1
Fork 0
mirror of https://github.com/RGBCube/serenity synced 2025-07-27 10:07:44 +00:00

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

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

View file

@ -95,12 +95,37 @@ public:
[](auto const& view) { return view.length(); });
}
return length_in_code_units();
}
size_t length_in_code_units() const
{
return m_view.visit(
[](Utf16View const& view) { return view.length_in_code_units(); },
[](Utf8View const& view) { return view.byte_length(); },
[](auto const& view) { return view.length(); });
}
size_t length_of_code_point(u32 code_point) const
{
return m_view.visit(
[](Utf32View const&) { return 1; },
[&](Utf16View const&) {
if (code_point < 0x10000)
return 1;
return 2;
},
[&](auto const&) {
if (code_point <= 0x7f)
return 1;
else if (code_point <= 0x07ff)
return 2;
else if (code_point <= 0xffff)
return 3;
return 4;
});
}
RegexStringView typed_null_view()
{
auto view = m_view.visit(
@ -230,6 +255,7 @@ public:
});
}
// Note: index must always be the code unit offset to return.
u32 operator[](size_t index) const
{
return m_view.visit(
@ -239,17 +265,12 @@ public:
return 256u + ch;
return ch;
},
[&](Utf32View& view) -> u32 { return view[index]; },
[&](Utf16View& view) -> u32 { return view.code_point_at(index); },
[&](auto& view) -> u32 {
// FIXME: Iterating to the code point is inefficient, particularly for very large
// strings. Implement something like code_point_at to Utf8View.
size_t i = index;
for (auto it = view.begin(); it != view.end(); ++it, --i) {
if (i == 0)
return *it;
}
VERIFY_NOT_REACHED();
[&](Utf32View const& view) -> u32 { return view[index]; },
[&](Utf16View const& view) -> u32 { return view.code_point_at(index); },
[&](Utf8View const& view) -> u32 {
auto it = view.iterator_at_byte_offset(index);
VERIFY(it != view.end());
return *it;
});
}
@ -462,11 +483,13 @@ struct MatchInput {
mutable size_t fail_counter { 0 };
mutable Vector<size_t> saved_positions;
mutable Vector<size_t> saved_code_unit_positions;
};
struct MatchState {
size_t string_position_before_match { 0 };
size_t string_position { 0 };
size_t string_position_in_code_units { 0 };
size_t instruction_position { 0 };
size_t fork_at_position { 0 };
Vector<Match> matches;