mirrors/ladybird
0
0
Fork 0
mirror of https://github.com/LadybirdBrowser/ladybird.git synced 2025-08-28 21:26:22 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 9

LibRegex: Account for opcode size when calculating incoming jump edges

Browse source 
Not accounting for opcode size when calculating incoming jump edges
meant that we were merging nodes where we otherwise shouldn't have been,
for example /.*a|.*b/.
This commit is contained in:
Callum Law 2025-07-29 01:25:28 +12:00 • committed by Ali Mohammad Pur
commit 8ada4b7fdc
Notes: github-actions[bot] 2025-07-28 15:08:19 +00:00
2 changed files with 46 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

54
Libraries/LibRegex/RegexOptimizer.cpp
View file

@ -1372,34 +1372,48 @@ void Optimizer::append_alternation(ByteCode& target, Span<ByteCode> alternatives
auto opcode_bytes = alternative_bytes.slice(state.instruction_position, opcode.size());
switch (opcode.opcode_id()) {
case OpCodeId::Jump:
incoming_jump_edges.ensure(static_cast<OpCode_Jump const&>(opcode).offset() + state.instruction_position).append({ opcode_bytes });
has_any_backwards_jump |= static_cast<OpCode_Jump const&>(opcode).offset() < 0;
case OpCodeId::Jump: {
auto const& cast_opcode = static_cast<OpCode_Jump const&>(opcode);
incoming_jump_edges.ensure(cast_opcode.offset() + cast_opcode.size() + state.instruction_position).append({ opcode_bytes });
has_any_backwards_jump |= cast_opcode.offset() < 0;
break;
case OpCodeId::JumpNonEmpty:
incoming_jump_edges.ensure(static_cast<OpCode_JumpNonEmpty const&>(opcode).offset() + state.instruction_position).append({ opcode_bytes });
has_any_backwards_jump |= static_cast<OpCode_JumpNonEmpty const&>(opcode).offset() < 0;
}
case OpCodeId::JumpNonEmpty: {
auto const& cast_opcode = static_cast<OpCode_JumpNonEmpty const&>(opcode);
incoming_jump_edges.ensure(cast_opcode.offset() + cast_opcode.size() + state.instruction_position).append({ opcode_bytes });
has_any_backwards_jump |= cast_opcode.offset() < 0;
break;
case OpCodeId::ForkJump:
incoming_jump_edges.ensure(static_cast<OpCode_ForkJump const&>(opcode).offset() + state.instruction_position).append({ opcode_bytes });
has_any_backwards_jump |= static_cast<OpCode_ForkJump const&>(opcode).offset() < 0;
}
case OpCodeId::ForkJump: {
auto const& cast_opcode = static_cast<OpCode_ForkJump const&>(opcode);
incoming_jump_edges.ensure(cast_opcode.offset() + cast_opcode.size() + state.instruction_position).append({ opcode_bytes });
has_any_backwards_jump |= cast_opcode.offset() < 0;
break;
case OpCodeId::ForkStay:
incoming_jump_edges.ensure(static_cast<OpCode_ForkStay const&>(opcode).offset() + state.instruction_position).append({ opcode_bytes });
has_any_backwards_jump |= static_cast<OpCode_ForkStay const&>(opcode).offset() < 0;
}
case OpCodeId::ForkStay: {
auto const& cast_opcode = static_cast<OpCode_ForkStay const&>(opcode);
incoming_jump_edges.ensure(cast_opcode.offset() + cast_opcode.size() + state.instruction_position).append({ opcode_bytes });
has_any_backwards_jump |= cast_opcode.offset() < 0;
break;
case OpCodeId::ForkReplaceJump:
incoming_jump_edges.ensure(static_cast<OpCode_ForkReplaceJump const&>(opcode).offset() + state.instruction_position).append({ opcode_bytes });
has_any_backwards_jump |= static_cast<OpCode_ForkReplaceJump const&>(opcode).offset() < 0;
}
case OpCodeId::ForkReplaceJump: {
auto const& cast_opcode = static_cast<OpCode_ForkReplaceJump const&>(opcode);
incoming_jump_edges.ensure(cast_opcode.offset() + cast_opcode.size() + state.instruction_position).append({ opcode_bytes });
has_any_backwards_jump |= cast_opcode.offset() < 0;
break;
case OpCodeId::ForkReplaceStay:
incoming_jump_edges.ensure(static_cast<OpCode_ForkReplaceStay const&>(opcode).offset() + state.instruction_position).append({ opcode_bytes });
has_any_backwards_jump |= static_cast<OpCode_ForkReplaceStay const&>(opcode).offset() < 0;
}
case OpCodeId::ForkReplaceStay: {
auto const& cast_opcode = static_cast<OpCode_ForkReplaceStay const&>(opcode);
incoming_jump_edges.ensure(cast_opcode.offset() + cast_opcode.size() + state.instruction_position).append({ opcode_bytes });
has_any_backwards_jump |= cast_opcode.offset() < 0;
break;
case OpCodeId::Repeat:
incoming_jump_edges.ensure(state.instruction_position - static_cast<OpCode_Repeat const&>(opcode).offset()).append({ opcode_bytes });
}
case OpCodeId::Repeat: {
auto const& cast_opcode = static_cast<OpCode_Repeat const&>(opcode);
incoming_jump_edges.ensure(state.instruction_position - cast_opcode.offset()).append({ opcode_bytes });
has_any_backwards_jump = true;
break;
}
default:
break;
}

12
Tests/LibRegex/TestRegex.cpp
View file

@ -1367,3 +1367,15 @@ TEST_CASE(zero_width_backreference)
EXPECT_EQ(result.capture_group_matches.first()[0].view.to_byte_string(), ""sv);
}
}
TEST_CASE(account_for_opcode_size_calculating_incoming_jump_edges)
{
{
// The optimizer should not optimize the initial ForkStay for these alternatives as they are jumped to from different locations.
Regex<ECMA262> re(".*a|.*b", ECMAScriptFlags::Global);
auto result = re.match("aa"sv);
EXPECT_EQ(result.success, true);
EXPECT_EQ(result.matches.size(), 1u);
EXPECT_EQ(result.matches.first().view.to_byte_string(), "aa"sv);
}
}