Guess Text File Encoding
//----------------------------------------------------------------------------------------
// Copyright (C) 2008 ???? ?????
//
// ?????
// ? ? ?? TxtFileEncoding.cs
// ??????? ???????????????(Encoding)
//
// ????? ??? 2008-3-22 13:01:03
//
// ?????
// ?????
//
// ?????
// ?????
//----------------------------------------------------------------------------------------
using System;
using System.Text;
using System.IO;
namespace MaoCaiJun.DataBase.Sys.Common
{
/// <summary>
/// ???????????????(Encoding)?
/// </summary>
class TxtFileEncoding
{
//public TxtFileEncoding()
//{
// //
// // TODO: ???????????
// //
//}
/// <summary>
/// ????????????????????????????????Encoding.Default?????
/// </summary>
/// <param name="fileName">????</param>
/// <returns></returns>
public static Encoding GetEncoding(string fileName)
{
return GetEncoding(fileName, Encoding.Default);
}
/// <summary>
/// ???????????????
/// </summary>
/// <param name="stream">??????</param>
/// <returns></returns>
public static Encoding GetEncoding(FileStream stream)
{
return GetEncoding(stream, Encoding.Default);
}
/// <summary>
/// ??????????????
/// </summary>
/// <param name="fileName">????</param>
/// <param name="defaultEncoding">??????????????????????????????????????</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>
/// ???????????????
/// </summary>
/// <param name="stream">??????</param>
/// <param name="defaultEncoding">??????????????????????????????????????</param>
/// <returns></returns>
public static Encoding GetEncoding(FileStream stream, Encoding defaultEncoding)
{
Encoding targetEncoding = defaultEncoding;
if (stream != null && stream.Length >= 2)
{
//???????4???
byte byte1 = 0;
byte byte2 = 0;
byte byte3 = 0;
byte byte4 = 0;
//????Seek??
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());
}
//???????4?????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;
}
//??Seek??
stream.Seek(origPos, SeekOrigin.Begin);
}
return targetEncoding;
}
}
}
Related examples in the same category
