public static DataTable OpenCSV(string filePath)//从csv读取数据返回table
{System.Text.Encoding encoding = GetType(filePath); //Encoding.ASCII;//DataTable dt = new DataTable();System.IO.FileStream fs = new System.IO.FileStream(filePath, System.IO.FileMode.Open, System.IO.FileAccess.Read);System.IO.StreamReader sr = new System.IO.StreamReader(fs, encoding);//记录每次读取的一行记录string strLine = "";//记录每行记录中的各字段内容string[] aryLine = null;string[] tableHead = null;//标示列数int columnCount = 0;//标示是否是读取的第一行bool IsFirst = true;//逐行读取CSV中的数据while ((strLine = sr.ReadLine()) != null){if (IsFirst == true){tableHead = strLine.Split(',');IsFirst = false;columnCount = tableHead.Length;//创建列for (int i = 0; i < columnCount; i++){DataColumn dc = new DataColumn(tableHead[i]);dt.Columns.Add(dc);}}else{aryLine = strLine.Split(',');DataRow dr = dt.NewRow();for (int j = 0; j < columnCount; j++){dr[j] = aryLine[j];}dt.Rows.Add(dr);}}if (aryLine != null && aryLine.Length > 0){dt.DefaultView.Sort = tableHead[0] + " " + "asc";}sr.Close();fs.Close();return dt;
}
/// 给定文件的路径，读取文件的二进制数据，判断文件的编码类型
/// <param name="FILE_NAME">文件路径</param>
/// <returns>文件的编码类型</returns>public static System.Text.Encoding GetType(string FILE_NAME)
{System.IO.FileStream fs = new System.IO.FileStream(FILE_NAME, System.IO.FileMode.Open, System.IO.FileAccess.Read);System.Text.Encoding r = GetType(fs);fs.Close();return r;
}/// 通过给定的文件流，判断文件的编码类型
/// <param name="fs">文件流</param>
/// <returns>文件的编码类型</returns>
public static System.Text.Encoding GetType(System.IO.FileStream fs)
{byte[] Unicode = new byte[] { 0xFF, 0xFE, 0x41 };byte[] UnicodeBIG = new byte[] { 0xFE, 0xFF, 0x00 };byte[] UTF8 = new byte[] { 0xEF, 0xBB, 0xBF }; //带BOMSystem.Text.Encoding reVal = System.Text.Encoding.Default;System.IO.BinaryReader r = new System.IO.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 = System.Text.Encoding.UTF8;}else if (ss[0] == 0xFE && ss[1] == 0xFF && ss[2] == 0x00){reVal = System.Text.Encoding.BigEndianUnicode;}else if (ss[0] == 0xFF && ss[1] == 0xFE && ss[2] == 0x41){reVal = System.Text.Encoding.Unicode;}r.Close();return reVal;
}/// 判断是否是不带 BOM 的 UTF8 格式
/// <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1if ((curByte & 0xC0) != 0x80){return false;}charByteCounter--;}}if (charByteCounter > 1){throw new Exception("非预期的byte格式");}return true;
}