anishshri-db commented on code in PR #48110:
URL: https://github.com/apache/spark/pull/48110#discussion_r1760492985
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/state/StateDataSource.scala:
##########
@@ -374,6 +377,15 @@ object StateSourceOptions extends DataSourceOptions {
val stateVarName = Option(options.get(STATE_VAR_NAME))
.map(_.trim)
+ val flattenCollectionTypes = try {
+ Option(options.get(FLATTEN_COLLECTION_TYPES))
+ .map(_.toBoolean).getOrElse(true)
+ } catch {
+ case _: Exception =>
Review Comment:
Done
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/state/StatePartitionReader.scala:
##########
@@ -178,44 +176,75 @@ class StatePartitionReader(
}
}
+ private def processListStateEntries(stateVarName: String):
Iterator[InternalRow] = {
+ if (partition.sourceOptions.flattenCollectionTypes) {
+ store
+ .iterator(stateVarName)
+ .flatMap { pair =>
+ val key = pair.key
+ val result = store.valuesIterator(key, stateVarName)
+ result.map { entry =>
+ SchemaUtil.unifyStateRowPair((key, entry), partition.partition)
+ }
+ }
+ } else {
+ store
+ .iterator(stateVarName)
+ .map { pair =>
+ val key = pair.key
+ val result = store.valuesIterator(key, stateVarName)
+ var unsafeRowArr: Seq[UnsafeRow] = Seq.empty
+ result.foreach { entry =>
+ unsafeRowArr = unsafeRowArr :+ entry.copy()
+ }
Review Comment:
Done
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
