hadoop示例WordCount（代码）

hadoop示例WordCount（代码）

1. hapoop-2.7.3  解压，加入环境变量
2. 下载  hadoo2.7.3的hadoop.dll和winutils.exe 文件
3. hadop.dll 文件放入 C:\Windows\System32  ，winutils.exe放入  
               E:\workspace\java\  hadoop-2.7.3\bin目录下，防止在windows下 莫名其妙的报错
4. 

pom.xml

  4.0.0

  com.kay
  hadoopDemo01
  1.0-SNAPSHOT
  jar

  hadoopDemo01
  https://maven.apache.org

  UTF-8

  
    
      junit
      junit
      4.12
    
    
      org.apache.hadoop
      hadoop-client
      2.7.3
    
    
      org.apache.hadoop
      hadoop-common
      2.7.3
    
    
      org.apache.hadoop
      hadoop-hdfs
      2.7.3
    
  

WordCountMapper.java

package com.kay;

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 org.apache.hadoop.util.StringUtils;

import java.io.IOException;

/**
 * Created by kay on 2017/12/12.
 */
public class WordCountMapper extends Mapper{
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String[] words = StringUtils.split(value.toString(), ' ');
        for (String w : words) {
            context.write(new Text(w), new IntWritable(1));
        }
    }
}

WordCountReducer.java

package com.kay;

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

import java.io.IOException;

/**
 * Created by kay on 2017/12/12.
 */
public class WordCountReducer extends Reducer{
    @Override
    protected void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException {
        int sum = 0;
        for (IntWritable i : values) {
            sum = sum + i.get();
        }
        context.write(key, new IntWritable(sum));
    }
}

App.java

package com.kay;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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;

/**
 * Hello world!
 *
 */
public class App {

    public static void main( String[] args ){
        //若hadoop未加入环境变量可以加上这句
        //System.setProperty("hadoop.home.dir", "E:\\workspace\\java\\hadoop-2.7.3");
        Configuration config = new Configuration();
        //设置hdfs的通讯地址
        config.set("fs.defaultFS", "hdfs://192.168.1.200:9000");
        //设置RN的主机
        config.set("yarn.resourcemanager.hostname", "master");

        try {
            FileSystem fs = FileSystem.get(config);

            Job job = Job.getInstance(config);
            job.setJarByClass(App.class);

            job.setJobName("wc");

            job.setMapperClass(WordCountMapper.class);
            job.setReducerClass(WordCountReducer.class);

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

//输入路径
            FileInputFormat.addInputPath(job, new Path("/user/test"));
//输出路径
            Path outpath = new Path("/user/out");
            if (fs.exists(outpath)) {
                fs.delete(outpath, true);
            }
            FileOutputFormat.setOutputPath(job, outpath);

            boolean f = job.waitForCompletion(true);
            if (f) {
                System.out.println("job任务执行成功");
            }
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}