Concise, efficient, and 99% reliable sentence tokenizer for all Latin languages.

sentence-tokenizer.js

function sentencesArray (text) {
  return text
    .replace(/([\s,]?[\d,-]?([A-Z][a-z]{3,}|[a-z]{2,}|[0-9])[.?!…\n]+([\s\n"]))/g, '$1|')
    .split('|')
    .map(s => s.trim())
    .filter(s => s)
}