vegarsti commented on code in PR #18424:
URL: https://github.com/apache/datafusion/pull/18424#discussion_r2484880239
##########
datafusion/functions-nested/src/reverse.rs:
##########
@@ -183,6 +195,75 @@ fn general_array_reverse<O: OffsetSizeTrait +
TryFrom<i64>>(
)?))
}
+fn list_view_reverse<O: OffsetSizeTrait + TryFrom<i64>>(
+ array: &GenericListViewArray<O>,
+ field: &FieldRef,
+) -> Result<ArrayRef> {
+ let (_, offsets, sizes, values, nulls) = array.clone().into_parts();
+
+ // Construct indices, sizes and offsets for the reversed array by
iterating over
+ // the list view array in the logical order, and reversing the order of
the elements.
+ // We end up with a list view array where the elements are in order,
+ // even if the original array had elements out of order.
+ let mut indices: Vec<O> = Vec::with_capacity(values.len());
+ let mut new_sizes = Vec::with_capacity(sizes.len());
+ let mut new_offsets: Vec<O> = Vec::with_capacity(offsets.len());
+ let mut new_nulls =
+ Vec::with_capacity(nulls.clone().map(|nulls|
nulls.len()).unwrap_or(0));
+ new_offsets.push(O::zero());
+ let has_nulls = nulls.is_some();
+ for (i, offset) in offsets.iter().enumerate().take(offsets.len()) {
+ // If this array is null, we set the new array to null with size 0 and
continue
+ if let Some(ref nulls) = nulls {
+ if nulls.is_null(i) {
+ new_nulls.push(false); // null
+ new_sizes.push(O::zero());
+ new_offsets.push(new_offsets[i]);
+ continue;
+ } else {
+ new_nulls.push(true); // valid
+ }
+ }
+
+ // Each array is located at [offset, offset + size), so we collect
indices in the reverse order
+ let array_start = offset.as_usize();
+ let array_end = array_start + sizes[i].as_usize();
+ for idx in (array_start..array_end).rev() {
+ indices.push(O::usize_as(idx));
+ }
+ new_sizes.push(sizes[i]);
+ if i < sizes.len() - 1 {
+ new_offsets.push(new_offsets[i] + sizes[i]);
+ }
+ }
+
+ // Materialize values from underlying array with take
+ let indices_array: ArrayRef = if O::IS_LARGE {
+ Arc::new(arrow::array::UInt64Array::from(
+ indices
+ .iter()
+ .map(|i| i.as_usize() as u64)
+ .collect::<Vec<_>>(),
+ ))
+ } else {
+ Arc::new(UInt32Array::from(
+ indices
+ .iter()
+ .map(|i| i.as_usize() as u32)
+ .collect::<Vec<_>>(),
+ ))
+ };
+ let values_reversed = take(&values, &indices_array, None)?;
+
+ Ok(Arc::new(GenericListViewArray::<O>::try_new(
+ Arc::clone(field),
+ ScalarBuffer::from(new_offsets),
+ ScalarBuffer::from(new_sizes),
+ values_reversed,
+ has_nulls.then_some(NullBuffer::from(new_nulls)),
Review Comment:
Oh, yes! Thanks! I mixed these up, but indeed we can, since we keep the
logical order of the arrays.
--
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]
