/// <summary>
/// Parses a character set into an encoding
/// </summary>
/// <param name="characterSet">The character set that needs to be parsed. <see langword="null"/> is allowed.</param>
/// <returns>The encoding specified by the <paramref name="characterSet"/> parameter, or ASCII if the character set was <see langword="null"/> or empty</returns>
private static Encoding ParseBodyEncoding(string characterSet)
{
// Default encoding in Mime messages is US-ASCII
Encoding encoding = Encoding.ASCII;
// If the character set was specified, find the encoding that the character
// set describes, and use that one instead
if (!string.IsNullOrEmpty(characterSet))
{
encoding = HeaderFieldParser.ParseCharsetToEncoding(characterSet);
}
return(encoding);
}
/// <summary>
/// 标题转码类 <see cref="EncodedWord"/> encoding.<br/>
///<br/>
/// This method will decode any encoded-word found in the string.<br/>
/// All parts which is not encoded will not be touched.<br/>
/// <br/>
/// From <a href="http://tools.ietf.org/html/rfc2047">RFC 2047</a>:<br/>
/// <code>
/// Generally, an "encoded-word" is a sequence of printable ASCII
/// characters that begins with "=?", ends with "?=", and has two "?"s in
/// between. It specifies a character set and an encoding method, and
/// also includes the original text encoded as graphic ASCII characters,
/// according to the rules for that encoding method.
/// </code>
/// Example:<br/>
/// <c>=?ISO-8859-1?q?this=20is=20some=20text?= other text here</c>
/// </summary>
/// <remarks>See <a href="http://tools.ietf.org/html/rfc2047#section-2">RFC 2047 section 2</a> "Syntax of encoded-words" for more details</remarks>
/// <param name="encodedWords">Source text. May be content which is not encoded.</param>
/// <returns>Decoded text</returns>
/// <exception cref="ArgumentNullException">If <paramref name="encodedWords"/> is <see langword="null"/></exception>
public static string Decode(string encodedWords)
{
if (encodedWords == null)
{
throw new ArgumentNullException("encodedWords");
}
string decodedWords = encodedWords;
const string strRegEx = @"\=\?(?<Charset>\S+?)\?(?<Encoding>\w)\?(?<Content>.+?)\?\=";
// \w Matches any word character including underscore. Equivalent to "[A-Za-z0-9_]".
// \S Matches any nonwhite space character. Equivalent to "[^ \f\n\r\t\v]".
// +? non-gready equivalent to +
// (?<NAME>REGEX) is a named group with name NAME and regular expression REGEX
MatchCollection matches = Regex.Matches(encodedWords, strRegEx);
foreach (Match match in matches)
{
// If this match was not a success, we should not use it
if (!match.Success)
{
continue;
}
string fullMatchValue = match.Value;
string encodedText = match.Groups["Content"].Value;
string encoding = match.Groups["Encoding"].Value;
string charset = match.Groups["Charset"].Value;
// Get the encoding which corrosponds to the character set
Encoding charsetEncoding = HeaderFieldParser.ParseCharsetToEncoding(charset);
// Store decoded text here when done
string decodedText;
// Encoding may also be written in lowercase
switch (encoding.ToUpperInvariant())
{
// RFC:
// The "B" encoding is identical to the "BASE64"
// encoding defined by RFC 2045.
// http://tools.ietf.org/html/rfc2045#section-6.8
case "B":
decodedText = Base64.Decode(encodedText, charsetEncoding);
break;
// RFC:
// The "Q" encoding is similar to the "Quoted-Printable" content-
// transfer-encoding defined in RFC 2045.
// There are more details to this. Please check
// http://tools.ietf.org/html/rfc2047#section-4.2
//
case "Q":
decodedText = QuotedPrintable.DecodeEncodedWord(encodedText, charsetEncoding);
break;
default:
throw new ArgumentException("The encoding " + encoding + " was not recognized");
}
// Repalce our encoded value with our decoded value
decodedWords = decodedWords.Replace(fullMatchValue, decodedText);
}
return(decodedWords);
}