[GitHub] [spark] cloud-fan commented on a diff in pull request #40755: [SPARK-37829][SQL] Dataframe.joinWith outer-join should return a null value for unmatched row

["cloud-fan (via GitHub)" <gi...@apache.org>]

cloud-fan commented on code in PR #40755:
URL: https://github.com/apache/spark/pull/40755#discussion_r1166814363


##########
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's kind of we push down the null check to the children deserializers. Why is the serializer fine?



-- 
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: reviews-unsubscribe@spark.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org