diff options
Diffstat (limited to 'inc')
| -rw-r--r-- | inc/config.php | 2 | ||||
| -rw-r--r-- | inc/functions.php | 49 |
2 files changed, 50 insertions, 1 deletions
diff --git a/inc/config.php b/inc/config.php index f046392b..f691d4f5 100644 --- a/inc/config.php +++ b/inc/config.php @@ -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 $config['max_body'] = 1800; diff --git a/inc/functions.php b/inc/functions.php index 180c74d5..609e27c8 100644 --- a/inc/functions.php +++ b/inc/functions.php @@ -1556,7 +1556,54 @@ function utf8tohtml($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) { + $o = 0; + $ord = ordutf8($char, $o); + + if ($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); |