RGBCube/serenity
1
Fork 0
mirror of https://github.com/RGBCube/serenity synced 2025-07-26 09:17:35 +00:00
Code Issues Activity Actions

LibRegex: Implement min/max repetition using the Repeat bytecode

Browse source 
This makes repetitions with large max bounds work correctly.
Also fixes an OOM issue found by OSS-Fuzz:
https://oss-fuzz.com/testcase?key=4725721980338176
This commit is contained in:
Ali Mohammad Pur 2021-08-31 00:55:35 +04:30 • committed by Andreas Kling
parent b64d6bb3a3
commit 98624fe03f
1 changed files with 23 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

29
Userland/Libraries/LibRegex/RegexByteCode.h
View file

@ -339,17 +339,34 @@ public:
new_bytecode.insert_bytecode_repetition_n(bytecode_to_repeat, minimum, repetition_mark_id); new_bytecode.insert_bytecode_repetition_n(bytecode_to_repeat, minimum, repetition_mark_id);
if (maximum.has_value()) { if (maximum.has_value()) {
// (REPEAT REGEXP MIN)
// LABEL _MAX_LOOP |
// FORK END |
// REGEXP |
// REPEAT _MAX_LOOP MAX-1 | if max > min
// REGEXP |
// FORK END |
// LABEL END |
auto jump_kind = static_cast<ByteCodeValueType>(greedy ? OpCodeId::ForkStay : OpCodeId::ForkJump); auto jump_kind = static_cast<ByteCodeValueType>(greedy ? OpCodeId::ForkStay : OpCodeId::ForkJump);
if (maximum.value() > minimum) { if (maximum.value() > minimum) {
auto diff = maximum.value() - minimum;
new_bytecode.empend(jump_kind); new_bytecode.empend(jump_kind);
new_bytecode.empend(diff * (bytecode_to_repeat.size() + 2)); // Jump to the _END label new_bytecode.empend((ByteCodeValueType)0); // Placeholder for the jump target.
auto pre_loop_fork_jump_index = new_bytecode.size();
for (T i = 0; i < diff; ++i) { auto repetitions = maximum.value() - minimum;
dbgln("max {}, min {}, reps {}", *maximum, minimum, repetitions);
if (repetitions > 1) {
new_bytecode.extend(bytecode_to_repeat); new_bytecode.extend(bytecode_to_repeat);
new_bytecode.empend(jump_kind); new_bytecode.empend((ByteCodeValueType)OpCodeId::Repeat);
new_bytecode.empend((diff - i - 1) * (bytecode_to_repeat.size() + 2)); // Jump to the _END label new_bytecode.empend(bytecode_to_repeat.size() + 2);
new_bytecode.empend(static_cast<ByteCodeValueType>(repetitions - 1));
new_bytecode.empend(repetition_mark_id);
} }
new_bytecode.extend(bytecode_to_repeat);
new_bytecode.empend(jump_kind);
new_bytecode.empend((ByteCodeValueType)0); // Placeholder for the jump target.
auto post_loop_fork_jump_index = new_bytecode.size();
new_bytecode[pre_loop_fork_jump_index - 1] = (ByteCodeValueType)(new_bytecode.size() - pre_loop_fork_jump_index);
new_bytecode[post_loop_fork_jump_index - 1] = (ByteCodeValueType)(new_bytecode.size() - post_loop_fork_jump_index);
} }
} else { } else {
// no maximum value set, repeat finding if possible // no maximum value set, repeat finding if possible