Merge remote-tracking branch 'origin/develop' into HEAD

Resolves a conflict in tests/src/unit-diagnostics.cpp: develop's
swap(array_t&)/swap(object_t&) parent-pointer regression test and this
branch's copy-descent regression test both added a new SECTION at the
same place; kept both as siblings.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
This commit is contained in:
Niels Lohmann
2026-09-15 21:16:52 +02:00
47 changed files with 2817 additions and 331 deletions
+4 -1
View File
@@ -101,7 +101,10 @@ class exception : public std::exception
{
if (&element.second == current)
{
tokens.emplace_back(element.first.c_str());
// data() is null-terminated, so a key containing
// a null byte is cut short here rather than
// truncating the whole message at what()
tokens.emplace_back(element.first.data());
break;
}
}
+3 -1
View File
@@ -114,7 +114,9 @@ std::size_t hash(const BasicJsonType& j)
seed = combine(seed, static_cast<std::size_t>(j.get_binary().subtype()));
for (const auto byte : j.get_binary())
{
seed = combine(seed, std::hash<std::uint8_t> {}(byte));
// the cast is needed for binary types whose value type is not
// an integer (e.g., std::byte)
seed = combine(seed, std::hash<std::uint8_t> {}(static_cast<std::uint8_t>(byte)));
}
return seed;
}
@@ -3146,7 +3146,10 @@ class binary_reader
number_string,
out_of_range::create(406, concat("number overflow parsing '", number_string, '\''), nullptr));
}
return sax->number_float(parsed_float, std::move(number_string));
// number_string is a std::string, while the SAX interface takes a
// string_t; convert explicitly, as the two are only implicitly
// convertible for some string types
return sax->number_float(parsed_float, string_t(number_string.data(), number_string.size()));
}
case token_type::uninitialized:
case token_type::literal_true:
@@ -88,8 +88,13 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
iter_impl() = default;
~iter_impl() = default;
iter_impl(iter_impl&&) noexcept = default;
iter_impl& operator=(iter_impl&&) noexcept = default;
// the exception specification is left to be computed rather than declared:
// an array or object type whose iterator is not nothrow move constructible
// (std::deque's is not before libstdc++ 11) would make a declared noexcept
// differ from the implicit one, which deletes the function -- and is an
// error outright with older compilers
iter_impl(iter_impl&&) = default; // NOLINT(hicpp-noexcept-move,performance-noexcept-move-constructor,cppcoreguidelines-noexcept-move-operations)
iter_impl& operator=(iter_impl&&) = default; // NOLINT(hicpp-noexcept-move,performance-noexcept-move-constructor,cppcoreguidelines-noexcept-move-operations)
/*!
@brief constructor for a given JSON instance
+47 -8
View File
@@ -17,6 +17,7 @@
#endif // JSON_NO_IO
#include <limits> // max
#include <numeric> // accumulate
#include <set> // set
#include <string> // string
#include <utility> // move
#include <vector> // vector
@@ -71,7 +72,7 @@ class json_pointer
string_t{},
[](const string_t& a, const string_t& b)
{
return detail::concat(a, '/', detail::escape(b));
return detail::concat<string_t>(a, '/', detail::escape(b));
});
}
@@ -265,7 +266,7 @@ class json_pointer
JSON_THROW(detail::parse_error::create(109, 0, detail::concat("array index '", s, "' is not a number"), nullptr));
}
const char* p = s.c_str();
const char* p = s.data();
char* p_end = nullptr; // NOLINT(misc-const-correctness)
errno = 0; // strtoull doesn't reset errno
const unsigned long long res = std::strtoull(p, &p_end, 10); // NOLINT(runtime/int)
@@ -300,19 +301,35 @@ class json_pointer
}
private:
/*!
@brief the reference token sequences that denote arrays
@ref unflatten collects the pointer prefixes that have a reference token 0
among their children; @ref get_and_create creates arrays exactly below
those prefixes and objects everywhere else. Deciding this up front keeps
the result independent of the order in which the flattened object is
iterated, which is unspecified for some object types.
*/
using array_parents_t = std::set<std::vector<string_t>>;
/*!
@brief create and return a reference to the pointed to value
@complexity Linear in the number of reference tokens.
