Skip to content

[SPARK-55742][SQL] Support TransformingEncoder inside RowEncoder #54539

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
eejbyfeldt wants to merge 1 commit into
base: master
Choose a base branch
from
+17 −3
Open

[SPARK-55742][SQL] Support TransformingEncoder inside RowEncoder #54539

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
9 changes: 7 additions & 2 deletions sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SerializerBuildHelper.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@ import org.apache.spark.sql.catalyst.{expressions => exprs}
import org.apache.spark.sql.catalyst.DeserializerBuildHelper.expressionWithNullSafety
import org.apache.spark.sql.catalyst.encoders.{AgnosticEncoder, AgnosticEncoders, AgnosticExpressionPathEncoder, Codec, JavaSerializationCodec, KryoSerializationCodec}
import org.apache.spark.sql.catalyst.encoders.AgnosticEncoders.{ArrayEncoder, BoxedBooleanEncoder, BoxedByteEncoder, BoxedDoubleEncoder, BoxedFloatEncoder, BoxedIntEncoder, BoxedLeafEncoder, BoxedLongEncoder, BoxedShortEncoder, CharEncoder, DateEncoder, DayTimeIntervalEncoder, GeographyEncoder, GeometryEncoder, InstantEncoder, IterableEncoder, JavaBeanEncoder, JavaBigIntEncoder, JavaDecimalEncoder, JavaEnumEncoder, LocalDateEncoder, LocalDateTimeEncoder, LocalTimeEncoder, MapEncoder, OptionEncoder, PrimitiveLeafEncoder, ProductEncoder, ScalaBigIntEncoder, ScalaDecimalEncoder, ScalaEnumEncoder, StringEncoder, TimestampEncoder, TransformingEncoder, UDTEncoder, VarcharEncoder, YearMonthIntervalEncoder}
import org.apache.spark.sql.catalyst.encoders.EncoderUtils.{externalDataTypeFor, isNativeEncoder, lenientExternalDataTypeFor}
import org.apache.spark.sql.catalyst.encoders.EncoderUtils.{dataTypeForClass, externalDataTypeFor, isNativeEncoder, lenientExternalDataTypeFor}
import org.apache.spark.sql.catalyst.expressions.{BoundReference, CheckOverflow, CreateNamedStruct, Expression, IsNull, KnownNotNull, Literal, UnsafeArrayData}
import org.apache.spark.sql.catalyst.expressions.objects._
import org.apache.spark.sql.catalyst.util.{ArrayData, CharVarcharCodegenUtils, DateTimeUtils, GenericArrayData, IntervalUtils, STUtils}
Expand Down Expand Up @@ -421,11 +421,16 @@ object SerializerBuildHelper {

case AgnosticEncoders.RowEncoder(fields) =>
val serializedFields = fields.zipWithIndex.map { case (field, index) =>
val expected = field.enc match {
case AgnosticEncoders.TransformingEncoder(tag, _, _, _) =>
dataTypeForClass(tag.runtimeClass)
case other => field.enc.dataType
}
val fieldValue = createSerializer(
field.enc,
ValidateExternalType(
GetExternalRowField(input, index, field.name),
field.enc.dataType,
expected,
lenientExternalDataTypeFor(field.enc)))

val convertedField = if (field.nullable) {
Expand Down
11 changes: 10 additions & 1 deletion ...talyst/src/test/scala/org/apache/spark/sql/catalyst/encoders/ExpressionEncoderSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,7 @@ import org.apache.spark.sql.{Encoder, Encoders, Row}
import org.apache.spark.sql.catalyst.{FooClassWithEnum, FooEnum, OptionalData, PrimitiveData, ScalaReflection, ScroogeLikeExample}
import org.apache.spark.sql.catalyst.analysis.AnalysisTest
import org.apache.spark.sql.catalyst.dsl.plans._
import org.apache.spark.sql.catalyst.encoders.AgnosticEncoders.{BinaryEncoder, EncoderField, IterableEncoder, MapEncoder, OptionEncoder, PrimitiveIntEncoder, ProductEncoder, TimestampEncoder, TransformingEncoder}
import org.apache.spark.sql.catalyst.encoders.AgnosticEncoders.{BinaryEncoder, EncoderField, IterableEncoder, MapEncoder, OptionEncoder, PrimitiveIntEncoder, ProductEncoder, RowEncoder => AgnosticRowEncoder, TimestampEncoder, TransformingEncoder}
import org.apache.spark.sql.catalyst.expressions.{AttributeReference, NaNvl}
import org.apache.spark.sql.catalyst.plans.CodegenInterpretedPlanTest
import org.apache.spark.sql.catalyst.plans.logical.LocalRelation
Expand Down Expand Up @@ -829,6 +829,15 @@ class ExpressionEncoderSuite extends CodegenInterpretedPlanTest with AnalysisTes

testDataTransformingEnc(enc, data)
}

test("SPARK-55742: Transforming encoder inside row encoder") {
val enc = AgnosticRowEncoder(Seq(
EncoderField("time", longEncForTimestamp, nullable = false, Metadata.empty)
))
val data = Seq(Row(V(0L)), Row(V(1L)))
testDataTransformingEnc(enc, data)
}

// Scala / Java big decimals ----------------------------------------------------------

encodeDecodeTest(BigDecimal("9".repeat(20) + "." + "9".repeat(18)),
Expand Down