Dandandan commented on code in PR #5066:
URL: https://github.com/apache/arrow-datafusion/pull/5066#discussion_r1087037512
##########
datafusion/core/src/physical_plan/limit.rs:
##########
@@ -571,6 +572,36 @@ mod tests {
Ok(())
}
+ #[tokio::test]
+ async fn limit_equals_batch_size() -> Result<()> {
+ let batches = vec![
+ test::make_partition(6),
+ test::make_partition(6),
+ test::make_partition(6),
+ ];
+ let input = test::exec::TestStream::new(batches);
+
+ let index = input.index();
+ assert_eq!(index.value(), 0);
+
+ // limit of six needs to consume the entire first record batch
+ // (6 rows) and stop immediately
+ let baseline_metrics =
BaselineMetrics::new(&ExecutionPlanMetricsSet::new(), 0);
+ let limit_stream =
+ LimitStream::new(Box::pin(input), 0, Some(6), baseline_metrics);
+ assert_eq!(index.value(), 0);
+
+ let results = collect(Box::pin(limit_stream)).await.unwrap();
+ let num_rows: usize = results.into_iter().map(|b| b.num_rows()).sum();
+ // Only 6 rows should have been produced
+ assert_eq!(num_rows, 6);
+
+ // Only the first batch should be consumed
+ assert_eq!(index.value(), 1);
Review Comment:
This returns `2` on master
--
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]
