mr分区代码

1.数据

1363157985066 	13726230503	00-FD-07-A4-72-B8:CMCC	120.196.100.82	i02.c.aliimg.com		24	27	2481	24681	200
1363157995052 	13826544101	5C-0E-8B-C7-F1-E0:CMCC	120.197.40.4			4	0	264	0	200
1363157991076 	13926435656	20-10-7A-28-CC-0A:CMCC	120.196.100.99			2	4	132	1512	200
1363154400022 	13926251106	5C-0E-8B-8B-B1-50:CMCC	120.197.40.4			4	0	240	0	200
1363157993044 	18211575961	94-71-AC-CD-E6-18:CMCC-EASY	120.196.100.99	iface.qiyi.com	视频网站	15	12	1527	2106	200
1363157995074 	84138413	5C-0E-8B-8C-E8-20:7DaysInn	120.197.40.4	122.72.52.12		20	16	4116	1432	200
1363157993055 	13560439658	C4-17-FE-BA-DE-D9:CMCC	120.196.100.99			18	15	1116	954	200
1363157995033 	15920133257	5C-0E-8B-C7-BA-20:CMCC	120.197.40.4	sug.so.360.cn	信息安全	20	20	3156	2936	200
1363157983019 	13719199419	68-A1-B7-03-07-B1:CMCC-EASY	120.196.100.82			4	0	240	0	200
1363157984041 	13660577991	5C-0E-8B-92-5C-20:CMCC-EASY	120.197.40.4	s19.cnzz.com	站点统计	24	9	6960	690	200
1363157973098 	15013685858	5C-0E-8B-C7-F7-90:CMCC	120.197.40.4	rank.ie.sogou.com	搜索引擎	28	27	3659	3538	200
1363157986029 	15989002119	E8-99-C4-4E-93-E0:CMCC-EASY	120.196.100.99	www.umeng.com	站点统计	3	3	1938	180	200
1363157992093 	13560439658	C4-17-FE-BA-DE-D9:CMCC	120.196.100.99			15	9	918	4938	200
1363157986041 	13480253104	5C-0E-8B-C7-FC-80:CMCC-EASY	120.197.40.4			3	3	180	180	200
1363157984040 	13602846565	5C-0E-8B-8B-B6-00:CMCC	120.197.40.4	2052.flash2-http.qq.com	综合门户	15	12	1938	2910	200
1363157995093 	13922314466	00-FD-07-A2-EC-BA:CMCC	120.196.100.82	img.qfc.cn		12	12	3008	3720	200
1363157982040 	13502468823	5C-0A-5B-6A-0B-D4:CMCC-EASY	120.196.100.99	y0.ifengimg.com	综合门户	57	102	7335	110349	200
1363157986072 	18320173382	84-25-DB-4F-10-1A:CMCC-EASY	120.196.100.99	input.shouji.sogou.com	搜索引擎	21	18	9531	2412	200
1363157990043 	13925057413	00-1F-64-E1-E6-9A:CMCC	120.196.100.55	t3.baidu.com	搜索引擎	69	63	11058	48243	200
1363157988072 	13760778710	00-FD-07-A4-7B-08:CMCC	120.196.100.82			2	2	120	120	200
1363157985066 	13726238888	00-FD-07-A4-72-B8:CMCC	120.196.100.82	i02.c.aliimg.com		24	27	2481	24681	200
1363157993055 	13560436666	C4-17-FE-BA-DE-D9:CMCC	120.196.100.99			18	15	1116	954	200
1363157985066 	13726238888	00-FD-07-A4-72-B8:CMCC	120.196.100.82	i02.c.aliimg.com		24	27	10000	20000	200

2.需求

• 手机13开头放入一个分区,15放入一个,其他放入一个

3.代码

1. AccessPartitioner–自定义规则

package com.ruozedata.bigdata.hadoop.mapreduce.Partitioner;

import com.ruozedata.bigdata.hadoop.mapreduce.ser.Access;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Partitioner;

public class AccessPartitioner extends Partitioner<Text, Access> {
    @Override
    public int getPartition(Text phoneText, Access access, int numPartitions) {

        String phone=phoneText.toString();
        if(phone.startsWith("13")){
            return 0;
        }else if(phone.startsWith("15")){
            return 1;
        }else {
            return 2;
        }  
    }
}

2. AccessApp—setPartitionerClass, setNumReduceTasks

package com.ruozedata.bigdata.hadoop.mapreduce.Partitioner;

import com.ruozedata.bigdata.hadoop.mapreduce.ser.Access;
import com.ruozedata.bigdata.hadoop.mapreduce.wc.com.ruozedata.bigdata.hadoop.utils.FileUtils;
import org.apache.hadoop.conf.Configuration;
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 AccessApp {


    public static void main(String[] args) throws Exception {
        //1.获取job对象
        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);

        String input = "data/access.log";
        String output = "out/";

        FileUtils.deleteTarget(output,configuration);


        //2.设置jar的相关信息
        job.setJarByClass(AccessApp.class);

        //3.设置自定义的myMapper和myReducer
        job.setMapperClass(AccessApp.MyMapper.class);
        job.setReducerClass(AccessApp.MyReducer.class);

        //4.设置map阶段输出的key和value类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Access.class);

        //5.设置reduce阶段输出的key和value类型
        job.setOutputKeyClass(NullWritable.class);
        job.setOutputValueClass(Access.class);

        //6.设置输入输出路径

        FileInputFormat.setInputPaths(job, new Path(input));
        FileOutputFormat.setOutputPath(job, new Path(output));

        job.setPartitionerClass(AccessPartitioner.class);
        job.setNumReduceTasks(3);


        //7.提交job
        boolean result = job.waitForCompletion(true);

        System.exit(result ? 0 : 1);
    }


    public static class MyMapper extends Mapper<LongWritable, Text, Text, Access> {
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String[] splits = value.toString().split("\t");

            String phone = splits[1];
            long up = Long.parseLong(splits[splits.length-3]);
            long down = Long.parseLong(splits[splits.length-2]);

            context.write(new Text(phone), new Access(phone,up,down));

        }
    }



    public static class MyReducer extends Reducer<Text, Access, NullWritable, Access> {

        @Override
        protected void reduce(Text key, Iterable<Access> values, Context context) throws IOException, InterruptedException {
            long ups = 0;
            long downs = 0;
            for(Access access: values){
                ups+=access.getUp();
                downs+=access.getDown();
            }
            context.write(NullWritable.get(),new Access(key.toString(),ups,downs));
        }
    }
}