zhuqi-lucas commented on code in PR #19064:
URL: https://github.com/apache/datafusion/pull/19064#discussion_r2618622289
##########
datafusion/datasource-parquet/src/opener.rs:
##########
@@ -1344,4 +1397,268 @@ mod test {
assert_eq!(num_batches, 0);
assert_eq!(num_rows, 0);
}
+
+ #[tokio::test]
+ async fn test_reverse_scan_row_groups() {
+ use parquet::file::properties::WriterProperties;
+
+ let store = Arc::new(InMemory::new()) as Arc<dyn ObjectStore>;
+
+ // Create multiple batches to ensure multiple row groups
+ let batch1 =
+ record_batch!(("a", Int32, vec![Some(1), Some(2),
Some(3)])).unwrap();
+ let batch2 =
+ record_batch!(("a", Int32, vec![Some(4), Some(5),
Some(6)])).unwrap();
+ let batch3 =
+ record_batch!(("a", Int32, vec![Some(7), Some(8),
Some(9)])).unwrap();
+
+ // Write parquet file with multiple row groups
+ // Force small row groups by setting max_row_group_size
+ let props = WriterProperties::builder()
+ .set_max_row_group_size(3) // Force each batch into its own row
group
+ .build();
+
+ let mut out = BytesMut::new().writer();
Review Comment:
Addressed it in latest PR.
--
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]
