UTF-8 與 GBK互轉亂碼的原因

public class CodecTest {
    public static void main(String[] args) throws UnsupportedEncodingException {

        String s = "我是中國人";
        //GBK編碼后的字節
        //gbkEncode[-50, -46, -54, -57, -42, -48, -71, -6, -56, -53]
        byte[] gbkEncode = s.getBytes("GBK");
        System.out.println("gbkEncode" + Arrays.toString(gbkEncode));

        //utf-8編碼后的字節
        //utfEncode[-26, -120, -111, -26, -104, -81, -28, -72, -83, -27, -101, -67, -28, -70, -70]
        byte[] utfEncode = s.getBytes("utf-8");
        System.out.println("utfEncode" + Arrays.toString(utfEncode));

        //用utf-8解碼gbk編碼后的字節，形成的字符串：�����й���
        String gbkDecodedByUTF = new String(gbkEncode,"utf-8");
        System.out.println(gbkDecodedByUTF);

        // 對上一步的字符串 �����й��� 用utf-8編碼后的字節
        //[-17, -65, -67, -17, -65, -67, -17, -65, -67, -17, -65, -67, -17, -65, -67, -48, -71, -17, -65, -67, -17, -65, -67, -17, -65, -67]
        byte[] gbkDecodedByUTF_EncodeByUTF = gbkDecodedByUTF.getBytes("utf-8");
        System.out.println(Arrays.toString(gbkDecodedByUTF_EncodeByUTF));

        //不出意外，這里解碼應該是 �����й���
        //所以，問題的源頭出在 我們用 utf-8 gbk編碼的字節上，形成了錯誤的字符。
　　　　　// 用utf-8 對錯誤的字符串編碼和解碼 都是錯誤的字符串，是一致的（字符串沒變），形成錯誤的字符串的原因是 utf-8 和GBK解碼的不兼容
        String gbkDecodedByUTF_EncodeByUTF_DecodeByUTF = new String(gbkEncode,"utf-8");
        System.out.println(gbkDecodedByUTF_EncodeByUTF_DecodeByUTF);
    }
}

 

Print：

gbkEncode[-50, -46, -54, -57, -42, -48, -71, -6, -56, -53]
utfEncode[-26, -120, -111, -26, -104, -81, -28, -72, -83, -27, -101, -67, -28, -70, -70]
�������
[-17, -65, -67, -17, -65, -67, -17, -65, -67, -17, -65, -67, -17, -65, -67, -48, -71, -17, -65, -67, -17, -65, -67, -17, -65, -67]
�������

 

 

 

utf-8編碼格式：

ref：

字符編碼筆記：ASCII，Unicode 和 UTF-8