grundprinzip commented on code in PR #38468:
URL: https://github.com/apache/spark/pull/38468#discussion_r1013643400
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/arrow/ArrowConverters.scala:
##########
@@ -128,6 +128,65 @@ private[sql] object ArrowConverters extends Logging {
}
}
+ private[sql] def toArrowBatchIterator(
+ rowIter: Iterator[InternalRow],
+ schema: StructType,
+ maxRecordsPerBatch: Int,
+ timeZoneId: String,
+ context: TaskContext): Iterator[(Array[Byte], Long, Long)] = {
+ val arrowSchema = ArrowUtils.toArrowSchema(schema, timeZoneId)
+ val allocator = ArrowUtils.rootAllocator.newChildAllocator(
+ "toArrowBatchIterator", 0, Long.MaxValue)
+
+ val root = VectorSchemaRoot.create(arrowSchema, allocator)
+ val unloader = new VectorUnloader(root)
+ val arrowWriter = ArrowWriter.create(root)
+
+ if (context != null) { // for test at driver
+ context.addTaskCompletionListener[Unit] { _ =>
+ root.close()
+ allocator.close()
+ }
+ }
+
+ new Iterator[(Array[Byte], Long, Long)] {
+
+ override def hasNext: Boolean = rowIter.hasNext || {
+ root.close()
+ allocator.close()
+ false
+ }
+
+ override def next(): (Array[Byte], Long, Long) = {
Review Comment:
did you check what happens if you do a `select * from table limit 0` I have
previously had some challenges where the query returned 0 partitions and
because of that we would not send a schema.
--
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]
