wordcount在mapreduce的例子

1.启动集群

2.创建项目

 项目结构为:

3.pom.xml文件为

<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/maven-v4_0_0.xsd">
  <modelVersion>4.0.0</modelVersion>
  <groupId>org.example</groupId>
  <artifactId>mapReduceTest</artifactId>
  <packaging>war</packaging>
  <version>1.0-SNAPSHOT</version>
  <name>mapReduceTest Maven Webapp</name>
  <url>http://maven.apache.org</url>
  <dependencies>
    <dependency>
      <groupId>junit</groupId>
      <artifactId>junit</artifactId>
      <version>3.8.1</version>
      <scope>test</scope>
    </dependency>

    <dependency>
      <groupId>org.apache.logging.log4j</groupId>
      <artifactId>log4j-slf4j-impl</artifactId>
      <version>2.12.0</version>
    </dependency>
    <dependency>
      <groupId>org.apache.hadoop</groupId>
      <artifactId>hadoop-common</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>org.apache.hadoop</groupId>
      <artifactId>hadoop-mapreduce-client-core</artifactId>
      <version>3.1.3</version>
    </dependency>

    <dependency>
      <groupId>org.apache.hadoop</groupId>
      <artifactId>hadoop-client</artifactId>
      <version>3.1.3</version>
      <exclusions>
        <!-- ’d Log4j 1.x -->
        <exclusion>
          <groupId>log4j</groupId>
          <artifactId>log4j</artifactId>
        </exclusion>
        <!-- ’d SLF4J ’ Log4j 1.x „e¥ -->
        <exclusion>
          <groupId>org.slf4j</groupId>
          <artifactId>slf4j-log4j12</artifactId>
        </exclusion>
      </exclusions>
    </dependency>
  </dependencies>
  <build>
    <finalName>mapReduceTest</finalName>
  </build>
</project>

4.WordCountMapper代码为

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> {
    @Override
    protected void map(LongWritable key1,Text value1,Context context) throws IOException, InterruptedException {
        String data=value1.toString();
        String[] words=data.split(" ");
        for(String w:words){
            context.write(new Text(w),new IntWritable(1));
        }
    }

}

5.WordCountReduce代码为:

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

import java.io.IOException;

public class WordCountReduce extends Reducer<Text,IntWritable,Text,IntWritable> {
    @Override
    protected void reduce(Text k3,Iterable<IntWritable> v3,Context context) throws IOException, InterruptedException {
        int total=0;
        for(IntWritable v:v3){
            total+=v.get();
        }
        context.write(k3,new IntWritable(total));
    }
}

6.WordCountMain代码为:

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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.Job;

public class WordCountMain {
    public static void main(String[] args) throws Exception {
        Job job = Job.getInstance(new Configuration());
        job.setJarByClass(WordCountMain.class);

        job.setMapperClass(WordCountMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        job.setReducerClass(WordCountReduce.class);
        job.setOutputKeyClass(Text.class);

        job.setOutputValueClass(IntWritable.class);

        FileInputFormat.setInputPaths(job, new Path("hdfs://172.18.0.2:9000/input"));
        FileOutputFormat.setOutputPath(job, new Path("hdfs://172.18.0.2:9000/WordCountOutput"));

        job.waitForCompletion(true);
    }
}

7.测试结果

本地测试:

运行这个main,可以看到

用shell脚本可以查看

 

 集群测试:

pom.xml需要设置build部分

<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/maven-v4_0_0.xsd">
  <modelVersion>4.0.0</modelVersion>
  <groupId>org.example</groupId>
  <artifactId>mapReduceTest</artifactId>
  <packaging>jar</packaging>
  <version>1.0-SNAPSHOT</version>
  <name>mapReduceTest Maven Webapp</name>
  <url>http://maven.apache.org</url>
  <dependencies>
    <dependency>
      <groupId>junit</groupId>
      <artifactId>junit</artifactId>
      <version>3.8.1</version>
      <scope>test</scope>
    </dependency>

    <dependency>
      <groupId>org.apache.logging.log4j</groupId>
      <artifactId>log4j-slf4j-impl</artifactId>
      <version>2.12.0</version>
    </dependency>
    <dependency>
      <groupId>org.apache.hadoop</groupId>
      <artifactId>hadoop-common</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>org.apache.hadoop</groupId>
      <artifactId>hadoop-mapreduce-client-core</artifactId>
      <version>3.1.3</version>
    </dependency>

    <dependency>
      <groupId>org.apache.hadoop</groupId>
      <artifactId>hadoop-client</artifactId>
      <version>3.1.3</version>
      <exclusions>
        <!-- ’d Log4j 1.x -->
        <exclusion>
          <groupId>log4j</groupId>
          <artifactId>log4j</artifactId>
        </exclusion>
        <!-- ’d SLF4J ’ Log4j 1.x „e¥ -->
        <exclusion>
          <groupId>org.slf4j</groupId>
          <artifactId>slf4j-log4j12</artifactId>
        </exclusion>
      </exclusions>
    </dependency>
  </dependencies>
  <build>
    <finalName>mapReduceTest</finalName>
    <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>WordCountMain</mainClass>
          </manifest>
        </archive>
      </configuration>
      <executions>
        <execution>
          <id>make-assembly</id>
          <phase>package</phase>
          <goals>
            <goal>single</goal>
          </goals>
        </execution>
      </executions>
    </plugin>
    </plugins>
  </build>
</project>
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.Job;

public class WordCountMain {
    public static void main(String[] args) throws Exception {
        Job job = Job.getInstance(new Configuration());
        job.setJarByClass(WordCountMain.class);

        job.setMapperClass(WordCountMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        job.setReducerClass(WordCountReduce.class);
        job.setOutputKeyClass(Text.class);

        job.setOutputValueClass(IntWritable.class);

//        FileInputFormat.setInputPaths(job, new Path("hdfs://172.18.0.2:9000/input"));
//        FileOutputFormat.setOutputPath(job, new Path("hdfs://172.18.0.2:9000/WordCountOutput"));

        FileInputFormat.setInputPaths(job, new Path(args[1]));
        FileOutputFormat.setOutputPath(job, new Path(args[2]));


        job.waitForCompletion(true);
    }
}

使用mvn生成jar包

生成了target的文件

使用下面的命令,将cg服务器的jar包上传到master上面。

# 确保你已在本地(cg)操作,直接使用本地路径
scp /root/IdeaProjects/mapReduceTest/target/mapReduceTest-jar-with-dependencies.jar root@172.18.0.2:/usr/local/hadoop

密码是:83953588abc

在master上运行代码

hadoop jar mapReduceTest-jar-with-dependencies.jar /input /wcoutputhdfs1

hadoop jar mapReduceTest.jar WordCountMain /input /wcoutputhdfs1

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值