Compare commits

..
Author SHA1 Message Date
Niels Lohmann 3f6a037b9c Flatten deeply nested values without recursing per nesting level
json_pointer::flatten() called itself once per nesting level, so
flatten() on a value nested deeply enough exhausted the call stack.
#5547 and #5548 fixed merge_patch() and diff() from #5393, but flatten()
was left out.

flatten() now walks the value with an explicit stack and keeps the path
in one buffer that grows and shrinks with it. It has a single code path
and no depth limit: the old version built a new path string per child,
so the iterative one is no slower on shallow values and much faster on
deep ones. The output, including the order of an ordered_json result,
is unchanged.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-10-09 09:16:55 +02:00
10 changed files with 420 additions and 111 deletions
+12 -1
View File
@@ -64,7 +64,18 @@ values of that type directly to a `basic_json` instance, and they will automatic
rather than arrays:
```cpp
using custom_json = nlohmann::ordered_json::with_binary_t<std::vector<std::byte>>;
using custom_json = nlohmann::basic_json<
nlohmann::ordered_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,
std::vector<std::byte> // Custom BinaryType
>;
std::vector<std::byte> data{std::byte{1}, std::byte{2}, std::byte{3}};
custom_json j = data; // Creates a binary value, not an array
+13 -1
View File
@@ -15,7 +15,19 @@ class base_class_with_hidden_members
}
};
using json = nlohmann::json::with_base_class_t<base_class_with_hidden_members>;
using json = nlohmann::basic_json <
std::map,
std::vector,
std::string,
bool,
std::int64_t,
std::uint64_t,
double,
std::allocator,
nlohmann::adl_serializer,
std::vector<std::uint8_t>,
base_class_with_hidden_members
>;
int main()
{
+111 -48
View File
@@ -878,64 +878,127 @@ class json_pointer
@param[in,out] result the result object to insert values to
@note Empty objects or arrays are flattened to `null`.
The value is walked with an explicit stack rather than the call stack, so
arbitrarily deeply nested values can be flattened.
@sa https://github.com/nlohmann/json/issues/5393
*/
template<typename BasicJsonType>
static void flatten(const string_t& reference_string,
const BasicJsonType& value,
BasicJsonType& result)
{
switch (value.type())
using object_const_iterator = typename BasicJsonType::object_t::const_iterator;
// an array or object being walked: the container, the array index or
// object iterator of the next child, and the length of the path of the
// container itself
struct frame
{
case detail::value_t::array:
{
if (value.m_data.m_value.array->empty())
{
// flatten empty array as null
result[reference_string] = nullptr;
}
else
{
// iterate array and use index as a reference string
for (std::size_t i = 0; i < value.m_data.m_value.array->size(); ++i)
{
flatten(detail::concat<string_t>(reference_string, '/', std::to_string(i)),
value.m_data.m_value.array->operator[](i), result);
}
}
break;
}
const BasicJsonType* container;
std::size_t index;
object_const_iterator member;
std::size_t path_length;
};
case detail::value_t::object:
{
if (value.m_data.m_value.object->empty())
{
// flatten empty object as null
result[reference_string] = nullptr;
}
else
{
// iterate object and use keys as reference string
for (const auto& element : *value.m_data.m_value.object)
{
flatten(detail::concat<string_t>(reference_string, '/', detail::escape(element.first)), element.second, result);
}
}
break;
}
// The containers being flattened are kept on an explicit stack, and
// every child is flattened completely before the next one, so the
// entries come out in the same order as with a recursive walk. The
// path of the value being flattened is kept in one buffer that grows
// and shrinks with the stack, rather than in a new string per level.
