Dandandan commented on code in PR #7695:
URL: https://github.com/apache/arrow-rs/pull/7695#discussion_r2153152210
##########
arrow-select/src/interleave.rs:
##########
@@ -238,32 +237,45 @@ fn interleave_views<T: ByteViewType>(
indices: &[(usize, usize)],
) -> Result<ArrayRef, ArrowError> {
let interleaved = Interleave::<'_, GenericByteViewArray<T>>::new(values,
indices);
- let mut views_builder = BufferBuilder::new(indices.len());
let mut buffers = Vec::new();
// (input array_index, input buffer_index) -> output buffer_index
- let mut buffer_lookup: HashMap<(usize, u32), u32> = HashMap::new();
- for (array_idx, value_idx) in indices {
- let array = interleaved.arrays[*array_idx];
- let raw_view = array.views().get(*value_idx).unwrap();
- let view_len = *raw_view as u32;
- if view_len <= 12 {
- views_builder.append(*raw_view);
- continue;
- }
- // value is big enough to be in a variadic buffer
- let view = ByteView::from(*raw_view);
- let new_buffer_idx: &mut u32 = buffer_lookup
- .entry((*array_idx, view.buffer_index))
- .or_insert_with(|| {
- buffers.push(array.data_buffers()[view.buffer_index as
usize].clone());
- (buffers.len() - 1) as u32
- });
- views_builder.append(view.with_buffer_index(*new_buffer_idx).into());
- }
+ // A mapping from (input array_index, input buffer_index) -> output
buffer_index
+ // The outer vec corresponds to the input array index.
+ // The inner vec corresponds to the buffer index within that input array.
+ // The value is the index of the buffer in the output array.
+ let mut buffer_remap: Vec<Vec<Option<u32>>> = interleaved
Review Comment:
We can perhaps store this in two vecs - (offsets / values) - let me check
--
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]
