一个Mapreduce案例

一个统计文件中单词出现次数的Mapreduce案例

WordCountMapper.java中的内容：

package com.jxd.mapreduce.wordcount;

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

import java.io.IOException;

public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
    private Text outK = new Text();
    private IntWritable outV = new IntWritable(1);
    @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) {
            outK.set(word);
            context.write(outK, outV);
        }
    }
}

WordCountReducer.java中的内容

package com.jxd.mapreduce.wordcount;

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

import java.io.IOException;

public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
    private IntWritable outV = new IntWritable();
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int sum = 0;
        for (IntWritable value : values) {
            sum += value.get();
        }
        outV.set(sum);
        context.write(key, outV);
    }
}

WordCountDriver.java中的内容：

package com.jxd.mapreduce.wordcount;

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;

public class WordCountDriver {
    public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
        //1. 获取job
        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);
        //2. 设置jar包路径
        job.setJarByClass(WordCountDriver.class);
        //3. 关联mapper和reducer
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);
        //4. 设置map输出的kv类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        //5. 设置最终的kv类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        //6. 设置输入路径和输出路径
        FileInputFormat.setInputPaths(job, new Path("G:\\input\\inputword"));
        FileOutputFormat.setOutputPath(job, new Path("G:\\output\\WordCount"));
        //7. 提交job
        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);
    }
}