Skip to content

[SPARK-41395][SQL] InterpretedMutableProjection should use setDecimal to set null values for decimals in an unsafe row #38923

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
bersprockets wants to merge 4 commits into from
Closed

[SPARK-41395][SQL] InterpretedMutableProjection should use setDecimal to set null values for decimals in an unsafe row #38923

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
55e1b72
possible fix and test
bersprockets Dec 3, 2022
34b764a
update
bersprockets Dec 5, 2022
ea338f0
update
bersprockets Dec 5, 2022
484a7db
Simplify based on what codegen does
bersprockets Dec 6, 2022
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 ...c/main/scala/org/apache/spark/sql/catalyst/expressions/InterpretedMutableProjection.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.sql.catalyst.InternalRow
import org.apache.spark.sql.catalyst.expressions.BindReferences.bindReferences
import org.apache.spark.sql.catalyst.expressions.aggregate.NoOp
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.types.DecimalType


/**
Expand Down Expand Up @@ -72,7 +73,7 @@ class InterpretedMutableProjection(expressions: Seq[Expression]) extends Mutable

private[this] val fieldWriters: Array[Any => Unit] = validExprs.map { case (e, i) =>
val writer = InternalRow.getWriter(i, e.dataType)
if (!e.nullable) {
if (!e.nullable || e.dataType.isInstanceOf[DecimalType]) {
Copy link
Contributor

@cloud-fan cloud-fan Dec 12, 2022

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is a good catch! It's better to add some code comments to explain it, or refactor the code to make codegen and interpreted code paths share some util functions to update an internal row.

Copy link
Contributor Author

@bersprockets bersprockets Dec 12, 2022

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I can follow up, since calendar interval has the same problem (in the case of calendar interval, the issue exists in both InterpretedMutableProjection and InterpretedUnsafeProjection).

(v: Any) => writer(mutableRow, v)
} else {
(v: Any) => {
Expand Down
62 changes: 62 additions & 0 deletions ...yst/src/test/scala/org/apache/spark/sql/catalyst/expressions/MutableProjectionSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,6 +65,68 @@ class MutableProjectionSuite extends SparkFunSuite with ExpressionEvalHelper {
assert(SafeProjection.create(fixedLengthTypes)(projUnsafeRow) === inputRow)
}

def testRows(
bufferSchema: StructType,
buffer: InternalRow,
scalaRows: Seq[Seq[Any]]): Unit = {
val bufferTypes = bufferSchema.map(_.dataType).toArray
val proj = createMutableProjection(bufferTypes)

scalaRows.foreach { scalaRow =>
val inputRow = InternalRow.fromSeq(scalaRow.zip(bufferTypes).map {
case (v, dataType) => CatalystTypeConverters.createToCatalystConverter(dataType)(v)
})
val projRow = proj.target(buffer)(inputRow)
assert(SafeProjection.create(bufferTypes)(projRow) === inputRow)
}
}

testBothCodegenAndInterpreted("SPARK-41395: unsafe buffer with null decimal (high precision)") {
val bufferSchema = StructType(Array(
StructField("dec1", DecimalType(27, 2), nullable = true),
StructField("dec2", DecimalType(27, 2), nullable = true)))
val buffer = UnsafeProjection.create(bufferSchema)
.apply(new GenericInternalRow(bufferSchema.length))
val scalaRows = Seq(
Seq(null, null),
Seq(BigDecimal(77.77), BigDecimal(245.00)))
testRows(bufferSchema, buffer, scalaRows)
}

testBothCodegenAndInterpreted("SPARK-41395: unsafe buffer with null decimal (low precision)") {
val bufferSchema = StructType(Array(
StructField("dec1", DecimalType(10, 2), nullable = true),
StructField("dec2", DecimalType(10, 2), nullable = true)))
val buffer = UnsafeProjection.create(bufferSchema)
.apply(new GenericInternalRow(bufferSchema.length))
val scalaRows = Seq(
Seq(null, null),
Seq(BigDecimal(77.77), BigDecimal(245.00)))
testRows(bufferSchema, buffer, scalaRows)
}

testBothCodegenAndInterpreted("SPARK-41395: generic buffer with null decimal (high precision)") {
val bufferSchema = StructType(Array(
StructField("dec1", DecimalType(27, 2), nullable = true),
StructField("dec2", DecimalType(27, 2), nullable = true)))
val buffer = new GenericInternalRow(bufferSchema.length)
val scalaRows = Seq(
Seq(null, null),
Seq(BigDecimal(77.77), BigDecimal(245.00)))
testRows(bufferSchema, buffer, scalaRows)
}

testBothCodegenAndInterpreted("SPARK-41395: generic buffer with null decimal (low precision)") {
val bufferSchema = StructType(Array(
StructField("dec1", DecimalType(10, 2), nullable = true),
StructField("dec2", DecimalType(10, 2), nullable = true)))
val buffer = new GenericInternalRow(bufferSchema.length)
val scalaRows = Seq(
Seq(null, null),
Seq(BigDecimal(77.77), BigDecimal(245.00)))
testRows(bufferSchema, buffer, scalaRows)
}

testBothCodegenAndInterpreted("variable-length types") {
val proj = createMutableProjection(variableLengthTypes)
val scalaValues = Seq("abc", BigDecimal(10),
Expand Down