You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@spark.apache.org by cloud-fan <gi...@git.apache.org> on 2018/06/05 05:53:48 UTC
[GitHub] spark pull request #20915: [SPARK-23803][SQL] Support bucket pruning
Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/20915#discussion_r192953104
--- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileSourceStrategy.scala ---
@@ -50,6 +51,84 @@ import org.apache.spark.sql.execution.SparkPlan
* and add it. Proceed to the next file.
*/
object FileSourceStrategy extends Strategy with Logging {
+
+ // should prune buckets iff num buckets is greater than 1 and there is only one bucket column
+ private def shouldPruneBuckets(bucketSpec: Option[BucketSpec]): Boolean = {
+ bucketSpec match {
+ case Some(spec) => spec.bucketColumnNames.length == 1 && spec.numBuckets > 1
+ case None => false
+ }
+ }
+
+ private def getExpressionBuckets(expr: Expression,
--- End diff --
nit: code style
```
def xxx(
para1: A,
para2: B): XXX
```
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org