using System;
using System.IO;
using System.Text; /// <summary>
/// 用于取得一个文本文件的编码方式(Encoding)。
/// </summary>
public class TxtFileEncoder
{
public TxtFileEncoder()
{
//
// TODO: 在此处添加构造函数逻辑
//
}
/// <summary>
/// 取得一个文本文件的编码方式。如果无法在文件头部找到有效的前导符，Encoding.Default将被返回。
/// </summary>
/// <param name="fileName">文件名。</param>
/// <returns></returns>
public static Encoding GetEncoding(string fileName)
{
return GetEncoding(fileName, Encoding.Default);
}
/// <summary>
/// 取得一个文本文件流的编码方式。
/// </summary>
/// <param name="stream">文本文件流。</param>
/// <returns></returns>
public static Encoding GetEncoding(FileStream stream)
{
return GetEncoding(stream, Encoding.Default);
}
/// <summary>
/// 取得一个文本文件的编码方式。
/// </summary>
/// <param name="fileName">文件名。</param>
/// <param name="defaultEncoding">默认编码方式。当该方法无法从文件的头部取得有效的前导符时，将返回该编码方式。</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>
/// 取得一个文本文件流的编码方式。
/// </summary>
/// <param name="stream">文本文件流。</param>
/// <param name="defaultEncoding">默认编码方式。当该方法无法从文件的头部取得有效的前导符时，将返回该编码方式。</param>
/// <returns></returns>
public static Encoding GetEncoding(FileStream stream, Encoding defaultEncoding)
{
Encoding targetEncoding = defaultEncoding;
if (stream != null && stream.Length >= )
{
//保存文件流的前4个字节
byte byte1 = ;
byte byte2 = ;
byte byte3 = ;
byte byte4 = ;
//保存当前Seek位置
long origPos = stream.Seek(, SeekOrigin.Begin);
stream.Seek(, SeekOrigin.Begin); int nByte = stream.ReadByte();
byte1 = Convert.ToByte(nByte);
byte2 = Convert.ToByte(stream.ReadByte());
if (stream.Length >= )
{
byte3 = Convert.ToByte(stream.ReadByte());
}
if (stream.Length >= )
{
byte4 = Convert.ToByte(stream.ReadByte());
}
//根据文件流的前4个字节判断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;
}
//恢复Seek位置
stream.Seek(origPos, SeekOrigin.Begin);
}
return targetEncoding;
} // 新增加一个方法，解决了不带BOM的 UTF8 编码问题
/// <summary>
/// 通过给定的文件流，判断文件的编码类型
/// </summary>
/// <param name="fs">文件流</param>
/// <returns>文件的编码类型</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 }; //带BOM
Encoding reVal = Encoding.Default; BinaryReader r = new BinaryReader(fs, System.Text.Encoding.Default);
byte[] ss = r.ReadBytes();
if (ss[] == 0xFE && ss[] == 0xFF && ss[] == 0x00)
{
reVal = Encoding.BigEndianUnicode;
}
else if (ss[] == 0xFF && ss[] == 0xFE && ss[] == 0x41)
{
reVal = Encoding.Unicode;
}
else
{
if (ss[] == 0xEF && ss[] == 0xBB && ss[] == 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>
/// 判断是否是不带 BOM 的 UTF8 格式
/// </summary>
/// <param name="data"></param>
/// <returns></returns>
private static bool IsUTF8Bytes(byte[] data)
{
int charByteCounter = ; //计算当前正分析的字符应还有的字节数
byte curByte; //当前分析的字节.
for (int i = ; i < data.Length; i++)
{
curByte = data[i];
if (charByteCounter == )
{
if (curByte >= 0x80)
{
//判断当前
while (((curByte <<= ) & 0x80) != )
{
charByteCounter++;
}
//标记位首位若为非0 则至少以2个1开始 如:110XXXXX...........1111110X
if (charByteCounter == || charByteCounter > )
{
return false;
}
}
}
else
{
//若是UTF-8 此时第一位必须为1
if ((curByte & 0xC0) != 0x80)
{
return false;
}
charByteCounter--;
}
}
if (charByteCounter > )
{
throw new Exception("非预期的byte格式!");
}
return true;
}
}