gabotechs commented on code in PR #7627:
URL: https://github.com/apache/arrow-rs/pull/7627#discussion_r2272891050
##########
arrow-row/src/lib.rs:
##########
@@ -1863,6 +1887,64 @@ mod tests {
back[0].to_data().validate_full().unwrap();
}
+ #[test]
+ fn test_dictionary_in_struct() {
+ let ty = DataType::Struct(
+ vec![Field::new_dictionary(
+ "foo",
+ DataType::Int32,
+ DataType::Int32,
+ false,
+ )]
+ .into(),
+ );
+ let s = arrow_array::new_empty_array(&ty);
+
+ let sort_fields = vec![SortField::new(s.data_type().clone())];
+ let converter = RowConverter::new(sort_fields).unwrap();
+ let r = converter.convert_columns(&[Arc::clone(&s)]).unwrap();
+
+ let back = converter.convert_rows(&r).unwrap();
+ let [s2] = back.try_into().unwrap();
+
+ // RowConverter flattens Dictionary
+ // s.ty = Struct(foo Dictionary(Int32, Int32)), s2.ty = Struct(foo
Int32)
+ assert_ne!(&s.data_type(), &s2.data_type());
+
+ s2.to_data().validate_full().unwrap();
+ }
+
+ #[test]
+ fn test_list_of_primitive_dictionary() {
+ let mut builder =
+ ListBuilder::<PrimitiveDictionaryBuilder<Int32Type,
Int32Type>>::default();
+ builder.values().append(2).unwrap();
+ builder.values().append(3).unwrap();
+ builder.values().append(0).unwrap();
+ builder.values().append_null();
+ builder.values().append(5).unwrap();
+ builder.values().append(3).unwrap();
+ builder.values().append(-1).unwrap();
+ builder.append(true);
+
+ let a = Arc::new(builder.finish()) as ArrayRef;
+ let data_type = a.data_type().clone();
+
+ let field = SortField::new(data_type.clone());
+ let converter = RowConverter::new(vec![field]).unwrap();
+ let rows = converter.convert_columns(&[Arc::clone(&a)]).unwrap();
+
+ let back = converter.convert_rows(&rows).unwrap();
+ assert_eq!(back.len(), 1);
+ let [a2] = back.try_into().unwrap();
+
+ // RowConverter flattens Dictionary
+ // a.ty: List(Dictionary(Int32, Int32)), a2.ty: List(Int32)
+ assert_ne!(&a.data_type(), &a2.data_type());
Review Comment:
🤔 I think technically they do are the same values, they just happen to be
encoded differently (Dictionary encoded VS raw).
Probably this test should be asserting that the data remains the same on
both ends regardless of the encoding.
--
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]
