sbd-fork
Version:
Split text into sentences with Sentence Boundary Detection (SBD).
114 lines (93 loc) • 4.57 kB
HTML
<html class="no-js">
<head>
<meta charset="utf-8">
<meta http-equiv="x-ua-compatible" content="ie=edge">
<title>Sentence Boundary Detection (SBD).</title>
<meta name="description" content="Sentence Boundary Detection with javascript">
<meta name="viewport" content="width=device-width, initial-scale=1">
<link href="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/css/bootstrap.min.css" rel="stylesheet">
<style>
.padpad {
padding: 40px 0;
}
.site-footer {
border-top:1px solid #eee;
margin-top:60px;
text-align: center;
}
</style>
<script src="dist/sbd.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/angular.js/1.3.15/angular.min.js"></script>
<script type="text/javascript">
var app = angular.module('sbdApp', []);
app.controller('Index', function($scope) {
$scope.textContent = "On Jan. 20, former Sen. Barack Obama became the 44th President of the U.S. Millions attended the Inauguration.";
});
app.filter('tokenize', function() {
return function(input) {
return tokenizer.sentences(input);
};
});
app.filter('pluralize', function() {
return function(input) {
var len = tokenizer.sentences(input).length || 0;
if (len > 1) {
return len + " sentences";
}
else if (len === 1) {
return "1 sentence";
}
return "No sentences";
};
});
</script>
</head>
<body ng-app='sbdApp' ng-controller='Index'>
<!--[if lt IE 8]>
<p class="browserupgrade">You are using an <strong>outdated</strong> browser. Please <a href="http://browsehappy.com/">upgrade your browser</a> to improve your experience.</p>
<![endif]-->
<a href="https://github.com/Tessmore/sbd">
<img style="position: absolute; top: 0; right: 0; border: 0;" src="https://camo.githubusercontent.com/38ef81f8aca64bb9a64448d0d70f1308ef5341ab/68747470733a2f2f73332e616d617a6f6e6177732e636f6d2f6769746875622f726962626f6e732f666f726b6d655f72696768745f6461726b626c75655f3132313632312e706e67" alt="Fork me on GitHub" data-canonical-src="https://s3.amazonaws.com/github/ribbons/forkme_right_darkblue_121621.png">
</a>
<div class="container">
<div class="row">
<div class="col-md-12">
<h1 class="page-header">Sentence Boundary Detection (SBD).</h1>
<p class="lead">Split text into sentences with a `vanilla` rule based approach (i.e working ~95% of the time).</p>
<ul>
<li>Split a text based on period, question- and exclamation marks.</li>
<li>Skips (most) abbreviations (Mr., Mrs., PhD.)</li>
<li>Skips numbers/currency</li>
<li>Skips urls, websites, email addresses, phone nr.</li>
<li>Counts ellipsis and ?! as single punctuation</li>
</ul>
</div>
</div>
<div class="row padpad">
<div class="col-md-6">
<div class="form-group">
<label>Type your text here:</label>
<textarea class="form-control" ng-model='textContent' rows='12' style='width:100%'></textarea>
</div>
</div>
<div class="col">
<div class="form-group">
<label>Your results will appear here:</label>
<div>
<pre id="results">{{textContent | tokenize | json}}</pre>
<div class="help-block">{{textContent | pluralize }}</div>
</div>
</div>
</div>
</div>
<div class="padpad site-footer">
<span class="site-footer-owner">
<a href="https://github.com/Tessmore/sbd">Sbd</a> is maintained by <a href="https://github.com/Tessmore">Tessmore</a>.
</span>
<span class="site-footer-credits">This page was created by <a href="https://github.com/fpereira1">Filype Pereira (@fpereira1)</a></span>
</div>
</div>
<script src="https://ajax.googleapis.com/ajax/libs/jquery/1.11.3/jquery.min.js"></script>
</body>
</html>