Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/21004#discussion_r180995890
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSource.scala
---
@@ -384,13 +356,9 @@ case class DataSource(
// This is a non-streaming file based datasource.
case (format: FileFormat, _) =>
- val allPaths = caseInsensitiveOptions.get("path") ++ paths
- val hadoopConf = sparkSession.sessionState.newHadoopConf()
- val globbedPaths = allPaths.flatMap(
- DataSource.checkAndGlobPathIfNecessary(hadoopConf, _,
checkFilesExist)).toArray
-
- val fileStatusCache = FileStatusCache.getOrCreate(sparkSession)
- val (dataSchema, partitionSchema) =
getOrInferFileFormatSchema(format, fileStatusCache)
+ checkAndGlobPathIfNecessary(checkEmptyGlobPath = true,
checkFilesExist = checkFilesExist)
--- End diff --
now we may glob the path twice?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
