add Japanese (ja) community translation #181
Conversation
WalkthroughAdds Japanese (ja) localization to i18n: documentation updated, comment examples adjusted, tests extended to cover ja, and a new ja Map introduced with comprehensive Japanese error messages across types. Changes
Sequence Diagram(s)sequenceDiagram
autonumber
actor Dev as Developer
participant App as App/Validator
participant I18N as i18n Registry
participant JA as ja.Map
Dev->>I18N: SetLanguagesErrsMap({"en": en.Map, "es": es.Map, "ja": ja.Map})
Note right of I18N: Registers language maps
App->>I18N: Resolve(lang="ja", type=String, code=Required)
I18N->>JA: Lookup message for (String, Required)
JA-->>I18N: "必須です"
I18N-->>App: Localized message
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly related issues
Poem
Tip 🔌 Remote MCP (Model Context Protocol) integration is now available!Pro plan users can now connect to remote MCP servers from the Integrations page. Connect with popular remote MCPs such as Notion and Linear to add more context to your reviews and chats. ✨ Finishing Touches
🧪 Generate unit tests
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. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR/Issue comments)Type Other keywords and placeholders
CodeRabbit Configuration File (
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (7)
i18n/i18n.go (1)
16-16: Comment example looks good; add JA inclusion. Also keep examples consistent with docs default.The usage snippet correctly adds ja.Map. Minor nit: here the defaultLang in the example is "en", while the docs example uses "es" as default. Consider aligning both to reduce confusion.
docs/docs/packages/i18n.md (1)
48-50: Fix markdownlint MD010: replace hard tabs or disable for code fences.markdownlint flagged hard tabs on these lines. Two options:
- Preferred: replace leading tabs with spaces in code blocks.
- Alternatively: disable MD010 for the specific code fence.
Apply this minimal change to replace tabs with spaces on the touched lines:
-import ( - "github.com/Oudwins/zog/i18n" // import the i18n library - "github.com/Oudwins/zog/i18n/en" - "github.com/Oudwins/zog/i18n/es" - "github.com/Oudwins/zog/i18n/ja" // import any of the supported language maps or build your own -) +import ( + "github.com/Oudwins/zog/i18n" // import the i18n library + "github.com/Oudwins/zog/i18n/en" + "github.com/Oudwins/zog/i18n/es" + "github.com/Oudwins/zog/i18n/ja" // import any of the supported language maps or build your own +)- i18n.SetLanguagesErrsMap(map[string]i18n.LangMap{ - "es": es.Map, - "en": en.Map, - "ja": ja.Map, - }, - "es", // default language - i18n.WithLangKey("langKey"), // (optional) default lang key is "lang" and is stored in i18n.LangKey - ) + i18n.SetLanguagesErrsMap(map[string]i18n.LangMap{ + "es": es.Map, + "en": en.Map, + "ja": ja.Map, + }, + "es", // default language + i18n.WithLangKey("langKey"), // (optional) default lang key is "lang" and is stored in i18n.LangKey + )If you prefer disabling the rule for the fence instead, wrap it like:
<!-- markdownlint-disable MD010 --> ```go ... code ...Also applies to: 53-55, 65-65 </blockquote></details> <details> <summary>i18n/ja/ja.go (2)</summary><blockquote> `23-24`: **Consistency: unify wording for “NotNil/Empty”.** Messages alternate between 「空であってはいけません」 and 「空ではいけません」. Consider picking one phrasing across types (e.g., 「空ではいけません」) or tailor per-type: - Strings/Slices: 「空であってはいけません」 - Non-collection scalars (number/bool/time/struct): 「nil（未設定）ではいけません」 Purely stylistic; current text is understandable. Also applies to: 43-44, 51-51, 64-64, 72-73, 83-83 --- `7-40`: **Excellent coverage and parity confirmed** - A parity check between `i18n/en/en.go` and `i18n/ja/ja.go` shows no missing or extra `IssueCode` entries in the Japanese map. - All string validators—including `NotIssueCode` variants and placeholder keys—are covered in `ja.Map`. - Optional Japanese phrasing nitpick: for more natural negative forms, you might use 「〜であってはいけません」 instead of 「〜ではいけません」. For example: • Current: 「有効なメールアドレスではいけません」 • Suggested: 「有効なメールアドレスであってはいけません」 </blockquote></details> <details> <summary>i18n/i18n_test.go (3)</summary><blockquote> `22-26`: **Prefer using the real ja.Map instead of redefining jaMap here.** Importing the new i18n/ja package keeps tests aligned with production translations and avoids drift. Apply within this hunk: ```diff -var jaMap = zconst.LangMap{ - zconst.TypeString: { - zconst.IssueCodeRequired: "必須です", - }, -}And add the import (outside this hunk; see below).
