Compare commits

..
Author SHA1 Message Date
Niels Lohmann 93295e08b7 Fix to_bjdata() emitting the Draft-3-only 'B' marker in default Draft-2 mode
_ArrayType_ = "byte" mapped unconditionally to the BJData type marker
'B', regardless of the requested bjdata_version. 'B' is defined only by
BJData Draft 3; with the default version (draft2), this produced a
stream that is invalid for Draft 2 and, unlike every other
_ArrayType_, round-tripped back as a binary value instead of the
original annotated object.

Only accept "byte" / emit 'B' when bjdata_version selects Draft 3.
Under Draft 2, fall back to the same plain-object encoding used
elsewhere in this function for other invalid-annotation cases, so the
value round-trips correctly.

Fixes #5404.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-09-11 17:56:19 +02:00
11 changed files with 69 additions and 597 deletions
+2 -6
View File
@@ -34,14 +34,10 @@ void swap(typename binary_t::container_type& other);
```
1. Exchanges the contents of the JSON value with those of `other`. Does not invoke any move, copy, or swap operations on
individual elements. All iterators and references remain valid. The past-the-end iterator is invalidated. If macro
[`JSON_DIAGNOSTIC_POSITIONS`](../macros/json_diagnostic_positions.md) is defined to `#!cpp 1`, the
[`start_pos()`](start_pos.md)/[`end_pos()`](end_pos.md) diagnostic positions are exchanged along with the value.
individual elements. All iterators and references remain valid. The past-the-end iterator is invalidated.
2. Exchanges the contents of the JSON value from `left` with those of `right`. Does not invoke any move, copy, or swap
operations on individual elements. All iterators and references remain valid. The past-the-end iterator is
invalidated. Implemented as a friend function callable via ADL. If macro
[`JSON_DIAGNOSTIC_POSITIONS`](../macros/json_diagnostic_positions.md) is defined to `#!cpp 1`, the
[`start_pos()`](start_pos.md)/[`end_pos()`](end_pos.md) diagnostic positions are exchanged along with the value.
invalidated. Implemented as a friend function callable via ADL.
3. Exchanges the contents of a JSON array with those of `other`. Does not invoke any move, copy, or swap operations on
individual elements. All iterators and references remain valid. The past-the-end iterator is invalidated.
4. Exchanges the contents of a JSON object with those of `other`. Does not invoke any move, copy, or swap operations on
@@ -8,7 +8,6 @@
#pragma once
#include <algorithm> // min
#include <cstddef>
#include <string> // string
#include <type_traits> // enable_if_t
@@ -18,7 +17,6 @@
#include <nlohmann/detail/exceptions.hpp>
#include <nlohmann/detail/input/lexer.hpp>
#include <nlohmann/detail/macro_scope.hpp>
#include <nlohmann/detail/meta/cpp_future.hpp>
#include <nlohmann/detail/string_concat.hpp>
NLOHMANN_JSON_NAMESPACE_BEGIN
@@ -152,29 +150,6 @@ constexpr std::size_t unknown_size()
return (std::numeric_limits<std::size_t>::max)();
}
/*!
@brief reserve capacity for @a len elements in array @a arr
Reserving upfront avoids repeated reallocations while the elements are added,
but the reservation is capped 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.
The overload below is selected for array types without reserve() (e.g.,
std::deque), which are then left untouched.
*/
template<typename ArrayType>
auto reserve_array(ArrayType& arr, std::size_t len, priority_tag<1> /*unused*/)
-> decltype(arr.reserve(len), void())
{
constexpr std::size_t reserve_cap = 16384;
arr.reserve((std::min)(len, reserve_cap));
}
template<typename ArrayType>
inline void reserve_array(ArrayType& /*arr*/, std::size_t /*len*/, priority_tag<0> /*unused*/)
{}
/*!
