Add multibyte search_path case conversion coverage#1206
Merged
gaoxueyu merged 1 commit intoIvorySQL:masterfrom Mar 12, 2026
Merged
Add multibyte search_path case conversion coverage#1206gaoxueyu merged 1 commit intoIvorySQL:masterfrom
gaoxueyu merged 1 commit intoIvorySQL:masterfrom
Conversation
Extend case_conversion.sql to cover multibyte quoted schema names through the search_path code path. The scenario now makes the active identifier_case_switch setting explicit, checks both interchange and normal behavior, and includes a failure case where a quoted schema name stops resolving once the case-conversion mode changes. Also removed the alternative file output, I suppose it was added by mistake because their diff was very small.
Contributor
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (3)
💤 Files with no reviewable changes (1)
📝 WalkthroughWalkthroughUpdates regression test fixtures for identifier case conversion feature, removing previous expectations from case_conversion_1.out and expanding case_conversion.out with new schema-based test sequences using Chinese character identifiers. Adds corresponding SQL test setup blocks in case_conversion.sql to exercise identifier_case_switch modes across schema and search_path operations. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly related PRs
Suggested reviewers
Poem
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@src/backend/utils/adt/varlena.c`:
- Around line 2757-2766: The code in identifier_case_transform_cstring wrongly
asserts that identifier_case_transform returns the same byte length; change the
check to allow a shorter result and copy only the transformed bytes plus the NUL
terminator instead of assuming equal length. Concretely, replace the
Assert(strlen(new_name) == len) with Assert(strlen(new_name) <= len) (or
equivalent) and use the transformed length (strlen(new_name)) when copying back
into ident (e.g. memcpy/strncpy of strlen(new_name)+1) so truncated names
produced by identifier_case_transform (via
upcase_identifier()/downcase_identifier()) are handled safely before
pfree(new_name).
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
Run ID: 502e88fc-d75d-48e9-89e7-473146567e34
📒 Files selected for processing (4)
src/backend/utils/adt/varlena.csrc/oracle_test/regress/expected/case_conversion.outsrc/oracle_test/regress/expected/case_conversion_1.outsrc/oracle_test/regress/sql/case_conversion.sql
💤 Files with no reviewable changes (1)
- src/oracle_test/regress/expected/case_conversion_1.out
cb1b0df to
be7f6e4
Compare
Contributor
Author
|
@coderabbitai full review |
Contributor
✅ Actions performedFull review triggered. |
Collaborator
yuanyl630
approved these changes
Mar 12, 2026
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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.
Extend case_conversion.sql to cover multibyte quoted schema names through the search_path code path. The scenario now makes the active identifier_case_switch setting explicit, checks both interchange and normal behavior, and includes a failure case where a quoted schema name stops resolving once the case-conversion mode changes.
Also removed the alternative file output, I suppose it was added by mistake because their diff was very small.
Summary by CodeRabbit