Hdoop——代码统计文本单词

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;;
import org.apache.hadoop.mapreduce.Job;

import java.io.IOException;


public class WordCount {
    public static void main(String[] args) throws InterruptedException, IOException, ClassNotFoundException {
        //定义配置对象
        Configuration conf=new Configuration();
        //定义一个工作任务对象
        Job job=Job.getInstance(conf);

        //获取map阶段的一个对象
        job.setMapperClass(WordCountMap.class);
        //指定map阶段的一个输出key
        job.setMapOutputKeyClass(Text.class);
        //指定map阶段输出的values类型
        job.setMapOutputValueClass(IntWritable.class);
        //map阶段的输入文件
        FileInputFormat.setInputPaths(job,new Path("C:\\Users\\抱抱\\Desktop\\aaa.txt"));
        job.setJarByClass(WordCount.class);
        //指定Reduce的类
        job.setReducerClass(WordCountReduce.class);
        //指定reduce阶段的一个输出key
        job.setOutputKeyClass(Text.class);
        //指定reduce阶段输出的values类型
        job.setOutputValueClass(IntWritable.class);
        //指定reduce阶段的输出文件
        FileOutputFormat.setOutputPath(job,new Path("C:\\Users\\抱抱\\Desktop\\bbb"));

        //submit
        job.waitForCompletion(true);
    }
}