static System.Text.Encoding GetEncodingOfFile(string filename)
{
int count;
byte[] buf;
using (FileStream fs = new FileStream(filename, FileMode.Open, FileAccess.Read))
{
buf = new byte[fs.Length];
count = fs.Read(buf, 0, buf.Length);
}
if (buf.Length > 2 && buf[0] == 0xEF && buf[1] == 0xBB && buf[2] == 0xBF)
{
return(System.Text.Encoding.UTF8);
}
else if (buf.Length >= 2 && buf[0] == 0xFF && buf[1] == 0xFE)
{
if (buf.Length >= 4 && buf[2] == 0x00 && buf[3] == 0x00)
{
return(System.Text.Encoding.UTF32);
}
else
{
return(System.Text.Encoding.Unicode);
}
}
else if (buf.Length >= 2 && buf[0] == 0xFE && buf[1] == 0xFF)
{
return(System.Text.Encoding.BigEndianUnicode);
}
else if (buf.Length >= 4 && buf[0] == 0x00 && buf[1] == 0x00 && buf[2] == 0xFE && buf[3] == 0xFF)
{
return(System.Text.Encoding.GetEncoding("UTF-32BE"));
}
else
{
MyCharsetDetectionObserver cdo = new MyCharsetDetectionObserver();
NChardet.Detector detector = new NChardet.Detector();
detector.Init(cdo);
if (detector.isAscii(buf, count))
{
return(System.Text.Encoding.ASCII);
}
else
{
detector.DoIt(buf, count, false);
detector.Done();
if (string.IsNullOrEmpty(cdo.Charset))
{
return(System.Text.Encoding.Default);
}
else
{
return(System.Text.Encoding.GetEncoding(cdo.Charset));
}
}
}
}
public System.Text.Encoding GetEncodingOfFile(string filename)
{
int count = 0;
byte[] buf;
using (System.IO.FileStream fs = new System.IO.FileStream(filename, System.IO.FileMode.Open, System.IO.FileAccess.Read, System.IO.FileShare.Read))
{
buf = new byte[fs.Length];
count = fs.Read(buf, 0, buf.Length);
}
if (count < 1)
{
return(System.Text.Encoding.Default);
}
NChardet.Detector detect = new NChardet.Detector();
CharsetDetectionObserver cdo = new CharsetDetectionObserver();
detect.Init(cdo);
if (detect.isAscii(buf, count))
{
return(System.Text.Encoding.ASCII);
}
else
{
detect.DoIt(buf, count, true);
detect.DataEnd();
if (string.IsNullOrEmpty(cdo.Charset))
{
return(System.Text.Encoding.Default);
}
else
{
return(System.Text.Encoding.GetEncoding(cdo.Charset));
}
}
}
public static string DetectStream(Stream stream)
{
int lang = 2;
NChardet.Detector det = new NChardet.Detector(lang);
CharsetDetectionObserver cdo = new CharsetDetectionObserver();
det.Init(cdo);
byte[] buf = new byte[1024];
bool done = false;
bool isAscii = true;
int len;
using (stream)
{
while ((len = stream.Read(buf, 0, buf.Length)) != 0)
{
// 探测是否为Ascii编码
if (isAscii == true)
{
isAscii = det.isAscii(buf, len);
}
// 如果不是Ascii编码，并且编码未确定，则继续探测
if (isAscii == false && done == false)
{
done = det.DoIt(buf, len, false);
}
}
}
//调用DatEnd方法，
//如果引擎认为已经探测出了正确的编码，
//则会在此时调用ICharsetDetectionObserver的Notify方法
det.DataEnd();
string charset = Encoding.Default.BodyName;
if (isAscii == true)
{
charset = Encoding.ASCII.BodyName;
}
else if (!string.IsNullOrEmpty(cdo.Charset))
{
charset = cdo.Charset;
}
else
{
string[] probable = det.getProbableCharsets();
if (probable != null && probable.Length >= 1)
{
string probableCharset = probable[0].ToLower();
if (probableCharset == "gb2312" || probableCharset == "utf-8")
{
charset = probableCharset;
}
}
}
return(charset);
}
