Github user liancheng commented on a diff in the pull request:
https://github.com/apache/spark/pull/15703#discussion_r87309760
--- Diff: sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUDFs.scala
---
@@ -365,4 +382,66 @@ private[hive] case class HiveUDAFFunction(
val distinct = if (isDistinct) "DISTINCT " else " "
s"$name($distinct${children.map(_.sql).mkString(", ")})"
}
+
+ override def createAggregationBuffer(): AggregationBuffer =
+ partial1ModeEvaluator.getNewAggregationBuffer
+
+ @transient
+ private lazy val inputProjection = new InterpretedProjection(children)
+
+ override def update(buffer: AggregationBuffer, input: InternalRow): Unit
= {
+ partial1ModeEvaluator.iterate(
+ buffer, wrap(inputProjection(input), inputWrappers, cached,
inputDataTypes))
+ }
+
+ override def merge(buffer: AggregationBuffer, input: AggregationBuffer):
Unit = {
+ partial2ModeEvaluator.merge(buffer,
partial1ModeEvaluator.terminatePartial(input))
+ }
+
+ override def eval(buffer: AggregationBuffer): Any = {
+ resultUnwrapper(finalModeEvaluator.terminate(buffer))
+ }
+
+ override def serialize(buffer: AggregationBuffer): Array[Byte] = {
+ aggBufferSerDe.serialize(buffer)
+ }
+
+ override def deserialize(bytes: Array[Byte]): AggregationBuffer = {
+ aggBufferSerDe.deserialize(bytes)
+ }
+
+ // Helper class used to de/serialize Hive UDAF `AggregationBuffer`
objects
+ private class AggregationBufferSerDe {
+ private val partialResultUnwrapper =
unwrapperFor(partialResultInspector)
+
+ private val partialResultWrapper = wrapperFor(partialResultInspector,
partialResultDataType)
+
+ private val projection =
UnsafeProjection.create(Array(partialResultDataType))
--- End diff --
It does work as expected:
```
scala> sql("CREATE TEMPORARY FUNCTION hive_max AS
'org.apache.hadoop.hive.ql.udf.generic.GenericUDAFMax'")
res0: org.apache.spark.sql.DataFrame = []
scala> spark.range(100).createOrReplaceTempView("t")
scala> sql("SELECT hive_max(id) FROM t").explain()
== Physical Plan ==
SortAggregate(key=[], functions=[hive_max(hive_max,
HiveFunctionWrapper(org.apache.hadoop.hive.ql.udf.generic.GenericUDAFMax,org.apache.hadoop.hive.ql.udf.generic.GenericUDAFMax@144792d5),
id#1L, false, 0, 0)])
+- Exchange SinglePartition
+- SortAggregate(key=[], functions=[partial_hive_max(hive_max,
HiveFunctionWrapper(org.apache.hadoop.hive.ql.udf.generic.GenericUDAFMax,org.apache.hadoop.hive.ql.udf.generic.GenericUDAFMax@144792d5),
id#1L, false, 0, 0)])
+- *Range (0, 100, step=1, splits=Some(8))
scala> sql("SELECT hive_max(id) FROM t").show()
+-------------+
|hive_max( id)|
+-------------+
| 99|
+-------------+
```
Why do you think `UnsafeProjection` can't be used here?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
