【答客問】信件標題解碼範例

2013-04-11 09:23 PM

網友提問，希望了解中文編碼解析工具關於信件標題(如=?x-gbk?q?=B5=C4=B7=AD=D2=EB?=)的解碼邏輯，特整理為程式範例並加註說明如下:

using System;

using System.Text;

using System.Text.RegularExpressions;

using System.Web;

namespace ConsoleApplication1

    class Program

        static void Main(string[] args)

            string s = "=?big5?B?UmU6IKZVpuyl66bxLKdAt36o06RGLi4u?=";

            Console.WriteLine(decodeMailSubject(s));

            s = "=?big5?Q?=B6=C2=B7t=B0=F5=A6=E6=BA=FC?=";

            Console.WriteLine(decodeMailSubject(s));

            Console.Read();

        static string decodeMailSubject(string raw)

            //若字串結尾是?=會識別失敗，加上一個空白

              raw += " ";

            StringBuilder sb = new StringBuilder();

            //先解出一段一段的=?..... ?=

            foreach (Match m in Regex.Matches(raw,

                "=[?](?<enc>.+?)[?](?<type>.+?)[?](?<body>.+?)[?]=[^0-9A-Z]"))

                string enc = m.Groups["enc"].Value.ToLower();

                string type = m.Groups["type"].Value.ToLower();

                string body = m.Groups["body"].Value;

                Encoding encoder = null;

                //識別出Encoding

                if (enc == "gbk" || enc == "x-gbk")

                    encoder = Encoding.GetEncoding(936);

                else if (enc == "big5")

                    encoder = Encoding.GetEncoding(950);

                else if (enc == "utf-8")

                    encoder = Encoding.UTF8;

                else

                    return "不支援編碼格式[" + m.Groups["enc"].Value + "]!";

                if (type == "q")

                    body = body.Replace("=", "%");

                    body = HttpUtility.UrlDecode(body, encoder);

                    raw = raw.Replace(m.Value, body);

                else if (type == "b")

                    byte[] buff = Convert.FromBase64String(body);

                    raw = raw.Replace(m.Value, encoder.GetString(buff));

            return raw;

Comments