std::vector<frame> stack;
string_t path = reference_string;
case detail::value_t::null:
case detail::value_t::string:
case detail::value_t::boolean:
case detail::value_t::number_integer:
case detail::value_t::number_unsigned:
case detail::value_t::number_float:
case detail::value_t::binary:
case detail::value_t::discarded:
default:
// flatten `v`, whose path is `path`: primitives and empty containers
// are added to the result right away; other containers get a frame
const auto enter = [&stack, &path, &result](const BasicJsonType & v)
{
switch (v.type())
{
// add a primitive value with its reference string
result[reference_string] = value;
break;
case detail::value_t::array:
{
if (v.m_data.m_value.array->empty())
{
// flatten empty array as null
result[path] = nullptr;
}
else
{
stack.push_back({&v, 0, object_const_iterator(), path.size()});
}
return;
}
case detail::value_t::object:
{
if (v.m_data.m_value.object->empty())
{
// flatten empty object as null
result[path] = nullptr;
}
else
{
stack.push_back({&v, 0, v.m_data.m_value.object->begin(), path.size()});
}
return;
}
case detail::value_t::null:
case detail::value_t::string:
case detail::value_t::boolean:
case detail::value_t::number_integer:
case detail::value_t::number_unsigned:
case detail::value_t::number_float:
case detail::value_t::binary:
case detail::value_t::discarded:
default:
{
// add a primitive value with its reference string
result[path] = v;
return;
}
}
};
enter(value);
while (!stack.empty())
{
// the frame is changed through stack.back(): enter() may push a
// frame, which would invalidate a reference to it
const BasicJsonType* const container = stack.back().container;
// drop the path of the previous child
path.resize(stack.back().path_length);
if (container->is_array())
{
const auto& array = *container->m_data.m_value.array;
const std::size_t i = stack.back().index;
if (i == array.size())
{
stack.pop_back();
continue;
}
// iterate array and use index as a reference string
++stack.back().index;
detail::concat_into(path, '/', detail::to_string<string_t>(i));
enter(array[i]);
}
else
{
const object_const_iterator it = stack.back().member;
if (it == container->m_data.m_value.object->end())
{
stack.pop_back();
continue;
}
// iterate object and use keys as reference string
++stack.back().member;
detail::concat_into(path, '/', detail::escape(it->first));
enter(it->second);
}
}
}
+111 -48
View File
@@ -20796,64 +20796,127 @@ class json_pointer
@param[in,out] result the result object to insert values to
@note Empty objects or arrays are flattened to `null`.
The value is walked with an explicit stack rather than the call stack, so
arbitrarily deeply nested values can be flattened.
@sa https://github.com/nlohmann/json/issues/5393
*/
template<typename BasicJsonType>
static void flatten(const string_t& reference_string,
const BasicJsonType& value,
BasicJsonType& result)
{
switch (value.type())
using object_const_iterator = typename BasicJsonType::object_t::const_iterator;
// an array or object being walked: the container, the array index or
// object iterator of the next child, and the length of the path of the
// container itself
struct frame
{
case detail::value_t::array:
{
if (value.m_data.m_value.array->empty())
{
// flatten empty array as null
result[reference_string] = nullptr;
}
else
{
// iterate array and use index as a reference string
for (std::size_t i = 0; i < value.m_data.m_value.array->size(); ++i)
{
flatten(detail::concat<string_t>(reference_string, '/', std::to_string(i)),
value.m_data.m_value.array->operator[](i), result);
}
}
break;
}
const BasicJsonType* container;
std::size_t index;
object_const_iterator member;
std::size_t path_length;
};
case detail::value_t::object:
{
if (value.m_data.m_value.object->empty())
{
// flatten empty object as null
result[reference_string] = nullptr;
}
else
{
// iterate object and use keys as reference string
for (const auto& element : *value.m_data.m_value.object)
{
flatten(detail::concat<string_t>(reference_string, '/', detail::escape(element.first)), element.second, result);
}
}
break;
}
// The containers being flattened are kept on an explicit stack, and
// every child is flattened completely before the next one, so the
// entries come out in the same order as with a recursive walk. The
// path of the value being flattened is kept in one buffer that grows
// and shrinks with the stack, rather than in a new string per level.
std::vector<frame> stack;
string_t path = reference_string;
case detail::value_t::null:
case detail::value_t::string:
case detail::value_t::boolean:
case detail::value_t::number_integer:
case detail::value_t::number_unsigned:
case detail::value_t::number_float:
case detail::value_t::binary:
case detail::value_t::discarded:
default:
// flatten `v`, whose path is `path`: primitives and empty containers
