LibUnicode: Tweak code point general category APIs

The motivation is to have `code_point_has_*_control_general_category()`
functions, so that clients don't have to look at `GeneralCategory`
values directly and hence don't have to worry about
`code_point_has_general_category()` returning an empty Optional. This
isn't quite achieved since some code inside LibLocale still uses some of
them, but it removes uses in LibGfx and LibJS.

This kind of cherry-picks the 2nd commit of
LadybirdBrowser/ladybird#239 (aa3a30870b58c47cb37bce1418d7e6bee7af71d9):
The Lexer.cpp, RegexByteCode.cpp, CharacterTypes.h, KeyboardEvent.cpp
changes are by trflynn.

This does not (yet?) pick up the new type for `GeneralCategory`. In the
future, we might want to make the generator generate a
`GeneralCategoryEnum` type and have the
`AK_TYPEDEF_DISTINCT_NUMERIC_GENERAL` in Forward.h, but at the moment
that makes things more complicated. (It also means we don't pick up the
RegexParser.cpp changes.)

Co-authored-by: Tim Flynn <trflynn89@serenityos.org>

Userland/Libraries/LibJS/Lexer.cpp

@@ -518,11 +518,7 @@ bool Lexer::is_whitespace() const
     auto code_point = current_code_point();
     if (code_point == NO_BREAK_SPACE || code_point == ZERO_WIDTH_NO_BREAK_SPACE)
         return true;
-
-    static auto space_separator_category = Unicode::general_category_from_string("Space_Separator"sv);
-    if (space_separator_category.has_value())
-        return Unicode::code_point_has_general_category(code_point, *space_separator_category);
-    return false;
+    return Unicode::code_point_has_space_separator_general_category(code_point);
 }
 
 // UnicodeEscapeSequence :: https://tc39.es/ecma262/#prod-UnicodeEscapeSequence

Userland/Libraries/LibRegex/RegexByteCode.cpp

@@ -776,15 +776,11 @@ ALWAYS_INLINE void OpCode_Compare::compare_character_class(MatchInput const& inp
 bool OpCode_Compare::matches_character_class(CharClass character_class, u32 ch, bool insensitive)
 {
     constexpr auto is_space_or_line_terminator = [](u32 code_point) {
-        static auto space_separator = Unicode::general_category_from_string("Space_Separator"sv);
-        if (!space_separator.has_value())
-            return is_ascii_space(code_point);
-
         if ((code_point == 0x0a) || (code_point == 0x0d) || (code_point == 0x2028) || (code_point == 0x2029))
             return true;
         if ((code_point == 0x09) || (code_point == 0x0b) || (code_point == 0x0c) || (code_point == 0xfeff))
             return true;
-        return Unicode::code_point_has_general_category(code_point, *space_separator);
+        return Unicode::code_point_has_space_separator_general_category(code_point);
     };
 
     switch (character_class) {

Userland/Libraries/LibUnicode/CharacterTypes.cpp

@@ -150,6 +150,25 @@ template Optional<size_t> find_ignoring_case(Utf32View, Utf32View);
 
 Optional<GeneralCategory> __attribute__((weak)) general_category_from_string(StringView) { return {}; }
 bool __attribute__((weak)) code_point_has_general_category(u32, GeneralCategory) { return {}; }
+
+bool code_point_has_control_general_category(u32 code_point)
+{
+#if ENABLE_UNICODE_DATA
+    return code_point_has_general_category(code_point, Unicode::GeneralCategory::Control);
+#else
+    return false;
+#endif
+}
+
+bool code_point_has_space_separator_general_category(u32 code_point)
+{
+#if ENABLE_UNICODE_DATA
+    return code_point_has_general_category(code_point, Unicode::GeneralCategory::Space_Separator);
+#else
+    return is_ascii_space(code_point);
+#endif
+}
+
 Optional<Property> __attribute__((weak)) property_from_string(StringView) { return {}; }
 bool __attribute__((weak)) code_point_has_property(u32, Property) { return {}; }
 

Userland/Libraries/LibUnicode/CharacterTypes.h

@@ -57,6 +57,9 @@ Optional<size_t> find_ignoring_case(ViewType, ViewType);
 Optional<GeneralCategory> general_category_from_string(StringView);
 bool code_point_has_general_category(u32 code_point, GeneralCategory general_category);
 
+bool code_point_has_control_general_category(u32 code_point);
+bool code_point_has_space_separator_general_category(u32 code_point);
+
 Optional<Property> property_from_string(StringView);
 bool code_point_has_property(u32 code_point, Property property);
 

Userland/Libraries/LibWeb/UIEvents/KeyboardEvent.cpp

@@ -246,11 +246,7 @@ static ErrorOr<Optional<String>> get_event_key_string(u32 code_point)
     auto is_non_control_character = [&]() {
         // A non-control character is any valid Unicode character except those that are part of the "Other, Control"
         // ("Cc") General Category.
-        static auto control_general_category = Unicode::general_category_from_string("Cc"sv);
-        if (!control_general_category.has_value())
-            return true;
-
-        return !Unicode::code_point_has_general_category(code_point, *control_general_category);
+        return !Unicode::code_point_has_control_general_category(code_point);
     };
 
     // A key string is a string containing a 0 or 1 non-control characters ("base" characters) followed by 0 or more