Hadoop之MapReduce单词计数经典实例

MapReduce实现单词计数示意图

MapReduce实现单词计数实例代码（Java）

①Mapper

import java.io.IOException;

import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class WM extends Mapper<LongWritable, Text, Text, LongWritable> {
    protected void map(LongWritable key, Text value, Context context)
            throws IOException, InterruptedException {

        String line = value.toString();
        String[] words = StringUtils.split(line, " ");
        for (String word : words) {
            context.write(new Text(word), new LongWritable(1));
        }

    }
}

②Reducer

import java.io.IOException;

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

public class WR extends Reducer<Text, LongWritable, Text, LongWritable> {
    protected void reduce(Text word, Iterable<LongWritable> counts,
            Context context) throws IOException, InterruptedException {     
        int counter = 0;

        for (LongWritable count : counts) {
            long i = count.get();
            counter += i;
        }

        context.write(word, new LongWritable(counter));

    }
}

③主程序

import java.io.IOException;

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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.Job;

public class Launcher {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();

        Job job = Job.getInstance(conf);

        job.setMapperClass(WM.class);

        job.setMapOutputKeyClass(Text.class);

        job.setMapOutputValueClass(LongWritable.class);

        job.setReducerClass(WR.class);

        job.setOutputKeyClass(Text.class);

        job.setOutputValueClass(LongWritable.class);

        job.setJarByClass(Launcher.class);

        FileInputFormat.setInputPaths(job, "e://hello//words.txt");

        FileOutputFormat.setOutputPath(job, new Path("e://hello//output"));

        job.waitForCompletion(true);
    }
}