判斷文本文件的編碼

 

調用：

Encoding encoding = GetFileEncodeType(sourcePath);
TextReader tr = new StreamReader(sourcePath, encoding);

 

 

        #region 判斷文本文件的編碼    

        /// <summary>
        /// 給定文件的路徑，讀取文件的二進制數據，判斷文件的編碼類型
        /// </summary>
        /// <param name=“FILE_NAME“>文件路徑</param>
        /// <returns>文件的編碼類型</returns>
        public static System.Text.Encoding GetFileEncodeType(string FILE_NAME)
        {
            try
            {
                FileStream fs = new FileStream(FILE_NAME, FileMode.Open, FileAccess.Read);
                Encoding r = GetType(fs);
                fs.Close();
                return r;
            }
            catch
            {
                return Encoding.Default;
            }
        }

        /// <summary>
        /// 通過給定的文件流，判斷文件的編碼類型
        /// </summary>
        /// <param name=“fs“>文件流</param>
        /// <returns>文件的編碼類型</returns>
        public static System.Text.Encoding GetType(FileStream fs)
        {
            try
            {

                byte[] Unicode = new byte[] { 0xFF, 0xFE, 0x41 };
                byte[] UnicodeBIG = new byte[] { 0xFE, 0xFF, 0x00 };
                byte[] UTF8 = new byte[] { 0xEF, 0xBB, 0xBF }; //帶BOM
                Encoding reVal = Encoding.Default;

                BinaryReader r = new BinaryReader(fs, System.Text.Encoding.Default);
                int i;
                int.TryParse(fs.Length.ToString(), out 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;
                }
                //else if (ss[0] == 0x31 && ss[1] == 0xA1 && ss[2] == 0xA2)
                else
                {
                    reVal = Encoding.GetEncoding("GB2312");
                }
                r.Close();
                return reVal;
            }
            catch
            {
                return Encoding.Default;
            }

        }

        /// <summary>
        /// 判斷是否是不帶 BOM 的 UTF8 格式
        /// </summary>
        /// <param name=“data“></param>
        /// <returns></returns>
        private static bool IsUTF8Bytes(byte[] data)
        {
            try
            {

                int charByteCounter = 1; //計算當前正分析的字符應還有的字節數
                byte curByte; //當前分析的字節.
                for (int i = 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)
                            {
                                return false;
                            }
                        }
                    }
                    else
                    {
                        //若是UTF-8 此時第一位必須為1
                        if ((curByte & 0xC0) != 0x80)
                        {
                            return false;
                        }
                        charByteCounter--;
                    }
                }
                if (charByteCounter > 1)
                {
                    throw new Exception("非預期的byte格式");
                }
                return true;
            }
            catch
            {
                return false;
            }
        }
        #endregion