mapduce 入门操作

首先准备程序代码

import java.io.IOException;

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

public class WCMapper  extends Mapper<LongWritable,Text , Text, LongWritable>
{

    @Override
    protected void map(LongWritable key, Text value,Context context)
    {
        //接受value数据
        String line=value.toString();
        //切分数据
        String[] words=line.split(" ");
        //循环
        for(String w : words)
        {
            //出现一次  寄一个1      输出
            try {
                context.write(new Text(w), new LongWritable(1));
            } catch (IOException e) {
                // TODO Auto-generated catch block
                e.printStackTrace();
            } catch (InterruptedException e) {
                // TODO Auto-generated catch block
                e.printStackTrace();
            }

        }
    }

}










import java.io.IOException;

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

public class WCReduce extends Reducer<Text, LongWritable, Text, LongWritable>{

    @Override
    protected void reduce(Text key, Iterable<LongWritable> v2s,Context context)
            throws IOException, InterruptedException {
        //接收数据
        //定义一个计算器
        long  counter =0;
        //循环  v2s
        for(LongWritable i : v2s)
        {
            counter+=i.get();//返回 long 类型
        }
        //输出
        context.write(key,new LongWritable(counter));
    }


}














import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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 WordCount {
    public static void main(String[] args) throws Exception {
        Job job=Job.getInstance(new Configuration());


        //main 所在的类
        job.setJarByClass(WordCount.class);

        job.setMapperClass(WCMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);
        FileInputFormat.setInputPaths(job, new Path("/words.txt"));
        //设置 reducer 相关 属性
        job.setReducerClass(WCReduce.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);
        FileOutputFormat.setOutputPath(job, new Path("/wcout666"));
        job.waitForCompletion(true);
    }

}




<dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.9.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.9.0</version>
        </dependency>

        <!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-mapreduce-client-core -->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>2.9.0</version>
        </dependency>

    </dependencies>

View Code

  main方法的最后一个  waitforcomplete 表示将运行进度等信息及时输出给用户

编译器和集群  jdk版本要一样

maven打包

IDEA

 先添加包文件 
FILE   ------>    Project    Structure   --------->   Artifacts


打包

Build  ------>  Build   Artifact     ----------------> BUILD  生成jar包

运行

Hadoop  jar   xxxx.jar    WordCount