C# unicode 编码 和 解码

首先转换方面：

 byte[] 
bytes = System.Text.Encoding.UTF8.GetBytes(msgStr);
 bytes = Encoding.Convert(Encoding.UTF8, Encoding.Unicode, bytes);
 bytes = System.Text.Encoding.Unicode.GetBytes(msgStr);
msgStr = System.Text.Encoding.GetEncoding("gb2312").GetString(Encoding.Convert(Encoding.Unicode, Encoding.GetEncoding("gb2312"), bytes));

编码："\\uxxxx" 转换为"\uxxxx"
解码："\uxxxx" 转换为"\\uxxxxx"

编码算法

//UNICODE字符转为中文 
对这个方法做一点改进 使他支持中英混排 
public static string ConvertUnicodeStringToChinese(string unicodeString) 
{ 
if (string.IsNullOrEmpty(unicodeString)) 
return string.Empty; 

string outStr = unicodeString; 

Regex re = new Regex("\\\\u[0123456789abcdef]{4}", RegexOptions.IgnoreCase); 
MatchCollection mc = re.Matches(unicodeString); 
foreach (Match ma in mc) 
{ 
outStr = outStr.Replace(ma.Value, ConverUnicodeStringToChar(ma.Value).ToString()); 
} 
return outStr; 
} 

private static char ConverUnicodeStringToChar(string str) 
{ 
  char outStr = Char.MinValue; 
  outStr = (char)int.Parse(str.Remove(0, 2),  System.Globalization.NumberStyles.HexNumber); 
   return outStr; 
}

解码：

static Regex reUnicode = new Regex(@"\\u([0-9a-fA-F]{4})", RegexOptions.Compiled);
public static string ConvertChineseToUnicodeString(string chinese)
{
   MatchCollection mc = re.Matches(chinese);
   string unicodeString="";
   foreach(Match ma in mc)
   {
      char c;
      if(Short.TryParse(ma.Remove(0,1), System.Globalization.NumberStyles.HexNumber, CultureInfo.InvariantCulture, out c))
      {
        unicodeString +=("\\u"+c);
      }
   }
return unicodeString;
} 

评论

1 楼 Foveni 2015-05-24  

Short.TryParse(ma.Remove   不包含定义