pitrou commented on a change in pull request #7449:
URL: https://github.com/apache/arrow/pull/7449#discussion_r447143530
##########
File path: cpp/src/arrow/compute/kernels/scalar_string_test.cc
##########
@@ -81,5 +147,40 @@ TYPED_TEST(TestStringKernels,
StrptimeDoesNotProvideDefaultOptions) {
ASSERT_RAISES(Invalid, CallFunction("strptime", {input}));
}
+TEST(TestStringKernels, UnicodeLibraryAssumptions) {
+ uint8_t output[4];
+ for (utf8proc_int32_t codepoint = 0x100; codepoint < 0x110000; codepoint++) {
+ utf8proc_ssize_t encoded_nbytes = utf8proc_encode_char(codepoint, output);
+ utf8proc_int32_t codepoint_upper = utf8proc_toupper(codepoint);
+ utf8proc_ssize_t encoded_nbytes_upper =
utf8proc_encode_char(codepoint_upper, output);
+ if (encoded_nbytes == 2) {
+ EXPECT_LE(encoded_nbytes_upper, 3)
+ << "Expected the upper case codepoint for a 2 byte encoded codepoint
to be "
+ "encoded in maximum 3 bytes, not "
+ << encoded_nbytes_upper;
+ }
+ if (encoded_nbytes == 3) {
Review comment:
Ok, thank you.
----------------------------------------------------------------
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:
us...@infra.apache.org
