word frequency in javascript

Question

How can I implement javascript function to calculate frequency of each word in

Answer 1

I'd go with Sampson's match-reduce method for slightly better efficiency. Here's a modified version of it that is more production-ready. It's not perfect, but it should cover the vast majority of scenarios (i.e., "good enough").

function calcWordFreq(s) {
  // Normalize
  s = s.toLowerCase();
  // Strip quotes and brackets
  s = s.replace(/["“”(\[{}\])]|\B['‘]([^'’]+)['’]/g, '$1');
  // Strip dashes and ellipses
  s = s.replace(/[‒–—―…]|--|\.\.\./g, ' ');
  // Strip punctuation marks
  s = s.replace(/[!?;:.,]\B/g, '');
  return s.match(/\S+/g).reduce(function(oFreq, sWord) {
    if (oFreq.hasOwnProperty(sWord)) ++oFreq[sWord];
    else oFreq[sWord] = 1;
    return oFreq;
  }, {});
}

calcWordFreq('A ‘bad’, “BAD” wolf-man...a good ol\' spook -- I\'m frightened!') returns

{
  "a": 2
  "bad": 2
  "frightened": 1
  "good": 1
  "i'm": 1
  "ol'": 1
  "spook": 1
  "wolf-man": 1
}