mirror of
https://github.com/ezyang/htmlpurifier.git
synced 2024-12-23 17:01:51 +00:00
522c8ed7c2
- Add FSTools:globr() - require_once removed from all files - HTMLPurifier.autoload.php added to register autoload handler - Removed redundant chdir in maintenance script - Modified standalone to use HTMLPurifier.includes.php for including stuff - Added maintenance script remove-require-once.php which we used once and should never use again git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@1516 48356398-32a2-884e-a903-53898d9a118a
61 lines
2.1 KiB
PHP
61 lines
2.1 KiB
PHP
<?php
|
|
|
|
/**
|
|
* Parses a URI into the components and fragment identifier as specified
|
|
* by RFC 2396.
|
|
* @todo Replace regexps with a native PHP parser
|
|
*/
|
|
class HTMLPurifier_URIParser
|
|
{
|
|
|
|
/**
|
|
* Parses a URI
|
|
* @param $uri string URI to parse
|
|
* @return HTMLPurifier_URI representation of URI
|
|
*/
|
|
public function parse($uri) {
|
|
$r_URI = '!'.
|
|
'(([^:/?#<>\'"]+):)?'. // 2. Scheme
|
|
'(//([^/?#<>\'"]*))?'. // 4. Authority
|
|
'([^?#<>\'"]*)'. // 5. Path
|
|
'(\?([^#<>\'"]*))?'. // 7. Query
|
|
'(#([^<>\'"]*))?'. // 8. Fragment
|
|
'!';
|
|
|
|
$matches = array();
|
|
$result = preg_match($r_URI, $uri, $matches);
|
|
|
|
if (!$result) return false; // *really* invalid URI
|
|
|
|
// seperate out parts
|
|
$scheme = !empty($matches[1]) ? $matches[2] : null;
|
|
$authority = !empty($matches[3]) ? $matches[4] : null;
|
|
$path = $matches[5]; // always present, can be empty
|
|
$query = !empty($matches[6]) ? $matches[7] : null;
|
|
$fragment = !empty($matches[8]) ? $matches[9] : null;
|
|
|
|
// further parse authority
|
|
if ($authority !== null) {
|
|
// ridiculously inefficient: it's a stacked regex!
|
|
$HEXDIG = '[A-Fa-f0-9]';
|
|
$unreserved = 'A-Za-z0-9-._~'; // make sure you wrap with []
|
|
$sub_delims = '!$&\'()'; // needs []
|
|
$pct_encoded = "%$HEXDIG$HEXDIG";
|
|
$r_userinfo = "(?:[$unreserved$sub_delims:]|$pct_encoded)*";
|
|
$r_authority = "/^(($r_userinfo)@)?(\[[^\]]+\]|[^:]*)(:(\d*))?/";
|
|
$matches = array();
|
|
preg_match($r_authority, $authority, $matches);
|
|
$userinfo = !empty($matches[1]) ? $matches[2] : null;
|
|
$host = !empty($matches[3]) ? $matches[3] : '';
|
|
$port = !empty($matches[4]) ? (int) $matches[5] : null;
|
|
} else {
|
|
$port = $host = $userinfo = null;
|
|
}
|
|
|
|
return new HTMLPurifier_URI(
|
|
$scheme, $userinfo, $host, $port, $path, $query, $fragment);
|
|
}
|
|
|
|
}
|
|
|