Merge branch 'develop' into claude/binary-utf8-roundtrip-5651

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
This commit is contained in:
Niels Lohmann committed 2026-10-01 07:44:29 +02:00
commit f3e30fa5b7
295 files changed
+5316 -15043

No files matched your search

File diff suppressed because it is too large. Load diff
@@ -8,11 +8,10 @@
#pragma once
#include <algorithm> // copy
#include <cstddef> // size_t
#include <iterator> // back_inserter
#include <memory> // shared_ptr, make_shared
#include <string> // basic_string
#include <type_traits> // conditional, integral_constant, is_same
#include <utility> // move
#include <vector> // vector
@@ -31,6 +30,10 @@ namespace detail
template<typename CharType> struct output_adapter_protocol
{
virtual void write_character(CharType c) = 0;
/// @param[in] s pointer to the characters to write; binary_writer legitimately
/// passes a null pointer together with length 0 for an empty
/// string or binary value, so implementations must tolerate that
/// @param[in] length number of characters at @a s
virtual void write_characters(const CharType* s, std::size_t length) = 0;
virtual ~output_adapter_protocol() = default;
@@ -97,7 +100,6 @@ class output_vector_adapter : public output_adapter_protocol<CharType>
sink.write_character(c);
}
JSON_HEDLEY_NON_NULL(2)
void write_characters(const CharType* s, std::size_t length) override
{
sink.write_characters(s, length);
@@ -117,12 +119,13 @@ class output_stream_adapter : public output_adapter_protocol<CharType>
: stream(s)
{}
// NOLINTNEXTLINE(portability-template-virtual-member-function)
void write_character(CharType c) override
{
stream.put(c);
}
JSON_HEDLEY_NON_NULL(2)
// NOLINTNEXTLINE(portability-template-virtual-member-function)
void write_characters(const CharType* s, std::size_t length) override
{
stream.write(s, static_cast<std::streamsize>(length));
@@ -147,7 +150,6 @@ class output_string_adapter : public output_adapter_protocol<CharType>
str.push_back(c);
}
JSON_HEDLEY_NON_NULL(2)
void write_characters(const CharType* s, std::size_t length) override
{
str.append(s, length);
@@ -190,7 +192,82 @@ class output_adapter_sink
output_adapter_t<CharType> oa;
};
template<typename CharType, typename StringType = std::basic_string<CharType>>
/// @brief whether std::basic_string<CharType> has a non-deprecated std::char_traits
/// specialization, and is therefore usable as output_adapter's default StringType
///
/// std::char_traits is only guaranteed (and, on some standard libraries, only
/// implemented without a deprecation warning) for the character types listed
/// below; std::char_traits<T> for any other T (e.g. std::uint8_t, as used by the
/// binary writers) is a non-standard extension some standard libraries deprecate.
/// See https://github.com/nlohmann/json/issues/5725 item 2.
template<typename CharType>
struct is_output_adapter_string_char_type : std::integral_constant < bool,
std::is_same<CharType, char>::value ||
std::is_same<CharType, wchar_t>::value ||
std::is_same<CharType, char16_t>::value ||
std::is_same<CharType, char32_t>::value
#if defined(__cpp_lib_char8_t) && (__cpp_lib_char8_t >= 201907L)
|| std::is_same<CharType, char8_t>::value
#endif
> {};
/// @brief placeholder type for output_adapter's StringType and (with JSON_NO_IO
/// undefined) its std::basic_ostream constructor parameter, for CharType
/// with no non-deprecated std::char_traits specialization
///
/// Never actually used: the StringType- and std::basic_ostream-based
/// output_adapter constructors are neither documented nor tested for such
/// CharType (only the std::vector-based constructor is used for them, by the
/// binary writers). Naming std::basic_string<CharType> or
/// std::basic_ostream<CharType> anywhere such a constructor would otherwise be
/// declared - even as an unused default template argument or an unused,
/// never-called overload - instantiates std::char_traits<CharType> merely to
/// name the type, which is exactly what triggers the deprecation warning this
/// placeholder avoids.