34-35: Wire the real ja.Map into SetLanguagesErrsMap.With the import added, switch to:
- "ja": jaMap, + "ja": ja.Map,
28-36: Optional: add a parity test to prevent key drift between EN and JA.A lightweight test ensures JA keeps the same set of issue codes per type as EN. Example:
// add near other tests func TestJALangMapParityWithEN(t *testing.T) { t.Parallel() // remove if global formatter causes flakiness enMap := en.Map jaMap := ja.Map // Compare keys per type for zogType, enIssues := range enMap { jaIssues, ok := jaMap[zogType] if !ok { t.Fatalf("ja.Map missing type %q", zogType) } // Build sets enSet := map[string]struct{}{} for code := range enIssues { enSet[string(code)] = struct{}{} } jaSet := map[string]struct{}{} for code := range jaIssues { jaSet[string(code)] = struct{}{} } for c := range enSet { if _, ok := jaSet[c]; !ok { t.Errorf("ja.Map missing issue code %q for type %q", c, zogType) } } } }Note: you’ll need to import:
- "github.com/Oudwins/zog/i18n/en"
- "github.com/Oudwins/zog/i18n/ja"
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (4)
docs/docs/packages/i18n.md(3 hunks)i18n/i18n.go(1 hunks)i18n/i18n_test.go(2 hunks)i18n/ja/ja.go(1 hunks)
🧰 Additional context used
🧬 Code graph analysis (2)
i18n/ja/ja.go (3)
i18n/i18n.go (1)
LangMap(51-51)zconst/consts.go (36)
ZogType(38-38)ZogIssueCode(54-54)TypeString(41-41)IssueCodeLen(97-97)IssueCodeEmail(123-123)IssueCodeUUID(127-127)IssueCodeMatch(131-131)IssueCodeURL(135-135)IssueCodeHasPrefix(139-139)IssueCodeHasSuffix(143-143)IssueCodeContains(101-101)IssueCodeContainsDigit(155-155)IssueCodeContainsUpper(147-147)IssueCodeContainsLower(151-151)IssueCodeContainsSpecial(159-159)IssueCodeOneOf(85-85)IssueCodeRequired(63-63)IssueCodeNotNil(67-67)IssueCodeMin(89-89)IssueCodeMax(93-93)IssueCodeFallback(77-77)TypeBool(43-43)IssueCodeEQ(81-81)TypeNumber(42-42)IssueCodeLTE(106-106)IssueCodeLT(110-110)IssueCodeGTE(114-114)IssueCodeGT(118-118)TypeTime(44-44)IssueCodeAfter(164-164)IssueCodeBefore(168-168)TypeSlice(45-45)TypeStruct(46-46)IssueCodeInvalidJSON(182-182)IssueCodeZHTTPInvalidForm(187-187)IssueCodeZHTTPInvalidQuery(191-191)zconst/utils.go (1)
NotIssueCode(7-12)
i18n/i18n_test.go (2)
i18n/i18n.go (2)
LangMap(51-51)SetLanguagesErrsMap(19-38)zconst/consts.go (3)
LangMap(36-36)TypeString(41-41)IssueCodeRequired(63-63)
🪛 markdownlint-cli2 (0.17.2)
docs/docs/packages/i18n.md
48-48: Hard tabs
Column: 1
(MD010, no-hard-tabs)
49-49: Hard tabs
Column: 1
(MD010, no-hard-tabs)
53-53: Hard tabs
Column: 1
(MD010, no-hard-tabs)
54-54: Hard tabs
Column: 1
(MD010, no-hard-tabs)
55-55: Hard tabs
Column: 1
(MD010, no-hard-tabs)
🔇 Additional comments (9)
docs/docs/packages/i18n.md (3)
17-17: Verify contributor attribution for Japanese.Docs credit Japanese to @sarada824, while this PR is authored by @sawada-naoya. Please confirm intended attribution and update if necessary.
55-55: LGTM: JA registered in languages map.Including "ja": ja.Map in the example correctly mirrors the implementation.
65-65: LGTM: JA usage example added.The example showing z.WithCtxValue("langKey", "ja") clarifies how to select Japanese errors at parse time.
i18n/ja/ja.go (5)
50-61: LGTM: number translations and placeholders look correct.lte/lt/gte/gt/eq and one-of variants are covered, including NotIssue for eq and one_of. Placeholders match expected keys.
62-69: LGTM: time translations.after/before/eq handled with clear messages; reasonable fallback.
70-80: LGTM: slice translations, including NotIssue variants.Min/Max/Len/Contains and negative forms present; good coverage.
81-91: LGTM: struct and JSON/ZHTTP issues.Invalid JSON body, invalid form/query included and consistent with other locales.
41-48: Boolean issue codes confirmed
The constantsIssueCodeTrueandIssueCodeFalseare already defined inzconst/consts.go(lines 173 and 177), so the Japanese translations can remain as-is.i18n/i18n_test.go (1)
64-70: LGTM: JA test case.Validates that “必須です” is returned under lang=ja for required errors. Reads well alongside EN/ES cases.
|
Awesome! |
* chore:add ja to the Third Party Languages list * chore:add Japanese (ja) translation map
2 participants
This PR adds a Japanese (ja) translation map to the i18n package.
Changes:
i18n/ja/ja.gowith a full translation map mirroring EN keysNotes:
Thanks for reviewing!
Summary by CodeRabbit
New Features
Documentation
Tests