java中的编码转换过程(以utf8和gbk为例)

/**
 * 测试编码转换 中文 => utf-8 编码 - 解码
 */
@Test
public void test0() {
    String test = "测试";
    System.out.println(Arrays.toString(test.getBytes(StandardCharsets.UTF_8)));//[-26, -75, -117, -24, -81, -107]
    System.out.println(new String(test.getBytes(StandardCharsets.UTF_8), StandardCharsets.UTF_8));//测试
}

/**
 * 测试编码转换 中文 => gbk 编码 - 解码
 */
@Test
public void test1() throws UnsupportedEncodingException {
    String test = "测试";
    System.out.println(Arrays.toString(test.getBytes("gbk")));//[-78, -30, -54, -44]
    System.out.println(new String(test.getBytes("gbk"), "GBK"));//测试
}

/**
 * 测试编码转换 中文 => utf-8 编码- gbk解码
 */
@Test
public void test2() throws UnsupportedEncodingException {
    String test = "测试";
    System.out.println(Arrays.toString(test.getBytes(StandardCharsets.UTF_8)));//[-26, -75, -117, -24, -81, -107]
    System.out.println(new String(test.getBytes(StandardCharsets.UTF_8), "gbk"));//娴嬭瘯
}

/**
 * 测试编码转换 中文 => utf-8 编码 - gbk 解码 ===> gbk 编码 - utf-8解码
 * "测试" => (utf8-encode)[-26, -75, -117, -24, -81, -107] => (gbk-decode)娴嬭瘯
 * "娴嬭瘯" => (utf8-encode)[-26, -75, -117, -24, -81, -107] => (utf8-decode)"测试"
 */
@Test
public void test3() throws UnsupportedEncodingException {
    String test = "测试";
    String test_gbk_utf8 = new String(test.getBytes(StandardCharsets.UTF_8), "gbk");
    System.out.println(test_gbk_utf8);//娴嬭瘯
    String test_utf8_gbk = new String(test_gbk_utf8.getBytes("gbk"), StandardCharsets.UTF_8);
    System.out.println(test_utf8_gbk);//测试

}

@Test
    public void test4() throws UnsupportedEncodingException {
        String test = "测试";
        System.out.println(Arrays.toString(test.getBytes(StandardCharsets.ISO_8859_1)));//[63, 63]
        System.out.println(new String(test.getBytes(StandardCharsets.ISO_8859_1), StandardCharsets.ISO_8859_1));//??
    }

new String(str.getBytes("gbk"),"utf8")

  String str="彩虹";
        String [] a=new String[] {"gbk","unicode","utf8","gb2312"};
        for (int i=0;i<a.length;i++){
            for (int j=0;j<a.length;j++){
                System.out.println("二进制格式:   "+a[i]+"编码格式:  "+a[j]);
                System.out.println("编码后的字符串:  "+new String(str.getBytes(a[i]),a[j]));
 
            }
        }

       String str="褰╄櫣";
        String [] charset=new String[] {"gbk","unicode","utf8","gb2312"};
        for (int i=0;i<charset.length;i++){
            for (int j=0;j<charset.length;j++){
                System.out.println("二进制格式:   "+charset[i]+"编码格式:  "+charset[j]);
                System.out.println("编码后的字符串:  "+new String(str.getBytes(charset[i]),charset[j]));
 
            }
        }