文件字符流 編碼判斷

using System;
using System.Collections.Generic;
using System.IO;
using System.Linq;
using System.Text;
using System.Web;

namespace Wordsearch1
{
public class FileEncoding
{
public FileEncoding()
{
//
// TODO: 在此處添加構造函數邏輯
//
}

/// <summary>
/// 取得一個文本文件的編碼方式。若是沒法在文件頭部找到有效的前導符，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>
/// 取得一個文本文件的編碼方式。
/// </summary>
/// <param name="fileName">文件名。</param>
/// <param name="defaultEncoding">默認編碼方式。當該方法沒法從文件的頭部取得有效的前導符時，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">默認編碼方式。當該方法沒法從文件的頭部取得有效的前導符時，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個字節
byte byte1 = 0;
byte byte2 = 0;
byte byte3 = 0;
byte byte4 = 0;
//保存當前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());
}

//根據文件流的前4個字節判斷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Seek位置
stream.Seek(origPos, SeekOrigin.Begin);
}
return targetEncoding;
}
}
}