hadoop中MapReduce对大量小文件的操作

package com.zyc.hadoop.mapreduce.weblog;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.*;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat;
import java.io.IOException;

/**
* Created with IntelliJ IDEA.
*
* @Author: [email protected]
* @Date: 2020/9/10 22:14
* @Version: 1.0
* @Description: 大量小文件的处理：通过自定义InputFormat完成一次性读取整个文件的操作
*/
public class WebLogSequenceFile {
    public static void main(Strin