Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/20915#discussion_r193260674
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/DataSourceScanExec.scala
---
@@ -371,14 +387,27 @@ case class FileSourceScanExec(
val hosts = getBlockHosts(getBlockLocations(f), 0, f.getLen)
PartitionedFile(p.values, f.getPath.toUri.toString, 0, f.getLen,
hosts)
}
- }.groupBy { f =>
- BucketingUtils
- .getBucketId(new Path(f.filePath).getName)
- .getOrElse(sys.error(s"Invalid bucket file ${f.filePath}"))
}
+ val prunedBucketed = if (optionalBucketSet.isDefined) {
+ val bucketSet = optionalBucketSet.get
+ bucketed.filter {
+ f => bucketSet.get(
+ BucketingUtils.getBucketId(new Path(f.filePath).getName)
+ .getOrElse(sys.error(s"Invalid bucket file ${f.filePath}")))
+ }
+ } else {
+ bucketed
+ }
+
+ val filesGroupedToBuckets = prunedBucketed.groupBy { f =>
+ BucketingUtils
--- End diff --
can we avoid calculating bucket id from file name twice?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
