自定义分区合并

原理过程

分区

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

//分区
public class PhonePartitioner extends Partitioner<Text, IntWritable> {

    @Override
    public int getPartition(Text text, IntWritable intWritable, int i) {
        System.out.println(text.toString());
        //136，137    138，139    其他号码归为一类
        if ("136".equals(text.toString().substring(0, 3)) || "137".equals(text.toString().substring(0, 3)))
            return 0;
        else if ("138".equals(text.toString().substring(0, 3)) || "139".equals(text.toString().substring(0, 3)))
            return 1;
        else return 2;
    }
}

合并

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

//合并
import java.io.IOException;

public class PhoneCombiner extends Reducer<Text, IntWritable, Text, IntWritable> {
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException {
        int count = 0;
        for (IntWritable value : values) {
            count += value.get();
        }
        context.write(key, new IntWritable(count));
    }
}