1
Fork 0
mirror of https://github.com/RGBCube/serenity synced 2025-07-25 21:07:35 +00:00

LibUnicode: Implement locale-aware MORE_ABOVE special casing

This commit is contained in:
Timothy Flynn 2021-09-05 15:03:56 -04:00 committed by Linus Groh
parent 1427ebc622
commit 436faf9fd9
2 changed files with 70 additions and 0 deletions

View file

@ -115,6 +115,26 @@ static bool is_final_code_point(Utf8View const& string, size_t index, size_t byt
return true;
}
static bool is_followed_by_combining_class_above(Utf8View const& string, size_t index, size_t byte_length)
{
// C is followed by a character of combining class 230 (Above) with no intervening character of combining class 0 or 230 (Above).
auto following_view = ((index + byte_length) < string.byte_length())
? string.substring_view(index + byte_length)
: Utf8View {};
for (auto code_point : following_view) {
auto unicode_data = Detail::unicode_data_for_code_point(code_point);
if (!unicode_data.has_value())
return false;
if (unicode_data->canonical_combining_class == 0)
return false;
if (unicode_data->canonical_combining_class == 230)
return true;
}
return false;
}
static SpecialCasing const* find_matching_special_case(Utf8View const& string, Optional<StringView> locale, size_t index, size_t byte_length, UnicodeData const& unicode_data)
{
auto requested_locale = Locale::None;
@ -149,6 +169,11 @@ static SpecialCasing const* find_matching_special_case(Utf8View const& string, O
return special_casing;
break;
case Condition::MoreAbove:
if (is_followed_by_combining_class_above(string, index, byte_length))
return special_casing;
break;
default:
break;
}