Mapreduce实例——二次排序

实验步骤

1.开启Hadoop

2.新建mapreduce8目录

在Linux本地新建/data/mapreduce8目录

3. 上传文件到linux中

（自行生成文本文件，放到个人指定文件夹下）

goods_visit2

1010037 100

1010102 100

1010152 97

1010178 96

1010280 104

1010320 103

1010510 104

1010603 96

1010637 97

4.在HDFS中新建目录

首先在HDFS上新建/mymapreduce8/in目录，然后将Linux本地/data/mapreduce8目录下的goods_visit2文件导入到HDFS的/mymapreduce8/in目录中。

hadoop fs -mkdir -p /mymapreduce8/in

hadoop fs -put /root/data/mapreduce8/goods_visit2 /mymapreduce8/in

5.新建Java Project项目

新建Java Project项目，项目名为mapreduce。

在mapreduce项目下新建包，包名为mapreduce7。

在mapreduce7包下新建类，类名为SecondarySort。

6.添加项目所需依赖的jar包

右键项目，新建一个文件夹，命名为：hadoop2lib,用于存放项目所需的jar包。

将/data/mapreduce2目录下，hadoop2lib目录中的jar包，拷贝到eclipse中mapreduce2项目的hadoop2lib目录下。

hadoop2lib为自己从网上下载的，并不是通过实验教程里的命令下载的

选中所有项目hadoop2lib目录下所有jar包，并添加到Build Path中。

7.编写程序代码

SecondarySort.java

package mapreduce7;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Partitioner;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
public class SecondarySort
{

    public static class IntPair implements WritableComparable
    {
        int first;
        int second;

        public void set(int left, int right)
        {
            first = left;
            second = right;
        }
        public int getFirst()
        {
            return first;
        }
        public int getSecond()
        {
            return second;
        }
        @Override

        public void readFields(DataInput in) throws IOException
        {
            // TODO Auto-generated method stub
            first = in.readInt();
            second = in.readInt();
        }
        @Override

        public void write(DataOutput out) throws IOException
        {
            // TODO Auto-generated method stub
            out.writeInt(first);
            out.writeInt(second);
        }
        @Override

        public int compareTo(IntPair o)
        {
            // TODO Auto-generated method stub
            if (first != o.first)
            {
                return first < o.first ? 1 : -1;
            }
            else if (second != o.second)
            {
                return second < o.second ? -1 : 1;
            }
            else
            {
                return 0;
            }
        }
        @Override
        public int hashCode()
        {
            return first * 157 + second;
        }
        @Override
        public boolean equals(Object right)
        {
            if (right == null)
                return false;
            if (this == right)
                return true;
            if (right instanceof IntPair)
            {
                IntPair r = (IntPair) right;
                return r.first == first && r.second == second;
            }
            else
            {
                return false;
            }
        }
    }

    public static class FirstPartitioner extends Partitioner
    {
        @Override
        public int getPartition(IntPair key, IntWritable value,int numPartitions)
        {
            return Math.abs(key.getFirst() * 127) % numPartitions;
        }
    }
    public static class GroupingComparator extends WritableComparator
    {
        protected GroupingComparator()
        {
            super(IntPair.class, true);
        }
        @Override
        //Compare two WritableComparables.
        public int compare(WritableComparable w1, WritableComparable w2)
        {
            IntPair ip1 = (IntPair) w1;
            IntPair ip2 = (IntPair) w2;
            int l = ip1.getFirst();
            int r = ip2.getFirst();
            return l == r ? 0 : (l < r ? -1 : 1);
        }
    }
    public static class Map extends Mapper
    {
        private final IntPair intkey = new IntPair();
        private final IntWritable intvalue = new IntWritable();
        public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException
        {
            String line = value.toString();
            StringTokenizer tokenizer = new StringTokenizer(line);
            int left = 0;
            int right = 0;
            if (tokenizer.hasMoreTokens())
            {
                left = Integer.parseInt(tokenizer.nextToken());
                if (tokenizer.hasMoreTokens())
                    right = Integer.parseInt(tokenizer.nextToken());
                intkey.set(right, left);
                intvalue.set(left);
                context.write(intkey, intvalue);
            }
        }
    }

    public static class Reduce extends Reducer
    {
        private final Text left = new Text();
        private static final Text SEPARATOR = new Text("------------------------------------------------");

        public void reduce(IntPair key, Iterable values,Context context) throws IOException, InterruptedException
        {
            context.write(SEPARATOR, null);
            left.set(Integer.toString(key.getFirst()));
            System.out.println(left);
            for (IntWritable val : values)
            {
                context.write(left, val);
                //System.out.println(val);
            }
        }
    }
    public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException
    {

        Configuration conf = new Configuration();
        Job job = new Job(conf, "secondarysort");
        job.setJarByClass(SecondarySort.class);
        job.setMapperClass(Map.class);
        job.setReducerClass(Reduce.class);
        job.setPartitionerClass(FirstPartitioner.class);

        job.setGroupingComparatorClass(GroupingComparator.class);
        job.setMapOutputKeyClass(IntPair.class);

        job.setMapOutputValueClass(IntWritable.class);

        job.setOutputKeyClass(Text.class);

        job.setOutputValueClass(IntWritable.class);

        job.setInputFormatClass(TextInputFormat.class);

        job.setOutputFormatClass(TextOutputFormat.class);
        String[] otherArgs=new String[2];
        otherArgs[0]="hdfs://192.168.109.10:9000/mymapreduce8/in/goods_visit2";
        otherArgs[1]="hdfs://192.168.109.10:9000/mymapreduce8/out";

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

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

        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

8.运行代码

在SecondarySort类文件中，右键并点击=>Run As=>Run on Hadoop选项，将MapReduce任务提交到Hadoop中。

9.查看实验结果

待执行完毕后，进入命令模式下，在HDFS中/mymapreduce8/out查看实验结果。

hadoop fs -ls /mymapreduce8/out  

hadoop fs -cat /mymapreduce8/out/part-r-00000  

图一为我的运行结果，图二为实验结果

经过对比，发现结果一样

此处为浏览器截图