@brief SAX implementation to create a JSON value from SAX events
@@ -330,11 +305,6 @@ class json_sax_dom_parser
JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
}
if (len != detail::unknown_size())
{
reserve_array(*ref_stack.back()->m_data.m_value.array, len, priority_tag<1> {});
}
return true;
}
@@ -713,11 +683,6 @@ class json_sax_dom_callback_parser
{
JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
}
if (len != detail::unknown_size())
{
reserve_array(*ref_stack.back()->m_data.m_value.array, len, priority_tag<1> {});
}
}
return true;
@@ -1691,6 +1691,16 @@ class binary_writer
}
CharType dtype = it->second;
// the 'B' (byte) marker is only defined by BJData Draft 3; emitting it
// under the default Draft 2 mode would produce a stream that Draft 2
// readers reject, so such an object falls back to a plain object
// encoding instead (see the "Binary values" section of the BJData
// documentation)
if (dtype == 'B' && bjdata_version != bjdata_version_t::draft3)
{
return true;
}
key = "_ArraySize_";
// the dimensions are written verbatim as the header length below, so a
// value that is not an array cannot produce a valid one: null emits 'Z'
-5
View File
@@ -3576,11 +3576,6 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
std::swap(m_data.m_type, other.m_data.m_type);
std::swap(m_data.m_value, other.m_data.m_value);
#if JSON_DIAGNOSTIC_POSITIONS
std::swap(start_position, other.start_position);
std::swap(end_position, other.end_position);
#endif
set_parents();
other.set_parents();
assert_invariant();
+10 -41
View File
@@ -7892,7 +7892,6 @@ NLOHMANN_JSON_NAMESPACE_END
#include <algorithm> // min
#include <cstddef>
#include <string> // string
#include <type_traits> // enable_if_t
@@ -10730,8 +10729,6 @@ NLOHMANN_JSON_NAMESPACE_END
// #include <nlohmann/detail/macro_scope.hpp>
// #include <nlohmann/detail/meta/cpp_future.hpp>
// #include <nlohmann/detail/string_concat.hpp>
NLOHMANN_JSON_NAMESPACE_BEGIN
@@ -10866,29 +10863,6 @@ constexpr std::size_t unknown_size()
return (std::numeric_limits<std::size_t>::max)();
}
/*!
@brief reserve capacity for @a len elements in array @a arr
Reserving upfront avoids repeated reallocations while the elements are added,
but the reservation is capped 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.
The overload below is selected for array types without reserve() (e.g.,
std::deque), which are then left untouched.
*/
template<typename ArrayType>
auto reserve_array(ArrayType& arr, std::size_t len, priority_tag<1> /*unused*/)
-> decltype(arr.reserve(len), void())
{
constexpr std::size_t reserve_cap = 16384;
arr.reserve((std::min)(len, reserve_cap));
}
template<typename ArrayType>
inline void reserve_array(ArrayType& /*arr*/, std::size_t /*len*/, priority_tag<0> /*unused*/)
{}
/*!
@brief SAX implementation to create a JSON value from SAX events
@@ -11044,11 +11018,6 @@ class json_sax_dom_parser
JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
}
if (len != detail::unknown_size())
{
reserve_array(*ref_stack.back()->m_data.m_value.array, len, priority_tag<1> {});
}
return true;
}
@@ -11427,11 +11396,6 @@ class json_sax_dom_callback_parser
{
JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
}
if (len != detail::unknown_size())
{
reserve_array(*ref_stack.back()->m_data.m_value.array, len, priority_tag<1> {});
}
}
return true;
@@ -20262,6 +20226,16 @@ class binary_writer
}
CharType dtype = it->second;
// the 'B' (byte) marker is only defined by BJData Draft 3; emitting it
// under the default Draft 2 mode would produce a stream that Draft 2
// readers reject, so such an object falls back to a plain object
// encoding instead (see the "Binary values" section of the BJData
// documentation)
if (dtype == 'B' && bjdata_version != bjdata_version_t::draft3)
{
return true;
}
key = "_ArraySize_";
// the dimensions are written verbatim as the header length below, so a
// value that is not an array cannot produce a valid one: null emits 'Z'
@@ -27345,11 +27319,6 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
std::swap(m_data.m_type, other.m_data.m_type);
std::swap(m_data.m_value, other.m_data.m_value);
#if JSON_DIAGNOSTIC_POSITIONS
std::swap(start_position, other.start_position);
std::swap(end_position, other.end_position);
#endif
set_parents();
other.set_parents();
assert_invariant();
+47 -107
View File
@@ -2586,7 +2586,12 @@ TEST_CASE("BJData")
CHECK(json::to_bjdata(json::from_bjdata(v_d), true, true) == v_d);
CHECK(json::to_bjdata(json::from_bjdata(v_D), true, true) == v_D);
CHECK(json::to_bjdata(json::from_bjdata(v_C), true, true) == v_C);
CHECK(json::to_bjdata(json::from_bjdata(v_B), true, true) == v_B);
// v_B uses the Draft-3-only 'B' marker, so it round-trips only when
// Draft 3 is explicitly selected (see GitHub issue #5404); the
// default Draft 2 falls back to a plain object instead, covered by
// the "ndarray with _ArrayType_ "byte" is gated by the BJData draft
// version" section below
CHECK(json::to_bjdata(json::from_bjdata(v_B), true, true, json::bjdata_version_t::draft3) == v_B);
}
SECTION("ndarray with data not matching _ArrayType_ is written as an object")
@@ -2629,8 +2634,10 @@ TEST_CASE("BJData")
// the C++ API stores an int literal as number_integer, so _ArrayType_
// names the wire type rather than the storage. Both storages have to
// produce the same typed array for every type.
