brkyvz commented on a change in pull request #25330: [SPARK-28565][SQL]
DataFrameWriter saveAsTable support for V2 catalogs
URL: https://github.com/apache/spark/pull/25330#discussion_r312154411
##########
File path: sql/core/src/main/scala/org/apache/spark/sql/DataFrameWriter.scala
##########
@@ -485,7 +485,65 @@ final class DataFrameWriter[T] private[sql](ds:
Dataset[T]) {
* @since 1.4.0
*/
def saveAsTable(tableName: String): Unit = {
-
saveAsTable(df.sparkSession.sessionState.sqlParser.parseTableIdentifier(tableName))
+ import df.sparkSession.sessionState.analyzer.{AsTableIdentifier,
CatalogObjectIdentifier}
+ import org.apache.spark.sql.catalog.v2.CatalogV2Implicits._
+
+ val session = df.sparkSession
+
+ session.sessionState.sqlParser.parseMultipartIdentifier(tableName) match {
+ case CatalogObjectIdentifier(Some(catalog), ident) =>
+ saveAsTable(catalog.asTableCatalog, ident, modeForDSV2)
+
+ case AsTableIdentifier(tableIdentifier) =>
+ saveAsTable(tableIdentifier)
+ }
+ }
+
+
+ private def saveAsTable(catalog: TableCatalog, ident: Identifier, mode:
SaveMode): Unit = {
+ val partitioning = partitioningColumns.map { colNames =>
+ colNames.map(name => IdentityTransform(FieldReference(name)))
+ }.getOrElse(Seq.empty[Transform])
+ val bucketing = bucketColumnNames.map { cols =>
+ Seq(BucketTransform(LiteralValue(numBuckets.get, IntegerType),
cols.map(FieldReference(_))))
+ }.getOrElse(Seq.empty[Transform])
+ val partitionTransforms = partitioning ++ bucketing
+
+ val tableOpt = try Option(catalog.loadTable(ident)) catch {
+ case _: NoSuchTableException => None
+ }
+
+ val command = (mode, tableOpt) match {
+ case (SaveMode.Append, Some(table)) =>
+ AppendData.byName(DataSourceV2Relation.create(table), df.logicalPlan)
+
+ case (SaveMode.Overwrite, _) =>
Review comment:
As discussed in DSV2 sync, the old behavior was to drop the old table and
create a new one, therefore the Replace behavior here works.
----------------------------------------------------------------
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]
