Skip to content

[SPARK-53538][SQL] ExpandExec should initialize the unsafe projections #52292

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

Closed
wants to merge 5 commits into from
Closed

[SPARK-53538][SQL] ExpandExec should initialize the unsafe projections #52292

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
4f8f07e
Add failing test
bersprockets Apr 24, 2025
701f6f9
Possible fix
bersprockets Apr 24, 2025
a30b1b7
Update test name
bersprockets Aug 27, 2025
f1bfb42
Update
bersprockets Sep 9, 2025
154bb84
Update test name
bersprockets Sep 9, 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
3 changes: 2 additions & 1 deletion sql/core/src/main/scala/org/apache/spark/sql/execution/ExpandExec.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,8 +56,9 @@ case class ExpandExec(
protected override def doExecute(): RDD[InternalRow] = {
val numOutputRows = longMetric("numOutputRows")

child.execute().mapPartitions { iter =>
child.execute().mapPartitionsWithIndexInternal { (index, iter) =>
val groups = projections.map(projection).toArray
groups.foreach(_.initialize(index))
new Iterator[InternalRow] {
private[this] var result: InternalRow = _
private[this] var idx = -1 // -1 means the initial state
Expand Down
20 changes: 20 additions & 0 deletions sql/core/src/test/scala/org/apache/spark/sql/connector/UpdateTableSuiteBase.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,7 @@ import org.apache.spark.SparkRuntimeException
import org.apache.spark.sql.Row
import org.apache.spark.sql.connector.catalog.{Column, ColumnDefaultValue, TableChange, TableInfo}
import org.apache.spark.sql.connector.expressions.{GeneralScalarExpression, LiteralValue}
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.types.{IntegerType, StringType}

abstract class UpdateTableSuiteBase extends RowLevelOperationSuiteBase {
Expand Down Expand Up @@ -618,6 +619,25 @@ abstract class UpdateTableSuiteBase extends RowLevelOperationSuiteBase {
Row(2) :: Nil)
}

test("SPARK-53538: update with nondeterministic assignments and no wholestage codegen") {
val extraColCount = SQLConf.get.wholeStageMaxNumFields - 4
val schema = "pk INT NOT NULL, id INT, value DOUBLE, dep STRING, " +
((1 to extraColCount).map(i => s"col$i INT").mkString(", "))
val data = (1 to 3).map { i =>
s"""{ "pk": $i, "id": $i, "value": 2.0, "dep": "hr", """ +
((1 to extraColCount).map(j => s""""col$j": $i""").mkString(", ")) +
"}"
}.mkString("\n")
createAndInitTable(schema, data)

// rand() always generates values in [0, 1) range
sql(s"UPDATE $tableNameAsString SET value = rand() WHERE id <= 2")

checkAnswer(
sql(s"SELECT count(*) FROM $tableNameAsString WHERE value < 2.0"),
Row(2) :: Nil)
}

test("update with default values") {
val idDefault = new ColumnDefaultValue("42", LiteralValue(42, IntegerType))
val columns = Array(
Expand Down