Mapreduce编程案例3——自定义类型

FlowBean.java

package Hadoop.mapreduce.flowerLog;

import org.apache.hadoop.io.Writable;

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

public class FlowBean implements Writable {

    private int upFlow;
    private int downFlow;
    private int amountFlow;
    private String phone;


    public FlowBean(){}

    public FlowBean(String phone,int upFlow, int downFlow) {

        this.phone = phone;
        this.upFlow = upFlow;
        this.downFlow = downFlow;
        this.amountFlow = upFlow + downFlow;
    }

    public int getUpFlow() {
        return upFlow;
    }

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

    public int getDownFlow() {
        return downFlow;
    }

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

    public int getAmountFlow() {
        return amountFlow;
    }

    public void setAmountFlow(int amountFlow) {
        this.amountFlow = amountFlow;
    }

    public String getPhone() {
        return phone;
    }

    public void setPhone(String phone) {
        this.phone = phone;
    }

    /**
     * hadoop在序列化该类的对象所调用的方法
     * @param out
     * @throws IOException
     */
    @Override
    public void write(DataOutput out) throws IOException {

        out.writeInt(upFlow);
        out.writeUTF(phone); //字符串的写入
        out.writeInt(downFlow);
        out.writeInt(amountFlow);
        ;  //
    }

    /**
     * hadoop在反序列化该类的对象所调用的方法
     * @param in
     * @throws IOException
     */
    @Override
    public void readFields(DataInput in) throws IOException {

        this.upFlow = in.readInt();
        this.phone = in.readUTF();
        this.downFlow = in.readInt();
        this.amountFlow = in.readInt();

    }

    @Override
    public String toString() {
        return this.phone + "," + this.upFlow + "," + this.downFlow + "," + this.amountFlow;
    }
}

FlowCountMapper.java

package Hadoop.mapreduce.flowerLog;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import scala.Int;

import java.io.IOException;

public class FlowCountMapper extends Mapper<LongWritable,Text, Text, FlowBean> {


    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {


        String line = value.toString();

        String[] fields = line.split("\t");

        String phone = fields[1];

        int upFlow = Integer.parseInt(fields[fields.length - 3]);
        int downFlow = Integer.parseInt(fields[fields.length - 2]);

        context.write(new Text(phone),new FlowBean(phone,upFlow,downFlow));
    }
}

FlowCountReduce.java

package Hadoop.mapreduce.flowerLog;

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

import java.io.IOException;

public class FlowCountReduce extends Reducer<Text, FlowBean, Text, FlowBean> {


        /**
         *  key：是某个手机号
         *  values：是这个手机号所产生的所有访问记录中的流量数据
         *
         *  <135,flowBean1><135,flowBean2><135,flowBean3><135,flowBean4>
         */
        @Override
        protected void reduce (Text key, Iterable < FlowBean > values, Reducer < Text, FlowBean, Text, FlowBean >.
        Context context)throws IOException, InterruptedException {

            int upSum = 0;
            int dSum = 0;

            for (FlowBean value : values) {
                upSum += value.getUpFlow();
                dSum += value.getDownFlow();
            }

            context.write(key, new FlowBean(key.toString(), upSum, dSum));

        }

}

JobFlowSubmitter.java

package Hadoop.mapreduce.flowerLog;

import org.apache.hadoop.conf.Configuration;
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.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;
/**
*本案例的功能：演示自定义数据类型如何实现hadoop的序列化接口
*1，该类一定要保留空参构造函数
*2，write方法中输出字段二进制数据的顺序要与readFields方法读取数据的顺序一致
*
*/

public class JobFlowSubmitter {

        public static void main(String[] args) throws Exception{

            // 在代码中设置JVM系统参数，用于给job对象来获取访问HDFS的用户身份
            System.setProperty("HADOOP_USER_NAME", "root");

            Configuration conf = new Configuration();
            // 1、设置job运行时要访问的默认文件系统
            conf.set("fs.defaultFS", "file:///");
            // 2、设置job提交到哪去运行
            conf.set("mapreduce.framework.name", "local");

            Job job = Job.getInstance(conf);

            job.setJarByClass(JobFlowSubmitter.class);

            job.setMapperClass(FlowCountMapper.class);
            job.setReducerClass(FlowCountReduce.class);


            // 3、封装参数：本次job的Mapper实现类、Reducer实现类产生的结果数据的key、value类型
            job.setMapOutputKeyClass(Text.class);
            job.setMapOutputValueClass(FlowBean.class);

            job.setOutputKeyClass(Text.class);
            job.setOutputValueClass(FlowBean.class);

            // 4、封装参数：本次job要处理的输入数据集所在路径、最终结果的输出路径
            FileInputFormat.setInputPaths(job, new Path("C://Users//shujuelin//Desktop//spark//hadoop//input"));
            FileOutputFormat.setOutputPath(job,new Path( "C://Users//shujuelin//Desktop//spark//hadoop//output"));  // 注意：输出路径必须不存在


            // 5、封装参数：想要启动的reduce task的数量
            job.setNumReduceTasks(3);



            // 6、提交job给yarn
            boolean res = job.waitForCompletion(true); //true表示在控制台打印出进度信息

            System.exit(res?0:-1);    //如果成功则打印0，不成功则打印-1



        }
}

Mapreduce编程案例3——自定义类型

相关推荐