note 98612 deleted from function.strip-tags by danbrown
| From: | danbrown@php.net | Date: | Sun, 27 Jun 2010 00:03:33 +0000 |
| Subject: | note 98612 deleted from function.strip-tags by danbrown | ||
| References: | 1 | Groups: | php.notes |
| Request: | Send a blank email to php-notes+get-170504@lists.php.net to get a copy of this message | ||
Note Submitter: phpnet at buzzhost dot co dot uk
----
the sample below by php at whizzaps dot com will max out & time out the server if a single <
(less than) sign is entered without a matching close. This function does *not* suffer from this
problem:
<?php
function StripHTML ($arg,$cleanup) {
//cleanup ==1 replace any stray less than /great than with alt html entities
//else leave as are
$allowed_tags = array('a','b','i','br', 'p',
'div', 'strong', 'em', 'ul', 'ol', 'li',
'dl', 'dd', 'dt');
$arg_length = strlen($arg);
if ($arg_length < 2) { return 0; }
$flipflop = 0;
for ($i = 0; $i <= $arg_length; $i++) {
$character = substr($arg, $i, 1);
switch ($character){
case "<":
if ($flipflop ==0){
$start_position = $i;
$flipflop = 1;
} else {
if ($cleanup==1) {
$buffer = "<" . substr($arg, ($start_position+1), (($i-$start_position)-1));
} else {
$buffer = "<" . substr($arg, ($start_position+1), (($i-$start_position)-1));
}
$output .= $buffer;
}
break;
case ">":
if ($flipflop ==0){
if ($cleanup==1) {
$output .= ">";
} else {
$output .= ">;";
}
}else{
$flipflop = 0;
$tmptagtext = trim($tagtext);
$tmp = explode(" ", $tmptagtext,2);
$tmptagtext = $tmp[0];
$tagtext = "<$tagtext>";
foreach ($allowed_tags as $value) {
if (($tmptagtext==$value)||($tmptagtext=="/$value")) {
$output .= "$tagtext";
}
}
$tagtext ="";
$tmptagtext = "";
unset($value);
}
break;
default:
if ($flipflop ==0) {
$output .= $character;
}
if ($flipflop ==1) {
$tagtext .= $character;
}
}
}
return $output;
}
?>
However, any javascript or other embeded content may still be abused as user input. This function
deals with that added menace:
<?php
function NoICT ($arg) {
$match = array(
// Remove invisible content
'@<head[^>]*?>.*?</head>@siu',
'@<style[^>]*?>.*?</style>@siu',
'@<script[^>]*?.*?</script>@siu',
'@<object[^>]*?.*?</object>@siu',
'@<embed[^>]*?.*?</embed>@siu',
'@<applet[^>]*?.*?</applet>@siu',
'@<noframes[^>]*?.*?</noframes>@siu',
'@<noscript[^>]*?.*?</noscript>@siu',
'@<noembed[^>]*?.*?</noembed>@siu',
'@</?((frameset)|(frame)|(iframe))@iu'
);
$arg = preg_replace($match, "", $arg);
return $arg;
}
?>