viirya commented on a change in pull request #33650:
URL: https://github.com/apache/spark/pull/33650#discussion_r701326979
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/FileScanBuilder.scala
##########
@@ -57,6 +68,26 @@ abstract class FileScanBuilder(
StructType(fields)
}
+ override def pushFilters(filters: Seq[Expression]): Seq[Expression] = {
+ val (partitionFilters, dataFilters) =
+ DataSourceUtils.getPartitionFiltersAndDataFilters(partitionSchema,
filters)
+ this.partitionFilters = partitionFilters
+ this.dataFilters = dataFilters
+ val translatedFilters = mutable.ArrayBuffer.empty[sources.Filter]
+ for (filterExpr <- dataFilters) {
+ val translated = DataSourceStrategy.translateFilter(filterExpr, true)
+ if (translated.nonEmpty) {
+ translatedFilters += translated.get
+ }
+ }
+ pushedDataFilters = pushDataFilters(translatedFilters.toArray)
+ dataFilters
+ }
+
+ override def pushedFilters: Array[Filter] = pushedDataFilters
+
+ protected def pushDataFilters(dataFilters: Array[Filter]): Array[Filter] =
Array.empty[Filter]
Review comment:
Looks like the default implementation is returning empty array. So it
means by default `FileScanBuilder` won't push down data filters?
--
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]
