wt/json
1
0
Fork 0
mirror of https://github.com/nlohmann/json.git synced 2026-10-12 10:13:13 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
9adb510a0d0687ca8dc1165d005c9766a4bccbeb
json/tests/src/unit-regression2.cpp
T
Niels Lohmann 9adb510a0d Recover from parse errors when parse_error() returns true (#3989) 
The return value of json_sax::parse_error() was documented both as "must
return false" and as "whether the parsing should continue", and the code
just passed it on. For JSON text, parsing stopped anyway, but sax_parse()
could report success for invalid input. The binary readers read on after
the error, looping forever on a CBOR indefinite-length array without its
end.

Now false stops parsing, and true recovers from the error:

- JSON text is repaired with the smallest local edit (insert a missing
  ',' or ':', remove a stray token, keep the readable part of a broken
  string or number, null for a value that cannot be read, close the
  innermost container at a wrong closing bracket and all of them at the
  end of the input), and parsing continues. The SAX events stay balanced,
  every key is followed by exactly one value, and each token is reported
  at most once.
- The binary formats cannot resynchronize, so they stop, but complete
  the value read so far.

sax_parse() returns false after any error. parse(), accept(), and the
from_*() functions never recover and compile to the same code as before.

Supersedes #4522.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-09-27 20:16:42 +02:00

1132 lines
38 KiB
C++
Raw Blame History

// __ _____ _____ _____
// __| | __| | | | JSON for Modern C++ (supporting code)
// | | |__ | | | | | | version 3.12.0
// |_____|_____|_____|_|___| https://github.com/nlohmann/json
//
// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
// SPDX-License-Identifier: MIT
// cmake/test.cmake selects the C++ standard versions with which to build a
// unit test based on the presence of JSON_HAS_CPP_<VERSION> macros.
// When using macros that are only defined for particular versions of the standard
// (e.g., JSON_HAS_FILESYSTEM for C++17 and up), please mention the corresponding
// version macro in a comment close by, like this:
// JSON_HAS_CPP_<VERSION> (do not remove; see note at top of file)
#include "doctest_compatibility.h"
// for some reason including this after the json header leads to linker errors with VS 2017...
#include <locale>
#define JSON_TESTS_PRIVATE
#include <nlohmann/json.hpp>
using json = nlohmann::json;
using ordered_json = nlohmann::ordered_json;
#ifdef JSON_TEST_NO_GLOBAL_UDLS
using namespace nlohmann::literals; // NOLINT(google-build-using-namespace)
#endif
#include <cstdio>
#include <list>
#include <type_traits>
#include <utility>
#include "test_utils.hpp"
#ifdef JSON_HAS_CPP_17
#include <any>
#include <variant>
#endif
#ifdef JSON_HAS_CPP_17
#if __has_include(<optional>)
#include <optional>
#elif __has_include(<experimental/optional>)
#include <experimental/optional>
#endif
/////////////////////////////////////////////////////////////////////
// for #4804
/////////////////////////////////////////////////////////////////////
using json_4804 = nlohmann::basic_json<std::map, // ObjectType
std::vector, // ArrayType
std::string, // StringType
bool, // BooleanType
std::int64_t, // NumberIntegerType
std::uint64_t, // NumberUnsignedType
double, // NumberFloatType
std::allocator, // AllocatorType
nlohmann::adl_serializer, // JSONSerializer
std::vector<std::byte>, // BinaryType
void // CustomBaseClass
>;
#endif
#ifdef JSON_HAS_CPP_20
#if __has_include(<span>)
#include <span>
#endif
#endif
/////////////////////////////////////////////////////////////////////
// for #4825 - explicitly instantiating basic_json must compile; this
// forces instantiation of binary_writer::write_bjdata_ndarray, whose
// static_cast<string_t> was ambiguous under explicit instantiation on
// C++17. Merely compiling this translation unit is the regression test.
