7.编写mapreduce案例

在写一个mapreduce类之前先添加依赖包

<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.it19gong</groupId>
  <artifactId>testmaven</artifactId>
  <version>0.0.1-SNAPSHOT</version>
  <packaging>jar</packaging>

  <name>testmaven</name>
  <url>http://maven.apache.org</url>

  <properties>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
  </properties>

  <dependencies>
    <dependency>
      <groupId>junit</groupId>
      <artifactId>junit</artifactId>
      <version>3.8.1</version>
      <scope>test</scope>
    </dependency>
     <dependency>
            <groupId>jdk.tools</groupId>
            <artifactId>jdk.tools</artifactId>
            <version>1.8</version>
            <scope>system</scope>
         <systemPath>${JAVA_HOME}/lib/tools.jar</systemPath>
    </dependency>
 <dependency>
  <groupId>org.apache.hadoop</groupId>
  <artifactId>hadoop-common</artifactId>
  <version>2.6.0</version>
 </dependency>
   
<dependency>
  <groupId>org.apache.hadoop</groupId>
  <artifactId>hadoop-hdfs</artifactId>
  <version>2.6.0</version>
 </dependency>
 <dependency>
  <groupId>org.apache.hadoop</groupId>
  <artifactId>hadoop-client</artifactId>
  <version>2.6.0</version>
 </dependency>

   <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.6.0</version>
        </dependency>
         
        <dependency>
            <groupId>org.apache.mrunit</groupId>
            <artifactId>mrunit</artifactId>
            <version>1.1.0</version>
            <classifier>hadoop2</classifier>
            <scope>test</scope>
        </dependency>

    <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>2.6.0</version>
        </dependency>
      
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-yarn-api</artifactId>
            <version>2.6.0</version>
        </dependency>
        
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-auth</artifactId>
            <version>2.6.0</version>
        </dependency>
 
       
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-minicluster</artifactId>
            <version>2.6.0</version>
            <scope>test</scope>
        </dependency>
        
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-jobclient</artifactId>
            <version>2.6.0</version>
            <scope>provided</scope>
        </dependency>
 
  </dependencies>
</project>

新建一个WordCountMapper类

 

package com.it19gong.testmaven;

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>{
    @Override
    protected void map(LongWritable key, Text value, Context context)
            throws IOException, InterruptedException
    {
                //拿到一行数据转换为string
                String line = value.toString();
                //将这一行切分出各个单词
                String[] words = line.split(" ");
                //遍历数组，输出<单词，1>
                for(String word:words)
                {
                    context.write(new Text(word), new IntWritable(1));
               }
  }
}

 定义WordCountReducer类

package com.it19gong.testmaven;

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>{
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        //定义一个计数器
        int count = 0;
        //遍历这一组kv的所有v，累加到count中
        for(IntWritable value:values){
            count += value.get();
        }
        context.write(key, new IntWritable(count));
    }
}

定义WordCountRunner类

package com.it19gong.testmaven;

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 WordCountRunner {
    //把业务逻辑相关的信息（哪个是mapper，哪个是reducer，要处理的数据在哪里，输出的结果放哪里……）描述成一个job对象
    //把这个描述好的job提交给集群去运行
    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job wcjob = Job.getInstance(conf);
        //指定我这个job所在的jar包
//        wcjob.setJar("/home/hadoop/wordcount.jar");
        wcjob.setJarByClass(WordCountRunner.class);
        
        wcjob.setMapperClass(WordCountMapper.class);
        wcjob.setReducerClass(WordCountReducer.class);
        //设置我们的业务逻辑Mapper类的输出key和value的数据类型
        wcjob.setMapOutputKeyClass(Text.class);
        wcjob.setMapOutputValueClass(IntWritable.class);
        //设置我们的业务逻辑Reducer类的输出key和value的数据类型
        wcjob.setOutputKeyClass(Text.class);
        wcjob.setOutputValueClass(IntWritable.class);
        
        //指定要处理的数据所在的位置
    //    FileInputFormat.setInputPaths(wcjob, "hdfs://hdp-server01:9000/wordcount/data/big.txt");
        FileInputFormat.setInputPaths(wcjob, new Path(args[0]));
        //指定处理完成之后的结果所保存的位置
    //    FileOutputFormat.setOutputPath(wcjob, new Path("hdfs://hdp-server01:9000/wordcount/output/"));
        FileOutputFormat.setOutputPath(wcjob, new Path(args[1]));
        
        //向yarn集群提交这个job
        boolean res = wcjob.waitForCompletion(true);
        System.exit(res?0:1);
    }
}

打成架包

 

 把打包好的架包上传到集群

 然后在集群上运行一个wordcount小案例

hadoop jar mr.jar  com.it19gong.testmaven.WordCountRunner /wc_input /wc_output