MapReduce 实现 WordCount

Java操作Hadoop

1、Windows安装并配置Hadoop；详情请见【Windows安装并配置Hadoop】

2、打开IDEA创建一个maven项目

3、填好GroupId（包名）、ArtifactId（项目名）

4、选择maven安装路径、maven中sittings.xml文件路径

5、创建完成即可创建相应的Java类

MapReduce 实现 WordCount

在实现java操作Hadoop之前需要先下载maven依赖包 ；

在pom.xml文件中配置依赖项，IDEA会自动下载;

MapReduce需要的依赖包如下

 <dependencies>
    <dependency>
      <groupId>junit</groupId>
      <artifactId>junit</artifactId>
      <version>4.12</version>
      <scope>test</scope>
    </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-auth</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-mapreduce-client-jobclient</artifactId>
      <version>2.6.0</version>
    </dependency>
    <dependency>
      <groupId>org.apache.hadoop</groupId>
      <artifactId>hadoop-mapreduce-client-core</artifactId>
      <version>2.6.0</version>
    </dependency>
  </dependencies>

下载好需要的安装包以后，创建Java类实现文件单词计数；

1、WCMapper 类

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 WCMapper extends Mapper<LongWritable, Text,Text, IntWritable> {

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        System.out.println(key);
        String line=value.toString();
        String[] words=line.split(" ");
        for(String word : words){
            context.write(new Text(word),new IntWritable(1));
        }
    }
}

2、WCPartitioner 类
该类用于手动分区，将较大文件分区执行，提高效率

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

public class WCPartitioner extends Partitioner<Text, IntWritable> {
    @Override
    public int getPartition(Text text, IntWritable intWritable, int i) {
        return Math.abs(text.hashCode()%i);
    }
}

3、WCReduce 类

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

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

4、WCDriver 类

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 WCDriver {
    public static void main(String[] args) throws Exception {
        //1.建立连接
        Configuration cfg=new Configuration();
        Job job=Job.getInstance(cfg,"wc");
        job.setJarByClass(WCDriver.class);
        //2.指定mapper和reduce
        job.setMapperClass(WCMapper.class);
        job.setReducerClass(WCReduce.class);
        //指定mapper输出类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        //指定partitioner
//        job.setNumReduceTasks(4);
//        job.setPartitionerClass(WCPartitioner.class);
        //指定reduce输出类型
        job.setOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        //指定输出路径
        FileInputFormat.setInputPaths(job,new Path("E:/test/settings.txt"));
        FileOutputFormat.setOutputPath(job,new Path("E:/test/M"));
        //3.运行
        boolean result=job.waitForCompletion(true);
        System.out.println(result?"成功":"失败");
        System.exit(result?0:1);
    }
}

运行结果如下

运行成功会生成M文件夹，里面包含读取结果文件

HDFS系统执行java代码

在HDFS系统上执行java实现单词分区；
1、将WCDriver类中的读取文件路径与输出路径修改为传参方式；

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 WCDriver {
    public static void main(String[] args) throws Exception {
        //1.建立连接
        Configuration cfg=new Configuration();
        Job job=Job.getInstance(cfg,"wc");
        job.setJarByClass(WCDriver.class);
        //2.指定mapper和reduce
        job.setMapperClass(WCMapper.class);
        job.setReducerClass(WCReduce.class);
        //指定mapper输出类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        job.setOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        //指定输出路径
        FileInputFormat.setInputPaths(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));
        //3.运行
        boolean result=job.waitForCompletion(true);
        System.out.println(result?"成功":"失败");
        System.exit(result?0:1);
    }
}

2、打jar包

给该项目打一个jar包上传到虚拟机上，然后在虚拟机上执行命令；

hadoop jar test1.jar /test/c.txt /test/Mn

随后就可以在HDFS系统中找到输出结果文件