lidavidm commented on a change in pull request #12248:
URL: https://github.com/apache/arrow/pull/12248#discussion_r800633991
##########
File path: cpp/src/arrow/compute/kernels/scalar_cast_nested.cc
##########
@@ -150,6 +150,80 @@ void AddListCast(CastFunction* func) {
DCHECK_OK(func->AddKernel(SrcType::type_id, std::move(kernel)));
}
+struct CastStruct {
+ static Status Exec(KernelContext* ctx, const ExecBatch& batch, Datum* out) {
+ const CastOptions& options = CastState::Get(ctx);
+ const auto in_field_count =
+ checked_cast<const StructType&>(*batch[0].type()).num_fields();
+ const auto out_field_count =
+ checked_cast<const StructType&>(*out->type()).num_fields();
+
+ if (in_field_count != out_field_count) {
+ return Status::TypeError("struct field sizes do not match: ",
+ batch[0].type()->ToString(), " ",
out->type()->ToString());
+ }
+
+ for (int64_t i = 0; i < in_field_count; ++i) {
+ const auto in_field_name =
+ checked_cast<const StructType&>(*batch[0].type()).field(i)->name();
+ const auto out_field_name =
+ checked_cast<const StructType&>(*out->type()).field(i)->name();
Review comment:
Should we also check field nullability here? It seems fine to cast
non-nullable to nullable, but not the other way around (unless there are no
nulls).
##########
File path: cpp/src/arrow/compute/kernels/scalar_cast_nested.cc
##########
@@ -150,6 +150,80 @@ void AddListCast(CastFunction* func) {
DCHECK_OK(func->AddKernel(SrcType::type_id, std::move(kernel)));
}
+struct CastStruct {
+ static Status Exec(KernelContext* ctx, const ExecBatch& batch, Datum* out) {
+ const CastOptions& options = CastState::Get(ctx);
+ const auto in_field_count =
+ checked_cast<const StructType&>(*batch[0].type()).num_fields();
+ const auto out_field_count =
+ checked_cast<const StructType&>(*out->type()).num_fields();
+
+ if (in_field_count != out_field_count) {
+ return Status::TypeError("struct field sizes do not match: ",
+ batch[0].type()->ToString(), " ",
out->type()->ToString());
+ }
+
+ for (int64_t i = 0; i < in_field_count; ++i) {
Review comment:
MSVC is a bit stricter about comparing integers of the same width/sign
so it might be easier to use `int` here to keep types consistent
##########
File path: cpp/src/arrow/compute/kernels/scalar_cast_nested.cc
##########
@@ -150,6 +150,78 @@ void AddListCast(CastFunction* func) {
DCHECK_OK(func->AddKernel(SrcType::type_id, std::move(kernel)));
}
+struct CastStruct {
+ static Status Exec(KernelContext* ctx, const ExecBatch& batch, Datum* out) {
+ const CastOptions& options = CastState::Get(ctx);
+ const auto in_field_count =
+ checked_cast<const StructType&>(*batch[0].type()).num_fields();
+ const auto out_field_count =
+ checked_cast<const StructType&>(*out->type()).num_fields();
+
+ if (in_field_count != out_field_count) {
+ return Status::TypeError(
+ "struct field sizes do not match: ", batch[0].type()->ToString(), "
", " and ",
+ out->type()->ToString());
+ }
+
+ for (int64_t i = 0; i < in_field_count; ++i) {
+ const auto in_field_name =
+ checked_cast<const StructType&>(*batch[0].type()).field(i)->name();
+ const auto out_field_name =
+ checked_cast<const StructType&>(*out->type()).field(i)->name();
+ if (in_field_name != out_field_name) {
+ return Status::TypeError(
+ "struct field names do not match: ", batch[0].type()->ToString(),
" ",
+ out->type()->ToString());
+ }
+ }
+
+ if (out->kind() == Datum::SCALAR) {
+ const auto& in_scalar = checked_cast<const
StructScalar&>(*batch[0].scalar());
+ auto out_scalar = checked_cast<StructScalar*>(out->scalar().get());
+
+ DCHECK(!out_scalar->is_valid);
+ if (in_scalar.is_valid) {
+ for (int64_t i = 0; i < in_field_count; i++) {
+ auto values = in_scalar.value[i];
+ auto target_type = out->type()->field(i)->type();
+ ARROW_ASSIGN_OR_RAISE(Datum cast_values,
+ Cast(values, target_type, options,
ctx->exec_context()));
+ DCHECK_EQ(Datum::SCALAR, cast_values.kind());
+ out_scalar->value.push_back(cast_values.scalar());
+ }
+ out_scalar->is_valid = true;
+ }
+ return Status::OK();
+ }
+
+ const ArrayData& in_array = *batch[0].array();
+ ArrayData* out_array = out->mutable_array();
+
+ for (int64_t i = 0; i < in_field_count; ++i) {
+ auto values = in_array.child_data[i];
Review comment:
This looks right. (Absolute offset = child offset + parent offset)
--
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]
