cyb70289 commented on a change in pull request #10354:
URL: https://github.com/apache/arrow/pull/10354#discussion_r634864302
##########
File path: cpp/src/arrow/compute/kernels/scalar_string.cc
##########
@@ -1300,12 +1300,90 @@ void AddSplitWhitespaceUTF8(FunctionRegistry* registry)
{
}
#endif
+#ifdef ARROW_WITH_RE2
+template <typename Type, typename ListType>
+struct SplitRegexTransform : SplitBaseTransform<Type, ListType,
SplitPatternOptions,
+ SplitRegexTransform<Type,
ListType>> {
+ using Base = SplitBaseTransform<Type, ListType, SplitPatternOptions,
+ SplitRegexTransform<Type, ListType>>;
+ using ArrayType = typename TypeTraits<Type>::ArrayType;
+ using string_offset_type = typename Type::offset_type;
+ using ScalarType = typename TypeTraits<Type>::ScalarType;
+
+ const RE2 regex_split;
+
+ explicit SplitRegexTransform(SplitPatternOptions options)
+ : Base(options), regex_split(MakePattern(options)) {}
+
+ static std::string MakePattern(const SplitPatternOptions& options) {
+ // RE2 does *not* give you the full match! Must wrap the regex in a
capture group
+ // There is FindAndConsume, but it would give only the end of the separator
+ std::string pattern = "(";
+ pattern.reserve(options.pattern.size() + 1);
+ pattern += options.pattern;
+ pattern += ')';
Review comment:
Reserve `options.patterns.size() + 2`?
--
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.
For queries about this service, please contact Infrastructure at:
[email protected]
