51-52: Consider tracking the TODO as a separate issue.

The comment references PR #1320 which might eliminate the need for temporary GCS bucket config.

Want me to create an issue to track this TODO?

📜 Review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro (Legacy)

📥 Commits

Reviewing files that changed from the base of the PR and between f2f5867 and c52cfbf.

📒 Files selected for processing (1)

• cloud_gcp/src/main/scala/ai/chronon/integrations/cloud_gcp/GcpFormatProvider.scala (1 hunks)

⏰ Context from checks skipped due to timeout of 90000ms (1)

• GitHub Check: scala_compile_fmt_fix

🔇 Additional comments (1)

cloud_gcp/src/main/scala/ai/chronon/integrations/cloud_gcp/GcpFormatProvider.scala (1)

53-53: LGTM! Fix for partitioned tables.

The change from direct to indirect write method correctly addresses the partitioned tables issue.

Let's verify the impact:

✅ Verification successful

Verified: Single centralized writeMethod configuration

The indirect writeMethod setting is correctly configured in the centralized GcpFormatProvider and no other instances require updates.

🏁 Scripts executed

The following scripts were executed for the analysis:

Script:

#!/bin/bash
# Search for any other direct write method configurations that might need updating
rg -i "writeMethod.*direct" 

Length of output: 223

---

Script:

#!/bin/bash
# Search for BigQuery-related configurations
rg -i "bigquery|writeformat" -A 2 -B 2

Length of output: 44157