1
0
mirror of https://github.com/vichan-devel/vichan.git synced 2024-11-23 23:20:57 +01:00

Strip combining characters from Unicode strings (eg. Zalgo)

This commit is contained in:
Michael Foster 2013-07-28 20:33:26 -04:00
parent cea7881749
commit 57c8e4ee7c
3 changed files with 57 additions and 2 deletions

View File

@ -282,6 +282,8 @@
$config['strip_superfluous_returns'] = true;
// Require an image for threads?
$config['force_image_op'] = true;
// Strip combining characters from Unicode strings (eg. "Zalgo")
$config['strip_combining_chars'] = true;
// Max body length
$config['max_body'] = 1800;

View File

@ -1526,7 +1526,53 @@ function utf8tohtml($utf8) {
return htmlspecialchars($utf8, ENT_NOQUOTES, 'UTF-8');
}
function buildThread($id, $return=false, $mod=false) {
function ordutf8($string, &$offset) {
$code = ord(substr($string, $offset,1));
if ($code >= 128) { // otherwise 0xxxxxxx
if ($code < 224)
$bytesnumber = 2; // 110xxxxx
else if ($code < 240)
$bytesnumber = 3; // 1110xxxx
else if ($code < 248)
$bytesnumber = 4; // 11110xxx
$codetemp = $code - 192 - ($bytesnumber > 2 ? 32 : 0) - ($bytesnumber > 3 ? 16 : 0);
for ($i = 2; $i <= $bytesnumber; $i++) {
$offset ++;
$code2 = ord(substr($string, $offset, 1)) - 128; //10xxxxxx
$codetemp = $codetemp*64 + $code2;
}
$code = $codetemp;
}
$offset += 1;
if ($offset >= strlen($string))
$offset = -1;
return $code;
}
function strip_combining_chars($str) {
$chars = preg_split('//u', $str, -1, PREG_SPLIT_NO_EMPTY);
$str = '';
foreach ($chars as $char) {
$ord = ordutf8($char, $o = 0);
if ($ord >= 768 && $ord <= 879)
continue;
if ($ord >= 7616 && $ord <= 7679)
continue;
if ($ord >= 8400 && $ord <= 8447)
continue;
if ($ord >= 65056 && $ord <= 65071)
continue;
$str .= $char;
}
return $str;
}
function buildThread($id, $return = false, $mod = false) {
global $board, $config;
$id = round($id);

View File

@ -357,6 +357,13 @@ if (isset($_POST['delete'])) {
$post['thumb'] = $board['dir'] . $config['dir']['thumb'] . $post['file_id'] . '.' . ($config['thumb_ext'] ? $config['thumb_ext'] : $post['extension']);
}
if ($config['strip_combining_chars']) {
$post['name'] = strip_combining_chars($post['name']);
$post['email'] = strip_combining_chars($post['email']);
$post['subject'] = strip_combining_chars($post['name']);
$post['body'] = strip_combining_chars($post['body']);
}
// Check string lengths
if (mb_strlen($post['name']) > 35)
error(sprintf($config['error']['toolong'], 'name'));
@ -368,7 +375,7 @@ if (isset($_POST['delete'])) {
error($config['error']['toolong_body']);
if (mb_strlen($post['password']) > 20)
error(sprintf($config['error']['toolong'], 'password'));
wordfilters($post['body']);
$post['body_nomarkup'] = $post['body'];