Decoding Quoted printable message
-
15-04-2021 - |
문제
Iam having trouble decoding Japanese message, the final output seems to be a garbage value.
Encoded ISO-2022-JP Quoted Printable Message:
"=82=B1=82=EA=82=CD=92P=82=C8=82=E9=83e=83X=83g=82=C5=82=B7=82=DD=82=C8=82=B3=\r\n=82=F1=81A=82=B1 =82=F1=82=C9=82=BF=82=CD"
Code for decoding Quoted Printable:
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
return Encoding.GetEncoding(bodycharset).GetString(output.ToArray());
}
Final Output:
・ア・・・ヘ・P・ネ・・・e・X・g・ナ・キ・ン・ネ・ウ・・・A・ア・・・ノ・ソ・ヘ
Any ideas to resolve it?.
해결책
try this
var str = Decode(inp, "Shift_JIS");
or
var str = Decode(inp, "sjis");
다른 팁
You can use a trick demonstrated in following article:
So you could be something like:
private static string Decode(string input, string bodycharset)
{
Attachment attachment = Attachment.CreateAttachmentFromString("", "=?"+bodycharset+"?"+input+"?=");
return (attachment.Name);
}
Also you need to add:
using System.Net.Mail;
I hope this helps :-)
Will something similar to this work..? just Sudu coded this kind of quickly
Encoding encoding = Encoding.GetEncoding("iso-2022-jp");
byte[] bytes = encoding.GetBytes(output);
string uuEncoded = Convert.ToBase64String(bytes);
This Quoted Printable saved my life. It work like a charm!
public static byte[] FromHex(byte[] hexData)
{
if (hexData == null)
{
throw new ArgumentNullException("hexData");
}
if (hexData.Length < 2 || (hexData.Length / (double)2 != Math.Floor(hexData.Length / (double)2)))
{
throw new Exception("Illegal hex data, hex data must be in two bytes pairs, for example: 0F,FF,A3,... .");
}
MemoryStream retVal = new MemoryStream(hexData.Length / 2);
// Loop hex value pairs
for (int i = 0; i < hexData.Length; i += 2)
{
byte[] hexPairInDecimal = new byte[2];
// We need to convert hex char to decimal number, for example F = 15
for (int h = 0; h < 2; h++)
{
if (((char)hexData[i + h]) == '0')
{
hexPairInDecimal[h] = 0;
}
else if (((char)hexData[i + h]) == '1')
{
hexPairInDecimal[h] = 1;
}
else if (((char)hexData[i + h]) == '2')
{
hexPairInDecimal[h] = 2;
}
else if (((char)hexData[i + h]) == '3')
{
hexPairInDecimal[h] = 3;
}
else if (((char)hexData[i + h]) == '4')
{
hexPairInDecimal[h] = 4;
}
else if (((char)hexData[i + h]) == '5')
{
hexPairInDecimal[h] = 5;
}
else if (((char)hexData[i + h]) == '6')
{
hexPairInDecimal[h] = 6;
}
else if (((char)hexData[i + h]) == '7')
{
hexPairInDecimal[h] = 7;
}
else if (((char)hexData[i + h]) == '8')
{
hexPairInDecimal[h] = 8;
}
else if (((char)hexData[i + h]) == '9')
{
hexPairInDecimal[h] = 9;
}
else if (((char)hexData[i + h]) == 'A' || ((char)hexData[i + h]) == 'a')
{
hexPairInDecimal[h] = 10;
}
else if (((char)hexData[i + h]) == 'B' || ((char)hexData[i + h]) == 'b')
{
hexPairInDecimal[h] = 11;
}
else if (((char)hexData[i + h]) == 'C' || ((char)hexData[i + h]) == 'c')
{
hexPairInDecimal[h] = 12;
}
else if (((char)hexData[i + h]) == 'D' || ((char)hexData[i + h]) == 'd')
{
hexPairInDecimal[h] = 13;
}
else if (((char)hexData[i + h]) == 'E' || ((char)hexData[i + h]) == 'e')
{
hexPairInDecimal[h] = 14;
}
else if (((char)hexData[i + h]) == 'F' || ((char)hexData[i + h]) == 'f')
{
hexPairInDecimal[h] = 15;
}
}
// Join hex 4 bit(left hex cahr) + 4bit(right hex char) in bytes 8 it
retVal.WriteByte((byte)((hexPairInDecimal[0] << 4) | hexPairInDecimal[1]));
}
return retVal.ToArray();
}
public static byte[] QuotedPrintableDecode(byte[] data)
{
if (data == null)
{
throw new ArgumentNullException("data");
}
MemoryStream msRetVal = new MemoryStream();
MemoryStream msSourceStream = new MemoryStream(data);
int b = msSourceStream.ReadByte();
while (b > -1)
{
// Encoded 8-bit byte(=XX) or soft line break(=CRLF)
if (b == '=')
{
byte[] buffer = new byte[2];
int nCount = msSourceStream.Read(buffer, 0, 2);
if (nCount == 2)
{
// Soft line break, line splitted, just skip CRLF
if (buffer[0] == '\r' && buffer[1] == '\n')
{
}
// This must be encoded 8-bit byte
else
{
try
{
msRetVal.Write(FromHex(buffer), 0, 1);
}
catch
{
// Illegal value after =, just leave it as is
msRetVal.WriteByte((byte)'=');
msRetVal.Write(buffer, 0, 2);
}
}
}
// Illegal =, just leave as it is
else
{
msRetVal.Write(buffer, 0, nCount);
}
}
// Just write back all other bytes
else
{
msRetVal.WriteByte((byte)b);
}
// Read next byte
b = msSourceStream.ReadByte();
}
return msRetVal.ToArray();
}
Late for the party, but as i've got a solution for this annoying task.
I've found the solution in the following link: http://sourceforge.net/apps/trac/syncmldotnet/wiki/Quoted%20Printable
If you just need to decode the QPs, pull inside of your code those three functions from the link above:
HexDecoderEvaluator(Match m)
HexDecoder(string line)
Decode(string encodedText)
And then just:
var humanReadable = Decode(myQPString);
Anyway the link provide functions for encoding aswell.
Enjoy