cloud-fan commented on a change in pull request #23606: [SPARK-26666][SQL]
Support DSv2 overwrite and dynamic partition overwrite.
URL: https://github.com/apache/spark/pull/23606#discussion_r257113339
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/WriteToDataSourceV2Exec.scala
##########
@@ -41,18 +46,107 @@ case class WriteToDataSourceV2(batchWrite: BatchWrite,
query: LogicalPlan)
override def output: Seq[Attribute] = Nil
}
+case class AppendDataExec(
+ table: SupportsBatchWrite,
+ writeOptions: DataSourceOptions,
+ query: SparkPlan) extends V2TableWriteExec with BatchWriteHelper {
+
+ override protected def doExecute(): RDD[InternalRow] = {
+ val batchWrite = newWriteBuilder() match {
+ case builder: SupportsSaveMode => // TODO: Remove this
+ builder.mode(SaveMode.Append).buildForBatch()
+
+ case builder =>
+ builder.buildForBatch()
+ }
+ doWrite(batchWrite)
+ }
+}
+
+case class OverwriteByExpressionExec(
+ table: SupportsBatchWrite,
+ filters: Array[Filter],
+ writeOptions: DataSourceOptions,
+ query: SparkPlan) extends V2TableWriteExec with BatchWriteHelper {
+
+ override protected def doExecute(): RDD[InternalRow] = {
+ val batchWrite = newWriteBuilder() match {
+ case builder: SupportsOverwrite =>
+ builder.overwrite(filters).buildForBatch()
+
+ case builder: SupportsSaveMode => // TODO: Remove this
+ builder.mode(SaveMode.Overwrite).buildForBatch()
+
+ case _ =>
+ throw new SparkException(s"Table does not support dynamic partition
overwrite: $table")
Review comment:
Here we are executing a plan, so `AnalysisException` should not be used. I'm
still worried about `SparkException` because we are not launching a Spark job
here.
Shall we throw `IllegalStateException`? Eventually we will make this never
happen, as this kind of check should be done as early as possible.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on 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]
