如何判断文件夹下的文件编码?
2018-05-11 本文已影响0人
程序员潜规则
/// <summary>
/// 验证文件里是否有不是utf8的文件
/// </summary>
/// <param name="sender"></param>
/// <param name="e"></param>
private void button2_Click(object sender, EventArgs e)
{
// 文件格式
string fileStyle = "*.*";
DirectoryInfo folder = new DirectoryInfo(@"C:\Users\sunjj\Desktop\textfile");
Encoding encodingUTF8 = Encoding.UTF8;
foreach (FileInfo file in folder.GetFiles(fileStyle))
{
if (!encodingUTF8.Equals(GetEncoding(file.FullName, Encoding.ASCII)))
{
MessageBox.Show(file.Name);
}
}
}
public static Encoding GetEncoding(string fileName, Encoding defaultEncoding)
{
FileStream fs = new FileStream(fileName, FileMode.Open);
Encoding targetEncoding = GetEncoding(fs, defaultEncoding);
fs.Close();
return targetEncoding;
}
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个字节
byte byte1 = 0;
byte byte2 = 0;
byte byte3 = 0;
byte byte4 = 0;
//保存当前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;
}