MapReduce編寫wordcount程序代碼實現(xiàn)

MapReduce經(jīng)典案例代碼（wordcount）

以經(jīng)典的wordcount為例，通過自定義的mapper和reducer來實現(xiàn)單詞計數(shù)

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單詞統(tǒng)計
 */
public class WordCountDemo {

    /**
     * 自定義Mapper繼承：org.apache.hadoop.mapreduce.Mapper，實現(xiàn)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));
            }
        }
    }

    /**
     * 自定義Reducer繼承:org.apache.hadoop.mapreduce.Reducer，實現(xiàn)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啟動類，設(shè)置參數(shù)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目錄下數(shù)據(jù)內(nèi)容

打包項目，執(zhí)行job

hadoop jar fwmagic-wordcount.jar 

執(zhí)行輸出結(jié)果