fix(consensus): use Locale.ROOT for case-insensitive operations#128
fix(consensus): use Locale.ROOT for case-insensitive operations#128halibobo1205 wants to merge 1 commit intodevelopfrom
Conversation
|
CodeAnt AI is reviewing your PR. Thanks for using CodeAnt! 🎉We're free for open-source projects. if you're enjoying it, help us grow by sharing. Share on X · |
|
@codex: review |
|
CodeAnt AI finished reviewing your PR. |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 813385b420
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
813385b to
8793848
Compare
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 879384827e
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| if (ArrayUtils.isEmpty(existing)) { | ||
| revokingDB.put(rootKey, entry.getValue()); | ||
| } | ||
| keysToDelete.add(entry.getKey()); |
There was a problem hiding this comment.
Handle colliding Turkish keys before deleting legacy entries
This migration still drops mappings when multiple legacy Turkish keys normalize to the same ROOT key (even if no ROOT key existed before migration). For example, two historical IDs like IIIIIIII and IIIIIIIi can produce distinct Turkish-lower keys (ı... variants) that both map to the same ROOT key; the first one wins, later ones are skipped by the existing check, and then all legacy keys are deleted, making at least one account ID permanently unresolvable after startup.
Useful? React with 👍 / 👎.
lxcmyf
left a comment
There was a problem hiding this comment.
Leaving one inline comment for the migration conflict case.
| // Only write if ROOT key doesn't already exist | ||
| byte[] existing = revokingDB.getUnchecked(rootKey); | ||
| if (ArrayUtils.isEmpty(existing)) { | ||
| revokingDB.put(rootKey, entry.getValue()); | ||
| } | ||
| keysToDelete.add(entry.getKey()); | ||
| } | ||
|
|
||
| // Phase 3: delete old Turkish keys | ||
| for (byte[] key : keysToDelete) { | ||
| revokingDB.delete(key); |
There was a problem hiding this comment.
This migration still needs an explicit collision path before deleting the Turkish legacy key. A fixed-locale node should reject conflicting SetAccountId transactions, but the risky case is a DB that has already been run under different default locales over time: an old Turkish-locale index entry can remain stored under a dotless-ı key, and after the node later runs under a ROOT-style locale a new transaction can pass has(accountId) against the new canonical key and write a second mapping there. In that state getUnchecked(rootKey) is non-empty, we skip the migration write, and then delete the only legacy index entry for the first account. Please detect that mismatch explicitly and fail or reconcile it instead of deleting silently.
8793848 to
9c9acc5
Compare
|
CodeAnt AI is running Incremental review Thanks for using CodeAnt! 🎉We're free for open-source projects. if you're enjoying it, help us grow by sharing. Share on X · |
|
CodeAnt AI Incremental review completed. |
String.toLowerCase()/toUpperCase() without an explicit Locale uses Locale.getDefault(), which on Turkish (tr) or Azerbaijani (az) systems folds 'I' to dotless-ı (U+0131) instead of 'i' (U+0069). Changes: - Fix all toLowerCase()/toUpperCase() calls to use Locale.ROOT - Enable the ErrorProne StringCaseLocaleUsage checker at ERROR level to prevent future regressions at compile time - Add one-time data migration (MigrateTurkishKeyHelper) to normalize all Turkish legacy keys (ı → i) at startup.
9c9acc5 to
1c3e5c1
Compare
|
CodeAnt AI is running Incremental review Thanks for using CodeAnt! 🎉We're free for open-source projects. if you're enjoying it, help us grow by sharing. Share on X · |
|
CodeAnt AI Incremental review completed. |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 1c3e5c1349
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| import com.sun.tools.javac.code.Symbol; | ||
| import com.sun.tools.javac.code.Type; |
There was a problem hiding this comment.
Avoid non-exported javac APIs in the new checker
This checker imports com.sun.tools.javac.* internals, which are encapsulated by the jdk.compiler module on Java 11+ and are not exported to unnamed modules by default. Because this commit does not add any --add-exports compiler args for :errorprone, :errorprone:compileJava will fail before the build can run the new check. Please switch to public Error Prone APIs for type inspection (or add explicit module exports in the build).
Useful? React with 👍 / 👎.
User description
String.toLowerCase()/toUpperCase() without an explicit Locale uses Locale.getDefault(), which on Turkish (tr) or Azerbaijani (az) systems folds 'I' to dotless-ı (U+0131) instead of 'i' (U+0069). Changes:
CodeAnt-AI Description
Use locale-agnostic case handling and migrate old Turkish account keys
What Changed
Impact
✅ Fewer lookup failures on Turkish and Azerbaijani systems✅ Existing account keys continue to work after upgrade✅ More consistent command and API matching across locales🔄 Retrigger CodeAnt AI Review
Details
💡 Usage Guide
Checking Your Pull Request
Every time you make a pull request, our system automatically looks through it. We check for security issues, mistakes in how you're setting up your infrastructure, and common code problems. We do this to make sure your changes are solid and won't cause any trouble later.
Talking to CodeAnt AI
Got a question or need a hand with something in your pull request? You can easily get in touch with CodeAnt AI right here. Just type the following in a comment on your pull request, and replace "Your question here" with whatever you want to ask:
This lets you have a chat with CodeAnt AI about your pull request, making it easier to understand and improve your code.
Example
Preserve Org Learnings with CodeAnt
You can record team preferences so CodeAnt AI applies them in future reviews. Reply directly to the specific CodeAnt AI suggestion (in the same thread) and replace "Your feedback here" with your input:
This helps CodeAnt AI learn and adapt to your team's coding style and standards.
Example
Retrigger review
Ask CodeAnt AI to review the PR again, by typing:
Check Your Repository Health
To analyze the health of your code repository, visit our dashboard at https://app.codeant.ai. This tool helps you identify potential issues and areas for improvement in your codebase, ensuring your repository maintains high standards of code health.