C#: Class for decoding Quoted-Printable encoding?

There is functionality in the framework libraries to do this, but it doesn't appear to be cleanly exposed. The implementation is in the internal class System.Net.Mime.QuotedPrintableStream. This class defines a method called DecodeBytes which does what you want. The method appears to be used by only one method which is used to decode MIME headers. This method is also internal, but is called fairly directly in a couple of places, e.g., the Attachment.Name setter. A demonstration:

using System;
using System.Net.Mail;

namespace ConsoleApplication1
{
    class Program
    {
        static void Main(string[] args)
        {
            Attachment attachment = Attachment.CreateAttachmentFromString("", "=?iso-8859-1?Q?=A1Hola,_se=F1or!?=");
            Console.WriteLine(attachment.Name);
        }
    }
}

Produces the output:

¡Hola,_señor!

You may have to do some testing to ensure carriage returns, etc are treated correctly although in a quick test I did they seem to be. However, it may not be wise to rely on this functionality unless your use-case is close enough to decoding of a MIME header string that you don't think it will be broken by any changes made to the library. You might be better off writing your own quoted-printable decoder.

I extended the solution of Martin Murphy and I hope it will work in every case.

private static string DecodeQuotedPrintables(string input, string charSet)
{           
    if (string.IsNullOrEmpty(charSet))
    {
        var charSetOccurences = new Regex(@"=\?.*\?Q\?", RegexOptions.IgnoreCase);
        var charSetMatches = charSetOccurences.Matches(input);
        foreach (Match match in charSetMatches)
        {
            charSet = match.Groups[0].Value.Replace("=?", "").Replace("?Q?", "");
            input = input.Replace(match.Groups[0].Value, "").Replace("?=", "");
        }
    }

    Encoding enc = new ASCIIEncoding();
    if (!string.IsNullOrEmpty(charSet))
    {
        try
        {
            enc = Encoding.GetEncoding(charSet);
        }
        catch
        {
            enc = new ASCIIEncoding();
        }
    }

    //decode iso-8859-[0-9]
    var occurences = new Regex(@"=[0-9A-Z]{2}", RegexOptions.Multiline);
    var matches = occurences.Matches(input);
    foreach (Match match in matches)
    {
        try
        {
            byte[] b = new byte[] { byte.Parse(match.Groups[0].Value.Substring(1), System.Globalization.NumberStyles.AllowHexSpecifier) };
            char[] hexChar = enc.GetChars(b);
            input = input.Replace(match.Groups[0].Value, hexChar[0].ToString());
        }
        catch { }
    }

    //decode base64String (utf-8?B?)
    occurences = new Regex(@"\?utf-8\?B\?.*\?", RegexOptions.IgnoreCase);
    matches = occurences.Matches(input);
    foreach (Match match in matches)
    {
        byte[] b = Convert.FromBase64String(match.Groups[0].Value.Replace("?utf-8?B?", "").Replace("?UTF-8?B?", "").Replace("?", ""));
        string temp = Encoding.UTF8.GetString(b);
        input = input.Replace(match.Groups[0].Value, temp);
    }

    input = input.Replace("=\r\n", "");
    return input;
}

I wrote this up real quick.

    public static string DecodeQuotedPrintables(string input)
    {
        var occurences = new Regex(@"=[0-9A-H]{2}", RegexOptions.Multiline);
        var matches = occurences.Matches(input);
        var uniqueMatches = new HashSet<string>(matches);
        foreach (string match in uniqueMatches)
        {
            char hexChar= (char) Convert.ToInt32(match.Substring(1), 16);
            input =input.Replace(match, hexChar.ToString());
        }
        return input.Replace("=\r\n", "");
    }       

If you are decoding quoted-printable with UTF-8 encoding you will need to be aware that you cannot decode each quoted-printable sequence one-at-a-time as the others have shown if there are runs of quoted printable characters together.

For example - if you have the following sequence =E2=80=99 and decode this using UTF8 one-at-a-time you get three "weird" characters - if you instead build an array of three bytes and convert the three bytes with the UTF8 encoding you get a single aphostrope.

Obviously if you are using ASCII encoding then one-at-a-time is no problem however decoding runs means your code will work regardless of the text encoder used.

Oh and don't forget =3D is a special case that means you need to decode whatever you have one more time... That is a crazy gotcha!

Hope that helps

I was looking for a dynamic solution and spent 2 days trying different solutions. This solution will support Japanese characters and other standard character sets

private static string Decode(string input, string bodycharset) {
        var i = 0;
        var output = new List<byte>();
        while (i < input.Length) {
            if (input[i] == '=' && input[i + 1] == '\r' && input[i + 2] == '\n') {
                //Skip
                i += 3;
            } else if (input[i] == '=') {
                string sHex = input;
                sHex = sHex.Substring(i + 1, 2);
                int hex = Convert.ToInt32(sHex, 16);
                byte b = Convert.ToByte(hex);
                output.Add(b);
                i += 3;
            } else {
                output.Add((byte)input[i]);
                i++;
            }
        }


        if (String.IsNullOrEmpty(bodycharset))
            return Encoding.UTF8.GetString(output.ToArray());
        else {
            if (String.Compare(bodycharset, "ISO-2022-JP", true) == 0)
                return Encoding.GetEncoding("Shift_JIS").GetString(output.ToArray());
            else
                return Encoding.GetEncoding(bodycharset).GetString(output.ToArray());
        }

    }

Then you can call the function with

Decode("=E3=82=AB=E3=82=B9=E3", "utf-8")

This was originally found here