// are added to the result right away; other containers get a frame
const auto enter = [&stack, &path, &result](const BasicJsonType & v)
{
switch (v.type())
{
// add a primitive value with its reference string
result[reference_string] = value;
break;
case detail::value_t::array:
{
if (v.m_data.m_value.array->empty())
{
// flatten empty array as null
result[path] = nullptr;
}
else
{
stack.push_back({&v, 0, object_const_iterator(), path.size()});
}
return;
}
case detail::value_t::object:
{
if (v.m_data.m_value.object->empty())
{
// flatten empty object as null
result[path] = nullptr;
}
else
{
stack.push_back({&v, 0, v.m_data.m_value.object->begin(), path.size()});
}
return;
}
case detail::value_t::null:
case detail::value_t::string:
case detail::value_t::boolean:
case detail::value_t::number_integer:
case detail::value_t::number_unsigned:
case detail::value_t::number_float:
case detail::value_t::binary:
case detail::value_t::discarded:
default:
{
// add a primitive value with its reference string
result[path] = v;
return;
}
}
};
enter(value);
while (!stack.empty())
{
// the frame is changed through stack.back(): enter() may push a
// frame, which would invalidate a reference to it
const BasicJsonType* const container = stack.back().container;
// drop the path of the previous child
path.resize(stack.back().path_length);
if (container->is_array())
{
const auto& array = *container->m_data.m_value.array;
const std::size_t i = stack.back().index;
if (i == array.size())
{
stack.pop_back();
continue;
}
// iterate array and use index as a reference string
++stack.back().index;
detail::concat_into(path, '/', detail::to_string<string_t>(i));
enter(array[i]);
}
else
{
const object_const_iterator it = stack.back().member;
if (it == container->m_data.m_value.object->end())
{
stack.pop_back();
continue;
}
// iterate object and use keys as reference string
++stack.back().member;
detail::concat_into(path, '/', detail::escape(it->first));
enter(it->second);
}
}
}
+6 -2
View File
@@ -46,7 +46,9 @@ class huge_binary_t : public std::vector<std::uint8_t>
}
};
using huge_binary_json = nlohmann::json::with_binary_t<huge_binary_t>;
using huge_binary_json = nlohmann::basic_json <
std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t,
double, std::allocator, nlohmann::adl_serializer, huge_binary_t, void >;
// a string type that can be made to report a size beyond INT32_MAX without
// allocating that much memory, so BSON length overflow can be tested for
@@ -94,7 +96,9 @@ class huge_string_t : public std::string
bool pretend_huge = false;
};
using huge_string_json = nlohmann::json::with_string_t<huge_string_t>;
using huge_string_json = nlohmann::basic_json <
std::map, std::vector, huge_string_t, bool, std::int64_t, std::uint64_t,
double, std::allocator, nlohmann::adl_serializer, std::vector<std::uint8_t>, void >;
} // namespace
TEST_CASE("BSON")
+27 -2
View File
@@ -400,7 +400,20 @@ class base_class_with_hidden_members
std::size_t m_size = 42;
};
using json_with_hidden_base_members = nlohmann::json::with_base_class_t<base_class_with_hidden_members>;
using json_with_hidden_base_members =
nlohmann::basic_json <
std::map,
std::vector,
std::string,
bool,
std::int64_t,
std::uint64_t,
double,
std::allocator,
nlohmann::adl_serializer,
std::vector<std::uint8_t>,
base_class_with_hidden_members
>;
TEST_CASE("JSON Node as_base_class")
{
@@ -446,7 +459,19 @@ struct const_member_base
const int id = 7; // NOLINT(misc-non-private-member-variables-in-classes)
};
using json_with_const_base = nlohmann::json::with_base_class_t<const_member_base>;
using json_with_const_base = nlohmann::basic_json <
std::map,
std::vector,
std::string,
bool,
std::int64_t,
std::uint64_t,
double,
std::allocator,
nlohmann::adl_serializer,
std::vector<std::uint8_t>,
const_member_base
>;
// build an array nested @a depth levels deep, with the innermost value 1;
// every level is constructed (never assigned), since const_member_base does
+6 -2
View File
@@ -26,11 +26,15 @@ namespace
// a BinaryType whose value type is signed: the elements must still be
// processed as the numbers 0..255
using char_binary_json = nlohmann::json::with_binary_t<std::vector<char>>;
using char_binary_json = nlohmann::basic_json <
std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t,
double, std::allocator, nlohmann::adl_serializer, std::vector<char>, void >;
#ifdef JSON_HAS_CPP_17
// a BinaryType whose value type is not an integer type at all
using byte_binary_json = nlohmann::json::with_binary_t<std::vector<std::byte>>;
using byte_binary_json = nlohmann::basic_json <
std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t,
double, std::allocator, nlohmann::adl_serializer, std::vector<std::byte>, void >;
#endif
} // namespace
+78
View File
