MapReduce自定义数据类型

实现WritableComparable接口的类大多数（在io包中的都可以）可以作为MapReduce中Mapper或Reducer的key-value数据类型。在hadoop框架中自带实现WritableComparable接口的类（FlowBean是自定义的）有：

可以看出，自带的类实现了对整形，浮点型，布尔型及String（Text类）的封装，都是比较简单的数据类型，在实际应用中通常需要自定义数据类型。在写自定义数据类之前首先分析一下自带的LongWritable数据类型，如下：

public class LongWritable implements WritableComparable<LongWritable> {  private long value;  public LongWritable() {}  public LongWritable(long value) { set(value); }  /** Set the value of this LongWritable. */  public void set(long value) { this.value = value; }  /** Return the value of this LongWritable. */  public long get() { return value; }  @Override  public void readFields(DataInput in) throws IOException {    value = in.readLong();  }  @Override  public void write(DataOutput out) throws IOException {    out.writeLong(value);  }  /** Returns true iff <code>o</code> is a LongWritable with the same value. */  @Override  public boolean equals(Object o) {    if (!(o instanceof LongWritable))      return false;    LongWritable other = (LongWritable)o;    return this.value == other.value;  }  @Override  public int hashCode() {    return (int)value;  }  /** Compares two LongWritables. */  @Override  public int compareTo(LongWritable o) {    long thisValue = this.value;    long thatValue = o.value;    return (thisValue<thatValue ? -1 : (thisValue==thatValue ? 0 : 1));  }  @Override  public String toString() {    return Long.toString(value);  }}

LongWritable类主要包括一个私有类变量、该变量的get,set方法、一个无参构造函数和有参数构造函数、WritableComparable接口的readFields方法和write方法、Comparable接口的compareTo方法、同时重写了toString方法。

根据上述分析自定义的数据类型也应当包括这些方法，比如用于进行手机流量统计FlowBean。

package sempp.lsl.hadoop.mr.flowSum;import java.io.DataInput;import java.io.DataOutput;import java.io.IOException;import org.apache.hadoop.io.WritableComparable;public class FlowBean implements WritableComparable<FlowBean>{private String phone;private long uploadFlow;private long downloadFlow;private long sumFlow;public FlowBean(){//在反序列化时，反射机制需要调用空参构造函数}//为了初始化方便加入带参数构造函数public FlowBean(String phone, long uploadFlow, long downloadFlow) {this.phone = phone;this.uploadFlow = uploadFlow;this.downloadFlow = downloadFlow;this.sumFlow=uploadFlow+downloadFlow;}public String getPhone() {return phone;}public void setPhone(String phone) {this.phone = phone;}public long getUploadFlow() {return uploadFlow;}public void setUploadFlow(long uploadFlow) {this.uploadFlow = uploadFlow;}public long getDownloadFlow() {return downloadFlow;}public void setDownloadFlow(long downloadFlow) {this.downloadFlow = downloadFlow;}public long getsumFlow() {return sumFlow;}public void setsumFlow(long sumFlow) {this.sumFlow = sumFlow;}//序列化对象  将java对象转换为字节，并将字节写入二进制流中public void write(DataOutput out) throws IOException {out.writeUTF(phone);out.writeLong(uploadFlow);out.writeLong(downloadFlow);out.writeLong(sumFlow);}//从数据流中反序列化 从数据流中读出对象，必须跟序列化时的顺序保持一致public void readFields(DataInput in) throws IOException {phone = in.readUTF();uploadFlow=in.readLong();downloadFlow=in.readLong();sumFlow=in.readLong();}/** * 重写这个toString作为 输出 */@Overridepublic String toString(){return ""+phone+"\t"+uploadFlow+"\t"+downloadFlow+"\t"+sumFlow;}/** bean作为key时按照sumFlow进行排序 */       public int compareTo(FlowBean o) {return sumFlow>o.getsumFlow()?-1:1;}}