Github user jinxing64 commented on a diff in the pull request:
https://github.com/apache/spark/pull/19868#discussion_r181571746
--- Diff: core/src/main/scala/org/apache/spark/rdd/NewHadoopRDD.scala ---
@@ -124,17 +126,25 @@ class NewHadoopRDD[K, V](
configurable.setConf(_conf)
case _ =>
}
- val allRowSplits = inputFormat.getSplits(new JobContextImpl(_conf,
jobId)).asScala
- val rawSplits = if (ignoreEmptySplits) {
- allRowSplits.filter(_.getLength > 0)
- } else {
- allRowSplits
- }
- val result = new Array[Partition](rawSplits.size)
- for (i <- 0 until rawSplits.size) {
- result(i) = new NewHadoopPartition(id, i,
rawSplits(i).asInstanceOf[InputSplit with Writable])
+ try {
--- End diff --
Put original logic in try-catch
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
