package hive.udaf;
import org.apache.hadoop.hive.ql.exec.UDAF;
import org.apache.hadoop.hive.ql.exec.UDAFEvaluator;
/**
*
* It should be very easy to follow and can be used as an example for writing
* new UDAFs.
*
* Note that Hive internally uses a different mechanism (called GenericUDAF) to
* implement built-in aggregation functions, which are harder to program but
* more efficient.
*
*/
public final class ActionCount extends UDAF {
/**
* The internal state of an aggregation for average.
*
* Note that this is only needed if the internal state cannot be represented
* by a primitive.
*
* The internal state can also contains fields with types like
* ArrayList and HashMap if needed.
*/
public static class UDAFState {
private long mCount;
private long mSum;
}
/**
* The actual class for doing the aggregation. Hive will automatically look
* for all internal classes of the UDAF that implements UDAFEvaluator.
*/
public static class UDAFExampleAvgEvaluator implements UDAFEvaluator {
UDAFState state;
public UDAFExampleAvgEvaluator() {
super();
state = new UDAFState();
init();
}
/**
* Reset the state of the aggregation.
*/
public void init() {
state.mSum = 0;
state.mCount = 0;
}
/**
* Iterate through one row of original data.
*
* The number and type of arguments need to the same as we call this UDAF
* from Hive command line.
*
* This function should always return true.
*/
public boolean iterate(String act_code,long act_times,String act_type) // 来了一行
{
if (act_code .equals(act_type))
{
state.mSum += act_times;
state.mCount++;
}
return true;
}
/**
* Terminate a partial aggregation and return the state. If the state is a
* primitive, just return primitive Java classes like Integer or String.
*/
public UDAFState terminatePartial() {//状态传递
// This is SQL standard - average of zero items should be null.
return state.mCount == 0 ? null : state;
}
/**
* Merge with a partial aggregation.
*
* This function should always have a single argument which has the same
* type as the return value of terminatePartial().
*/
public boolean merge(UDAFState o) {//子任务合并
if (o != null) {
state.mSum += o.mSum;
state.mCount += o.mCount;
}
return true;
}
/**
* Terminates the aggregation and return the final result.
*/
public long terminate() {//返回最终结果
// This is SQL standard - average of zero items should be null.
return state.mCount == 0 ? 0 : state.mSum;
}
}
private ActionCount() {
// prevent instantiation
}
}
关键还是要深刻理解map-reduce工作模型，才能更好驾驭hive。
218
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