/////////////////////////////////////////////////////////////////////
template class nlohmann::basic_json<>;
/////////////////////////////////////////////////////////////////////
// for #4440
/////////////////////////////////////////////////////////////////////
#if JSON_HAS_RANGES == 1
#include <ranges>
#endif
// NLOHMANN_JSON_SERIALIZE_ENUM uses a static std::pair
DOCTEST_CLANG_SUPPRESS_WARNING_PUSH
DOCTEST_CLANG_SUPPRESS_WARNING("-Wexit-time-destructors")
/////////////////////////////////////////////////////////////////////
// for #1021
/////////////////////////////////////////////////////////////////////
using float_json = nlohmann::basic_json<std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t, float>;
/////////////////////////////////////////////////////////////////////
// for #1647
/////////////////////////////////////////////////////////////////////
namespace
{
struct NonDefaultFromJsonStruct
{};
inline bool operator==(NonDefaultFromJsonStruct const& /*unused*/, NonDefaultFromJsonStruct const& /*unused*/)
{
return true;
}
enum class for_1647
{
one,
two
};
// NOLINTNEXTLINE(misc-const-correctness,cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays): this is a false positive
NLOHMANN_JSON_SERIALIZE_ENUM(for_1647,
{
{for_1647::one, "one"},
{for_1647::two, "two"},
})
} // namespace
/////////////////////////////////////////////////////////////////////
// for #1299
/////////////////////////////////////////////////////////////////////
struct Data
{
Data() = default;
Data(std::string a_, std::string b_)
: a(std::move(a_))
, b(std::move(b_))
{}
std::string a{}; // NOLINT(readability-redundant-member-init)
std::string b{}; // NOLINT(readability-redundant-member-init)
};
void from_json(const json& j, Data& data); // NOLINT(misc-use-internal-linkage)
void from_json(const json& j, Data& data)
{
j["a"].get_to(data.a);
j["b"].get_to(data.b);
}
bool operator==(Data const& lhs, Data const& rhs); // NOLINT(misc-use-internal-linkage)
bool operator==(Data const& lhs, Data const& rhs)
{
return lhs.a == rhs.a && lhs.b == rhs.b;
}
//bool operator!=(Data const& lhs, Data const& rhs)
//{
// return !(lhs == rhs);
//}
namespace nlohmann
{
template<>
struct adl_serializer<NonDefaultFromJsonStruct>
{
static NonDefaultFromJsonStruct from_json(json const& /*unused*/) noexcept
{
return {};
}
};
} // namespace nlohmann
/////////////////////////////////////////////////////////////////////
// for #1805
/////////////////////////////////////////////////////////////////////
struct NotSerializableData
{
int mydata;
float myfloat;
};
/////////////////////////////////////////////////////////////////////
// for #2574
/////////////////////////////////////////////////////////////////////
struct NonDefaultConstructible
{
explicit NonDefaultConstructible(int a)
: x(a)
{}
int x;
};
namespace nlohmann
{
template<>
struct adl_serializer<NonDefaultConstructible>
{
static NonDefaultConstructible from_json(json const& j)
{
return NonDefaultConstructible(j.get<int>());
}
};
} // namespace nlohmann
/////////////////////////////////////////////////////////////////////
// for #2824
/////////////////////////////////////////////////////////////////////
class sax_no_exception : public nlohmann::detail::json_sax_dom_parser<json, nlohmann::detail::string_input_adapter_type>
{
public:
explicit sax_no_exception(json& j)
: nlohmann::detail::json_sax_dom_parser<json, nlohmann::detail::string_input_adapter_type>(j, false)
{}
static bool parse_error(std::size_t /*position*/, const std::string& /*last_token*/, const json::exception& ex)
{
error_string = new std::string(ex.what()); // NOLINT(cppcoreguidelines-owning-memory)
return false;
}
static std::string* error_string;
};
std::string* sax_no_exception::error_string = nullptr;
/////////////////////////////////////////////////////////////////////
// for #2982
/////////////////////////////////////////////////////////////////////
template<class T>
class my_allocator : public std::allocator<T>
{
public:
using std::allocator<T>::allocator;
my_allocator() = default;
template<class U> my_allocator(const my_allocator<U>& /*unused*/) { }
template <class U>
struct rebind
{
using other = my_allocator<U>;
};
};
TEST_CASE("regression tests 2")
{
SECTION("issue #1001 - Fix memory leak during parser callback")
{
const auto* geojsonExample = R"(
{ "type": "FeatureCollection",
"features": [
{ "type": "Feature",
"geometry": {"type": "Point", "coordinates": [102.0, 0.5]},
"properties": {"prop0": "value0"}
},
{ "type": "Feature",
"geometry": {
"type": "LineString",
"coordinates": [
[102.0, 0.0], [103.0, 1.0], [104.0, 0.0], [105.0, 1.0]
]
},
"properties": {
"prop0": "value0",
"prop1": 0.0
}
},
{ "type": "Feature",
"geometry": {
"type": "Polygon",
"coordinates": [
[ [100.0, 0.0], [101.0, 0.0], [101.0, 1.0],
[100.0, 1.0], [100.0, 0.0] ]
]
},
"properties": {
"prop0": "value0",
"prop1": {"this": "that"}
}
}
]
})";
const json::parser_callback_t cb = [&](int /*level*/, json::parse_event_t event, json & parsed) noexcept
{
// skip uninteresting events
if (event == json::parse_event_t::value && !parsed.is_primitive())
{
return false;
}
switch (event)
{
case json::parse_event_t::key:
{
return true;
}
case json::parse_event_t::value:
{
return false;
}
case json::parse_event_t::object_start:
{
return true;
}
case json::parse_event_t::object_end:
{
return false;
}
case json::parse_event_t::array_start:
{
return true;
}
case json::parse_event_t::array_end:
{
return false;
}
default:
{
return true;
}
}
};
auto j = json::parse(geojsonExample, cb, true);
CHECK(j == json());
}
SECTION("issue #1021 - to/from_msgpack only works with standard typization")
{
float_json j = 1000.0;
CHECK(float_json::from_cbor(float_json::to_cbor(j)) == j);
CHECK(float_json::from_msgpack(float_json::to_msgpack(j)) == j);
CHECK(float_json::from_ubjson(float_json::to_ubjson(j)) == j);
CHECK(float_json::from_bon8(float_json::to_bon8(j)) == j);
float_json j2 = {1000.0, 2000.0, 3000.0};
CHECK(float_json::from_ubjson(float_json::to_ubjson(j2, true, true)) == j2);
}
SECTION("issue #1045 - Using STL algorithms with JSON containers with expected results?")
