gengliangwang commented on a change in pull request #23684: [SPARK-26765][SQL]
Avro: Validate input and output schema
URL: https://github.com/apache/spark/pull/23684#discussion_r251892805
##########
File path:
external/avro/src/main/scala/org/apache/spark/sql/avro/AvroFileFormat.scala
##########
@@ -243,6 +243,23 @@ private[avro] class AvroFileFormat extends FileFormat
}
}
}
+
+ override def supportDataType(dataType: DataType): Boolean = dataType match {
+ case _: AtomicType => true
+
+ case st: StructType => st.forall { f => supportDataType(f.dataType) }
+
+ case ArrayType(elementType, _) => supportDataType(elementType)
+
+ case MapType(keyType, valueType, _) =>
+ supportDataType(keyType) && supportDataType(valueType)
+
+ case udt: UserDefinedType[_] => supportDataType(udt.sqlType)
+
+ case _: NullType => true
+
+ case _ => false
Review comment:
E.g Interval data type. The supported types are the same as JSON.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
