Dandandan commented on code in PR #7873:
URL: https://github.com/apache/arrow-rs/pull/7873#discussion_r2189275118
##########
arrow-array/src/array/byte_view_array.rs:
##########
@@ -473,13 +473,81 @@ impl<T: ByteViewType + ?Sized> GenericByteViewArray<T> {
/// Note: this function does not attempt to canonicalize / deduplicate
values. For this
/// feature see [`GenericByteViewBuilder::with_deduplicate_strings`].
pub fn gc(&self) -> Self {
- let mut builder =
GenericByteViewBuilder::<T>::with_capacity(self.len());
+ // 1) Read basic properties once
+ let len = self.len(); // number of elements
+ let views = self.views(); // raw u128 “view” values per slot
+ let nulls = self.nulls().cloned(); // reuse & clone existing null
bitmap
+
+ // 2) Pre-scan to determine how many out‑of‑line bytes we must store
+ let total_large: usize = (0..len)
+ .filter_map(|i| {
+ // skip null entries
+ if self.is_null(i) {
+ None
+ } else {
+ // extract the ByteView metadata from the u128
+ let raw_view: u128 = views[i];
+ let bv = ByteView::from(raw_view);
+ // if length exceeds inline limit, count it
+ (bv.length > MAX_INLINE_VIEW_LEN).then_some(bv.length as
usize)
+ }
+ })
+ .sum();
+ // allocate exactly the capacity needed for all non‑inline data
+ let mut data_buf = Vec::with_capacity(total_large);
+
+ // 3) Build new view array in one pass
+ // map each index to a new u128, collecting into a Vec<u128>
+ let views_buf: Vec<u128> = (0..len)
+ .map(|i| {
+ // if null, represent as 0
+ if self.is_null(i) {
Review Comment:
Same here - could use `set_indices` for nulls, could optimize non-null case.
--
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]
