WordCount实现--Hadoop学习笔记

首先添加依赖pom.xml

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>com.meng</groupId>
    <artifactId>hdfs</artifactId>
    <version>1.0-SNAPSHOT</version>

    <dependencies>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.13</version>
        </dependency>

        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-core</artifactId>
            <version>2.12.1</version>
        </dependency>

        <dependency>
            <groupId>org.projectlombok</groupId>
            <artifactId>lombok</artifactId>
            <version>1.16.18</version>
        </dependency>

        <!--hadoop-->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.8.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.8.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.8.2</version>
        </dependency>
    </dependencies>

    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <configuration>
                    <source>6</source>
                    <target>6</target>
                </configuration>
            </plugin>
        </plugins>
    </build>
    
</project>

然后是固定的格式，Mapper、Reducer、主启动类。

Mapper

package 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;

/**
 * @author Administrator
 */
public class WordCountMapper extends Mapper<LongWritable, Text,Text, IntWritable> {
    
    

    Text k = new Text();
    IntWritable v = new IntWritable(1);

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

        String line=value.toString();
        String[] words = line.split("\t");

        for (String word:words){
    
    
            k.set(word);
            context.write(k,v);
        }
    }
}

Reducer

package wordcount;

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

import java.io.IOException;

/**
 * @author Administrator
 */
public class WordCountReducer extends Reducer<Text, IntWritable,Text,IntWritable> {
    
    

    IntWritable v = 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();
        }
        v.set(sum);
        context.write(key,v);
    }
}

Main

package 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;

/**
 * @author Administrator
 */
public class WordCountMain {
    
    
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
    
    
        args=new String[]{
    
    "C:/Users/Administrator/Desktop/test/intputword.txt","C:/Users/Administrator/Desktop/test1/"};
        Configuration conf=new Configuration();

        //获取job对象
        Job job = Job.getInstance(conf);

        //设置jar路径
        job.setJarByClass(WordCountMain.class);

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

        //设置mapper输出key和value类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        //设置最终输出key和value类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        //设置输入输出路径
        FileInputFormat.setInputPaths(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));

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