Docs: add zh-CN entrypoint translations#6300
Merged
Conversation
scripts/docs-i18n/process.go
Outdated
Comment on lines
+15
to
+21
| absPath, err := filepath.Abs(filePath) | ||
| if err != nil { | ||
| return err | ||
| } | ||
| if !strings.HasPrefix(absPath, docsRoot) { | ||
| return fmt.Errorf("file %s not under docs root %s", absPath, docsRoot) | ||
| } |
Contributor
There was a problem hiding this comment.
[P1] strings.HasPrefix(absPath, docsRoot) is not a safe “is under directory” check: it will accept paths like /docs-root-evil/... when docsRoot is /docs-root, and can also behave unexpectedly with path separator differences. This can let inputs outside the docs root pass the guard (depending on how the tool is invoked). Prefer checking with filepath.Rel and ensuring the result doesn’t start with .. (and isn’t absolute).
Prompt To Fix With AI
This is a comment left during a code review.
Path: scripts/docs-i18n/process.go
Line: 15:21
Comment:
[P1] `strings.HasPrefix(absPath, docsRoot)` is not a safe “is under directory” check: it will accept paths like `/docs-root-evil/...` when `docsRoot` is `/docs-root`, and can also behave unexpectedly with path separator differences. This can let inputs outside the docs root pass the guard (depending on how the tool is invoked). Prefer checking with `filepath.Rel` and ensuring the result doesn’t start with `..` (and isn’t absolute).
How can I resolve this? If you propose a fix, please make it concise.
scripts/docs-i18n/tm.go
Outdated
Comment on lines
+44
to
+52
| scanner := bufio.NewScanner(file) | ||
| for scanner.Scan() { | ||
| line := strings.TrimSpace(scanner.Text()) | ||
| if line == "" { | ||
| continue | ||
| } | ||
| var entry TMEntry | ||
| if err := json.Unmarshal([]byte(line), &entry); err != nil { | ||
| return nil, fmt.Errorf("translation memory decode failed: %w", err) |
Contributor
There was a problem hiding this comment.
[P1] bufio.Scanner has a default token limit (~64K). Since TM entries can include long text/translated fields, a larger line will cause scanner.Err() and make LoadTranslationMemory fail on real-world docs. Using a bufio.Reader (ReadString/ReadBytes) or increasing the scanner buffer would avoid hard failures on large segments.
Prompt To Fix With AI
This is a comment left during a code review.
Path: scripts/docs-i18n/tm.go
Line: 44:52
Comment:
[P1] `bufio.Scanner` has a default token limit (~64K). Since TM entries can include long `text`/`translated` fields, a larger line will cause `scanner.Err()` and make `LoadTranslationMemory` fail on real-world docs. Using a `bufio.Reader` (ReadString/ReadBytes) or increasing the scanner buffer would avoid hard failures on large segments.
How can I resolve this? If you propose a fix, please make it concise.
scripts/docs-i18n/html_translate.go
Outdated
Comment on lines
+160
to
+166
| return stack[:len(stack)-1] | ||
| } | ||
| for i := len(stack) - 2; i >= 0; i-- { | ||
| if stack[i] == tag { | ||
| return stack[:i] | ||
| } | ||
| } |
Contributor
There was a problem hiding this comment.
[P1] popTag returns stack[:i] when it finds a matching tag below the top; this drops the matching tag and everything above it, but also keeps any earlier unmatched tags. For nested/mismatched HTML, this can leave the stack in an inconsistent state and cause later text to be translated or skipped incorrectly (e.g., prematurely leaving a code/pre context). Consider trimming to stack[:i] vs stack[:i]/stack[:i+?] semantics carefully based on intended behavior.
Prompt To Fix With AI
This is a comment left during a code review.
Path: scripts/docs-i18n/html_translate.go
Line: 160:166
Comment:
[P1] `popTag` returns `stack[:i]` when it finds a matching tag below the top; this drops the matching tag *and* everything above it, but also keeps any earlier unmatched tags. For nested/mismatched HTML, this can leave the stack in an inconsistent state and cause later text to be translated or skipped incorrectly (e.g., prematurely leaving a `code`/`pre` context). Consider trimming to `stack[:i]` vs `stack[:i]`/`stack[:i+?]` semantics carefully based on intended behavior.
How can I resolve this? If you propose a fix, please make it concise.
Contributor
Author
|
Greptile fixes are in
Let me know if you want me to re-run the translator outputs after these changes. |
buiilding
pushed a commit
to buiilding/openclaw
that referenced
this pull request
Feb 2, 2026
* Docs: add zh-CN entrypoint translations * Docs: harden docs-i18n parsing
HashWarlock
pushed a commit
to HashWarlock/openclaw
that referenced
this pull request
Feb 4, 2026
* Docs: add zh-CN entrypoint translations * Docs: harden docs-i18n parsing
uxcu
pushed a commit
to uxcu/kook-openclaw
that referenced
this pull request
Feb 5, 2026
* Docs: add zh-CN entrypoint translations * Docs: harden docs-i18n parsing
bestNiu
pushed a commit
to bestNiu/clawdbot
that referenced
this pull request
Feb 5, 2026
* Docs: add zh-CN entrypoint translations * Docs: harden docs-i18n parsing
batao9
pushed a commit
to batao9/openclaw
that referenced
this pull request
Feb 7, 2026
* Docs: add zh-CN entrypoint translations * Docs: harden docs-i18n parsing
hughdidit
pushed a commit
to hughdidit/DAISy-Agency
that referenced
this pull request
Feb 8, 2026
* Docs: add zh-CN entrypoint translations * Docs: harden docs-i18n parsing (cherry picked from commit 0e0e395)
This was referenced Feb 8, 2026
hughdidit
pushed a commit
to hughdidit/DAISy-Agency
that referenced
this pull request
Feb 8, 2026
* Docs: add zh-CN entrypoint translations * Docs: harden docs-i18n parsing (cherry picked from commit 0e0e395)
battman21
pushed a commit
to battman21/openclaw
that referenced
this pull request
Feb 12, 2026
* Docs: add zh-CN entrypoint translations * Docs: harden docs-i18n parsing
battman21
pushed a commit
to battman21/openclaw
that referenced
this pull request
Feb 12, 2026
* Docs: add zh-CN entrypoint translations * Docs: harden docs-i18n parsing
zooqueen
pushed a commit
to hanzoai/bot
that referenced
this pull request
Mar 6, 2026
* Docs: add zh-CN entrypoint translations * Docs: harden docs-i18n parsing
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
1 participant
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
Testing
Greptile Overview
Greptile Summary
This PR adds a Go-based documentation i18n pipeline (
scripts/docs-i18n) that segments Markdown/HTML, preserves placeholders, consults a glossary + translation memory, and emits translated docs underdocs/zh-CN/. It also updatesdocs/docs.jsonto include a topbar link to the new zh-CN entrypoint pages and adds i18n asset files (glossary + TM).The overall approach fits the repo by keeping translation artifacts under
docs/.i18n/and generating localized markdown into a language-prefixed docs tree, while leaving existing English content intact.Confidence Score: 3/5
bufio.Scannerlimits, and HTML tag stack handling may lead to incorrect translate/skip decisions on mismatched HTML blocks.