PHP代码如下：
<?php
function c_substr($string, $from, $length = null){
preg_match_all('/[x80-xff]?./', $string, $match);
if(is_null($length)){
$result = implode('', array_slice($match[0], $from));
}else{
$result = implode('', array_slice($match[0], $from, $length));
}
return $result;
}
$str = "zhon华人min共和guo";
$from = 3;
$length = 7;
echo(c_substr($str, $from, $length));
// 输出: n华人min共
//还有utf-8的
/*
Regarding windix's function to handle UTF-8 strings:
one can use the "u" modifier on the regular expression so that the pattern string is treated as UTF-8
(available from PHP 4.1.0 or greater on Unix and from PHP 4.2.3 on win32).
This way the function works for other encodings too (like Greek for example).
The modified function would read like this:
*/
function utf8_substr($str,$start) {
$null = "";
preg_match_all("/./u", $str, $ar);
if(func_num_args() >= 3) {
$end = func_get_arg(2);
return join($null, array_slice($ar[0],$start,$end));
} else {
return join($null, array_slice($ar[0],$start));
}
}
?>
之二：
<?php
/* http://www.dngz.net/blog/ */
function get_substr($string,$start='0',$length='')
{
$start = (int)$start;
$length = (int)$length;
$i = 0;
if(!$string)
{
return;
}
if($start>=0)
{
while($i<$start)
{
if(ord($string[$i])>127)
{
$i = $i+2;
}
else
{
$i++;
}
}
$start = $i;
if($length=='')
{
return substr($string,$start);
}
elseif($length>0)
{
$end = $start+$length;
while($i<$end)
{
if(ord($string[$i])>127)
{
$i = $i+2;
}
else
{
$i++;
}
}
if($end != $i-1)
{
$end = $i;
}
else
{
$end--;
}
$length = $end-$start;
return substr($string,$start,$length);
}
elseif($length==0)
{
return;
}
else
{
$length = strlen($string)-abs($length)-$start;
return get_substr($string,$start,$length);
}
}
else
{
$start = strlen($string)-abs($start);
return get_substr($string,$start,$length);
}
}
?>
