milesgranger commented on code in PR #14395:
URL: https://github.com/apache/arrow/pull/14395#discussion_r1016136776
##########
cpp/src/arrow/compute/kernels/scalar_nested.cc:
##########
@@ -87,6 +89,198 @@ Status GetListElementIndex(const ExecValue& value, T* out) {
return Status::OK();
}
+template <typename Type, typename IndexType>
+struct ListSlice {
+ using offset_type = typename Type::offset_type;
+
+ static Status Exec(KernelContext* ctx, const ExecSpan& batch, ExecResult*
out) {
+ const auto opts = OptionsWrapper<ListSliceOptions>::Get(ctx);
+
+ // Invariants
+ if (!opts.stop.has_value()) {
+ // TODO: Support slicing to arbitrary end
+ // For variable size list, this would be the largest difference in
offsets
+ // For fixed size list, this would be the fixed size.
+ return Status::NotImplemented(
+ "Slicing to end not yet implemented, please set `stop` parameter.");
+ }
+ if (opts.start < 0 || opts.start >= opts.stop.value()) {
+ // TODO: support start == stop which should give empty lists
+ return Status::Invalid("`start`(", opts.start,
+ ") should be greater than 0 and smaller than
`stop`(",
+ opts.stop, ")");
+ }
+ if (opts.step != 1) {
+ // TODO: support step in slicing
+ return Status::NotImplemented(
+ "Setting `step` to anything other than 1 is not supported; got
step=",
+ opts.step);
+ }
+
+ const ArraySpan& list_ = batch[0].array;
+ const Type* list_type = checked_cast<const Type*>(list_.type);
+ const auto field_name = list_type->field(0)->name();
+ const auto value_type = list_type->field(0)->WithName(field_name);
+ const auto return_fixed_size_list = opts.return_fixed_size_list.value_or(
+ list_type->id() == arrow::Type::FIXED_SIZE_LIST);
+ std::unique_ptr<ArrayBuilder> builder;
+
+ // construct array values
+ if (return_fixed_size_list) {
+ RETURN_NOT_OK(MakeBuilder(
+ ctx->memory_pool(),
+ fixed_size_list(value_type,
+ static_cast<int32_t>(opts.stop.value() -
opts.start)),
+ &builder));
+ RETURN_NOT_OK(BuildArray<FixedSizeListBuilder>(batch, opts, *builder));
+ } else {
+ if constexpr (std::is_same_v<Type, LargeListType>) {
+ RETURN_NOT_OK(MakeBuilder(ctx->memory_pool(), large_list(value_type),
&builder));
+ RETURN_NOT_OK(BuildArray<LargeListBuilder>(batch, opts, *builder));
+ } else {
+ RETURN_NOT_OK(MakeBuilder(ctx->memory_pool(), list(value_type),
&builder));
+ RETURN_NOT_OK(BuildArray<ListBuilder>(batch, opts, *builder));
+ }
+ }
+
+ // build output arrays and set result
+ ARROW_ASSIGN_OR_RAISE(auto result, builder->Finish());
+ out->value = std::move(result->data());
+ return Status::OK();
+ }
+
+ template <typename BuilderType>
+ static Status BuildArray(const ExecSpan& batch, const ListSliceOptions& opts,
+ ArrayBuilder& builder) {
+ if constexpr (std::is_same_v<Type, FixedSizeListType>) {
+ RETURN_NOT_OK(BuildArrayFromFixedSizeListType<BuilderType>(batch, opts,
builder));
+ } else {
+ RETURN_NOT_OK(BuildArrayFromListType<BuilderType>(batch, opts, builder));
+ }
+ return Status::OK();
+ }
+
+ template <typename BuilderType>
+ static Status BuildArrayFromFixedSizeListType(const ExecSpan& batch,
+ const ListSliceOptions& opts,
+ ArrayBuilder& builder) {
+ const auto list_size =
+ checked_cast<const FixedSizeListType&>(*batch[0].type()).list_size();
+ const ArraySpan& list_ = batch[0].array;
Review Comment:
Sorry, was trying not to clash with the existing `list(..)` function, but
better anyway to rename to `list_array`.
--
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]
