MapReduce-流量统计求和-Reducer和JobMain代码编写

定义FlowReducer类

package cn.learn.mapreduce_flowcount;

import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

public class FlowCountReducer extends Reducer<Text,FlowBean,Text,FlowBean> {
    @Override
    protected void reduce(Text key, Iterable<FlowBean> values, Context context) throws 
IOException, InterruptedException {
       //封装新的FlowBean
        FlowBean flowBean = new FlowBean();
        Integer upFlow = 0;
        Integer  downFlow = 0;
        Integer upCountFlow = 0;
        Integer downCountFlow = 0;
        for (FlowBean value : values) {
            upFlow  += value.getUpFlow();
            downFlow += value.getDownFlow();
            upCountFlow += value.getUpCountFlow();
            downCountFlow += value.getDownCountFlow();
        }
        flowBean.setUpFlow(upFlow);
        flowBean.setDownFlow(downFlow);
        flowBean.setUpCountFlow(upCountFlow);
        flowBean.setDownCountFlow(downCountFlow);
        //将K3和V3写入上下文中
        context.write(key, flowBean);
    }
}

程序main函数入口FlowMain

package cn.learn.mapreduce_flowcount;

import cn.learn.mapreduce_sort.FlowCountSortReducer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
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;

public class JobMain extends Configured  implements Tool {
    @Override
    public int run(String[] strings) throws Exception {
        //创建一个任务对象
        Job job = Job.getInstance(super.getConf(), "mapreduce_flowcount");

        //打包放在集群运行时，需要做一个配置
        job.setJarByClass(JobMain.class);
        //第一步:设置读取文件的类: K1 和V1
        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.addInputPath(job, new Path("hdfs://node01:8020/input/flowcount"));

        //第二步：设置Mapper类
        job.setMapperClass(FlowCountMapper.class);
        //设置Map阶段的输出类型: k2 和V2的类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);

        //第三,四，五，六步采用默认方式(分区，排序，规约，分组)


        //第七步 ：设置文的Reducer类
        job.setReducerClass(FlowCountReducer.class);
        //设置Reduce阶段的输出类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);

        //设置Reduce的个数

        //第八步:设置输出类
        job.setOutputFormatClass(TextOutputFormat.class);
        //设置输出的路径
        TextOutputFormat.setOutputPath(job, new Path("hdfs://node01:8020/out/flowcount_out"));


        boolean b = job.waitForCompletion(true);
        return b?0:1;

    }
    public static void main(String[] args) throws Exception {
        Configuration configuration = new Configuration();

        //启动一个任务
        int run = ToolRunner.run(configuration, new JobMain(), args);
        System.exit(run);
    }

}