如何在Hadoop中定制Writable类？ [英] How to customize Writable class in Hadoop?

问题描述

我试图实现Writable类，但我不知道如何实现一个可写类，如果在我的类中有嵌套对象，如列表等。可以任何身体帮助我吗？谢谢

  public class StorageClass implements Writable {
 
 public String xStr; 
 public String yStr; 
 
公共列表< Field> sStor 
 
 //省略ctors 
 
 
 @override 
 public void write（DataOutput out）throws IOException {
 out.writeChars（xStr ）; 
 out.WriteChars（yStr）; 
 
 //我应该做些什么List< Field> 
 
 
 $ b @override 
 public void readFields（DataInput in）throws IOException {
 xStr = in.readLine（）; 
 yStr = in.readLine（）; 
 
 //我应该做些什么List< Field> 
} 
 
} 
 
公共类SubStorage {
 public String x; 
 public String y; 
} 
 
} 
  

以下是Field类：

  public final class Field implements Comparable< Field>，Serializable {
 
 private String name; 
 private DataType dataType; 
私有对象值; 
 private FieldType fieldType; 
 
 
 public Field（）{
 
} 
 
 
 
 public Field（String name，DataType dataType ，FieldType fieldType）{
 this（name，dataType，null，fieldType）; 
 
 $ b $ public Field（String name，DataType type，Object value，FieldType fieldType）{
 this.name = name; 
 this.dataType = type; 
 this.value = value; 
 this.fieldType = fieldType; 
 
 
 
 
 
 
 $ b public enum FieldType {
 PRI，LOOKUP，SCD，VERSION，其他
 
 
 
 
 public enum DataType {
 
 UNDEFINED（4）{
 public int getSizeInBytes（Object value） {
 return STRING.getSizeInBytes（value）; 
 
 
 
 STRING（4）{
 public int getSizeInBytes（Object value）{
 if（value == null）{
返回0; 
} 
 return super.getSizeInBytes（value）+（value.toString（）。length（）* 2）; （8），
（8），
 
 
）DATETIME（8），
 BOOLEAN（1），
 BYTE（1），
 FLOAT（4），
 SHORT（2），
 CHAR（2） ，
 DATE（8），
 TIME（8），
 
 BLOB（0）{
 public int getSizeInBytes（Object value）{
 if（值== null）{
 return 0; 
} 
 return（（byte []）value）.length; 
} 
}; 
 
 private final int sizeInBytes; 
 
 private DataType（int sizeInBytes）{
 this.sizeInBytes = sizeInBytes; 
} 
 
 public int getSizeInBytes（Object value）{
 return sizeInBytes; 
} 
 
} 
  

解决方案

序列化集合非常简单。

  @Override 
 public void readFields（DataInput in）throws IOException { b $ b int size = in.readInt（）; 
 list = new ArrayList< Field>（size）; 
 for（int i = 0; i< size; i ++）{
 Field f = new Field（）; 
 f.readFields（in）; 
 list.add（f）; 
} 
} 
 
 @Override 
 public void write（DataOutput out）throws IOException {
 out.writeInt（list.size（））; 
 for（Field l：list）{
 l.write（out）; 
 
 
 
 
 $ b $ p $字段必须实现可写还有。
 
I'm trying to implement Writable class, but i have no idea on how to implement a writable class if in my class there is nested object, such as list, etc. Could any body help me? thanks
public class StorageClass implements Writable{

public String xStr;
public String yStr;

public List<Field> sStor

//omitted ctors


@override
public void write(DataOutput out) throws IOException{
    out.writeChars(xStr);
    out.WriteChars(yStr);

    //WHAT SHOULD I DO FOR List<Field>

}

@override
public void readFields(DataInput in) throws IOException{
    xStr = in.readLine();
    yStr = in.readLine();

    //WHAT SHOULD I DO FOR List<Field>
}

}

public class SubStorage{
    public String x;
    public String y;
}

}
Following is the Field class:    
public final class Field implements Comparable<Field>, Serializable {

    private String name;
    private DataType dataType;
    private Object value;
    private FieldType fieldType;


    public Field(){

    }



    public  Field(String name, DataType dataType, FieldType fieldType){
        this(name, dataType, null, fieldType);
    }

    public  Field(String name, DataType type, Object value, FieldType fieldType){
        this.name = name;
        this.dataType = type;
        this.value = value;
        this.fieldType = fieldType;
    }
}





public enum FieldType {
    PRI, LOOKUP, SCD, VERSION, OTHER
}



public enum DataType {

    UNDEFINED(4) {
        public int getSizeInBytes(Object value) {
            return STRING.getSizeInBytes(value);
        }
    },

    STRING(4) {
        public int getSizeInBytes(Object value) {
            if (value == null) {
                return 0;
            }
            return super.getSizeInBytes(value) + (value.toString().length() * 2); // length + chars
        }
    },

    INT(4),
    LONG(8),
    DOUBLE(8),
    DATETIME(8),
    BOOLEAN(1),
    BYTE(1),
    FLOAT(4),
    SHORT(2),
    CHAR(2),
    DATE(8),
    TIME(8),

    BLOB(0) {
        public int getSizeInBytes(Object value) {
            if (value == null) {
                return 0;
            }
            return ((byte[])value).length;
        }
    };

    private final int sizeInBytes;

    private DataType(int sizeInBytes) {
        this.sizeInBytes = sizeInBytes;
    }

    public int getSizeInBytes(Object value) {
        return sizeInBytes;
    }

}

解决方案
Serializing collections is quite simple.
@Override
public void readFields(DataInput in) throws IOException {
    int size = in.readInt();
    list= new ArrayList<Field>(size);
    for(int i = 0; i < size; i++){
        Field f = new Field();
        f.readFields(in);
        list.add(f);
    }
}

@Override
public void write(DataOutput out) throws IOException {
    out.writeInt(list.size());
    for (Field l : list) {
        l.write(out);
    }
}
Field has to implement Writable as well.

                        
这篇关于如何在Hadoop中定制Writable类？的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！