//方法一
using System.Text;
using System.Data;
using System.IO;
namespace OpenCSV
{
public class CSVFile
{
public class CSVFileHelper
{
/// <summary>
/// 将CSV文件的数据读取到DataTable中
/// </summary>
/// <param name="fileName">CSV文件路径</param>
/// <returns>返回读取了CSV数据的DataTable</returns>
public static DataTable OpenCSV(string filePath)
{
Encoding encoding = Common.GetType(filePath); //Encoding.ASCII;//
DataTable dt = new DataTable();
FileStream fs = new FileStream(filePath, System.IO.FileMode.Open, System.IO.FileAccess.Read);
//StreamReader sr = new StreamReader(fs, Encoding.UTF8);
StreamReader sr = new StreamReader(fs, encoding);
//string fileContent = sr.ReadToEnd();
//encoding = sr.CurrentEncoding;
//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)
{
//strLine = Common.ConvertStringUTF8(strLine, encoding);
//strLine = Common.ConvertStringUTF8(strLine);
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;
}
}
}
}
//方法二
using System;
using System.Text;
using System.IO;
namespace OpenCSV
{
/// <summary>
/// FileEncoding 的摘要说明
/// </summary>
class Common
{
/// <summary>
/// 获取文件的编码格式
/// </summary>
/// <summary>
/// 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
/// </summary>
/// <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)
{
FileStream fs = new FileStream(FILE_NAME, FileMode.Open, FileAccess.Read);
Encoding r = GetType(fs);
fs.Close();
return r;
}
/// <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 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;
}
/// <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;
}
}
}
//方法三
public static class CsvFileReader
{
public static string[][] Read(string fullname)
{
if (!File.Exists(fullname)) return new string[][] { };
var lines = File.ReadAllLines(fullname).Skip(1);
var list=new List<string[]>();
var builder = new StringBuilder();
foreach (var line in lines)
{
builder.Clear();
var comma = false;
var array = line.ToCharArray();
var values = new List<string>();
var length = array.Length - 1;
var index = 0;
while (index < length)
{
var item = array[index++];
switch (item)
{
case ',':
if (comma)
{
builder.Append(item);
}
else
{
values.Add(builder.ToString());
builder.Clear();
}
break;
case '"':
comma = !comma;
break;
default:
builder.Append(item);
break;
}
}
var count = values.Count;
if (count == 0) continue;
list.Add(values.ToArray());
}
return list.ToArray();
}
}