- Java is a 16-bit unicode char type, but also Chinese, two bytes, but if (general system default) or with utf-8 is converted to an array of bytes read, will become 3 bytes.
- Unicode character set, UTF-8 / UTF-16 encoding rules, or generalized Unicode character set and including a plurality of encoding rules. That character set specified binary code, each character encoding rules only specifies how to store the binary code.
- Then utf-16 you a question about the big-endian (Big Endian order) and the little-endian (Little Endian order) are (more complex utf-8, so it is best not to cause programming under windows).
- In Java, a Chinese character for char, getByte result, if not specified coding rule, the default is UTF-8, a Chinese 3 bytes , if unicode or utf-16, default is 4 bytes, the first two bytes represented 0xFEFF big endian, 0xFFEF indicates little-endian , if specified utf-16be or utf-16le, is 2 bytes ,
package IOTest;
import javax.management.StandardEmitterMBean;
import java.io.UnsupportedEncodingException;
import java.nio.charset.Charset;
import java.nio.charset.StandardCharsets;
public class CharTest {
public static void main(String[] args) throws UnsupportedEncodingException {
//Java的char是两字节的Unicode字符(0-65535)
char b='中';
System.out.println((int)b);
byte[] bs=char2Byte(b);
System.out.println(byte2HexString(bs));
byte[] cs=String.valueOf(b).getBytes("unicode");
byte[] ds=String.valueOf(b).getBytes(StandardCharsets.UTF_16BE);
byte[] es=String.valueOf(b).getBytes(StandardCharsets.UTF_16LE);
byte[] fs=String.valueOf(b).getBytes(StandardCharsets.UTF_16);
byte[] gs=String.valueOf(b).getBytes(StandardCharsets.UTF_8);
System.out.println(byte2HexString(cs));
System.out.println(byte2HexString(ds));
System.out.println(byte2HexString(es));
System.out.println(byte2HexString(fs));
System.out.println(byte2HexString(gs));
}
public static byte[] char2Byte(char c){
byte[] ans=new byte[2];
ans[1]=(byte)(c&0x00ff);
ans[0]=(byte)((c&0xff00)>>8);
return ans;
}
public static String byte2HexString(byte[] bs){
StringBuilder sb=new StringBuilder();
for(byte b:bs){
int c=b&0x0f;
if(c<10){
sb.append(c);
}else{
sb.append((char)((c-10)+'A'));
}
c=(b&0xf0)>>4;
if(c<10){
sb.append(c);
}else{
sb.append((char)((c-10)+'A'));
}
sb.append(' ');
}
return sb.toString();
}
}