viirya commented on code in PR #50301:
URL: https://github.com/apache/spark/pull/50301#discussion_r2031248970
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/python/PythonArrowOutput.scala:
##########
@@ -83,17 +89,37 @@ private[python] trait PythonArrowOutput[OUT <: AnyRef] {
self: BasePythonRunner[
throw writer.exception.get
}
try {
- if (reader != null && batchLoaded) {
+ if (batchLoaded && rowCount > 0 && currentRowIdx < rowCount) {
+ val batchRoot = if (arrowMaxRecordsPerOutputBatch > 0) {
+ val remainingRows = rowCount - currentRowIdx
+ if (remainingRows > arrowMaxRecordsPerOutputBatch) {
+ root.slice(currentRowIdx, arrowMaxRecordsPerOutputBatch)
+ } else {
+ root
+ }
+ } else {
+ root
+ }
+
+ currentRowIdx = currentRowIdx + batchRoot.getRowCount
+
+ vectors = batchRoot.getFieldVectors().asScala.map { vector =>
+ new ArrowColumnVector(vector)
+ }.toArray[ColumnVector]
+
+ val batch = new ColumnarBatch(vectors)
+ batch.setNumRows(batchRoot.getRowCount)
+ deserializeColumnarBatch(batch, schema)
Review Comment:
I put the code change into isolation now. I will add some tests then.
--
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
