C#实现获取文本文件的编码的一个类(区分GB2312和UTF8)-来自转载收集

时间:2023-12-10 22:11:38
using System;
using System.IO;
using System.Text; /// <summary>
/// FileEncoding 的摘要说明
/// </summary>
namespace FileEncoding
{
/// <summary>
/// 获取文件的编码格式
/// </summary>
public class EncodingType
{
/// <summary>
/// 给定文件的路径,读取文件的二进制数据,判断文件的编码类型
/// </summary>
/// <param name="FILE_NAME">文件路径</param>
/// <returns>文件的编码类型</returns>
public static System.Text.Encoding GetType(string FILE_NAME)
{
FileStream fs = new FileStream(FILE_NAME, FileMode.Open, FileAccess.Read);
Encoding r = GetType(fs);
fs.Close();
return r;
} /// <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 GetType(FileStream 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);
int i;
int.TryParse(fs.Length.ToString(), out i);
byte[] ss = r.ReadBytes(i);
if (IsUTF8Bytes(ss) || (ss[] == 0xEF && ss[] == 0xBB && ss[] == 0xBF))
{
reVal = Encoding.UTF8;
}
else if (ss[] == 0xFE && ss[] == 0xFF && ss[] == 0x00)
{
reVal = Encoding.BigEndianUnicode;
}
else if (ss[] == 0xFF && ss[] == 0xFE && ss[] == 0x41)
{
reVal = Encoding.Unicode;
}
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;
} } }

来自转载