一、分析数据处理的过程

二、程序代码

2.1 main程序

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;

public class SalaryTotalMain {
    public static void main(String[] args) throws Exception {
        //1、创建任务Job，并且指定任务的入口
        Job job = Job.getInstance(new Configuration());
        job.setJarByClass(SalaryTotalMain.class);

        //2、指定任务的Map，Map的输出类型
        job.setMapperClass(SalaryTotalMapper.class);
        job.setMapOutputKeyClass(IntWritable.class); //k2
        job.setMapOutputValueClass(IntWritable.class); //v2
        
        //3、指定任务的Reduce，Reduce的输出类型
        job.setReducerClass(SalaryTotalReducer.class);
        job.setOutputKeyClass(IntWritable.class); //k4
        job.setOutputValueClass(IntWritable.class); //v4

        //4、指定任务的输入路径和输出路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        //5、执行任务
        job.waitForCompletion(true);
    }
}

2.2 Map程序

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

import java.io.IOException;

public class SalaryTotalMapper extends Mapper<LongWritable, Text,IntWritable, IntWritable> {


    @Override
    protected void map(LongWritable key1, Text value1, Context context) throws IOException, InterruptedException {
        /*
        context代表Map的上下文
        上文：DHFS的输入
        下文：Reduce
         */
        String data =value1.toString();
        String [] words = data.split(",");
        for ( String w:words){
            context.write(new IntWritable(Integer.parseInt(words[7])),new IntWritable(Integer.parseInt(words[5])));
        }

    }
}

2.1 Reduce程序

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

public class SalaryTotalReducer extends Reducer<IntWritable, IntWritable,IntWritable,IntWritable> {
    @Override
    protected void reduce(IntWritable k3, Iterable<IntWritable> v3, Context context) throws IOException, InterruptedException {
        int total = 0;
        for (IntWritable v:v3){
            total += v.get();
        }
        context.write(k3,new IntWritable(total));

    }
}