mirrors/serenity
1
0
Fork 0
mirror of https://github.com/SerenityOS/serenity.git synced 2025-01-23 01:41:59 -05:00
Code Issues Projects Releases Packages Wiki Activity

LibUnicode: Handle edge-case script extensions, Common and Inherited

Browse source 
These script extensions have some peculiar behavior in the Unicode spec.
The UCD ScriptExtension file does not contain these scripts. Rather, it
is implied the code points which have these scripts as an extension are
the code points that both:

  1. Have Common or Inherited as their primary script value
  2. Do not have any other script value in their script extension lists

Because these are not explictly listed in the UCD, we must manually form
these script extensions.
This commit is contained in:
Timothy Flynn 2021-08-10 17:42:21 -04:00 committed by Andreas Kling
parent 47bb350ebd
commit 1e91334008
2 changed files with 49 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

22
Tests/LibUnicode/TestUnicodeCharacterTypes.cpp
View file

@ -464,4 +464,26 @@ TEST_CASE(script_extension)
EXPECT(!Unicode::code_point_has_script(0x1dc1, script_greek));
EXPECT(Unicode::code_point_has_script_extension(0x1dc1, script_greek));
auto script_common = script("Common"sv);
auto script_zyyy = script("Zyyy"sv);
EXPECT_EQ(script_common, script_zyyy);
EXPECT(Unicode::code_point_has_script(0x202f, script_common));
EXPECT(!Unicode::code_point_has_script_extension(0x202f, script_common));
EXPECT(Unicode::code_point_has_script(0x3000, script_common));
EXPECT(Unicode::code_point_has_script_extension(0x3000, script_common));
auto script_inherited = script("Inherited"sv);
auto script_qaai = script("Qaai"sv);
auto script_zinh = script("Zinh"sv);
EXPECT_EQ(script_inherited, script_qaai);
EXPECT_EQ(script_inherited, script_zinh);
EXPECT(Unicode::code_point_has_script(0x1ced, script_inherited));
EXPECT(!Unicode::code_point_has_script_extension(0x1ced, script_inherited));
EXPECT(Unicode::code_point_has_script(0x101fd, script_inherited));
EXPECT(Unicode::code_point_has_script_extension(0x101fd, script_inherited));
}

27
Userland/Libraries/LibUnicode/CodeGenerators/GenerateUnicodeData.cpp
View file

@ -883,6 +883,33 @@ static void normalize_script_extensions(PropList& script_extensions, PropList co
sort_and_merge_code_point_ranges(code_points);
}
// Lastly, the Common and Inherited script extensions are special. They must not contain any
// code points which appear in other script extensions. The ScriptExtensions UCD file does not
// list these extensions, therefore this peculiarity must be handled programatically.
// https://www.unicode.org/reports/tr24/#Assignment_ScriptX_Values
auto code_point_has_other_extension = [&](StringView key, u32 code_point) {
for (auto const& extension : extensions) {
if (extension.key == key)
continue;
if (any_of(extension.value, [&](auto const& r) { return (r.first <= code_point) && (code_point <= r.last); }))
return true;
}
return false;
};
auto get_code_points_without_other_extensions = [&](StringView key) {
auto code_points = flatten_code_point_ranges(script_list.find(key)->value);
code_points.remove_all_matching([&](u32 c) { return code_point_has_other_extension(key, c); });
return code_points;
};
auto common_code_points = get_code_points_without_other_extensions("Common"sv);
script_extensions.set("Common"sv, form_code_point_ranges(common_code_points));
auto inherited_code_points = get_code_points_without_other_extensions("Inherited"sv);
script_extensions.set("Inherited"sv, form_code_point_ranges(inherited_code_points));
}
int main(int argc, char** argv)