chore: Merge upstream changes #10
Open
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
…etsentry#134) The debug ID field on all source maps is now **serialized as `debugId` rather than `debug_id`**. To maintain backwards-compatibility with source maps that contain a `debug_id` field, we can still read the `debug_id` field. If a source map contains a `debugId` field and a `debug_id` field, **the `debugId` field takes precedence, which is a change from the old behavior**. Corresponding Sentry CLI PR: getsentry/sentry-cli#3005 Closes getsentry#96 Closes [CLI-240](https://linear.app/getsentry/issue/CLI-240/turn-debug-id-field-to-debugid)
Integrate changes from upstream getsentry/rust-sourcemap v9.3.0 release: - Update CHANGELOG.md with upstream changes - Merge improvements to decoder, encoder, and type definitions - Update test suite with upstream enhancements Conflicts resolved by keeping swc-project fork modifications: - Cargo.toml: Maintain package name as 'swc_sourcemap' and current version - src/sourceview.rs: Keep BytesStr-based implementation 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <[email protected]>
|
|
Copilot finished reviewing on behalf of
kdy1
December 4, 2025 10:54
There was a problem hiding this comment.
Pull request overview
This PR merges upstream changes that standardize the serialization of debug IDs in source maps. The main change involves serializing the debugId field using camelCase instead of snake_case (debug_id) while maintaining backward compatibility for deserialization.
Key changes:
- Introduced a new
DebugIdFieldstruct with custom deserialization logic that accepts bothdebugIdanddebug_id(with camelCase taking precedence), but always serializes asdebugId - Simplified encoder and decoder implementations by consolidating debug ID handling into the new field type
- Added comprehensive tests to verify camelCase serialization for both
SourceMapandSourceMapIndex
Reviewed changes
Copilot reviewed 8 out of 8 changed files in this pull request and generated 2 comments.
Show a summary per file
| File | Description |
|---|---|
| src/jsontypes.rs | Implements new DebugIdField struct with custom serde logic for backward-compatible deserialization and standardized camelCase serialization |
| src/encoder.rs | Updates SourceMap and SourceMapIndex encoders to use the new DebugIdField type, simplifying the code |
| src/decoder.rs | Simplifies debug ID extraction logic by using the new DebugIdField's Into conversion, and removes redundant test case |
| src/types.rs | Adjusts test data to swap order of debug_id and debugId fields to verify camelCase precedence behavior |
| tests/test_index.rs | Adds test ensuring SourceMapIndex serializes debug IDs using camelCase |
| tests/test_encoder.rs | Adds test ensuring SourceMap serializes debug IDs using camelCase |
| cli/Cargo.toml | Bumps version to 9.3.0 |
| CHANGELOG.md | Documents the new feature and other changes in version 9.3.0 |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
|
|
||
| /// This struct represents a `RawSourceMap`'s debug ID fields. | ||
| /// | ||
| /// The reason this exists as a seperate struct is so that we can have custom deserialization |
There was a problem hiding this comment.
Spelling error: "seperate" should be "separate".
Suggested change
| /// The reason this exists as a seperate struct is so that we can have custom deserialization | |
| /// The reason this exists as a separate struct is so that we can have custom deserialization |
| /// This struct represents a `RawSourceMap`'s debug ID fields. | ||
| /// | ||
| /// The reason this exists as a seperate struct is so that we can have custom deserialization | ||
| /// logic, which can read both the legacy snake_case debug_id and the new camelCase debugId |
There was a problem hiding this comment.
Extra whitespace: There are two spaces between "the" and "legacy" in the comment. Should be: "which can read both the legacy snake_case debug_id".
Suggested change
| /// logic, which can read both the legacy snake_case debug_id and the new camelCase debugId | |
| /// logic, which can read both the legacy snake_case debug_id and the new camelCase debugId |
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.
No description provided.