CSV文件读取
package com.suning.crawler.util;

import java.io.BufferedReader;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import org.apache.log4j.Logger;

/**
* cvs文件读取
*
* @author xxx
*/
public class CSVParser
{
// 日志记录
private Logger logger = Logger.getLogger(CSVParser.class);

/**
* 文件路径
*/
private String filePath;

/**
* 字符编码
*/
private String encode;

/**
* 数据存储
*/
private Map<Integer, List<String>> info;

/**
* @param filePath
* 需要解析的文件路径
*/
public CSVParser(String filePath)
{
this(filePath, "UTF-8");
}

/**
* @param filePath
* 需要解析的文件路径
* @param encode
* 字符编码
*/
public CSVParser(String filePath, String encode)
{
this.filePath = filePath;
this.encode = encode;
info = new HashMap<Integer, List<String>>();

// 开始解析
parseCsv();
}

/**
* 获取行<code>row<row>中的数据，若该行<code>row<row>中的数据，返回<code>null<code>，否则返回该行中的数据
*
* @param row
* 记录行数
* @return 当行数据
*/
public List<String> readLine(int row)
{
return info.get(row);
}

/**
* 解析文件的核心代码
*
* @return csv文件中的数据
*/
private List<String> parseCsv()
{
List<String> row = null;
BufferedReader reader = null;
try
{
// 读取文件
reader = new BufferedReader(new InputStreamReader(new FileInputStream(filePath), encode));
String rowInfo = reader.readLine();
// 行记录指针
int rowIndex = 0;
while (null != rowInfo && !"".equals(rowInfo.trim()))
{
row = new ArrayList<String>();
// 分割数据列
for (String cell : rowInfo.split(","))
{
row.add(cell);
}
info.put(rowIndex, row);
rowInfo = reader.readLine();
++rowIndex;
}
}
catch (FileNotFoundException e)
{
logger.error("file can not be found, file path: " + filePath);
}
catch (IOException e)
{
logger.error("I/O operations, file path: " + filePath);
}
finally
{
if (null != reader)
{
try
{
reader.close();
}
catch (IOException e)
{
logger.error("I/O operations, file path: " + filePath);
}
}
}

return row;
}

}