Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/19868#discussion_r181607746
--- Diff: core/src/main/scala/org/apache/spark/rdd/HadoopRDD.scala ---
@@ -197,17 +200,24 @@ class HadoopRDD[K, V](
val jobConf = getJobConf()
// add the credentials here as this can be called before SparkContext
initialized
SparkHadoopUtil.get.addCredentials(jobConf)
- val allInputSplits = getInputFormat(jobConf).getSplits(jobConf,
minPartitions)
- val inputSplits = if (ignoreEmptySplits) {
- allInputSplits.filter(_.getLength > 0)
- } else {
- allInputSplits
- }
- val array = new Array[Partition](inputSplits.size)
- for (i <- 0 until inputSplits.size) {
- array(i) = new HadoopPartition(id, i, inputSplits(i))
+ try {
+ val allInputSplits = getInputFormat(jobConf).getSplits(jobConf,
minPartitions)
+ val inputSplits = if (ignoreEmptySplits) {
+ allInputSplits.filter(_.getLength > 0)
+ } else {
+ allInputSplits
+ }
+ val array = new Array[Partition](inputSplits.size)
+ for (i <- 0 until inputSplits.size) {
+ array(i) = new HadoopPartition(id, i, inputSplits(i))
+ }
+ array
+ } catch {
+ case e: InvalidInputException if ignoreMissingFiles =>
--- End diff --
when will this happen? the root path doesn't exist?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
