mirror of
https://github.com/EGroupware/egroupware.git
synced 2024-11-19 06:23:12 +01:00
8f797be836
- can be used via html class like:
$clean_html = html::purify($html);
- using it now in eTemplate to remove malicious code from html:
a) when displaying "formatted text"
b) when "formatted text" get's input by the user
49 lines
1.5 KiB
PHP
Executable File
49 lines
1.5 KiB
PHP
Executable File
<?php
|
|
|
|
/**
|
|
* Validates contents based on NMTOKENS attribute type.
|
|
* @note The only current use for this is the class attribute in HTML
|
|
* @note Could have some functionality factored out into Nmtoken class
|
|
* @warning We cannot assume this class will be used only for 'class'
|
|
* attributes. Not sure how to hook in magic behavior, then.
|
|
*/
|
|
class HTMLPurifier_AttrDef_HTML_Nmtokens extends HTMLPurifier_AttrDef
|
|
{
|
|
|
|
public function validate($string, $config, $context) {
|
|
|
|
$string = trim($string);
|
|
|
|
// early abort: '' and '0' (strings that convert to false) are invalid
|
|
if (!$string) return false;
|
|
|
|
// OPTIMIZABLE!
|
|
// do the preg_match, capture all subpatterns for reformulation
|
|
|
|
// we don't support U+00A1 and up codepoints or
|
|
// escaping because I don't know how to do that with regexps
|
|
// and plus it would complicate optimization efforts (you never
|
|
// see that anyway).
|
|
$matches = array();
|
|
$pattern = '/(?:(?<=\s)|\A)'. // look behind for space or string start
|
|
'((?:--|-?[A-Za-z_])[A-Za-z_\-0-9]*)'.
|
|
'(?:(?=\s)|\z)/'; // look ahead for space or string end
|
|
preg_match_all($pattern, $string, $matches);
|
|
|
|
if (empty($matches[1])) return false;
|
|
|
|
// reconstruct string
|
|
$new_string = '';
|
|
foreach ($matches[1] as $token) {
|
|
$new_string .= $token . ' ';
|
|
}
|
|
$new_string = rtrim($new_string);
|
|
|
|
return $new_string;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
// vim: et sw=4 sts=4
|