中文编码

char c = '淘';  中文字
String uncoide = Integer.toHexString(c); 把中文字转成16进制的 unicode 因为是2个字节的
 System.out.println(c+"的uncoide编码:\t"+uncoide);
       

c = '宝';
uncoide = Integer.toHexString(c);
System.out.println(c+"的uncoide编码:\t"+uncoide);


//从uncoide编码转换成10进制
int x = Integer.parseInt(uncoide, 16);
System.out.println(uncoide+"转成10进制:\t"+x);


打印出 23453

宝 的10进制数是  23453
 System.out.println(Integer.toBinaryString(23453));


淘宝 两个字的16进制树
String a = "\u6dd8\u5b9d";
System.out.println(a);

package dannytest.charset;

import java.io.UnsupportedEncodingException;
import java.nio.ByteBuffer;
import java.nio.CharBuffer;
import java.nio.charset.Charset;

public class CharsetTest {
	
	public static void main(String[] args) throws UnsupportedEncodingException {
		
		Charset charset = Charset.forName("UTF-8");
		ByteBuffer byteBuffer = charset.encode("淘宝");
		byte[] c1 = byteBuffer.array();
		for(byte t : c1){
			System.out.println(t);
		}
		
		System.out.println(new String(c1, "UTF-8"));
		CharBuffer charBuffer = charset.decode(byteBuffer);
		String c2 = charBuffer.toString();
		System.out.println(c2);
		
		parseByISO_8859_1();
		parseByGB2312();
		parseByUtf8();
		
		parseByUnicode();
        
       
        
		
		
	}
	
	
	public static void parseByUnicode(){
		//获得字符的uncoide编码
        char c = '淘';
        String uncoide = Integer.toHexString(c);
        System.out.println(c+"的uncoide编码:\t"+uncoide);
        
         c = '宝';
        uncoide = Integer.toHexString(c);
        System.out.println(c+"的uncoide编码:\t"+uncoide);
         
        
        //从uncoide编码转换成10进制
        int x = Integer.parseInt(uncoide, 16);
        System.out.println(uncoide+"转成10进制:\t"+x);
         
        //从10进制转成uncoide编码
        int y = 39118;
        System.out.println(y+"转成uncoide编码:\t"+Integer.toHexString(y));
		
		
		String a = "\u6dd8\u5b9d";
		
		
		System.out.println(a);
	}
	
	public static void parseByUtf8() throws UnsupportedEncodingException{
		String tao = "淘";
		String bao = "宝";
		
		byte[] taoByte = tao.getBytes("UTF-8");
		
		for(byte t : taoByte){
			System.out.println(t);
		}
		
		System.out.println("word1 : " + new String(taoByte, "UTF-8"));
		
		byte[] baoByte = bao.getBytes("UTF-8");
		
		for(byte t : baoByte){
			System.out.println(t);
		}		
		
		System.out.println("word2 : " + new String(baoByte, "UTF-8"));
		
	}

	public static void parseByISO_8859_1() throws UnsupportedEncodingException{
		String tao = "淘";
		String bao = "宝";
		
		byte[] taoByte = tao.getBytes("ISO-8859-1");
		
		for(byte t : taoByte){
			System.out.println(t);
		}
		
		System.out.println("word1 : " + new String(taoByte, "ISO-8859-1"));
		
		byte[] baoByte = bao.getBytes("ISO-8859-1");
		
		for(byte t : baoByte){
			System.out.println(t);
		}		
		
		System.out.println("word2 : " + new String(baoByte, "ISO-8859-1"));
		
	}
	
	public static void parseByGB2312() throws UnsupportedEncodingException{
		String tao = "淘";
		String bao = "宝";
		
		byte[] taoByte = tao.getBytes("GB2312");
		
		for(byte t : taoByte){
			System.out.println(t);
		}
		
		System.out.println("word1 : " + new String(taoByte, "GB2312"));
		
		byte[] baoByte = bao.getBytes("GB2312");
		
		for(byte t : baoByte){
			System.out.println(t);
		}		
		
		System.out.println("word2 : " + new String(baoByte, "GB2312"));
		
	}
	
}