Hadoop MapReduce 获取Uv数据

需要的数据：

192.168.33.16,hunter,2017-09-16 10:30:20,/a
192.168.33.16,jack,2017-09-16 10:30:40,/a
192.168.33.16,jack,2017-09-16 10:30:40,/a
192.168.33.16,jack,2017-09-16 10:30:40,/a
192.168.33.16,jack,2017-09-16 10:30:40,/a
192.168.33.18,polo,2017-09-16 10:30:50,/b
192.168.33.39,nissan,2017-09-16 10:30:53,/b
192.168.33.39,nissan,2017-09-16 10:30:55,/b
192.168.33.39,nissan,2017-09-16 10:30:58,/c
192.168.33.20,ford,2017-09-16 10:30:54,/c
192.168.33.20,ford,2017-09-16 10:30:54,/c

 

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.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 Uv {
    public static class MyMapper extends Mapper<LongWritable,Text,Text,Text>{
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String s = value.toString();
            String[] split = s.split(",");
            context.write(new Text(split[0]),new Text());
        }
    }
    public static class MyReducer extends Reducer<Text,Text,Text,Text> {
        @Override
        protected void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
            context.write(new Text(key),new Text());
        }
    }
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "two");

        job.setJarByClass(Uv.class);

        //获取输入
        FileInputFormat.addInputPath(job,new Path(args[0]));
        //map计算
        job.setMapperClass(MyMapper.class);
        //shuffle计算
        //reduce计算
        job.setReducerClass(MyReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);
        //获取输出
        FileOutputFormat.setOutputPath(job,new Path(args[1]));
        //判断文件是否存在
        FileSystem fs = FileSystem.get(conf);
        if (fs.exists(new Path(args[1]))){
            fs.delete(new Path(args[1]),true);
        }
        boolean b = job.waitForCompletion(true);
        System.out.println(b?1:0);
    }
}

 

输出UV：

192.168.33.16    
192.168.33.18    
192.168.33.20    
192.168.33.39