cloud-fan commented on a change in pull request #25830: [SPARK-29140][SQL]
Handle parameters having "array" of javaType properly in HashAggregateExec
URL: https://github.com/apache/spark/pull/25830#discussion_r326488722
##########
File path:
sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/AggregationQuerySuite.scala
##########
@@ -1018,6 +1018,24 @@ abstract class AggregationQuerySuite extends QueryTest
with SQLTestUtils with Te
val agg2 = agg1.groupBy($"text").agg(sum($"avg_res"))
checkAnswer(agg2, Row("a", BigDecimal("11.9999999994857142860000")))
}
+
+ test("SPARK-29140: HashAggregateExec aggregating binary type doesn't break
codegen compilation") {
+ val withDistinct = countDistinct($"c1")
+
+ val schema = new StructType().add("id", IntegerType, nullable = false)
+ .add("c1", BinaryType, nullable = true)
+
+ withSQLConf(
+ SQLConf.CODEGEN_SPLIT_AGGREGATE_FUNC.key -> "true",
+ SQLConf.CODEGEN_METHOD_SPLIT_THRESHOLD.key -> "1") {
+ val emptyRows = spark.sparkContext.parallelize(Seq.empty[Row], 1)
+ val aggDf = spark.createDataFrame(emptyRows, schema)
+ .groupBy($"id" % 10 as "group")
+ .agg(withDistinct)
Review comment:
nit: we can simply put `countDistinct($"c1")` here.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
