MapReduce编写wordcount程序代码实现

Posted 2020-12-27

MapReduce经典案例代码（wordcount）

以经典的wordcount为例，通过自定义的mapper和reducer来实现单词计数

package com.fwmagic.mapreduce;

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.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 java.io.IOException;

/**
 * MapReduce单词统计
 */
public class WordCountDemo {

    /**
     * 自定义Mapper继承：org.apache.hadoop.mapreduce.Mapper，实现map方法
     */
    public static class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {

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

    /**
     * 自定义Reducer继承:org.apache.hadoop.mapreduce.Reducer，实现reduce方法
     */
    public static class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        @Override
        protected void reduce(Text key, Iterable<IntWritable> values,
                              Reducer<Text, IntWritable, Text, IntWritable>.Context context)
                throws IOException, InterruptedException {
            int count = 0;
            for (IntWritable writable : values) {
                count += writable.get();
            }
            context.write(key, new IntWritable(count));
        }
    }

    /**
     * job启动类，设置参数并集群中提交job
     * @param args
     * @throws Exception
     */
    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        job.setJarByClass(WordCountDemo.class);

        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        FileInputFormat.setInputPaths(job, new Path("/wordcount/input"));
        FileOutputFormat.setOutputPath(job, new Path("/wordcount/output"));

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

集群中/wordcount/input目录下数据内容

打包项目，执行job

hadoop jar fwmagic-wordcount.jar 

执行输出结果