asubiotto commented on code in PR #9856:
URL: https://github.com/apache/arrow-rs/pull/9856#discussion_r3194680162
##########
arrow-select/src/interleave.rs:
##########
@@ -411,6 +417,70 @@ fn interleave_list<O: OffsetSizeTrait>(
Ok(Arc::new(list_array))
}
+/// Specialized [`interleave`] for [`RunArray`].
+fn interleave_run_end<R: RunEndIndexType>(
+ values: &[&dyn Array],
+ indices: &[(usize, usize)],
+) -> Result<ArrayRef, ArrowError> {
+ if indices.is_empty() {
+ return Ok(new_empty_array(values[0].data_type()));
+ }
+
+ let n = indices.len();
+ R::Native::from_usize(n).ok_or_else(|| {
+ ArrowError::ComputeError(format!(
+ "interleave_run_end: output length {n} does not fit run-end type"
+ ))
+ })?;
+
+ let runs: Vec<&RunArray<R>> = values.iter().map(|a|
a.as_run::<R>()).collect();
+ let value_arrays: Vec<&dyn Array> = runs.iter().map(|r|
r.values().as_ref()).collect();
+
+ // Resolve each (array, logical_row) to (array, physical_row), so we can
+ // lookup physical indices by batch.
+ let mut phys_pairs: Vec<(usize, usize)> = vec![(0, 0); n];
+ let mut grouped: Vec<(Vec<R::Native>, Vec<usize>)> =
+ (0..runs.len()).map(|_| (Vec::new(), Vec::new())).collect();
+ for (out_pos, &(arr, row)) in indices.iter().enumerate() {
+ let row = R::Native::from_usize(row).ok_or_else(|| {
+ ArrowError::InvalidArgumentError(format!(
+ "interleave_run_end: row index {row} out of range"
Review Comment:
Yeah, I think the confusion is the error message. I will change that. What
I'm really doing here is a `usize->R` conversion based on need so that I can
use it in `get_physical_indices` below and erroring if it fails. I'm checking
whether the index is even representable in the array's type *not* whether the
index is out of bounds on the input.
--
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]
