c21 commented on a change in pull request #31413:
URL: https://github.com/apache/spark/pull/31413#discussion_r569963322
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/sources/BucketedReadSuite.scala
##########
@@ -148,19 +151,51 @@ abstract class BucketedReadSuite extends QueryTest with
SQLTestUtils with Adapti
if (invalidBuckets.nonEmpty) {
fail(s"Buckets ${invalidBuckets.mkString(",")} should have been
pruned from:\n$plan")
}
+
+ withSQLConf(SQLConf.AUTO_BUCKETED_SCAN_ENABLED.key -> "true") {
+ // Bucket pruning should still work without bucketed scan
+ val planWithoutBucketedScan =
spark.table("bucketed_table").select("i", "j", "k")
+ .filter(filterCondition).queryExecution.executedPlan
+ val fileScan = getFileScan(planWithoutBucketedScan)
+ assert(!fileScan.bucketedScan, s"except no bucketed scan but
found\n$fileScan")
+
+ val tableSchema = fileScan.schema
+ val bucketColumnIndex =
tableSchema.fieldIndex(bucketColumnNames.head)
+ val bucketColumn = tableSchema.toAttributes(bucketColumnIndex)
+ val bucketColumnType = tableSchema.apply(bucketColumnIndex).dataType
+ val rowsWithInvalidBuckets = fileScan.execute().filter(row => {
Review comment:
@cloud-fan - sure, improved to remove several statements.
----------------------------------------------------------------
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:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
