Skip to content
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

[SPARK-23588][SQL] CatalystToExternalMap should support interpreted execution #20979

Closed
wants to merge 2 commits into from
Closed

[SPARK-23588][SQL] CatalystToExternalMap should support interpreted execution #20979

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
ad6762a
CatalystToExternalMap should support interpreted execution
maropu Mar 12, 2018
07f4c82
Fix
maropu Apr 11, 2018
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
39 changes: 35 additions & 4 deletions sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,12 +28,12 @@ import scala.util.Try
import org.apache.spark.{SparkConf, SparkEnv}
import org.apache.spark.serializer._
import org.apache.spark.sql.Row
import org.apache.spark.sql.catalyst.{InternalRow, ScalaReflection}
import org.apache.spark.sql.catalyst.{CatalystTypeConverters, InternalRow, ScalaReflection}
import org.apache.spark.sql.catalyst.ScalaReflection.universe.TermName
import org.apache.spark.sql.catalyst.encoders.RowEncoder
import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.catalyst.expressions.codegen._
import org.apache.spark.sql.catalyst.util.{ArrayBasedMapData, ArrayData, GenericArrayData}
import org.apache.spark.sql.catalyst.util.{ArrayBasedMapData, ArrayData, GenericArrayData, MapData}
import org.apache.spark.sql.types._
import org.apache.spark.util.Utils

Expand Down Expand Up @@ -1009,8 +1009,39 @@ case class CatalystToExternalMap private(
override def children: Seq[Expression] =
keyLambdaFunction :: valueLambdaFunction :: inputData :: Nil

override def eval(input: InternalRow): Any =
throw new UnsupportedOperationException("Only code-generated evaluation is supported")
private lazy val inputMapType = inputData.dataType.asInstanceOf[MapType]

private lazy val keyConverter =
CatalystTypeConverters.createToScalaConverter(inputMapType.keyType)
private lazy val valueConverter =
CatalystTypeConverters.createToScalaConverter(inputMapType.valueType)

private def newMapBuilder(): Builder[AnyRef, AnyRef] = {
Copy link
Contributor

Choose a reason for hiding this comment

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

Can you make sure the builder only get's resolved once per expression instead of once per row. Can you address this in a follow-up?

val clazz = Utils.classForName(collClass.getCanonicalName + "$")
val module = clazz.getField("MODULE$").get(null)
val method = clazz.getMethod("newBuilder")
method.invoke(module).asInstanceOf[Builder[AnyRef, AnyRef]]
}

override def eval(input: InternalRow): Any = {
val result = inputData.eval(input).asInstanceOf[MapData]
if (result != null) {
val builder = newMapBuilder()
builder.sizeHint(result.numElements())
val keyArray = result.keyArray()
val valueArray = result.valueArray()
var i = 0
while (i < result.numElements()) {
val key = keyConverter(keyArray.get(i, inputMapType.keyType))
val value = valueConverter(valueArray.get(i, inputMapType.valueType))
builder += Tuple2(key, value)
i += 1
}
builder.result()
} else {
null
}
}

override def dataType: DataType = ObjectType(collClass)

Expand Down
34 changes: 28 additions & 6 deletions ...yst/src/test/scala/org/apache/spark/sql/catalyst/expressions/ObjectExpressionsSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,12 +27,14 @@ import org.apache.spark.{SparkConf, SparkFunSuite}
import org.apache.spark.serializer.{JavaSerializer, KryoSerializer}
import org.apache.spark.sql.{RandomDataGenerator, Row}
import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.catalyst.analysis.ResolveTimeZone
import org.apache.spark.sql.catalyst.encoders.{ExamplePointUDT, ExpressionEncoder, RowEncoder}
import org.apache.spark.sql.catalyst.analysis.{ResolveTimeZone, SimpleAnalyzer, UnresolvedDeserializer}
import org.apache.spark.sql.catalyst.dsl.expressions._
import org.apache.spark.sql.catalyst.encoders._
import org.apache.spark.sql.catalyst.expressions.codegen.GenerateUnsafeProjection
import org.apache.spark.sql.catalyst.expressions.objects._
import org.apache.spark.sql.catalyst.util._
import org.apache.spark.sql.catalyst.util.DateTimeUtils.{SQLDate, SQLTimestamp}
import org.apache.spark.sql.catalyst.plans.logical.{LocalRelation, Project}
import org.apache.spark.sql.catalyst.util.{ArrayBasedMapData, ArrayData, GenericArrayData}
import org.apache.spark.sql.catalyst.util.DateTimeUtils
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.types._
import org.apache.spark.unsafe.types.UTF8String
Expand Down Expand Up @@ -148,9 +150,10 @@ class ObjectExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper {
"fromPrimitiveArray", ObjectType(classOf[Array[Int]]),
Array[Int](1, 2, 3), UnsafeArrayData.fromPrimitiveArray(Array[Int](1, 2, 3))),
(DateTimeUtils.getClass, ObjectType(classOf[Date]),
"toJavaDate", ObjectType(classOf[SQLDate]), 77777, DateTimeUtils.toJavaDate(77777)),
"toJavaDate", ObjectType(classOf[DateTimeUtils.SQLDate]), 77777,
DateTimeUtils.toJavaDate(77777)),
(DateTimeUtils.getClass, ObjectType(classOf[Timestamp]),
"toJavaTimestamp", ObjectType(classOf[SQLTimestamp]),
"toJavaTimestamp", ObjectType(classOf[DateTimeUtils.SQLTimestamp]),
88888888.toLong, DateTimeUtils.toJavaTimestamp(88888888))
).foreach { case (cls, dataType, methodName, argType, arg, expected) =>
checkObjectExprEvaluation(StaticInvoke(cls, dataType, methodName,
Expand Down Expand Up @@ -415,6 +418,25 @@ class ObjectExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper {
}
}
}

implicit private def mapIntStrEncoder = ExpressionEncoder[Map[Int, String]]()

test("SPARK-23588 CatalystToExternalMap should support interpreted execution") {
// To get a resolved `CatalystToExternalMap` expression, we build a deserializer plan
// with dummy input, resolve the plan by the analyzer, and replace the dummy input
// with a literal for tests.
val unresolvedDeser = UnresolvedDeserializer(encoderFor[Map[Int, String]].deserializer)
val dummyInputPlan = LocalRelation('value.map(MapType(IntegerType, StringType)))
val plan = Project(Alias(unresolvedDeser, "none")() :: Nil, dummyInputPlan)

val analyzedPlan = SimpleAnalyzer.execute(plan)
val Alias(toMapExpr: CatalystToExternalMap, _) = analyzedPlan.expressions.head

// Replaces the dummy input with a literal for tests here
val data = Map[Int, String](0 -> "v0", 1 -> "v1", 2 -> null, 3 -> "v3")
val deserializer = toMapExpr.copy(inputData = Literal.create(data))
checkObjectExprEvaluation(deserializer, expected = data)
}
}

class TestBean extends Serializable {
Expand Down