大数据之Hadoop(MapReduce)：WritableComparable排序案例实操（全排序）

Posted 2021-06-26 浊酒南街

目录

• 1.需求
• 2.需求分析
• 3．代码实现

1.需求

根据上案例产生的结果再次对总流量进行排序
（1）输入数据
原始数据 phone_data.txt

1	13736230513	192.196.100.1	www.jinghang.com	2481	24681	200
2	13846544121	192.196.100.2			264	0	200
3 	13956435636	192.196.100.3			132	1512	200
4 	13966251146	192.168.100.1			240	0	404
5 	18271575951	192.168.100.2	www.jinghang.com	1527	2106	200
6 	84188413	192.168.100.3	www.jinghang.com	4116	1432	200
7 	13590439668	192.168.100.4			1116	954	200
8 	15910133277	192.168.100.5	www.hao123.com	3156	2936	200
9 	13729199489	192.168.100.6			240	0	200
10 	13630577991	192.168.100.7	www.shouhu.com	6960	690	200
11 	15043685818	192.168.100.8	www.baidu.com	3659	3538	200
12 	15959002129	192.168.100.9	www.jinghang.com	1938	180	500
13 	13560439638	192.168.100.10			918	4938	200
14 	13470253144	192.168.100.11			180	180	200
15 	13682846555	192.168.100.12	www.qq.com	1938	2910	200
16 	13992314666	192.168.100.13	www.gaga.com	3008	3720	200
17 	13509468723	192.168.100.14	www.qinghua.com	7335	110349	404
18 	18390173782	192.168.100.15	www.sogou.com	9531	2412	200
19 	13975057813	192.168.100.16	www.baidu.com	11058	48243	200
20 	13768778790	192.168.100.17			120	120	200
21 	13568436656	192.168.100.18	www.alibaba.com	2481	24681	200
22 	13568436656	192.168.100.19			1116	954	200

第一次处理后的数据 part-r-00000
（2）期望输出数据
13509468723 7335 110349 117684
13736230513 2481 24681 27162
13956435636 132 1512 1644
13846544121 264 0 264
…

2.需求分析

3．代码实现

（1）FlowBean对象在在需求1基础上增加了比较功能

package com.jinghang.mapreduce.sort;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import org.apache.hadoop.io.WritableComparable;

public class FlowBean implements WritableComparable<FlowBean> {

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

	// 反序列化时，需要反射调用空参构造函数，所以必须有
	public FlowBean() {
		super();
	}

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

	public void set(long upFlow, long downFlow) {
		this.upFlow = upFlow;
		this.downFlow = downFlow;
		this.sumFlow = upFlow + downFlow;
	}

	public long getSumFlow() {
		return sumFlow;
	}

	public void setSumFlow(long sumFlow) {
		this.sumFlow = 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;
	}

	/**
	 * 序列化方法
	 * @param out
	 * @throws IOException
	 */
	@Override
	public void write(DataOutput out) throws IOException {
		out.writeLong(upFlow);
		out.writeLong(downFlow);
		out.writeLong(sumFlow);
	}

	/**
	 * 反序列化方法 注意反序列化的顺序和序列化的顺序完全一致
	 * @param in
	 * @throws IOException
	 */
	@Override
	public void readFields(DataInput in) throws IOException {
		upFlow = in.readLong();
		downFlow = in.readLong();
		sumFlow = in.readLong();
	}

	@Override
	public String toString() {
		return upFlow + "\\t" + downFlow + "\\t" + sumFlow;
	}

	@Override
	public int compareTo(FlowBean o) {
		
		int result;
		
		// 按照总流量大小，倒序排列
		if (sumFlow > bean.getSumFlow()) {
			result = -1;
		}else if (sumFlow < bean.getSumFlow()) {
			result = 1;
		}else {
			result = 0;
		}

		return result;
	}
}

（2）编写Mapper类

package com.jinghang.mapreduce.sort;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

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

	FlowBean bean = new FlowBean();
	Text v = new Text();

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

		// 1 获取一行
		String line = value.toString();
		
		// 2 截取
		String[] fields = line.split("\\t");
		
		// 3 封装对象
		String phoneNbr = fields[0];
		long upFlow = Long.parseLong(fields[1]);
		long downFlow = Long.parseLong(fields[2]);
		
		bean.set(upFlow, downFlow);
		v.set(phoneNbr);
		
		// 4 输出
		context.write(bean, v);
	}
}

（3）编写Reducer类

package com.jinghang.mapreduce.sort;
import java.io.IOException;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

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

	@Override
	protected void reduce(FlowBean key, Iterable<Text> values, Context context)	throws IOException, InterruptedException {
		
		// 循环输出，避免总流量相同情况
		for (Text text : values) {
			context.write(text, key);
		}
	}
}

（4）编写Driver类

package com.jinghang.mapreduce.sort;
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 FlowCountSortDriver {

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

		// 输入输出路径需要根据自己电脑上实际的输入输出路径设置
		args = new String[]{"e:/output1","e:/output2"};

		// 1 获取配置信息，或者job对象实例
		Configuration configuration = new Configuration();
		Job job = Job.getInstance(configuration);

		// 2 指定本程序的jar包所在的本地路径
		job.setJarByClass(FlowCountSortDriver.class);

		// 3 指定本业务job要使用的mapper/Reducer业务类
		job.setMapperClass(FlowCountSortMapper.class);
		job.setReducerClass(FlowCountSortReducer.class);

		// 4 指定mapper输出数据的kv类型
		job.setMapOutputKeyClass(FlowBean.class);
		job.setMapOutputValueClass(Text.class);

		// 5 指定最终输出的数据的kv类型
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(FlowBean.class);

		// 6 指定job的输入原始文件所在目录
		FileInputFormat.setInputPaths(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		
		// 7 将job中配置的相关参数，以及job所用的java类所在的jar包， 提交给yarn去运行
		boolean result = job.waitForCompletion(true);
		System.exit(result ? 0 : 1);
	}
}