{
json diffs = nlohmann::json::array();
json m1{{"key1", 42}};
json m2{{"key2", 42}};
auto p1 = m1.items();
auto p2 = m2.items();
using it_type = decltype(p1.begin());
std::set_difference(
p1.begin(),
p1.end(),
p2.begin(),
p2.end(),
std::inserter(diffs, diffs.end()),
[&](const it_type & e1, const it_type & e2) -> bool
{
using comper_pair = std::pair<std::string, decltype(e1.value())>; // Trying to avoid unneeded copy
return comper_pair(e1.key(), e1.value()) < comper_pair(e2.key(), e2.value()); // Using pair comper
});
CHECK(diffs.size() == 1); // Note the change here, was 2
}
#ifdef JSON_HAS_CPP_17
SECTION("issue #1292 - Serializing std::variant causes stack overflow")
{
static_assert(!std::is_constructible<json, std::variant<int, float>>::value, "unexpected value");
}
#endif
SECTION("issue #1299 - compile error in from_json converting to container "
"with std::pair")
{
const json j =
{
{"1", {{"a", "testa_1"}, {"b", "testb_1"}}},
{"2", {{"a", "testa_2"}, {"b", "testb_2"}}},
{"3", {{"a", "testa_3"}, {"b", "testb_3"}}},
};
const std::map<std::string, Data> expected
{
{"1", {"testa_1", "testb_1"}},
{"2", {"testa_2", "testb_2"}},
{"3", {"testa_3", "testb_3"}},
};
const auto data = j.get<decltype(expected)>();
CHECK(expected == data);
}
SECTION("issue #1445 - buffer overflow in dumping invalid utf-8 strings")
{
SECTION("a bunch of -1, ensure_ascii=true")
{
const auto length = 300;
json dump_test;
dump_test["1"] = std::string(length, static_cast<std::string::value_type>(-1));
std::string expected = R"({"1":")";
for (int i = 0; i < length; ++i)
{
expected += "\\ufffd";
}
expected += "\"}";
auto s = dump_test.dump(-1, ' ', true, nlohmann::json::error_handler_t::replace);
CHECK(s == expected);
}
SECTION("a bunch of -2, ensure_ascii=false")
{
const auto length = 500;
json dump_test;
dump_test["1"] = std::string(length, static_cast<std::string::value_type>(-2));
std::string expected = R"({"1":")";
for (int i = 0; i < length; ++i)
{
expected += "\xEF\xBF\xBD";
}
expected += "\"}";
auto s = dump_test.dump(-1, ' ', false, nlohmann::json::error_handler_t::replace);
CHECK(s == expected);
}
SECTION("test case in issue #1445")
{
nlohmann::json dump_test;
const std::array<int, 108> data =
{
{109, 108, 103, 125, -122, -53, 115, 18, 3, 0, 102, 19, 1, 15, -110, 13, -3, -1, -81, 32, 2, 0, 0, 0, 0, 0, 0, 0, 8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -80, 2, 0, 0, 96, -118, 46, -116, 46, 109, -84, -87, 108, 14, 109, -24, -83, 13, -18, -51, -83, -52, -115, 14, 6, 32, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 64, 3, 0, 0, 0, 35, -74, -73, 55, 57, -128, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 33, 0, 0, 0, -96, -54, -28, -26}
};
std::string s;
for (const int i : data)
{
s += static_cast<char>(i);
}
dump_test["1"] = s;
// dump() is nodiscard; this only checks that dumping does not throw/crash
utils::ignore_return_value(dump_test.dump(-1, ' ', true, nlohmann::json::error_handler_t::replace));
}
}
SECTION("issue #1447 - Integer Overflow (OSS-Fuzz 12506)")
{
const json j = json::parse("[-9223372036854775808]");
CHECK(j.dump() == "[-9223372036854775808]");
}
SECTION("issue #1708 - minimum value of int64_t can be outputted")
{
constexpr auto smallest = (std::numeric_limits<int64_t>::min)();
const json j = smallest;
CHECK(j.dump() == std::to_string(smallest));
}
SECTION("issue #1727 - Contains with non-const lvalue json_pointer picks the wrong overload")
{
const json j = {{"root", {{"settings", {{"logging", true}}}}}};
auto jptr1 = "/root/settings/logging"_json_pointer;
auto jptr2 = json::json_pointer{"/root/settings/logging"};
CHECK(j.contains(jptr1));
CHECK(j.contains(jptr2));
}
SECTION("issue #1647 - compile error when deserializing enum if both non-default from_json and non-member operator== exists for other type")
{
// does not compile on ICPC when targeting C++20
#if !(defined(__INTEL_COMPILER) && __cplusplus >= 202000)
