note 85866 deleted from function.utf8-encode by cmb
| From: | cmb@php.net | Date: | Sun, 04 Dec 2016 12:14:58 +0000 |
| Subject: | note 85866 deleted from function.utf8-encode by cmb | ||
| References: | 1 | Groups: | php.notes |
| Request: | Send a blank email to php-notes+get-208204@lists.php.net to get a copy of this message | ||
Note Submitter: bitseeker
----
...or just use this simple piece of code to check valid utf-8 string:
<?php
/**
* Returns true if $string is valid UTF-8 and false otherwise.
*
* @since 1.14
* @param [mixed] $string string to be tested
* @subpackage
*/
function is_utf8($string) {
// From http://w3.org/International/questions/qa-forms-utf-8.html
return preg_match('%^(?:
[\x09\x0A\x0D\x20-\x7E] # ASCII
| [\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
)*$%xs', $string);
}
?>