j0shua/wordcount.html

## wordcount.html
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN"
	"http://www.w3.org/TR/html4/strict.dtd">
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<title>Word counter</title>
<style type="text/css">
div.textareas textarea {
	vertical-align: middle;
}
</style>
<script type="text/javascript">
function countWords(s, stopwords) {
	/* Need to split up words, but NOT split on apostrophes. Solution is to
	   first replace punctuation we don't care about (like fullstops and
	   commas) with spaces, then extract all non-whitespace sequences. */
	s = s.toLowerCase();
	s = s.replace(/[\.\,\;\:\!\?\(\)\&]/g, ' ');
	var re = /\S+/ig;
	var m, word;
	var counts = {};
	while ((m = re.exec(s)) != null) {
		word = m[0];
		if (!stopwords[word]) {
			counts[word] = (counts[word] || 0) + 1;
		}
	}
	var results = [];
	for (var word in counts) {
		results.push([word, counts[word]]);
	}
	results = results.sort(function(a, b) {
		return ((a[1] < b[1]) ? -1 : ((a[1] > b[1]) ? 1 : 0));
	});
	results.reverse();
	return results;
}

window.onload = function() {
	var input = document.getElementsByName('input')[0];
	var output = document.getElementsByName('output')[0];
	var results = document.getElementById('results');
	var form = document.forms[0];
	form.onsubmit = function() {
		var stopwords = document.getElementsByName(
			'stopwords'
		)[0].value.split(/\s+/);
		var stopwords_lookup = {};
		for (var i = 0, word; word = stopwords[i]; i++) {
			stopwords_lookup[word] = 1;
		}
		var counts = countWords(input.value, stopwords_lookup);
		var s = '';
		for (var i = 0; i < counts.length; i++) {
			s += counts[i][0] + '\t' + counts[i][1] + '\n';
		}
		output.value = s;
		results.style.display = 'inline';
		return false;
	}
}
</script>
</head>
<body>
<h1>Word counter</h1>
<p>Paste in text and hit "Count words" to count the number of times each word appears.</p>
<form action="/" method="get">
	<div class="textareas">
		<textarea name="input" rows="40" cols="80"></textarea>
		<span id="results" style="display: none">
			output:
			<textarea name="output" rows="40" cols="80"></textarea>
		</span>
	</div>
	<p><input type="submit" value="Count words"></p>
	<p>The following stop words are ignored:</p>
	<p><textarea name="stopwords" rows="4" cols="120">a all an and are as at be but by can do for from had have if in is it me my no not of on or our s so t that the their they this to us was we who with you</textarea></p>
</form>
</body>
</html>
	<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN"
	"http://www.w3.org/TR/html4/strict.dtd">
	<html>
	<head>
	<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
	<title>Word counter</title>
	<style type="text/css">
	div.textareas textarea {
	vertical-align: middle;
	}
	</style>
	<script type="text/javascript">
	function countWords(s, stopwords) {
	/* Need to split up words, but NOT split on apostrophes. Solution is to
	first replace punctuation we don't care about (like fullstops and
	commas) with spaces, then extract all non-whitespace sequences. */
	s = s.toLowerCase();
	s = s.replace(/[\.\,\;\:\!\?\(\)\&]/g, ' ');
	var re = /\S+/ig;
	var m, word;
	var counts = {};
	while ((m = re.exec(s)) != null) {
	word = m[0];
	if (!stopwords[word]) {
	counts[word] = (counts[word] \|\| 0) + 1;
	}
	}
	var results = [];
	for (var word in counts) {
	results.push([word, counts[word]]);
	}
	results = results.sort(function(a, b) {
	return ((a[1] < b[1]) ? -1 : ((a[1] > b[1]) ? 1 : 0));
	});
	results.reverse();
	return results;
	}

	window.onload = function() {
	var input = document.getElementsByName('input')[0];
	var output = document.getElementsByName('output')[0];
	var results = document.getElementById('results');
	var form = document.forms[0];
	form.onsubmit = function() {
	var stopwords = document.getElementsByName(
	'stopwords'
	)[0].value.split(/\s+/);
	var stopwords_lookup = {};
	for (var i = 0, word; word = stopwords[i]; i++) {
	stopwords_lookup[word] = 1;
	}
	var counts = countWords(input.value, stopwords_lookup);
	var s = '';
	for (var i = 0; i < counts.length; i++) {
	s += counts[i][0] + '\t' + counts[i][1] + '\n';
	}
	output.value = s;
	results.style.display = 'inline';
	return false;
	}
	}
	</script>
	</head>
	<body>
	<h1>Word counter</h1>
	<p>Paste in text and hit "Count words" to count the number of times each word appears.</p>
	<form action="/" method="get">
	<div class="textareas">
	<textarea name="input" rows="40" cols="80"></textarea>
	<span id="results" style="display: none">
	output:
	<textarea name="output" rows="40" cols="80"></textarea>
	</span>
	</div>
	<p><input type="submit" value="Count words"></p>
	<p>The following stop words are ignored:</p>
	<p><textarea name="stopwords" rows="4" cols="120">a all an and are as at be but by can do for from had have if in is it me my no not of on or our s so t that the their they this to us was we who with you</textarea></p>
	</form>
	</body>
	</html>