java字符编码,字符转码

编码:String->byte[]; str.getBytes(charsetName)

解码:byte[]->String; new String(byte[],charsetName);

package pack;

import java.io.UnsupportedEncodingException;
import java.lang.reflect.Array;
import java.util.Arrays;

public class Demo{
    /**
     *    用gbk编码 utf解码,然后再用utf编码 ,gbk解码,这样转不过来,因为gbk和utf-8里面都有中文,不过 iso8859-1可以
     */
    public static void main(String[] args) throws Exception{
        String s = "哈哈";
        byte[] b = s.getBytes("gbk");    //gbk编码
        System.out.println(Arrays.toString(b));
        
        String str = new String(b,"utf-8");    //utf-8解码
        System.out.println(str);
        
        b = str.getBytes("utf-8");
        System.out.println(Arrays.toString(b));
        str = new String(b,"gbk");
        System.out.println(str);
    }
}

 

package pack;

import java.io.UnsupportedEncodingException;
import java.lang.reflect.Array;
import java.util.Arrays;

/**
 * 把联通用gbk编码,然后把字节以二进制形式输出,是110开头,后面是10,所以系统就用utf-8去解码.
 * 这个是特例,输出二进制时候,前面有很多个1,是32位的,输出低4位,就&上255
 */
public class Demo{
    /**
     *    用gbk编码 utf解码,然后再用utf编码 ,gbk解码,这样转不过来,因为gbk和utf-8里面都有中文,不过 iso8859-1可以
     */
    public static void main(String[] args) throws Exception{
        String s = "联通";
        byte[] b = s.getBytes("gbk");    //gbk编码
        for (byte b1 : b) {
            System.out.println(Integer.toBinaryString(b1));
        }
        System.out.println(Arrays.toString(b));
        
        byte[] bb = s.getBytes("utf-8");    //gbk编码
        System.out.println(Arrays.toString(bb));
        for(byte b2:bb){
            System.out.println(Integer.toBinaryString(b2&255));
        }
        
    }
}