Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/17510#discussion_r109374757
--- Diff:
sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala ---
@@ -1039,37 +1039,14 @@ private[spark] class HiveExternalCatalog(conf:
SparkConf, hadoopConf: Configurat
defaultTimeZoneId: String): Seq[CatalogTablePartition] = withClient {
val rawTable = getRawTable(db, table)
val catalogTable = restoreTableMetadata(rawTable)
- val partitionColumnNames = catalogTable.partitionColumnNames.toSet
- val nonPartitionPruningPredicates = predicates.filterNot {
- _.references.map(_.name).toSet.subsetOf(partitionColumnNames)
- }
- if (nonPartitionPruningPredicates.nonEmpty) {
- sys.error("Expected only partition pruning predicates: " +
- predicates.reduceLeft(And))
- }
+ val partColNameMap = buildLowerCasePartColNameMap(catalogTable)
- val partitionSchema = catalogTable.partitionSchema
- val partColNameMap = buildLowerCasePartColNameMap(getTable(db, table))
-
- if (predicates.nonEmpty) {
- val clientPrunedPartitions = client.getPartitionsByFilter(rawTable,
predicates).map { part =>
+ val clientPrunedPartitions =
+ client.getPartitionsByFilter(rawTable, predicates).map { part =>
--- End diff --
if `predicates.isEmpty`, the previous code will run `client.getPartitions`.
Can you double check there is no performance regression?
---
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