@@ -939,3 +939,81 @@ TEST_CASE("unescaping keeps a '~' that does not start an escape sequence")
nlohmann::detail::unescape(s);
CHECK(s == "~/~");
}
TEST_CASE("flatten of structured values")
{
SECTION("values nested too deeply for the call stack (#5393)")
{
// flatten() used to recurse once per nesting level
const std::size_t depth = 100000;
for (const bool objects :
{
false, true
})
{
CAPTURE(objects)
std::string text;
std::string path;
for (std::size_t i = 0; i < depth; ++i)
{
text += objects ? "{\"a\":" : "[";
path += objects ? "/a" : "/0";
}
text += "0";
text += std::string(depth, objects ? '}' : ']');
const auto value = json::parse(text);
const auto flat = value.flatten();
REQUIRE(flat.size() == 1);
REQUIRE(flat.begin().key().size() == path.size());
CHECK(flat.begin().key() == path);
CHECK(flat.begin().value() == 0);
// unflatten() is not iterative: it takes time and memory
// quadratic in the depth, so it is only roundtripped for a
// moderate depth
std::string small_text;
for (std::size_t i = 0; i < 500; ++i)
{
small_text += objects ? "{\"a\":" : "[";
}
small_text += "0";
small_text += std::string(500, objects ? '}' : ']');
const auto small_value = json::parse(small_text);
CHECK(small_value.flatten().unflatten() == small_value);
}
}
SECTION("objects and arrays interleaved")
{
const json value =
{
{"a", {1, {{"b", json::array()}, {"c", json::object()}}, json::array({{{"x~/", {true, nullptr}}}})}},
{"a/b", {{"~", 1}}},
{"z", "s"}
};
const json expected =
{
{"/a/0", 1},
{"/a/1/b", nullptr},
{"/a/1/c", nullptr},
{"/a/2/0/x~0~1/0", true},
{"/a/2/0/x~0~1/1", nullptr},
{"/a~1b/~0", 1},
{"/z", "s"}
};
CHECK(value.flatten() == expected);
}
SECTION("order of the entries of an ordered_json")
{
const auto value = nlohmann::ordered_json::parse(
R"({"z":"s","a/b":{"~":1,"k":[]},"a":[1,{"c":{},"b":[]},[{"x~/":[true,null],"w":2}]]})");
const auto flat = value.flatten();
CHECK(flat.dump() ==
R"({"/z":"s","/a~1b/~0":1,"/a~1b/k":null,"/a/0":1,"/a/1/c":null,"/a/1/b":null,"/a/2/0/x~0~1/0":true,"/a/2/0/x~0~1/1":null,"/a/2/0/w":2})");
}
}
+46 -6
View File
@@ -2201,7 +2201,10 @@ struct huge_array : std::vector<T, A>
}
};
using huge_array_json = nlohmann::json::with_array_t<huge_array>;
using huge_array_json = nlohmann::basic_json <
std::map, huge_array, std::string, bool, std::int64_t, std::uint64_t,
double, std::allocator, nlohmann::adl_serializer,
std::vector<std::uint8_t>, void >;
TEST_CASE("MessagePack Size above uint32 for array")
{
@@ -2246,7 +2249,18 @@ template<typename K, typename V,
}
};
using huge_object_json = nlohmann::json::with_object_t<huge_map>;
using huge_object_json = nlohmann::basic_json <
huge_map,
std::vector,
std::string,
bool,
std::int64_t,
std::uint64_t,
double,
std::allocator,
nlohmann::adl_serializer,
std::vector<std::uint8_t>,
void >;
TEST_CASE("MessagePack Size above uint32 for object")
{
@@ -2281,7 +2295,18 @@ struct huge_string : std::string
}
};
using huge_string_json = nlohmann::json::with_string_t<huge_string>;
using huge_string_json = nlohmann::basic_json <
std::map,
std::vector,
huge_string,
bool,
std::int64_t,
std::uint64_t,
double,
std::allocator,
nlohmann::adl_serializer,
std::vector<std::uint8_t>,
void >;
TEST_CASE("MessagePack Size above uint32 for string")
{
@@ -2304,7 +2329,18 @@ struct huge_binary : std::vector<std::uint8_t>
}
};
using huge_binary_json = nlohmann::json::with_binary_t<huge_binary>;
using huge_binary_json = nlohmann::basic_json <
std::map,
std::vector,
std::string,
bool,
std::int64_t,
std::uint64_t,
double,
std::allocator,
nlohmann::adl_serializer,
huge_binary,
void >;
TEST_CASE("MessagePack Size above uint32 for binary")
{
@@ -2354,10 +2390,14 @@ class beyond_uint32_string_t : public std::string
}
};
using beyond_uint32_string_json = nlohmann::json::with_string_t<beyond_uint32_string_t>;
using beyond_uint32_string_json = nlohmann::basic_json <
std::map, std::vector, beyond_uint32_string_t, bool, std::int64_t, std::uint64_t,
double, std::allocator, nlohmann::adl_serializer, std::vector<std::uint8_t>, void >;
#endif
using beyond_uint32_binary_json = nlohmann::json::with_binary_t<beyond_uint32_binary_t>;
using beyond_uint32_binary_json = nlohmann::basic_json <
std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t,
double, std::allocator, nlohmann::adl_serializer, beyond_uint32_binary_t, void >;
} // namespace
TEST_CASE("MessagePack lengths beyond UINT32_MAX cannot be serialized")
+10 -1
View File
@@ -217,7 +217,16 @@ void int_to_string(alt_string& target, std::size_t value)
target = std::to_string(value).c_str();
}
using alt_json = nlohmann::json::with_string_t<alt_string>;
using alt_json = nlohmann::basic_json <
std::map,
std::vector,
alt_string,
bool,
std::int64_t,
std::uint64_t,
double,
std::allocator,
nlohmann::adl_serializer >;
bool operator<(const char* op1, const alt_string& op2) noexcept
{