Last active
April 22, 2017 15:22
-
-
Save scriptype/a96279c03e55c5da5ab57f1e2622b890 to your computer and use it in GitHub Desktop.
Flawed HTML Parser
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
(function(input) { | |
class HTMLFragment { | |
constructor(htmlText) { | |
this.raw = htmlText | |
this.parsed = HTMLFragment.parse(removeWhitespace(htmlText)) | |
return this | |
} | |
static parse(htmlText) { | |
var elementPattern = /<(\w+)(.[^>]+)?>(.+)<\/\1>/ | |
var attributesPattern = /(?:\w(?:-\w+)?)+(?:=(?:"|').[^"']+(?:"|'))?/g | |
var match = htmlText.match(elementPattern) | |
if (!match) { | |
return null | |
} | |
var [, tagName, attributesText, innerHTML ] = match | |
var firstChild = HTMLFragment.parse(innerHTML) | |
var attributes = attributesText | |
.trim() | |
.match(attributesPattern) | |
.map(attr => { | |
var [ key, value ] = attr.split('=') | |
return [ key, (value || '').slice(1, -1) ] | |
}) | |
.reduce((prev, curr) => (prev[curr[0]] = curr[1] || true, prev), {}) | |
return { | |
tagName, | |
attributes, | |
innerHTML, | |
firstChild | |
} | |
} | |
} | |
function removeWhitespace(html) { | |
return html.replace(/\n/g, '').replace(/>\s+/g, '>').trim() | |
} | |
return new HTMLFragment(input) | |
})(` | |
<div class="container pull-left" id="hello"> | |
<h1 id="main-header" class="title" aria-role="title">Oh my header!</h1> | |
<p> | |
Lorem ipsum dolor sit amet <a href="http://enes.in">Enes</a>. So, good bye! | |
</p> | |
</div> | |
`) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment