cdegroc commented on a change in pull request #35139:
URL: https://github.com/apache/spark/pull/35139#discussion_r786166674
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/encoders/ExpressionEncoder.scala
##########
@@ -110,23 +110,28 @@ 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 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 {
Review comment:
Pushed a [new
commit](https://github.com/apache/spark/pull/35139/commits/3831f769b588f4deb49fe8a4fdad78f35cc995d5).
There are multiple ways to implement this. Please let me know what you think.
--
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]