@throw parse_error.106 if an array index begins with '0'
@throw parse_error.109 if array index is not a number
@throw type_error.313 if value cannot be unflattened
*/
template<typename BasicJsonType>
BasicJsonType& get_and_create(BasicJsonType& j) const
BasicJsonType& get_and_create(BasicJsonType& j, const array_parents_t& array_parents) const
{
auto* result = &j;
// the reference tokens that have been consumed so far; used to look up
// whether the value to be created below is an array or an object
std::vector<string_t> prefix;
// in case no reference tokens exist, return a reference to the JSON value
// j which will be overwritten by a primitive value
for (const auto& reference_token : reference_tokens)
@@ -321,10 +338,11 @@ class json_pointer
{
case detail::value_t::null:
{
if (reference_token == "0")
if (array_parents.find(prefix) != array_parents.end())
{
// start a new array if the reference token is 0
result = &result->operator[](0);
// some reference token below this position is 0, so the
// value is an array
result = &result->operator[](array_index<BasicJsonType>(reference_token));
}
else
{
@@ -364,6 +382,8 @@ class json_pointer
default:
JSON_THROW(detail::type_error::create(313, "invalid value to unflatten", &j));
}
prefix.push_back(reference_token);
}
return *result;
@@ -837,7 +857,8 @@ class json_pointer
{
// use the text between the beginning of the reference token
// (start) and the last slash (slash).
auto reference_token = reference_string.substr(start, slash - start);
const auto count = (slash == string_t::npos ? reference_string.size() : slash) - start;
auto reference_token = string_t(reference_string.data() + start, count);
// check reference tokens are properly escaped
for (std::size_t pos = reference_token.find_first_of('~');
@@ -953,6 +974,24 @@ class json_pointer
BasicJsonType result;
// collect the pointer prefixes that have a reference token 0 among
// their children; the values below them are arrays, all others are
// objects (see array_parents_t)
array_parents_t array_parents;
for (const auto& element : *value.m_data.m_value.object)
{
json_pointer ptr(element.first);
std::vector<string_t> prefix;
for (auto& reference_token : ptr.reference_tokens)
{
if (reference_token == "0")
{
array_parents.insert(prefix);
}
prefix.push_back(std::move(reference_token));
}
}
// iterate the JSON object values
for (const auto& element : *value.m_data.m_value.object)
{
@@ -965,7 +1004,7 @@ class json_pointer
// that if the JSON pointer is "" (i.e., points to the whole value),
// function get_and_create returns a reference to the result itself.
// An assignment will then create a primitive value.
json_pointer(element.first).get_and_create(result) = element.second;
json_pointer(element.first).get_and_create(result, array_parents) = element.second;
}
return result;
+23 -6
View File
@@ -172,17 +172,18 @@ struct has_to_json < BasicJsonType, T, enable_if_t < !is_basic_json<T>::value >>
template<typename T>
using detect_key_compare = typename T::key_compare;
template<typename T>
struct has_key_compare : std::integral_constant<bool, is_detected<detect_key_compare, T>::value> {};
// obtains the actual object key comparator
// obtains the actual object key comparator: object_t::key_compare if the
// object type defines it, and default_object_comparator_t otherwise
//
// note detected_or_t is used rather than std::conditional, because the latter
// names both of its type arguments eagerly; object_t::key_compare would then
// be a hard error for an object type that does not define it
template<typename BasicJsonType>
struct actual_object_comparator
{
using object_t = typename BasicJsonType::object_t;
using object_comparator_t = typename BasicJsonType::default_object_comparator_t;
using type = typename std::conditional < has_key_compare<object_t>::value,
typename object_t::key_compare, object_comparator_t>::type;
using type = detected_or_t<object_comparator_t, detect_key_compare, object_t>;
};
template<typename BasicJsonType>
@@ -778,6 +779,22 @@ using has_erase_with_key_type = typename std::conditional <
std::true_type,
std::false_type >::type;
template<typename ObjectType, typename IteratorType>
using detect_erase_with_iterator = decltype(std::declval<ObjectType&>().erase(std::declval<IteratorType>()));
// type trait to check if erase(iterator) returns void instead of the following
// iterator, as the object types that do not compute a successor the caller may
// not need do
template<typename ObjectType, typename IteratorType>
using erase_returns_void = is_detected_exact<void, detect_erase_with_iterator, ObjectType, IteratorType>;
template<typename T>
using detect_capacity = decltype(std::declval<const T&>().capacity());
// type trait to check if a type has a capacity() member function
template<typename T>
struct has_capacity : std::integral_constant<bool, is_detected<detect_capacity, T>::value> {};
// a naive helper to check if a type is an ordered_map (exploits the fact that
// ordered_map inherits capacity() from std::vector)
