lidavidm commented on a change in pull request #11159:
URL: https://github.com/apache/arrow/pull/11159#discussion_r712380898
##########
File path: cpp/src/arrow/compute/kernels/scalar_nested.cc
##########
@@ -80,6 +80,134 @@ const FunctionDoc list_value_length_doc{
"Null values emit a null in the output."),
{"lists"}};
+template <typename Type, typename IndexType>
+Status ListElementArray(KernelContext* ctx, const ExecBatch& batch, Datum*
out) {
+ using ListArrayType = typename TypeTraits<Type>::ArrayType;
+ using IndexScalarType = typename TypeTraits<IndexType>::ScalarType;
+ const auto& index_scalar = batch[1].scalar_as<IndexScalarType>();
+ if (ARROW_PREDICT_FALSE(!index_scalar.is_valid)) {
+ return Status::Invalid("Index must not be null");
+ }
+ ListArrayType list_array(batch[0].array());
+ auto index = index_scalar.value;
+ if (ARROW_PREDICT_FALSE(index < 0)) {
+ return Status::Invalid("Index ", index,
+ " is out of bounds: should be greater than or equal
to 0");
+ }
+ std::unique_ptr<ArrayBuilder> builder;
+ RETURN_NOT_OK(MakeBuilder(ctx->memory_pool(), list_array.value_type(),
&builder));
+ RETURN_NOT_OK(builder->Reserve(list_array.length()));
+ for (int i = 0; i < list_array.length(); ++i) {
+ if (list_array.IsNull(i)) {
+ RETURN_NOT_OK(builder->AppendNull());
+ continue;
+ }
+ std::shared_ptr<arrow::Array> value_array = list_array.value_slice(i);
+ auto len = value_array->length();
+ if (ARROW_PREDICT_FALSE(index >= static_cast<typename
IndexType::c_type>(len))) {
+ return Status::Invalid("Index ", index, " is out of bounds: should be in
[0, ", len,
+ ")");
+ }
+ RETURN_NOT_OK(builder->AppendArraySlice(*value_array->data(), index, 1));
+ }
+ ARROW_ASSIGN_OR_RAISE(auto result, builder->Finish());
+ out->value = result->data();
+ return Status::OK();
+}
+
+template <typename, typename IndexType>
+struct ListElementScalar {
+ static Status Exec(KernelContext* /*ctx*/, const ExecBatch& batch, Datum*
out) {
+ using IndexScalarType = typename TypeTraits<IndexType>::ScalarType;
+ const auto& index_scalar = batch[1].scalar_as<IndexScalarType>();
+ if (ARROW_PREDICT_FALSE(!index_scalar.is_valid)) {
+ return Status::Invalid("Index must not be null");
+ }
+ const auto& list_scalar = batch[0].scalar_as<BaseListScalar>();
+ if (ARROW_PREDICT_FALSE(!list_scalar.is_valid)) {
+ out->value = MakeNullScalar(
+ checked_cast<const BaseListType&>(*batch[0].type()).value_type());
+ return Status::OK();
+ }
+ auto list = list_scalar.value;
+ auto index = index_scalar.value;
+ auto len = list->length();
+ if (ARROW_PREDICT_FALSE(index < 0 ||
+ index >= static_cast<typename
IndexType::c_type>(len))) {
+ return Status::Invalid("Index ", index, " is out of bounds: should be in
[0, ", len,
+ ")");
+ }
+ ARROW_ASSIGN_OR_RAISE(out->value, list->GetScalar(index));
+ return Status::OK();
+ }
+};
+
+template <typename InListType, typename IndexType>
+void AddListElementArrayKernel(ScalarFunction* func) {
+ auto inputs = {InputType::Array(InListType::type_id),
+ InputType::Scalar(IndexType::type_id)};
+ auto output = OutputType{ListValuesType};
+ auto sig =
+ KernelSignature::Make(std::move(inputs), std::move(output),
/*is_varargs=*/false);
+ auto array_exec = ListElementArray<InListType, IndexType>;
Review comment:
Note if you wanted, for consistency, this could be
`GenerateInteger<ListElementArray, InListType>`.
--
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]
