Last active
September 21, 2022 09:38
-
-
Save seanghay/90774fa212025339c086d48f8381a159 to your computer and use it in GitHub Desktop.
Automatically insert ZWSP into text.
This file contains 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
import MagicString from "magic-string"; | |
/** | |
* Automatically insert ZWSP into text. | |
* @param {string} value | |
* @param {string | undefined} sep | |
* @returns {string} | |
*/ | |
export function insertZeroWidthSpace(value, sep = '\u200b') { | |
const regex = /[\u1780-\u17ff]+/gm | |
const str = new MagicString(value); | |
const segmenter = new Intl.Segmenter('km', { granularity: "word" }); | |
let result; | |
while (result = regex.exec(value)) { | |
const { index: start } = result; | |
const end = regex.lastIndex; | |
const text = result[0]; | |
const iterator = segmenter.segment(text); | |
const segments = Array.from(iterator); | |
// skipped because cannot segment | |
if (segments.length <= 1) { | |
continue; | |
}; | |
const parts = new MagicString(''); | |
for (let i = 0; i < segments.length; i++) { | |
const { segment, isWordLike } = segments[i]; | |
parts.append(segment); | |
const nextSegment = segments[i + 1] | |
if (isWordLike && nextSegment && nextSegment.isWordLike) { | |
if (nextSegment.segment.length > 1) { | |
parts.append(sep); | |
} | |
} | |
} | |
str.overwrite(start, end, parts.toString()); | |
} | |
return str.toString(); | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment