C#获取文本文件的编码，自动区分GB2312和UTF8

引用：C#获取文本文件的编码，自动区分GB2312和UTF8

参考代码未在项目中应用，只在测试时使用过。

        /// <summary>
        /// 获取文件编码格式
        /// </summary>
        /// <param name="file"></param>
        /// <returns></returns>
        public static System.Text.Encoding GetType(string file)
        {
            using (FileStream fs = new FileStream(file, 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 r = new BinaryReader(fs, System.Text.Encoding.Default))
                {
                    int.TryParse(fs.Length.ToString(), out int i);
                    byte[] ss = r.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;
                    }
                    r.Close();
                }
                fs.Close();
                fs.Dispose();
                return reVal;
            }
        }

        /// <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;
        }