Merged
Conversation
apply_vowel_length関数（ei→eː, oɯ→oː, oo→oː）を削除。 Google TTSがeːを英語の/eɪ/と解釈し「名鉄」が「まいてつ」と 発音される問題を修正。カタカナの音素をそのまま出力するようにした。 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Contributor
📝 WalkthroughWalkthroughIPA変換パイプラインから母音長短縮処理を削除し、連続母音間にドットで音節境界を挿入する新処理（insert_syllable_breaks）を導入。公開APIは変わらず、テスト期待値を新出力に合わせて更新。 Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches
🧪 Generate unit tests (beta)
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
🧹 Nitpick comments (1)
stationapi/src/domain/ipa.rs (1)
438-450: Google TTS 実機での回帰確認をこのPRで完了させたいです。
ケイセイ・メイテツの文字列期待値は適切ですが、今回の目的は Google TTS の誤読修正なので、最低でも「名鉄」「京成」「東京」の実読み上げ確認結果（ログ/音声）をPRに添付しておくと安全です。🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@stationapi/src/domain/ipa.rs` around lines 438 - 450, Add Google TTS verification artifacts for the corrected readings: run the ipa("メイテツ"), ipa("ケイセイ"), and ipa("トウキョウ") through the actual Google TTS engine (using the same voice/settings as production), save the resulting audio files and short logs showing the spoken text and output URI/response, and attach those files to the PR; reference the related test functions (ipa, test_meitetsu, test_oshiage/test_keisei) in the PR description and include a brief note indicating the command/parameters used for reproduction so reviewers can replay the audio.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Nitpick comments:
In `@stationapi/src/domain/ipa.rs`:
- Around line 438-450: Add Google TTS verification artifacts for the corrected
readings: run the ipa("メイテツ"), ipa("ケイセイ"), and ipa("トウキョウ") through the actual
Google TTS engine (using the same voice/settings as production), save the
resulting audio files and short logs showing the spoken text and output
URI/response, and attach those files to the PR; reference the related test
functions (ipa, test_meitetsu, test_oshiage/test_keisei) in the PR description
and include a brief note indicating the command/parameters used for reproduction
so reviewers can replay the audio.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 1d1f52a4-0937-43b7-ab5c-548833814a4e
📒 Files selected for processing (2)
stationapi/src/domain/ipa.rsstationapi/src/use_case/dto/line.rs
Google TTSが連続母音(ei, ou等)を英語の二重母音として解釈し 「西武」が「サイブ」と発音される問題を修正。 insert_syllable_breaks関数で母音間に「.」を挿入し、 各母音が独立した音節であることをTTSに伝える。 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
セイー、コウー、オオー、ラーメン、カッジ、カッジュ、ニッキョウ など架空の組み合わせのテストを削除。 ニッキョウのパターンはドッキョウダイガクマエのテストでカバー済み。 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Member
Author
|
@coderabbitai resume |
Contributor
✅ Actions performedReviews resumed. |
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 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 353-364: The syllable-break inserter insert_syllable_breaks
currently resets the vowel state when it sees the long-vowel mark (e.g. 'ː' or
'ー'), causing a dot to be inserted before a vowel that follows a long mark;
modify the loop so that long-vowel characters are treated as transparent: push
the long mark into result but do not change prev_is_vowel (i.e. preserve the
previous vowel state) so a following vowel is not treated as a new-vowel
boundary, and add a regression test (e.g. input containing "eːa" / "エーアイ") to
assert no dot is inserted between the long mark and the following vowel; refer
to insert_syllable_breaks and the prev_is_vowel variable when locating the
change.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 142aa642-64a2-41e1-8f59-f54d9df92ad2
📒 Files selected for processing (2)
stationapi/src/domain/ipa.rsstationapi/src/use_case/dto/line.rs
✅ Files skipped from review due to trivial changes (1)
- stationapi/src/use_case/dto/line.rs
Member
Author
|
@coderabbitai 他に指摘がないならapproveしてください |
Contributor
|
🧠 Learnings used✅ Actions performedComments resolved and changes approved. |
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
apply_vowel_length関数（ei→eː,oɯ→oː,oo→oː）を削除eːを英語の /eɪ/ と解釈し「名鉄(メイテツ)」が「まいてつ」と発音される問題を修正Test plan
domain::ipa::tests全52テスト通過確認済み🤖 Generated with Claude Code
Summary by CodeRabbit