Compare commits

..
Author SHA1 Message Date
Niels Lohmann cc749ac699 Keep full byte2 x byte3 combinatorics in the wrong-fourth-byte sections
The maintainer wants exhaustive coverage of every byte combination here
rather than the representative-prefix reduction, matching the style of
the sibling "wrong second/third byte" sections in the same files.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-09-05 23:18:51 +02:00
Niels Lohmann 1c6ca81b8a Fix dead ill-formed-fourth-byte UTF-8 test sections (byte3/byte4 typo)
The "ill-formed: wrong fourth byte" SECTIONs in unit-unicode3.cpp,
unit-unicode4.cpp, and unit-unicode5.cpp guarded their loop with a check
on byte3 instead of byte4. Since the enclosing loop already restricts
byte3 to its valid range, the guard was always true and the section's
"continue" fired unconditionally, so check_utf8string()/check_utf8dump()
were never actually invoked for a malformed fourth byte.

Fixing the guard naively (byte3 -> byte4) would also have swept the full
byte2 x byte3 combinatorics for every byte4 value, adding millions of
redundant iterations: the lexer validates continuation bytes strictly in
sequence with early exit (see next_byte_in_range() in lexer.hpp), so once
byte2/byte3 are within their valid range, the byte4 outcome does not
depend on which valid byte2/byte3 values were chosen. Instead, byte2 and
byte3 are now held to a small hedge of representative valid prefixes
(range corners plus a midpoint) while byte4 is still swept exhaustively
over its full 0x00-0xFF range, since that is the actual property under
test. Also fixed the garbled "skip fourth second byte" comment in
unit-unicode3.cpp.

Verified offline: before the fix, the "wrong fourth byte" subcase
executes 0 assertions in all three files (proving it was dead code);
after the fix, it executes 11520 (unicode3), 34560 (unicode4), and 11520
(unicode5) assertions, and a deliberately reintroduced bug in the
lexer's byte4 range check causes it to fail (proving it is now
meaningful). Total per-file assertion counts grow by the same small
amounts, not by millions, and all other sections in these files still
pass unchanged.

Fixes #5416

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-09-05 23:05:42 +02:00
9 changed files with 4 additions and 371 deletions
@@ -301,16 +301,6 @@ class json_sax_dom_parser
JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back())); JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
} }
if (len != detail::unknown_size())
{
// reserve upfront to avoid repeated reallocations while adding elements,
// but cap the reservation so a bogus/hostile length (which is not bounded
// by max_size(), unlike e.g. std::vector) cannot trigger an oversized
// allocation for a small or truncated input
constexpr std::size_t reserve_cap = 16384;
ref_stack.back()->m_data.m_value.array->reserve(len < reserve_cap ? len : reserve_cap);
}
return true; return true;
} }
@@ -671,16 +661,6 @@ class json_sax_dom_callback_parser
{ {
JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back())); JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
} }
if (len != detail::unknown_size())
{
// reserve upfront to avoid repeated reallocations while adding elements,
// but cap the reservation so a bogus/hostile length (which is not bounded
// by max_size(), unlike e.g. std::vector) cannot trigger an oversized
// allocation for a small or truncated input
constexpr std::size_t reserve_cap = 16384;
ref_stack.back()->m_data.m_value.array->reserve(len < reserve_cap ? len : reserve_cap);
}
} }
return true; return true;
-20
View File
@@ -9829,16 +9829,6 @@ class json_sax_dom_parser
JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back())); JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
} }
if (len != detail::unknown_size())
{
// reserve upfront to avoid repeated reallocations while adding elements,
// but cap the reservation so a bogus/hostile length (which is not bounded
// by max_size(), unlike e.g. std::vector) cannot trigger an oversized
// allocation for a small or truncated input
constexpr std::size_t reserve_cap = 16384;
ref_stack.back()->m_data.m_value.array->reserve(len < reserve_cap ? len : reserve_cap);
}
return true; return true;
} }
@@ -10199,16 +10189,6 @@ class json_sax_dom_callback_parser
{ {
JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back())); JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
} }
if (len != detail::unknown_size())
{
// reserve upfront to avoid repeated reallocations while adding elements,
// but cap the reservation so a bogus/hostile length (which is not bounded
// by max_size(), unlike e.g. std::vector) cannot trigger an oversized
// allocation for a small or truncated input
constexpr std::size_t reserve_cap = 16384;
ref_stack.back()->m_data.m_value.array->reserve(len < reserve_cap ? len : reserve_cap);
}
} }
return true; return true;
-84
View File
@@ -3489,90 +3489,6 @@ TEST_CASE("BJData")
} }
} }
TEST_CASE("issue #5405 - array reserve for definite-length BJData arrays")
{
SECTION("a huge claimed length with no element data must not over-allocate")
{
// optimized form [$type#count: type 'i' (int8), count as a four-byte
// little-endian 'l' (int32) of 0x7FFFFFFF (2147483647), but no
// element data at all. max_size() for a std::vector is far larger
// than this count, so it does not reject the header outright; the
// (capped) reservation must not attempt to allocate space for
// billions of elements before the missing data is detected.
