05 MapReduce——IP去重

思路

去除重复用什么？

reduce阶段本身就会去除重复

package ip;

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 IpMapper extends Mapper<LongWritable, Text,Text, IntWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
       context.write(value,new IntWritable(1));
    }
}

当不需要某个value时，可以使用NullWritable类型

map的输出value值其实是可以不要的

package ip;

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 IpMapper extends Mapper<LongWritable, Text,Text, NullWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
       context.write(value,NullWritable.get());
    }
}

package ip;

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

import java.io.IOException;

public class IpReducer extends Reducer<Text, IntWritable, Text,IntWritable> {
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        //测试会不会提前归于一组
        context.write(key,new IntWritable(1));
    }
}

"reduce也不用输出值"

package ip;

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

import java.io.IOException;

public class IpReducer extends Reducer<Text, NullWritable, Text,NullWritable> {
    @Override
    protected void reduce(Text key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
        context.write(key,NullWritable.get());
    }
}

package ip;

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 IpDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        //配置类,可以通过这个类提交作业参数
        Configuration conf = new Configuration();
        //封装作业
        Job job = Job.getInstance(conf);
        // 设置入口类
        job.setJarByClass(IpDriver.class);
        // 设置Mapper类
        job.setMapperClass(IpMapper.class);
        // 设置Reducer类
        job.setReducerClass(IpReducer.class);
        //设置mapper的输出类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(NulllWritable.class);
        //设置reducer的输出类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);
        //文件输入路径
        FileInputFormat.addInputPath(job,new Path("hdfs://hadoop01:9000/txt/ip.txt"));
        // 设置输出路径
        // 要求输出路径在HDFS上不存在
        FileOutputFormat.setOutputPath(job, new Path("hdfs://hadoop01:9000/result/ipcount"));
        // 提交任务
        job.waitForCompletion(true);
    }
}