edponce commented on a change in pull request #10869:
URL: https://github.com/apache/arrow/pull/10869#discussion_r698416792
##########
File path: cpp/src/arrow/compute/kernels/scalar_string.cc
##########
@@ -527,6 +517,55 @@ struct Utf8CapitalizeTransform : public
StringTransformBase {
template <typename Type>
using Utf8Capitalize = StringTransformExec<Type, Utf8CapitalizeTransform>;
+struct Utf8TitleTransform : public StringTransformCodepointBase {
+ int64_t Transform(const uint8_t* input, int64_t input_string_ncodeunits,
+ uint8_t* output) {
+ uint8_t* output_start = output;
+ const uint8_t* end = input + input_string_ncodeunits;
+ const uint8_t* curr = NULLPTR;
+ uint32_t codepoint = 0;
+
+ do {
+ // Uppercase first alpha character of current word
+ while (input < end) {
+ curr = input;
+ if (ARROW_PREDICT_FALSE(!util::UTF8Decode(&curr, &codepoint))) {
+ return kTransformError;
+ }
+ if (IsCasedCharacterUnicode(codepoint)) {
+ output =
+ util::UTF8Encode(output,
UTF8UpperTransform::TransformCodepoint(codepoint));
+ input = curr;
+ break;
+ }
+ output = std::copy(input, curr, output);
+ input = curr;
+ }
+
+ // Lowercase characters until a whitespace is found
Review comment:
[Python's
`str.title`](https://docs.python.org/3/library/stdtypes.html#str.title) also
discusses the need for handling special cases such as apostrophes.
--
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]