json _;
const std::vector<uint8_t> input = {'[', '$', 'i', '#', 'l', 0xFF, 0xFF, 0xFF, 0x7F};
// On a platform where std::vector<json>::max_size() is smaller than
// the claimed count (e.g. 32-bit, where max_size() is bounded by a
// 32-bit SIZE_MAX divided by sizeof(json)), the SAX consumer's own
// check rejects the header outright (out_of_range.408, with the
// claimed count in the message) instead of accepting it and only
// finding it short of data once the (capped) reservation looks for
// element bytes that were never provided (parse_error.110). Either
// is an acceptable, bounded rejection of the hostile header -- the
// property under test is that no path attempts to allocate space
// for billions of elements.
bool threw = false;
try
{
_ = json::from_bjdata(input);
}
catch (const json::parse_error& e)
{
threw = true;
CHECK(e.id == 110);
CHECK(std::string(e.what()) == "[json.exception.parse_error.110] parse error at byte 10: syntax error while parsing BJData number: unexpected end of input");
}
catch (const json::out_of_range& e)
{
threw = true;
CHECK(e.id == 408);
CHECK(std::string(e.what()).find("excessive array size") != std::string::npos);
}
CHECK(threw);
CHECK(json::from_bjdata(input, true, false).is_discarded());
}
SECTION("arrays of various sizes decode to the same value as before the reserve optimization")
{
for (const auto size :
{
std::size_t(0), std::size_t(1), std::size_t(5), // small
std::size_t(16384), // exactly at the reserve cap
std::size_t(20000) // above the reserve cap
})
{
CAPTURE(size)
json j = json::array();
for (std::size_t i = 0; i < size; ++i)
{
j.push_back(static_cast<int>(i % 1000));
}
// exercise both the plain and the optimized [$type#count encoding
const auto packed_plain = json::to_bjdata(j);
CHECK(json::from_bjdata(packed_plain) == j);
const auto packed_optimized = json::to_bjdata(j, true, true);
CHECK(json::from_bjdata(packed_optimized) == j);
}
}
SECTION("a user-defined SAX consumer is unaffected by the internal DOM reserve optimization")
{
// the reserve() call is local to json_sax_dom_parser / json_sax_dom_callback_parser;
// a custom SAX consumer that does not touch a DOM array sees identical events
json j = json::array();
for (int i = 0; i < 100; ++i)
{
j.push_back(i);
}
const auto packed = json::to_bjdata(j, true, true);
SaxCountdown scp(1000000); // large enough to never trigger an abort
CHECK(json::sax_parse(packed, &scp, json::input_format_t::bjdata));
}
}
TEST_CASE("Universal Binary JSON Specification Examples 1") TEST_CASE("Universal Binary JSON Specification Examples 1")
{ {
SECTION("Null Value") SECTION("Null Value")
-80
View File
@@ -2035,86 +2035,6 @@ TEST_CASE("CBOR definite length equal to the indefinite-length sentinel")
} }
} }
TEST_CASE("issue #5405 - array reserve for definite-length CBOR arrays")
{
SECTION("a huge claimed length with no element data must not over-allocate")
{
// 0x9A: array with a four-byte length; claims 0xFFFFFFFF (4294967295)
// elements but provides none. max_size() for a std::vector is far
// larger than this count, so it does not reject the header outright;
// the (capped) reservation must not attempt to allocate space for
// billions of elements before the missing data is detected.
json _;
const std::vector<uint8_t> input = {0x9A, 0xFF, 0xFF, 0xFF, 0xFF};
// On a platform where std::size_t is narrower than 64 bits (e.g.
// 32-bit), the claimed count 0xFFFFFFFF coincides with that
// platform's detail::unknown_size() sentinel (SIZE_MAX), so the
// format-level size check rejects it outright (out_of_range.408,
// "excessive ... size") before the SAX consumer's own max_size()
// check would even run; on a 64-bit platform it passes both of
// those checks and is only found short of data once the (capped)
// reservation looks for element bytes that were never provided
// (parse_error.110). Either is an acceptable, bounded rejection of
// the hostile header -- the property under test is that no path
// attempts to allocate space for billions of elements.
