自动获取编码格式

 public static DataSet GetDataSetByXmlpath(string strXmlPath)
        {
            try
            {
                DataSet ds = new DataSet();
                //读取XML到DataSet 
             Encoding encoding=GetEncoding(strXmlPath, Encoding.Default);
                
               StreamReader sr = new StreamReader(strXmlPath, encoding);//, new UTF8Encoding(false)
              
                ds.ReadXml(sr);

                sr.Close();

                if (ds.Tables.Count > 0)
                    return ds;
                return null;
            }
            catch (Exception ex)
            {

                return null;
            }
        }

        /// <summary>
        /// 取得一个文本文件的编码方式。
        /// </summary>
        /// <param name="fileName">文件名。</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 static Encoding GetEncoding(string fileName, Encoding defaultEncoding)
        {
            FileStream fs = new FileStream(fileName, FileMode.Open);
            Encoding targetEncoding = GetEncoding(fs, defaultEncoding);
            fs.Close();
            return targetEncoding;
        }

        /// <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 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 = new UTF8Encoding(true);
                }
                else
                {
                    targetEncoding= GetEncoding(stream);
                }
                //恢复Seek位置      
                //stream.Seek(0, SeekOrigin.Begin);
            }
            return targetEncoding;
        }

        /// <summary>
        /// 通过给定的文件流,判断文件的编码类型
        /// </summary>
        /// <param name="fs">文件流</param>
        /// <returns>文件的编码类型</returns>
        public static System.Text.Encoding GetEncoding(Stream fs)
        {
            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;

            BinaryReader r = new BinaryReader(fs, System.Text.Encoding.Default);
            byte[] ss = r.ReadBytes(4);
            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] == 0xEF && ss[1] == 0xBB && ss[2] == 0xBF)
                {
                    reVal = new UTF8Encoding(true);
                }
                else
                {
                    int i;
                    int.TryParse(fs.Length.ToString(), out i);
                    ss = r.ReadBytes(i);

                    if (IsUTF8Bytes(ss))
                        reVal = new UTF8Encoding(true);
                }
            }
           // r.Close();
            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;
        }

添加重定为0,导致保存错误提示:

Dataset.Readxml(stream) 错误 “缺少根元素”

之后就将重定去除,即可使用。推测可能是重定导致无法检测到根元素

posted @ 2021-03-08 11:19  学竹  阅读(94)  评论(0编辑  收藏  举报