https://en.wikipedia.org/wiki/List_of_Unicode_characters
选取一个特殊字符
U+015E | Ş | 350 | Ş | Latin Capital Letter S with cedilla | 0286 |
然后尝试处理
[Test] public void Test20210521002() { var str = "Ş"; //PrintHexString(Encoding.ASCII, str); //ascii本身不支持中文的,所以打印出来的是错误的 PrintHexString(Encoding.UTF8, str); PrintHexString(Encoding.BigEndianUnicode, str); PrintHexString(Encoding.GetEncoding(936), str); PrintHexString(Encoding.GetEncoding(54936), str); } private void PrintHexString(Encoding encoding, string str) { int count = 0; foreach (var c in str) { var array = encoding.GetBytes(c.ToString()); var hexString = GetHexString(array); Console.WriteLine($"{c}, {encoding.WebName}, U+{hexString}, {string.Join(string.Empty,array.Select(GetBinaryString))}"); count += array.Length; } Console.WriteLine($"【{str}】 occupy {count} bytes when encoded by {encoding.WebName}"); Console.WriteLine(); } private string GetBinaryString(byte b) { return Convert.ToString(b, 2).PadLeft(8, '0'); } private string GetHexString(byte[] array) { var list = array.Select(x => x.ToString("X2")); var str = string.Join(string.Empty, list); return str; } [Test] public void Test20210521003() { var array = new byte[] {0xc5, 0x9e}; Encoding utf8 = Encoding.UTF8; var str1 = utf8.GetString(array); Console.WriteLine(str1); var array4 = new byte[] { 0x01, 0x5e }; Encoding utf16 = Encoding.BigEndianUnicode; var str4 = utf16.GetString(array4); Console.WriteLine(str4); var array2 = new byte[] {0x35}; Encoding gb2312 = Encoding.GetEncoding(936); var str2 = gb2312.GetString(array2); Console.WriteLine(str2); var array3 = new byte[] {0x81, 0x30, 0x94, 0x35}; Encoding gb18030 = Encoding.GetEncoding(54936); var str3 = gb18030.GetString(array3); Console.WriteLine(str3); }
Ş, utf-8, U+C59E, 1100010110011110
【Ş】 occupy 2 bytes when encoded by utf-8
Ş, utf-16BE, U+015E, 0000000101011110
【Ş】 occupy 2 bytes when encoded by utf-16BE
Ş, gb2312, U+3F, 00111111 这个是错误的
【Ş】 occupy 1 bytes when encoded by gb2312
Ş, GB18030, U+81309435, 10000001001100001001010000110101
【Ş】 occupy 4 bytes when encoded by GB18030
把上面的字节,反过来输出成字符的话
Ş utf8
Ş utf16
5 gb2312 因为上面的输出就是错误的,所以这里没法得到正确的。而且gb2312本身不支持Ş
Ş gb18030