MapReduce实验——英语单词个数统计实验

英语单词个数统计

Map类

package WordSum_02;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

public class MyMap extends Mapper<LongWritable,Text, NullWritable,LongWritable> {
    @Override
    protected void map(LongWritable key,Text value,Context context) throws IOException, InterruptedException {
        //1 get values string
        String valueString = value.toString();
        //2 split string
        String wArr[] = valueString.split(" ");
        //3 map out key/value
        context.write(NullWritable.get(),new LongWritable(wArr.length));
    }
}

Reduce类

package WordSum_02;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;
import java.util.Iterator;

public class MyReduce extends Reducer<NullWritable, LongWritable,NullWritable,LongWritable> {
    @Override
    protected void reduce(NullWritable key,Iterable<LongWritable> valueIn,Context context) throws IOException, InterruptedException {
        Iterator<LongWritable> it = valueIn.iterator();
        //define sum
        long sum = 0;
        //iterator count arr
        while(it.hasNext()){
            sum += it.next().get();
        }
        context.write(NullWritable.get(),new LongWritable(sum));
    }
}

Job类

package WordSum_02;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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 TestJob {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        //1 get a job
        Job job = Job.getInstance(conf);
        //2 set jar main class
        job.setJarByClass(TestJob.class);
        //3 set map class and reducer class
        job.setMapperClass(MyMap.class);
        job.setReducerClass(MyReduce.class);
        //4 set map reduce output type
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);
        //5 set key/value output file format and input/output path
        FileInputFormat.setInputPaths(job,new Path("file:///simple/wordsum.txt"));
        FileOutputFormat.setOutputPath(job,new Path("file:///simple/result"));
        //6 commit job
        job.waitForCompletion(true);
    }
}