MapReduce之WordCount本地测试

1）需求

在给定的文本文件中统计输出每一个单词出现的总次数。
（1）输入数据
在这里插入图片描述

2）期望输出数据

banzhang 1
cls 2
hadoop 1
jiao 1
ss 2
xue 1

2）需求分析

按照MapReduce编程规范，分别编写Mapper，Reducer，Driver。

3）环境准备

（1）创建maven工程，MapReduceDemo
（2）在pom.xml文件中添加如下依赖

<dependencies><dependency><groupId>org.apache.hadoop</groupId><artifactId>hadoop-client</artifactId><version>3.1.3</version></dependency><dependency><groupId>junit</groupId><artifactId>junit</artifactId><version>4.12</version></dependency><dependency><groupId>org.slf4j</groupId><artifactId>slf4j-log4j12</artifactId><version>1.7.30</version></dependency>
</dependencies>

（2）在项目的src/main/resources目录下，新建一个文件，命名为“log4j.properties”，在

（3）创建包名：com.xiaoming.mapreduce.wordcount

4）编写程序

（1）编写Mapper类

import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable>{Text k = new Text();IntWritable v = new IntWritable(1);@Overrideprotected void map(LongWritable key, Text value, Context context)	throws IOException, InterruptedException {// 1 获取一行String line = value.toString();// 2 切割String[] words = line.split(" ");// 3 输出for (String word : words) {k.set(word);context.write(k, v);}}
}

（2）编写Reducer类

import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable>{int sum;
IntWritable v = new IntWritable();@Overrideprotected void reduce(Text key, Iterable<IntWritable> values,Context context) throws IOException, InterruptedException {// 1 累加求和sum = 0;for (IntWritable count : values) {sum += count.get();}// 2 输出v.set(sum);context.write(key,v);}
}

（3）编写Driver驱动类

import java.io.IOException;
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;public class WordCountDriver {public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {// 1 获取配置信息以及获取job对象Configuration conf = new Configuration();Job job = Job.getInstance(conf);// 2 关联本Driver程序的jarjob.setJarByClass(WordCountDriver.class);// 3 关联Mapper和Reducer的jarjob.setMapperClass(WordCountMapper.class);job.setReducerClass(WordCountReducer.class);// 4 设置Mapper输出的kv类型job.setMapOutputKeyClass(Text.class);job.setMapOutputValueClass(IntWritable.class);// 5 设置最终输出kv类型job.setOutputKeyClass(Text.class);job.setOutputValueClass(IntWritable.class);// 6 设置输入和输出路径FileInputFormat.setInputPaths(job, new Path(args[0]));FileOutputFormat.setOutputPath(job, new Path(args[1]));// 7 提交jobboolean result = job.waitForCompletion(true);System.exit(result ? 0 : 1);}
}