// note that you have to handle splits with \n, \r, and \t later since they *are* allowed in some inputs
$val = preg_replace('/(?:[\x00-\x08][\x0b-\x0c][\x0e-\x20])/', '', $val);
// straight replacements, the user should never need these since they're normal characters
// this prevents like )
$search = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890!@#$%^&*()~`";:?+/={}[]-_|\'\\';
$length = strlen($search);
for ($i = 0; $i < $length; $i++) {
// ;? matches the ;, which is optional
// 0{0,7} matches any padded zeros, which are optional and go up to 8 chars
// @ @ search for the hex values
$val = preg_replace('/(?:&#[x|X]0{0,8}'.dechex(ord($search[$i])).';?)/i', $search[$i], $val); // with a ;
// @ @ 0{0,7} matches '0' zero to seven times
$val = preg_replace('/(?:�{0,8}'.ord($search[$i]).';?)/', $search[$i], $val); // with a ;
}
// now the only remaining whitespace attacks are \t, \n, and \r
$found = true; // keep replacing as long as the previous round replaced something
while ($found == true) {
$val_before = $val;
$ra_length = count($ra);
for ($i = 0; $i < $ra_length; $i++) {
$pattern = '/';
$ra_str_length = strlen($ra[$i]);
for ($j = 0; $j < $ra_str_length; $j++) {
$pattern .= '('
. '(?:&#[x|X]0{0,8}([9][a][b]);?)?'
. '|(?:�{0,8}([9][10][13]);?)?'
. ')?'
. $ra[$i][$j];
}
$pattern .= '/i';
$replacement = substr($ra[$i], 0, 2).''.substr($ra[$i], 2); // add in <> to nerf the tag
$val = preg_replace($pattern, $replacement, $val); // filter out the hex tags
if ($val_before == $val) {
// no replacements were made, so exit the loop
$found = false;
}
}
}
return $val;
}
?>