{
const json j;
const NonDefaultFromJsonStruct x(j);
NonDefaultFromJsonStruct y;
CHECK(x == y);
}
#endif
auto val = nlohmann::json("one").get<for_1647>();
CHECK(val == for_1647::one);
const json j = val;
}
SECTION("issue #1715 - json::from_cbor does not respect allow_exceptions = false when input is string literal")
{
SECTION("string literal")
{
const json cbor = json::from_cbor("B", true, false);
CHECK(cbor.is_discarded());
}
SECTION("string array")
{
const std::array<char, 2> input = {{'B', 0x00}};
const json cbor = json::from_cbor(input, true, false);
CHECK(cbor.is_discarded());
}
SECTION("std::string")
{
const json cbor = json::from_cbor(std::string("B"), true, false);
CHECK(cbor.is_discarded());
}
}
SECTION("issue #1805 - A pair<T1, T2> is json constructible only if T1 and T2 are json constructible")
{
static_assert(!std::is_constructible<json, std::pair<std::string, NotSerializableData>>::value, "unexpected result");
static_assert(!std::is_constructible<json, std::pair<NotSerializableData, std::string>>::value, "unexpected result");
static_assert(std::is_constructible<json, std::pair<int, std::string>>::value, "unexpected result");
}
SECTION("issue #1825 - A tuple<Args..> is json constructible only if all T in Args are json constructible")
{
static_assert(!std::is_constructible<json, std::tuple<std::string, NotSerializableData>>::value, "unexpected result");
static_assert(!std::is_constructible<json, std::tuple<NotSerializableData, std::string>>::value, "unexpected result");
static_assert(std::is_constructible<json, std::tuple<int, std::string>>::value, "unexpected result");
}
SECTION("issue #1983 - JSON patch diff for op=add formation is not as per standard (RFC 6902)")
{
const auto source = R"({ "foo": [ "1", "2" ] })"_json;
const auto target = R"({"foo": [ "1", "2", "3" ]})"_json;
const auto result = json::diff(source, target);
CHECK(result.dump() == R"([{"op":"add","path":"/foo/-","value":"3"}])");
}
SECTION("issue #2067 - cannot serialize binary data to text JSON")
{
const std::array<unsigned char, 23> data = {{0x81, 0xA4, 0x64, 0x61, 0x74, 0x61, 0xC4, 0x0F, 0x33, 0x30, 0x30, 0x32, 0x33, 0x34, 0x30, 0x31, 0x30, 0x37, 0x30, 0x35, 0x30, 0x31, 0x30}};
const json j = json::from_msgpack(data.data(), data.size());
// dump() is nodiscard; this only checks that dumping does not throw
CHECK_NOTHROW(
utils::ignore_return_value(
j.dump(4, // Indent
' ', // Indent char
false, // Ensure ascii
json::error_handler_t::strict // Error
)));
}
SECTION("PR #2181 - regression bug with lvalue")
{
// see https://github.com/nlohmann/json/pull/2181#issuecomment-653326060
const json j{{"x", "test"}};
const std::string defval = "default value";
auto val = j.value("x", defval); // NOLINT(bugprone-unused-local-non-trivial-variable)
auto val2 = j.value("y", defval); // NOLINT(bugprone-unused-local-non-trivial-variable)
}
SECTION("issue #2293 - eof doesn't cause parsing to stop")
{
const std::vector<uint8_t> data =
{
0x7B,
0x6F,
0x62,
0x6A,
0x65,
0x63,
0x74,
0x20,
0x4F,
0x42
};
const json result = json::from_cbor(data, true, false);
CHECK(result.is_discarded());
}
SECTION("issue #2315 - json.update and vector<pair>does not work with ordered_json")
{
nlohmann::ordered_json jsonAnimals = {{"animal", "dog"}};
const nlohmann::ordered_json jsonCat = {{"animal", "cat"}};
jsonAnimals.update(jsonCat);
CHECK(jsonAnimals["animal"] == "cat");
auto jsonAnimals_parsed = nlohmann::ordered_json::parse(jsonAnimals.dump());
CHECK(jsonAnimals == jsonAnimals_parsed);
const std::vector<std::pair<std::string, int64_t>> intData = {std::make_pair("aaaa", 11),
std::make_pair("bbb", 222)
};
nlohmann::ordered_json jsonObj;
for (const auto& data : intData)
{
jsonObj[data.first] = data.second;
}
CHECK(jsonObj["aaaa"] == 11);
CHECK(jsonObj["bbb"] == 222);
}
SECTION("issue #2330 - ignore_comment=true fails on multiple consecutive lines starting with comments")
