Hadoop-2.x 学习笔记（7） ——MapRedce框架数据类型

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/u012292754/article/details/86482963

1 MapRedce框架数据类型

• 数据类型都实现 Writable 接口,以便用这些类型定义的数据可以被序列化进行网络传输和文件存储；

1.1 基本数据类型

• BooleanWritable
• ByteWritable
• DoubleWritable
• FloatWritable
• IntWritable
• LongWritable
• Text:使用 UTF-8 格式存储的文本
• NullWritable ： 当 <key,value> 中的 key 或者 value 为空是使用；

1.2 自定义数据类型

import org.apache.hadoop.io.WritableComparable;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import java.util.Objects;

public class PairWritable implements WritableComparable<PairWritable> {

    private int id;
    private String name;

    public PairWritable() {
    }

    public PairWritable(int id, String name) {
        this.id = id;
        this.name = name;
    }

    public int getId() {
        return id;
    }

    public void setId(int id) {
        this.id = id;
    }

    public String getName() {
        return name;
    }

    public void setName(String name) {
        this.name = name;
    }
    
    @Override
    public String toString() {
        return id + "\t" + name;
    }

    @Override
    public boolean equals(Object o) {
        if (this == o) return true;
        if (o == null || getClass() != o.getClass()) return false;
        PairWritable that = (PairWritable) o;
        return id == that.id &&
                Objects.equals(name, that.name);
    }

    @Override
    public int hashCode() {
        return Objects.hash(id, name);
    }

    public void write(DataOutput out) throws IOException {
        out.write(id);
        out.writeUTF(name);
    }

    public void readFields(DataInput in) throws IOException {
        this.id = in.readInt();
        this.name = in.readUTF();
    }

    @Override
    public int compareTo(PairWritable o) {

        int comp = Integer.valueOf(this.getId()).compareTo(Integer.valueOf(o.getId()));

        if( 0 != comp){
            return comp;
        }
        return this.getName().compareTo(o.getName());
    }
}