yuchenhuo commented on a change in pull request #26957: [WIP][SPARK-30314] Add
identifier and catalog information to DataSourceV2Relation
URL: https://github.com/apache/spark/pull/26957#discussion_r365040141
##########
File path: sql/core/src/main/scala/org/apache/spark/sql/DataFrameReader.scala
##########
@@ -206,27 +207,29 @@ class DataFrameReader private[sql](sparkSession:
SparkSession) extends Logging {
val finalOptions = sessionOptions ++ extraOptions.toMap ++ pathsOption
val dsOptions = new CaseInsensitiveStringMap(finalOptions.asJava)
- val table = provider match {
+ val (table, catalogOpt, ident) = provider match {
case _: SupportsCatalogOptions if userSpecifiedSchema.nonEmpty =>
throw new IllegalArgumentException(
s"$source does not support user specified schema. Please don't
specify the schema.")
case hasCatalog: SupportsCatalogOptions =>
val ident = hasCatalog.extractIdentifier(dsOptions)
val catalog = CatalogV2Util.getTableProviderCatalog(
hasCatalog,
- sparkSession.sessionState.catalogManager,
+ catalogManager,
dsOptions)
- catalog.loadTable(ident)
+ (catalog.loadTable(ident),
catalogManager.catalogIdentifier(catalog), Seq(ident))
case _ =>
userSpecifiedSchema match {
- case Some(schema) => provider.getTable(dsOptions, schema)
- case _ => provider.getTable(dsOptions)
+ case Some(schema) => (provider.getTable(dsOptions, schema), None,
Seq.empty)
+ case _ => (provider.getTable(dsOptions), None, Seq.empty)
Review comment:
Any suggestion around what the identifier should be here?
----------------------------------------------------------------
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:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
