RGBCube/serenity
1
Fork 0
mirror of https://github.com/RGBCube/serenity synced 2025-05-31 09:58:11 +00:00
Code Issues Activity Actions

LibUnicode: Dynamically load the generated UnicodeData symbols

Browse source 
The generated data for libunicodedata.so is quite large, and loading it
is a price paid by nearly every application by way of depending on
LibRegex. In order to defer this cost until an application actually uses
one of the surrounding APIs, dynamically load the generated symbols.

To be able to load the symbols dynamically, the generated methods must
have demangled names. Typically, this is accomplished with `extern "C"`
blocks. The clang toolchain complains about this here because the types
returned from the generators are strictly C++ types. So to demangle the
names, we use the asm() compiler directive to manually define a symbol
name; the caveat is that we *must* be sure the symbols are unique. As an
extra precaution, we prefix each symbol name with "unicode_". For more
details, see: https://gcc.gnu.org/onlinedocs/gcc/Asm-Labels.html

This symbol loader used in this implementation provides the additional
benefit of removing many [[maybe_unused]] attributes from the LibUnicode
methods. Internally, if ENABLE_UNICODE_DATABASE_DOWNLOAD is OFF, the
loader is able to stub out the function pointers it returns.

Note that as of this commit, LibUnicode is still directly linked against
LibUnicodeData. This commit is just a first step towards removing that.
This commit is contained in:
Timothy Flynn 2021-12-15 18:42:51 -05:00 • committed by Brian Gianforcaro
parent 749d5ebd68
commit 3fd53baa25
7 changed files with 256 additions and 101 deletions
Download patch file Download diff file Expand all files Collapse all files

54
Meta/Lagom/Tools/CodeGenerators/LibUnicode/GeneratorUtil.h
View file

@ -345,6 +345,60 @@ Optional<@return_type@> @method_name@(StringView key)
)~~~");
}
// This is a temporary duplicate of generate_value_from_string() until all generators support dynamic loading.
template<typename ValueType>
void generate_value_from_string_for_dynamic_loading(SourceGenerator& generator, StringView method_name_format, StringView value_type, StringView value_name, HashValueMap<ValueType> hashes, Optional<StringView> return_type = {}, StringView return_format = "{}"sv)
{
ensure_from_string_types_are_generated(generator);
generator.set("method_name", String::formatted(method_name_format, value_name));
generator.set("value_type", value_type);
generator.set("value_name", value_name);
generator.set("return_type", return_type.has_value() ? *return_type : value_type);
generator.set("size", String::number(hashes.size()));
generator.append(R"~~~(
Optional<@return_type@> @method_name@(StringView key) asm("unicode_@method_name@");
Optional<@return_type@> @method_name@(StringView key)
{
constexpr Array<HashValuePair<@value_type@>, @size@> hash_pairs { {
)~~~");
auto hash_keys = hashes.keys();
quick_sort(hash_keys);
constexpr size_t max_values_per_row = 10;
size_t values_in_current_row = 0;
for (auto hash_key : hash_keys) {
if (values_in_current_row++ > 0)
generator.append(" ");
if constexpr (IsIntegral<ValueType>)
generator.set("value"sv, String::number(hashes.get(hash_key).value()));
else
generator.set("value"sv, String::formatted("{}::{}", value_type, hashes.get(hash_key).value()));
generator.set("hash"sv, String::number(hash_key));
generator.append("{ @hash@U, @value@ },"sv);
if (values_in_current_row == max_values_per_row) {
generator.append("\n ");
values_in_current_row = 0;
}
}
generator.set("return_statement", String::formatted(return_format, "value->value"sv));
generator.append(R"~~~(
} };
if (auto const* value = binary_search(hash_pairs, key.hash(), nullptr, HashValueComparator<@value_type@> {}))
return @return_statement@;
return {};
}
)~~~");
}
template<typename IdentifierFormatter>
void generate_enum(SourceGenerator& generator, IdentifierFormatter&& format_identifier, StringView name, StringView default_, Vector<String>& values, Vector<Alias> aliases = {})
{