Php Chinese and encoding judgment code

Php judges Chinese characters and codes. gbk indicates dubyte, and utf8 indicates three bytes. it can be determined based on the range of Chinese characters. Encoding range: 1. GBK (GB2312/GB18030)
\ X00-\ xff GBK dubyte 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 greater than [\ u9fa5]
Regular expression example:
Preg_replace ("/([\ x80-\ xff])/", "", $ str );
Preg_replace ("/([u4e00-u9fa5])/", ", $ str );
II. code example
The code is as follows:
// Determine whether the content contains Chinese characters-GBK (PHP)
Function check_is_chinese ($ s ){
Return preg_match ('/[\ x80-\ xff]./', $ s );
}
// Obtain 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;
}
// Truncate the 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 );
}
// Count the length of the string-UTF8 (PHP)
Function utf8_strlen ($ str ){
$ Count = 0;
For ($ I = 0; $ I <strlen ($ str); $ I ++ ){
$ Value = ord ($ str [$ I]);
If ($ value & gt; 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;
}
// Truncate the 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 & gt; 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 if there is a 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 a Chinese character-GBK (JavaScript) exists)
Function check_chinese_char (s ){
Return (s. length! = S. replace (/[^ \ x00-\ xff]/g, "**"). length );
}