hadoop序列化实现

Hadoop序列化特点

• 紧凑：高效实用存储空间
• 快速：读写数据额外开销小
• 可扩展：随着通信协议的升级而可以升级
• 互操作：支持多种语言的交互

自定义Bean对象实现序列化

1. 必须实现Writable接口
2. 反序列化时，需要反射调用无参构造函数
3. 如果需要将自定义的bean放在key中传输，则还需要实现Comparable接口

案例

package com.chen.phoneproject;

import org.apache.hadoop.io.Writable;

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

public class FlowBean implements Writable {

    private long upFlow;
    private long downFlow;
    private long sumFlow;

    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() {
        super();
    }

    public FlowBean(long upFlow, long downFlow) {
        super();
        this.upFlow = upFlow;
        this.downFlow = downFlow;
    }

    public FlowBean(long upFlow, long downFlow, long sumFlow) {
        super();
        this.upFlow = upFlow;
        this.downFlow = downFlow;
        this.sumFlow = sumFlow;
    }

    @Override
    public void write(DataOutput dataOutput) throws IOException {
        dataOutput.writeLong(upFlow);
        dataOutput.writeLong(downFlow);
        dataOutput.writeLong(sumFlow);
    }

    @Override
    public void readFields(DataInput dataInput) throws IOException {
        this.upFlow = dataInput.readLong();
        this.downFlow = dataInput.readLong();
        this.sumFlow = dataInput.readLong();
    }

    @Override
    public String toString() {
        return "FlowBean{" +
                "upFlow=" + upFlow +
                ", downFlow=" + downFlow +
                ", sumFlow=" + sumFlow +
                '}';
    }
}

package com.chen.phoneproject;

import lombok.extern.slf4j.Slf4j;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

@Slf4j
public class FlowCountMapper extends Mapper<LongWritable, Text,Text,FlowBean> {

    Text k = new Text();

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

        log.info("---mapper---"+"key:"+key+",value:"+value);
        String line = value.toString();

        String[] fields = line.split("\t");

        String phoneNum = fields[1];
        long upFlow = Long.parseLong(fields[3]);
        long downFlow = Long.parseLong(fields[4]);

        k.set(phoneNum);
        FlowBean bean = new FlowBean(upFlow,downFlow);

        context.write(k,bean);
    }

}

package com.chen.phoneproject;

import lombok.extern.slf4j.Slf4j;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;


@Slf4j
public class FlowCountReducer extends Reducer<Text,FlowBean,Text,FlowBean> {


    @Override
    protected void reduce(Text key, Iterable<FlowBean> values, Context context) throws IOException, InterruptedException {

       log.info("---reduce---"+"key:"+key+",value:"+values);
        long sum_upFlow = 0;
        long sum_downFlow = 0;

        for (FlowBean flowBean:values){
            sum_upFlow += flowBean.getUpFlow();
            sum_downFlow += flowBean.getDownFlow();
        }

        FlowBean result = new FlowBean(sum_upFlow,sum_downFlow,sum_downFlow + sum_upFlow);

        context.write(key,result);
    }
}

package com.chen.phoneproject;

import com.chen.mapreduce.WordcountDriver;
import com.chen.mapreduce.WordcountMapper;
import com.chen.mapreduce.WordcountReducer;
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;

public class FlowsumDriver {

    public static void main(String[] args) throws Exception {

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

        job.setJarByClass(FlowsumDriver.class);

        job.setMapperClass(FlowCountMapper.class);
        job.setReducerClass(FlowCountReducer.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);

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

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

        boolean result = job.waitForCompletion(true);

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