{
const std::string ss = "//\n//\n{\n}\n";
const json j = json::parse(ss, nullptr, true, true);
CHECK(j.dump() == "{}");
}
#ifdef JSON_HAS_CPP_20
#ifndef _LIBCPP_VERSION // see https://github.com/nlohmann/json/issues/4490
// classic Intel ICC reports <span> as includable but cannot actually compile
// std::span/std::as_bytes usage below
#if __has_include(<span>) && !defined(__ICC) && !defined(__INTEL_COMPILER)
SECTION("issue #2546 - parsing containers of std::byte")
{
const char DATA[] = R"("Hello, world!")"; // NOLINT(misc-const-correctness,cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
// exclude the trailing '\0' that string-literal initialization adds to
// DATA: std::span(DATA) would span the full array extent (including
// that NUL), which is only silently accepted as end-of-input by default
// and would fail under JSON_STRICT_NUL_HANDLING
const auto s = std::as_bytes(std::span(DATA, sizeof(DATA) - 1));
const json j = json::parse(s);
CHECK(j.dump() == "\"Hello, world!\"");
}
#endif
#endif
#endif
SECTION("issue #2574 - Deserialization to std::array, std::pair, and std::tuple with non-default constructable types fails")
{
SECTION("std::array")
{
{
const json j = {7, 4};
auto arr = j.get<std::array<NonDefaultConstructible, 2>>();
CHECK(arr[0].x == 7);
CHECK(arr[1].x == 4);
}
{
const json j = 7;
CHECK_THROWS_AS((j.get<std::array<NonDefaultConstructible, 1>>()), json::type_error);
}
}
SECTION("std::pair")
{
{
const json j = {3, 8};
auto p = j.get<std::pair<NonDefaultConstructible, NonDefaultConstructible>>();
CHECK(p.first.x == 3);
CHECK(p.second.x == 8);
}
{
const json j = {4, 1};
auto p = j.get<std::pair<int, NonDefaultConstructible>>();
CHECK(p.first == 4);
CHECK(p.second.x == 1);
}
{
const json j = {6, 7};
auto p = j.get<std::pair<NonDefaultConstructible, int>>();
CHECK(p.first.x == 6);
CHECK(p.second == 7);
}
{
const json j = 7;
CHECK_THROWS_AS((j.get<std::pair<NonDefaultConstructible, int>>()), json::type_error);
}
}
SECTION("std::tuple")
{
{
const json j = {9};
auto t = j.get<std::tuple<NonDefaultConstructible>>();
CHECK(std::get<0>(t).x == 9);
}
{
const json j = {9, 8, 7};
auto t = j.get<std::tuple<NonDefaultConstructible, int, NonDefaultConstructible>>();
CHECK(std::get<0>(t).x == 9);
CHECK(std::get<1>(t) == 8);
CHECK(std::get<2>(t).x == 7);
}
{
const json j = 7;
CHECK_THROWS_AS((j.get<std::tuple<NonDefaultConstructible>>()), json::type_error);
}
}
}
SECTION("issue #4530 - Serialization of empty tuple")
{
const auto source_tuple = std::tuple<>();
const nlohmann::json j = source_tuple;
CHECK(j.get<decltype(source_tuple)>() == source_tuple);
CHECK("[]" == j.dump());
}
SECTION("issue #2865 - ASAN detects memory leaks")
{
// the code below is expected to not leak memory
{
nlohmann::json o;
const std::string s = "bar";
nlohmann::to_json(o["foo"], s);
nlohmann::json p = o;
// call to_json with a non-null JSON value
nlohmann::to_json(p["foo"], s);
}
{
nlohmann::json o;
const std::string s = "bar";
nlohmann::to_json(o["foo"], s);
// call to_json with a non-null JSON value
nlohmann::to_json(o["foo"], s);
}
}
SECTION("issue #2824 - encoding of json::exception::what()")
{
json j;
sax_no_exception sax(j);
CHECK(!json::sax_parse("xyz", &sax));
CHECK(*sax_no_exception::error_string == "[json.exception.parse_error.101] parse error at line 1, column 1: syntax error while parsing value - invalid literal; last read: 'x'");
delete sax_no_exception::error_string; // NOLINT(cppcoreguidelines-owning-memory)
}
SECTION("issue #2825 - Properly constrain the basic_json conversion operator")
{
static_assert(std::is_copy_assignable<nlohmann::ordered_json>::value, "ordered_json must be copy assignable");
}
SECTION("issue #2958 - Inserting in unordered json using a pointer retains the leading slash")
{
const std::string p = "/root";
json test1;
test1[json::json_pointer(p)] = json::object();
CHECK(test1.dump() == "{\"root\":{}}");
