RGBCube/serenity
1
Fork 0
mirror of https://github.com/RGBCube/serenity synced 2025-07-26 06:47:34 +00:00
Code Issues Activity Actions

LibRegex: Track string position in both code units and code points

Browse source 
In non-Unicode mode, the existing MatchState::string_position is tracked
in code units; in Unicode mode, it is tracked in code points.

In order for some RegexStringView operations to be performant, it is
useful for the MatchState to have a field to always track the position
in code units. This will allow RegexStringView methods (e.g. operator[])
to perform lookups based on code unit offsets, rather than needing to
iterate over the entire string to find a code point offset.
This commit is contained in:
Timothy Flynn 2021-08-02 15:06:43 -04:00 • committed by Andreas Kling
parent dae7674ca9
commit 27d555bab0
3 changed files with 95 additions and 41 deletions
Download patch file Download diff file Expand all files Collapse all files

5
Userland/Libraries/LibRegex/RegexMatcher.cpp
View file

@ -198,6 +198,7 @@ RegexResult Matcher<Parser>::match(Vector<RegexStringView> const& views, Optiona
auto view_length = view.length();
size_t view_index = m_pattern->start_offset;
state.string_position = view_index;
state.string_position_in_code_units = view_index;
bool succeeded = false;
if (view_index == view_length && m_pattern->parser_result.match_length_minimum == 0) {
@ -210,6 +211,7 @@ RegexResult Matcher<Parser>::match(Vector<RegexStringView> const& views, Optiona
input.match_index = match_count;
state.string_position = view_index;
state.string_position_in_code_units = view_index;
state.instruction_position = 0;
auto success = execute(input, state, temp_output);
@ -241,6 +243,7 @@ RegexResult Matcher<Parser>::match(Vector<RegexStringView> const& views, Optiona
input.match_index = match_count;
state.string_position = view_index;
state.string_position_in_code_units = view_index;
state.instruction_position = 0;
auto success = execute(input, state, output);
@ -388,7 +391,7 @@ private:
Node* previous { nullptr };
};
UniformBumpAllocator<Node, true> m_allocator;
UniformBumpAllocator<Node, true, 8 * MiB> m_allocator;
Node* m_first { nullptr };
Node* m_last { nullptr };
};