MapReduce使用

maven:

<dependency>
      <groupId>org.apache.hadoop</groupId>
      <artifactId>hadoop-client</artifactId>
      <version>2.7.3</version>
    </dependency>

MapAction

package com.item.test;

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

import java.io.IOException;

public class MapAction extends Mapper<LongWritable, Text, Text, LongWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String[] split = value.toString().split(" ");
        for (String s : split) {
            context.write(new Text(s), new LongWritable(1));
        }
    }
}

ReduceAction

package com.item.test;

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

import java.io.IOException;

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

Action

package com.item.test;

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;

import java.io.IOException;

public class Action {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        job.setJarByClass(Action.class);
        job.setMapperClass(MapAction.class);
        job.setReducerClass(ReduceAction.class);

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

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);

        FileInputFormat.setInputPaths(job,new Path("/abcd/info.txt"));
        FileOutputFormat.setOutputPath(job,new Path("/infos"));

        boolean b = job.waitForCompletion(true);
        System.exit(b?0:1);
    }
}

生成jar包

讲jar放在【/opt/soft/hadoop/share/hadoop/mapreduce】中

预先上传文件作用记录【info.txt】

asdasd asd asdhkajshas jdhasjk djkas hdas hdj sa 
dashkj dajks d jksa hdas hjkd haksj dsa
dsaji djkas  kjdsah jdh askjdhkjash kj
adhjks djak dja hsjkdsakhd 

hadoop fs -mkdir /abcd

hadoop fs -put info.txt /abcd

执行

hadoop jar T9_1.jar com/item.test/Action /abcde/info.txt /infos

查看结果

hadoop fs -cat /infos/part-r-00000