hadoop-mapreduce--统计单词数量

Posted 2020-10-15 dyh004

编写map程序

package com.cvicse.ump.hadoop.mapreduce.map;

import java.io.IOException;

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

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

    @Override
    protected void map(LongWritable key, Text value, Context context)
            throws IOException, InterruptedException {
        
        String line = value.toString();
        String[] words = line.split(" ");
        for(String word:words){
            context.write(new Text(word), new IntWritable(1));
        }
        
    }

}

编写reduce程序

package com.cvicse.ump.hadoop.mapreduce.reduce;

import java.io.IOException;

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

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

    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context)
            throws IOException, InterruptedException {
        
        Integer count = 0;
        for(IntWritable value:values){
            count+=value.get();
        }
        
        context.write(key, new IntWritable(count));
        
    }

}

 

编写main函数

package com.cvicse.ump.hadoop.mapreduce;

import org.apache.hadoop.conf.Configuration;
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 com.cvicse.ump.hadoop.mapreduce.map.WordCountMap;
import com.cvicse.ump.hadoop.mapreduce.reduce.WordCountReduce;

public class WordCount {
    
    public static void main(String[] args) throws Exception {
        
        Configuration conf = new Configuration();
        
        Job job = Job.getInstance(conf,"wordCount");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(WordCountMap.class);
        job.setReducerClass(WordCountReduce.class);
        
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        
        boolean bb = job.waitForCompletion(true);
        if(!bb){
            System.out.println("wrodcount task fail!");
        }else{
            System.out.println("wordcount task success!");
        }
        
    }

}

 

把wordcount.txt放在hdfs的/dyh/data/input/目录下

执行：hadoop jar hdfs.jar com.cvicse.ump.hadoop.mapreduce.WordCount /dyh/data/input/wordcount.txt /dyh/data/output/1