justaparth commented on code in PR #40686:
URL: https://github.com/apache/spark/pull/40686#discussion_r1181194005
##########
connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala:
##########
@@ -299,6 +298,36 @@ private[sql] class ProtobufDeserializer(
}
}
+ private def getFieldValue(record: DynamicMessage, field: FieldDescriptor):
AnyRef = {
+ // We return a value if one of:
+ // - the field is repeated
+ // - the field is explicitly present in the serialized proto
+ // - the field is proto2 with a default
+ // - we should materialize the zero value
+ //
+ // Repeated fields have to be treated separately as they cannot have
`hasField`
+ // called on them.
+ if (
+ field.isRepeated
+ || record.hasField(field) // checks for the field explicitly being set
+ || field.hasDefaultValue
+ || shouldGetZeroValue(record, field)) {
+ record.getField(field)
+ } else {
+ null
+ }
+ }
+
+ // See the docs for materialize.default.values in [[ProtobufOptions]].
+ // Decides whether we should get the zero values. We do this when
+ // the field is not present in the proto, and theres ambiguity about
+ // whether it was never set or if it was set to its zero value (i.e.
+ // the field lacks field presence information). This is basically
+ // proto3 scalar values only.
+ private def shouldGetZeroValue(record: DynamicMessage, field:
FieldDescriptor): Boolean = {
+ !record.hasField(field) && !field.hasPresence && this.materializeZeroValues
Review Comment:
okay moved it back
--
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]
