Skip to content

[SPARK-3365][SQL]Wrong schema generated for List type #4581

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 1 commit into from
Closed

[SPARK-3365][SQL]Wrong schema generated for List type #4581

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
30 changes: 15 additions & 15 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 @@ -122,6 +122,21 @@ trait ScalaReflection {
case t if t <:< typeOf[Option[_]] =>
val TypeRef(_, _, Seq(optType)) = t
Schema(schemaFor(optType).dataType, nullable = true)
// Need to decide if we actually need a special type here.
case t if t <:< typeOf[Array[Byte]] => Schema(BinaryType, nullable = true)
case t if t <:< typeOf[Array[_]] =>
val TypeRef(_, _, Seq(elementType)) = t
val Schema(dataType, nullable) = schemaFor(elementType)
Schema(ArrayType(dataType, containsNull = nullable), nullable = true)
case t if t <:< typeOf[Seq[_]] =>
val TypeRef(_, _, Seq(elementType)) = t
val Schema(dataType, nullable) = schemaFor(elementType)
Schema(ArrayType(dataType, containsNull = nullable), nullable = true)
case t if t <:< typeOf[Map[_, _]] =>
val TypeRef(_, _, Seq(keyType, valueType)) = t
val Schema(valueDataType, valueNullable) = schemaFor(valueType)
Schema(MapType(schemaFor(keyType).dataType,
valueDataType, valueContainsNull = valueNullable), nullable = true)
case t if t <:< typeOf[Product] =>
val formalTypeArgs = t.typeSymbol.asClass.typeParams
val TypeRef(_, _, actualTypeArgs) = t
Expand All @@ -144,21 +159,6 @@ trait ScalaReflection {
schemaFor(p.typeSignature.substituteTypes(formalTypeArgs, actualTypeArgs))
StructField(p.name.toString, dataType, nullable)
}), nullable = true)
// Need to decide if we actually need a special type here.
case t if t <:< typeOf[Array[Byte]] => Schema(BinaryType, nullable = true)
case t if t <:< typeOf[Array[_]] =>
val TypeRef(_, _, Seq(elementType)) = t
val Schema(dataType, nullable) = schemaFor(elementType)
Schema(ArrayType(dataType, containsNull = nullable), nullable = true)
case t if t <:< typeOf[Seq[_]] =>
val TypeRef(_, _, Seq(elementType)) = t
val Schema(dataType, nullable) = schemaFor(elementType)
Schema(ArrayType(dataType, containsNull = nullable), nullable = true)
case t if t <:< typeOf[Map[_, _]] =>
val TypeRef(_, _, Seq(keyType, valueType)) = t
val Schema(valueDataType, valueNullable) = schemaFor(valueType)
Schema(MapType(schemaFor(keyType).dataType,
valueDataType, valueContainsNull = valueNullable), nullable = true)
case t if t <:< typeOf[String] => Schema(StringType, nullable = true)
case t if t <:< typeOf[Timestamp] => Schema(TimestampType, nullable = true)
case t if t <:< typeOf[java.sql.Date] => Schema(DateType, nullable = true)
Expand Down
5 changes: 5 additions & 0 deletions sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/ScalaReflectionSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,6 +61,7 @@ case class OptionalData(
case class ComplexData(
arrayField: Seq[Int],
arrayField1: Array[Int],
arrayField2: List[Int],
arrayFieldContainsNull: Seq[java.lang.Integer],
mapField: Map[Int, Long],
mapFieldValueContainsNull: Map[Int, java.lang.Long],
Expand Down Expand Up @@ -137,6 +138,10 @@ class ScalaReflectionSuite extends FunSuite {
"arrayField1",
ArrayType(IntegerType, containsNull = false),
nullable = true),
StructField(
"arrayField2",
ArrayType(IntegerType, containsNull = false),
nullable = true),
StructField(
"arrayFieldContainsNull",
ArrayType(IntegerType, containsNull = true),
Expand Down