Github user viirya commented on a diff in the pull request:
https://github.com/apache/spark/pull/19394#discussion_r143321383
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/SparkPlan.scala ---
@@ -274,19 +274,26 @@ abstract class SparkPlan extends QueryPlan[SparkPlan]
with Logging with Serializ
val byteArrayRdd = getByteArrayRdd()
val results = ArrayBuffer[InternalRow]()
- byteArrayRdd.collect().foreach { bytes =>
- decodeUnsafeRows(bytes).foreach(results.+=)
+ byteArrayRdd.collect().foreach { rdd =>
+ decodeUnsafeRows(rdd._2).foreach(results.+=)
}
results.toArray
}
+ private[spark] def executeCollectIterator(): (Long,
Iterator[InternalRow]) = {
+ val countsAndBytes = getByteArrayRdd().collect()
+ val total = countsAndBytes.map(_._1).sum
+ val rows = countsAndBytes.iterator.flatMap(rdd =>
decodeUnsafeRows(rdd._2))
--- End diff --
nit: `rdd` maybe confusing.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
