Skip to content

[spark]Handle NPE for pushdown aggregate when a datasplit has a null max/min value #6611

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

[spark]Handle NPE for pushdown aggregate when a datasplit has a null max/min value #6611

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ab214b3
[spark]Handle NPE for pushdown aggregate when a datasplit has a null …
Nov 15, 2025
10cc611
make code formatter happy
Nov 15, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions ...imon-spark-common/src/main/scala/org/apache/paimon/spark/aggregate/AggFuncEvaluator.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,6 +59,9 @@ case class MinEvaluator(idx: Int, dataField: DataField, evolutions: SimpleStatsE

override def update(dataSplit: DataSplit): Unit = {
val other = dataSplit.minValue(idx, dataField, evolutions)
if (other == null) {
return
}
if (_result == null || CompareUtils.compareLiteral(dataField.`type`(), _result, other) > 0) {
_result = other;
}
Expand All @@ -80,6 +83,9 @@ case class MaxEvaluator(idx: Int, dataField: DataField, evolutions: SimpleStatsE

override def update(dataSplit: DataSplit): Unit = {
val other = dataSplit.maxValue(idx, dataField, evolutions)
if (other == null) {
return
}
if (_result == null || CompareUtils.compareLiteral(dataField.`type`(), _result, other) < 0) {
_result = other
}
Expand Down
13 changes: 13 additions & 0 deletions ...k/paimon-spark-ut/src/test/scala/org/apache/paimon/spark/sql/PushDownAggregatesTest.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -294,4 +294,17 @@ class PushDownAggregatesTest extends PaimonSparkTestBase with AdaptiveSparkPlanH
Seq(Row(1, "t1"))
)
}

// https://github.com/apache/paimon/issues/6610
test("Push down aggregate: aggregate a column in one partition is all null and another is not") {
withTable("T") {
spark.sql("CREATE TABLE T (c1 INT, c2 LONG) PARTITIONED BY(day STRING)")

spark.sql("INSERT INTO T VALUES (1, 2, '2025-11-10')")
spark.sql("INSERT INTO T VALUES (null, 2, '2025-11-11')")

runAndCheckAggregate("SELECT MIN(c1) FROM T", Row(1) :: Nil, 0)
runAndCheckAggregate("SELECT MAX(c1) FROM T", Row(1) :: Nil, 0)
}
}
}
Loading