Hadoop Demo(一)【统计文件中单词出现的频率】

TokenizerMapper.java

package com.hadoop.demo1.word;

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

import java.io.IOException;
import java.util.StringTokenizer;

/**
 * @Description: Map类
 */
public class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {
    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();

    @Override
    protected void map(Object key, Text value, Context context) throws IOException, InterruptedException {
        StringTokenizer itr = new StringTokenizer(value.toString());
        while (itr.hasMoreTokens()) {
            word.set(itr.nextToken());
            context.write(word, one);
        }
    }
}

IntSumReducer.java

package com.hadoop.demo1.word;

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

import java.io.IOException;

/**
 * @Description: Reducer
 */
public class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
    private IntWritable result = new IntWritable();

    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int sum = 0;
        for (IntWritable i : values) {
            sum += i.get();
        }
        result.set(sum);
        context.write(key, result);
    }
}

Main.java

package com.hadoop.demo1.word;

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 java.io.IOException;

/**
 * @Description: 统计单词中出现的频率
 */
public class Main {
    public static void main(String[] args) {
        Configuration conf = new Configuration();

        try {
            Job job = Job.getInstance(conf, "Words");
            job.setJarByClass(Main.class);
            job.setMapperClass(TokenizerMapper.class);
            job.setReducerClass(IntSumReducer.class);
            job.setCombinerClass(IntSumReducer.class);
            job.setMapOutputKeyClass(Text.class);
            job.setMapOutputValueClass(IntWritable.class);

            FileInputFormat.addInputPath(job, new Path("hdfs://localhost:9000/demo/data/hadoop/input"));
            FileOutputFormat.setOutputPath(job, new Path("hdfs://localhost:9000/demo/data/hadoop/output_words"));
            System.exit(job.waitForCompletion(true) ? 0 : 1);
        } catch (IOException e) {
            e.printStackTrace();
        } catch (InterruptedException e) {
            e.printStackTrace();
        } catch (ClassNotFoundException e) {
            e.printStackTrace();
        }
    }
}

运行结果如图:

---

---