edponce commented on a change in pull request #10896:
URL: https://github.com/apache/arrow/pull/10896#discussion_r691569402
##########
File path: cpp/src/arrow/compute/kernels/scalar_validity.cc
##########
@@ -76,11 +79,32 @@ struct IsInfOperator {
struct IsNullOperator {
static Status Call(KernelContext* ctx, const Scalar& in, Scalar* out) {
- checked_cast<BooleanScalar*>(out)->value = !in.is_valid;
+ auto options = OptionsWrapper<NanNullOptions>::Get(ctx);
+ bool* out_value = &checked_cast<BooleanScalar*>(out)->value;
+ if (in.is_valid) {
+ switch (in.type->id()) {
+ case Type::FLOAT:
+ *out_value = options.nan_is_null &&
+ std::isnan(internal::UnboxScalar<FloatType>::Unbox(in));
+ break;
+ case Type::DOUBLE:
+ *out_value = options.nan_is_null &&
+
std::isnan(internal::UnboxScalar<DoubleType>::Unbox(in));
+ break;
+ default:
+ *out_value = false;
+ }
+ } else {
+ *out_value = true;
+ }
+
return Status::OK();
}
static Status Call(KernelContext* ctx, const ArrayData& arr, ArrayData* out)
{
+ // TODO: Is `options` needed for detect nulls? Which is the better way to
+ // handle is_null for ArrayData
+ auto options = OptionsWrapper<NanNullOptions>::Get(ctx);
Review comment:
@pitrou The `is_null` compute function most of the time will iterate
through the bitmap of the input `ArrayData` and when `nan_is_null` option is
set, it can increase the null count. Would it be a good idea to update the null
count of the input array (`arr.SetNullCount(...)`) as a side-effect of invoking
this compute function?
--
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]
