Created
October 22, 2010 07:23
-
-
Save wjzhangq/640093 to your computer and use it in GitHub Desktop.
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 | |
var_dump(mb_str_split('hello 小姐 韩语中字全集')); | |
var_dump(utf8_split('hello 小姐 韩语中字全集')); | |
var_dump(utf8_split_by_mb('hello 小姐 韩语中字全集')); | |
function utf8_split($str){ | |
$bin11 = 0xC0; | |
$bin10 = 0x80; | |
$ch11 = chr($bin11); | |
$ch10 = chr($bin10); | |
$data = array(); | |
$str_len = strlen($str); //str length | |
$pos = -1; //postion | |
for($i=0; $i<$str_len; $i++){ | |
if(($str{$i} & $ch11) != $ch10){ | |
++$pos; | |
} | |
isset($data[$pos]) or $data[$pos] = ''; | |
$data[$pos] .= $str{$i}; | |
} | |
return $data; | |
} | |
function mb_str_split( $string ) { | |
# Split at all position not after the start: ^ | |
# and not before the end: $ | |
return preg_split('/(?<!^)(?!$)/u', $string ); | |
} | |
function utf8_split_by_mb($string){ | |
$stop = mb_strlen( $string); | |
$result = array(); | |
for( $idx = 0; $idx < $stop; $idx++) | |
{ | |
$result[] = mb_substr( $string, $idx, 1); | |
} | |
return $result; | |
} | |
?> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment