一个简单的WordCount程序

package com.demo.hadoop.mapreduce;


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.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

/**
 * MapReduce开发WordCount应用程序
 * */
public class WordCountApp {

    /**
     *
     * Map:读取输入的文件
     * */
    public static class MyMapper extends Mapper<LongWritable, Text, Text, LongWritable> {
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            LongWritable one =  new LongWritable(1);

            String line = value.toString();
            String[] words = line.split(" ");

            for(String word: words) {
                context.write(new Text(word), one);
            }
        }
    }

    /**
     * Reduce
     * */
    public  static class MyReducer extends Reducer<Text, LongWritable, Text, LongWritable> {
        @Override
        protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {

            long sum =  0;
            for(LongWritable value: values) {
                sum += value.get();
            }

            context.write(key, new LongWritable(sum));
        }
    }

    /**
     * 定义Driver类
     * */

    public static void main(String[] args) throws Exception {
        Configuration configuration = new Configuration();

        Job job = Job.getInstance(configuration, "wordcount");


        job.setJarByClass(WordCountApp.class);

        FileInputFormat.setInputPaths(job, new Path(args[0]));

        job.setMapperClass(MyMapper.class);

        job.setMapOutputKeyClass(Text.class);

        job.setMapOutputValueClass(LongWritable.class);

        job.setReducerClass(MyReducer.class);

        job.setOutputKeyClass(Text.class);

        job.setOutputValueClass(LongWritable.class);

        FileOutputFormat.setOutputPath(job, new Path(args[1]));

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



启动hadoop
pumbaa@pumbaapc:~/hadoopapp/hadoop-2.6.0-cdh5.7.0/sbin$ ./start-all.sh

打jar包
pumbaa@pumbaapc:~/IdeaProjects/hadooptrain$ mvn clean package

把target下面的包copy到其他目录文件夹
pumbaa@pumbaapc:~/IdeaProjects/hadooptrain/target$ scp hadoop-train-1.0.jar /home/pumbaa/hadooplib

运行jar包
hadoop jar hadoop-train-1.0.jar  com.demo.hadoop.mapreduce.WordCountApp hdfs://pumbaapc:8020/hello.txt hdfs://pumbaapc:8020/output/wc

查看输出文件
hadoop fs -text /output/wc/part-r-00000

pumbaa@pumbaapc:~/hadooplib$ hadoop fs -text /output/wc/part-r-00000
18/03/04 17:15:35 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
hadoop    2
hdfs    2
hello    2
welcome    2




利用partitioner把相似的块分配到同一个reducer中

package com.demo.hadoop.mapreduce;

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.Mapper;
import org.apache.hadoop.mapreduce.Partitioner;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

public class PartitionerApp {


    /**
     *
     * Map:读取输入的文件
     * */
    public static class MyMapper extends Mapper<LongWritable, Text, Text, LongWritable> {
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            LongWritable one =  new LongWritable(1);

            String line = value.toString();
            String[] words = line.split(" ");
            context.write(new Text(words[0]), new LongWritable(Long.parseLong(words[1])));

        }
    }

    /**
     * Reduce
     * */
    public  static class MyReducer extends Reducer<Text, LongWritable, Text, LongWritable> {
        @Override
        protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {

            long sum =  0;
            for(LongWritable value: values) {
                sum += value.get();
            }

            context.write(key, new LongWritable(sum));
        }
    }


    public static class Mypartitioner extends Partitioner<Text, LongWritable> {
        @Override
        public int getPartition(Text text, LongWritable longWritable, int numPartitions) {
            if(text.toString().equals("xiaomi")) {
                return 0;
            }else if(text.toString().equals("huawei")) {
                return 1;
            }else if(text.toString().equals("iphone7")) {
                return 2;
            }else {
                return 3;
            }
        }
    }

    /**
     * 定义Driver类
     * */

    public static void main(String[] args) throws Exception {
        Configuration configuration = new Configuration();

        Job job = Job.getInstance(configuration, "wordcount");


        job.setJarByClass(PartitionerApp.class);

        FileInputFormat.setInputPaths(job, new Path(args[0]));

        job.setMapperClass(PartitionerApp.MyMapper.class);

        job.setMapOutputKeyClass(Text.class);

        job.setMapOutputValueClass(LongWritable.class);

        job.setReducerClass(PartitionerApp.MyReducer.class);

        job.setOutputKeyClass(Text.class);

        job.setOutputValueClass(LongWritable.class);



        //job.setCombinerClass(MyReducer.class);



        job.setPartitionerClass(Mypartitioner.class);
        job.setNumReduceTasks(4);


        FileOutputFormat.setOutputPath(job, new Path(args[1]));

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