nikolamand-db commented on code in PR #47525:
URL: https://github.com/apache/spark/pull/47525#discussion_r1698576113
##########
sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala:
##########
@@ -2339,6 +2340,119 @@ class DataFrameAggregateSuite extends QueryTest
test("SPARK-32761: aggregating multiple distinct CONSTANT columns") {
checkAnswer(sql("select count(distinct 2), count(distinct 2,3)"), Row(1,
1))
}
+
+ test("aggregating with various distinct expressions") {
+ abstract class AggregateTestCaseBase(
+ val query: String,
+ val resultSeq: Seq[Seq[Row]],
+ val hasExpandNodeInPlan: Boolean)
+ case class AggregateTestCase(
+ override val query: String,
+ override val resultSeq: Seq[Seq[Row]],
+ override val hasExpandNodeInPlan: Boolean)
+ extends AggregateTestCaseBase(query, resultSeq, hasExpandNodeInPlan)
+ case class AggregateTestCaseDefault(
+ override val query: String)
+ extends AggregateTestCaseBase(
+ query,
+ Seq(Seq(Row(0)), Seq(Row(1)), Seq(Row(1))),
+ hasExpandNodeInPlan = true)
+
+ val t = "t"
+ val testCases: Seq[AggregateTestCaseBase] = Seq(
+ AggregateTestCaseDefault(
+ s"""SELECT COUNT(DISTINCT "col") FROM $t"""
+ ),
+ AggregateTestCaseDefault(
+ s"SELECT COUNT(DISTINCT 1) FROM $t"
+ ),
+ AggregateTestCaseDefault(
+ s"SELECT COUNT(DISTINCT 1 + 2) FROM $t"
+ ),
+ AggregateTestCaseDefault(
+ s"SELECT COUNT(DISTINCT 1, 2, 1 + 2) FROM $t"
+ ),
+ AggregateTestCase(
+ s"SELECT COUNT(1), COUNT(DISTINCT 1) FROM $t",
+ Seq(Seq(Row(0, 0)), Seq(Row(1, 1)), Seq(Row(2, 1))),
+ hasExpandNodeInPlan = true
+ ),
+ AggregateTestCaseDefault(
+ s"""SELECT COUNT(DISTINCT 1, "col") FROM $t"""
+ ),
+ AggregateTestCaseDefault(
+ s"""SELECT COUNT(DISTINCT collation("abc")) FROM $t"""
+ ),
+ AggregateTestCaseDefault(
+ s"""SELECT COUNT(DISTINCT current_date()) FROM $t"""
+ ),
+ AggregateTestCaseDefault(
+ s"""SELECT COUNT(DISTINCT array(1, 2)[1]) FROM $t"""
+ ),
+ AggregateTestCaseDefault(
+ s"""SELECT COUNT(DISTINCT map(1, 2)[1]) FROM $t"""
+ ),
+ AggregateTestCaseDefault(
+ s"""SELECT COUNT(DISTINCT struct(1, 2).col1) FROM $t"""
+ ),
+ AggregateTestCase(
+ s"SELECT COUNT(DISTINCT 1) FROM $t GROUP BY col",
+ Seq(Seq(), Seq(Row(1)), Seq(Row(1), Row(1))),
+ hasExpandNodeInPlan = false
+ ),
+ AggregateTestCaseDefault(
+ s"SELECT COUNT(DISTINCT 1) FROM $t WHERE 1 = 1"
+ ),
+ AggregateTestCase(
+ s"SELECT COUNT(DISTINCT 1) FROM $t WHERE 1 = 0",
+ Seq(Seq(Row(0)), Seq(Row(0)), Seq(Row(0))),
+ hasExpandNodeInPlan = false
+ ),
+ AggregateTestCase(
+ s"SELECT SUM(DISTINCT 1) FROM (SELECT COUNT(DISTINCT 1) FROM $t)",
+ Seq(Seq(Row(1)), Seq(Row(1)), Seq(Row(1))),
+ hasExpandNodeInPlan = false
+ ),
+ AggregateTestCase(
+ s"SELECT SUM(DISTINCT 1) FROM (SELECT COUNT(1) FROM $t)",
+ Seq(Seq(Row(1)), Seq(Row(1)), Seq(Row(1))),
+ hasExpandNodeInPlan = false
+ ),
+ AggregateTestCase(
+ s"SELECT SUM(1) FROM (SELECT COUNT(DISTINCT 1) FROM $t)",
+ Seq(Seq(Row(1)), Seq(Row(1)), Seq(Row(1))),
+ hasExpandNodeInPlan = false
+ ),
+ AggregateTestCaseDefault(
+ s"SELECT SUM(x) FROM (SELECT COUNT(DISTINCT 1) AS x FROM $t)"),
+ AggregateTestCase(
+ s"""SELECT COUNT(DISTINCT 1), COUNT(DISTINCT "col") FROM $t""",
+ Seq(Seq(Row(0, 0)), Seq(Row(1, 1)), Seq(Row(1, 1))),
+ hasExpandNodeInPlan = true
+ ),
+ AggregateTestCase(
+ s"""SELECT COUNT(DISTINCT 1), COUNT(DISTINCT col) FROM $t""",
Review Comment:
That's right:
https://github.com/apache/spark/pull/47525/files#diff-bd3d5c79ede5675f4bf10d2efb313db893d57443d6d6d67b1f8766e6ce741271R2376.
--
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.
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
