MapReduce案例之WordCount

1. 环境准备

在maven项目的pom.xml文件中添加如下依赖

<dependencies>
		<dependency>
			<groupId>junit</groupId>
			<artifactId>junit</artifactId>
			<version>RELEASE</version>
		</dependency>
		<dependency>
			<groupId>org.apache.logging.log4j</groupId>
			<artifactId>log4j-core</artifactId>
			<version>2.8.2</version>
		</dependency>
		<dependency>
			<groupId>org.apache.hadoop</groupId>
			<artifactId>hadoop-common</artifactId>
			<version>2.7.2</version>
		</dependency>
		<dependency>
			<groupId>org.apache.hadoop</groupId>
			<artifactId>hadoop-client</artifactId>
			<version>2.7.2</version>
		</dependency>
		<dependency>
			<groupId>org.apache.hadoop</groupId>
			<artifactId>hadoop-hdfs</artifactId>
			<version>2.7.2</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”，在文件中填入。

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

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

2. 编写程序

（1）编写Mapper类

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;

//map阶段
//KEYIN 输入数据的key
//VALUENIN 输入数据的value
//KEYOUT 输出数据的类型
//VALUEOUT 出书数据的value类型
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 {

        // 1 获取一行
        String line = value.toString();

        //2切割单词
        String[] words = line.split(" ");

        //3循环写出
        for(String word : words){
            //hadoop
            k.set(word);

            context.write(k,v);
        }
    }
}

（2）编写Reducer类

package wordcount;

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

import java.io.IOException;

//KEYIN,VALUEIN map阶段输出的Key，value
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;
        //1累加求和
        for(IntWritable value : values){

            sum += value.get();
        }

        //2写出
        v.set(sum);

        context.write(key,v);
    }
}

（3）编写Driver驱动类

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.Cluster;
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 {

        Configuration conf = new Configuration();
        //1 获取Job对象
        Job job = Job.getInstance(conf);

        //2 设置jar存储位置
        job.setJarByClass(WordcountDriver.class);

        //3 关联Map和Reduce类
        job.setMapperClass(WordcountMapper.class);
        job.setReducerClass(WordcountReducer.class);

        //4 设置Mapper阶段输出数据的key和value类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        //5 设置Reducer阶段输出的Key和value类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        //6 设置输入路径和输出路径
        FileInputFormat.setInputPaths(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));

        //7提交Job
        boolean result = job.waitForCompletion(true);

        System.exit(result ? 0 : 1);
    }
}

3. 本地测试

Idea上运行程序，打开output文件结果如下

4．集群上测试

用maven打jar包，需要添加的打包插件依赖
注意：需要替换为自己工程主类

<build>
		<plugins>
			<plugin>
				<artifactId>maven-compiler-plugin</artifactId>
				<version>2.3.2</version>
				<configuration>
					<source>1.8</source>
					<target>1.8</target>
				</configuration>
			</plugin>
			<plugin>
				<artifactId>maven-assembly-plugin </artifactId>
				<configuration>
					<descriptorRefs>
						<descriptorRef>jar-with-dependencies</descriptorRef>
					</descriptorRefs>
					<archive>
						<manifest>
							<mainClass>wordcount.WordcountDriver</mainClass>
						</manifest>
					</archive>
				</configuration>
				<executions>
					<execution>
						<id>make-assembly</id>
						<phase>package</phase>
						<goals>
							<goal>single</goal>
						</goals>
					</execution>
				</executions>
			</plugin>
		</plugins>
	</build>

（1）将程序打成jar包，然后拷贝到Hadoop集群中
步骤详情：右键->Run as->maven install。等待编译完成就会在项目的target文件夹中生成jar包。如果看不到。在项目上右键-》Refresh，即可看到。修改不带依赖的jar包名称为wc.jar，并拷贝该jar包到Hadoop集群。
（2）启动Hadoop集群
（3）执行WordCount程序

[hadoop@hadoop102 software]$ hadoop jar  wc.jar
 wordcount.WordcountDriver /user/hadoop/input /user/hadoop/output

（4）查看输出结果