c# 判斷Txt檔案的編碼格式
阿新 • • 發佈：2021-06-29
/// <summary>
/// 獲取檔案的編碼格式
/// </summary>
publicclassEncodingType
{
/// <summary>
/// 給定檔案的路徑，讀取檔案的二進位制資料，判斷檔案的編碼型別
/// </summary>
/// <param name=“FILE_NAME“>檔案路徑</param>
/// <returns>檔案的編碼型別</returns>
publicstaticSystem.Text.Encoding GetType(stringFILE_NAME)
{
FileStream fs =newFileStream(FILE_NAME, FileMode.Open, FileAccess.Read);
Encoding r = GetType(fs);
fs.Close();
returnr;
}
/// <summary>
/// 通過給定的檔案流，判斷檔案的編碼型別
/// </summary>
/// <param name=“fs“>檔案流</param>
/// <returns>檔案的編碼型別</returns>
publicstaticSystem.Text.Encoding GetType(FileStream fs)
{
byte[] Unicode =newbyte[] { 0xFF, 0xFE, 0x41 };
byte[] UnicodeBIG =newbyte[] { 0xFE, 0xFF, 0x00 };
byte[] UTF8 =newbyte[] { 0xEF, 0xBB, 0xBF };//帶BOM
Encoding reVal = Encoding.Default;
BinaryReader r =newBinaryReader(fs, System.Text.Encoding.Default);
inti;
int.TryParse(fs.Length.ToString(),outi);
byte[] ss = r.ReadBytes(i);if(IsUTF8Bytes(ss) || (ss[0] == 0xEF && ss[1] == 0xBB && ss[2] == 0xBF))
{
reVal = Encoding.UTF8;
}
elseif(ss[0] == 0xFE && ss[1] == 0xFF && ss[2] == 0x00)
{
reVal = Encoding.BigEndianUnicode;
}
elseif(ss[0] == 0xFF && ss[1] == 0xFE && ss[2] == 0x41)
{
reVal = Encoding.Unicode;
}
r.Close();
returnreVal;
}
/// <summary>
/// 判斷是否是不帶 BOM 的 UTF8 格式
/// </summary>
/// <param name=“data“></param>
/// <returns></returns>
privatestaticboolIsUTF8Bytes(byte[] data)
{
intcharByteCounter = 1;//計算當前正分析的字元應還有的位元組數
bytecurByte;//當前分析的位元組.
for(inti = 0; i < data.Length; i++)
{
curByte = data[i];
if(charByteCounter == 1)
{
if(curByte >= 0x80)
{
//判斷當前
while(((curByte <<= 1) & 0x80) != 0)
{
charByteCounter++;
}
//標記位首位若為非0 則至少以2個1開始 如:110XXXXX...........1111110X
if(charByteCounter == 1 || charByteCounter > 6)
{
returnfalse;
}
}
}
else
{
//若是UTF-8 此時第一位必須為1
if((curByte & 0xC0) != 0x80)
{
returnfalse;
}
charByteCounter--;
}
}
if(charByteCounter > 1)
{
thrownewException("非預期的byte格式");
}
returntrue;
}
}
轉自：https://www.cnblogs.com/cyberarmy/p/5652835.html