formats text into correct url format for any language

multi-lingual-url-formatter.js

const noHyphenLangs = ['ko', 'ja', 'zh-cn', 'zh-tw', 'ar', 'th']
const formatTranslationIntoPath = (text, symbol) => { // utf-8 encoding
  let t = text
  const replaceChar = noHyphenLangs.includes(symbol) ? '' : '-'
  t = t.replace(/-/g, ' ')
  t = t.replace(/\s/g, replaceChar)
  t = t.replace(/['`’]/g, '') // remove quotes
  t = t.replace(/[,，()]/g, '') // remove junk
  t = t.normalize('NFD').replace(/\p{Diacritic}/gu, '') // simplify letters for url https://stackoverflow.com/questions/990904/remove-accents-diacritics-in-a-string-in-javascript

  // fix any left over diacritic failed to replace
  t = t.replace(/[Łł]/g, 'l')
  t = t.replace(/đ/g, 'd')
  
  return t.toLowerCase()
}

const ex1 = formatTranslationIntoPath('让我们  尝试-这样-做', 'zh-cn') // 让我们尝试这样做
const ex2 = formatTranslationIntoPath('Việt miễn phí', 'vi') // viet-mien-phi