Retrieve source uri prefix from hive partitioning options when building the GCS format #204
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
WalkthroughThe pull request modifies the Changes
Possibly related PRs
Suggested Reviewers
Poem
Warning Review ran into problems🔥 ProblemsGitHub 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. 📜 Recent review detailsConfiguration used: CodeRabbit UI 📒 Files selected for processing (1)
🚧 Files skipped from review as they are similar to previous changes (1)
⏰ Context from checks skipped due to timeout of 90000ms (2)
🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
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)
Other keywords and placeholders
CodeRabbit Configuration File (
|
david-zlai
force-pushed
the
davidhan/fix_uri_suffix
branch
from
10a3af3 to
24e613a
Compare
tchow-zlai
reviewed
Jan 13, 2025
| val formatStr = table.getDefinition | ||
| .asInstanceOf[ExternalTableDefinition] | ||
| .getFormatOptions | ||
| .asInstanceOf[FormatOptions] | ||
| .getType | ||
|
|
||
| GCS(table.getTableId.getProject, uris.head, formatStr) | ||
| val uri = table.getDefinition |
There was a problem hiding this comment.
btw were you able to verify this works?
There was a problem hiding this comment.
There was a problem hiding this comment.
hmm think maybe we should do a fallback here? If the table isn't partitioned could we throw or go to the uri list?
tchow-zlai
approved these changes
Jan 13, 2025
david-zlai
changed the title
david-zlai
changed the title
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro (Legacy)
📒 Files selected for processing (1)
cloud_gcp/src/main/scala/ai/chronon/integrations/cloud_gcp/BigQueryFormat.scala(1 hunks)
🔇 Additional comments (1)
cloud_gcp/src/main/scala/ai/chronon/integrations/cloud_gcp/BigQueryFormat.scala (1)
68-73: Verify external table configurations in the codebase.Let's check for external table usage patterns.
✅ Verification successful
External table URI access is properly implemented
The code has appropriate type checking and is the only instance of external table URI access in the codebase.
🏁 Scripts executed
The following scripts were executed for the analysis:
Script:
#!/bin/bash # Search for external table configurations and usages rg -A 5 "ExternalTableDefinition|setHivePartitioningOptions|setSourceUris"Length of output: 2592
Script:
#!/bin/bash # Search for external table URI access patterns rg -A 3 "getSourceUris|getSourceUriPrefix|setSourceUriPrefix|setSourceUris|ExternalTableDefinition.*getUri"Length of output: 601
Comment on lines
68
to
72
| val uri = table.getDefinition | ||
| .asInstanceOf[ExternalTableDefinition] | ||
| .getHivePartitioningOptions | ||
| .getSourceUriPrefix | ||
|
|
There was a problem hiding this comment.
Add fallback for non-partitioned tables.
Direct use of getHivePartitioningOptions will fail for non-partitioned tables.
Add fallback to URI list:
- val uri = table.getDefinition
- .asInstanceOf[ExternalTableDefinition]
- .getHivePartitioningOptions
- .getSourceUriPrefix
+ val externalTable = table.getDefinition.asInstanceOf[ExternalTableDefinition]
+ val uri = Option(externalTable.getHivePartitioningOptions)
+ .map(_.getSourceUriPrefix)
+ .getOrElse {
+ val uris = externalTable.getSourceUris
+ require(uris.size == 1, s"Expected exactly one source URI, got ${uris.size}")
+ uris.get(0).replaceAll("/\\*\\.parquet$", "")
+ }📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| val uri = table.getDefinition | |
| .asInstanceOf[ExternalTableDefinition] | |
| .getHivePartitioningOptions | |
| .getSourceUriPrefix | |
| val externalTable = table.getDefinition.asInstanceOf[ExternalTableDefinition] | |
| val uri = Option(externalTable.getHivePartitioningOptions) | |
| .map(_.getSourceUriPrefix) | |
| .getOrElse { | |
| val uris = externalTable.getSourceUris | |
| require(uris.size == 1, s"Expected exactly one source URI, got ${uris.size}") | |
| uris.get(0).replaceAll("/\\*\\.parquet$", "") | |
| } |
There was a problem hiding this comment.
@david-zlai Thank you! Let me know if you need any further assistance! 😊
There was a problem hiding this comment.
@david-zlai I would if I could! But I'm just a code-reviewing rabbit. Perhaps I can help review more code while you grab that coffee? 🐰
(_/)
(>☕<)
/ >
tchow-zlai
reviewed
Jan 13, 2025
| ZIPLINE_GCP_DATAPROC_CLUSTER_NAME=canary-2 |
tchow-zlai
reviewed
Jan 13, 2025
| .getOrElse { | ||
| val uris = externalTable.getSourceUris | ||
| require(uris.size == 1, s"External table ${tableName} can be backed by only one URI.") | ||
| uris.get(0).replaceAll("/\\*\\.parquet$", "") |
There was a problem hiding this comment.
sounds good, thanks. Would be great to unit test this but not a big deal.
This was referenced Jan 16, 2025
4 tasks
Merged
4 tasks
kumar-zlai
pushed a commit
that referenced
this pull request
Apr 25, 2025
…ng the GCS format (#204) ## Summary ^^^ Context: Previously when using the source uri (not via hive partitioning options), we would run into spark load problems when given a gcs uri to our code that included a suffix of `/*.parquet`. See image below  Instead, we're going to use the `Hive Partitioning Source URI Prefix`. we don't have to strip the suffix for this one since this uri value should be the gcs root folder for the hive table ## Checklist - [ ] Added Unit Tests - [ ] Covered by existing CI - [ ] Integration tested - [ ] Documentation update <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit - **Improvements** - Enhanced BigQuery external table handling by simplifying source URI retrieval process. - **Bug Fixes** - Corrected string formatting in the print statement for clarity. - Adjusted indentation for consistency in code formatting. - **Chores** - Updated environment variable `ZIPLINE_GCP_DATAPROC_CLUSTER_NAME` from `zipline-canary-cluster` to `canary-2`. <!-- end of auto-generated comment: release notes by coderabbit.ai -->
kumar-zlai
pushed a commit
that referenced
this pull request
Apr 29, 2025
…ng the GCS format (#204) ## Summary ^^^ Context: Previously when using the source uri (not via hive partitioning options), we would run into spark load problems when given a gcs uri to our code that included a suffix of `/*.parquet`. See image below  Instead, we're going to use the `Hive Partitioning Source URI Prefix`. we don't have to strip the suffix for this one since this uri value should be the gcs root folder for the hive table ## Checklist - [ ] Added Unit Tests - [ ] Covered by existing CI - [ ] Integration tested - [ ] Documentation update <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit - **Improvements** - Enhanced BigQuery external table handling by simplifying source URI retrieval process. - **Bug Fixes** - Corrected string formatting in the print statement for clarity. - Adjusted indentation for consistency in code formatting. - **Chores** - Updated environment variable `ZIPLINE_GCP_DATAPROC_CLUSTER_NAME` from `zipline-canary-cluster` to `canary-2`. <!-- end of auto-generated comment: release notes by coderabbit.ai -->
chewy-zlai
pushed a commit
that referenced
this pull request
May 15, 2025
…ng the GCS format (#204) ## Summary ^^^ Context: Previously when using the source uri (not via hive partitioning options), we would run into spark load problems when given a gcs uri to our code that included a suffix of `/*.parquet`. See image below  Instead, we're going to use the `Hive Partitioning Source URI Prefix`. we don't have to strip the suffix for this one since this uri value should be the gcs root folder for the hive table ## Checklist - [ ] Added Unit Tests - [ ] Covered by existing CI - [ ] Integration tested - [ ] Documentation update <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit - **Improvements** - Enhanced BigQuery external table handling by simplifying source URI retrieval process. - **Bug Fixes** - Corrected string formatting in the print statement for clarity. - Adjusted indentation for consistency in code formatting. - **Chores** - Updated environment variable `ZIPLINE_GCP_DATAPROC_CLUSTER_NAME` from `zipline-canary-cluster` to `canary-2`. <!-- end of auto-generated comment: release notes by coderabbit.ai -->
chewy-zlai
pushed a commit
that referenced
this pull request
May 16, 2025
…ng the GCS format (#204) ## Summary ^^^ Context: Previously when using the source uri (not via hive partitioning options), we would run into spark load problems when given a gcs uri to our code that included a suffix of `/*.parquet`. See image below  Instead, we're going to use the `Hive Partitioning Source URI Prefix`. we don't have to strip the suffix for this one since this uri value should be the gcs root folder for the hive table ## Cheour clientslist - [ ] Added Unit Tests - [ ] Covered by existing CI - [ ] Integration tested - [ ] Documentation update <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit - **Improvements** - Enhanced BigQuery external table handling by simplifying source URI retrieval process. - **Bug Fixes** - Corrected string formatting in the print statement for clarity. - Adjusted indentation for consistency in code formatting. - **Chores** - Updated environment variable `ZIPLINE_GCP_DATAPROC_CLUSTER_NAME` from `zipline-canary-cluster` to `canary-2`. <!-- end of auto-generated comment: release notes by coderabbit.ai -->
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
^^^
Context: Previously when using the source uri (not via hive partitioning options), we would run into spark load problems when given a gcs uri to our code that included a suffix of
/*.parquet. See image belowInstead, we're going to use the
Hive Partitioning Source URI Prefix. we don't have to strip the suffix for this one since this uri value should be the gcs root folder for the hive tableChecklist
Summary by CodeRabbit
ZIPLINE_GCP_DATAPROC_CLUSTER_NAMEfromzipline-canary-clustertocanary-2.