Add segmented TTS metadata for mixed-language names#1432
Merged
Conversation
Contributor
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (3)
📝 WalkthroughWalkthroughText-to-Speech（TTS）メタデータをStation、StationMinimal、Line、TrainTypeエンドポイントに公開するため、名前のセグメント化APIを追加し、プロトバッファ型に対応するserde派生や DTO/インタラクタでの name_tts_segments 統合を行った。 Changes
Sequence Diagram(s)sequenceDiagram
participant Client
participant Interactor as UseCase/Interactor
participant Domain as domain::ipa
participant DTO as use_case::dto
participant Proto as generated::proto
Client->>Interactor: get_routes / get_routes_minimal
Interactor->>Domain: station_name_to_tts_segments(name_k, name_r)
Domain-->>Interactor: Vec<TtsNameSegment>
Interactor->>DTO: to_proto_tts_segments(segments)
DTO-->>Interactor: Vec<TtsSegment>
Interactor->>Proto: build Station/Line/TrainType with name_tts_segments
Interactor-->>Client: gRPC response (includes name_tts_segments)
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly related PRs
Suggested labels
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)
📝 Coding Plan
Comment |
# Conflicts: # stationapi/src/domain/ipa.rs # stationapi/src/use_case/dto/line.rs # stationapi/src/use_case/dto/station.rs # stationapi/src/use_case/dto/train_type.rs
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 2
🧹 Nitpick comments (1)
stationapi/src/use_case/dto/station.rs (1)
189-191: セグメント[1]のpronunciationフィールドの検証が不足しています。
Rinkaiセグメントはsurface、fallback_text、separatorを検証していますが、pronunciationの検証がありません。他のセグメントと同様に、このフィールドも検証することで、TTSセグメント生成ロジックのより完全なカバレッジが得られます。💡 pronunciationアサーションの追加提案
assert_eq!(grpc_station.name_tts_segments[1].surface, "Rinkai"); assert_eq!(grpc_station.name_tts_segments[1].fallback_text, "りんかい"); + assert_eq!(grpc_station.name_tts_segments[1].pronunciation, "ɾiŋka.i"); // 期待される発音を確認してください assert_eq!(grpc_station.name_tts_segments[1].separator, " ");🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@stationapi/src/use_case/dto/station.rs` around lines 189 - 191, テストで grpc_station の TTS セグメント検証が抜けているため、name_tts_segments[1] の pronunciation フィールドも検証するアサーションを追加してください（対象は grpc_station.name_tts_segments[1].pronunciation）；期待値は既存のテストデータ／他のセグメントで使っている発音フォーマットに合わせて設定し、Rinkai セグメントの surface/fallback_text/separator と同様に確実に比較するようにします。
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@stationapi/src/domain/ipa.rs`:
- Around line 255-263: The code computes stem_len from normalized byte lengths
and slices original by that byte index, which can split UTF-8 chars; instead
compute the stem boundaries in characters and map to a byte index in original:
determine stem_char_count = normalized.chars().count() - suffix.chars().count()
(or find the char-index where suffix begins), then get the byte offset in
original via original.char_indices().nth(stem_char_count).map(|(i,_)|
i).unwrap_or(original.len()) and use that byte offset for
&original[..byte_offset]; then pass that safe UTF-8 stem to
word_to_tts_segments(stem) and leave suffix handling unchanged (references:
JAPANESE_SUFFIXES, normalized, original, stem_len, word_to_tts_segments).
In `@stationapi/src/use_case/dto/line.rs`:
- Around line 20-23: name_tts_segments
のフォールバックが無効になっているので、station_name_to_tts_segments
に空文字列を渡すのではなくカタカナフォールバック用の値を渡してください: 修正箇所は
to_proto_tts_segments(station_name_to_tts_segments(...)) の呼び出しで、第一引数の "" を
line.line_name_k に差し替え、line.line_name_r はそのまま第二引数に渡してカタカナフォールバックを有効にしてください（参照:
name_tts_segments, station_name_to_tts_segments, line.line_name_k,
line.line_name_r）。
---
Nitpick comments:
In `@stationapi/src/use_case/dto/station.rs`:
- Around line 189-191: テストで grpc_station の TTS
セグメント検証が抜けているため、name_tts_segments[1] の pronunciation
フィールドも検証するアサーションを追加してください（対象は
grpc_station.name_tts_segments[1].pronunciation）；期待値は既存のテストデータ／他のセグメントで使っている発音フォーマットに合わせて設定し、Rinkai
セグメントの surface/fallback_text/separator と同様に確実に比較するようにします。
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: a1b60049-1777-46bf-a8db-e389e6c33b4b
📒 Files selected for processing (10)
AGENTS.mdstationapi/build.rsstationapi/protostationapi/src/domain/ipa.rsstationapi/src/use_case/dto.rsstationapi/src/use_case/dto/line.rsstationapi/src/use_case/dto/station.rsstationapi/src/use_case/dto/train_type.rsstationapi/src/use_case/dto/tts.rsstationapi/src/use_case/interactor/query.rs
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
Verification
Related
Summary by CodeRabbit
ドキュメント
新機能
テスト