bool threw = false;
try
{
_ = json::from_cbor(input);
}
catch (const json::parse_error& e)
{
threw = true;
CHECK(e.id == 110);
CHECK(std::string(e.what()) == "[json.exception.parse_error.110] parse error at byte 6: syntax error while parsing CBOR value: unexpected end of input");
}
catch (const json::out_of_range& e)
{
threw = true;
CHECK(e.id == 408);
CHECK(std::string(e.what()).find("excessive") != std::string::npos);
}
CHECK(threw);
CHECK(json::from_cbor(input, true, false).is_discarded());
}
SECTION("arrays of various sizes decode to the same value as before the reserve optimization")
{
for (const auto size :
{
std::size_t{0}, std::size_t{1}, std::size_t{5}, // small
std::size_t{16384}, // exactly at the reserve cap
std::size_t{20000} // above the reserve cap
})
{
CAPTURE(size)
json j = json::array();
for (std::size_t i = 0; i < size; ++i)
{
j.push_back(static_cast<int>(i % 1000));
}
const auto packed = json::to_cbor(j);
CHECK(json::from_cbor(packed) == j);
}
}
SECTION("a user-defined SAX consumer is unaffected by the internal DOM reserve optimization")
{
// the reserve() call is local to json_sax_dom_parser / json_sax_dom_callback_parser;
// a custom SAX consumer that does not touch a DOM array sees identical events
json j = json::array();
for (int i = 0; i < 100; ++i)
{
j.push_back(i);
}
const auto packed = json::to_cbor(j);
SaxCountdown scp(1000000); // large enough to never trigger an abort
CHECK(json::sax_parse(packed, &scp, json::input_format_t::cbor));
}
}
TEST_CASE("CBOR roundtrips" * doctest::skip()) TEST_CASE("CBOR roundtrips" * doctest::skip())
{ {
SECTION("input from flynn") SECTION("input from flynn")
-79
View File
@@ -1597,85 +1597,6 @@ TEST_CASE("MessagePack")
} }
} }
TEST_CASE("issue #5405 - array reserve for definite-length MessagePack arrays")
{
SECTION("a huge claimed length with no element data must not over-allocate")
{
// 0xdd: array 32 (four-byte length); claims 0xFFFFFFFF (4294967295)
// elements but provides none. max_size() for a std::vector is far
// larger than this count, so it does not reject the header outright;
// the (capped) reservation must not attempt to allocate space for
// billions of elements before the missing data is detected.
json _;
const std::vector<uint8_t> input = {0xdd, 0xFF, 0xFF, 0xFF, 0xFF};
// On a platform where std::size_t is narrower than 64 bits (e.g.
// 32-bit), the claimed count 0xFFFFFFFF coincides with that
// platform's SIZE_MAX, which some size-narrowing checks treat the
// same as detail::unknown_size(); it may then be rejected before
// the SAX consumer's own max_size() check (out_of_range.408) rather
// than being accepted and only found short of data once the
// (capped) reservation looks for element bytes that were never
// provided (parse_error.110). Either is an acceptable, bounded
// rejection of the hostile header -- the property under test is
// that no path attempts to allocate space for billions of elements.
bool threw = false;
try
{
_ = json::from_msgpack(input);
}
catch (const json::parse_error& e)
{
threw = true;
CHECK(e.id == 110);
CHECK(std::string(e.what()) == "[json.exception.parse_error.110] parse error at byte 6: syntax error while parsing MessagePack value: unexpected end of input");
}
catch (const json::out_of_range& e)
{
threw = true;
CHECK(e.id == 408);
CHECK(std::string(e.what()).find("excessive") != std::string::npos);
}
CHECK(threw);
CHECK(json::from_msgpack(input, true, false).is_discarded());
}
SECTION("arrays of various sizes decode to the same value as before the reserve optimization")
{
for (const auto size :
{
std::size_t(0), std::size_t(1), std::size_t(5), // small
std::size_t(16384), // exactly at the reserve cap
std::size_t(20000) // above the reserve cap
})
{
CAPTURE(size)
json j = json::array();
for (std::size_t i = 0; i < size; ++i)
{
j.push_back(static_cast<int>(i % 1000));
}
const auto packed = json::to_msgpack(j);
CHECK(json::from_msgpack(packed) == j);
}
}
SECTION("a user-defined SAX consumer is unaffected by the internal DOM reserve optimization")
{
// the reserve() call is local to json_sax_dom_parser / json_sax_dom_callback_parser;
// a custom SAX consumer that does not touch a DOM array sees identical events
json j = json::array();
for (int i = 0; i < 100; ++i)
{
j.push_back(i);
}
const auto packed = json::to_msgpack(j);
SaxCountdown scp(1000000); // large enough to never trigger an abort
CHECK(json::sax_parse(packed, &scp, json::input_format_t::msgpack));
}
}
// use this testcase outside [hide] to run it with Valgrind // use this testcase outside [hide] to run it with Valgrind
TEST_CASE("single MessagePack roundtrip") TEST_CASE("single MessagePack roundtrip")
{ {
-84
View File
@@ -2149,90 +2149,6 @@ TEST_CASE("UBJSON")
} }
} }
TEST_CASE("issue #5405 - array reserve for definite-length UBJSON arrays")
{
SECTION("a huge claimed length with no element data must not over-allocate")
{
// optimized form [$type#count: type 'i' (int8), count as a four-byte
// 'l' (int32) of 0x7FFFFFFF (2147483647), but no element data at all.
