PHP Chinese and encoding judgment code_PHP tutorial

Encoding 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 example

Copy Code The code is as follows:

//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, $i);
}
//Statistical string length-UTF8 (PHP)
function utf8_strlen($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));
}
//Determine whether there is Korean-UTF-8 (JavaScript)
function checkKoreaChar(str) {
for(i=0; iif(((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);
}

http://www.bkjia.com/PHPjc/321937.htmlwww.bkjia.comtruehttp: //www.bkjia.com/PHPjc/321937.htmlTechArticleEncoding 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...