template<typename CharType>
struct output_adapter_no_string_type {};
// Select output_adapter's default StringType (and, below, its ostream
// constructor's parameter type) via partial specialization, not
// std::conditional: std::conditional<B, T, F> requires both T and F to be named
// as template arguments up front, which would still instantiate (and thus name)
// std::basic_string<CharType> / std::basic_ostream<CharType> for every CharType,
// defeating the point. A bool non-type parameter with two specializations only
// ever names the type that is actually selected.
template<typename CharType, bool = is_output_adapter_string_char_type<CharType>::value>
struct output_adapter_default_string_type
{
using type = output_adapter_no_string_type<CharType>;
};
template<typename CharType>
struct output_adapter_default_string_type<CharType, true>
{
using type = std::basic_string<CharType>;
};
#ifndef JSON_NO_IO
/// distinct from output_adapter_no_string_type, so the placeholder overloads of
/// output_adapter's constructor (used when CharType is not a character type)
/// stay distinct overloads instead of colliding into a single redeclaration
template<typename CharType>
struct output_adapter_no_ostream_type {};
template<typename CharType, bool = is_output_adapter_string_char_type<CharType>::value>
struct output_adapter_ostream_type
{
using type = output_adapter_no_ostream_type<CharType>;
};
template<typename CharType>
struct output_adapter_ostream_type<CharType, true>
{
using type = std::basic_ostream<CharType>;
};
#endif // JSON_NO_IO
template < typename CharType, typename StringType =
typename output_adapter_default_string_type<CharType>::type >
class output_adapter
{
public:
@@ -199,7 +276,7 @@ class output_adapter
: oa(std::make_shared<output_vector_adapter<CharType, AllocatorType>>(vec)) {}
#ifndef JSON_NO_IO
output_adapter(std::basic_ostream<CharType>& s)
output_adapter(typename output_adapter_ostream_type<CharType>::type& s)
: oa(std::make_shared<output_stream_adapter<CharType>>(s)) {}
#endif // JSON_NO_IO
+67 -173
View File
@@ -3,24 +3,23 @@
// | | |__ | | | | | | version 3.12.0
// |_____|_____|_____|_|___| https://github.com/nlohmann/json
//
// SPDX-FileCopyrightText: 2008, 2009 Björn Hoehrmann <bjoern@hoehrmann.de>
// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
// SPDX-License-Identifier: MIT
#pragma once
#include <algorithm> // reverse, remove, fill, find, none_of, min
#include <algorithm> // remove, fill, find, none_of, min
#include <array> // array
#include <clocale> // localeconv, lconv
#include <cmath> // labs, isfinite, isnan, signbit
#include <cmath> // isfinite
#include <cstddef> // size_t, ptrdiff_t
#include <cstdint> // uint8_t
#include <cstdio> // snprintf
#include <cstring> // memcpy, memset
#include <iterator> // next
#include <limits> // numeric_limits
#include <string> // string, char_traits
#include <type_traits> // is_same
#include <utility> // move
#include <vector> // vector
#include <nlohmann/detail/conversions/to_chars.hpp>
@@ -28,7 +27,6 @@
#include <nlohmann/detail/input/string_scan.hpp>
#include <nlohmann/detail/macro_scope.hpp>
#include <nlohmann/detail/meta/cpp_future.hpp>
#include <nlohmann/detail/output/binary_writer.hpp>
#include <nlohmann/detail/output/output_adapters.hpp>
#include <nlohmann/detail/recursion_depth_limit.hpp>
#include <nlohmann/detail/string_concat.hpp>
@@ -67,7 +65,7 @@ class serializer
@param[in] ichar indentation character to use
@param[in] pretty_print_ whether the output shall be pretty-printed
@param[in] ensure_ascii_ If @a ensure_ascii_ is true, all non-ASCII
characters in the output are escaped with `\uXXXX` sequences, and the
characters in the output are escaped with `\\uXXXX` sequences, and the
result consists of ASCII characters only.
