MapReduce本地wordcount案例

Mapper类

将MapTask传入的文本内容按行读入转换成String
根据划分方式将这一行切分成单个单词
将单词输出为 <单词，1>
1）读入转化为string：abc abc abc
2）切分
abc
abc
abc
3）输出：（abc，1）、（abc，1）、（abc，1）

package com.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;

//KEYIN,map阶段输入的key的类型：LongWritable
//VALUE，map阶段输入的value类型：Text
//KEYOUT,map阶段输出的key类ing：Text
//VALUEOUT，map阶段输出的value类型：IntWritable
public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
    private Text outK = new Text();
    private IntWritable outV = new IntWritable(1);//初始化为1，不聚合

    @Override
    protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, IntWritable>.Context context) throws IOException, InterruptedException {
        //获取一行 （abc abc）
        String line = value.toString();
        //切割 根据文本(abc
        //            abc)
        String[] words = line.split(" ");
        //循环写出
        for (String word : words) {
            //封装
            outK.set(word);
            //写出
            context.write(outK, outV);
        }
    }
}

Reducer类

汇总各个key的个数， 输出该key的总次数。
1）汇总 （abc，1）、（abc，1）、（abc，1）
2）输出key总次数 (abc，3)

package com.mapreduce.wordcount;

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

import java.io.IOException;

//KEYIN,reduce阶段输入的key的类型：Text
//VALUE，reduce阶段输入的value类型：IntWritable
//KEYOUT,reduce阶段输出的key类ing：Text
//VALUEOUT，reduce阶段输出的value类型：IntWritable
public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
    IntWritable outV = new IntWritable();

    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException {
        //xx(1,1)
        //累加
        int sum = 0;
        for (IntWritable value : values) {
            sum += value.get();
        }
        outV.set(sum);
        //写出
        context.write(key, outV);
    }
}

Driver类

获取配置信息，获取job对象实例
关联Mapper/Reducer业务类
指定Mapper输出数据的kv类型
指定最终输出的数据的kv类型
指定job的输入原始文件所在目录
指定job的输出结果所在目录
指定本程序的jar包所在的本地路径
提交

package com.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 {

        //获取job
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        //设置jar包路径
        job.setJarByClass(WordCountDriver.class);

        //关联mapper和reducer
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);

        //设置map输出的kv类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        //设置最终输出的kv类型
        job.setOutputKeyClass(Text.class);
        job.setOutputKeyClass(IntWritable.class);

        //设置输入路径和输出路径
        FileInputFormat.setInputPaths(job, new Path("D:\\input"));
        FileOutputFormat.setOutputPath(job, new Path("D:\\output\\output4"));

        //提交job
        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);

    }
}

根据源码，将verbose置为true，可以收集更多信息