自定序列化（hadoop）

什么是序列化？

序列化：把对象转换为字节序列的过程称为对象的序列化。
反序列化：把字节序列恢复为对象的过程称为对象的反序列化。

上面求最大值最小值，关于多个value值得问题我们用/001的分割符进行链接。但是这里是两个。要是很多个我们怎么解决？

我可以使用自定义序列化类，将这个类作为我们value的输出类型。再通过创建这个类的对象，获得封装对象的属性来实现多个value值。

实例：

自定义序列化类：

package com.hnxy.mr.entity;

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

import org.apache.hadoop.io.Writable;

/*
 * 自定义序列化类
 */
public class WordWritable implements Writable {

	private String keyName = "";
	private Double keyval = 0D;

	public String getKeyName() {
		return keyName;
	}

	public void setKeyName(String keyName) {
		this.keyName = keyName;
	}

	public Double getKeyval() {
		return keyval;
	}

	public void setKeyval(Double keyval) {
		this.keyval = keyval;
	}

	@Override
	public void write(DataOutput out) throws IOException {
		// TODO Auto-generated method stub
		out.writeUTF(keyName);
		out.writeDouble(keyval);
	}

	// 反序列化 -->从硬盘读取到内存
	@Override
	public void readFields(DataInput in) throws IOException {
		// TODO Auto-generated method stub
		this.keyName = in.readUTF();
		this.keyval = in.readDouble();
	}

	@Override
	public String toString() {
		return " [keyName=" + keyName + ", keyval=" + keyval + "]";
	}

}

封装了商品的名称和价格属性

实现类：

package com.hnxy.mr.max;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
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 org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

import com.hnxy.mr.entity.WordWritable;

public class MaxMinWord extends Configured implements Tool {
	private static class MWMapper extends Mapper<LongWritable, Text, Text, WordWritable> {
		// 定义属性
		private Text outkey = new Text();
		private WordWritable outval = new WordWritable();
		// 定义临时变量
		private String maxkey = "";
		private Double maxval = 0D;
		private String minkey = "";
		private Double minval = 0D;

		@Override
		protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, WordWritable>.Context context)
				throws IOException, InterruptedException {
			// TODO Auto-generated method stub
			String[] str = value.toString().split("\t");
			// 判断是否符合要求
			if (null != str && str.length == 7) {
				// 判断最大值
				if (maxval < Double.parseDouble(str[6])) {
					maxval = Double.parseDouble(str[6]);
					maxkey = str[3];
				}
				// 判断最小值
				if (minval <= 0D) {
					minval = Double.parseDouble(str[6]);
					minkey = str[3];
				}
				if (minval < Double.parseDouble(str[6])) {
					minval = Double.parseDouble(str[6]);
					minkey = str[3];
				}
			} else {
				context.getCounter("错误数据", "记录").increment(1);
			}
		}

		@Override
		protected void cleanup(Mapper<LongWritable, Text, Text, WordWritable>.Context context)
				throws IOException, InterruptedException {
			// 输出
			// 保存最大值
			outkey.set("max_min");
			outval.setKeyName(maxkey);
			outval.setKeyval(maxval);
			context.write(outkey, outval);
			// 保存最小值
			outkey.set("max_min");
			outval.setKeyName(minkey);
			outval.setKeyval(minval);
			context.write(outkey, outval);

		}
	}

	public static class MWReducer extends Reducer<Text, WordWritable, WordWritable, NullWritable> {
		// 定义属性
		private WordWritable outkey = new WordWritable();
		// 定义临时变量
		private String maxkey = "";
		private Double maxval = 0D;
		private String minkey = "";
		private Double minval = 0D;

		// 获取每个key的val
		private Double tmpval = 0D;

		@Override
		protected void reduce(Text key, Iterable<WordWritable> values,
				Reducer<Text, WordWritable, WordWritable, NullWritable>.Context context)
				throws IOException, InterruptedException {
			// 处理数据(最大值与最小值)
			for (WordWritable w : values) {
				// 求最大值
				if (maxval < w.getKeyval()) {
					maxval = w.getKeyval();
					maxkey = w.getKeyName();
				}
				// 求最小值
				if (minval <= 0D) {
					minval = w.getKeyval();
					minkey = w.getKeyName();
				}
				if (minval > w.getKeyval()) {
					minval = w.getKeyval();
					minkey = w.getKeyName();
				}
			}
			// 输出最大值与最小值

			outkey.setKeyName(maxkey);
			outkey.setKeyval(maxval);
			context.write(outkey, NullWritable.get());
			outkey.setKeyName(minkey);
			outkey.setKeyval(minval);
			context.write(outkey, NullWritable.get());
		}
	}

	@Override
	public int run(String[] args) throws Exception {
		// 创建方法的返回值
		int count = 0;
		// 创建核心配置对象
		Configuration conf = this.getConf();
		// 创建一个任务
		Job job = Job.getInstance(conf, "maxword");
		// 配置任务打包类
		job.setJarByClass(MaxMinWord.class);
		// 设置MapReduce类
		job.setMapperClass(MWMapper.class);
		job.setReducerClass(MWReducer.class);
		// 设置 map 阶段 和 reduce 节点的 输出数据类型
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(WordWritable.class);
		job.setOutputKeyClass(WordWritable.class);
		job.setOutputValueClass(NullWritable.class);
		// 设置文件路径
		Path in = new Path(args[0]);
		Path out = new Path(args[1]);
		// 设置hdfs操作对象
		FileSystem fs = FileSystem.get(conf);
		// 绑定文件输出输入目录
		FileInputFormat.addInputPath(job, in);
		FileOutputFormat.setOutputPath(job, out);
		// 自动删除
		if (fs.exists(out)) {
			fs.delete(out, true);
			// 提示
			System.out.println(job.getJobName() + "'s Path Output is deleted");
		}
		// 执行
		boolean con = job.waitForCompletion(true);
		// 返回
		if (con) {
			System.out.println("成功");
		} else {
			System.out.println("失败");
		}
		return 0;
	}

	public static void main(String[] args) throws Exception {
		System.exit(ToolRunner.run(new MaxMinWord(), args));
	}

}