ordered_json test2;
test2[ordered_json::json_pointer(p)] = json::object();
CHECK(test2.dump() == "{\"root\":{}}");
// json::json_pointer and ordered_json::json_pointer are the same type; behave as above
ordered_json test3;
test3[json::json_pointer(p)] = json::object();
CHECK(std::is_same<json::json_pointer::string_t, ordered_json::json_pointer::string_t>::value);
CHECK(test3.dump() == "{\"root\":{}}");
}
SECTION("issue #2982 - to_{binary format} does not provide a mechanism for specifying a custom allocator for the returned type")
{
std::vector<std::uint8_t, my_allocator<std::uint8_t>> my_vector;
const json j = {1, 2, 3, 4};
json::to_cbor(j, my_vector);
json k = json::from_cbor(my_vector);
CHECK(j == k);
}
}
TEST_CASE("regression test - parser callback must not lose a duplicate key's prior value")
{
// a callback that rejects only the scalar value 2
const json::parser_callback_t drop_value_2 = [](int /*depth*/, json::parse_event_t ev, json & v) noexcept
{
return !(ev == json::parse_event_t::value && v == 2);
};
SECTION("duplicate key, second (scalar) value rejected - prior value is restored")
{
const json j = json::parse(R"({"a":1,"a":2})", drop_value_2);
CHECK(j.dump() == "{\"a\":1}");
}
SECTION("duplicate key, second value is an object rejected at object_end - prior value is restored")
{
const json j = json::parse(R"({"a":1,"a":{"x":2}})",
[](int depth, json::parse_event_t ev, json& /*parsed*/) noexcept
{
return !(ev == json::parse_event_t::object_end && depth == 1);
});
CHECK(j.dump() == "{\"a\":1}");
}
SECTION("duplicate key, second value is an array rejected at array_end - prior value is restored")
{
const json j = json::parse(R"({"a":1,"a":[9,9]})",
[](int depth, json::parse_event_t ev, json& /*parsed*/) noexcept
{
return !(ev == json::parse_event_t::array_end && depth == 1);
});
CHECK(j.dump() == "{\"a\":1}");
}
SECTION("duplicate key, second value accepted (scalar) - last value wins")
{
const json j = json::parse(R"({"a":1,"a":2})", [](int, json::parse_event_t, json&) noexcept
{
return true;
});
CHECK(j.dump() == "{\"a\":2}");
}
SECTION("duplicate key, second value accepted (object) - last value wins")
{
const json j = json::parse(R"({"a":1,"a":{"x":2}})", [](int, json::parse_event_t, json&) noexcept
{
return true;
});
CHECK(j.dump() == "{\"a\":{\"x\":2}}");
}
SECTION("brand new (non-duplicate) key, value rejected - member is fully absent")
{
const json j = json::parse(R"({"a":1,"b":2})", drop_value_2);
CHECK(j.dump() == "{\"a\":1}");
}
SECTION("duplicate key nested two levels deep")
{
const json j = json::parse(R"({"outer":{"a":1,"a":2}})", drop_value_2);
CHECK(j.dump() == "{\"outer\":{\"a\":1}}");
}
SECTION("three occurrences of the same key - middle rejected, last accepted")
{
const json j = json::parse(R"({"k":1,"k":2,"k":3})", drop_value_2);
CHECK(j.dump() == "{\"k\":3}");
}
}
TEST_CASE("regression test - excessive binary container size honors allow_exceptions=false")
{
// CBOR array with declared length 2^63
const std::vector<std::uint8_t> cbor = {0x9b, 0x80, 0, 0, 0, 0, 0, 0, 0};
// CBOR map with declared length 2^63
const std::vector<std::uint8_t> cbor_m = {0xbb, 0x80, 0, 0, 0, 0, 0, 0, 0};
// UBJSON array with declared length 2^63-1
const std::vector<std::uint8_t> ubj = {'[', '#', 'L', 0x7f, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
// BJData array with declared length 2^63-1 (little endian)
const std::vector<std::uint8_t> bjd = {'[', '#', 'L', 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f};
// allow_exceptions=false must report failure instead of throwing/aborting
CHECK(json::from_cbor(cbor, true, false).is_discarded());
CHECK(json::from_cbor(cbor_m, true, false).is_discarded());
CHECK(json::from_ubjson(ubj, true, false).is_discarded());
CHECK(json::from_bjdata(bjd, true, false).is_discarded());
// allow_exceptions=true (the default) must still throw exactly as before.
