| Server IP : 49.231.201.246 / Your IP : 216.73.216.149 Web Server : Apache/2.4.18 (Ubuntu) System : Linux 246 4.4.0-210-generic #242-Ubuntu SMP Fri Apr 16 09:57:56 UTC 2021 x86_64 User : root ( 0) PHP Version : 7.0.33-0ubuntu0.16.04.16 Disable Function : exec,passthru,shell_exec,system,proc_open,popen,pcntl_exec MySQL : OFF | cURL : ON | WGET : ON | Perl : ON | Python : ON | Sudo : ON | Pkexec : ON Directory : /var/www/html/old/libraries/phputf8/utils/ |
Upload File : |
<?php
/**
* PCRE Regular expressions for UTF-8. Note this file is not actually used by
* the rest of the library but these regular expressions can be useful to have
* available.
* @version $Id$
* @see http://www.w3.org/International/questions/qa-forms-utf-8
* @package utf8
* @subpackage patterns
*/
//--------------------------------------------------------------------
/**
* PCRE Pattern to check a UTF-8 string is valid
* Comes from W3 FAQ: Multilingual Forms
* Note: modified to include full ASCII range including control chars
* @see http://www.w3.org/International/questions/qa-forms-utf-8
* @package utf8
* @subpackage patterns
*/
$UTF8_VALID = '^('.
'[\x00-\x7F]'. # ASCII (including control chars)
'|[\xC2-\xDF][\x80-\xBF]'. # non-overlong 2-byte
'|\xE0[\xA0-\xBF][\x80-\xBF]'. # excluding overlongs
'|[\xE1-\xEC\xEE\xEF][\x80-\xBF]{2}'. # straight 3-byte
'|\xED[\x80-\x9F][\x80-\xBF]'. # excluding surrogates
'|\xF0[\x90-\xBF][\x80-\xBF]{2}'. # planes 1-3
'|[\xF1-\xF3][\x80-\xBF]{3}'. # planes 4-15
'|\xF4[\x80-\x8F][\x80-\xBF]{2}'. # plane 16
')*$';
//--------------------------------------------------------------------
/**
* PCRE Pattern to match single UTF-8 characters
* Comes from W3 FAQ: Multilingual Forms
* Note: modified to include full ASCII range including control chars
* @see http://www.w3.org/International/questions/qa-forms-utf-8
* @package utf8
* @subpackage patterns
*/
$UTF8_MATCH =
'([\x00-\x7F])'. # ASCII (including control chars)
'|([\xC2-\xDF][\x80-\xBF])'. # non-overlong 2-byte
'|(\xE0[\xA0-\xBF][\x80-\xBF])'. # excluding overlongs
'|([\xE1-\xEC\xEE\xEF][\x80-\xBF]{2})'. # straight 3-byte
'|(\xED[\x80-\x9F][\x80-\xBF])'. # excluding surrogates
'|(\xF0[\x90-\xBF][\x80-\xBF]{2})'. # planes 1-3
'|([\xF1-\xF3][\x80-\xBF]{3})'. # planes 4-15
'|(\xF4[\x80-\x8F][\x80-\xBF]{2})'; # plane 16
//--------------------------------------------------------------------
/**
* PCRE Pattern to locate bad bytes in a UTF-8 string
* Comes from W3 FAQ: Multilingual Forms
* Note: modified to include full ASCII range including control chars
* @see http://www.w3.org/International/questions/qa-forms-utf-8
* @package utf8
* @subpackage patterns
*/
$UTF8_BAD =
'([\x00-\x7F]'. # ASCII (including control chars)
'|[\xC2-\xDF][\x80-\xBF]'. # non-overlong 2-byte
'|\xE0[\xA0-\xBF][\x80-\xBF]'. # excluding overlongs
'|[\xE1-\xEC\xEE\xEF][\x80-\xBF]{2}'. # straight 3-byte
'|\xED[\x80-\x9F][\x80-\xBF]'. # excluding surrogates
'|\xF0[\x90-\xBF][\x80-\xBF]{2}'. # planes 1-3
'|[\xF1-\xF3][\x80-\xBF]{3}'. # planes 4-15
'|\xF4[\x80-\x8F][\x80-\xBF]{2}'. # plane 16
'|(.{1}))'; # invalid byte