// max_size() for a std::vector is far larger than this count, so it
// does not reject the header outright; the (capped) reservation must
// not attempt to allocate space for billions of elements before the
// missing data is detected.
json _;
const std::vector<uint8_t> input = {'[', '$', 'i', '#', 'l', 0x7F, 0xFF, 0xFF, 0xFF};
// On a platform where std::vector<json>::max_size() is smaller than
// the claimed count (e.g. 32-bit, where max_size() is bounded by a
// 32-bit SIZE_MAX divided by sizeof(json)), the SAX consumer's own
// check rejects the header outright (out_of_range.408, with the
// claimed count in the message) instead of accepting it and only
// finding it short of data once the (capped) reservation looks for
// element bytes that were never provided (parse_error.110). Either
// is an acceptable, bounded rejection of the hostile header -- the
// property under test is that no path attempts to allocate space
// for billions of elements.
bool threw = false;
try
{
_ = json::from_ubjson(input);
}
catch (const json::parse_error& e)
{
threw = true;
CHECK(e.id == 110);
CHECK(std::string(e.what()) == "[json.exception.parse_error.110] parse error at byte 10: syntax error while parsing UBJSON number: unexpected end of input");
}
catch (const json::out_of_range& e)
{
threw = true;
CHECK(e.id == 408);
CHECK(std::string(e.what()).find("excessive array size") != std::string::npos);
}
CHECK(threw);
CHECK(json::from_ubjson(input, true, false).is_discarded());
}
SECTION("arrays of various sizes decode to the same value as before the reserve optimization")
{
for (const auto size :
{
std::size_t(0), std::size_t(1), std::size_t(5), // small
std::size_t(16384), // exactly at the reserve cap
std::size_t(20000) // above the reserve cap
})
{
CAPTURE(size)
json j = json::array();
for (std::size_t i = 0; i < size; ++i)
{
j.push_back(static_cast<int>(i % 1000));
}
// exercise both the plain and the optimized [$type#count encoding
const auto packed_plain = json::to_ubjson(j);
CHECK(json::from_ubjson(packed_plain) == j);
const auto packed_optimized = json::to_ubjson(j, true, true);
CHECK(json::from_ubjson(packed_optimized) == j);
}
}
SECTION("a user-defined SAX consumer is unaffected by the internal DOM reserve optimization")
{
// the reserve() call is local to json_sax_dom_parser / json_sax_dom_callback_parser;
// a custom SAX consumer that does not touch a DOM array sees identical events
json j = json::array();
for (int i = 0; i < 100; ++i)
{
j.push_back(i);
}
const auto packed = json::to_ubjson(j, true, true);
SaxCountdown scp(1000000); // large enough to never trigger an abort
CHECK(json::sax_parse(packed, &scp, json::input_format_t::ubjson));
}
}
TEST_CASE("Universal Binary JSON Specification Examples 1") TEST_CASE("Universal Binary JSON Specification Examples 1")
{ {
SECTION("Null Value") SECTION("Null Value")
+2 -2
View File
@@ -304,8 +304,8 @@ TEST_CASE("Unicode (3/5)" * doctest::skip())
{ {
for (int byte4 = 0x00; byte4 <= 0xFF; ++byte4) for (int byte4 = 0x00; byte4 <= 0xFF; ++byte4)
{ {
// skip fourth second byte // skip correct fourth byte
if (0x80 <= byte3 && byte3 <= 0xBF) if (0x80 <= byte4 && byte4 <= 0xBF)
{ {
continue; continue;
} }
+1 -1
View File
@@ -305,7 +305,7 @@ TEST_CASE("Unicode (4/5)" * doctest::skip())
for (int byte4 = 0x00; byte4 <= 0xFF; ++byte4) for (int byte4 = 0x00; byte4 <= 0xFF; ++byte4)
{ {
// skip correct fourth byte // skip correct fourth byte
if (0x80 <= byte3 && byte3 <= 0xBF) if (0x80 <= byte4 && byte4 <= 0xBF)
{ {
continue; continue;
} }
+1 -1
View File
@@ -305,7 +305,7 @@ TEST_CASE("Unicode (5/5)" * doctest::skip())
for (int byte4 = 0x00; byte4 <= 0xFF; ++byte4) for (int byte4 = 0x00; byte4 <= 0xFF; ++byte4)
{ {
// skip correct fourth byte // skip correct fourth byte
if (0x80 <= byte3 && byte3 <= 0xBF) if (0x80 <= byte4 && byte4 <= 0xBF)
{ {
continue; continue;
} }