AngersZhuuuu commented on a change in pull request #29881:
URL: https://github.com/apache/spark/pull/29881#discussion_r504714045
##########
File path: sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveUtils.scala
##########
@@ -396,6 +419,93 @@ private[spark] object HiveUtils extends Logging {
config = configurations,
barrierPrefixes = hiveMetastoreBarrierPrefixes,
sharedPrefixes = hiveMetastoreSharedPrefixes)
+ } else if (hiveMetastoreJars == "path") {
+
+ def addLocalHiveJars(file: File): Seq[URL] = {
+ if (file.getName == "*") {
+ val files = file.getParentFile.listFiles()
+ if (files == null) {
+ logWarning(s"Hive jar path '${file.getPath}' does not exist.")
+ Nil
+ } else {
+
files.filter(_.getName.toLowerCase(Locale.ROOT).endsWith(".jar")).map(_.toURL).toSeq
+ }
+ } else {
+ file.toURL :: Nil
+ }
+ }
+
+ def checkRemoteHiveJars(path: String): Seq[URL] = {
+ try {
+ val hadoopPath = new Path(path)
+ val fs = hadoopPath.getFileSystem(hadoopConf)
+ if (hadoopPath.getName == "*") {
Review comment:
> > can we use `DataSource.checkAndGlobPathIfNecessary`?
>
> Yea, I will test this.
@sunchao Follow this suggestion, we can support nested hdfs path wildcard
now.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
