Count number of words in string using JavaScript

Question

I am trying to count the number of words in a given string using the following code:

var t = document.getElementById('MSO_ContentTable').textContent;

if (t == undefined) {
  var total = document.getElementById('MSO_ContentTable').innerText;                
} else {
  var total = document.getElementById('MSO_ContentTable').textContent;        
}
countTotal = cword(total);   

function cword(w) {
  var count = 0;
  var words = w.split(" ");
  for (i = 0; i < words.length; i++) {
    // inner loop -- do the count
    if (words[i] != "") {
      count += 1;
    }
  }

  return (count);
}

In that code I am getting data from a div tag and sending it to the cword() function for counting. Though the return value is different in IE and Firefox. Is there any change required in the regular expression? One thing that I show that both browser send same string there is a problem inside the cword() function.

Answer 1

You can make a clever use of the replace() method although you are not replacing anything.

var str = "the very long text you have...";

var counter = 0;

// lets loop through the string and count the words
str.replace(/(\b+)/g,function (a) {
   // for each word found increase the counter value by 1
   counter++;
})

alert(counter);

the regex can be improved to exclude html tags for example

Answer 2

You can use split and add a wordcounter to the String prototype:

String.prototype.countWords = function(){
  return this.split(/\s+/).length;
}

'this string has five words'.countWords(); //=> 5

If you want to exclude things like ... or - in a sentence:

String.prototype.countWords = function(){
  return this.split(/\s+\b/).length;
}

'this string has seven ... words  - and counting'.countWords(); //=> 7

Answer 3

I would prefer a RegEx only solution:

var str = "your long string with many words.";
var wordCount = str.match(/(\w+)/g).length;
alert(wordCount); //6

The regex is

\w+    between one and unlimited word characters
/g     greedy - don't stop after the first match

The brackets create a group around every match. So the length of all matched groups should match the word count.

Answer 4

//Count words in a string or what appears as words :-)

        function countWordsString(string){

            var counter = 1;

            // Change multiple spaces for one space
            string=string.replace(/[\s]+/gim, ' ');

            // Lets loop through the string and count the words
            string.replace(/(\s+)/g, function (a) {
               // For each word found increase the counter value by 1
               counter++;
            });

            return counter;
        }


        var numberWords = countWordsString(string);

Answer 5

This is the best solution I've found:

function wordCount(str) { var m = str.match(/[^\s]+/g) return m ? m.length : 0; }

This inverts whitespace selection, which is better than \w+ because it only matches the latin alphabet and _ (see http://www.ecma-international.org/ecma-262/5.1/#sec-15.10.2.6)

If you're not careful with whitespace matching you'll count empty strings, strings with leading and trailing whitespace, and all whitespace strings as matches while this solution handles strings like ' ', ' a\t\t!\r\n#$%() d ' correctly (if you define 'correct' as 0 and 4).