template <typename T>
@@ -261,7 +261,7 @@ class binary_writer
// step 2: write the string
oa->write_characters(
reinterpret_cast<const CharType*>(j.m_data.m_value.string->c_str()),
reinterpret_cast<const CharType*>(j.m_data.m_value.string->data()),
j.m_data.m_value.string->size());
break;
}
@@ -581,7 +581,7 @@ class binary_writer
// step 2: write the string
oa->write_characters(
reinterpret_cast<const CharType*>(j.m_data.m_value.string->c_str()),
reinterpret_cast<const CharType*>(j.m_data.m_value.string->data()),
j.m_data.m_value.string->size());
break;
}
@@ -798,7 +798,7 @@ class binary_writer
}
write_number_with_ubjson_prefix(j.m_data.m_value.string->size(), true, use_bjdata);
oa->write_characters(
reinterpret_cast<const CharType*>(j.m_data.m_value.string->c_str()),
reinterpret_cast<const CharType*>(j.m_data.m_value.string->data()),
j.m_data.m_value.string->size());
break;
}
@@ -897,7 +897,9 @@ class binary_writer
for (size_t i = 0; i < j.m_data.m_value.binary->size(); ++i)
{
oa->write_character(to_char_type(bjdata_draft3 ? 'B' : 'U'));
oa->write_character(to_char_type(j.m_data.m_value.binary->data()[i]));
// the cast is needed for binary types whose value type
// is not an integer (e.g., std::byte)
oa->write_character(to_char_type(static_cast<std::uint8_t>(j.m_data.m_value.binary->data()[i])));
}
}
@@ -958,7 +960,7 @@ class binary_writer
{
write_number_with_ubjson_prefix(el.first.size(), true, use_bjdata);
oa->write_characters(
reinterpret_cast<const CharType*>(el.first.c_str()),
reinterpret_cast<const CharType*>(el.first.data()),
el.first.size());
write_ubjson(el.second, use_count, use_type, prefix_required, use_bjdata, bjdata_version);
}
@@ -1021,8 +1023,11 @@ class binary_writer
{
oa->write_character(to_char_type(element_type));
oa->write_characters(
reinterpret_cast<const CharType*>(name.c_str()),
name.size() + 1u);
reinterpret_cast<const CharType*>(name.data()),
name.size());
// the terminating null byte is written explicitly rather than taken
// from the buffer, so that string_t::data() need not be null-terminated
oa->write_character(to_char_type(0x00));
}
/*!
@@ -1063,8 +1068,11 @@ class binary_writer
write_number<std::int32_t>(to_bson_length(value.size() + 1ul), true);
oa->write_characters(
reinterpret_cast<const CharType*>(value.c_str()),
value.size() + 1);
reinterpret_cast<const CharType*>(value.data()),
value.size());
// the terminating null byte is written explicitly rather than taken
// from the buffer, so that string_t::data() need not be null-terminated
oa->write_character(to_char_type(0x00));
}
/*!
@@ -1155,7 +1163,11 @@ class binary_writer
const std::size_t embedded_document_size = std::accumulate(std::begin(value), std::end(value), static_cast<std::size_t>(0), [&array_index](std::size_t result, const typename BasicJsonType::array_t::value_type & el)
{
return result + calc_bson_element_size(std::to_string(array_index++), el);
// the index is built as a std::string, while calc_bson_element_size
// takes a string_t; convert explicitly, as the two are only
// implicitly convertible for some string types
const auto key = std::to_string(array_index++);
return result + calc_bson_element_size(string_t(key.data(), key.size()), el);
});
return sizeof(std::int32_t) + embedded_document_size + 1ul;
@@ -1182,7 +1194,11 @@ class binary_writer
for (const auto& el : value)
{
write_bson_element(std::to_string(array_index++), el);
// the index is built as a std::string, while write_bson_element takes
// a string_t; convert explicitly, as the two are only implicitly
// convertible for some string types
const auto key = std::to_string(array_index++);
write_bson_element(string_t(key.data(), key.size()), el);
}
oa->write_character(to_char_type(0x00));
+20 -6
View File
@@ -1061,7 +1061,7 @@ class serializer
{
case error_handler_t::strict:
{
JSON_THROW(type_error::create(316, concat("incomplete UTF-8 string; last byte: 0x", hex_bytes(static_cast<std::uint8_t>(s.back() | 0))), nullptr));
JSON_THROW(type_error::create(316, concat("incomplete UTF-8 string; last byte: 0x", hex_bytes(static_cast<std::uint8_t>(s[s.size() - 1] | 0))), nullptr));
}
case error_handler_t::ignore:
@@ -1322,6 +1322,19 @@ class serializer
pos += 6;
}
/*!
@brief convert a single element of a binary value to its byte value
The elements of a binary value are dumped as the numbers 0..255, regardless
of the value type of the configured BinaryType: that type may be signed
(`char`), unsigned (`std::uint8_t`), or not an integer at all
(`std::byte`), none of which @ref dump_integer can handle uniformly.
*/
static std::uint8_t to_byte_value(binary_char_t x) noexcept
{
return static_cast<std::uint8_t>(x);
}
// templates to avoid warnings about useless casts
template <typename NumberType, enable_if_t<std::is_signed<NumberType>::value, int> = 0>
bool is_negative_number(NumberType x)
@@ -1343,8 +1356,10 @@ class serializer
an arbitrary number, and the three digits it takes at most are written
straight into the write buffer.
