Files
kte/RegexGuard.cc
T
Claude 9f3da72765 Regex: don't overflow the stack on long lines
libstdc++'s std::regex matcher recurses about once per matched
character, so '.*', 'a+' or '(a|b)*' on a line of a few tens of
thousands of characters (minified JS/JSON) overflowed the 8 MiB stack
and crashed the editor from the regex search prompt or regex replace.

Regex search and regex replace now run their matching on a worker
thread with a 1 GiB reserved stack (RunWithLargeStack; the caller
waits, so nothing is shared concurrently). Renderers skip regex match
highlighting on lines over 10,000 bytes. Catastrophic backtracking
(e.g. (a*)*b) is still possible: std::regex has no time limit.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015rcVQiiWyTzoNrsvLSaAfB
2026-09-24 09:16:04 -07:00

52 lines
971 B
C++

#include "RegexGuard.h"
#include <exception>
#include <pthread.h>
namespace kte {
namespace {
// 1 GiB supports matches spanning several million characters.
constexpr std::size_t kLargeStackBytes = std::size_t{1} << 30;
struct Job {
const std::function<void()> *fn;
std::exception_ptr error;
};
void *
run_job(void *arg)
{
auto *job = static_cast<Job *>(arg);
try {
(*job->fn)();
} catch (...) {
job->error = std::current_exception();
}
return nullptr;
}
} // namespace
void
RunWithLargeStack(const std::function<void()> &fn)
{
Job job{&fn, nullptr};
pthread_attr_t attr;
bool started = false;
pthread_t tid{};
if (pthread_attr_init(&attr) == 0) {
if (pthread_attr_setstacksize(&attr, kLargeStackBytes) == 0)
started = pthread_create(&tid, &attr, run_job, &job) == 0;
pthread_attr_destroy(&attr);
}
if (!started) {
fn();
return;
}
pthread_join(tid, nullptr);
if (job.error)
std::rethrow_exception(job.error);
}
} // namespace kte