tustvold commented on code in PR #6893:
URL: https://github.com/apache/arrow-rs/pull/6893#discussion_r1889300411
##########
arrow-select/src/concat.rs:
##########
@@ -851,4 +1018,169 @@ mod tests {
assert_eq!(array.null_count(), 10);
assert_eq!(array.logical_null_count(), 10);
}
+
+ #[test]
+ fn concat_dictionary_list_array_simple() {
+ let scalars = vec![
+ create_single_row_list_of_dict(vec![Some("a")]),
+ create_single_row_list_of_dict(vec![Some("a")]),
+ create_single_row_list_of_dict(vec![Some("b")]),
+ ];
+
+ let arrays = scalars.iter().map(|a| a as &(dyn
Array)).collect::<Vec<_>>();
+ let concat_res = concat(arrays.as_slice()).unwrap();
+
+ let expected_list = create_list_of_dict(vec![
+ // Row 1
+ Some(vec![Some("a")]),
+ Some(vec![Some("a")]),
+ Some(vec![Some("b")]),
+ ]);
+
+ let list = concat_res.as_list::<i32>();
+
+ // Assert that the list is equal to the expected list
+ list.iter().zip(expected_list.iter()).for_each(|(a, b)| {
+ assert_eq!(a, b);
+ });
+
+ let dict = list
+ .values()
+ .as_dictionary::<Int32Type>()
+ .downcast_dict::<StringArray>()
+ .unwrap();
+ println!("{:?}", dict);
+
+ assert_dictionary_has_unique_values::<_, StringArray>(
+ list.values().as_dictionary::<Int32Type>(),
+ );
+ }
+
+ #[test]
+ fn concat_dictionary_list_array_with_multiple_rows() {
+ let scalars = vec![
+ create_list_of_dict(vec![
+ // Row 1
+ Some(vec![Some("a"), Some("c")]),
+ // Row 2
+ None,
+ // Row 3
+ Some(vec![Some("f"), Some("g"), None]),
+ // Row 4
+ Some(vec![Some("c"), Some("f")]),
+ ]),
+ create_list_of_dict(vec![
+ // Row 1
+ Some(vec![Some("a")]),
+ // Row 2
+ Some(vec![]),
+ // Row 3
+ Some(vec![None, Some("b")]),
+ // Row 4
+ Some(vec![Some("d"), Some("e")]),
+ ]),
+ create_list_of_dict(vec![
+ // Row 1
+ Some(vec![Some("g")]),
+ // Row 2
+ Some(vec![Some("h"), Some("i")]),
+ // Row 3
+ Some(vec![Some("j"), Some("a")]),
+ // Row 4
+ Some(vec![Some("d"), Some("e")]),
+ ]),
+ ];
+ let arrays = scalars
+ .iter()
+ .map(|a| a as &(dyn Array))
+ .collect::<Vec<_>>();
+ let concat_res = concat(arrays.as_slice()).unwrap();
+
+ let expected_list = create_list_of_dict(vec![
+ // First list:
+
+ // Row 1
+ Some(vec![Some("a"), Some("c")]),
+ // Row 2
+ None,
+ // Row 3
+ Some(vec![Some("f"), Some("g"), None]),
+ // Row 4
+ Some(vec![Some("c"), Some("f")]),
+ // Second list:
+ // Row 1
+ Some(vec![Some("a")]),
+ // Row 2
+ Some(vec![]),
+ // Row 3
+ Some(vec![None, Some("b")]),
+ // Row 4
+ Some(vec![Some("d"), Some("e")]),
+ // Third list:
+
+ // Row 1
+ Some(vec![Some("g")]),
+ // Row 2
+ Some(vec![Some("h"), Some("i")]),
+ // Row 3
+ Some(vec![Some("j"), Some("a")]),
+ // Row 4
+ Some(vec![Some("d"), Some("e")]),
+ ]);
+
+ let list = concat_res.as_list::<i32>();
+
+ // Assert that the list is equal to the expected list
+ list.iter().zip(expected_list.iter()).for_each(|(a, b)| {
+ assert_eq!(a, b);
+ });
+
+ // Assert that the
+ assert_dictionary_has_unique_values::<_, StringArray>(
Review Comment:
The dictionary recomputation is a best-effort optimisation, it is not
guaranteed to eliminate all duplicates (or even run at all)
--
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]
