mirror of
https://github.com/stablyai/orca.git
synced 2026-11-15 18:37:24 +00:00
Kelvin Amoaba
1bf2276bdd
* fix(dictation): join Chinese and Japanese phrases without a space, and space Korean ones The shared transcript fold joined every phrase with a space, so the pill and phone replies showed Chinese and Japanese text with spaces the inserted text doesn't have. It now joins with the same rule as insertion. That rule treated Hangul like Chinese and Japanese, so Korean phrases were inserted with no space between sentences; Korean spaces words, so Hangul now spaces like Latin text. * fix(dictation): don't space after Chinese and Japanese full-width punctuation * fix(dictation): join retried phrases with the same spacing rule * fix(dictation): escape the spacing rule's non-ASCII marks for the orcad bundle The shared fold now pulls the spacing rule into the orcad server bundle, which must stay ASCII. A rich-draft test pinned Hangul joining without a space; it now expects the Korean spacing.
45 lines
1.5 KiB
TypeScript
45 lines
1.5 KiB
TypeScript
import { describe, expect, it } from 'vitest'
|
|
import { DictationTranscript } from './dictation-transcript'
|
|
|
|
function fold(events: { type: 'partial' | 'final'; text: string }[]) {
|
|
const transcript = new DictationTranscript()
|
|
events.forEach((event) => transcript.accept(event))
|
|
return transcript.snapshot()
|
|
}
|
|
|
|
describe('DictationTranscript', () => {
|
|
it('joins Chinese and Japanese phrases without a space, as they are inserted', () => {
|
|
expect(
|
|
fold([
|
|
{ type: 'final', text: '西班牙人开始了殖民时期。' },
|
|
{ type: 'final', text: '2023年他们来自欧洲' },
|
|
{ type: 'partial', text: '然后' }
|
|
])
|
|
).toMatchObject({
|
|
committed: '西班牙人开始了殖民时期。2023年他们来自欧洲',
|
|
text: '西班牙人开始了殖民时期。2023年他们来自欧洲然后'
|
|
})
|
|
expect(
|
|
fold([
|
|
{ type: 'final', text: '今日は晴れです。' },
|
|
{ type: 'final', text: '散歩に行きます。' }
|
|
]).committed
|
|
).toBe('今日は晴れです。散歩に行きます。')
|
|
})
|
|
|
|
it('spaces Korean and Latin phrases', () => {
|
|
expect(
|
|
fold([
|
|
{ type: 'final', text: '안녕하세요.' },
|
|
{ type: 'final', text: '감사합니다.' }
|
|
]).committed
|
|
).toBe('안녕하세요. 감사합니다.')
|
|
expect(
|
|
fold([
|
|
{ type: 'final', text: 'Open the file.' },
|
|
{ type: 'partial', text: 'then save' }
|
|
]).text
|
|
).toBe('Open the file. then save')
|
|
})
|
|
})
|