rdblue 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_r256637814
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/WriteToDataSourceV2Exec.scala
##########
@@ -41,18 +46,114 @@ 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 =>
+ 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 {
+
+ private def isTruncate(filters: Array[Filter]): Boolean = {
+ filters.length == 1 && filters(0).isInstanceOf[AlwaysTrue]
+ }
+
+ override protected def doExecute(): RDD[InternalRow] = {
+ val batchWrite = newWriteBuilder() match {
+ case builder: SupportsTruncate if isTruncate(filters) =>
+ builder.truncate().buildForBatch()
+
+ case builder: SupportsOverwrite =>
+ builder.overwrite(filters).buildForBatch()
Review comment:
I agree that these tests should be added, but there isn't a good way to add
them right now. My plan is to add these tests as functionality is exposed in
improved APIs that make overwrite by expression available, along with a new
test table implementation. Since this PR is already large and there is no way
to access this through a public API, I think adding this can wait.
----------------------------------------------------------------
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]
