pitrou commented on a change in pull request #11298:
URL: https://github.com/apache/arrow/pull/11298#discussion_r742941294
##########
File path: cpp/src/arrow/compute/kernels/scalar_string.cc
##########
@@ -672,11 +678,64 @@ struct Utf8TitleTransform : public
FunctionalCaseMappingTransform {
template <typename Type>
using Utf8Title = StringTransformExec<Type, Utf8TitleTransform>;
+struct Utf8NormalizeTransform : public FunctionalCaseMappingTransform {
+ using State = OptionsWrapper<Utf8NormalizeOptions>;
+
+ const Utf8NormalizeOptions* options;
+
+ explicit Utf8NormalizeTransform(const Utf8NormalizeOptions& options)
+ : options{&options} {}
+
+ int64_t MaxCodeunits(const uint8_t* input, int64_t ninputs,
+ int64_t input_ncodeunits) override {
+ const auto option = GenerateUtf8NormalizeOption(options->method);
Review comment:
I would simply not do what @edponce suggested if it entails a public
inclusion of utf8proc :-)
--
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]