@param[in] indent_step_ the indent level
@param[in] error_handler_ how to react on decoding errors
@@ -83,7 +81,6 @@ class serializer
const std::size_t indent_step_ = 0,
error_handler_t error_handler_ = error_handler_t::strict)
: o(&s)
, locale(std::localeconv())
, indent_char(ichar)
, pretty_print(pretty_print_)
, ensure_ascii(ensure_ascii_)
@@ -106,9 +103,10 @@ class serializer
additional parameter. Arrays and objects are serialized without recursion,
however deeply they are nested.
- strings and object keys are escaped using `escape_string()`
- integer numbers are converted implicitly via `operator<<`
- floating-point numbers are converted to a string using `"%g"` format
- strings and object keys are escaped using @ref dump_escaped
- integer numbers are converted using a digit-pair lookup table (@ref dump_integer)
- floating-point numbers are converted to a string using @ref dump_float, which
uses `to_chars` for IEEE-754 types and `snprintf` otherwise
- binary values are serialized as objects containing the subtype and the
byte array
@@ -283,127 +281,16 @@ class serializer
}
case value_t::string:
{
put_char('"');
dump_escaped(*val.m_data.m_value.string);
put_char('"');
return;
}
case value_t::binary:
{
if (pretty_print)
{
put_literal("{\n");
// variable to hold indentation for recursive calls
const auto new_indent = next_indent(current_indent, indent_step);
put_indent(new_indent);
put_literal("\"bytes\": [");
if (!val.m_data.m_value.binary->empty())
{
for (auto i = val.m_data.m_value.binary->cbegin();
i != val.m_data.m_value.binary->cend() - 1; ++i)
{
dump_byte(*i);
put_literal(", ");
}
dump_byte(val.m_data.m_value.binary->back());
}
put_literal("],\n");
put_indent(new_indent);
put_literal("\"subtype\": ");
if (val.m_data.m_value.binary->has_subtype())
{
dump_integer(val.m_data.m_value.binary->subtype());
}
else
{
put_literal("null");
}
put_char('\n');
put_indent(current_indent);
put_char('}');
}
else
{
put_literal("{\"bytes\":[");
if (!val.m_data.m_value.binary->empty())
{
for (auto i = val.m_data.m_value.binary->cbegin();
i != val.m_data.m_value.binary->cend() - 1; ++i)
{
dump_byte(*i);
put_char(',');
}
dump_byte(val.m_data.m_value.binary->back());
}
put_literal("],\"subtype\":");
if (val.m_data.m_value.binary->has_subtype())
{
dump_integer(val.m_data.m_value.binary->subtype());
put_char('}');
}
else
{
put_literal("null}");
}
}
return;
}
case value_t::boolean:
{
if (val.m_data.m_value.boolean)
{
put_literal("true");
}
else
{
put_literal("false");
}
return;
}
case value_t::number_integer:
{
dump_integer(val.m_data.m_value.number_integer);
return;
}
case value_t::number_unsigned:
{
dump_integer(val.m_data.m_value.number_unsigned);
return;
}
case value_t::number_float:
{
dump_float(val.m_data.m_value.number_float);
return;
}
case value_t::discarded:
{
put_literal("<discarded>");
return;
}
case value_t::null:
{
put_literal("null");
default:
dump_scalar(val, current_indent);
return;
}
default: // LCOV_EXCL_LINE
JSON_ASSERT(false); // NOLINT(cert-dcl03-c,hicpp-static-assert,misc-static-assert) LCOV_EXCL_LINE
}
}
@@ -560,9 +447,9 @@ class serializer
@brief serialize the value @a val, but not the elements of a container
An object or array with elements is opened and pushed onto @a stack for
@ref dump_internal to walk; everything else - including a binary value,
@ref dump_iteratively to walk; everything else - including a binary value,
which looks like an object but has no elements to descend into - is written
out here in full.
out in full by @ref dump_scalar.
*/
void dump_value(const BasicJsonType& val,
const std::size_t current_indent,
@@ -620,6 +507,35 @@ class serializer
return;
}
case value_t::string:
case value_t::binary:
case value_t::boolean:
case value_t::number_integer:
case value_t::number_unsigned:
case value_t::number_float:
case value_t::discarded:
case value_t::null:
default:
dump_scalar(val, current_indent);
return;
}
}
/*!
