beenull/ladybird
1
0
Fork 0
mirror of https://github.com/LadybirdBrowser/ladybird.git synced 2024-11-22 15:40:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

LibRegex: Use the correct capture group index in ERE bytecode generation

Browse source 
Otherwise the left and right capture instructions wouldn't point to the
same capture group if there was another nested group there.
This commit is contained in:
Ali Mohammad Pur 2021-09-07 14:33:06 +04:30 committed by Andreas Kling
parent 44b8afdbc4
commit 7fefb8148b
Notes: sideshowbarker 2024-07-18 04:30:23 +09:00 
Author: https://github.com/alimpfard
Commit: https://github.com/SerenityOS/serenity/commit/7fefb8148bc
Pull-request: https://github.com/SerenityOS/serenity/pull/9874
2 changed files with 22 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
Tests/LibRegex/Regex.cpp
View file

@ -485,6 +485,18 @@ TEST_CASE(simple_period_end_benchmark)
EXPECT_EQ(re.search("hello?", m), true);
}
TEST_CASE(posix_extended_nested_capture_group)
{
Regex<PosixExtended> re("(h(e(?<llo>llo)))"); // group 0 -> "hello", group 1 -> "ello", group 2/"llo" -> "llo"
auto result = re.match("hello");
EXPECT(result.success);
EXPECT_EQ(result.capture_group_matches.size(), 1u);
EXPECT_EQ(result.capture_group_matches[0].size(), 3u);
EXPECT_EQ(result.capture_group_matches[0][0].view, "hello"sv);
EXPECT_EQ(result.capture_group_matches[0][1].view, "ello"sv);
EXPECT_EQ(result.capture_group_matches[0][2].view, "llo"sv);
}
TEST_CASE(ECMA262_parse)
{
struct _test {

19
Userland/Libraries/LibRegex/RegexParser.cpp
View file

@ -799,6 +799,7 @@ ALWAYS_INLINE bool PosixExtendedParser::parse_sub_expression(ByteCode& stack, si
last_token = consume();
}
capture_group_name = StringView(start_token.value().characters_without_null_termination(), capture_group_name_length);
++m_parser_state.named_capture_groups_count;
} else if (match(TokenType::EqualSign)) { // positive lookahead
consume();
@ -817,8 +818,11 @@ ALWAYS_INLINE bool PosixExtendedParser::parse_sub_expression(ByteCode& stack, si
}
}
if (!(m_parser_state.regex_options & AllFlags::SkipSubExprResults || prevent_capture_group))
bytecode.insert_bytecode_group_capture_left(m_parser_state.capture_groups_count);
auto current_capture_group = m_parser_state.capture_groups_count;
if (!(m_parser_state.regex_options & AllFlags::SkipSubExprResults || prevent_capture_group)) {
bytecode.insert_bytecode_group_capture_left(current_capture_group);
m_parser_state.capture_groups_count++;
}
ByteCode capture_group_bytecode;
@ -846,13 +850,10 @@ ALWAYS_INLINE bool PosixExtendedParser::parse_sub_expression(ByteCode& stack, si
consume(TokenType::RightParen, Error::MismatchingParen);
if (!(m_parser_state.regex_options & AllFlags::SkipSubExprResults || prevent_capture_group)) {
if (capture_group_name.has_value()) {
bytecode.insert_bytecode_group_capture_right(m_parser_state.capture_groups_count, capture_group_name.value());
++m_parser_state.named_capture_groups_count;
} else {
bytecode.insert_bytecode_group_capture_right(m_parser_state.capture_groups_count);
}
++m_parser_state.capture_groups_count;
if (capture_group_name.has_value())
bytecode.insert_bytecode_group_capture_right(current_capture_group, capture_group_name.value());
else
bytecode.insert_bytecode_group_capture_right(current_capture_group);
}
should_parse_repetition_symbol = true;
break;