Jefffrey commented on code in PR #18432:
URL: https://github.com/apache/datafusion/pull/18432#discussion_r2492531635
##########
datafusion/functions-nested/src/extract.rs:
##########
@@ -449,10 +452,162 @@ fn array_slice_inner(args: &[ArrayRef]) ->
Result<ArrayRef> {
let array = as_large_list_array(&args[0])?;
general_array_slice::<i64>(array, from_array, to_array, stride)
}
+ ListView(_) => {
+ let array = as_list_view_array(&args[0])?;
+ general_list_view_array_slice::<i32>(array, from_array, to_array,
stride)
+ }
+ LargeListView(_) => {
+ let array = as_large_list_view_array(&args[0])?;
+ general_list_view_array_slice::<i64>(array, from_array, to_array,
stride)
+ }
_ => exec_err!("array_slice does not support type: {}",
array_data_type),
}
}
+fn adjusted_from_index<O: OffsetSizeTrait>(index: i64, len: O) ->
Result<Option<O>>
+where
+ i64: TryInto<O>,
+{
+ // 0 ~ len - 1
+ let adjusted_zero_index = if index < 0 {
+ if let Ok(index) = index.try_into() {
+ // When index < 0 and -index > length, index is clamped to the
beginning of the list.
+ // Otherwise, when index < 0, the index is counted from the end of
the list.
+ //
+ // Note, we actually test the contrapositive, index < -length,
because negating a
+ // negative will panic if the negative is equal to the smallest
representable value
+ // while negating a positive is always safe.
+ if index < (O::zero() - O::one()) * len {
+ O::zero()
+ } else {
+ index + len
+ }
+ } else {
+ return exec_err!("array_slice got invalid index: {}", index);
+ }
+ } else {
+ // array_slice(arr, 1, to) is the same as array_slice(arr, 0, to)
+ if let Ok(index) = index.try_into() {
+ std::cmp::max(index - O::usize_as(1), O::usize_as(0))
+ } else {
+ return exec_err!("array_slice got invalid index: {}", index);
+ }
+ };
+
+ if O::usize_as(0) <= adjusted_zero_index && adjusted_zero_index < len {
+ Ok(Some(adjusted_zero_index))
+ } else {
+ // Out of bounds
+ Ok(None)
+ }
+}
+
+fn adjusted_to_index<O: OffsetSizeTrait>(index: i64, len: O) ->
Result<Option<O>>
+where
+ i64: TryInto<O>,
+{
+ // 0 ~ len - 1
+ let adjusted_zero_index = if index < 0 {
+ // array_slice in duckdb with negative to_index is python-like, so
index itself is exclusive
+ if let Ok(index) = index.try_into() {
+ index + len
+ } else {
+ return exec_err!("array_slice got invalid index: {}", index);
+ }
+ } else {
+ // array_slice(arr, from, len + 1) is the same as array_slice(arr,
from, len)
+ if let Ok(index) = index.try_into() {
+ std::cmp::min(index - O::usize_as(1), len - O::usize_as(1))
+ } else {
+ return exec_err!("array_slice got invalid index: {}", index);
+ }
+ };
+
+ if O::usize_as(0) <= adjusted_zero_index && adjusted_zero_index < len {
+ Ok(Some(adjusted_zero_index))
+ } else {
+ // Out of bounds
+ Ok(None)
+ }
+}
+
+/// Internal plan describing how to materialize a single row's slice after
+/// the slice bounds/stride have been normalized. Both list layouts consume
+/// this to drive their copy logic.
+enum SlicePlan<O: OffsetSizeTrait> {
+ /// No values should be produced.
+ Empty,
+ /// A contiguous run starting at `start` (relative to the row) with `len`
+ /// elements can be copied in one go.
+ Contiguous { start: O, len: O },
+ /// Arbitrary positions (already relative to the row) must be copied in
+ /// sequence.
+ Indices(Vec<O>),
+}
+
+/// Produces a [`SlicePlan`] for the given logical slice parameters.
+fn compute_slice_plan<O: OffsetSizeTrait>(
+ len: O,
+ from_raw: i64,
+ to_raw: i64,
+ stride_raw: Option<i64>,
+) -> Result<SlicePlan<O>>
+where
+ i64: TryInto<O>,
+{
+ if len == O::usize_as(0) {
+ return Ok(SlicePlan::Empty);
+ }
+
+ let from_index = adjusted_from_index::<O>(from_raw, len)?;
+ let to_index = adjusted_to_index::<O>(to_raw, len)?;
+
+ let (Some(from), Some(to)) = (from_index, to_index) else {
+ return Ok(SlicePlan::Empty);
+ };
+
+ let stride_value = stride_raw.unwrap_or(1);
Review Comment:
Sorry disregard, this is when stride is omitted not null
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
