c21 commented on a change in pull request #33695:
URL: https://github.com/apache/spark/pull/33695#discussion_r696272822
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala
##########
@@ -170,7 +170,16 @@ class ParquetFileFormat
val conf = sparkSession.sessionState.conf
conf.parquetVectorizedReaderEnabled && conf.wholeStageEnabled &&
schema.length <= conf.wholeStageMaxNumFields &&
- schema.forall(_.dataType.isInstanceOf[AtomicType])
+
schema.map(_.dataType).forall(isBatchReadSupported(sparkSession.sessionState.conf,
_))
+ }
+
+ private def isBatchReadSupported(sqlConf: SQLConf, dt: DataType): Boolean =
dt match {
+ case _: AtomicType =>
+ true
+ case _: ArrayType | _: MapType | _: StructType =>
+ sqlConf.parquetVectorizedReaderNestedColumnEnabled
Review comment:
We need to check the sub-field type recursively right?
--
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]
