Merge branch 'develop' into custom-number-type-fixes

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

docs/mkdocs/docs/api/basic_json/to_bjdata.md

@@ -123,4 +123,6 @@ Linear in the size of the JSON value `j`.
   that is not valid UTF-8 unchanged, as before; `strict` (the default if
   [`JSON_STRICT_BINARY_UTF8`](../macros/json_strict_binary_utf8.md) is enabled) throws `type_error.316`.
 - Throws `type_error.321` for a discarded value since version 3.13.0; previously, a discarded value nested in an
-  array or object was silently skipped, producing invalid BJData.
+  array or object was silently skipped, producing invalid BJData.
+- Writes unsigned integers wider than 64 bits as high-precision numbers since version 3.13.0; previously, they were
+  silently truncated to 64 bits.

docs/mkdocs/docs/api/basic_json/to_bon8.md

@@ -37,8 +37,9 @@ With (2), the bytes written before the exception remain in the output adapter.
 
 ## Exceptions
 
-- Throws [out_of_range.407](../../home/exceptions.md#jsonexceptionout_of_range407) if `j` contains an unsigned integer
-  above 9223372036854775807, which BON8 cannot represent
+- Throws [out_of_range.407](../../home/exceptions.md#jsonexceptionout_of_range407) if `j` contains an integer outside
+  the range of int64 (an unsigned integer above 9223372036854775807, or, with a number type wider than 64 bits, any
+  integer beyond int64), which BON8 cannot represent
 - Throws [type_error.316](../../home/exceptions.md#jsonexceptiontype_error316) if `j` contains a string that is not
   valid UTF-8
 - Throws [type_error.321](../../home/exceptions.md#jsonexceptiontype_error321) if `j` or a value nested in it is

docs/mkdocs/docs/api/basic_json/to_bson.md

@@ -47,6 +47,10 @@ Strong guarantee: if an exception is thrown, there are no changes in the JSON va
 
 - Throws [`type_error.317`](../../home/exceptions.md#jsonexceptiontype_error317) if the top-level type of the JSON value
   is not an object; example: `"to serialize to BSON, top-level type must be object, but is string"`
+- Throws [`out_of_range.407`](../../home/exceptions.md#jsonexceptionout_of_range407) if `j` contains a signed integer
+  outside the range of int64 or an unsigned integer outside the range of uint64, which is only possible with a number
+  type wider than 64 bits; example:
+  `"integer number 9223372036854775808 cannot be represented by BSON as it does not fit int64"`
 - Throws [`out_of_range.409`](../../home/exceptions.md#jsonexceptionout_of_range409) if a key in the JSON object contains
   a null byte (code point U+0000); example: `"BSON key cannot contain code point U+0000 (at byte 2)"`
 - Throws [`out_of_range.412`](../../home/exceptions.md#jsonexceptionout_of_range412) if the length of a document, array,
@@ -119,3 +123,5 @@ pass before anything is written.
   that is not valid UTF-8 unchanged, as before; `strict` (the default if
   [`JSON_STRICT_BINARY_UTF8`](../macros/json_strict_binary_utf8.md) is enabled) throws `type_error.316` before anything
   is written.
+- Throws `out_of_range.407` for integers that do not fit 64 bits since version 3.13.0; previously, integers of a
+  number type wider than 64 bits were silently truncated.

docs/mkdocs/docs/api/basic_json/to_cbor.md

@@ -46,6 +46,9 @@ Strong guarantee: if an exception is thrown, there are no changes in the JSON va
 
 ## Exceptions
 
+- Throws [`out_of_range.407`](../../home/exceptions.md#jsonexceptionout_of_range407) if `j` contains an integer
+  outside [-2^64, 2^64-1], which is only possible with a number type wider than 64 bits; example:
+  `"integer number 18446744073709551616 cannot be represented by CBOR as it does not fit [-2^64, 2^64-1]"`
 - Throws [type_error.316](../../home/exceptions.md#jsonexceptiontype_error316) if a string or object key in `j` is
   not valid UTF-8 and `error_handler` is `strict` (the default only if
   [`JSON_STRICT_BINARY_UTF8`](../macros/json_strict_binary_utf8.md) is enabled)
@@ -90,3 +93,5 @@ Linear in the size of the JSON value `j`.
   [`JSON_STRICT_BINARY_UTF8`](../macros/json_strict_binary_utf8.md) is enabled) throws `type_error.316`.
 - Throws `type_error.321` for a discarded value since version 3.13.0; previously, a discarded value nested in an
   array or object was silently skipped, producing invalid CBOR.
+- Throws `out_of_range.407` for integers that do not fit 64 bits since version 3.13.0; previously, integers of a
+  number type wider than 64 bits were silently truncated.

