Github user davies commented on a diff in the pull request: https://github.com/apache/spark/pull/14690#discussion_r83065354 --- Diff: sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala --- @@ -616,6 +617,44 @@ private[spark] class HiveExternalCatalog(conf: SparkConf, hadoopConf: Configurat client.getPartition(db, table, spec) } + override def listPartitionsByFilter( + db: String, + table: String, + predicates: Seq[Expression]): Seq[CatalogTablePartition] = withClient { + val catalogTable = client.getTable(db, table) + 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 partitionSchema = catalogTable.partitionSchema + + if (predicates.nonEmpty) { + val clientPrunedPartitions = + client.getPartitionsByFilter(catalogTable, predicates) + val boundPredicate = + InterpretedPredicate.create(predicates.reduce(And).transform { + case att: AttributeReference => + val index = partitionSchema.indexWhere(_.name == att.name) + BoundReference(index, partitionSchema(index).dataType, nullable = true) + }) + clientPrunedPartitions.filter { case CatalogTablePartition(spec, _, _) => + val row = + InternalRow.fromSeq(partitionSchema.map { case StructField(name, dataType, _, _) => + Cast(Literal(spec(name)), dataType).eval() + }) + boundPredicate(row) --- End diff -- We should have a logging for false-positive from Hive client?
--- 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