cloud-fan commented on code in PR #40755:
URL: https://github.com/apache/spark/pull/40755#discussion_r1169501050
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/encoders/ExpressionEncoder.scala:
##########
@@ -97,26 +97,33 @@ object ExpressionEncoder {
}
val newSerializer = CreateStruct(serializers)
+ def nullSafe(input: Expression, result: Expression): Expression = {
+ If(IsNull(input), Literal.create(null, result.dataType), result)
+ }
+
val newDeserializerInput = GetColumnByOrdinal(0, newSerializer.dataType)
- val deserializers = encoders.zipWithIndex.map { case (enc, index) =>
+ val childrenDeserializers = encoders.zipWithIndex.map { case (enc, index)
=>
val getColExprs = enc.objDeserializer.collect { case c:
GetColumnByOrdinal => c }.distinct
assert(getColExprs.size == 1, "object deserializer should have only one
" +
s"`GetColumnByOrdinal`, but there are ${getColExprs.size}")
val input = GetStructField(newDeserializerInput, index)
- enc.objDeserializer.transformUp {
+ val newDeserializer = enc.objDeserializer.transformUp {
case GetColumnByOrdinal(0, _) => input
}
- }
- val newDeserializer = NewInstance(cls, deserializers, ObjectType(cls),
propagateNull = false)
- def nullSafe(input: Expression, result: Expression): Expression = {
- If(IsNull(input), Literal.create(null, result.dataType), result)
+ if (enc.objSerializer.nullable) {
+ nullSafe(input, newDeserializer)
+ } else {
+ newDeserializer
+ }
}
+ val newDeserializer =
+ NewInstance(cls, childrenDeserializers, ObjectType(cls), propagateNull =
false)
new ExpressionEncoder[Any](
nullSafe(newSerializerInput, newSerializer),
- nullSafe(newDeserializerInput, newDeserializer),
Review Comment:
It looks correct to me to add the null check for the children deserializers.
But I don't quite understand why this PR removes the outermost null check.
After looking at the code, I think it doesn't matter, as the outermost null
check will be removed anyway:
https://github.com/apache/spark/blob/master/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/encoders/ExpressionEncoder.scala#L274
Since this is unrelated to this PR, let's not touch it. If you do want to
fix it (adding null check and removing it later is useless), let's fix the
serializer as well.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