docs/mkdocs/docs/api/basic_json/to_msgpack.md

@@ -46,6 +46,9 @@ Strong guarantee: if an exception is thrown, there are no changes in the JSON va
 
 ## Exceptions
 
+- Throws [`out_of_range.407`](../../home/exceptions.md#jsonexceptionout_of_range407) if `j` contains an integer
+  outside [-2^63, 2^64-1], which is only possible with a number type wider than 64 bits; example:
+  `"integer number 18446744073709551616 cannot be represented by MessagePack as it does not fit [-2^63, 2^64-1]"`
 - Throws [`out_of_range.412`](../../home/exceptions.md#jsonexceptionout_of_range412) if the length of a string, binary
   value, array, or object exceeds 4294967295, the maximum MessagePack can store; example:
   `"MessagePack length 4294967296 exceeds maximum of 4294967295"`
@@ -112,3 +115,5 @@ Linear in the size of the JSON value `j`.
   `number_unsigned_t`.
 - Throws `type_error.321` for a discarded value since version 3.13.0; previously, a discarded value nested in an
   array or object was silently skipped, producing invalid MessagePack.
+- Throws `out_of_range.407` for integers that do not fit 64 bits since version 3.13.0; previously, integers of a
+  number type wider than 64 bits were silently truncated.

docs/mkdocs/docs/home/exceptions.md

@@ -916,9 +916,19 @@ double-precision number when `number_float_t` is `#!cpp float`.
 
 ### json.exception.out_of_range.407
 
-An unsigned integer number greater than 9223372036854775807 cannot be represented in the binary format. This exception
-is only thrown by [`to_bon8`](../api/basic_json/to_bon8.md), as [BON8](../features/binary_formats/bon8.md) has no
-unsigned 64-bit integer type.
+An integer number cannot be represented by the binary format it is serialized to:
+
+- [BON8](../features/binary_formats/bon8.md) only stores integers that fit into int64, so
+  [`to_bon8`](../api/basic_json/to_bon8.md) throws for unsigned integers greater than 9223372036854775807.
+- [CBOR](../features/binary_formats/cbor.md), [MessagePack](../features/binary_formats/messagepack.md), and
+  [BSON](../features/binary_formats/bson.md) store integers in at most 64 bits. With the default number types, every
+  integer fits, but a [`number_integer_t`](../api/basic_json/number_integer_t.md) or
+  [`number_unsigned_t`](../api/basic_json/number_unsigned_t.md) wider than 64 bits (e.g., `__int128`) can hold values
+  outside the range of the format: [-2^64, 2^64-1] for CBOR, [-2^63, 2^64-1] for MessagePack, and the range of int64
+  (signed integers) or uint64 (unsigned integers) for BSON.
+
+[UBJSON](../features/binary_formats/ubjson.md) and [BJData](../features/binary_formats/bjdata.md) never throw this
+exception, because they serialize integers beyond 64 bits as high-precision numbers.
 
 !!! note "Former occurrences"
 
@@ -927,11 +937,17 @@ unsigned 64-bit integer type.
     - Since version 3.9.0, integer numbers beyond int64 are serialized as high-precision UBJSON numbers.
     - Since version 3.12.0, integer numbers beyond int64 are serialized as uint64 BSON numbers.
 
