mapreduce -天龙八部 示例wordcount

下面是要执行单词统计的文本

hello,hello
world,world
hadoop,hadoop
hello,world
hello,flume
hadoop,hive
hive,kafka
flume,storm
hive,oozie

 

主类

package com.wxj.mapreduce;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

/*
 * Created by wxj on 2019/8/4 0004 20:41
 */
public class JobMain extends Configured implements Tool {

    @Override
    public int run(String[] strings) throws Exception {
        //获取一个job对象，用于我们的任务组织，通过job对象将mapreduce的八个步骤组织起来，提交给yarn集群
        Job job = Job.getInstance(super.getConf