sdf-jkl commented on code in PR #8354:
URL: https://github.com/apache/arrow-rs/pull/8354#discussion_r2373555195
##########
parquet-variant-compute/src/variant_get.rs:
##########
@@ -100,12 +103,56 @@ pub(crate) fn follow_shredded_path_element(
Ok(ShreddedPathStep::Success(struct_array.into()))
}
- VariantPathElement::Index { .. } => {
+ VariantPathElement::Index { index } => {
// TODO: Support array indexing. Among other things, it will
require slicing not
// only the array we have here, but also the corresponding
metadata and null masks.
- Err(ArrowError::NotYetImplemented(
- "Pathing into shredded variant array index".into(),
- ))
+ let Some(list_array) =
typed_value.as_any().downcast_ref::<GenericListArray<i64>>()// <- shouldn't be
just i64
+ else {
+ // Downcast failure - if strict cast options are enabled, this
should be an error
+ if !cast_options.safe {
+ return Err(ArrowError::CastError(format!(
+ "Cannot access index '{}' on non-list type: {}",
+ index,
+ typed_value.data_type()
+ )));
+ }
+ // With safe cast options, return NULL (missing_path_step)
+ return Ok(missing_path_step());
+ };
+
+ let offsets = list_array.offsets();
+ let list_len = list_array.len(); // number of lists
+ let values = list_array.values(); // This is a StructArray
+
+ let Some(struct_array) =
values.as_any().downcast_ref::<StructArray>() else {
+ return Ok(missing_path_step());
+ };
+
+ let Some(field_array) = struct_array.column_by_name("typed_value")
else {
+ return Ok(missing_path_step());
+ };
+
+ // Build the list of indices to take
+ let mut take_indices = Vec::with_capacity(list_len);
+ for i in 0..list_len {
+ let start = offsets[i] as usize;
+ let end = offsets[i + 1] as usize;
+ let len = end - start;
+
+ if *index < len {
+ take_indices.push(Some((start + index) as u32));
+ } else {
+ take_indices.push(None);
+ }
+ }
+
+ let index_array = UInt32Array::from(take_indices);
+
+ // Use Arrow compute kernel to gather elements
+ let taken = take(field_array, &index_array, None)?;
Review Comment:
You can see the basic idea here
--
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]
