prehistoric-systems/omnivore
1
0
Fork 0
mirror of https://github.com/omnivore-app/omnivore.git synced 2026-03-11 08:54:26 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge pull request #1307 from omnivore-app/fix/escaped-utterance-in-speech-file

Browse source 
Do not escape utterance in speech file and do it when streaming
This commit is contained in:
Hongbo Wu 2022-10-13 18:11:06 +08:00 committed by GitHub
commit 369240dff4
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
packages/text-to-speech/src/htmlToSsml.ts
View file

@ -1,5 +1,4 @@
import { parseHTML } from 'linkedom'
import * as _ from 'underscore'
import { SentenceTokenizer, WordPunctTokenizer } from 'natural'
import { htmlToText } from 'html-to-text'
@ -114,12 +113,8 @@ function emit(textItems: string[], text: string) {
textItems.push(text)
}
const cleanText = (text: string): string => {
return stripEmojis(_.escape(text.replace(/\s+/g, ' ')))
}
function cleanTextNode(textNode: ChildNode): string {
return cleanText(textNode.textContent ?? '')
return stripEmojis(textNode.textContent ?? '')
}
function emitTextNode(
@ -395,7 +390,7 @@ export const htmlToSpeechFile = (htmlInput: HtmlInput): SpeechFile => {
const titleUtterance = textToUtterances({
tokenizer,
idx: '',
textItems: [cleanText(title)], // title could have HTML entity names like & or emoji
textItems: [stripEmojis(title)], // title could have emoji
wordOffset,
isHtml: false,
})[0]