// The exact message text is not checked here: on platforms where
// std::size_t is 32-bit, the CBOR reader's own length-narrowing check
// (get_cbor_container_size(), unrelated to this fix) intercepts a
// declared length of 2^63 before it ever reaches the check this test
// targets, with different (but equally valid, and already correct)
// wording -- see unit-cbor.cpp for coverage of that message.
json _;
CHECK_THROWS_AS(_ = json::from_cbor(cbor), json::out_of_range);
// regression guard: a genuinely truncated CBOR input must remain discarded
CHECK(json::from_cbor(std::vector<std::uint8_t> {0x9b, 0, 0, 0, 0, 0, 0, 0, 0x02}, true, false).is_discarded());
}
namespace
{
/// builds a value from SAX events, asks the parser to recover from its first
/// 100 errors, and checks that the events are balanced (see #3989)
class RecoveringParser : public nlohmann::detail::json_sax_dom_parser<json>
{
using base = nlohmann::detail::json_sax_dom_parser<json>;
public:
explicit RecoveringParser(json& j)
: base(j, false)
{}
bool null()
{
value();
return base::null();
}
bool boolean(bool val)
{
value();
return base::boolean(val);
}
bool number_integer(json::number_integer_t val)
{
value();
return base::number_integer(val);
}
bool number_unsigned(json::number_unsigned_t val)
{
value();
return base::number_unsigned(val);
}
bool number_float(json::number_float_t val, const std::string& s)
{
value();
return base::number_float(val, s);
}
bool string(std::string& val)
{
value();
return base::string(val);
}
bool binary(json::binary_t& val)
{
value();
return base::binary(val);
}
bool start_object(std::size_t elements)
{
value();
stack.push_back('o');
return base::start_object(elements);
}
bool key(std::string& val)
{
if (stack.empty() || stack.back() != 'o')
{
well_formed = false;
return false;
}
stack.back() = 'v';
return base::key(val);
}
bool end_object()
{
if (stack.empty() || stack.back() != 'o')
{
well_formed = false;
return false;
}
stack.pop_back();
return base::end_object();
}
bool start_array(std::size_t elements)
{
value();
stack.push_back('a');
return base::start_array(elements);
}
bool end_array()
{
if (stack.empty() || stack.back() != 'a')
{
well_formed = false;
return false;
}
stack.pop_back();
return base::end_array();
}
bool parse_error(std::size_t /*unused*/, const std::string& /*unused*/, const json::exception& /*unused*/)
{
// a limit, so that a reader that does not stop fails the test
// instead of making it hang
return ++errors < 100;
}
/// whether the events were balanced and every key was followed by a value
bool balanced() const
{
return well_formed && stack.empty();
}
std::size_t errors = 0;
std::vector<char> stack {}; // NOLINT(readability-redundant-member-init)
bool well_formed = true;
private:
void value()
{
if (!stack.empty())
{
if (stack.back() == 'v')
{
stack.back() = 'o';
}
else if (stack.back() == 'o')
{
well_formed = false;
}
}
}
};
struct BinaryParseResult
{
json value;
std::size_t errors;
bool ok;
bool balanced;
};
BinaryParseResult parse_binary_recovering(const std::vector<std::uint8_t>& input, const json::input_format_t format)
{
json j;
RecoveringParser sax(j);
const bool ok = json::sax_parse(input, &sax, format);
return {j, sax.errors, ok, sax.balanced()};
}
} // namespace
TEST_CASE("regression test - #3989 SAX parse_error() returning true")
{
SECTION("binary formats stop after an error and complete what was read")
{
const json j = {{"a", {1, -2, {{"b", "c"}}, json::array()}}, {"d", {{"e", nullptr}, {"f", true}}}, {"g", 1.5}, {"h", json::binary({1, 2, 3})}};
const std::vector<std::pair<json::input_format_t, std::vector<std::uint8_t>>> encodings =
