在hadoop集群中用java代码实现单词的统计--------MapReduce

单词统计的例子：
hello,world
hello,bigdata
bigdata,is,very,good

代码实现：

package shujia;

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;

public class MR_WC_Demo {
        //第一阶段，map阶段
        public static class MyMap extends Mapper<LongWritable,Text,Text,LongWritable> {
            @Override
            protected void map(LongWritable k1, Text v1, Context context) throws IOException, InterruptedException {
                //切分数据，这里处理的是一条数据
                //将数据转换成String
                String string = v1.toString();
                //将一行数据切分成数组。
                String[] words = string.split(",");
                for (String string2 : words) {
                    //组装k2和v2
                    String kstring = string;
                    long v2 = 1L;

                    //将数据写出到磁盘
                    context.write(new Text(kstring), new LongWritable(v2));
                    //根据Key进行排序合并，相同key的数据写出到一起
                }
            }
        }
 //====================================shuffle=================================
 //相同的key数据拉取到同一个reduce（函数）中，分组

         //第二阶段：reduce阶段
         public static class MyReduce extends Reducer<Text,LongWritable,Text,LongWritable>{
                    //重写reduce函数，一组数据调用一次reduce函数

             @Override
             protected void reduce(Text k2, Iterable<LongWritable> v2s, Context context) throws IOException, InterruptedException {
                 long s = 0L;
                 for (LongWritable longWritable:v2s){
                     //迭代求和
                     s+=longWritable.get();
                 }
                 //将结果输出，写到hdfs上
                 context.write(k2,new LongWritable(s));
             }

             //组装MapReduce
             public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
                 //获取配置项
                 Configuration conf = new Configuration();
                 //获取job
                 Job job = Job.getInstance(conf, MR_WC_Demo.class.getSimpleName());
                 //设置打jar包的类
                 job.setJarByClass(MR_WC_Demo.class);

                 //设置输入hdfs文件路径：FileInputFormat
                 FileInputFormat.addInputPath(job,new Path(args[0]));

                 //指定map和reduce的序列化类型以及人任务类
                 job.setMapperClass(MyMap.class);
                 job.setMapOutputKeyClass(LongWritable.class);
                 job.setMapOutputValueClass(Text.class);

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

                 //指定输出hdfs的路径
                 FileOutputFormat.setOutputPath(job,new Path(args[1]));

                 //提交任务
                 job.waitForCompletion(true);
             }
         }
}