hadoop分割槽--虛擬碼
partition分割槽
//預設
public class HashPartitioner<K,V> extends Partitioner<k,v>{
public int getPartition(K key, V value, int numReduceTasks){
return (key.hashCode() & Integer.MAX_VALUE) % numReduceTasks;
}
}
//自定義
public class PhonenumPartitioner extends Partitioner<Text, FlowBean>{
@Override
public int getPartition(Text key, FlowBean value, int numPartitions){
//1、獲取手機號前三位
String phoneNum = key.toString().substring(0,3);
//2、分割槽
int partitioner = 4;
if("135".equals(phoneNum)){
return 0;
}else if("137".equals(phoneNum)){
return 1;
}else ("138".equals(phoneNum)){
return 2;
}
return partitioner;
}
}
Diriver類{
job.setPartitionerClass(PhonenumPartitioner.class);
job.setNumReduceTask(4); //設定的數量,要大於自定義的時候分割槽的數量
}