JavaScript - calculate Start and End of a Word in a Sentence of a Document

doc2tokens.js

var text = "Lorem ipsum dolor sit amet,\nconsectetur adipiscing elit,\nsed do eiusmod tempor incididunt ut labore et dolore magna aliqua"

sentences = text.split(/\n/);
var doc = {};
doc.sentences = [];
for (var i = 0; i < sentences.length; i++) {
  var sentence = sentences[i];
  var words = sentence.split(/\s+/)
  var sent = {}
  sent.tokens = [];
  sent.text = sentence;
  for (var j = 0; j < words.length; j++) {
    var word = words[j];
    var reg = new RegExp("\\b(" + word + ")\\b", "g");
    var match;
    var token = {}
    token.word = word
    while ((match = reg.exec(text)) !== null) {
      var characterOffsetBegin = match.index;
      var characterOffsetEnd = characterOffsetBegin + word.length - 1;
      token.characterOffsetBegin = characterOffsetBegin
      token.characterOffsetEnd = characterOffsetEnd
      sent.tokens.push(token);
    }
  }
  doc.sentences.push(sent);
}
for (var s = 0; s < doc.sentences.length; s++) {
  var sentence = doc.sentences[s];
  console.log("", sentence.text);
  for (var i = 0; sentence.tokens && i < sentence.tokens.length; i++) {
    var token = sentence.tokens[i];
    var begin = token.characterOffsetBegin;
    var end = token.characterOffsetEnd + 1;
    var reconstructed = text.substring(begin, end);
    console.log("\t[" + token.word + "] begin:" + token.characterOffsetBegin + " end:" + token.characterOffsetEnd + " ---> [" + reconstructed + "]");
  }
}