Skip to content

[SPARK-12438][SQL] Add SQLUserDefinedType support for encoder #10390

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 9 commits into from
Closed

[SPARK-12438][SQL] Add SQLUserDefinedType support for encoder #10390

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
089ab18
Add SQLUserDefinedType support for encoder.
viirya Dec 19, 2015
51b76b1
Add assert.
viirya Dec 19, 2015
d01c661
Add UserDefinedType to Cast.
viirya Dec 21, 2015
42303d2
Complete the update to Cast for UDT.
viirya Dec 30, 2015
72446f1
Move tests.
viirya Dec 31, 2015
c76ea47
Merge remote-tracking branch 'upstream/master' into encoder-udt
viirya Dec 31, 2015
62fa738
Update for new NewInstance.
viirya Dec 31, 2015
79e6ec9
Merge remote-tracking branch 'upstream/master' into encoder-udt
viirya Jan 5, 2016
80a3f7b
For comments.
viirya Jan 5, 2016
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
22 changes: 22 additions & 0 deletions sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/ScalaReflection.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -177,6 +177,7 @@ object ScalaReflection extends ScalaReflection {
case _ => UpCast(expr, expected, walkedTypePath)
}

val className = getClassNameFromType(tpe)
tpe match {
case t if !dataTypeFor(t).isInstanceOf[ObjectType] => getPath

Expand Down Expand Up @@ -360,6 +361,16 @@ object ScalaReflection extends ScalaReflection {
} else {
newInstance
}

case t if Utils.classIsLoadable(className) &&
Utils.classForName(className).isAnnotationPresent(classOf[SQLUserDefinedType]) =>
val udt = Utils.classForName(className)
.getAnnotation(classOf[SQLUserDefinedType]).udt().newInstance()
val obj = NewInstance(
udt.userClass.getAnnotation(classOf[SQLUserDefinedType]).udt(),
Nil,
dataType = ObjectType(udt.userClass.getAnnotation(classOf[SQLUserDefinedType]).udt()))
Invoke(obj, "deserialize", ObjectType(udt.userClass), getPath :: Nil)
}
}

Expand Down Expand Up @@ -409,6 +420,7 @@ object ScalaReflection extends ScalaReflection {
if (!inputObject.dataType.isInstanceOf[ObjectType]) {
inputObject
} else {
val className = getClassNameFromType(tpe)
tpe match {
case t if t <:< localTypeOf[Option[_]] =>
val TypeRef(_, _, Seq(optType)) = t
Expand Down Expand Up @@ -559,6 +571,16 @@ object ScalaReflection extends ScalaReflection {
case t if t <:< localTypeOf[java.lang.Boolean] =>
Invoke(inputObject, "booleanValue", BooleanType)

case t if Utils.classIsLoadable(className) &&
Utils.classForName(className).isAnnotationPresent(classOf[SQLUserDefinedType]) =>
val udt = Utils.classForName(className)
.getAnnotation(classOf[SQLUserDefinedType]).udt().newInstance()
val obj = NewInstance(
udt.userClass.getAnnotation(classOf[SQLUserDefinedType]).udt(),
Nil,
dataType = ObjectType(udt.userClass.getAnnotation(classOf[SQLUserDefinedType]).udt()))
Invoke(obj, "serialize", udt.sqlType, inputObject :: Nil)

case other =>
throw new UnsupportedOperationException(
s"No Encoder found for $tpe\n" + walkedTypePath.mkString("\n"))
Expand Down
14 changes: 14 additions & 0 deletions sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,7 @@ package org.apache.spark.sql.catalyst.expressions

import java.math.{BigDecimal => JavaBigDecimal}

import org.apache.spark.SparkException
import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.catalyst.analysis.TypeCheckResult
import org.apache.spark.sql.catalyst.expressions.codegen._
Expand Down Expand Up @@ -81,6 +82,9 @@ object Cast {
toField.nullable)
}

case (udt1: UserDefinedType[_], udt2: UserDefinedType[_]) if udt1.userClass == udt2.userClass =>
Copy link
Contributor

@cloud-fan cloud-fan Dec 21, 2015

Choose a reason for hiding this comment

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

I think this worth another JIRA.

Is ScalaRelfection the only place that may use UDT in Cast?

Copy link
Member Author

@viirya viirya Dec 21, 2015

Choose a reason for hiding this comment

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

I think so, as it is a special use case. I will open another JIRA for it.

Copy link
Member Author

@viirya viirya Dec 21, 2015

Choose a reason for hiding this comment

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

This fixing is submitted as pr #10410.

true

case _ => false
}

Expand Down Expand Up @@ -431,6 +435,11 @@ case class Cast(child: Expression, dataType: DataType) extends UnaryExpression {
case array: ArrayType => castArray(from.asInstanceOf[ArrayType].elementType, array.elementType)
case map: MapType => castMap(from.asInstanceOf[MapType], map)
case struct: StructType => castStruct(from.asInstanceOf[StructType], struct)
case udt: UserDefinedType[_]
if udt.userClass == from.asInstanceOf[UserDefinedType[_]].userClass =>
identity[Any]
case _: UserDefinedType[_] =>
throw new SparkException(s"Cannot cast $from to $to.")
}

private[this] lazy val cast: Any => Any = cast(child.dataType, dataType)
Expand Down Expand Up @@ -473,6 +482,11 @@ case class Cast(child: Expression, dataType: DataType) extends UnaryExpression {
castArrayCode(from.asInstanceOf[ArrayType].elementType, array.elementType, ctx)
case map: MapType => castMapCode(from.asInstanceOf[MapType], map, ctx)
case struct: StructType => castStructCode(from.asInstanceOf[StructType], struct, ctx)
case udt: UserDefinedType[_]
if udt.userClass == from.asInstanceOf[UserDefinedType[_]].userClass =>
(c, evPrim, evNull) => s"$evPrim = $c;"
case _: UserDefinedType[_] =>
throw new SparkException(s"Cannot cast $from to $to.")
}

// Since we need to cast child expressions recursively inside ComplexTypes, such as Map's
Expand Down
2 changes: 2 additions & 0 deletions ...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 @@ -242,6 +242,8 @@ class ExpressionEncoderSuite extends SparkFunSuite {
ExpressionEncoder.tuple(intEnc, ExpressionEncoder.tuple(intEnc, longEnc))
}

productTest(("UDT", new ExamplePoint(0.1, 0.2)))

test("nullable of encoder schema") {
def checkNullable[T: ExpressionEncoder](nullable: Boolean*): Unit = {
assert(implicitly[ExpressionEncoder[T]].schema.map(_.nullable) === nullable.toSeq)
Expand Down