@brief serialize the value @a val, which is neither an object nor an array
Shared by @ref dump_internal and @ref dump_value, so that a value is written
the same way however deeply it is nested. A binary value is written out here
in full: it looks like an object, but has no elements to descend into.
@param[in] val value to serialize; not an object or array
@param[in] current_indent the indentation of @a val, used for a
pretty-printed binary value
*/
void dump_scalar(const BasicJsonType& val, const std::size_t current_indent)
{
switch (val.m_data.m_type)
{
case value_t::string:
{
put_char('"');
@@ -740,6 +656,8 @@ class serializer
return;
}
case value_t::object: // LCOV_EXCL_LINE
case value_t::array: // LCOV_EXCL_LINE
default: // LCOV_EXCL_LINE
JSON_ASSERT(false); // NOLINT(cert-dcl03-c,hicpp-static-assert,misc-static-assert) LCOV_EXCL_LINE
}
@@ -768,11 +686,11 @@ class serializer
Escape a string by replacing certain special characters by a sequence of an
escape character (backslash) and another character and other control
characters by a sequence of "\u" followed by a four-digit hex
representation. The escaped string is written to output stream @a o.
representation. The escaped string is appended to @ref write_buffer.
@param[in] s the string to escape
@complexity Linear in the length of string @a s.
Complexity: Linear in the length of string @a s.
*/
void dump_escaped(const string_t& s)
{
@@ -962,7 +880,7 @@ class serializer
{
case error_handler_t::strict:
{
JSON_THROW(type_error::create(316, concat("invalid UTF-8 byte at index ", std::to_string(i), ": 0x", hex_bytes(byte | 0)), nullptr));
JSON_THROW(type_error::create(316, concat("invalid UTF-8 byte at index ", std::to_string(i), ": 0x", detail::hex_byte(byte)), nullptr));
}
case error_handler_t::ignore:
@@ -995,9 +913,9 @@ class serializer
}
else
{
string_buffer[bytes++] = detail::binary_writer<BasicJsonType, char>::to_char_type('\xEF');
string_buffer[bytes++] = detail::binary_writer<BasicJsonType, char>::to_char_type('\xBF');
string_buffer[bytes++] = detail::binary_writer<BasicJsonType, char>::to_char_type('\xBD');
string_buffer[bytes++] = '\xEF';
string_buffer[bytes++] = '\xBF';
string_buffer[bytes++] = '\xBD';
}
// write buffer and reset index; there must be 13 bytes
@@ -1054,7 +972,7 @@ 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[s.size() - 1] | 0))), nullptr));
JSON_THROW(type_error::create(316, concat("incomplete UTF-8 string; last byte: 0x", detail::hex_byte(static_cast<std::uint8_t>(s[s.size() - 1]))), nullptr));
}
case error_handler_t::ignore:
@@ -1276,21 +1194,7 @@ class serializer
}
/*!
* @brief convert a byte to a uppercase hex representation
* @param[in] byte byte to represent
* @return representation ("00".."FF")
*/
static std::string hex_bytes(std::uint8_t byte)
{
std::string result = "FF";
constexpr const char* nibble_to_hex = "0123456789ABCDEF";
result[0] = nibble_to_hex[byte / 16];
result[1] = nibble_to_hex[byte % 16];
return result;
}
/*!
* @brief write a lowercase "\uXXXX" escape sequence into @a string_buffer
* @brief write a lowercase "\\uXXXX" escape sequence into @a string_buffer
*
* Branch-free replacement for `snprintf(buf, 7, "\\u%04x", codeunit)` in the
* string escaping hot path. It writes exactly six characters ('\\', 'u' and
@@ -1402,7 +1306,7 @@ class serializer
/*!
@brief dump an integer
Dump a given integer to output stream @a o. Works internally with
Dump a given integer, appending it to @ref write_buffer. Works internally with
@a number_buffer.
