pitrou commented on code in PR #46590:
URL: https://github.com/apache/arrow/pull/46590#discussion_r2111223493
##########
cpp/src/arrow/compute/kernels/scalar_string_test.cc:
##########
@@ -1384,10 +1384,12 @@ TYPED_TEST(TestStringKernels, IsDecimalUnicode) {
}
TYPED_TEST(TestStringKernels, IsDigitUnicode) {
- // These are digits according to Python, but we don't have the information in
- // utf8proc for this
- // this->CheckUnary("utf8_is_digit", "[\"²\", \"①\"]", boolean(), "[true,
- // true]");
+ // Tests for digits across various Unicode scripts.
+ // ٤: Arabic 4, ³: Superscript 3, ५: Devanagari 5, Ⅷ: Roman 8 (not digit),
１２３: Fullwidth 123
+ this->CheckUnary("utf8_is_digit",
+ R"(["٤", "³", "५", "Ⅷ", "٣٣", "१२३", "abc", "１２３"])",
+ boolean(),
+ "[true, true, true, false, true, true, false, true]");
}
TYPED_TEST(TestStringKernels, IsNumericUnicode) {
Review Comment:
I think we can a comment stating this indeed.
--
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: github-unsubscr...@arrow.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
