package com.isea.mapreduce;

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

import java.io.IOException;

public class WordCountDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {

        args = new String[]{"G:/input/input1/wordcount.txt","g:/output/output1"};

        //获取Job的配置信息
        Configuration configuration = new Configuration();

        //获取job
        Job job = Job.getInstance(configuration);

        //设置jar包的加载路径
        job.setJarByClass(WordCountDriver.class);

        //关联Mapper和Reducer的逻辑类
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);

        //设置Mapper的输出的key和value的类型
        job.setMapOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        //设置最后的输出的key和value的类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        //设置输入输出路径
        FileInputFormat.setInputPaths(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));

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