mirror/php-htmlpurifier
1
0
Fork 0
mirror of https://github.com/ezyang/htmlpurifier.git synced 2025-07-31 03:10:09 +02:00
Code Issues Releases Wiki Activity

Accept leading digits in hostnames as per RFC 1123.

Browse Source 
Signed-off-by: Edward Z. Yang <ezyang@cs.stanford.edu>
This commit is contained in:
Edward Z. Yang
2016-03-23 22:42:18 -07:00
parent 25db9e1dd0
commit 45161b4fb1
3 changed files with 17 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
library/HTMLPurifier/AttrDef/URI/Host.php
View File

@@ -76,17 +76,23 @@ class HTMLPurifier_AttrDef_URI_Host extends HTMLPurifier_AttrDef
// fairly well supported.
$underscore = $config->get('Core.AllowHostnameUnderscore') ? '_' : '';
// Based off of RFC 1738, but amended so that
// as per RFC 3696, the top label need only not be all numeric.
// The productions describing this are:
$a = '[a-z]'; // alpha
$an = '[a-z0-9]'; // alphanum
$and = "[a-z0-9-$underscore]"; // alphanum | "-"
// domainlabel = alphanum | alphanum *( alphanum | "-" ) alphanum
$domainlabel = "$an($and*$an)?";
// toplabel = alpha | alpha *( alphanum | "-" ) alphanum
$toplabel = "$a($and*$an)?";
$domainlabel = "$an(?:$and*$an)?";
// AMENDED as per RFC 3696
// toplabel = alphanum | alphanum *( alphanum | "-" ) alphanum
// side condition: not all numeric
$toplabel = "$an(?:$and*$an)?";
// hostname = *( domainlabel "." ) toplabel [ "." ]
if (preg_match("/^($domainlabel\.)*$toplabel\.?$/i", $string)) {
return $string;
if (preg_match("/^(?:$domainlabel\.)*($toplabel)\.?$/i", $string, $matches)) {
if (!ctype_digit($matches[1])) {
return $string;
}
}
// PHP 5.3 and later support this functionality natively