Hadoop學習之路(7)MapReduce自定義排序

本文測試文本：

tom 20 8000
nancy 22 8000
ketty 22 9000
stone 19 10000
green 19 11000
white 39 29000
socrates 30 40000

   MapReduce中，根據key進行分區、排序、分組
MapReduce會按照基本類型對應的key進行排序，如int類型的IntWritable，long類型的LongWritable,Text類型，默認升序排序
   爲什麼要自定義排序規則？現有需求，需要自定義key類型，並自定義key的排序規則，如按照人的salary降序排序，若相同，則再按age升序排序
以Text類型爲例：




Text類實現了WritableComparable接口，並且有write()、readFields()和compare()方法
readFields()方法：用來反序列化操作
write()方法：用來序列化操作
所以要想自定義類型用來排序需要有以上的方法
自定義類代碼：

import org.apache.hadoop.io.WritableComparable;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
public class Person implements WritableComparable<Person> {
    private String name;
    private int age;
    private int salary;
    public Person() {
    }
    public Person(String name, int age, int salary) {
        //super();
        this.name = name;
        this.age = age;
        this.salary = salary;
    }
    public String getName() {
        return name;
    }
    public void setName(String name) {
        this.name = name;
    }
    public int getAge() {
        return age;
    }
    public void setAge(int age) {
        this.age = age;
    }
    public int getSalary() {
        return salary;
    }
    public void setSalary(int salary) {
        this.salary = salary;
    }
    @Override
    public String toString() {
        return this.salary + "  " + this.age + "    " + this.name;
    }
    //先比較salary，高的排序在前；若相同，age小的在前
    public int compareTo(Person o) {
        int compareResult1= this.salary - o.salary;
        if(compareResult1 != 0) {
            return -compareResult1;
        } else {
            return this.age - o.age;
        }
    }
    //序列化，將NewKey轉化成使用流傳送的二進制
    public void write(DataOutput dataOutput) throws IOException {
        dataOutput.writeUTF(name);
        dataOutput.writeInt(age);
        dataOutput.writeInt(salary);
    }
    //使用in讀字段的順序，要與write方法中寫的順序保持一致
    public void readFields(DataInput dataInput) throws IOException {
        //read string
        this.name = dataInput.readUTF();
        this.age = dataInput.readInt();
        this.salary = dataInput.readInt();
    }

}

MapReuduce程序：

import org.apache.hadoop.conf.Configuration;
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 java.io.IOException;
import java.net.URI;
public class  SecondarySort {
    public static void main(String[] args) throws Exception {
        System.setProperty("HADOOP_USER_NAME","hadoop2.7");
        Configuration configuration = new Configuration();
        //設置本地運行的mapreduce程序 jar包
        configuration.set("mapreduce.job.jar","C:\\Users\\tanglei1\\IdeaProjects\\Hadooptang\\target\\com.kaikeba.hadoop-1.0-SNAPSHOT.jar");
        Job job = Job.getInstance(configuration, SecondarySort.class.getSimpleName());
        FileSystem fileSystem = FileSystem.get(URI.create(args[1]), configuration);
        if (fileSystem.exists(new Path(args[1]))) {
            fileSystem.delete(new Path(args[1]), true);
        }
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        job.setMapperClass(MyMap.class);
        job.setMapOutputKeyClass(Person.class);
        job.setMapOutputValueClass(NullWritable.class);
        //設置reduce的個數
        job.setNumReduceTasks(1);
        job.setReducerClass(MyReduce.class);
        job.setOutputKeyClass(Person.class);
        job.setOutputValueClass(NullWritable.class);
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        job.waitForCompletion(true);
    }
    public static class MyMap extends
            Mapper<LongWritable, Text, Person, NullWritable> {
        //LongWritable：輸入參數鍵類型，Text：輸入參數值類型
        //Persion:輸出參數鍵類型，NullWritable：輸出參數值類型
        @Override
        //map的輸出值是鍵值對<K,V>，NullWritable說關心V的值
        protected void map(LongWritable key, Text value,
                Context context)
                throws IOException, InterruptedException {
            //LongWritable key：輸入參數鍵值對的鍵，Text value：輸入參數鍵值對的值
            //獲得一行數據，輸入參數的鍵（距首行的位置）,Hadoop讀取數據的時候逐行讀取文本
            //fields:代表着文本一行的的數據
            String[] fields = value.toString().split(" ");
            // 本列中文本一行數據：nancy 22 8000
            String name = fields[0];
            //字符串轉換成int
            int age = Integer.parseInt(fields[1]);
            int salary = Integer.parseInt(fields[2]);
            //在自定義類中進行比較
            Person person = new Person(name, age, salary);
            context.write(person, NullWritable.get());
        }
    }
    public static class MyReduce extends
            Reducer<Person, NullWritable, Person, NullWritable> {
        @Override
        protected void reduce(Person key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
            context.write(key, NullWritable.get());
        }
    }
}

運行結果：

40000  30    socrates
29000  39    white
11000  19    green
10000  19    stone
9000  22    ketty
8000  20    tom
8000  22    nancy