Github user nongli commented on a diff in the pull request:
https://github.com/apache/spark/pull/10604#discussion_r49115416
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/bucket.scala
---
@@ -55,3 +59,29 @@ private[sql] abstract class BucketedOutputWriterFactory
extends OutputWriterFact
context: TaskAttemptContext): OutputWriter =
throw new UnsupportedOperationException("use bucket version")
}
+
+private[sql] object BucketingUtils {
+
+ def bucketIdExpression(bucketColumns: Seq[Attribute], numBuckets: Int):
Expression =
+ Pmod(new Murmur3Hash(bucketColumns), Literal(numBuckets))
+
+ private val bucketedFileName = """.*-(\d+)(?:\..*)?$""".r
+
+ def getBucketId(fileName: String): Int = fileName match {
+ case bucketedFileName(bucketId) => bucketId.toInt
+ }
+
+ def coalesce(
--- End diff --
This needs a comment.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
