用一个MapReduce输出多个key的分区文件

先看一下要处理的数据类型

19392963501,17816115082,2018-09-18 16:19:44,1431
14081946321,13094566759,2018-05-23 09:34:27,0610
13415701165,18939575060,2018-11-23 21:33:23,1031
15590483587,16303009156,2018-08-02 07:38:00,0487
15539613975,17882324598,2018-10-19 09:08:15,0948
数据字段分别为主叫号码，被叫号码，通话时间，通话时长
我们的需求是：将数据按号码的通话日期的年，月，日分别计算时长和次数，用一个MapReduce实现，在这里我处理的时候是忽略被叫号码的通话时长，仅以主叫号码为例。

代码部分

package mapReducePhone;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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.Partitioner;
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 PhoneNum {
    public static void main(String[] args) throws Exception{
    	//获取连接
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        //设置要运行的 jar
        job.setJarByClass(PhoneNum.class);
        //指定map和reduce
        job.setMapperClass(PhoneMapper.class);
        job.setReducerClass(PhoneReducer.class);
        //设置map输出类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        //设置reduce 输出类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);
        //设置分区与reduce task 的数量
        job.setPartitionerClass(PhonePartitioner.class);
        job.setNumReduceTasks(3);
        //设置输入输出路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        //答应结果是否成功
        boolean result = job.waitForCompletion(true);
        System.out.println(result);
    }
}
//数据格式  17026053728,17816115082,2108-03-28 11:09:19,1792
class PhoneMapper extends Mapper<LongWritable,Text,Text,IntWritable>{
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
      //  Text k = new Text();
    	String[] split = value.toString().split(",");
        String caller =split[0];
       // String callee =split[1];
       // String date =split[2];
        int statetime =Integer.parseInt(split[3]);
        String yearData = split[2].replaceAll("-", "").substring(0, 4);
        String monthData = split[2].replaceAll("-", "").substring(0, 6);
        String  dayData = split[2].replaceAll("-", "").substring(0,9);
        //仅计算主叫号码的通话记录  若需求被叫号码则将被叫号码提取出来进行同样操作
        context.write(new Text(caller+"-"+dayData),new IntWritable(statetime));
        context.write(new Text(caller+"-"+yearData),new IntWritable(statetime));
        context.write(new Text(caller+"-"+monthData),new IntWritable(statetime));
    }
}
class PhoneReducer extends Reducer<Text,IntWritable,Text,Text> {
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int sum = 0;
        int i =0;
        for(IntWritable value :values){
            sum += value.get();
            i++;
        }
        context.write(new Text(key),new Text(sum+" 次数"+ i));
    }
}
class PhonePartitioner<K, V> extends Partitioner<K, V>{

    @Override
    //自定义partition的数量需要和reduce task数量保持一致
    public int getPartition(K key, V value, int numPartitions) {
        // TODO Auto-generated method stub
    	//根据key的长度进行分区
        int datelongth=key.toString().length();
        switch(datelongth)
        {
        case 16 :
        	return 0;
        case 18 : 
        	return 1;
        }
        return 2;
    }
}

结果部分展示，有3个分区文件

按日分

按年分

按月分