分区汇总流量MapReduce

ProviceCountMapper.java

package os.bigdata.provincflowcount;

import java.io.IOException;

import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class ProviceCountMapper extends Mapper<LongWritable, Text, Text, FlowBean>{

    private Text k = new Text();
    private FlowBean bean = new FlowBean();


    @Override
    protected void map(LongWritable key, Text value, Context context)throws IOException, InterruptedException {

        String  line = value.toString();
        String[] fields = StringUtils.split(line,'\t');

        String phone = fields[1];
        long upflow = Long.parseLong(fields[fields.length-3]);
        long downflow = Long.parseLong(fields[fields.length-2]);

        bean = new FlowBean(upflow,downflow);

        k.set(phone);
        bean.set(upflow, downflow);

        context.write(k, bean);

    }
}

ProviceCountReducer.java

import java.io.IOException;

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

public class ProviceCountReducer extends Reducer<Text, FlowBean, Text, FlowBean>{

    private Text k = new Text();
    private FlowBean bean = new FlowBean();
    @Override
    protected void reduce(Text key, Iterable<FlowBean> values, Context context)throws IOException, InterruptedException {

        long upflowSum = 0;
        long downflowSum = 0;

        for(FlowBean bean: values) {
            upflowSum += bean.getUpflow();
            downflowSum += bean.getDownflow();

        }

        bean.set(upflowSum, downflowSum);
        context.write(key, bean);
    }
}

ProvicePartitioner.java

package os.bigdata.provincflowcount;

import java.util.HashMap;

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

public class ProvicePartitioner extends Partitioner<Text, FlowBean> {

    private static HashMap<String,Integer> provinceMap = new HashMap<String,Integer>();

    //在parationer在初始化的时候将外部字典数据一次性加载到内存
    static{
        //加载外部的字典数据到本地内存
        provinceMap.put("136", 0);
        provinceMap.put("137", 1);
        provinceMap.put("138", 2);
        provinceMap.put("139", 3);

    }
    @Override
    public int getPartition(Text key, FlowBean value, int numPartitions) {

        //取手机号前缀
        String prefix = key.toString().substring(0,3);

        //从字典数据中查询分区的号
        Integer provinceNum =  provinceMap.get(prefix);
        if(provinceNum==null)
            provinceNum = 4;

        //拿到key -- 手机号前N位 ,然后查询一个外部字典,--归属地字典表


        return provinceNum;
    }

}

FlowBean.java

package os.bigdata.provincflowcount;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

import org.apache.hadoop.io.Writable;

/*
 * 自定义的数据类型,要做hadoop集群中传递,需要实现hadoop序列化框架,就是去实现一个接口 Writable
 */
public class FlowBean implements Writable{

    private long upflow;    //上行流量
    private long downflow;  //下行流量
    private long sumflow; //总流量


    //因为反射机制需要,必须定义一个无参构造函数
    public FlowBean() {

    }

    public long getUpflow() {
        return upflow;
    }
    public void setUpflow(long upflow) {
        this.upflow = upflow;
    }
    public long getDownflow() {
        return downflow;
    }
    public void setDownflow(long downflow) {
        this.downflow = downflow;
    }


    public long getSumflow() {
        return sumflow;
    }

    public void setSumflow(long sumflow) {
        this.sumflow = sumflow;
    }

    public FlowBean(long upflow, long downflow) {
        this.upflow = upflow;
        this.downflow = downflow;
        this.sumflow = upflow + downflow;
    }
    /*
     * 序列化方法,将我们要传输的数据序列化字节流
     * @see org.apache.hadoop.io.Writable#write(java.io.DataOutput)
     */
    @Override
    public void write(DataOutput out) throws IOException {

        out.writeLong(upflow);
        out.writeLong(downflow);

    }

    /*
     * 反序列化的方法,从自己流中恢复出各个字段
     * @see org.apache.hadoop.io.Writable#readFields(java.io.DataInput)
     */
    @Override
    public void readFields(DataInput in) throws IOException {

        upflow = in.readLong();  //从网络字节序,变成主机字节序
        downflow = in.readLong();
    }

    @Override
    public String toString() {
        return "FlowBean [upflow=" + upflow + ", downflow=" + downflow + ", sumflow=" + sumflow + "]";
    }

    public void set(long upflow,long downflow) {

        this.upflow = upflow;
        this.downflow = downflow;
        this.sumflow = upflow + downflow;

    }
}

JobClient.java

package os.bigdata.provincflowcount;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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;


public class JobClient {

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {

        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        job.setJarByClass(JobClient.class);

        job.setMapperClass(ProviceCountMapper.class);
        job.setReducerClass(ProviceCountReducer.class);

        // map输出的kv类型与reduce输出的kv类型一致时,这两行可以省略
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);

        //通过显示指定partioner类来让我们自定义partioner起作用
        job.setPartitionerClass(ProvicePartitioner.class);

        //设置本次job运行时reduce tack进程数,数量要个分区的数量一致
        job.setNumReduceTasks(4);

        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        job.waitForCompletion(true);

    }
}