C#获取文件的编码格式（UTF-8/UNICODE/ASCII）
C#获取文件的编码格式（UTF-8/UNICODE/ASCII）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, 返回文件的编码类型如：
Encoding.ASCII
Encoding.UTF8
Encoding.Unicode
Encoding.Defaut默认为ASCII编码。
C# Code:
/// <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)
{
using (FileStream fs = new FileStream(FILE_NAME, FileMode.Open, FileAccess.Read))
{
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;
using (BinaryReader reader = new BinaryReader(fs, System.Text.Encoding.Default))
{
int i;
int.TryParse(fs.Length.ToString(), out i);
byte[] ss = reader.ReadBytes(i);
if (IsUTF8Bytes(ss) || (ss[0] == 0xEF && ss[1] == 0xBB && ss[2] == 0xBF))
{
reVal = Encoding.UTF8;
}
else 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;
}
return reVal;
}
}
}
//来源:C/S框架网 | www.csframework.com | QQ:23404761
/// 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)
{
using (FileStream fs = new FileStream(FILE_NAME, FileMode.Open, FileAccess.Read))
{
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;
using (BinaryReader reader = new BinaryReader(fs, System.Text.Encoding.Default))
{
int i;
int.TryParse(fs.Length.ToString(), out i);
byte[] ss = reader.ReadBytes(i);
if (IsUTF8Bytes(ss) || (ss[0] == 0xEF && ss[1] == 0xBB && ss[2] == 0xBF))
{
reVal = Encoding.UTF8;
}
else 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;
}
return reVal;
}
}
}
//来源:C/S框架网 | www.csframework.com | QQ:23404761
C# Code:
/// <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 = 1; //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 = 0; i < data.Length; i++)
{
curByte = data[i];
if (charByteCounter == 1)
{
if (curByte >= 0x80)
{
//判断当前
while (((curByte <<= 1) & 0x80) != 0)
{
charByteCounter++;
}
//标记位首位若为非0 则至少以2个1开始 如:110XXXXX...........1111110X
if (charByteCounter == 1 || charByteCounter > 6)
{
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 > 1)
{
throw new Exception("非预期的byte格式");
}
return true;
}
//来源:C/S框架网 | www.csframework.com | QQ:23404761
/// <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 = 1; //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 = 0; i < data.Length; i++)
{
curByte = data[i];
if (charByteCounter == 1)
{
if (curByte >= 0x80)
{
//判断当前
while (((curByte <<= 1) & 0x80) != 0)
{
charByteCounter++;
}
//标记位首位若为非0 则至少以2个1开始 如:110XXXXX...........1111110X
if (charByteCounter == 1 || charByteCounter > 6)
{
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 > 1)
{
throw new Exception("非预期的byte格式");
}
return true;
}
//来源:C/S框架网 | www.csframework.com | QQ:23404761
扫一扫加微信
版权声明：本文为开发框架文库发布内容,转载请附上原文出处连接
NewDoc C/S框架网
