Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

No more segfault during regex parsing #451

Merged
merged 2 commits into from
Nov 4, 2024
Merged

No more segfault during regex parsing #451

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ecc240f
no more segfault
koniksedy Oct 30, 2024
f706d86
replace function call with trim
koniksedy Oct 31, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
52 changes: 5 additions & 47 deletions src/re2parser.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -252,7 +252,7 @@ namespace {
}
}
}
RegexParser::renumber_states(output_nfa, prog_size, explicit_nfa);
RegexParser::renumber_states(output_nfa, explicit_nfa);
}

private: // private methods
Expand Down Expand Up @@ -442,54 +442,12 @@ namespace {

/**
* Renumbers the states of the input_nfa to be from <0, numberOfStates>
* @param program_size Size of the RE2 prog
* @param input_nfa Nfa which states should be renumbered
* @return Same Nfa as input_nfa but with states from interval <0, numberOfStates>
* @return Equivalent Nfa as input_nfa but trimmed and with states from interval <0, numberOfStates>
*/
static Nfa renumber_states(Nfa* output_nfa,
size_t program_size,
Nfa &input_nfa) {
std::vector<mata::nfa::State> renumbered_states(program_size, mata::nfa::Limits::max_state);
Nfa& renumbered_explicit_nfa = *output_nfa;
for (mata::nfa::State state{ 0 }; state < program_size; state++) {
const auto& transition_list = input_nfa.delta.state_post(state);
// If the transition list is empty, the state is not used
if (transition_list.empty()) {
continue;
} else {
// addNewState returns next unused state of the new NFA, so we map it to the original state
renumbered_states[state] = renumbered_explicit_nfa.add_state();
}
}

for (auto state: input_nfa.final) {
if (static_cast<int>(renumbered_states[state]) == -1) {
renumbered_states[state] = renumbered_explicit_nfa.add_state();
}
renumbered_explicit_nfa.final.insert(renumbered_states[state]);
}

for (mata::nfa::State state{ 0 }; state < program_size; state++) {
const auto& transition_list = input_nfa.delta.state_post(state);
for (const auto& transition: transition_list) {
for (auto stateTo: transition.targets) {
if (renumbered_states[stateTo] == mata::nfa::Limits::max_state) {
renumbered_states[stateTo] = renumbered_explicit_nfa.add_state();
}
assert(renumbered_states[state] <= renumbered_explicit_nfa.num_of_states());
assert(renumbered_states[stateTo] <= renumbered_explicit_nfa.num_of_states());
renumbered_explicit_nfa.delta.add(renumbered_states[state], transition.symbol,
renumbered_states[stateTo]);
}
}
}


for (auto state: input_nfa.initial) {
renumbered_explicit_nfa.initial.insert(renumbered_states[state]);
}

return renumbered_explicit_nfa;
static Nfa renumber_states(Nfa* output_nfa, Nfa &input_nfa) {
*output_nfa = Nfa(input_nfa.delta, input_nfa.initial, input_nfa.final).trim();
return *output_nfa;
}

/**
Expand Down
Loading