Skip to content

Fix wrong bitmask and other utf8 validation bugs #57

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

Merged
biljazovic merged 4 commits into from
Aug 11, 2026
Merged

Fix wrong bitmask and other utf8 validation bugs #57

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
e9687e8
Add regression tests for UTF-8 noncharacter mask and malformed contin…
Aug 7, 2026
c41ddca
Fix the bitmask bug, check the extra bytes too
Aug 7, 2026
04937d0
Add tests for bad continuation bytes and overlong encodings
Aug 8, 2026
82d6e4a
Reject overlong utf8 encodings
Aug 8, 2026
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
47 changes: 34 additions & 13 deletions include/boost/mqtt5/detail/utf8_mqtt.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,10 @@ enum class validation_result : uint8_t {
invalid
};

inline bool is_continuation_byte(char c) {
return (c & 0xC0) == 0x80;
}

inline int pop_front_unichar(std::string_view& s) {
// assuming that s.length() is > 0

Expand All @@ -31,26 +35,44 @@ inline int pop_front_unichar(std::string_view& s) {
ch = s[0];
s.remove_prefix(1);
}
else if ((n == 0xC0 || n == 0xD0) && s.size() > 1) {
ch = ((s[0] & 0x1F) << 6) | (s[1] & 0x3F);
s.remove_prefix(2);
else if (
(n == 0xC0 || n == 0xD0) && s.size() > 1 &&
is_continuation_byte(s[1])
) {
int decoded = ((s[0] & 0x1F) << 6) | (s[1] & 0x3F);
if (decoded >= 0x80) {
ch = decoded;
s.remove_prefix(2);
}
}
else if ((n == 0xE0) && s.size() > 2) {
ch = ((s[0] & 0x1F) << 12) | ((s[1] & 0x3F) << 6) | (s[2] & 0x3F);
s.remove_prefix(3);
else if (
(n == 0xE0) && s.size() > 2 &&
is_continuation_byte(s[1]) && is_continuation_byte(s[2])
) {
int decoded = ((s[0] & 0x1F) << 12) | ((s[1] & 0x3F) << 6) | (s[2] & 0x3F);
if (decoded >= 0x800) {
ch = decoded;
s.remove_prefix(3);
}
}
else if ((n == 0xF0) && s.size() > 3) {
ch = ((s[0] & 0x1F) << 18) | ((s[1] & 0x3F) << 12) |
else if (
(n == 0xF0) && s.size() > 3 &&
is_continuation_byte(s[1]) && is_continuation_byte(s[2]) &&
is_continuation_byte(s[3])
) {
int decoded = ((s[0] & 0x07) << 18) | ((s[1] & 0x3F) << 12) |
((s[2] & 0x3F) << 6) | (s[3] & 0x3F);
s.remove_prefix(4);
if (decoded >= 0x10000) {
ch = decoded;
s.remove_prefix(4);
}
}

return ch;
}

inline validation_result validate_mqtt_utf8_char(int c) {
constexpr int fe_flag = 0xFE;
constexpr int ff_flag = 0xFF;
constexpr int noncharacter_flag = 0xFFFE;

constexpr int multi_lvl_wildcard = '#';
constexpr int single_lvl_wildcard = '+';
Expand All @@ -62,8 +84,7 @@ inline validation_result validate_mqtt_utf8_char(int c) {
(c < 0x007F || c > 0x009F) && // U+007F...0+009F control characters
(c < 0xD800 || c > 0xDFFF) && // U+D800...U+DFFF surrogates
(c < 0xFDD0 || c > 0xFDEF) && // U+FDD0...U+FDEF non-characters
(c & fe_flag) != fe_flag && // non-characters
(c & ff_flag) != ff_flag
(c & noncharacter_flag) != noncharacter_flag // non-characters
)
return validation_result::valid;

Expand Down
12 changes: 12 additions & 0 deletions test/unit/string_validation.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,6 +57,18 @@ BOOST_AUTO_TEST_CASE(utf8_string_validation) {
BOOST_CHECK(validate_mqtt_utf8(to_str(0xFDF0)) == validation_result::valid);
BOOST_CHECK(validate_mqtt_utf8(to_str(0x1FFFE)) == validation_result::invalid);
BOOST_CHECK(validate_mqtt_utf8(to_str(0x1FFFF)) == validation_result::invalid);

BOOST_CHECK(validate_mqtt_utf8(to_str(0xFE)) == validation_result::valid);
BOOST_CHECK(validate_mqtt_utf8(to_str(0xFF)) == validation_result::valid);
BOOST_CHECK(validate_mqtt_utf8(to_str(0x1F5FE)) == validation_result::valid);

BOOST_CHECK(validate_mqtt_utf8("\xC3z") == validation_result::invalid);
BOOST_CHECK(validate_mqtt_utf8("\xE2\x28\xA1") == validation_result::invalid);
BOOST_CHECK(validate_mqtt_utf8("\xF0\x28\x8C\xBC") == validation_result::invalid);

BOOST_CHECK(validate_mqtt_utf8("\xC1\x81") == validation_result::invalid);
BOOST_CHECK(validate_mqtt_utf8("\xE0\x81\x81") == validation_result::invalid);
BOOST_CHECK(validate_mqtt_utf8("\xF0\x80\x81\x81") == validation_result::invalid);
}

BOOST_AUTO_TEST_CASE(topic_filter_validation) {
Expand Down
Loading