1、PVStartV2App.java

src/main/java/project/mrv2/PVStartV2App.java

升级之处:数据输入来源为input/etl,即ETLApp.java的输出,即不读取全部原始数据,只读取处理后的数据。

package project.mrv2;

/*
 * 第二版本浏览量的统计
 */

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
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 PVStartV2App {

    public static void main(String[] args) throws Exception{

        Configuration configuration = new Configuration();

        FileSystem fileSystem = FileSystem.get(configuration);
        Path outputPath = new Path("output/v2/pvstart");
        if (fileSystem.exists(outputPath)){
            fileSystem.delete(outputPath, true);
        }

        Job job = Job .getInstance(configuration);
        job.setJarByClass(PVStartV2App.class);

        job.setMapperClass(MyMapper.class);
        job.setReducerClass(MyReducer.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);

        job.setOutputKeyClass(NullWritable.class);
        job.setOutputValueClass(LongWritable.class);

        FileInputFormat.setInputPaths(job, new Path("input/etl"));
        FileOutputFormat.setOutputPath(job, new Path("output/v2/pvstart"));

        job.waitForCompletion(true);
    }

    static class MyMapper extends Mapper<LongWritable, Text, Text, LongWritable>{

        //将key固定
        private Text KEY = new Text("key");
        private LongWritable ONE = new LongWritable(1);

        //在这里要实现一个map方法
        //直接输入map+回车
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            context.write(KEY, ONE);
        }
    }

    static class MyReducer extends Reducer<Text, LongWritable, NullWritable, LongWritable>{

        //在这里要实现一个reduce方法
        //直接输入reduce+回车
        @Override
        protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {

            long count = 0;
            for (LongWritable value: values){
                count++;
            }
            context.write(NullWritable.get(), new LongWritable(count));
        }
    }
}

电商项目实战-总浏览量PV统计功能升级(十)_hadoop