/// <summary>
/// Decodes "encoded-word"'s from the specified text. For more information see RFC 2047.
/// </summary>
/// <param name="text">Text to decode.</param>
/// <returns>Returns decoded text.</returns>
public static string DecodeWords(string text)
{
if(text == null){
return null;
}
/* RFC 2047 2. Syntax of encoded-words.
An 'encoded-word' is defined by the following ABNF grammar. The
notation of RFC 822 is used, with the exception that white space
characters MUST NOT appear between components of an 'encoded-word'.
encoded-word = "=?" charset "?" encoding "?" encoded-text "?="
charset = token ; see section 3
encoding = token ; see section 4
token = 1*<Any CHAR except SPACE, CTLs, and especials>
especials = "(" / ")" / "<" / ">" / "@" / "," / ";" / ":" / "
<"> / "/" / "[" / "]" / "?" / "." / "="
encoded-text = 1*<Any printable ASCII character other than "?" or SPACE>
; (but see "Use of encoded-words in message headers", section 5)
Both 'encoding' and 'charset' names are case-independent. Thus the
charset name "ISO-8859-1" is equivalent to "iso-8859-1", and the
encoding named "Q" may be spelled either "Q" or "q".
An 'encoded-word' may not be more than 75 characters long, including
'charset', 'encoding', 'encoded-text', and delimiters. If it is
desirable to encode more text than will fit in an 'encoded-word' of
75 characters, multiple 'encoded-word's (separated by CRLF SPACE) may
be used.
IMPORTANT: 'encoded-word's are designed to be recognized as 'atom's
by an RFC 822 parser. As a consequence, unencoded white space
characters (such as SPACE and HTAB) are FORBIDDEN within an
'encoded-word'. For example, the character sequence
=?iso-8859-1?q?this is some text?=
would be parsed as four 'atom's, rather than as a single 'atom' (by
an RFC 822 parser) or 'encoded-word' (by a parser which understands
'encoded-words'). The correct way to encode the string "this is some
text" is to encode the SPACE characters as well, e.g.
=?iso-8859-1?q?this=20is=20some=20text?=
*/
StringReader r = new StringReader(text);
StringBuilder retVal = new StringBuilder();
// We need to loop all words, if encoded word, decode it, othwerwise just append to return value.
bool lastIsEncodedWord = false;
while(r.Available > 0){
string whiteSpaces = r.ReadToFirstChar();
// Probably is encoded-word, we try to parse it.
if(r.StartsWith("=?") && r.SourceString.IndexOf("?=") > -1){
StringBuilder encodedWord = new StringBuilder();
string decodedWord = null;
try{
// NOTE: We can't read encoded word and then split !!!, we need to read each part.
// Remove =?
encodedWord.Append(r.ReadSpecifiedLength(2));
// Read charset
string charset = r.QuotedReadToDelimiter('?');
encodedWord.Append(charset + "?");
// Read encoding
string encoding = r.QuotedReadToDelimiter('?');
encodedWord.Append(encoding + "?");
// Read text
string encodedText = r.QuotedReadToDelimiter('?');
encodedWord.Append(encodedText + "?");
// We must have remaining '=' here
if(r.StartsWith("=")){
encodedWord.Append(r.ReadSpecifiedLength(1));
Encoding c = Encoding.GetEncoding(charset);
if(encoding.ToLower() == "q"){
decodedWord = Core.QDecode(c,encodedText);
}
else if(encoding.ToLower() == "b"){
decodedWord = c.GetString(Core.Base64Decode(Encoding.Default.GetBytes(encodedText)));
}
}
}
catch{
// Not encoded-word or contains unknwon charset/encoding, so leave
// encoded-word as is.
}
/* RFC 2047 6.2.
When displaying a particular header field that contains multiple
'encoded-word's, any 'linear-white-space' that separates a pair of
adjacent 'encoded-word's is ignored. (This is to allow the use of
multiple 'encoded-word's to represent long strings of unencoded text,
without having to separate 'encoded-word's where spaces occur in the
unencoded text.)
*/
if(!lastIsEncodedWord){
retVal.Append(whiteSpaces);
}
// Decoding failed for that encoded-word, leave encoded-word as is.
if(decodedWord == null){
retVal.Append(encodedWord.ToString());
}
// We deocded encoded-word successfully.
else{
retVal.Append(decodedWord);
}
lastIsEncodedWord = true;
}
// Normal word.
else if(r.StartsWithWord()){
retVal.Append(whiteSpaces + r.ReadWord(false));
lastIsEncodedWord = false;
}
// We have some separator or parenthesize.
else{
retVal.Append(whiteSpaces + r.ReadSpecifiedLength(1));
}
}
return retVal.ToString();
}
