目录
1.概念
- 序列化 (Serialization) 是指把结构化对象转化为字节流
- 反序列化 (Deserialization) 是序列化的逆过程. 把字节流转为结构化对象. 当要在进程间传递对象或持久化对象的时候, 就需要序列化对象成字节流, 反之当要将接收到或从磁盘读取的字节流转换为对象, 就要进行反序列化
- Java 的序列化 (Serializable) 是一个重量级序列化框架, 一个对象被序列化后, 会附带很多额外的信息 (各种校验信息, header, 继承体系等), 不便于在网络中高效传输. 所以, Hadoop自己开发了一套序列化机制(Writable), 精简高效. 不用像Java对象类一样传输多层的父子关系, 需要哪个属性就传输哪个属性值, 大大的减少网络传输的开销
- Writable 是 Hadoop 的序列化格式, Hadoop 定义了这样一个 Writable 接口. 一个类要支持可序列化只需实现这个接口即可
- 另外 Writable 有一个子接口是 WritableComparable, WritableComparable是既可实现序列化, 也可以对key进行比较, 我们这里可以通过自定义 Key 实现 WritableComparable 来实现我们的排序功能
2.需求分析
3.具体代码
3.1 自定义类型和比较器
package com.ucas.mapreduce_sort;
import org.apache.hadoop.io.WritableComparable;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
/**
* @author GONG
* @version 1.0
* @date 2020/10/9 16:55
*/
public class PairWritable implements WritableComparable<PairWritable> {
// 组合key,第一部分是我们第一列,第二部分是我们第二列
private String first;
private int second;
public PairWritable() {
}
public PairWritable(String first, int second) {
this.set(first, second);
}
/**
* 方便设置字段
*/
public void set(String first, int second) {
this.first = first;
this.second = second;
}
/**
* 反序列化
*/
@Override
public void readFields(DataInput input) throws IOException {
this.first = input.readUTF();
this.second = input.readInt();
}
/**
* 实现序列化
*/
@Override
public void write(DataOutput output) throws IOException {
output.writeUTF(first);
output.writeInt(second);
}
/*
* 重写比较器,实现排序规则
*/
public int compareTo(PairWritable o) {
//每次比较都是调用该方法的对象与传递的参数进行比较,
//说白了就是第一行与第二行比较完了之后的结果与第三行比较,
//得出来的结果再去与第四行比较,依次类推
int comp = this.first.compareTo(o.first);
if (comp != 0) {
return comp;
} else { // 若第一个字段相等,则比较第二个字段
return Integer.valueOf(this.second).compareTo(
Integer.valueOf(o.getSecond()));
}
}
public int getSecond() {
return second;
}
public void setSecond(int second) {
this.second = second;
}
public String getFirst() {
return first;
}
public void setFirst(String first) {
this.first = first;
}
@Override
public String toString() {
return "PairWritable{" +
"first='" + first + '\'' +
", second=" + second +
'}';
}
}
3.2 Mapper
package com.ucas.mapreduce_sort;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
/**
* @author GONG
* @version 1.0
* @date 2020/10/9 16:53
*/
public class SortMapper extends Mapper<LongWritable, Text, PairWritable, IntWritable> {
private PairWritable mapOutKey = new PairWritable();
private IntWritable mapOutValue = new IntWritable();
@Override
public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String lineValue = value.toString();
String[] strs = lineValue.split("\t");
//设置组合key和value ==> <(key,value),value>
mapOutKey.set(strs[0], Integer.valueOf(strs[1]));
mapOutValue.set(Integer.valueOf(strs[1]));
context.write(mapOutKey, mapOutValue);
}
}
3.3 Reducer
package com.ucas.mapreduce_sort;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
/**
* @author GONG
* @version 1.0
* @date 2020/10/9 16:53
*/
public class SortReducer extends Reducer<PairWritable, IntWritable, Text, IntWritable> {
private Text outPutKey = new Text();
@Override
public void reduce(PairWritable key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
//迭代输出
for (IntWritable value : values) {
outPutKey.set(key.getFirst());
context.write(outPutKey, value);
}
}
}
3.4 Main入口
package com.ucas.mapreduce_sort;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
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.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
/**
* @author GONG
* @version 1.0
* @date 2020/10/9 16:55
*/
public class JobMain extends Configured implements Tool {
@Override
public int run(String[] args) throws Exception {
Configuration conf = super.getConf();
conf.set("mapreduce.framework.name", "local");
Job job = Job.getInstance(conf, JobMain.class.getSimpleName());
job.setJarByClass(JobMain.class);
job.setInputFormatClass(TextInputFormat.class);
TextInputFormat.addInputPath(job, new Path("hdfs://192.168.0.101:8020/input/sort"));
TextOutputFormat.setOutputPath(job, new Path("hdfs://192.168.0.101:8020/out/sort_out"));
job.setMapperClass(SortMapper.class);
job.setMapOutputKeyClass(PairWritable.class);
job.setMapOutputValueClass(IntWritable.class);
job.setReducerClass(SortReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
boolean b = job.waitForCompletion(true);
return b ? 0 : 1;
}
public static void main(String[] args) throws Exception {
Configuration entries = new Configuration();
int run = ToolRunner.run(entries, new JobMain(), args);
System.exit(run);
}
}
4.运行并查看结果
4.1 准备工作
创建sort.txt
在hdfs中创建input文件夹,并且把sort.txt放进去
4.2 打包jar
需要先清理一下clean,然后双击打包
4.3 运行jar包,查看结果
将jar上传到 /export/software
运行:hadoop jar day03_mapreduce_wordcount-1.0-SNAPSHOT.jar com.ucas.mapreduce_sort.JobMain