Wrap unicode word tokens with html spans in a sentence, without losing any punctuation.

sentence_tokens.js

let XRegExp = require('xregexp');
let nonUnicodeLetter = XRegExp('[^\\pL\\pM]+?');

var sentence = "This is a sentence-with some punctuation, and it will be split-up."
console.log("sentence: ", sentence)

var tokens = sentence.split(nonUnicodeLetter)
console.log("tokens: ", tokens)

_sentence = sentence
var response = ""
tokens.forEach(function(token) {
  var regex = XRegExp('^(.*?)('+token+')')
  var match = _sentence.match(regex, '')
  _sentence = _sentence.replace(regex, '')
  console.log("token: ", token)
  console.log("match: ", match)
  response = response + match[1] + '<span>' + match[2] + '</span>'
})
response = "<div>" + response + _sentence + "</div>"
console.log("response: ", response)

// sentence:  This is a sentence-with some punctuation, and it will be split-up.
// tokens:  [ 'This',
//   'is',
//   'a',
//   'sentence',
//   'with',
//   'some',
//   'punctuation',
//   '',
//   'and',
//   'it',
//   'will',
//   'be',
//   'split',
//   'up',
//   '' ]
// token:  This
// match:  [ 'This',
//   '',
//   'This',
//   index: 0,
//   input: 'This is a sentence-with some punctuation, and it will be split-up.' ]
// token:  is
// match:  [ ' is',
//   ' ',
//   'is',
//   index: 0,
//   input: ' is a sentence-with some punctuation, and it will be split-up.' ]
// token:  a
// match:  [ ' a',
//   ' ',
//   'a',
//   index: 0,
//   input: ' a sentence-with some punctuation, and it will be split-up.' ]
// token:  sentence
// match:  [ ' sentence',
//   ' ',
//   'sentence',
//   index: 0,
//   input: ' sentence-with some punctuation, and it will be split-up.' ]
// token:  with
// match:  [ '-with',
//   '-',
//   'with',
//   index: 0,
//   input: '-with some punctuation, and it will be split-up.' ]
// token:  some
// match:  [ ' some',
//   ' ',
//   'some',
//   index: 0,
//   input: ' some punctuation, and it will be split-up.' ]
// token:  punctuation
// match:  [ ' punctuation',
//   ' ',
//   'punctuation',
//   index: 0,
//   input: ' punctuation, and it will be split-up.' ]
// token:  
// match:  [ '', '', '', index: 0, input: ', and it will be split-up.' ]
// token:  and
// match:  [ ', and',
//   ', ',
//   'and',
//   index: 0,
//   input: ', and it will be split-up.' ]
// token:  it
// match:  [ ' it', ' ', 'it', index: 0, input: ' it will be split-up.' ]
// token:  will
// match:  [ ' will', ' ', 'will', index: 0, input: ' will be split-up.' ]
// token:  be
// match:  [ ' be', ' ', 'be', index: 0, input: ' be split-up.' ]
// token:  split
// match:  [ ' split', ' ', 'split', index: 0, input: ' split-up.' ]
// token:  up
// match:  [ '-up', '-', 'up', index: 0, input: '-up.' ]
// token:  
// match:  [ '', '', '', index: 0, input: '.' ]
// response:  <div><span>This</span> <span>is</span> <span>a</span> <span>sentence</span>-<span>with</span> <span>some</span> <span>punctuation</span><span></span>, <span>and</span> <span>it</span> <span>will</span> <span>be</span> <span>split</span>-<span>up</span><span></span>.</div>