feat: TableUtils to be compatible with DataPointer (part 1)

[tchow-zlai]

Summary

• Fixing some earlier bugs. Doing case matching on java isn't the same with scala classes.
• Adding a few more params to GCS format. Need the source URI, and the format string (which is basically the file format).
• Deleting some queries to INFORMATION_SCHEMA in GCS format. no longer needed since we are using the BQ Client.
• Adding some code to handle Spark InternalRows. We are using a low level impl to get at the InMemoryFileIndex which contains file partitions. It gives us internal rows so we need to translate that to rows, which involves the correct serialization based on the column types.
• Add a couple tests to BigQueryCatalogTest
• Adding a name field to Format
• Begin to migrate some TableUtils methods to delegate to DataPointer.
• https://app.asana.com/0/1208949807589885/1208960391734329/f
• https://app.asana.com/0/1208949807589885/1208960391734331/f

Checklist

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

Summary by CodeRabbit

• New Features

  • Enhanced BigQuery and GCS format handling with improved table name resolution and data source support.
  • Updated Spark table utilities with more robust data loading and management capabilities.
  • Introduced new methods for resolving table names and handling data formats.
  • Added support for new dependencies related to Google Cloud Dataproc.
  • Introduced unit tests for GCS format functionality.

• Bug Fixes

  • Improved error handling for data source formats and table operations.
  • Streamlined data pointer operations for better format compatibility.

• Refactor

  • Simplified data loading and schema retrieval methods.
  • Consolidated format handling logic in data source operations.
  • Enhanced organization and clarity in data pointer handling.
  • Cleaned up dependency declarations and project settings in build configuration.
  • Improved error handling and control flow in join computation processes.

[coderabbitai]

Warning

Rate limit exceeded

@tchow-zlai has exceeded the limit for the number of commits or files that can be reviewed per hour. Please wait 5 minutes and 43 seconds before requesting another review.

⌛ How to resolve this issue?

After the wait time has elapsed, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

We recommend that you space out your commits to avoid hitting the rate limit.

🚦 How do rate limits work?

CodeRabbit enforces hourly rate limits for each developer per organization.

Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout.

Please see our FAQ for further information.

📥 Commits

Reviewing files that changed from the base of the PR and between 3271f72 and 6f228f2.

📒 Files selected for processing (5)

• cloud_gcp/src/main/scala/ai/chronon/integrations/cloud_gcp/BigQueryFormat.scala (2 hunks)
• cloud_gcp/src/main/scala/ai/chronon/integrations/cloud_gcp/GCSFormat.scala (3 hunks)
• spark/src/main/scala/ai/chronon/spark/Driver.scala (1 hunks)
• spark/src/main/scala/ai/chronon/spark/Extensions.scala (2 hunks)
• spark/src/main/scala/ai/chronon/spark/TableUtils.scala (8 hunks)

Walkthrough

This pull request introduces significant enhancements to Chronon's cloud integration and data handling capabilities, focusing on Google Cloud Platform (GCP) services. The changes span multiple files, including BigQuery and GCS format providers, Spark utilities, and build configurations. The modifications improve data pointer handling, table management, and format resolution, with a particular emphasis on more robust and flexible data source interactions.

Changes

File	Change Summary
cloud_gcp/src/main/scala/.../BigQueryFormat.scala	- Added resolveTableName method - Updated readFormat and writeFormat methods - Refined table name and format resolution logic
cloud_gcp/src/main/scala/.../GCSFormat.scala	- Extended GCS case class with sourceUri and fileFormat - Simplified partition handling
cloud_gcp/test/.../BigQueryCatalogTest.scala	- Added new test cases for Google runtime classes - Enhanced configuration and integration tests
spark/src/main/scala/.../TableUtils.scala	- Removed preAggRepartition for RDDs - Added archiveTableIfExists method - Refactored data loading and schema retrieval
spark/src/main/scala/.../Extensions.scala	- Replaced DataPointerOps with DataPointerAwareDataFrameWriter and DataPointerAwareDataFrameReader - Improved data pointer handling
build.sbt	- Added Google Cloud BigDataOSS utility dependency

Suggested reviewers

• nikhil-zlai
• piyush-zlai
• david-zlai

Possibly related PRs

• feat: introduce BigQueryFormat #146: BigQuery format feature enhancement
• feat: GCS format support #147: GCS format support
• feat: TableUtils to be compatible with DataPointer (part 1) #158: DataPointer compatibility improvements

Poem

🌥️ In clouds of data, we dance and spin,

Formats transforming, where magic begins.

Pointers and formats, a digital art,

Chronon's code weaves, with algorithmic heart! 🚀

Refactoring magic, one line at a time.

---

🪧 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]

Caution

Inline review comments failed to post. This is likely due to GitHub's limits when posting large numbers of comments.

Actionable comments posted: 1

🧹 Nitpick comments (5)

cloud_gcp/src/main/scala/ai/chronon/integrations/cloud_gcp/BigQueryFormat.scala (2)

16-24: Comments clarify default project resolution.

---

36-36: Private method naming "format" might be ambiguous. Consider rename.

cloud_gcp/src/test/scala/ai/chronon/integrations/cloud_gcp/test/BigQueryCatalogTest.scala (3)

52-61: Ignored test indicates manual bigquery integration. Fine for local dev.

---

63-63: Another ignored test. Same rationale.

---

70-74: Print statements help verify partition logic.