Any byte type that is not a plain unsigned byte is left to @ref dump_integer,
whose representation of it may differ.
Any byte type that is not a plain unsigned byte is converted to its
@ref to_byte_value "byte value" and left to @ref dump_integer, so a signed
or non-integral BinaryType::value_type (`char`, `std::byte`, ...) still
dumps as 0..255.
*/
template<typename ByteType>
void dump_byte(const ByteType value)
@@ -1357,7 +1372,7 @@ class serializer
template<typename ByteType>
void dump_byte(const ByteType value, std::false_type /*is_plain_byte*/)
{
dump_integer(value);
dump_integer(to_byte_value(value));
}
template<typename ByteType>
@@ -1403,8 +1418,7 @@ class serializer
template < typename NumberType, detail::enable_if_t <
std::is_integral<NumberType>::value ||
std::is_same<NumberType, number_unsigned_t>::value ||
std::is_same<NumberType, number_integer_t>::value ||
std::is_same<NumberType, binary_char_t>::value,
std::is_same<NumberType, number_integer_t>::value,
int > = 0 >
void dump_integer(NumberType x)
{
+68 -31
View File
@@ -8,50 +8,56 @@
#pragma once
#include <cstddef> // size_t
#include <nlohmann/detail/abi_macros.hpp>
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
/*!
@brief replace all occurrences of a substring by another string
@param[in,out] s the string to manipulate; changed so that all
occurrences of @a f are replaced with @a t
@param[in] f the substring to replace with @a t
@param[in] t the string to replace @a f
@pre The search string @a f must not be empty. **This precondition is
enforced with an assertion.**
@since version 2.0.0
*/
template<typename StringType>
inline void replace_substring(StringType& s, const StringType& f,
const StringType& t)
{
JSON_ASSERT(!f.empty());
for (auto pos = s.find(f); // find the first occurrence of f
pos != StringType::npos; // make sure f was found
s.replace(pos, f.size(), t), // replace with t, and
pos = s.find(f, pos + t.size())) // find the next occurrence of f
{}
}
/*!
* @brief string escaping as described in RFC 6901 (Sect. 4)
* @param[in] s string to escape
* @return escaped string
*
* Note the order of escaping "~" to "~0" and "/" to "~1" is important.
*
* The string is rebuilt in a single pass, appending whole runs between the
* characters that need escaping. Scanning with find_first_of() keeps the
* common case -- nothing to escape -- as fast as a single search, while
* repeated replace() calls would move the tail of the string once per
* escaped character.
*/
template<typename StringType>
inline StringType escape(StringType s)
inline StringType escape(const StringType& s)
{
replace_substring(s, StringType{"~"}, StringType{"~0"});
replace_substring(s, StringType{"/"}, StringType{"~1"});
return s;
auto next_special = [&s](std::size_t from)
{
const auto tilde = s.find_first_of('~', from);
const auto slash = s.find_first_of('/', from);
return tilde < slash ? tilde : slash; // npos is the largest value
};
auto pos = next_special(0);
if (pos == StringType::npos)
{
return s;
}
StringType result;
result.reserve(s.size() + 2);
std::size_t run = 0;
while (pos != StringType::npos)
{
result.append(s.data() + run, pos - run);
result.append(s[pos] == '~' ? "~0" : "~1", 2);
run = pos + 1;
pos = next_special(run);
}
result.append(s.data() + run, s.size() - run);
return result;
}
/*!
@@ -60,12 +66,43 @@ inline StringType escape(StringType s)
* @return unescaped string
*
* Note the order of escaping "~1" to "/" and "~0" to "~" is important.
*
* Rebuilt in a single pass, see @ref escape. A "~" that is followed by
* neither "0" nor "1" is passed through unchanged; @ref json_pointer rejects
* such input before it gets here.
*/
template<typename StringType>
inline void unescape(StringType& s)
{
replace_substring(s, StringType{"~1"}, StringType{"/"});
replace_substring(s, StringType{"~0"}, StringType{"~"});
auto pos = s.find_first_of('~', 0);
if (pos == StringType::npos)
{
return;
}
StringType result;
result.reserve(s.size());
std::size_t run = 0;
while (pos != StringType::npos)
{
result.append(s.data() + run, pos - run);
const auto next = pos + 1;
if (next < s.size() && (s[next] == '0' || s[next] == '1'))
{
result.append(s[next] == '0' ? "~" : "/", 1);
run = pos + 2;
}
else
{
result.append("~", 1);
run = pos + 1;
}
pos = s.find_first_of('~', run);
}
result.append(s.data() + run, s.size() - run);
s = result;
}
} // namespace detail