hadoop_topn_1120

.xml

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>cn.siit</groupId>
    <artifactId>topn</artifactId>
    <version>1.0-SNAPSHOT</version>

    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.7.4</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.7.4</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>2.7.4</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-jobclient</artifactId>
            <version>2.7.4</version>
        </dependency>

    </dependencies>
</project>

MySort

package s26;

import org.apache.hadoop.io.IntWritable;

public class MySort extends IntWritable.Comparator {

    @Override
    public int compare(byte[] b1, int s1, int l1, byte[] b2, int s2, int l2) {
        return -super.compare(b1, s1, l1, b2, s2, l2);
    }
}

MyMap

package s26;


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 java.io.IOException;

public class MyMap extends Mapper<LongWritable,Text,IntWritable,Text> {

    IntWritable ha_numReal = new IntWritable();
    Text ha_name = new Text();
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        super.map(key, value, context);
        //1.hadoop --> java
        String line = value.toString();
        //2.calc
        String[] info = line.split(" ");
        String name = info[0];
        String num = info[1];

        // 2.1 String --> int
        int numReal = Integer.parseInt(num);

        //3.java --> hadoop
        ha_numReal.set(numReal);
        ha_name.set(name);

        context.write(ha_numReal,ha_name);
    }
}

MyRed

package s26;

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

import java.io.IOException;

public class MyRed extends Reducer<IntWritable,Text,IntWritable,Text> {

    int count = 0;

    @Override
    protected void reduce(IntWritable key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
        super.reduce(key, values, context);
        for (Text t:
             values) {
            // 1. if >= 3
            if(count>=3){
                break;
            }
            context.write(key,t);
            count++;
        }
    }
}

MyJob

package s26;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;

import org.apache.hadoop.io.IntWritable;
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;

public class MyJob {

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

        //1.conf
        Configuration conf = new Configuration();
        conf.set("fs.defaultFS","hdfs://master:9000");

        //2.job
        Job job = Job.getInstance(conf);
        // jar-package
        job.setSortComparatorClass(MySort.class);
        job.setJarByClass(MyJob.class);
        job.setMapperClass(MyMap.class);
        job.setReducerClass(MyRed.class);
        //
        job.setOutputKeyClass(IntWritable.class);
        job.setOutputValueClass(Text.class);
        //3.io
        Path pin = new Path("/sjw");
        Path pout = new Path("/out");
        //delete out
        FileSystem fs = FileSystem.get(conf);
        if(fs.exists(pout)){
            fs.delete(pout,true);
        }
        FileInputFormat.setInputPaths(job,pin);
        FileOutputFormat.setOutputPath(job,pout);
        //4.run
        job.waitForCompletion(true);
    }
}