MapReduce排序

一、键排序

原数据：两列分别是品牌、销售额

Hino	3153
Toyota	177649
Buick	296183
Cadillac	20116
Audi	121804
Skoda	33554
VW	237156
Nissan	259545
Hyundai	240702
Kia	135666
Ford	403640
Fiat	48375
CIIMO	15087
Everus	13913
Honda	119542
Citroen	158735
Peugeot	33242
Suzuki	33244

排序后结果：

在shuffle(洗牌)过程中，会将map的输出结果按照key进行排序，所以只需要将Bean作为map输出的key值，前提是

Bean实现了Comparable接口。在hadoop中既实现Writable接口，又实现Comparable接口，可以简写为实现了

WritableComparable接口。

Bean.java

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

import org.apache.hadoop.io.WritableComparable;  

public class Bean implements WritableComparable<Bean> {  
  
    private String carName;  
    private long sum;  
  
    public Bean() {		
    }  
    public Bean(String carName, long sum) { 
        this.carName = carName;  
        this.sum = sum;  
    }  
    @Override  
    public void write(DataOutput out) throws IOException {  
        out.writeUTF(carName);  
        out.writeLong(sum);  
    }  
    @Override  
    public void readFields(DataInput in) throws IOException {  
        this.carName = in.readUTF();  
        this.sum = in.readLong();  
    }  
	
	public String getCarName() {
		return carName;
	}
	public void setCarName(String carName) {
		this.carName = carName;
	}
	public long getSum() {
		return sum;
	}
	public void setSum(long sum) {
		this.sum = sum;
	}  
  
    @Override  
    public String toString() {  
        return "" + sum;  
    }  
    @Override  
    public int compareTo(Bean o) {  
        return this.sum > o.sum ? -1 : 1;  
    }  
}  

SortMapReduce.java

import java.io.IOException;  
  
import org.apache.commons.lang.StringUtils;  
import org.apache.hadoop.conf.Configuration;  
import org.apache.hadoop.fs.Path;  
import org.apache.hadoop.io.LongWritable;  
import org.apache.hadoop.io.NullWritable;  
import org.apache.hadoop.io.Text;  
import org.apache.hadoop.mapreduce.Job;  
import org.apache.hadoop.mapreduce.Mapper;  
import org.apache.hadoop.mapreduce.Reducer;  
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;  
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;  
  
public class SortMapReduce {  
  
    public static class SortMapper extends  
            Mapper<LongWritable, Text, Bean, NullWritable> {  
        @Override  
        protected void map(  
                LongWritable k1,  
                Text v1,  
                Mapper<LongWritable, Text, Bean, NullWritable>.Context context)  
                throws IOException, InterruptedException {  
              
            String line = v1.toString();  
            String[] fields = StringUtils.split(line, "\t");  
            String carName = fields[0];
            long sum = Long.parseLong(fields[1]);  
  
            context.write(new Bean(carName,sum),NullWritable.get());  
        }  
    }  
  
    public static class SortReducer extends  
            Reducer<Bean, NullWritable, Text, Bean> {  
        @Override  
        protected void reduce(Bean k2, Iterable<NullWritable> v2s,  
                Reducer<Bean, NullWritable, Text, Bean>.Context context)  
                throws IOException, InterruptedException {  
				
            String carName = k2.getCarName();  
            context.write(new Text(carName), k2);  
			
        }  
    }  
  
    public static void main(String[] args) throws IOException,  
            ClassNotFoundException, InterruptedException {  
  
        Configuration conf = new Configuration();  
        Job job = Job.getInstance(conf);  
  
        job.setJarByClass(SortMapReduce.class);  
  
        job.setMapperClass(SortMapper.class);  
        job.setReducerClass(SortReducer.class);  
  
        job.setMapOutputKeyClass(Bean.class);  
        job.setMapOutputValueClass(NullWritable.class);  
  
        job.setOutputKeyClass(Text.class);  
        job.setOutputValueClass(Bean.class);  
  
        FileInputFormat.setInputPaths(job, new Path(args[0]));  
        FileOutputFormat.setOutputPath(job, new Path(args[1]));  
  
        System.exit(job.waitForCompletion(true) ? 0 : 1);  
    }  
}  

二、二次排序

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

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
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.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class SecondSort  extends Configured implements Tool{

	public static void main(String[] args) throws Exception {
		ToolRunner.run(new SecondSort(), args);
	}

	@Override
	public int run(String[] args) throws Exception {
		Configuration conf = getConf();
		@SuppressWarnings("deprecation")
		Job job = new Job(conf);
		job.setJarByClass(getClass());
		
		FileInputFormat.addInputPath(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		
		job.setMapperClass(SortMapper.class);
		job.setReducerClass(SortReducer.class);
		
		job.setOutputKeyClass(MyPairWritable.class);
		job.setOutputValueClass(NullWritable.class);
		
		job.setSortComparatorClass(PairKeyComparator.class);
		
		job.waitForCompletion(true);
		return 0;
	}
}

class SortMapper extends Mapper<LongWritable, Text, MyPairWritable, NullWritable>{
	MyPairWritable pair= new MyPairWritable();
	protected void map(LongWritable key, Text value, Context context) throws java.io.IOException ,InterruptedException {		
		String[] strs = value.toString().split(" ");
		Text keyy = new Text(strs[0]);
		IntWritable valuee = new IntWritable(Integer.parseInt(strs[1]));
		pair.set(keyy, valuee);
		context.write(pair, NullWritable.get());
	};
}

class SortReducer extends Reducer<MyPairWritable, NullWritable,MyPairWritable, NullWritable>{
	protected void reduce(MyPairWritable key, java.lang.Iterable<NullWritable> values, Context context) throws IOException ,InterruptedException {
		context.write(key, NullWritable.get());
		
	};
}

class PairKeyComparator extends WritableComparator{

	public  PairKeyComparator() {
		super(MyPairWritable.class,true);
	}
	@SuppressWarnings("rawtypes")
	@Override
	public int compare(WritableComparable a, WritableComparable b) {
		
		MyPairWritable p1 = (MyPairWritable)a;
		MyPairWritable p2 = (MyPairWritable)b;
		if(!p1.getFirst().toString().equals(p2.getFirst().toString())){
			return p1.first.toString().compareTo(p2.first.toString());
		}else {
			return p1.getSecond().get() - p2.getSecond().get();
		}
	}
}

class MyPairWritable implements WritableComparable<MyPairWritable>{
	Text first;
	IntWritable second;
	
    public void set(Text first, IntWritable second){
        this.first = first;
        this.second = second;
    }
    public Text getFirst(){
        return first;
    }
    public IntWritable getSecond(){
        return second;
    }
	
	@Override
	public void readFields(DataInput in) throws IOException {
		first = new Text(in.readUTF());
		second = new IntWritable(in.readInt());
	}

	@Override
	public void write(DataOutput out) throws IOException {
		out.writeUTF(first.toString());
		out.writeInt(second.get());
	}

	@Override
	public int compareTo(MyPairWritable o) {
		if(this.first != o.getFirst()){
			return this.first.toString().compareTo(o.first.toString());
		}else if(this.second != o.getSecond()){
			return this.second.get() - o.getSecond().get();
		}
		else	return 0;
	}
	
	@Override
	public String toString() {
		return first.toString() + " " + second.get();
	}
	
	@Override
	public boolean equals(Object obj) {
		MyPairWritable temp = (MyPairWritable)obj;
		return first.equals(temp.first) && second.equals(temp.second);
	}
	
	@Override
	public int hashCode() {
		return first.hashCode() * 163 + second.hashCode();
	}
}

GitHub ：Sort