Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/16931#discussion_r101315930
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/DataFrameWriter.scala ---
@@ -270,52 +269,17 @@ final class DataFrameWriter[T] private[sql](ds:
Dataset[T]) {
ifNotExists = false)).toRdd
}
- private def normalizedParCols: Option[Seq[String]] =
partitioningColumns.map { cols =>
- cols.map(normalize(_, "Partition"))
- }
-
- private def normalizedBucketColNames: Option[Seq[String]] =
bucketColumnNames.map { cols =>
- cols.map(normalize(_, "Bucketing"))
- }
-
- private def normalizedSortColNames: Option[Seq[String]] =
sortColumnNames.map { cols =>
- cols.map(normalize(_, "Sorting"))
- }
-
private def getBucketSpec: Option[BucketSpec] = {
if (sortColumnNames.isDefined) {
require(numBuckets.isDefined, "sortBy must be used together with
bucketBy")
}
- for {
- n <- numBuckets
- } yield {
+ numBuckets.map { n =>
require(n > 0 && n < 100000, "Bucket number must be greater than 0
and less than 100000.")
--- End diff --
feel free to submit one :)
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
