-
-
Save phillipwilhelm/4b89aef25df8212d5096f9643c4a7b02 to your computer and use it in GitHub Desktop.
Check to see if a string is UTF-8 and convert it if it's not. Accidentally posted this as anonymous before :(
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<?php | |
function getUtf8String($string) { | |
if ( !isUtf8($string) ) | |
return utf8_encode($string); | |
return $string; | |
} | |
function isUtf8($string) { | |
if ( function_exists("mb_check_encoding") ) { | |
return mb_check_encoding($string, 'UTF8'); | |
} | |
return preg_match('%^(?: | |
[\x09\x0A\x0D\x20-\x7E] # ASCII | |
| [\xC2-\xDF][\x80-\xBF] # non-overlong 2-byte | |
| \xE0[\xA0-\xBF][\x80-\xBF] # excluding overlongs | |
| [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2} # straight 3-byte | |
| \xED[\x80-\x9F][\x80-\xBF] # excluding surrogates | |
| \xF0[\x90-\xBF][\x80-\xBF]{2} # planes 1-3 | |
| [\xF1-\xF3][\x80-\xBF]{3} # planes 4-15 | |
| \xF4[\x80-\x8F][\x80-\xBF]{2} # plane 16 | |
)*$%xs', $string); | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment