dongjoon-hyun commented on a change in pull request #31958:
URL: https://github.com/apache/spark/pull/31958#discussion_r602918532
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcFileFormat.scala
##########
@@ -131,11 +131,27 @@ class OrcFileFormat
}
}
+ private def supportBatchForNestedColumn(
+ sparkSession: SparkSession,
+ schema: StructType): Boolean = {
+ val hasNestedColumn = schema.map(_.dataType).exists {
+ case _: ArrayType | _: MapType | _: StructType => true
+ case _ => false
+ }
+ if (hasNestedColumn) {
+ sparkSession.sessionState.conf.orcVectorizedReaderNestedColumnEnabled
+ } else {
+ true
+ }
+ }
+
override def supportBatch(sparkSession: SparkSession, schema: StructType):
Boolean = {
val conf = sparkSession.sessionState.conf
conf.orcVectorizedReaderEnabled && conf.wholeStageEnabled &&
schema.length <= conf.wholeStageMaxNumFields &&
- schema.forall(_.dataType.isInstanceOf[AtomicType])
+ schema.forall(s => supportDataType(s.dataType) &&
+ !s.dataType.isInstanceOf[UserDefinedType[_]]) &&
+ supportBatchForNestedColumn(sparkSession, schema)
Review comment:
Can we do the same thing for Parquet, @c21 ?
--
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.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
