eliott/ladybird
1
0
Fork 0
mirror of https://github.com/LadybirdBrowser/ladybird synced 2026-04-25 17:25:08 +02:00
Code Issues Packages Projects Releases Wiki Activity

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
parent c8888609f4
commit 8ada4b7fdc
Notes: github-actions[bot] 2025-07-28 15:08:19 +00:00 
Author: https://github.com/Calme1709
Commit: https://github.com/LadybirdBrowser/ladybird/commit/8ada4b7fdca
Pull-request: https://github.com/LadybirdBrowser/ladybird/pull/5623
Reviewed-by: https://github.com/alimpfard ✅
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;
}