🛑 Comments failed to post (1)

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

42-42: 💡 Codebase verification

Based on the code analysis, I can now provide a final response:

Add try-catch block around parquet read for better error handling

The parquet read operation in GCSFormat.scala could fail with various exceptions if sourceUri is incorrect:

• FileNotFoundException if path doesn't exist
• InvalidInputException for malformed URIs
• AccessDeniedException for permission issues

Add error handling to provide clear error messages to users.

🔗 Analysis chain

Might need error handling if sourceUri is incorrect.

---

Let me search for error handling patterns in the codebase.

---

Let me search for error handling patterns in the GCSFormat class and its parent class.

---

Let me check how parquet reads are handled in the codebase.

🏁 Scripts executed

The following scripts were executed for the analysis:

Error: No shell scripts found

---

Script:

#!/bin/bash
# Check the content of the file to understand the context
cat cloud_gcp/src/main/scala/ai/chronon/integrations/cloud_gcp/GCSFormat.scala

# Search for error handling patterns in Scala files
rg "try|catch|throw|error" --type scala -A 3

Length of output: 65727

---

Script:

#!/bin/bash
# Check if Format class has error handling for incorrect URIs
ast-grep --pattern 'class Format {
  $$$
  def parquet($uri: $_) {
    $$$
  }
  $$$
}'

# Search for any error handling around parquet reads
rg "parquet.*try|catch.*parquet" --type scala

Length of output: 137

---

Script:

#!/bin/bash
# Check GCSFormat implementation
cat cloud_gcp/src/main/scala/ai/chronon/integrations/cloud_gcp/GCSFormat.scala

# Search for parquet read patterns
rg "\.read\.parquet" --type scala -A 3

Length of output: 4637

[coderabbitai]

Caution

Inline review comments failed to post. This is likely due to GitHub's limits when posting large numbers of comments.

Actionable comments posted: 1

🧹 Nitpick comments (6)

cloud_gcp/src/main/scala/ai/chronon/integrations/cloud_gcp/BigQueryFormat.scala (2)

49-65: Enhance error handling for external table configuration.

Add null checks and more descriptive error messages for invalid URIs or format options.

 if (table.getDefinition.isInstanceOf[ExternalTableDefinition]) {
   val uris = table.getDefinition
     .asInstanceOf[ExternalTableDefinition]
     .getSourceUris
     .asScala
     .toList
     .map((uri) => uri.stripSuffix("/*") + "/")

-  assert(uris.length == 1, s"External table ${tableName} can be backed by only one URI.")
+  if (uris.isEmpty) {
+    throw new IllegalStateException(s"External table ${tableName} must have at least one source URI")
+  }
+  if (uris.length > 1) {
+    throw new IllegalStateException(s"External table ${tableName} can be backed by only one URI, found ${uris.length}")
+  }

   val formatStr = table.getDefinition
     .asInstanceOf[ExternalTableDefinition]
     .getFormatOptions
+    .getOrElse(throw new IllegalStateException(s"Format options not found for external table ${tableName}"))
     .asInstanceOf[FormatOptions]
     .getType

---

72-93: Remove commented federation code.

Consider moving this to a separate branch or documenting it elsewhere if needed for reference.

spark/src/main/scala/ai/chronon/spark/Extensions.scala (1)

300-339: Extract format strings as constants.

Move format strings to a companion object to improve maintainability.

object DataPointerAwareDataFrameWriter {
  val FORMAT_BIGQUERY = "bigquery"
  val FORMAT_SNOWFLAKE = "snowflake"
  val FORMAT_PARQUET = "parquet"
  val FORMAT_CSV = "csv"
  val FORMAT_HIVE = "hive"
  val FORMAT_DELTA = "delta"
  val FORMAT_ICEBERG = "iceberg"
}

spark/src/main/scala/ai/chronon/spark/TableUtils.scala (2)

136-136: Add error logging for table existence check.

Consider logging specific errors to aid debugging.

-Try(loadTable(tableName)).isSuccess
+Try(loadTable(tableName)).recoverWith { case e =>
+  logger.debug(s"Table $tableName does not exist: ${e.getMessage}")
+  Failure(e)
+}.isSuccess

---

Line range hint 650-659: Add table name length validation.

Long table names might exceed system limits after appending the timestamp.

 private def archiveTableIfExists(tableName: String, timestamp: Option[Instant]): Unit = {
   if (tableExists(tableName)) {
     val humanReadableTimestamp = archiveTimestampFormatter.format(timestamp.getOrElse(Instant.now()))
     val finalArchiveTableName = s"${tableName}_$humanReadableTimestamp"
+    if (finalArchiveTableName.length > 255) {
+      throw new IllegalArgumentException(s"Archived table name would exceed 255 characters: $finalArchiveTableName")
+    }
     val command = s"ALTER TABLE $tableName RENAME TO $finalArchiveTableName"
     logger.info(s"Archiving table with command: $command")
     sql(command)
   }
 }

spark/src/main/scala/ai/chronon/spark/JoinBase.scala (1)

497-501: Efficient small mode.
Combines ranges to reduce overhead. Could log memory usage.

🛑 Comments failed to post (1)

spark/src/main/scala/ai/chronon/spark/Extensions.scala (1)

341-374: 🛠️ Refactor suggestion

Extract common format handling logic.

Significant code duplication between reader and writer classes.

private object FormatHandler {
  def getReader(format: String, dfr: DataFrameReader, dp: DataPointer): DataFrame = {
    // Common format handling logic
  }
  
  def getWriter[T](format: String, dfw: DataFrameWriter[T], dp: DataPointer): Unit = {
    // Common format handling logic
  }
}