Github user vinodkc commented on a diff in the pull request:
https://github.com/apache/spark/pull/20611#discussion_r180993462
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/command/tables.scala ---
@@ -370,26 +339,35 @@ case class LoadDataCommand(
throw new AnalysisException(
s"LOAD DATA: URI scheme is required for non-local input
paths: '$path'")
}
-
// Follow Hive's behavior:
// If LOCAL is not specified, and the path is relative,
// then the path is interpreted relative to "/user/<username>"
val uriPath = uri.getPath()
val absolutePath = if (uriPath != null &&
uriPath.startsWith("/")) {
uriPath
} else {
- s"/user/${System.getProperty("user.name")}/$uriPath"
+ s"/user/${ System.getProperty("user.name") }/$uriPath"
}
new URI(scheme, authority, absolutePath, uri.getQuery(),
uri.getFragment())
}
- val hadoopConf = sparkSession.sessionState.newHadoopConf()
- val srcPath = new Path(hdfsUri)
- val fs = srcPath.getFileSystem(hadoopConf)
- if (!fs.exists(srcPath)) {
- throw new AnalysisException(s"LOAD DATA input path does not
exist: $path")
- }
- hdfsUri
}
+ }
+ val srcPath = new Path(loadPath)
+ val fs =
srcPath.getFileSystem(sparkSession.sessionState.newHadoopConf())
+ // This handling is because while reoslving the invalid urls starting
with file:///
+ // system throws IllegalArgumentException from globStatus api,so
inorder to handle
+ // such scenarios this code is added in try catch block and after
catching the
+ // run time exception a generic error will be displayed to the user.
+ try {
+ if (null == fs.globStatus(srcPath) ||
fs.globStatus(srcPath).isEmpty) {
+ throw new AnalysisException(s"LOAD DATA input path does not exist:
$path")
+ }
+ }
+ catch {
+ case e: Exception =>
--- End diff --
Avoid catching generic exception, catch IllegalArgumentException
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
