Removes HTML tags from a string that are not listed in the whitelist

remove-html-tags.js

/*
<b>              - bold, use as last resort <h1>-<h3>, <em>, and <strong> are 
                   preferred.
<blockquote>     - specifies a section that is quoted from another source.
<code>           - defines a piece of computer code.
<del>            - delete, used to indicate modifications.
<dd>             - describes the item in a <dl> description list.
<dl>             - description list.
<dt>             - title of an item in a <dl> description list.
<em>             - emphasized.
<h1>, <h2>, <h3> - headings.
<i>              - italic.
<img>            - specifies an image tag.
<kbd>            - represents user input (usually keyboard input).
<li>             - list item in an ordered list <ol> or an unordered list <ul>.
<ol>             - ordered list.
<p>              - paragraph.
<pre>            - pre-element displayed in a fixed width font and and 
                   unchanged line breaks.
<s>              - strikethrough.
<sup>            - superscript text appears 1/2 character above the baseline 
                   used for footnotes and other formatting.
<sub>            - subscript appears 1/2 character below the baseline.
<strong>         - defines important text.
<strike>         - strikethrough is deprecated, use <del> instead.
<ul>             - unordered list.
<br>             - line break.
<hr>             - defines a thematic change in the content, usually via a 
                   horizontal line.
*/

function cleanEvilTags(string) {
  if (!string) return '';

  var whitelistTags = 'b|blockquote|code|del|d[d|l|t]|em|h[1-7]|i|kbd|[o|i|u]l|p|pre|s|sup|sub|strong|strike|br|hr';
  var regex = new RegExp('\<(?!\/?(' + whitelistTags + ')[ >])[^>]*\>', 'ig');

  return string.replace(regex, '');
}