Skip to content

[SPARK-59459][CORE] Extract a helper for the HashPartitioner array-key check in PairRDDFunctions #58758

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
uros-b wants to merge 1 commit into
base: master
Choose a base branch
from
+10 −12
Open

[SPARK-59459][CORE] Extract a helper for the HashPartitioner array-key check in PairRDDFunctions #58758

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 10 additions & 12 deletions core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -526,9 +526,7 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)])
* Return a copy of the RDD partitioned using the specified partitioner.
*/
def partitionBy(partitioner: Partitioner): RDD[(K, V)] = self.withScope {
if (keyClass.isArray && partitioner.isInstanceOf[HashPartitioner]) {
throw SparkCoreErrors.hashPartitionerCannotPartitionArrayKeyError()
}
failOnHashPartitionerWithArrayKey(partitioner)
if (self.partitioner == Some(partitioner)) {
self
} else {
Expand Down Expand Up @@ -778,9 +776,7 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)])
other3: RDD[(K, W3)],
partitioner: Partitioner)
: RDD[(K, (Iterable[V], Iterable[W1], Iterable[W2], Iterable[W3]))] = self.withScope {
if (partitioner.isInstanceOf[HashPartitioner] && keyClass.isArray) {
throw SparkCoreErrors.hashPartitionerCannotPartitionArrayKeyError()
}
failOnHashPartitionerWithArrayKey(partitioner)
val cg = new CoGroupedRDD[K](Seq(self, other1, other2, other3), partitioner)
cg.mapValues { case Array(vs, w1s, w2s, w3s) =>
(vs.asInstanceOf[Iterable[V]],
Expand All @@ -796,9 +792,7 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)])
*/
def cogroup[W](other: RDD[(K, W)], partitioner: Partitioner)
: RDD[(K, (Iterable[V], Iterable[W]))] = self.withScope {
if (partitioner.isInstanceOf[HashPartitioner] && keyClass.isArray) {
throw SparkCoreErrors.hashPartitionerCannotPartitionArrayKeyError()
}
failOnHashPartitionerWithArrayKey(partitioner)
val cg = new CoGroupedRDD[K](Seq(self, other), partitioner)
cg.mapValues { case Array(vs, w1s) =>
(vs.asInstanceOf[Iterable[V]], w1s.asInstanceOf[Iterable[W]])
Expand All @@ -811,9 +805,7 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)])
*/
def cogroup[W1, W2](other1: RDD[(K, W1)], other2: RDD[(K, W2)], partitioner: Partitioner)
: RDD[(K, (Iterable[V], Iterable[W1], Iterable[W2]))] = self.withScope {
if (partitioner.isInstanceOf[HashPartitioner] && keyClass.isArray) {
throw SparkCoreErrors.hashPartitionerCannotPartitionArrayKeyError()
}
failOnHashPartitionerWithArrayKey(partitioner)
val cg = new CoGroupedRDD[K](Seq(self, other1, other2), partitioner)
cg.mapValues { case Array(vs, w1s, w2s) =>
(vs.asInstanceOf[Iterable[V]],
Expand Down Expand Up @@ -1111,4 +1103,10 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)])
private[spark] def valueClass: Class[_] = vt.runtimeClass

private[spark] def keyOrdering: Option[Ordering[K]] = Option(ord)

private def failOnHashPartitionerWithArrayKey(partitioner: Partitioner): Unit = {
if (partitioner.isInstanceOf[HashPartitioner] && keyClass.isArray) {
throw SparkCoreErrors.hashPartitionerCannotPartitionArrayKeyError()
}
}
}