/// <summary> 
 /// 用于取得一個(gè)文本文件的編碼方式(Encoding)。 
 /// </summary> 
 public class TxtFileEncoder
 {
  public TxtFileEncoder()
  {
   // 
   // TODO: 在此處添加構(gòu)造函數(shù)邏輯 
   // 
  }
  /// <summary> 
  /// 取得一個(gè)文本文件的編碼方式。如果無法在文件頭部找到有效的前導(dǎo)符，Encoding.Default將被返回。 
  /// </summary> 
  /// <param name="fileName">文件名。</param> 
  /// <returns></returns> 
  public static Encoding GetEncoding(string fileName)
  {
   return GetEncoding(fileName, Encoding.Default);
  }
  /// <summary> 
  /// 取得一個(gè)文本文件流的編碼方式。 
  /// </summary> 
  /// <param name="stream">文本文件流。</param> 
  /// <returns></returns> 
  public static Encoding GetEncoding(FileStream stream)
  {
   return GetEncoding(stream, Encoding.Default);
  }
  /// <summary> 
  /// 取得一個(gè)文本文件的編碼方式。 
  /// </summary> 
  /// <param name="fileName">文件名。</param> 
  /// <param name="defaultEncoding">默認(rèn)編碼方式。當(dāng)該方法無法從文件的頭部取得有效的前導(dǎo)符時(shí)，將返回該編碼方式。</param> 
  /// <returns></returns> 
  public static Encoding GetEncoding(string fileName, Encoding defaultEncoding)
  {
   FileStream fs = new FileStream(fileName, FileMode.Open);
   Encoding targetEncoding = GetEncoding(fs, defaultEncoding);
   fs.Close();
   return targetEncoding;
  }
  /// <summary> 
  /// 取得一個(gè)文本文件流的編碼方式。 
  /// </summary> 
  /// <param name="stream">文本文件流。</param> 
  /// <param name="defaultEncoding">默認(rèn)編碼方式。當(dāng)該方法無法從文件的頭部取得有效的前導(dǎo)符時(shí)，將返回該編碼方式。</param> 
  /// <returns></returns> 
  public static Encoding GetEncoding(FileStream stream, Encoding defaultEncoding)
  {
   Encoding targetEncoding = defaultEncoding;
   if (stream != null && stream.Length >= 2)
   {
    //保存文件流的前4個(gè)字節(jié) 
    byte byte1 = 0;
    byte byte2 = 0;
    byte byte3 = 0;
    byte byte4 = 0;
    //保存當(dāng)前Seek位置 
    long origPos = stream.Seek(0, SeekOrigin.Begin);
    stream.Seek(0, SeekOrigin.Begin);

    int nByte = stream.ReadByte();
    byte1 = Convert.ToByte(nByte);
    byte2 = Convert.ToByte(stream.ReadByte());
    if (stream.Length >= 3)
    {
     byte3 = Convert.ToByte(stream.ReadByte());
    }
    if (stream.Length >= 4)
    {
     byte4 = Convert.ToByte(stream.ReadByte());
    }
    //根據(jù)文件流的前4個(gè)字節(jié)判斷Encoding 
    //Unicode {0xFF, 0xFE}; 
    //BE-Unicode {0xFE, 0xFF}; 
    //UTF8 = {0xEF, 0xBB, 0xBF}; 
    if (byte1 == 0xFE && byte2 == 0xFF)//UnicodeBe 
    {
     targetEncoding = Encoding.BigEndianUnicode;
    }
    if (byte1 == 0xFF && byte2 == 0xFE && byte3 != 0xFF)//Unicode 
    {
     targetEncoding = Encoding.Unicode;
    }
    if (byte1 == 0xEF && byte2 == 0xBB && byte3 == 0xBF)//UTF8 
    {
     targetEncoding = Encoding.UTF8;
    }
    //恢復(fù)Seek位置   
    stream.Seek(origPos, SeekOrigin.Begin);
   }
   return targetEncoding;
  }



  // 新增加一個(gè)方法，解決了不帶BOM的 UTF8 編碼問題 

  /// <summary> 
  /// 通過給定的文件流，判斷文件的編碼類型 
  /// </summary> 
  /// <param name="fs">文件流</param> 
  /// <returns>文件的編碼類型</returns> 
  public static System.Text.Encoding GetEncoding(Stream fs)
  {
   byte[] Unicode = new byte[] { 0xFF, 0xFE, 0x41 };
   byte[] UnicodeBIG = new byte[] { 0xFE, 0xFF, 0x00 };
   byte[] UTF8 = new byte[] { 0xEF, 0xBB, 0xBF }; //帶BOM 
   Encoding reVal = Encoding.Default;

   BinaryReader r = new BinaryReader(fs, System.Text.Encoding.Default);
   byte[] ss = r.ReadBytes(4);
   if (ss[0] == 0xFE && ss[1] == 0xFF && ss[2] == 0x00)
   {
    reVal = Encoding.BigEndianUnicode;
   }
   else if (ss[0] == 0xFF && ss[1] == 0xFE && ss[2] == 0x41)
   {
    reVal = Encoding.Unicode;
   }
   else
   {
    if (ss[0] == 0xEF && ss[1] == 0xBB && ss[2] == 0xBF)
    {
     reVal = Encoding.UTF8;
    }
    else
    {
     int i;
     int.TryParse(fs.Length.ToString(), out i);
     ss = r.ReadBytes(i);

     if (IsUTF8Bytes(ss))
      reVal = Encoding.UTF8;
    }
   }
   r.Close();
   return reVal;

  }

  /// <summary> 
  /// 判斷是否是不帶 BOM 的 UTF8 格式 
  /// </summary> 
  /// <param name="data"></param> 
  /// <returns></returns> 
  private static bool IsUTF8Bytes(byte[] data)
  {
   int charByteCounter = 1;　 //計(jì)算當(dāng)前正分析的字符應(yīng)還有的字節(jié)數(shù) 
   byte curByte; //當(dāng)前分析的字節(jié). 
   for (int i = 0; i < data.Length; i++)
   {
    curByte = data[i];
    if (charByteCounter == 1)
    {
     if (curByte >= 0x80)
     {
      //判斷當(dāng)前 
      while (((curByte <<= 1) & 0x80) != 0)
      {
       charByteCounter++;
      }
      //標(biāo)記位首位若為非0 則至少以2個(gè)1開始 如:110XXXXX...........1111110X　 
      if (charByteCounter == 1 || charByteCounter > 6)
      {
       return false;
      }
     }
    }
    else
    {
     //若是UTF-8 此時(shí)第一位必須為1 
     if ((curByte & 0xC0) != 0x80)
     {
      return false;
     }
     charByteCounter--;
    }
   }
   if (charByteCounter > 1)
   {
    throw new Exception("非預(yù)期的byte格式!");
   }
   return true;
  }
 }