RGBCube/serenity
1
Fork 0
mirror of https://github.com/RGBCube/serenity synced 2025-07-26 11:57:34 +00:00
Code Issues Activity Actions

LibRegex: Partially implement the ECMAScript unicodeSets proposal

Browse source 
This skips the new string unicode properties additions, along with \q{}.
This commit is contained in:
Ali Mohammad Pur 2022-07-20 23:22:07 +04:30 • committed by Linus Groh
parent 7734914909
commit 598dc74a76
9 changed files with 611 additions and 69 deletions
Download patch file Download diff file Expand all files Collapse all files

39
Tests/LibRegex/Regex.cpp
View file

@ -765,6 +765,45 @@ TEST_CASE(ECMA262_unicode_match)
}
}
TEST_CASE(ECMA262_unicode_sets_match)
{
struct _test {
StringView pattern;
StringView subject;
bool matches { true };
ECMAScriptFlags options {};
};
constexpr _test tests[] {
{ "[\\w--x]"sv, "x"sv, false },
{ "[\\w&&x]"sv, "y"sv, false },
{ "[\\w--x]"sv, "y"sv, true },
{ "[\\w&&x]"sv, "x"sv, true },
{ "[[0-9\\w]--x--6]"sv, "6"sv, false },
{ "[[0-9\\w]--x--6]"sv, "x"sv, false },
{ "[[0-9\\w]--x--6]"sv, "y"sv, true },
{ "[[0-9\\w]--x--6]"sv, "9"sv, true },
{ "[\\w&&\\d]"sv, "a"sv, false },
{ "[\\w&&\\d]"sv, "4"sv, true },
};
for (auto& test : tests) {
Regex<ECMA262> re(test.pattern, (ECMAScriptFlags)regex::AllFlags::UnicodeSets | test.options);
if constexpr (REGEX_DEBUG) {
dbgln("\n");
RegexDebug regex_dbg(stderr);
regex_dbg.print_raw_bytecode(re);
regex_dbg.print_header();
regex_dbg.print_bytecode(re);
dbgln("\n");
}
EXPECT_EQ(re.parser_result.error, regex::Error::NoError);
auto result = re.match(test.subject).success;
EXPECT_EQ(result, test.matches);
}
}
TEST_CASE(ECMA262_property_match)
{
struct _test {