我正在 .NET 中处理法语字符串 解码邮件正文，我收到“Chasn=C3=A9 sur illet” 我想得到“Chasné sur illet” 而且我在 2 天的网络搜索中找不到任何解决方案。
C# 或 VB.NET 谁能帮帮我？
谢谢
【问题讨论】：
标签： c# vb.net mime quoted-printable
这是 UTF8 编码。
使用这篇文章：
http://www.dpit.co.uk/decoding-quoted-printable-email-in-c/
这是代码（如果有帮助别忘了接受答案）：
using System;
using System.Text;
using System.Text.RegularExpressions;
namespace ConsoleApplication1
{
class Program
{
static void Main(string[] args)
{
Console.WriteLine(DecodeQuotedPrintable("Chasn=C3=A9 sur illet"));
Console.ReadKey();
}
static string DecodeQuotedPrintable(string input)
{
var occurences = new Regex(@"(=[0-9A-Z][0-9A-Z])+", RegexOptions.Multiline);
var matches = occurences.Matches(input);
foreach (Match m in matches)
{
byte[] bytes = new byte[m.Value.Length / 3];
for (int i = 0; i < bytes.Length; i++)
{
string hex = m.Value.Substring(i * 3 + 1, 2);
int iHex = Convert.ToInt32(hex, 16);
bytes[i] = Convert.ToByte(iHex);
}
input = input.Replace(m.Value, Encoding.UTF8.GetString(bytes));
}
return input.Replace("=rn", "");
}
}
}
【讨论】：
static string ConverFromHex(string source)
{
string target = string.Empty;
int startPos = source.IndexOf('=', 0);
int prevStartPos = 0;
while (startPos >= 0)
{
// concat with substring from source
target += source.Substring(prevStartPos, startPos - prevStartPos);
// next offset
startPos++;
// update prev pos
prevStartPos = startPos;
// get substring
string hexString = source.Substring(startPos, 2);
// get int equiv
int hexNum = 0;
if (int.TryParse(hexString, System.Globalization.NumberStyles.AllowHexSpecifier, System.Globalization.CultureInfo.InvariantCulture, out hexNum))
{
// add to target string
target += (char)hexNum;
// add hex length
prevStartPos += 2;
}
// next occurence
startPos = source.IndexOf('=', startPos);
}
// add rest of source
target += source.Substring(prevStartPos);
return target;
}
【讨论】：
发件人：https://stackoverflow.com/a/36803911/6403521 我的解决方案：
[TestMethod]
public void TestMethod1()
{
Assert.AreEqual("La Bouichère", quotedprintable("La Bouich=C3=A8re", "utf-8"));
Assert.AreEqual("Chasné sur illet", quotedprintable("Chasn=C3=A9 sur illet", "utf-8"));
Assert.AreEqual("é è", quotedprintable("=C3=A9 =C3=A8", "utf-8"));
}
private string quotedprintable(string pStrIn, string encoding)
{
String strOut = pStrIn.Replace("=\r\n", "");
// Find the first =
int position = strOut.IndexOf("=");
while (position != -1)
{
// String before the =
string leftpart = strOut.Substring(0, position);
// get the QuotedPrintable String in a ArrayList
System.Collections.ArrayList hex = new System.Collections.ArrayList();
// The first Part
hex.Add(strOut.Substring(1 + position, 2));
// Look for the next parts
while (position + 3 < strOut.Length && strOut.Substring(position + 3, 1) == "=")
{
position = position + 3;
hex.Add(strOut.Substring(1 + position, 2));
}
// In the hex Array, we have two items
// Convert using the GetEncoding Function
byte[] bytes = new byte[hex.Count];
for (int i = 0; i < hex.Count; i++)
{
bytes[i] = System.Convert.ToByte(new string(((string)hex[i]).ToCharArray()), 16);
}
string equivalent = System.Text.Encoding.GetEncoding(encoding).GetString(bytes);
// Part of the orignal String after the last QP Symbol
string rightpart = strOut.Substring(position + 3);
// Re build the String
strOut = leftpart + equivalent + rightpart;
// find the new QP Position
position = leftpart.Length + equivalent.Length;
if (rightpart.Length == 0)
{
position = -1;
}
else
{
position = strOut.IndexOf("=", position + 1);
}
}
return strOut;
}
【讨论】：
或者最简单的，只需使用我的MimeKit 库中的QuotedPrintableDecoder：
static string DecodeQuotedPrintable (string input, string charset)
{
var decoder = new QuotedPrintableDecoder ();
var buffer = Encoding.ASCII.GetBytes (input);
var output = new byte[decoder.EstimateOutputLength (buffer.Length)];
int used = decoder.Decode (buffer, 0, buffer.Length, output);
var encoding = Encoding.GetEncoding (charset);
return encoding.GetString (output, 0, used);
}
请注意，上面的其他答案假设解码的内容是 ASCII 或 UTF-8，但不一定是这种情况。您需要从您正在解码的 MIME 部分的 Content-Type 标头中获取 charset 参数。
当然...如果您不知道如何获取该信息，您可以简单地使用我很棒的 MailKit 库从 IMAP 获取 MIME 部分并让它为您完成所有这些工作。
【讨论】：
我们在使用这种方法时遇到了问题 - 它非常慢。 以下增强性能A LOT
public static string FromMailTransferEncoding(this string messageText, Encoding enc, string transferEncoding)
{
if (string.IsNullOrEmpty(transferEncoding))
return messageText;
if ("quoted-printable".Equals(transferEncoding.ToLower()))
{
StringBuilder sb = new StringBuilder();
string delimitorRegEx = @"=[\r][\n]";
string[] parts = Regex.Split(messageText, delimitorRegEx);
foreach (string part in parts)
{
string subPart = part;
Regex occurences = new Regex(@"(=[0-9A-Z][0-9A-Z])+", RegexOptions.Multiline);
MatchCollection matches = occurences.Matches(subPart);
foreach (Match m in matches)
{
byte[] bytes = new byte[m.Value.Length / 3];
for (int i = 0; i < bytes.Length; i++)
{
string hex = m.Value.Substring(i * 3 + 1, 2);
int iHex = Convert.ToInt32(hex, 16);
bytes[i] = Convert.ToByte(iHex);
}
subPart = occurences.Replace(subPart, enc.GetString(bytes), 1);
}
sb.Append(subPart);
}
return sb.ToString();
}
return messageText;
}
【讨论】：