Counting words in string
Try these before reinventing the wheels
from Count number of words in string using JavaScript
function countWords(str) {
return str.trim().split(/\s+/).length;
}
from http://www.mediacollege.com/internet/javascript/text/count-words.html
function countWords(s){
s = s.replace(/(^\s*)|(\s*$)/gi,"");//exclude start and end white-space
s = s.replace(/[ ]{2,}/gi," ");//2 or more space to 1
s = s.replace(/\n /,"\n"); // exclude newline with a start spacing
return s.split(' ').filter(function(str){return str!="";}).length;
//return s.split(' ').filter(String).length; - this can also be used
}
from Use JavaScript to count words in a string, WITHOUT using a regex - this will be the best approach
function WordCount(str) {
return str.split(' ')
.filter(function(n) { return n != '' })
.length;
}
Notes From Author:
You can adapt this script to count words in whichever way you like. The important part is
s.split(' ').length— this counts the spaces. The script attempts to remove all extra spaces (double spaces etc) before counting. If the text contains two words without a space between them, it will count them as one word, e.g. "First sentence .Start of next sentence".
Use square brackets, not parentheses:
str[i] === " "
Or charAt:
str.charAt(i) === " "
You could also do it with .split():
return str.split(' ').length;
After cleaning the string, you can match non-whitespace characters or word-boundaries.
Here are two simple regular expressions to capture words in a string:
- Sequence of non-white-space characters:
/\S+/g - Valid characters between word boundaries:
/\b[a-z\d]+\b/g
The example below shows how to retrieve the word count from a string, by using these capturing patterns.
/*Redirect console output to HTML.*/document.body.innerHTML='';console.log=function(s){document.body.innerHTML+=s+'\n';};
/*String format.*/String.format||(String.format=function(f){return function(a){return f.replace(/{(\d+)}/g,function(m,n){return"undefined"!=typeof a[n]?a[n]:m})}([].slice.call(arguments,1))});
// ^ IGNORE CODE ABOVE ^
// =================
// Clean and match sub-strings in a string.
function extractSubstr(str, regexp) {
return str.replace(/[^\w\s]|_/g, '')
.replace(/\s+/g, ' ')
.toLowerCase().match(regexp) || [];
}
// Find words by searching for sequences of non-whitespace characters.
function getWordsByNonWhiteSpace(str) {
return extractSubstr(str, /\S+/g);
}
// Find words by searching for valid characters between word-boundaries.
function getWordsByWordBoundaries(str) {
return extractSubstr(str, /\b[a-z\d]+\b/g);
}
// Example of usage.
var edisonQuote = "I have not failed. I've just found 10,000 ways that won't work.";
var words1 = getWordsByNonWhiteSpace(edisonQuote);
var words2 = getWordsByWordBoundaries(edisonQuote);
console.log(String.format('"{0}" - Thomas Edison\n\nWord count via:\n', edisonQuote));
console.log(String.format(' - non-white-space: ({0}) [{1}]', words1.length, words1.join(', ')));
console.log(String.format(' - word-boundaries: ({0}) [{1}]', words2.length, words2.join(', ')));body { font-family: monospace; white-space: pre; font-size: 11px; }Finding Unique Words
You could also create a mapping of words to get unique counts.
