Github user cloud-fan commented on a diff in the pull request: https://github.com/apache/spark/pull/22009#discussion_r208439720 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceRDD.scala --- @@ -51,18 +58,19 @@ class DataSourceRDD[T: ClassTag]( valuePrepared } - override def next(): T = { + override def next(): Any = { if (!hasNext) { throw new java.util.NoSuchElementException("End of stream") } valuePrepared = false reader.get() } } - new InterruptibleIterator(context, iter) + // TODO: get rid of this type hack. + new InterruptibleIterator(context, iter.asInstanceOf[Iterator[InternalRow]]) } override def getPreferredLocations(split: Partition): Seq[String] = { - split.asInstanceOf[DataSourceRDDPartition[T]].inputPartition.preferredLocations() + split.asInstanceOf[DataSourceRDDPartition].inputPartition.preferredLocations() --- End diff -- It's a common pattern in RDD that we cast the `split` to the concrete `Partition` class defined by this RDD. The partitions are created in `RDD#getPartitions`, so if we see other splits here, it's a bug.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org