Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/20915#discussion_r192953337
--- 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,
+ bucketColumnName: String,
+ numBuckets: Int): BitSet = {
+
+ def getMatchedBucketBitSet(attr: Attribute, v: Any): BitSet = {
+ val matchedBuckets = new BitSet(numBuckets)
+ matchedBuckets.set(BucketingUtils.getBucketIdFromValue(attr,
numBuckets, v))
+ matchedBuckets
+ }
+
+ expr match {
+ case expressions.EqualTo(a: Attribute, Literal(v, _)) if a.name ==
bucketColumnName =>
--- End diff --
use `Equality` to match both `EqualTo` and `EqualNullSafe`
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
