alamb commented on code in PR #7513:
URL: https://github.com/apache/arrow-rs/pull/7513#discussion_r2113861230
##########
arrow-select/src/filter.rs:
##########
@@ -550,56 +671,18 @@ fn filter_boolean(array: &BooleanArray, predicate:
&FilterPredicate) -> BooleanA
BooleanArray::from(data)
}
-#[inline(never)]
-fn filter_native<T: ArrowNativeType>(values: &[T], predicate:
&FilterPredicate) -> Buffer {
- assert!(values.len() >= predicate.filter.len());
-
- match &predicate.strategy {
- IterationStrategy::SlicesIterator => {
- let mut buffer = Vec::with_capacity(predicate.count);
- for (start, end) in SlicesIterator::new(&predicate.filter) {
- buffer.extend_from_slice(&values[start..end]);
- }
- buffer.into()
- }
- IterationStrategy::Slices(slices) => {
- let mut buffer = Vec::with_capacity(predicate.count);
- for (start, end) in slices {
- buffer.extend_from_slice(&values[*start..*end]);
- }
- buffer.into()
- }
- IterationStrategy::IndexIterator => {
- let iter = IndexIterator::new(&predicate.filter,
predicate.count).map(|x| values[x]);
-
- // SAFETY: IndexIterator is trusted length
- unsafe { MutableBuffer::from_trusted_len_iter(iter) }.into()
- }
- IterationStrategy::Indices(indices) => {
- let iter = indices.iter().map(|x| values[*x]);
- iter.collect::<Vec<_>>().into()
- }
- IterationStrategy::All | IterationStrategy::None => unreachable!(),
- }
-}
-
/// `filter` implementation for primitive arrays
fn filter_primitive<T>(array: &PrimitiveArray<T>, predicate: &FilterPredicate)
-> PrimitiveArray<T>
where
T: ArrowPrimitiveType,
{
- let values = array.values();
- let buffer = filter_native(values, predicate);
- let mut builder = ArrayDataBuilder::new(array.data_type().clone())
- .len(predicate.count)
- .add_buffer(buffer);
-
- if let Some((null_count, nulls)) = filter_null_mask(array.nulls(),
predicate) {
- builder = builder.null_count(null_count).null_bit_buffer(Some(nulls));
- }
+ let builder = PrimitiveBuilder::<T>::with_capacity(predicate.count);
Review Comment:
No it is not necessary to change the original implementations -- I reworked
the existing filter kernels in this PR so that I reuse the existing tests and
have confidence in the correctness of the approach.
--
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]