// "byte" is checked separately below since it additionally requires
// BJData Draft 3 to be selected explicitly (see GitHub issue #5404).
for (const char* type :
{"uint8", "int8", "uint16", "int16", "uint32", "int32", "uint64", "int64", "char", "byte"
{"uint8", "int8", "uint16", "int16", "uint32", "int32", "uint64", "int64", "char"
})
{
CAPTURE(type);
@@ -2641,6 +2648,14 @@ TEST_CASE("BJData")
CHECK(from_text == json::to_bjdata(json({{"_ArrayType_", type}, {"_ArraySize_", {2, 3}}, {"_ArrayData_", {1, 2, 3, 4, 5, 6}}})));
}
{
const std::string text = R"({"_ArrayType_":"byte","_ArraySize_":[2,3],"_ArrayData_":[1,2,3,4,5,6]})";
const auto from_text = json::to_bjdata(json::parse(text), true, true, json::bjdata_version_t::draft3);
CHECK(from_text.at(0) == '[');
CHECK(from_text == json::to_bjdata(json({{"_ArrayType_", "byte"}, {"_ArraySize_", {2, 3}}, {"_ArrayData_", {1, 2, 3, 4, 5, 6}}}),
true, true, json::bjdata_version_t::draft3));
}
// negative values under a signed type behave the same way
const auto from_neg = json::to_bjdata(json::parse(R"({"_ArrayType_":"int32","_ArraySize_":[2],"_ArrayData_":[-5,7]})"));
CHECK(from_neg.at(0) == '[');
@@ -2823,6 +2838,36 @@ TEST_CASE("BJData")
CHECK(out_single_ok.at(0) == '[');
CHECK(json::from_bjdata(out_single_ok) == json({1.5f}));
}
SECTION("ndarray with _ArrayType_ \"byte\" is gated by the BJData draft version")
{
// the 'B' (byte) marker used by _ArrayType_ "byte" is only defined
// by BJData Draft 3; Draft 2 (the default) has no such marker, so
// emitting it unconditionally produced a stream that a Draft 2
// reader could not parse as intended (see GitHub issue #5404).
// Two dimensions are used so that a successfully written ndarray
// round-trips back into the annotated object (a single dimension
// is, by the BJData ndarray convention, read back as a plain
// binary value rather than the annotated object, same as every
// other single-dimension ndarray of a non-"byte" type is read
// back as a plain array instead of the annotated object).
json const j_byte = json({{"_ArrayType_", "byte"}, {"_ArraySize_", {2, 3}}, {"_ArrayData_", {1, 2, 3, 4, 5, 6}}});
// default (Draft 2): falls back to a plain object and round-trips
const auto out_draft2 = json::to_bjdata(j_byte);
CHECK(out_draft2.at(0) == '{');
CHECK(json::from_bjdata(out_draft2) == j_byte);
// explicit Draft 2: same as the default
const auto out_draft2_explicit = json::to_bjdata(j_byte, true, true, json::bjdata_version_t::draft2);
CHECK(out_draft2_explicit.at(0) == '{');
CHECK(json::from_bjdata(out_draft2_explicit) == j_byte);
// Draft 3 explicitly selected: still uses the compact 'B' ndarray encoding
const auto out_draft3 = json::to_bjdata(j_byte, true, true, json::bjdata_version_t::draft3);
CHECK(out_draft3 == std::vector<uint8_t>({'[', '$', 'B', '#', '[', '$', 'i', '#', 'i', 2, 2, 3, 1, 2, 3, 4, 5, 6}));
CHECK(json::from_bjdata(out_draft3) == j_byte);
}
}
}
@@ -3551,111 +3596,6 @@ TEST_CASE("BJData")
}
}
TEST_CASE("issue #5405 - array reserve for definite-length BJData arrays")
{
#if !defined(JSON_NOEXCEPTION)
// this SECTION relies on catching a thrown exception to distinguish
// which of two acceptable, bounded rejections a hostile header took;
// under JSON_NOEXCEPTION, JSON_THROW never produces a catchable C++
// exception (it aborts instead), so this cannot be tested that way here
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);
// json_sax_dom_parser::start_array()'s max_size() check (unlike the
// scanner's own parse_error path) throws unconditionally via
// JSON_THROW rather than going through sax->parse_error(), so it is
// not gated by allow_exceptions=false on a platform where this
// header hits that check (e.g. 32-bit, see above) -- allow either
// a discarded result or the same out_of_range it throws with
// exceptions enabled.
