/// <summary>
/// Changes fully translated Unicode data, e.g. with Japanaese Kanji characters, into
/// a string of characters that represents the raw, ISO character repertoire representation, i.e.
/// with escape sequences, but encoded as a Unicode string
/// </summary>
/// <param name="unicodeData">Fully translated Unicode data</param>
/// <param name="repertoire">Target repertoire to be transformed into</param>
/// <returns></returns>
private static string Encode(string unicodeData, CharacterSetInfo repertoire)
{
byte[] rawBytes;
Encode(unicodeData, repertoire, out rawBytes);
char[] rawCharacters = IsomorphicEncoding.GetChars(rawBytes);
return(new string(rawCharacters));
}
/// <summary>
/// Takes a string that is a representation of the raw sequence of bytes
/// encoded using an ISO repertoire, but current encoded as a Unicode string
/// and gives back a true Unicode string, e.g. containing the Japanese Kanji
/// characters
/// </summary>
/// <param name="rawData">Sequence of bytes formatted in Unicode</param>
/// <param name="repertoire">Original ISO repertoire used in the encoding</param>
/// <returns>True Unicode string</returns>
private static string Decode(string rawData, CharacterSetInfo repertoire)
{
// get it back to byte array form using a character set that includes
// both GR and GL areas (characters up to \xff in binary value)
// and it seems Windows-1252 works better than ISO-8859-1
byte[] rawBytes = IsomorphicEncoding.GetBytes(rawData);
return(Decode(rawBytes, repertoire));
}
public static byte[] GetIsomorphicBytes(string rawBytesEncodedAsString)
{
// add a null terminator, otherwise we're going to have problems in the unamanged world
if (rawBytesEncodedAsString == null)
{
return(null);
}
return(IsomorphicEncoding.GetBytes(rawBytesEncodedAsString));
}
public static string GetIsomorphicString(byte[] rawBytes)
{
return(IsomorphicEncoding.GetString(rawBytes));
}