function cleanString(str) {
return str.replace(/[^\w\s]|_/g, '')
.replace(/\s+/g, ' ')
.toLowerCase();
}
function extractSubstr(str, regexp) {
return cleanString(str).match(regexp) || [];
}
function getWordsByNonWhiteSpace(str) {
return extractSubstr(str, /\S+/g);
}
function getWordsByWordBoundaries(str) {
return extractSubstr(str, /\b[a-z\d]+\b/g);
}
function wordMap(str) {
return getWordsByWordBoundaries(str).reduce(function(map, word) {
map[word] = (map[word] || 0) + 1;
return map;
}, {});
}
function mapToTuples(map) {
return Object.keys(map).map(function(key) {
return [ key, map[key] ];
});
}
function mapToSortedTuples(map, sortFn, sortOrder) {
return mapToTuples(map).sort(function(a, b) {
return sortFn.call(undefined, a, b, sortOrder);
});
}
function countWords(str) {
return getWordsByWordBoundaries(str).length;
}
function wordFrequency(str) {
return mapToSortedTuples(wordMap(str), function(a, b, order) {
if (b[1] > a[1]) {
return order[1] * -1;
} else if (a[1] > b[1]) {
return order[1] * 1;
} else {
return order[0] * (a[0] < b[0] ? -1 : (a[0] > b[0] ? 1 : 0));
}
}, [1, -1]);
}
function printTuples(tuples) {
return tuples.map(function(tuple) {
return padStr(tuple[0], ' ', 12, 1) + ' -> ' + tuple[1];
}).join('\n');
}
function padStr(str, ch, width, dir) {
return (width <= str.length ? str : padStr(dir < 0 ? ch + str : str + ch, ch, width, dir)).substr(0, width);
}
function toTable(data, headers) {
return $('<table>').append($('<thead>').append($('<tr>').append(headers.map(function(header) {
return $('<th>').html(header);
})))).append($('<tbody>').append(data.map(function(row) {
return $('<tr>').append(row.map(function(cell) {
return $('<td>').html(cell);
}));
})));
}
function addRowsBefore(table, data) {
table.find('tbody').prepend(data.map(function(row) {
return $('<tr>').append(row.map(function(cell) {
return $('<td>').html(cell);
}));
}));
return table;
}
$(function() {
$('#countWordsBtn').on('click', function(e) {
var str = $('#wordsTxtAra').val();
var wordFreq = wordFrequency(str);
var wordCount = countWords(str);
var uniqueWords = wordFreq.length;
var summaryData = [
[ 'TOTAL', wordCount ],
[ 'UNIQUE', uniqueWords ]
];
var table = toTable(wordFreq, ['Word', 'Frequency']);
addRowsBefore(table, summaryData);
$('#wordFreq').html(table);
});
});table {
border-collapse: collapse;
table-layout: fixed;
width: 200px;
font-family: monospace;
}
thead {
border-bottom: #000 3px double;;
}
table, td, th {
border: #000 1px solid;
}
td, th {
padding: 2px;
width: 100px;
overflow: hidden;
}
textarea, input[type="button"], table {
margin: 4px;
padding: 2px;
}<script src="https://ajax.googleapis.com/ajax/libs/jquery/1.11.1/jquery.min.js"></script>
<h1>Word Frequency</h1>
<textarea id="wordsTxtAra" cols="60" rows="8">Four score and seven years ago our fathers brought forth on this continent, a new nation, conceived in Liberty, and dedicated to the proposition that all men are created equal.
Now we are engaged in a great civil war, testing whether that nation, or any nation so conceived and so dedicated, can long endure. We are met on a great battle-field of that war. We have come to dedicate a portion of that field, as a final resting place for those who here gave their lives that that nation might live. It is altogether fitting and proper that we should do this.
But, in a larger sense, we can not dedicate -- we can not consecrate -- we can not hallow -- this ground. The brave men, living and dead, who struggled here, have consecrated it, far above our poor power to add or detract. The world will little note, nor long remember what we say here, but it can never forget what they did here. It is for us the living, rather, to be dedicated here to the unfinished work which they who fought here have thus far so nobly advanced. It is rather for us to be here dedicated to the great task remaining before us -- that from these honored dead we take increased devotion to that cause for which they gave the last full measure of devotion -- that we here highly resolve that these dead shall not have died in vain -- that this nation, under God, shall have a new birth of freedom -- and that government of the people, by the people, for the people, shall not perish from the earth.</textarea><br />
<input type="button" id="countWordsBtn" value="Count Words" />
<div id="wordFreq"></div>One more way to count words in a string. This code counts words that contain only alphanumeric characters and "_", "’", "-", "'" chars.
function countWords(str) {
var matches = str.match(/[\w\d\’\'-]+/gi);
return matches ? matches.length : 0;
}