beenull/ladybird
1
0
Fork 0
mirror of https://github.com/LadybirdBrowser/ladybird.git synced 2024-11-22 07:30:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

LibRegex: Fix lookup table-based range checks in Compare

Browse source 
The lowercase version of a range is not required to be a valid range,
instead of casefolding the range and making it invalid, check twice with
both cases of the input character (which are the same as the input if
not insensitive).
This time includes an actual test :^)
This commit is contained in:
Ali Mohammad Pur 2022-07-07 23:27:51 +04:30 committed by Ali Mohammad Pur
parent b7c50f7094
commit b85666b3d2
Notes: sideshowbarker 2024-07-17 09:35:00 +09:00 
Author: https://github.com/alimpfard
Commit: https://github.com/SerenityOS/serenity/commit/b85666b3d2
Pull-request: https://github.com/SerenityOS/serenity/pull/14513
Reviewed-by: https://github.com/Lubrsi
2 changed files with 7 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
Tests/LibRegex/Regex.cpp
View file

@ -690,6 +690,7 @@ TEST_CASE(ECMA262_match)
{ "a|$"sv, "x"sv, true, (ECMAScriptFlags)regex::AllFlags::Global }, // #11940, Global (not the 'g' flag) regexps should attempt to match the zero-length end of the string too.
{ "foo\nbar"sv, "foo\nbar"sv, true }, // #12126, ECMA262 regexp should match literal newlines without the 's' flag.
{ "foo[^]bar"sv, "foo\nbar"sv, true }, // #12126, ECMA262 regexp should match newline with [^].
{ "^[_A-Z]+$"sv, "_aA"sv, true, ECMAScriptFlags::Insensitive } // Insensitive lookup table: characters in a range do not necessarily lie in the same range after being converted to lowercase.
};
// clang-format on

13
Userland/Libraries/LibRegex/RegexByteCode.cpp
View file

@ -531,16 +531,15 @@ ALWAYS_INLINE ExecutionResult OpCode_Compare::execute(MatchInput const& input, M
auto ch = input.view.substring_view(state.string_position, 1)[0];
auto const* matching_range = binary_search(range_data, ch, nullptr, [insensitive = input.regex_options & AllFlags::Insensitive](auto needle, CharRange range) {
auto from = range.from;
auto to = range.to;
auto upper_case_needle = needle;
auto lower_case_needle = needle;
if (insensitive) {
from = to_ascii_lowercase(from);
to = to_ascii_lowercase(to);
needle = to_ascii_lowercase(needle);
upper_case_needle = to_ascii_uppercase(needle);
lower_case_needle = to_ascii_lowercase(needle);
}
if (needle > to)
if (lower_case_needle > range.to && upper_case_needle > range.to)
return 1;
if (needle < from)
if (lower_case_needle < range.from && upper_case_needle < range.from)
return -1;
return 0;
});