hadoop-MapReduce案例流量统计+排序

Step 1: 自定义map的输出value对象FlowBean

用的是MapReduce案例流量统计的数据排序

package flowcount_sort_demo02;

import org.apache.hadoop.io.WritableComparable;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

public class FlowBean implements WritableComparable<FlowBean> {
    private Integer upFlow;  //上行数据包数
    private Integer downFlow;  //下行数据包数
    private Integer upCountFlow; //上行流量总和
    private Integer downCountFlow;//下行流量总和


    public Integer getUpFlow() {
        return upFlow;
    }

    public void setUpFlow(Integer upFlow) {
        this.upFlow = upFlow;
    }

    public Integer getDownFlow() {
        return downFlow;
    }

    public void setDownFlow(Integer downFlow) {
        this.downFlow = downFlow;
    }

    public Integer getUpCountFlow() {
        return upCountFlow;
    }

    public void setUpCountFlow(Integer upCountFlow) {
        this.upCountFlow = upCountFlow;
    }

    public Integer getDownCountFlow() {
        return downCountFlow;
    }

    public void setDownCountFlow(Integer downCountFlow) {
        this.downCountFlow = downCountFlow;
    }

    @Override
    public String toString() {
        return  upFlow +"\t"+
                downFlow +"\t"+
                upCountFlow +"\t"+
                downCountFlow;
    }

    @Override
    public void write(DataOutput dataOutput) throws IOException {
        dataOutput.writeInt(this.upFlow);
        dataOutput.writeInt(this.downFlow);
        dataOutput.writeInt(this.downCountFlow);
        dataOutput.writeInt(this.upCountFlow);
    }

    @Override
    public void readFields(DataInput dataInput) throws IOException {
        this.upFlow=dataInput.readInt();
        this.downFlow=dataInput.readInt();
        this.upCountFlow=dataInput.readInt();
        this.downCountFlow=dataInput.readInt();
    }
    //指定排序规则
    @Override
    public int compareTo(FlowBean flowBean) {
       // return this.upFlow.compareTo(flowBean.getUpFlow());

        //降序
        return flowBean.upFlow -this.upFlow;
    }
}

Step 2: 定义FlowSortMapper类

package flowcount_sort_demo02;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

public class FlowSortMapper extends Mapper<LongWritable, Text,FlowBean,Text> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //1.拆分行文本数据v1 得到四个流量字段，并封装FlowBean对象
        String[] split =value.toString().split("\t");

        FlowBean flowbean=new FlowBean();
        flowbean.setUpFlow(Integer.parseInt(split[1]));
        flowbean.setDownFlow(Integer.parseInt(split[2]));
        flowbean.setUpCountFlow(Integer.parseInt(split[3]));
        flowbean.setDownCountFlow(Integer.parseInt(split[4]));

        String phonenum =split[0];
        context.write(flowbean,new Text(phonenum));

    }
}

Step 3: 定义FlowSortReducer类

package flowcount_sort_demo02;

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

import java.io.IOException;

public class FlowSortReducer extends Reducer<FlowBean, Text,Text,FlowBean> {
    @Override
    protected void reduce(FlowBean key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
        for (Text value:values) {
            context.write(value,key);
        }
    }
}

Step 4: 程序main函数入口FlowMain

package flowcount_sort_demo02;
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[] args) throws Exception {
        Job job = Job.getInstance(super.getConf(), "flow_sort");
        //打包到集群上面运行时候，必须要添加以下配置，指定程序的main函数
        job.setJarByClass(JobMain.class);


        //第一步：读取输入文件解析成key，value对
        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.addInputPath(job,new Path("file:///D:\\out\\flowcount_out"));


        //第二步：设置我们的mapper类
        job.setMapperClass(FlowSortMapper.class);
        //设置我们map阶段完成之后的输出类型
        job.setMapOutputKeyClass(FlowBean.class);
        job.setMapOutputValueClass(Text.class);


        //第三步分区，第四步排序，第六步分组，都默认



        //第七步：设置我们的reduce类
        job.setReducerClass(FlowSortReducer.class);
        //设置我们reduce阶段完成之后的输出类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);

        //第八步：设置输出类以及输出路径
        job.setOutputFormatClass(TextOutputFormat.class);
        TextOutputFormat.setOutputPath(job,new Path("file:///D:\\out\\flowsort_out"));
        boolean b = job.waitForCompletion(true);
        return b?0:1;
    }

    /**
     * 程序main函数的入口类
     * @param args
     * @throws Exception
     */
    public static void main(String[] args) throws Exception {
        Configuration configuration = new Configuration();
        Tool tool  =  new JobMain();
        int run = ToolRunner.run(configuration, tool, args);
        System.exit(run);
    }
}