Github user aarondav commented on a diff in the pull request:
https://github.com/apache/spark/pull/1486#discussion_r17768989
--- Diff: core/src/main/scala/org/apache/spark/rdd/HadoopRDD.scala ---
@@ -309,4 +323,42 @@ private[spark] object HadoopRDD {
f(inputSplit, firstParent[T].iterator(split, context))
}
}
+
+ private[spark] class SplitInfoReflections {
+ val inputSplitWithLocationInfo =
+ Class.forName("org.apache.hadoop.mapred.InputSplitWithLocationInfo")
+ val getLocationInfo =
inputSplitWithLocationInfo.getMethod("getLocationInfo")
+ val newInputSplit =
Class.forName("org.apache.hadoop.mapreduce.InputSplit")
+ val newGetLocationInfo = newInputSplit.getMethod("getLocationInfo")
+ val splitLocationInfo =
Class.forName("org.apache.hadoop.mapred.SplitLocationInfo")
+ val isInMemory = splitLocationInfo.getMethod("isInMemory")
+ val getLocation = splitLocationInfo.getMethod("getLocation")
+ }
+
+ private[spark] val SPLIT_INFO_REFLECTIONS = try {
+ Some(new SplitInfoReflections)
+ } catch {
+ case e: Exception =>
+ logDebug("SplitLocationInfo and other new Hadoop classes are " +
+ "unavailable. Using the older Hadoop location info code.", e)
+ None
+ }
+
+ private[spark] def convertSplitLocationInfo(infos: Array[AnyRef])
:Seq[String] = {
--- End diff --
nit: '): Seq[String]`
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
