CNAS/CnasSynchronusDAL/DAL/TXTDAL.cs

using CnasSynchronousCommon;
using CnasSynchrousModel;
using System;
using System.Collections.Generic;
using System.Data;
using System.IO;
using System.Linq;
using System.Text;

namespace CnasSynchronusDAL
{
    public class TXTDAL
    {
        /// <summary>
        /// 获取表名表结构
        /// </summary>
        public static DataTable ReadTxtFileColumn(TXTOpenParams t)
        {
            DataTable dt = new DataTable();
            try
            {
                switch (t.TxtFileMode)
                {
                    case "1":
                        ReadFileCommon01.SplitType = t.SplitType;
                        ReadFileCommon01.StartLineIndex = t.StartLineIndex;
                        ReadFileCommon01.IfCustomCreateDateColumn = t.IfCustomCreateDateColumn;
                        ReadFileCommon01.Suffix = t.Suffix;
                        ReadFileCommon01.FileNameFormat = t.FileNameFormat;
                        dt = ReadFileCommon01.ReadTableStructure(t.StrPath);
                        break;
                    case "2":
                        dt = ReadFileSecond.ReadTableStructure();
                        break;
                    case "3":
                        dt = ReadFileThirdth.ReadTableStructure();
                        break;
                }
            }
            catch (Exception ex)
            {
                AppLog.Error(ex.Message);
            }
            return dt;
        }

        public static DataTable ReadTxtFileData(TXTOpenParams t)
        {
            DataTable dt = new DataTable();
            try
            {               
                switch (t.TxtFileMode)
                {
                    case "1":
                        ReadFileCommon01.SplitType = t.SplitType;
                        ReadFileCommon01.StartLineIndex = t.StartLineIndex;
                        ReadFileCommon01.IfCustomCreateDateColumn = t.IfCustomCreateDateColumn;
                        ReadFileCommon01.Suffix = t.Suffix;
                        ReadFileCommon01.FileNameFormat = t.FileNameFormat;
                        dt = ReadFileCommon01.ReadTableData(t.StrPath);
                        break;
                    case "2":
                        dt = ReadFileSecond.ReadTableData(t.StrPath);
                        break;
                    case "3":
                        dt = ReadFileThirdth.ReadTableData(t.StrPath);
                        break;
                } 
            }
            catch (Exception ex)
            {
                AppLog.Error(ex.Message);
            }
            return dt;
        }


        #region  得到文本的编码格式，避免因解析问题造成的乱码

        public static System.Text.Encoding GetType(string FILE_NAME)
        {
            FileStream fs = new FileStream(FILE_NAME, FileMode.Open, FileAccess.Read);
            Encoding r = GetType(fs);
            fs.Close();
            return r;
        }

        public static System.Text.Encoding GetType(FileStream 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);
            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;
            }
            r.Close();
            return reVal;

        }

        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;
        }
        #endregion
    }
}