大数据培训 GroupingComparator分组（辅助排序）

package com.atguigu.mapreduce.order;

import java.io.DataInput;

import java.io.DataOutput;

import java.io.IOException;

import org.apache.hadoop.io.WritableComparable;

public class OrderBean implements WritableComparable<OrderBean> {

  private int order_id; // 订单id号

  private double price; // 价格

  public OrderBean() {

      super();

  }

  public OrderBean(int order_id, double price) {

      super();

      this.order_id = order_id;

      this.price = price;

  }

  @Override

  public void write(DataOutput out) throws IOException {

      out.writeInt(order_id);

      out.writeDouble(price);

  }

  @Override

  public void readFields(DataInput in) throws IOException {

      order_id = in.readInt();

      price = in.readDouble();

  }

  @Override

  public String toString() {

      return order_id + “\t” + price;

  }

  public int getOrder_id() {

      return order_id;

  }

  public void setOrder_id(int order_id) {

      this.order_id = order_id;

  }

  public double getPrice() {

      return price;

  }

  public void setPrice(double price) {

      this.price = price;

  }

  // 二次排序

  @Override

  public int compareTo(OrderBean o) {

      int result;

      if (order_id > o.getOrder_id()) {

         result = 1;

      } else if (order_id < o.getOrder_id()) {

         result = -1;

      } else {

         // 价格倒序排序

         result = price > o.getPrice() ? -1 : 1;

      }

      return result;

  }

}

package com.atguigu.mapreduce.order;

import java.io.IOException;

import org.apache.hadoop.io.LongWritable;

import org.apache.hadoop.io.NullWritable;

import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapreduce.Mapper;

public class OrderMapper extends Mapper<LongWritable, Text, OrderBean, NullWritable> {

  OrderBean k = new OrderBean();

  @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

      k.setOrder_id(Integer.parseInt(fields[0]));

      k.setPrice(Double.parseDouble(fields[2]));

      // 4 写出

      context.write(k, NullWritable.get());

  }

}

package com.atguigu.mapreduce.order;

import org.apache.hadoop.io.WritableComparable;

import org.apache.hadoop.io.WritableComparator;

public class OrderGroupingComparator extends WritableComparator {

  protected OrderGroupingComparator() {

      super(OrderBean.class, true);

  }

  @Override

  public int compare(WritableComparable a, WritableComparable b) {

      OrderBean aBean = (OrderBean) a;

      OrderBean bBean = (OrderBean) b;

      int result;

      if (aBean.getOrder_id() > bBean.getOrder_id()) {

         result = 1;

  } else if (aBean.getOrder_id() < bBean.getOrder_id()) {

         result = -1;

      } else {

         result = 0;

      }

      return result;

  }

}

package com.atguigu.mapreduce.order;

import java.io.IOException;

import org.apache.hadoop.io.NullWritable;

import org.apache.hadoop.mapreduce.Reducer;

public class OrderReducer extends Reducer<OrderBean, NullWritable, OrderBean, NullWritable> {

  @Override

  protected void reduce(OrderBean key, Iterable<NullWritable> values, Context context)     throws IOException, InterruptedException {

      context.write(key, NullWritable.get());

  }

}

package com.atguigu.mapreduce.order;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;

import org.apache.hadoop.fs.Path;

import org.apache.hadoop.io.NullWritable;

import org.apache.hadoop.mapreduce.Job;

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;

import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class OrderDriver {

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

// 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:/input/inputorder” , “e:/output1”};

      // 1 获取配置信息

      Configuration conf = new Configuration();

      Job job = Job.getInstance(conf);

      // 2 设置jar包加载路径

      job.setJarByClass(OrderDriver.class);

      // 3 加载map/reduce类

      job.setMapperClass(OrderMapper.class);

      job.setReducerClass(OrderReducer.class);

      // 4 设置map输出数据key和value类型

      job.setMapOutputKeyClass(OrderBean.class);

      job.setMapOutputValueClass(NullWritable.class);

      // 5 设置最终输出数据的key和value类型

      job.setOutputKeyClass(OrderBean.class);

      job.setOutputValueClass(NullWritable.class);

      // 6 设置输入数据和输出数据路径

      FileInputFormat.setInputPaths(job, new Path(args[0]));

      FileOutputFormat.setOutputPath(job, new Path(args[1]));

     // 8 设置reduce端的分组

  job.setGroupingComparatorClass(OrderGroupingComparator.class);

      // 7 提交

      boolean result = job.waitForCompletion(true);

      System.exit(result ? 0 : 1);

  }

}