大数据入门——对WordCount的改进

package com.imooc.hadoop.mapreduce;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
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;

/**
 * 使用MapReduce开发WordCount应用程序
 */
public class CombinerApp {

    /**
     * Map：读取输入的文件
     */
    public static class MyMapper extends Mapper<LongWritable, Text, Text, LongWritable>{

        LongWritable one = new LongWritable(1);

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

            // 接收到的每一行数据
            String line = value.toString();

            //按照指定分隔符进行拆分
            String[] words = line.split(" ");

            for(String word :  words) {
                // 通过上下文把map的处理结果输出
                context.write(new Text(word), one);
            }

        }
    }

    /**
     * Reduce：归并操作
     */
    public static class MyReducer extends Reducer<Text, LongWritable, Text, LongWritable> {

        @Override
        protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {

            long sum = 0;
            for(LongWritable value : values) {
                // 求key出现的次数总和
                sum += value.get();
            }

            // 最终统计结果的输出
            context.write(key, new LongWritable(sum));
        }
    }

    /**
     * 定义Driver：封装了MapReduce作业的所有信息
     */
    public static void main(String[] args) throws Exception{

        //创建Configuration
        Configuration configuration = new Configuration();

        // 准备清理已存在的输出目录
        Path outputPath = new Path(args[1]);
        FileSystem fileSystem = FileSystem.get(configuration);
        if(fileSystem.exists(outputPath)){
            fileSystem.delete(outputPath, true);
            System.out.println("output file exists, but is has deleted");
        }

        //创建Job
        Job job = Job.getInstance(configuration, "wordcount");

        //设置job的处理类
        job.setJarByClass(CombinerApp.class);

        //设置作业处理的输入路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));

        //设置map相关参数
        job.setMapperClass(MyMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);

        //设置reduce相关参数
        job.setReducerClass(MyReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);

        //通过job设置combiner处理类，其实逻辑上和我们的reduce是一模一样的
        job.setCombinerClass(MyReducer.class);

        //设置作业处理的输出路径
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

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

增加了Combiner，为了使程序运行的速度更快。

Combiner运行机制