edponce commented on a change in pull request #11159:
URL: https://github.com/apache/arrow/pull/11159#discussion_r709800324
##########
File path: cpp/src/arrow/compute/kernels/scalar_nested.cc
##########
@@ -62,6 +62,57 @@ const FunctionDoc list_value_length_doc{
"Null values emit a null in the output."),
{"lists"}};
+template <typename Type, typename IndexType>
+Status ListElement(KernelContext* ctx, const ExecBatch& batch, Datum* out) {
+ using ListArrayType = typename TypeTraits<Type>::ArrayType;
+ using IndexScalarType = typename TypeTraits<IndexType>::ScalarType;
+ ListArrayType list_array(batch[0].array());
+ const auto& index_scalar = batch[1].scalar_as<IndexScalarType>();
+ 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");
+ }
Review comment:
I suggest to not embed the value of `index`. "Index must be
non-negative."
##########
File path: cpp/src/arrow/compute/kernels/scalar_nested.cc
##########
@@ -62,6 +62,57 @@ const FunctionDoc list_value_length_doc{
"Null values emit a null in the output."),
{"lists"}};
+template <typename Type, typename IndexType>
+Status ListElement(KernelContext* ctx, const ExecBatch& batch, Datum* out) {
+ using ListArrayType = typename TypeTraits<Type>::ArrayType;
+ using IndexScalarType = typename TypeTraits<IndexType>::ScalarType;
+ ListArrayType list_array(batch[0].array());
+ const auto& index_scalar = batch[1].scalar_as<IndexScalarType>();
+ 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));
+ 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 > len)) {
+ return Status::Invalid("Index ", index, " is out of bounds: should be in
[0, ", len,
+ "]");
+ }
Review comment:
I suggest to provide a generic message instead of embedding the value of
`len`. "Index is out of range, larger than array length."
##########
File path: cpp/src/arrow/compute/kernels/scalar_nested.cc
##########
@@ -62,6 +62,57 @@ const FunctionDoc list_value_length_doc{
"Null values emit a null in the output."),
{"lists"}};
+template <typename Type, typename IndexType>
+Status ListElement(KernelContext* ctx, const ExecBatch& batch, Datum* out) {
+ using ListArrayType = typename TypeTraits<Type>::ArrayType;
+ using IndexScalarType = typename TypeTraits<IndexType>::ScalarType;
+ ListArrayType list_array(batch[0].array());
+ const auto& index_scalar = batch[1].scalar_as<IndexScalarType>();
+ auto index = index_scalar.value;
Review comment:
Why not skip the `index_scalar` variable?
##########
File path: cpp/src/arrow/compute/kernels/scalar_nested.cc
##########
@@ -62,6 +62,57 @@ const FunctionDoc list_value_length_doc{
"Null values emit a null in the output."),
{"lists"}};
+template <typename Type, typename IndexType>
+Status ListElement(KernelContext* ctx, const ExecBatch& batch, Datum* out) {
+ using ListArrayType = typename TypeTraits<Type>::ArrayType;
+ using IndexScalarType = typename TypeTraits<IndexType>::ScalarType;
+ ListArrayType list_array(batch[0].array());
+ const auto& index_scalar = batch[1].scalar_as<IndexScalarType>();
+ 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));
+ 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 > len)) {
+ return Status::Invalid("Index ", index, " is out of bounds: should be in
[0, ", len,
+ "]");
+ }
+ ARROW_ASSIGN_OR_RAISE(auto scalar, (value_array->GetScalar(index)));
+ RETURN_NOT_OK(builder->AppendScalar(*scalar));
+ }
+ ARROW_ASSIGN_OR_RAISE(auto result, builder->Finish());
+ out->value = result->data();
+ return Status::OK();
+}
+
+template <typename InListType, typename IndexType>
+void AddListElement(ScalarFunction* func) {
+ ScalarKernel
kernel{KernelSignature::Make({InputType::Array(InListType::type_id),
+
InputType::Scalar(IndexType::type_id)},
+ OutputType{ListValuesType},
+ /*is_varargs=*/false),
+ ListElement<InListType, IndexType>};
+ kernel.null_handling = NullHandling::COMPUTED_NO_PREALLOCATE;
+ kernel.mem_allocation = MemAllocation::NO_PREALLOCATE;
+ DCHECK_OK(func->AddKernel(std::move(kernel)));
+}
+
+const FunctionDoc list_element_doc(
+ "Compute elements using of nested list values using an index",
+ ("`lists` must have a list-like type.\n"
+ "For each value in each list of `lists`, the element at `index`\n"
+ "is emitted."),
+ {"lists", "index"});
Review comment:
To long description, you can add a note about `null` behavior: "Null
values emit a null in the output."
--
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]
