Hadoop MapReduce WordCount案例

pom.xml

    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>3.1.3</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</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>
    <build>
        <plugins>
            <plugin>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.6.1</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                </configuration>
            </plugin>
        </plugins>
    </build>

log4j.properties

log4j.rootLogger=INFO, stdout  
log4j.appender.stdout=org.apache.log4j.ConsoleAppender  
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout  
log4j.appender.stdout.layout.ConversionPattern=%d %p [%c] - %m%n  
log4j.appender.logfile=org.apache.log4j.FileAppender  
log4j.appender.logfile.File=target/spring.log  
log4j.appender.logfile.layout=org.apache.log4j.PatternLayout  
log4j.appender.logfile.layout.ConversionPattern=%d %p [%c] - %m%n

WordCountMapper

package com.chen.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 outKey = new Text();
    private IntWritable outValue = new IntWritable(1);

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //获取一行
        String line = value.toString();
        //分割
        String[] words = line.split(" ");
        //循环写出
        for (String word : words) {
            //封装
            outKey.set(word);
            //写出
            context.write(outKey, outValue);
        }
    }
}

WordCountReducer

package com.chen.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);

        //写出
        context.write(key,outV);
    }
}

WordCountDriver

package com.chen.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, ClassNotFoundException, InterruptedException {
        //1，获取job
        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);

        //2，设置jar路径(通过本类反射)
        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，设置最终输出的kv类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        //6，设置路径和输出路径
        FileInputFormat.setInputPaths(job, new Path("D:\\chen.txt"));
        FileOutputFormat.setOutputPath(job, new Path("D:\\output\\output"));

        //7，提交job
        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);
    }
}

运行main，计算结果

提交到Linux集群运行

修改WordCountDriver中的输入和输出路径

FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));

用maven打包，修改名称为wc.jar，并拷贝该jar包到Hadoop集群的/opt/module/hadoop-3.1.3

hadoop jar wc.jar com.chen.wordcount.WordCountDriver /input /output

​​http://hadoop100:9870/explorer.html#/​​