{
{json::input_format_t::cbor, json::to_cbor(j)},
{json::input_format_t::msgpack, json::to_msgpack(j)},
{json::input_format_t::ubjson, json::to_ubjson(j)},
{json::input_format_t::ubjson, json::to_ubjson(j, true, true)},
{json::input_format_t::bjdata, json::to_bjdata(j)},
{json::input_format_t::bjdata, json::to_bjdata(j, true, true)},
{json::input_format_t::bson, json::to_bson(j)},
{json::input_format_t::bon8, json::to_bon8(j)},
};
for (const auto& encoding : encodings)
{
const auto format = encoding.first;
const auto& bytes = encoding.second;
CAPTURE(format);
// every prefix is truncated input
for (std::size_t length = 0; length < bytes.size(); ++length)
{
CAPTURE(length);
const auto result = parse_binary_recovering(std::vector<std::uint8_t>(bytes.begin(), bytes.begin() + static_cast<std::ptrdiff_t>(length)), format);
CHECK(!result.ok);
CHECK(result.errors == 1);
CHECK(result.balanced);
}
// the complete input is read as usual (binary values do not
// round-trip through every format, so compare with a plain parse)
json expected;
nlohmann::detail::json_sax_dom_parser<json> dom(expected);
CHECK(json::sax_parse(bytes, &dom, format));
const auto complete = parse_binary_recovering(bytes, format);
CHECK(complete.ok);
CHECK(complete.errors == 0);
CHECK(complete.value == expected);
// a byte after the value
auto trailing_bytes = bytes;
trailing_bytes.push_back(0x01);
const auto trailing = parse_binary_recovering(trailing_bytes, format);
CHECK(!trailing.ok);
CHECK(trailing.errors == 1);
CHECK(trailing.value == expected);
}
}
SECTION("containers without an end")
{
// these made the readers loop, or read on, after the error
const auto cbor_array = parse_binary_recovering({0x9F}, json::input_format_t::cbor);
CHECK(cbor_array.errors == 1);
CHECK(cbor_array.value == json::array());
const auto cbor_map = parse_binary_recovering({0xBF, 0x61, 'a'}, json::input_format_t::cbor);
CHECK(cbor_map.errors == 1);
CHECK(cbor_map.value == json({{"a", nullptr}}));
const auto msgpack_array = parse_binary_recovering({0xDD, 0xFF, 0xFF, 0xFF, 0xFF}, json::input_format_t::msgpack);
CHECK(msgpack_array.errors == 1);
CHECK(msgpack_array.value == json::array());
const auto msgpack_map = parse_binary_recovering({0x81, 0xA1, 'a', 0x92, 0x01}, json::input_format_t::msgpack);
CHECK(msgpack_map.errors == 1);
CHECK(msgpack_map.value == json({{"a", {1}}}));
}
SECTION("BJData ndarray")
{
// a 2x3 int8 array with two of its six elements; the annotated array
// format opens an object and two arrays of its own
const auto result = parse_binary_recovering({'[', '$', 'i', '#', '[', '$', 'i', '#', 'i', 2, 2, 3, 1, 2}, json::input_format_t::bjdata);
CHECK(result.errors == 1);
CHECK(result.balanced);
CHECK(result.value == json({{"_ArrayType_", "int8"}, {"_ArraySize_", {2, 3}}, {"_ArrayData_", {1, 2}}}));
}
SECTION("JSON text")
{
// the parser stopped, but reported success
json j;
RecoveringParser sax(j);
CHECK(!json::sax_parse("[1,2,3,]", &sax));
CHECK(sax.errors == 1);
CHECK(j == json({1, 2, 3}));
}
SECTION("the SAX parsers of the library stop")
{
json _;
CHECK(json::from_cbor(std::vector<std::uint8_t> {0x9F}, true, false).is_discarded());
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<std::uint8_t> {0x9F}), "[json.exception.parse_error.110] parse error at byte 2: syntax error while parsing CBOR value: unexpected end of input", json::parse_error&);
CHECK(json::parse("[1,2,3,]", nullptr, false).is_discarded());
CHECK(!json::accept("[1,2,3,]"));
}
}
DOCTEST_CLANG_SUPPRESS_WARNING_POP
Reference in New Issue View Git Blame Copy Permalink