@param[in] x integer number (signed or unsigned) to dump
@@ -1439,7 +1343,7 @@ class serializer
}
// use a pointer to fill the buffer
auto buffer_ptr = number_buffer.begin(); // NOLINT(llvm-qualified-auto,readability-qualified-auto,cppcoreguidelines-pro-type-vararg,hicpp-vararg)
auto buffer_ptr = number_buffer.begin(); // NOLINT(llvm-qualified-auto,readability-qualified-auto)
number_unsigned_t abs_value;
@@ -1493,7 +1397,7 @@ class serializer
/*!
@brief dump a floating-point number
Dump a given floating-point number to output stream @a o. Works internally
Dump a given floating-point number, appending it to @ref write_buffer. Works internally
with @a number_buffer.
@param[in] x floating-point number to dump
@@ -1554,21 +1458,28 @@ class serializer
// check if the buffer was large enough
JSON_ASSERT(static_cast<std::size_t>(len) < number_buffer.size());
// look up the locale's thousands separator and decimal point now,
// matching what snprintf_float() just used (see lexer::get_decimal_point())
const auto* loc = std::localeconv();
JSON_ASSERT(loc != nullptr);
const char thousands_sep = (loc->thousands_sep == nullptr) ? '\0' : *loc->thousands_sep;
const char decimal_point = (loc->decimal_point == nullptr) ? '\0' : *loc->decimal_point;
// erase thousands separators
if (locale.thousands_sep != '\0')
if (thousands_sep != '\0')
{
// NOLINTNEXTLINE(readability-qualified-auto,llvm-qualified-auto): std::remove returns an iterator, see https://github.com/nlohmann/json/issues/3081
const auto end = std::remove(number_buffer.begin(), number_buffer.begin() + len, locale.thousands_sep);
const auto end = std::remove(number_buffer.begin(), number_buffer.begin() + len, thousands_sep);
std::fill(end, number_buffer.end(), '\0');
JSON_ASSERT((end - number_buffer.begin()) <= len);
len = (end - number_buffer.begin());
}
// convert decimal point to '.'
if (locale.decimal_point != '\0' && locale.decimal_point != '.')
if (decimal_point != '\0' && decimal_point != '.')
{
// NOLINTNEXTLINE(readability-qualified-auto,llvm-qualified-auto): std::find returns an iterator, see https://github.com/nlohmann/json/issues/3081
const auto dec_pos = std::find(number_buffer.begin(), number_buffer.end(), locale.decimal_point);
const auto dec_pos = std::find(number_buffer.begin(), number_buffer.end(), decimal_point);
if (dec_pos != number_buffer.end())
{
*dec_pos = '.';
@@ -1613,34 +1524,17 @@ class serializer
*/
number_unsigned_t remove_sign(number_integer_t x) noexcept
{
JSON_ASSERT(x < 0 && x < (std::numeric_limits<number_integer_t>::max)()); // NOLINT(misc-redundant-expression)
JSON_ASSERT(x < 0);
return static_cast<number_unsigned_t>(-(x + 1)) + 1;
}
private:
/// the locale's thousand separator and decimal point characters
struct locale_chars
{
explicit locale_chars(const std::lconv* loc) noexcept
: thousands_sep(loc->thousands_sep == nullptr ? '\0' : std::char_traits<char>::to_char_type(* (loc->thousands_sep)))
, decimal_point(loc->decimal_point == nullptr ? '\0' : std::char_traits<char>::to_char_type(* (loc->decimal_point)))
{}
const char thousands_sep;
const char decimal_point;
};
/// the output of the serializer (non-owning; the adapter lives at the call site)
output_adapter_protocol<char>* o = nullptr;
/// a (hopefully) large enough character buffer
std::array<char, 64> number_buffer{{}};
/// computed once from std::localeconv() at construction; @ref
/// locale_chars keeps std::localeconv()'s pointer from having to be held
/// past the constructor, while still letting these stay const
const locale_chars locale;
/// string buffer
std::array<char, 512> string_buffer{{}};
@@ -1650,7 +1544,7 @@ class serializer
/// whether to pretty-print the output
const bool pretty_print;
/// whether to escape non-ASCII characters with \uXXXX sequences
/// whether to escape non-ASCII characters with \\uXXXX sequences
const bool ensure_ascii;
/// the indent level