anoopj commented on code in PR #3015:
URL: https://github.com/apache/iceberg-rust/pull/3015#discussion_r3844676792
##########
crates/iceberg/src/arrow/caching_delete_file_loader.rs:
##########
@@ -927,6 +971,66 @@ mod tests {
assert!(err.message().contains("negative position"));
}
+ fn sorted_positions(dv: &DeleteVector) -> Vec<u64> {
+ let mut positions: Vec<u64> = dv.iter().collect();
+ positions.sort_unstable();
+ positions
+ }
+
+ /// Spec-compliant input: rows sorted by (file_path, pos). Exercises the
+ /// common shape: multi-position runs, several files in one batch, and a
+ /// run for "b" that continues across the batch boundary.
+ #[tokio::test]
+ async fn test_parse_positional_deletes_merges_sorted_runs() {
+ let schema =
crate::arrow::delete_filter::tests::create_pos_del_schema();
+
+ let batch1 = RecordBatch::try_new(schema.clone(), vec![
+ Arc::new(StringArray::from_iter_values(vec!["a", "a", "a", "b"])),
+ Arc::new(Int64Array::from_iter_values(vec![1i64, 3, 5, 2])),
+ ])
+ .unwrap();
+ let batch2 = RecordBatch::try_new(schema, vec![
+ Arc::new(StringArray::from_iter_values(vec!["b", "c"])),
+ Arc::new(Int64Array::from_iter_values(vec![4i64, 0])),
+ ])
+ .unwrap();
+ let stream = futures::stream::iter(vec![Ok(batch1),
Ok(batch2)]).boxed();
+
+ let result =
CachingDeleteFileLoader::parse_positional_deletes_record_batch_stream(stream)
+ .await
+ .unwrap();
+
+ assert_eq!(result.len(), 3);
+ assert_eq!(sorted_positions(&result["a"]), vec![1, 3, 5]);
+ assert_eq!(sorted_positions(&result["b"]), vec![2, 4]);
Review Comment:
That makes sense. Added two focused tests.
--
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]
