Github user mallman commented on a diff in the pull request:
https://github.com/apache/spark/pull/15998#discussion_r89678259
--- Diff:
sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala ---
@@ -922,6 +923,29 @@ private[spark] class HiveExternalCatalog(conf:
SparkConf, hadoopConf: Configurat
/**
* Returns the partition names from hive metastore for a given table in
a database.
*/
+ override def listPartitionNames(
+ db: String,
+ table: String,
+ partialSpec: Option[TablePartitionSpec] = None): Seq[String] =
withClient {
+ val actualPartColNames = getTable(db, table).partitionColumnNames
+ val clientPartitionNames =
+ client.getPartitionNames(db, table,
partialSpec.map(lowerCasePartitionSpec))
+
+ if (actualPartColNames.exists(partColName => partColName !=
partColName.toLowerCase)) {
+ clientPartitionNames.map { partName =>
+ val partSpec = PartitioningUtils.parsePathFragmentAsSeq(partName)
+ partSpec.map { case (partName, partValue) =>
+ actualPartColNames.find(_.equalsIgnoreCase(partName)).get + "="
+ partValue
+ }.mkString("/")
+ }
+ } else {
+ clientPartitionNames
--- End diff --
I'll try a build with and without this code branch and see if there's a
noticeable performance difference.
---
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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
