tustvold commented on code in PR #6893:
URL: https://github.com/apache/arrow-rs/pull/6893#discussion_r1932194273
##########
arrow-select/src/concat.rs:
##########
@@ -129,6 +129,54 @@ fn concat_dictionaries<K: ArrowDictionaryKeyType>(
Ok(Arc::new(array))
}
+fn concat_lists<OffsetSize: OffsetSizeTrait>(
+ arrays: &[&dyn Array],
+ field: &FieldRef,
+) -> Result<ArrayRef, ArrowError> {
+ let mut output_len = 0;
+ let mut list_has_nulls = false;
+
+ let lists = arrays
+ .iter()
+ .map(|x| x.as_list::<OffsetSize>())
+ .inspect(|l| {
+ output_len += l.len();
+ list_has_nulls |= l.null_count() != 0;
+ })
+ .collect::<Vec<_>>();
+
+ let lists_nulls = list_has_nulls.then(|| {
+ let mut nulls = BooleanBufferBuilder::new(output_len);
+ for l in &lists {
+ match l.nulls() {
+ Some(n) => nulls.append_buffer(n.inner()),
+ None => nulls.append_n(l.len(), true),
+ }
+ }
+ NullBuffer::new(nulls.finish())
+ });
+
+ let values: Vec<&dyn Array> = lists
+ .iter()
+ .map(|x| x.values().as_ref())
Review Comment:
I think the bug is here, it needs to slice values() by the first offset
--
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]
