取得一个文本文件流的编码方式
#region 取得一个文本文件流的编码方式 /// <summary> /// 取得一个文本文件流的编码方式。 /// </summary> /// <param name="stream">文本文件流。</param> /// <param name="defaultEncoding">默认编码方式。当该方法无法从文件的头部取得有效的前导符时,将返回该编码方式。</param> /// <returns></returns> public string GetEncoding(FileStream stream, string defaultEncoding) { string 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.BodyName; } if (byte1 == 0xFF && byte2 == 0xFE && byte3 != 0xFF)//Unicode { targetEncoding = Encoding.Unicode.BodyName; } if (byte1 == 0xEF && byte2 == 0xBB && byte3 == 0xBF)//UTF8 { targetEncoding = Encoding.UTF8.BodyName; } //恢复Seek位置 stream.Seek(origPos, SeekOrigin.Begin); } return targetEncoding; } #endregion
工欲善其事,必先利其器。