try
{
CHECK(json::from_bjdata(input, true, false).is_discarded());
}
catch (const json::out_of_range& e)
{
CHECK(e.id == 408);
}
}
#endif
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")
{
SECTION("Null Value")
-86
View File
@@ -2174,92 +2174,6 @@ TEST_CASE("CBOR indefinite-length strings do not recurse per chunk")
}
}
TEST_CASE("issue #5405 - array reserve for definite-length CBOR arrays")
{
#if !defined(JSON_NOEXCEPTION)
// this SECTION relies on catching a thrown exception to distinguish
// which of two acceptable, bounded rejections a hostile header took;
// under JSON_NOEXCEPTION, JSON_THROW never produces a catchable C++
// exception (it aborts instead), so this cannot be tested that way here
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());
}
#endif
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())
{
SECTION("input from flynn")
-80
View File
@@ -2259,86 +2259,6 @@ TEST_CASE("parser class")
#endif
}
#if JSON_DIAGNOSTIC_POSITIONS
TEST_CASE("diagnostic positions: value lifetime")
{
SECTION("copy constructor copies positions, recursively")
{
const std::string s = R"({"a":1,"b":[1,2,3]})";
const json a = json::parse(s);
const json b = a; // NOLINT(performance-unnecessary-copy-initialization)
CHECK(b.start_pos() == a.start_pos());
CHECK(b.end_pos() == a.end_pos());
CHECK(b["b"].start_pos() == a["b"].start_pos());
CHECK(b["b"].end_pos() == a["b"].end_pos());
}
SECTION("move constructor resets the moved-from value to npos")
{
const std::string s = R"({"a":1,"b":[1,2,3]})";
json a = json::parse(s);
const auto a_start = a.start_pos();
const auto a_end = a.end_pos();
const json b(std::move(a));
CHECK(b.start_pos() == a_start);
CHECK(b.end_pos() == a_end);
CHECK(a.start_pos() == std::string::npos); // NOLINT(bugprone-use-after-move,clang-analyzer-cplusplus.Move)
CHECK(a.end_pos() == std::string::npos); // NOLINT(bugprone-use-after-move,clang-analyzer-cplusplus.Move)
}
SECTION("swap() exchanges positions along with the values")
{
// basic_json::swap() (and the friend swap() that forwards to it) used
// to swap only m_data.m_type/m_data.m_value, leaving
// start_position/end_position untouched -- unlike copy-assignment's
// operator=(basic_json), which swaps positions as part of its
// copy-and-swap implementation. After swap(a, b), each value ended up
// with the *other* value's content but its *own* original position.
// This is now fixed so that swap() is consistent with copy-assignment.
