大数据实训第三天

1.创建项目

创建三个类：
Mapper、Reducer、Main驱动类（需要导入 jar包）

2.代码

    WordMapper.java：

package wordcount;

import java.io.IOException;
import java.util.StringTokenizer;

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

/**
* @author: SuN Binghai
* @Description:
* @date: 2019年9月2日下午4:00:00
* @Filename: WordMapper.java
*/

public class WordMapper extends Mapper<Object, Text, Text, IntWritable> {
   private final static IntWritable one = new IntWritable(1);
   private Text word = new Text();

   // Mapper类的核心方法
   /**
   * key 首字符偏移量
   * value 文件的一行内容
   * context Mapper端的上下文
   * @throws InterruptedException
   * @throws IOException
   */
   public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
       StringTokenizer itr = new StringTokenizer(value.toString()); // 分割输入行为key，默认以空格/回车...分割
       while (itr.hasMoreTokens()) {
           word.set(itr.nextToken());
           context.write(word, one);
       }
   }
}
分析：StringTokenizer itr = new StringTokenizer(value.toString());

    WordReducer.java：

package wordcount;

import java.io.IOException;

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

/**
* @author: Gu Yongtao
* @Description:
* @date: 2018年11月6日下午4:40:16
* @Filename: WordReducer.java
*/

public class WordReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
   private IntWritable result = new IntWritable(); // 记录词的频数

   // Reducer抽象类的核心方法
   public void reduce (Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
       int sum = 0;
       // 遍历values 将 list<value> 叠加
       for (IntWritable value : values) {
           sum += value.get();
       }
       result.set(sum);
       context.write(key, result);
   }
}
    WordMain.java：（IP地址根据自身集群配置）

package wordcount;

import java.io.IOException;

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 org.apache.hadoop.util.GenericOptionsParser;

/**
* @author: Gu Yongtao
* @Description:
* @date: 2018年11月6日下午4:53:59
* @Filename: WordMain.java
*/

public class WordMain {
   public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
       // Configuration类：读取配置文件内容-core-site.xml
       Configuration conf = new Configuration();

       // 读取命令行参数，并设置到conf
       String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

       if (otherArgs.length != 2) { // 输入目录输出目录
           System.err.println("Usage: wordcount <in><out>");
           System.exit(2);
       }

       Job job = new Job(conf, "word count"); // 新建一个job
       job.setJarByClass(WordMain.class); // 设置主类
       job.setMapperClass(WordMapper.class); // 设置Mapper类
       job.setCombinerClass(WordReducer.class); // 设置作业合成类
       job.setReducerClass(WordReducer.class); // 设置Reducer类
       job.setOutputKeyClass(Text.class); // 设置输出数据的关键类
       job.setOutputValueClass(IntWritable.class); // 设置输出值类
       FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
       FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
       System.exit(job.waitForCompletion(true) ? 0 : 1);
   }
}

大数据实训第三天

猜你喜欢