Created
January 14, 2022 19:25
-
-
Save pedropuppim/a8f16cb91168cc8f0ca825d4863ee8ba to your computer and use it in GitHub Desktop.
encoding.php
This file contains 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 detect_encoding($string) | |
{ | |
//http://w3.org/International/questions/qa-forms-utf-8.html | |
if (preg_match('%^(?: [\x09\x0A\x0D\x20-\x7E] | [\xC2-\xDF][\x80-\xBF] | \xE0[\xA0-\xBF][\x80-\xBF] | [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2} | \xED[\x80-\x9F][\x80-\xBF] | \xF0[\x90-\xBF][\x80-\xBF]{2} | [\xF1-\xF3][\x80-\xBF]{3} | \xF4[\x80-\x8F][\x80-\xBF]{2} )*$%xs', $string)) | |
return 'UTF-8'; | |
//If you need to distinguish between UTF-8 and ISO-8859-1 encoding, list UTF-8 first in your encoding_list. | |
//if you list ISO-8859-1 first, mb_detect_encoding() will always return ISO-8859-1. | |
return mb_detect_encoding($string, array('UTF-8', 'ASCII', 'ISO-8859-1', 'JIS', 'EUC-JP', 'SJIS')); | |
} | |
function convert_encoding($string, $to_encoding, $from_encoding = '') | |
{ | |
if ($from_encoding == '') | |
$from_encoding = detect_encoding($string); | |
if ($from_encoding == $to_encoding) | |
return $string; | |
return mb_convert_encoding($string, $to_encoding, $from_encoding); | |
} | |
$newString = convert_encoding($oldString, 'UTF-8'); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment