viirya commented on code in PR #50080:
URL: https://github.com/apache/spark/pull/50080#discussion_r1971109180
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/python/PythonArrowInput.scala:
##########
@@ -140,3 +141,53 @@ private[python] trait BasicPythonArrowInput extends
PythonArrowInput[Iterator[In
}
}
}
+
+
+private[python] trait BatchedPythonArrowInput extends BasicPythonArrowInput {
+ self: BasePythonRunner[Iterator[InternalRow], _] =>
+ private val arrowMaxRecordsPerBatch = SQLConf.get.arrowMaxRecordsPerBatch
+
+ private val maxBytesPerBatch = SQLConf.get.arrowMaxBytesPerBatch
+
+ // Marker inside the input iterator to indicate the start of the next batch.
+ private var nextBatchStart: Iterator[InternalRow] = Iterator.empty
+
+ override protected def writeNextBatchToArrowStream(
+ root: VectorSchemaRoot,
+ writer: ArrowStreamWriter,
+ dataOut: DataOutputStream,
+ inputIterator: Iterator[Iterator[InternalRow]]): Boolean = {
+ if (!nextBatchStart.hasNext) {
+ if (inputIterator.hasNext) {
+ nextBatchStart = inputIterator.next()
+ }
+ }
+ if (nextBatchStart.hasNext) {
+ val startData = dataOut.size()
+
+ var numRowsInBatch: Int = 0
+
+ def underBatchSizeLimit: Boolean =
+ (maxBytesPerBatch == Int.MaxValue) || (arrowWriter.sizeInBytes() <
maxBytesPerBatch)
Review Comment:
Okay
--
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: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
