dongjoon-hyun commented on code in PR #45703:
URL: https://github.com/apache/spark/pull/45703#discussion_r1539455046
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetSchemaConverter.scala:
##########
@@ -404,6 +401,35 @@ class ParquetToSparkSchemaConverter(
}
}
+ private def convertVariantField(groupColumn: GroupColumnIO): ParquetColumn =
{
+ if (groupColumn.getChildrenCount != 2 ) {
+ // We may allow more than two children in the future, so consider this
unsupported.
+ throw QueryCompilationErrors.
+ parquetTypeUnsupportedYetError("variant with more than two fields")
+ }
+ // Find the binary columns, and validate that they have the correct type.
+ val valueAndMetadata = Seq("value", "metadata").map { colName =>
+ val idx = (0 until groupColumn.getChildrenCount)
+ .find(groupColumn.getChild(_).getName == colName)
+ if (idx.isEmpty) {
+ throw QueryCompilationErrors.illegalParquetTypeError(s"variant missing
$colName field")
+ }
+ val child = groupColumn.getChild(idx.get)
+ // The value and metadata cannot be individually null, only the full
struct can.
+ if (child.getType.getRepetition != REQUIRED ||
+ !child.isInstanceOf[PrimitiveColumnIO] ||
Review Comment:
nit. Indentation?
--
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]
