ADD XSS attacks filter

includes/pbboardCodeparse.class.php

@@ -637,7 +637,7 @@ function censor_words($text)
         $text = str_ireplace('rel="nofollow" href="#', 'href="#', $text);
         $text = str_ireplace('rel="dofollow" href="#', 'href="#', $text);
             eval($PowerBB->functions->get_fetch_hooks('BBCodeParseHooks3'));
-
+       // $text = strip_tags($text);
         $censorwords = preg_split('#[ \r\n\t]+#', $PowerBB->_CONF['info_row']['censorwords'], -1, PREG_SPLIT_NO_EMPTY);
         $text = str_ireplace($censorwords,'**', $text);
          $blankasciistrip ="160 173 u8205 u8204 u8237 u8238";
@@ -760,7 +760,8 @@ function censor_words($text)
             $text = str_replace('  rel="dofollow"   ', ' rel="dofollow" ', $text);
 
           $text = str_replace("<br>", "<br />", $text);
-
+          //XSS filtering function
+            $text = $this->xss_clean($text);
             eval($PowerBB->functions->get_fetch_hooks('BBCodeParseHooks_cr'));
 
 
@@ -818,6 +819,44 @@ function censor_words($text)
 
         return $this->replace($text."n-l-2-b-r");
 	}
+
+    //XSS filtering function
+	function xss_clean($data)
+	{
+	// Fix &entity\n;
+	$data = str_replace(array('&amp;','&lt;','&gt;'), array('&amp;amp;','&amp;lt;','&amp;gt;'), $data);
+	$data = preg_replace('/(&#*\w+)[\x00-\x20]+;/u', '$1;', $data);
+	$data = preg_replace('/(&#x*[0-9A-F]+);*/iu', '$1;', $data);
+	$data = html_entity_decode($data, ENT_COMPAT, 'UTF-8');
+
+	// Remove any attribute starting with "on" or xmlns
+	$data = preg_replace('#(<[^>]+?[\x00-\x20"\'])(?:on|xmlns)[^>]*+>#iu', '$1>', $data);
+
+	// Remove javascript: and vbscript: protocols
+	$data = preg_replace('#([a-z]*)[\x00-\x20]*=[\x00-\x20]*([`\'"]*)[\x00-\x20]*j[\x00-\x20]*a[\x00-\x20]*v[\x00-\x20]*a[\x00-\x20]*s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:#iu', '$1=$2nojavascript...', $data);
+	$data = preg_replace('#([a-z]*)[\x00-\x20]*=([\'"]*)[\x00-\x20]*v[\x00-\x20]*b[\x00-\x20]*s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:#iu', '$1=$2novbscript...', $data);
+	$data = preg_replace('#([a-z]*)[\x00-\x20]*=([\'"]*)[\x00-\x20]*-moz-binding[\x00-\x20]*:#u', '$1=$2nomozbinding...', $data);
+
+	// Only works in IE: <span style="width: expression(alert('Ping!'));"></span>
+	$data = preg_replace('#(<[^>]+?)style[\x00-\x20]*=[\x00-\x20]*[`\'"]*.*?expression[\x00-\x20]*\([^>]*+>#i', '$1>', $data);
+	$data = preg_replace('#(<[^>]+?)style[\x00-\x20]*=[\x00-\x20]*[`\'"]*.*?behaviour[\x00-\x20]*\([^>]*+>#i', '$1>', $data);
+	$data = preg_replace('#(<[^>]+?)style[\x00-\x20]*=[\x00-\x20]*[`\'"]*.*?s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:*[^>]*+>#iu', '$1>', $data);
+
+	// Remove namespaced elements (we do not need them)
+	$data = preg_replace('#</*\w+:\w[^>]*+>#i', '', $data);
+
+	do
+	{
+	    // Remove really unwanted tags
+	    $old_data = $data;
+	    $data = preg_replace('#</*(?:applet|b(?:ase|gsound|link)|embed|frame(?:set)?|i(?:frame|layer)|l(?:ayer|ink)|meta|object|s(?:cript|tyle)|title|xml)[^>]*+>#i', '', $data);
+	}
+	while ($old_data !== $data);
+
+	// we are done...
+	return $data;
+	}
+
    // long URL, Shortening Long URLs With PHP
  	function shortenurl($Aurl,$Burl,$lg_max)
 	{
@@ -1553,7 +1592,6 @@ function replace_htmlentities($string)
 				$string = preg_replace_callback($li_not, function($lidd) {
 				    return $this->li_not_bar($lidd[1]);
 				}, $string);
-
         return $string;
  	}