rluvaton commented on code in PR #8951:
URL: https://github.com/apache/arrow-rs/pull/8951#discussion_r2702353763
##########
arrow-select/src/coalesce/primitive.rs:
##########
@@ -95,6 +96,151 @@ impl<T: ArrowPrimitiveType + Debug> InProgressArray for
InProgressPrimitiveArray
Ok(())
}
+ /// Copy rows using a predicate
+ fn copy_rows_by_filter(
+ &mut self,
+ filter: &FilterPredicate,
+ offset: usize,
+ len: usize,
+ ) -> Result<(), ArrowError> {
+ self.ensure_capacity();
+
+ let s = self
+ .source
+ .as_ref()
+ .ok_or_else(|| {
+ ArrowError::InvalidArgumentError(
+ "Internal Error: InProgressPrimitiveArray: source not
set".to_string(),
+ )
+ })?
+ .slice(offset, len);
+ let s = s.as_primitive::<T>();
+
+ let values = s.values();
+ let count = filter.count();
+
+ // Use the predicate's strategy for optimal iteration
+ match filter.strategy() {
+ IterationStrategy::SlicesIterator => {
+ // Copy values, nulls using slices
+ if let Some(nulls) = s.nulls().filter(|n| n.null_count() > 0) {
+ for (start, end) in
SlicesIterator::new(filter.filter_array()) {
+ // SAFETY: slices are derived from filter predicate
+ self.current
+ .extend_from_slice(unsafe {
values.get_unchecked(start..end) });
Review Comment:
Note that this might not be vectorized, I would check in Compiler Explorer.
as LLVM in some cases is not smart enough for this
(same for the rest)
--
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]
