GBK and UTF8 encoding processing in PHP_PHP tutorial-PHP Tutorial-php.cn

GBK and UTF8 encoding processing in PHP_PHP tutorial

WBOY

Release： 2016-07-13 17:38:08

Original

772 people have browsed it

1. Coding range
1. GBK (GB2312/GB18030)
x00-xff GBK double-byte encoding range
x20-x7f ASCII
xa1-xff Chinese
x80-xff Chinese

2. UTF-8 (Unicode)
u4e00-u9fa5 (Chinese)
x3130-x318F (Korean)
xAC00-xD7A3 (Korean)
u0800-u4e00 (Japanese)
ps: Korean is a character larger than [u9fa5]

Regular example:
preg_replace("/([x80-xff])/","",$str);
preg_replace("/([u4e00-u9fa5])/","",$str);

2. Code examples

//Judge whether there is Chinese in the content-GBK (PHP)
function check_is_chinese($s){
Return preg_match(/[x80-xff]./, $s);
}
//Get the string length-GBK (PHP)
function gb_strlen($str){
$count = 0;
for($i=0; $i           $s = substr($str, $i, 1);
If (preg_match("/[x80-xff]/", $s)) ++$i;
         ++$count;
}
Return $count;
}
//Intercept string string-GBK (PHP)
function gb_substr($str, $len){
$count = 0;
for($i=0; $i If($count == $len) break;
If(preg_match("/[x80-xff]/", substr($str, $i, 1))) ++$i;
          ++$count;                                          }
Return substr($str, 0, $i);
}
//Statistics string length-UTF8 (PHP)
function utf8_strlen($str) {
$count = 0;
for($i = 0; $i < strlen($str); $i++){
         $value = ord($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 $count;
}

//Intercept string-UTF8(PHP)
function utf8_substr($str,$position,$length){
$start_position = strlen($str);
$start_byte = 0;
$end_position = strlen($str);
$count = 0;
for($i = 0; $i < strlen($str); $i++){
If($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));
}

//String length statistics-UTF8 [3 bytes for Chinese, 2 bytes for Russian and Korean, 1 byte for letters] (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
}

//Determine whether it contains Korean-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;
}

//Determine whether there are Chinese characters-GBK (javascript)
function check_chinese_char(s){
Return (s.length != s.replace(/[^x00-xff]/g,"**").length);
}