php 中的gbk,PHP中GBK和UTF8编码处理

以下为引用的内容：

if($count>= $position && $start_position> $i){

$start_position = $i;

$start_byte = $count;

}

if(($count-$start_byte)>=$length) {

$end_position = $i;

break;

}

$value = ord($str[$i]);

if($value> 127){

$count++;

if($value>= 192 && $value <= 223) $i++;

elseif($value>= 224 && $value <= 239) $i = $i + 2;

elseif($value>= 240 && $value <= 247) $i = $i + 3;

else die('Not a UTF-8 compatible string');

}

$count++;

}

return(substr($str,$start_position,$end_position-$start_position));

}

//字符串长度统计-UTF8 [中文3个字节，俄文、韩文占2个字节，字母占1个字节] (Ruby)

def utf8_string_length(str)

temp = CGI::unescape(str)

i = 0;

j = 0;

temp.length.times{|t|

if temp[t] <127

i += 1

elseif temp[t]>= 127 and temp[t] <224

j += 1

if 0 == (j % 2)

i += 2

j = 0

end

else

j += 1

if 0 == (j % 3)

i +=2

j = 0

end

end

}

return i

}

//判断是否是有韩文-UTF-8 (javascript)

function checkKoreaChar(str) {

for(i=0; i

if(((str.charCodeAt(i)> 0x3130 && str.charCodeAt(i) <0x318F) || (str.charCodeAt(i)>= 0xAC00 && str.charCodeAt(i) <= 0xD7A3))) {

return true;

}

}

return false;

}

//判断是否有中文字符-GBK (javascript)

function check_chinese_char(s){

return (s.length != s.replace(/[^x00-xff]/g,"**").length);

}