Github user zhzhan commented on a diff in the pull request:
https://github.com/apache/spark/pull/16068#discussion_r91142141
--- Diff:
sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveUDFSuite.scala
---
@@ -487,6 +488,52 @@ class HiveUDFSuite extends QueryTest with
TestHiveSingleton with SQLTestUtils {
assert(count4 == 1)
sql("DROP TABLE parquet_tmp")
}
+
+ test("Hive Stateful UDF") {
+ withUserDefinedFunction("statefulUDF" -> true, "statelessUDF" -> true)
{
+ sql(s"CREATE TEMPORARY FUNCTION statefulUDF AS
'${classOf[StatefulUDF].getName}'")
+ sql(s"CREATE TEMPORARY FUNCTION statelessUDF AS
'${classOf[StatelessUDF].getName}'")
+ withTempView("inputTable") {
--- End diff --
The test cannot resolve the function and throw the error if I use:
test("Hive Stateful UDF") {
withUserDefinedFunction("statefulUDF" -> true, "statelessUDF" -> true) {
sql(s"CREATE TEMPORARY FUNCTION statefulUDF AS
'${classOf[StatefulUDF].getName}'")
sql(s"CREATE TEMPORARY FUNCTION statelessUDF AS
'${classOf[StatelessUDF].getName}'")
val testData = spark.range(10).repartition(1)
println(s"start session: $spark")
val m = testData.select("statefulUDF() as s, ")
checkAnswer(testData.select("statefulUDF() as s").agg(max($"s")),
Row(10))
...
Do I miss anything, or is it a bug? I will investigate why this happens.
Failed to analyze query: org.apache.spark.sql.AnalysisException: cannot
resolve '`statefulUDF() as s`' given input columns: [id];;
'Project ['statefulUDF() as s]
+- Repartition 1, true
+- Range (0, 10, step=1, splits=Some(1))
org.apache.spark.sql.AnalysisException: cannot resolve '`statefulUDF() as
s`' given input columns: [id];;
'Project ['statefulUDF() as s]
+- Repartition 1, true
+- Range (0, 10, step=1, splits=Some(1))
at
org.apache.spark.sql.catalyst.analysis.package$AnalysisErrorAt.failAnalysis(package.scala:42)
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1$$anonfun$apply$2.applyOrElse(CheckAnalysis.scala:77)
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1$$anonfun$apply$2.applyOrElse(CheckAnalysis.scala:74)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:314)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:314)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:74)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:313)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionUp$1(QueryPlan.scala:282)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$2(QueryPlan.scala:292)
at
org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$2$1.apply(QueryPlan.scala:296)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.AbstractTraversable.map(Traversable.scala:104)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$2(QueryPlan.scala:296)
at
org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$7.apply(QueryPlan.scala:301)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:192)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionsUp(QueryPlan.scala:301)
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1.apply(CheckAnalysis.scala:74)
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1.apply(CheckAnalysis.scala:67)
at
org.apache.spark.sql.catalyst.trees.TreeNode.foreachUp(TreeNode.scala:132)
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$class.checkAnalysis(CheckAnalysis.scala:67)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.checkAnalysis(Analyzer.scala:57)
at
org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:48)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:63)
---
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]
