RGBCube/serenity
1
Fork 0
mirror of https://github.com/RGBCube/serenity synced 2025-07-26 05:57:44 +00:00
Code Issues Activity Actions

LibUnicode: Implement locale-aware BEFORE_DOT special casing

Browse source 
Note that the algorithm in the Unicode spec is for checking that a code
point precedes U+0307, but the special casing condition NotBeforeDot is
interested in the inverse of this rule.
This commit is contained in:
Timothy Flynn 2021-09-05 15:09:03 -04:00 • committed by Linus Groh
parent 436faf9fd9
commit 50158abaf1
2 changed files with 50 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

28
Userland/Libraries/LibUnicode/CharacterTypes.cpp
View file

@ -135,6 +135,30 @@ static bool is_followed_by_combining_class_above(Utf8View const& string, size_t
return false;
}
static bool is_followed_by_combining_dot_above(Utf8View const& string, size_t index, size_t byte_length)
{
// C is followed by combining dot above (U+0307). Any sequence of characters with a combining class that is neither 0 nor 230 may
// intervene between the current character and the combining dot above.
auto following_view = ((index + byte_length) < string.byte_length())
? string.substring_view(index + byte_length)
: Utf8View {};
for (auto code_point : following_view) {
if (code_point == 0x307)
return true;
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 false;
}
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;
@ -174,7 +198,9 @@ static SpecialCasing const* find_matching_special_case(Utf8View const& string, O
return special_casing;
break;
default:
case Condition::NotBeforeDot:
if (!is_followed_by_combining_dot_above(string, index, byte_length))
return special_casing;
break;
}
}