RGBCube/serenity
1
Fork 0
mirror of https://github.com/RGBCube/serenity synced 2025-07-25 11:27:35 +00:00
Code Issues Activity Actions

LibRegex: Support property escapes of Unicode General Categories

Browse source 
This changes LibRegex to parse the property escape as a Variant of
Unicode Property & General Category values. A byte code instruction is
added to perform matching based on General Category values.
This commit is contained in:
Timothy Flynn 2021-07-31 17:46:05 -04:00 • committed by Ali Mohammad Pur
parent 5de6d3dd90
commit 1e10d6d7ce
5 changed files with 77 additions and 19 deletions
Download patch file Download diff file Expand all files Collapse all files

2
Userland/Libraries/LibRegex/RegexByteCode.h
View file

@ -67,6 +67,7 @@ enum class OpCodeId : ByteCodeValueType {
__ENUMERATE_CHARACTER_COMPARE_TYPE(Reference) \
__ENUMERATE_CHARACTER_COMPARE_TYPE(NamedReference) \
__ENUMERATE_CHARACTER_COMPARE_TYPE(Property) \
__ENUMERATE_CHARACTER_COMPARE_TYPE(GeneralCategory) \
__ENUMERATE_CHARACTER_COMPARE_TYPE(RangeExpressionDummy)
enum class CharacterCompareType : ByteCodeValueType {
@ -725,6 +726,7 @@ private:
ALWAYS_INLINE static void compare_character_class(MatchInput const& input, MatchState& state, CharClass character_class, u32 ch, bool inverse, bool& inverse_matched);
ALWAYS_INLINE static void compare_character_range(MatchInput const& input, MatchState& state, u32 from, u32 to, u32 ch, bool inverse, bool& inverse_matched);
ALWAYS_INLINE static void compare_property(MatchInput const& input, MatchState& state, Unicode::Property property, bool inverse, bool& inverse_matched);
ALWAYS_INLINE static void compare_general_category(MatchInput const& input, MatchState& state, Unicode::GeneralCategory general_category, bool inverse, bool& inverse_matched);
};
template<typename T>