Skip to content

[#33567] DocDB: Escape non-ASCII bytes in Slice::ToDebugString regardless of locale #33568

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

Open
ellabaron-code wants to merge 1 commit into
base: master
Choose a base branch
from
Open

[#33567] DocDB: Escape non-ASCII bytes in Slice::ToDebugString regardless of locale #33568

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
21 changes: 20 additions & 1 deletion src/yb/util/slice-test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -224,7 +224,12 @@ TEST(SliceTest, OrderConsistency) {
LOG(INFO) << "made_checks: " << made_checks;
}

TEST(SliceTest, DebugStringLength) {
TEST(SliceTest, DebugStringLengthAndLocale) {
// On macOS in a UTF-8 locale isgraph() accepts bytes >= 0xA1, so ToDebugString leaked them
// into logs unescaped. Run under a UTF-8 locale to verify rendering is locale-independent.
const std::string saved_locale = setlocale(LC_ALL, nullptr);
setlocale(LC_ALL, "en_US.UTF-8");

constexpr auto kNumIters = 1000;
constexpr auto kSize = 1024;
for (auto i = 0; i < kNumIters; ++i) {
Expand All @@ -236,10 +241,24 @@ TEST(SliceTest, DebugStringLength) {
ASSERT_LE(debug_str.size(), max_len * 2 + 40)
<< " max_len: " << max_len << " debug_str: " << debug_str;

// Mostly-graph data stays under the hex-rendering threshold, so non-graph bytes are
// escaped individually.
std::string mixed(kSize, 'a');
for (auto j = 0; j < kSize / 20; ++j) {
mixed[RandomUniformInt(0, kSize - 1)] = static_cast<char>(RandomUniformInt(0, 255));
}
for (const auto& str : {debug_str, Slice(mixed).ToDebugString(0)}) {
for (const char c : str) {
ASSERT_TRUE(c >= ' ' && c < 0x7f) << "garbage in: " << str;
}
}

if (max_len < 100) {
YB_LOG_EVERY_N(INFO, 10) << debug_str;
}
}

setlocale(LC_ALL, saved_locale.c_str());
}

} // namespace yb
6 changes: 4 additions & 2 deletions src/yb/util/slice.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -83,7 +83,9 @@ std::string Slice::ToDebugString(size_t max_len) const {

size_t num_not_graph = 0;
for (size_t i = 0; i < bytes_to_print; i++) {
if (!isgraph(begin_[i])) {
// C locale explicitly: in UTF-8 locales macOS's isgraph() accepts bytes >= 0xA1,
// letting raw binary through into logs.
if (!std::isgraph(static_cast<char>(begin_[i]), std::locale::classic())) {
++num_not_graph;
}
}
Expand All @@ -106,7 +108,7 @@ std::string Slice::ToDebugString(size_t max_len) const {
} else {
for (size_t i = 0; i < bytes_to_print; i++) {
auto ch = begin_[i];
if (!isgraph(ch)) {
if (!std::isgraph(static_cast<char>(ch), std::locale::classic())) {
if (ch == '\r') {
ret += "\\r";
} else if (ch == '\n') {
Expand Down