From 968408b345a0e26f7ee9105a6a0c3456cf10576a Mon Sep 17 00:00:00 2001
From: DoingDone9 <799203320@qq.com>
Date: Wed, 25 Mar 2015 11:11:52 -0700
Subject: [PATCH] [SPARK-6409][SQL] It is not necessary that avoid old inteface
of hive, because this will make some UDAF can not work.
spark avoid old inteface of hive, then some udaf can not work like "org.apache.hadoop.hive.ql.udf.generic.GenericUDAFAverage"
Author: DoingDone9 <799203320@qq.com>
Closes #5131 from DoingDone9/udaf and squashes the following commits:
9de08d0 [DoingDone9] Update HiveUdfSuite.scala
49c62dc [DoingDone9] Update hiveUdfs.scala
98b134f [DoingDone9] Merge pull request #5 from apache/master
161cae3 [DoingDone9] Merge pull request #4 from apache/master
c87e8b6 [DoingDone9] Merge pull request #3 from apache/master
cb1852d [DoingDone9] Merge pull request #2 from apache/master
c3f046f [DoingDone9] Merge pull request #1 from apache/master
---
.../scala/org/apache/spark/sql/hive/hiveUdfs.scala | 3 +--
.../spark/sql/hive/execution/HiveUdfSuite.scala | 11 ++++++++++-
2 files changed, 11 insertions(+), 3 deletions(-)
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUdfs.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUdfs.scala
index bfe43373d9..47305571e5 100644
--- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUdfs.scala
+++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUdfs.scala
@@ -375,9 +375,8 @@ private[hive] case class HiveUdafFunction(
private val returnInspector = function.init(GenericUDAFEvaluator.Mode.COMPLETE, inspectors)
- // Cast required to avoid type inference selecting a deprecated Hive API.
private val buffer =
- function.getNewAggregationBuffer.asInstanceOf[GenericUDAFEvaluator.AbstractAggregationBuffer]
+ function.getNewAggregationBuffer
override def eval(input: Row): Any = unwrap(function.evaluate(buffer), returnInspector)
diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveUdfSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveUdfSuite.scala
index cb405f56bf..d7c5d1a25a 100644
--- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveUdfSuite.scala
+++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveUdfSuite.scala
@@ -22,7 +22,7 @@ import java.util
import java.util.Properties
import org.apache.hadoop.conf.Configuration
-import org.apache.hadoop.hive.ql.udf.generic.GenericUDF
+import org.apache.hadoop.hive.ql.udf.generic.{GenericUDAFAverage, GenericUDF}
import org.apache.hadoop.hive.ql.udf.generic.GenericUDF.DeferredObject
import org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory
import org.apache.hadoop.hive.serde2.objectinspector.{ObjectInspector, ObjectInspectorFactory}
@@ -93,6 +93,15 @@ class HiveUdfSuite extends QueryTest {
sql("DROP TEMPORARY FUNCTION IF EXISTS testUdf")
}
+ test("SPARK-6409 UDAFAverage test") {
+ sql(s"CREATE TEMPORARY FUNCTION test_avg AS '${classOf[GenericUDAFAverage].getName}'")
+ checkAnswer(
+ sql("SELECT test_avg(1), test_avg(substr(value,5)) FROM src"),
+ Seq(Row(1.0, 260.182)))
+ sql("DROP TEMPORARY FUNCTION IF EXISTS test_avg")
+ TestHive.reset()
+ }
+
test("SPARK-2693 udaf aggregates test") {
checkAnswer(sql("SELECT percentile(key, 1) FROM src LIMIT 1"),
sql("SELECT max(key) FROM src").collect().toSeq)
--
GitLab