viirya commented on a change in pull request #33639:
URL: https://github.com/apache/spark/pull/33639#discussion_r699900034
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/parquet/ParquetPartitionReaderFactory.scala
##########
@@ -87,36 +110,73 @@ case class ParquetPartitionReaderFactory(
}
override def buildReader(file: PartitionedFile):
PartitionReader[InternalRow] = {
- val reader = if (enableVectorizedReader) {
- createVectorizedReader(file)
+ val fileReader = if (aggregation.isEmpty) {
+ val reader = if (enableVectorizedReader) {
+ createVectorizedReader(file)
+ } else {
+ createRowBaseReader(file)
+ }
+
+ new PartitionReader[InternalRow] {
+ override def next(): Boolean = reader.nextKeyValue()
+
+ override def get(): InternalRow =
reader.getCurrentValue.asInstanceOf[InternalRow]
+
+ override def close(): Unit = reader.close()
+ }
} else {
- createRowBaseReader(file)
- }
+ new PartitionReader[InternalRow] {
+ var hasNext = true
Review comment:
nit: `private`?
--
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]