json a = json::parse(R"({"a":1})");
json b = json::parse(R"([1,2,3,4,5])");
const auto a_start = a.start_pos();
const auto a_end = a.end_pos();
const auto b_start = b.start_pos();
const auto b_end = b.end_pos();
// lengths (and thus end positions) differ, which is enough to tell
// after the swap whether positions actually moved with the values
CHECK(a_end != b_end);
using std::swap;
swap(a, b);
CHECK(a == json::parse(R"([1,2,3,4,5])"));
CHECK(b == json::parse(R"({"a":1})"));
CHECK(a.start_pos() == b_start);
CHECK(a.end_pos() == b_end);
CHECK(b.start_pos() == a_start);
CHECK(b.end_pos() == a_end);
// member swap() behaves the same as the free function
json c = json::parse(R"({"a":1})");
json d = json::parse(R"([1,2,3,4,5])");
const auto c_start = c.start_pos();
const auto c_end = c.end_pos();
const auto d_start = d.start_pos();
const auto d_end = d.end_pos();
c.swap(d);
CHECK(c.start_pos() == d_start);
CHECK(c.end_pos() == d_end);
CHECK(d.start_pos() == c_start);
CHECK(d.end_pos() == c_end);
}
}
#endif
// this test relies on parse errors being thrown, so it is skipped when
// exceptions are disabled (json::parse aborts instead of throwing there)
#if !defined(JSON_NOEXCEPTION)
-85
View File
@@ -1597,91 +1597,6 @@ TEST_CASE("MessagePack")
}
}
TEST_CASE("issue #5405 - array reserve for definite-length MessagePack arrays")
{
#if !defined(JSON_NOEXCEPTION)
// this SECTION relies on catching a thrown exception to distinguish
// which of two acceptable, bounded rejections a hostile header took;
// under JSON_NOEXCEPTION, JSON_THROW never produces a catchable C++
// exception (it aborts instead), so this cannot be tested that way here
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());
}
#endif
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
TEST_CASE("MessagePack nesting does not consume the call stack")
{
-46
View File
@@ -27,7 +27,6 @@ using ordered_json = nlohmann::ordered_json;
#endif
#include <cstdio>
#include <deque>
#include <list>
#include <type_traits>
#include <utility>
@@ -897,49 +896,4 @@ TEST_CASE("issue #5402 - update(merge_objects=true) overwrites a primitive with
}
TEST_CASE("regression test #5476 - array type without reserve()")
{
// the capacity reserved for definite-length arrays must not require the
// array type to have a reserve() member function
using deque_json = nlohmann::basic_json<std::map, std::deque>;
SECTION("std::deque")
{
const auto j = deque_json::parse(R"({"a":[1,[2,3]],"b":[]})");
CHECK(j.dump() == R"({"a":[1,[2,3]],"b":[]})");
// the binary formats pass a definite length to start_array()
CHECK(deque_json::from_cbor(deque_json::to_cbor(j)) == j);
CHECK(deque_json::from_msgpack(deque_json::to_msgpack(j)) == j);
// parse() instantiates the callback parser as well, which reserves too
const auto with_callback = deque_json::parse(R"([1,2,3])", [](int /*depth*/, deque_json::parse_event_t /*event*/, deque_json& /*parsed*/) noexcept
{
return true;
});
CHECK(with_callback == deque_json({1, 2, 3}));
}
SECTION("std::vector still reserves")
{
json array = json::array();
for (int i = 0; i < 100; ++i)
{
array.push_back(i);
}
const auto j = json::from_cbor(json::to_cbor(array));
CHECK(j == array);
CHECK(j.get_ref<const json::array_t&>().capacity() >= 100);
}
SECTION("the reservation stays capped")
{
// CBOR array announcing 2^32-1 elements, but truncated right after the
// header: the input must be rejected without reserving that capacity
const std::vector<std::uint8_t> truncated = {0x9A, 0xFF, 0xFF, 0xFF, 0xFF};
CHECK(json::from_cbor(truncated, true, false).is_discarded());
}
}
DOCTEST_CLANG_SUPPRESS_WARNING_POP
-106
View File
@@ -2315,112 +2315,6 @@ TEST_CASE("UBJSON optimized arrays of a valueless type are bounded")
}
}
TEST_CASE("issue #5405 - array reserve for definite-length UBJSON arrays")
{
#if !defined(JSON_NOEXCEPTION)
// this SECTION relies on catching a thrown exception to distinguish
// which of two acceptable, bounded rejections a hostile header took;
// under JSON_NOEXCEPTION, JSON_THROW never produces a catchable C++
// exception (it aborts instead), so this cannot be tested that way here
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);
// json_sax_dom_parser::start_array()'s max_size() check (unlike the
// scanner's own parse_error path) throws unconditionally via
// JSON_THROW rather than going through sax->parse_error(), so it is
// not gated by allow_exceptions=false on a platform where this
// header hits that check (e.g. 32-bit, see above) -- allow either
// a discarded result or the same out_of_range it throws with
// exceptions enabled.
try
{
CHECK(json::from_ubjson(input, true, false).is_discarded());
}
catch (const json::out_of_range& e)
{
CHECK(e.id == 408);
}
}
#endif
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")
{
SECTION("Null Value")