复制内容到剪贴板
代码:
上三个版本的都或解决了utf8 下截字的乱码问题，但功能不是很全面，这次贴出的在功能上和substr已经不相上下了，代码如下：
<?php
class splite_utf8
{
private function splite_single_utf8_left_word ($str )
{
$aciss = ord( $str);
$out_str = '';
if ($aciss >= 240 )
{
$out_str.=substr ( $str, 0, 4 );
}
elseif ($aciss >= 224 )
{
$out_str.=substr ( $str, 0, 3 );
}
elseif ($aciss >= 192 )
{
$out_str.=substr ( $str, 0, 2 );
}
else
{
$out_str.=substr ($str, 0, 1 );
}
return $out_str;
}
private function splite_single_utf8_right_word ($str )
{
$aciss = ord( $str);
$out_str = '';
if ($aciss >= 240 )
{
$out_str.=substr ( $str, 4 );
}
elseif ($aciss >= 224 )
{
$out_str.= substr ( $str, 3 );
}
elseif ($aciss >= 192 )
{
$out_str.= substr ( $str, 2 );
}
else
{
$out_str.= substr ($str, 1 );
}
return $out_str;
}
public function count_word($str, $length=0 )
{
$aciss = ord( $str);
if ($aciss >= 240 )
{
$length+= 1;
$str=substr($str,4);
}
elseif ($aciss >= 224 )
{
$length+= 1;
$str=substr($str,3);
}
elseif ($aciss >= 192 )
{
$length+= 1;
$str=substr($str,2);
}
else
{
$length+= 1;
$str=substr($str,1);
}
if($str=='')
{
return $length;
}
else
{
return $this->count_word($str,$length);
}
}
public function splite_mulit_utf8_word ($str, $start = 0, $length = -1 )
{
$temp = '';
if($start < 0 )
{
$start = $this->count_word($str) + $start;
}
for ($i = 0; $i < $start; $i++ )
{
$str=$this->splite_single_utf8_right_word ($str );
}
for ($i = 0; $i < $length; $i++ )
{
$temp.= $this->splite_single_utf8_left_word ($str );
$str = $this->splite_single_utf8_right_word ($str );
}
if( $length == -1 )
{
return $str;
}
else
{
return $temp;
}
}
}
$utf=new splite_utf8();
$text='的萨芬dfdf!@#$%^&*I()';
$length=$utf->count_word($text);
echo $length."\n";
$word=$utf->splite_mulit_utf8_word ($text, -6, 2);
var_dump($word);
?>
屏幕输出的就是
18
string(2) "^&"
