rluvaton commented on code in PR #9176:
URL: https://github.com/apache/arrow-rs/pull/9176#discussion_r2703988920
##########
arrow-row/src/lib.rs:
##########
@@ -3132,6 +3219,143 @@ mod tests {
test_nested_list::<i64>();
}
+ fn test_single_list_view<O: OffsetSizeTrait>() {
+ let mut builder = GenericListViewBuilder::<O,
_>::new(Int32Builder::new());
+ builder.values().append_value(32);
+ builder.values().append_value(52);
+ builder.values().append_value(32);
+ builder.append(true);
+ builder.values().append_value(32);
+ builder.values().append_value(52);
+ builder.values().append_value(12);
+ builder.append(true);
+ builder.values().append_value(32);
+ builder.values().append_value(52);
+ builder.append(true);
+ builder.values().append_value(32); // MASKED
+ builder.values().append_value(52); // MASKED
+ builder.append(false);
+ builder.values().append_value(32);
+ builder.values().append_null();
+ builder.append(true);
+ builder.append(true);
+ builder.values().append_value(17); // MASKED
+ builder.values().append_null(); // MASKED
+ builder.append(false);
+
+ let list = Arc::new(builder.finish()) as ArrayRef;
+ let d = list.data_type().clone();
+
+ let converter =
RowConverter::new(vec![SortField::new(d.clone())]).unwrap();
+
+ let rows = converter.convert_columns(&[Arc::clone(&list)]).unwrap();
+ assert!(rows.row(0) > rows.row(1)); // [32, 52, 32] > [32, 52, 12]
+ assert!(rows.row(2) < rows.row(1)); // [32, 52] < [32, 52, 12]
+ assert!(rows.row(3) < rows.row(2)); // null < [32, 52]
+ assert!(rows.row(4) < rows.row(2)); // [32, null] < [32, 52]
+ assert!(rows.row(5) < rows.row(2)); // [] < [32, 52]
+ assert!(rows.row(3) < rows.row(5)); // null < []
+ assert_eq!(rows.row(3), rows.row(6)); // null = null (different masked
values)
+
+ let back = converter.convert_rows(&rows).unwrap();
+ assert_eq!(back.len(), 1);
+ back[0].to_data().validate_full().unwrap();
+
+ // Verify the content matches (ListView may have different physical
layout but same logical content)
+ let back_list_view = back[0]
+ .as_any()
+ .downcast_ref::<GenericListViewArray<O>>()
+ .unwrap();
+ let orig_list_view = list
+ .as_any()
+ .downcast_ref::<GenericListViewArray<O>>()
+ .unwrap();
+
+ assert_eq!(back_list_view.len(), orig_list_view.len());
+ for i in 0..back_list_view.len() {
+ assert_eq!(back_list_view.is_valid(i), orig_list_view.is_valid(i));
+ if back_list_view.is_valid(i) {
+ assert_eq!(&back_list_view.value(i), &orig_list_view.value(i));
+ }
+ }
+
+ let options = SortOptions::default().asc().with_nulls_first(false);
+ let field = SortField::new_with_options(d.clone(), options);
+ let converter = RowConverter::new(vec![field]).unwrap();
+ let rows = converter.convert_columns(&[Arc::clone(&list)]).unwrap();
+
+ assert!(rows.row(0) > rows.row(1)); // [32, 52, 32] > [32, 52, 12]
+ assert!(rows.row(2) < rows.row(1)); // [32, 52] < [32, 52, 12]
+ assert!(rows.row(3) > rows.row(2)); // null > [32, 52]
+ assert!(rows.row(4) > rows.row(2)); // [32, null] > [32, 52]
+ assert!(rows.row(5) < rows.row(2)); // [] < [32, 52]
+ assert!(rows.row(3) > rows.row(5)); // null > []
+ assert_eq!(rows.row(3), rows.row(6)); // null = null (different masked
values)
+
+ let back = converter.convert_rows(&rows).unwrap();
+ assert_eq!(back.len(), 1);
+ back[0].to_data().validate_full().unwrap();
+
+ let options = SortOptions::default().desc().with_nulls_first(false);
+ let field = SortField::new_with_options(d.clone(), options);
+ let converter = RowConverter::new(vec![field]).unwrap();
+ let rows = converter.convert_columns(&[Arc::clone(&list)]).unwrap();
+
+ assert!(rows.row(0) < rows.row(1)); // [32, 52, 32] < [32, 52, 12]
+ assert!(rows.row(2) > rows.row(1)); // [32, 52] > [32, 52, 12]
+ assert!(rows.row(3) > rows.row(2)); // null > [32, 52]
+ assert!(rows.row(4) > rows.row(2)); // [32, null] > [32, 52]
+ assert!(rows.row(5) > rows.row(2)); // [] > [32, 52]
+ assert!(rows.row(3) > rows.row(5)); // null > []
+ assert_eq!(rows.row(3), rows.row(6)); // null = null (different masked
values)
+
+ let back = converter.convert_rows(&rows).unwrap();
+ assert_eq!(back.len(), 1);
+ back[0].to_data().validate_full().unwrap();
+
+ let options = SortOptions::default().desc().with_nulls_first(true);
+ let field = SortField::new_with_options(d, options);
+ let converter = RowConverter::new(vec![field]).unwrap();
+ let rows = converter.convert_columns(&[Arc::clone(&list)]).unwrap();
+
+ assert!(rows.row(0) < rows.row(1)); // [32, 52, 32] < [32, 52, 12]
+ assert!(rows.row(2) > rows.row(1)); // [32, 52] > [32, 52, 12]
+ assert!(rows.row(3) < rows.row(2)); // null < [32, 52]
+ assert!(rows.row(4) < rows.row(2)); // [32, null] < [32, 52]
+ assert!(rows.row(5) > rows.row(2)); // [] > [32, 52]
+ assert!(rows.row(3) < rows.row(5)); // null < []
+ assert_eq!(rows.row(3), rows.row(6)); // null = null (different masked
values)
+
+ let back = converter.convert_rows(&rows).unwrap();
+ assert_eq!(back.len(), 1);
+ back[0].to_data().validate_full().unwrap();
+
+ let sliced_list = list.slice(1, 5);
+ let rows_on_sliced_list = converter
+ .convert_columns(&[Arc::clone(&sliced_list)])
+ .unwrap();
+
+ assert!(rows_on_sliced_list.row(1) > rows_on_sliced_list.row(0)); //
[32, 52] > [32, 52, 12]
+ assert!(rows_on_sliced_list.row(2) < rows_on_sliced_list.row(1)); //
null < [32, 52]
+ assert!(rows_on_sliced_list.row(3) < rows_on_sliced_list.row(1)); //
[32, null] < [32, 52]
+ assert!(rows_on_sliced_list.row(4) > rows_on_sliced_list.row(1)); //
[] > [32, 52]
+ assert!(rows_on_sliced_list.row(2) < rows_on_sliced_list.row(4)); //
null < []
+
+ let back = converter.convert_rows(&rows_on_sliced_list).unwrap();
+ assert_eq!(back.len(), 1);
+ back[0].to_data().validate_full().unwrap();
+ }
+
+ #[test]
+ fn test_list_view() {
+ test_single_list_view::<i32>();
+ }
+
+ #[test]
+ fn test_large_list_view() {
+ test_single_list_view::<i64>();
+ }
Review Comment:
Please add nested tests like the regular list
--
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]
