cloud-fan commented on code in PR #39488:
URL: https://github.com/apache/spark/pull/39488#discussion_r1073096406
##########
sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala:
##########
@@ -3924,18 +3925,18 @@ class Dataset[T] private[sql](
* @since 2.0.0
*/
def inputFiles: Array[String] = {
- val files: Seq[String] = queryExecution.optimizedPlan.collect {
+ val files: Seq[SparkPath] = queryExecution.optimizedPlan.collect {
case LogicalRelation(fsBasedRelation: FileRelation, _, _, _) =>
fsBasedRelation.inputFiles
case fr: FileRelation =>
fr.inputFiles
case r: HiveTableRelation =>
- r.tableMeta.storage.locationUri.map(_.toString).toArray
+ r.tableMeta.storage.locationUri.map(SparkPath.fromUri).toArray
case DataSourceV2ScanRelation(DataSourceV2Relation(table: FileTable, _,
_, _, _),
_, _, _, _) =>
table.fileIndex.inputFiles
}.flatten
- files.toSet.toArray
+ files.iterator.map(_.urlEncoded).toSet.toArray
Review Comment:
did we also return url-encoded path string before?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
