Hadoop基础（二十一）：Shuffle机制（二）

package com.atguigu.mapreduce.sort;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import org.apache.hadoop.io.WritableComparable;

public class FlowBean implements WritableComparable<FlowBean> {

    private long upFlow;
    private long downFlow;
    private long sumFlow;

    // 反序列化时，需要反射调用空参构造函数，所以必须有
    public FlowBean() {
        super();
    }

    public FlowBean(long upFlow, long downFlow) {
        super();
        this.upFlow = upFlow;
        this.downFlow = downFlow;
        this.sumFlow = upFlow + downFlow;
    }

    public void set(long upFlow, long downFlow) {
        this.upFlow = upFlow;
        this.downFlow = downFlow;
        this.sumFlow = upFlow + downFlow;
    }

    public long getSumFlow() {
        return sumFlow;
    }

    public void setSumFlow(long sumFlow) {
        this.sumFlow = sumFlow;
    }    

    public long getUpFlow() {
        return upFlow;
    }

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

    public long getDownFlow() {
        return downFlow;
    }

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

    /**
     * 序列化方法
     * @param out
     * @throws IOException
     */
    @Override
    public void write(DataOutput out) throws IOException {
        out.writeLong(upFlow);
        out.writeLong(downFlow);
        out.writeLong(sumFlow);
    }

    /**
     * 反序列化方法 注意反序列化的顺序和序列化的顺序完全一致
     * @param in
     * @throws IOException
     */
    @Override
    public void readFields(DataInput in) throws IOException {
        upFlow = in.readLong();
        downFlow = in.readLong();
        sumFlow = in.readLong();
    }

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

    @Override
    public int compareTo(FlowBean o) {
        
        int result;
        
        // 按照总流量大小，倒序排列
        if (sumFlow > bean.getSumFlow()) {
            result = -1;
        }else if (sumFlow < bean.getSumFlow()) {
            result = 1;
        }else {
            result = 0;
        }

        return result;
    }
}

package com.atguigu.mapreduce.sort;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

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

    FlowBean bean = new FlowBean();
    Text v = new Text();

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

        // 1 获取一行
        String line = value.toString();
        
        // 2 截取
        String[] fields = line.split("\t");
        
        // 3 封装对象
        String phoneNbr = fields[0];
        long upFlow = Long.parseLong(fields[1]);
        long downFlow = Long.parseLong(fields[2]);
        
        bean.set(upFlow, downFlow);
        v.set(phoneNbr);
        
        // 4 输出
        context.write(bean, v);
    }
}

package com.atguigu.mapreduce.sort;
import java.io.IOException;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

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

    @Override
    protected void reduce(FlowBean key, Iterable<Text> values, Context context)    throws IOException, InterruptedException {
        
        // 循环输出，避免总流量相同情况
        for (Text text : values) {
            context.write(text, key);
        }
    }
}

package com.atguigu.mapreduce.sort;
import java.io.IOException;
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;

public class FlowCountSortDriver {

    public static void main(String[] args) throws ClassNotFoundException, IOException, InterruptedException {

        // 输入输出路径需要根据自己电脑上实际的输入输出路径设置
        args = new String[]{"e:/output1","e:/output2"};

        // 1 获取配置信息，或者job对象实例
        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);

        // 2 指定本程序的jar包所在的本地路径
        job.setJarByClass(FlowCountSortDriver.class);

        // 3 指定本业务job要使用的mapper/Reducer业务类
        job.setMapperClass(FlowCountSortMapper.class);
        job.setReducerClass(FlowCountSortReducer.class);

        // 4 指定mapper输出数据的kv类型
        job.setMapOutputKeyClass(FlowBean.class);
        job.setMapOutputValueClass(Text.class);

        // 5 指定最终输出的数据的kv类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);

        // 6 指定job的输入原始文件所在目录
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        
        // 7 将job中配置的相关参数，以及job所用的java类所在的jar包， 提交给yarn去运行
        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);
    }
}

package com.atguigu.mapreduce.sort;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Partitioner;

public class ProvincePartitioner extends Partitioner<FlowBean, Text> {

    @Override
    public int getPartition(FlowBean key, Text value, int numPartitions) {
        
        // 1 获取手机号码前三位
        String preNum = value.toString().substring(0, 3);
        
        int partition = 4;
        
        // 2 根据手机号归属地设置分区
        if ("136".equals(preNum)) {
            partition = 0;
        }else if ("137".equals(preNum)) {
            partition = 1;
        }else if ("138".equals(preNum)) {
            partition = 2;
        }else if ("139".equals(preNum)) {
            partition = 3;
        }

        return partition;
    }
}

// 加载自定义分区类
job.setPartitionerClass(ProvincePartitioner.class);

// 设置Reducetask个数
job.setNumReduceTasks(5);