-!!! failure "Example message"
+    Before version 3.13.0, CBOR, MessagePack, and BSON silently truncated integers wider than 64 bits, and BJData
+    truncated unsigned integers wider than 64 bits.
+
+!!! failure "Example messages"
 
     ```
     integer number 18446744073709551615 cannot be represented by BON8 as it does not fit int64
     ```
+    ```
+    integer number 1267650600228229401496703205376 cannot be represented by CBOR as it does not fit [-2^64, 2^64-1]
+    ```
 
 ### json.exception.out_of_range.408
 

include/nlohmann/detail/output/binary_writer.hpp

@@ -207,6 +207,10 @@ class binary_writer
             {
                 if (j.m_data.m_value.number_integer >= 0)
                 {
+                    if (JSON_HEDLEY_UNLIKELY(!integer_fits_max<std::uint64_t>(j.m_data.m_value.number_integer)))
+                    {
+                        throw_integer_out_of_range(j, "CBOR", "[-2^64, 2^64-1]");
+                    }
                     // CBOR does not differentiate between positive signed
                     // integers and unsigned integers
                     write_cbor_head(0x00, static_cast<std::uint64_t>(j.m_data.m_value.number_integer));
@@ -214,6 +218,10 @@ class binary_writer
                 else
                 {
                     // a negative integer n is encoded as -1 - n
+                    if (JSON_HEDLEY_UNLIKELY(!integer_fits_max<std::uint64_t>(-1 - j.m_data.m_value.number_integer)))
+                    {
+                        throw_integer_out_of_range(j, "CBOR", "[-2^64, 2^64-1]");
+                    }
                     write_cbor_head(0x20, static_cast<std::uint64_t>(-1 - j.m_data.m_value.number_integer));
                 }
                 break;
@@ -221,6 +229,10 @@ class binary_writer
 
             case value_t::number_unsigned:
             {
+                if (JSON_HEDLEY_UNLIKELY(!integer_fits_max<std::uint64_t>(j.m_data.m_value.number_unsigned)))
+                {
+                    throw_integer_out_of_range(j, "CBOR", "uint64");
+                }
                 write_cbor_head(0x00, conditional_static_cast<std::uint64_t>(j.m_data.m_value.number_unsigned));
                 break;
             }
@@ -423,12 +435,20 @@ class binary_writer
             {
                 if (j.m_data.m_value.number_integer >= 0)
                 {
+                    if (JSON_HEDLEY_UNLIKELY(!integer_fits_max<std::uint64_t>(j.m_data.m_value.number_integer)))
+                    {
+                        throw_integer_out_of_range(j, "MessagePack", "[-2^63, 2^64-1]");
+                    }
                     // MessagePack does not differentiate between positive
                     // signed integers and unsigned integers.
                     write_msgpack_unsigned(static_cast<std::uint64_t>(j.m_data.m_value.number_integer));
                 }
                 else
                 {
+                    if (JSON_HEDLEY_UNLIKELY(!integer_fits_min<std::int64_t>(j.m_data.m_value.number_integer)))
+                    {
+                        throw_integer_out_of_range(j, "MessagePack", "[-2^63, 2^64-1]");
+                    }
                     if (j.m_data.m_value.number_integer >= -32)
                     {
                         // negative fixnum
@@ -467,6 +487,10 @@ class binary_writer
 
             case value_t::number_unsigned:
             {
+                if (JSON_HEDLEY_UNLIKELY(!integer_fits_max<std::uint64_t>(j.m_data.m_value.number_unsigned)))
+                {
+                    throw_integer_out_of_range(j, "MessagePack", "uint64");
+                }
                 write_msgpack_unsigned(static_cast<std::uint64_t>(j.m_data.m_value.number_unsigned));
                 break;
             }
@@ -824,6 +848,133 @@ class binary_writer
         JSON_THROW(type_error::create(exception_id::discarded_value_used, concat("cannot serialize discarded value to ", format_name), &j));
     }
 
+    /*!
+    @brief whether integer @a n does not exceed the maximum of @a TargetType
+
+    The binary formats store integers in at most 64 bits, but number_integer_t
+    and number_unsigned_t may be wider (e.g., __int128). The range of the
+    integer is taken from std::numeric_limits, so a number type whose range
+    fits into @a TargetType is never checked: the function is then constant
+    true, and the default int64_t/uint64_t types pay nothing.
+    */
+    template<typename TargetType, typename NumberType>
+    static constexpr bool integer_fits_max(const NumberType n) noexcept
+    {
+        return integer_fits_max<TargetType>(n, std::integral_constant < bool,
+                                            (std::numeric_limits<NumberType>::digits > std::numeric_limits<TargetType>::digits) > ());
+    }
+
+    template<typename TargetType, typename NumberType>
+    static constexpr bool integer_fits_max(const NumberType /*unused*/, std::false_type /*may_exceed*/) noexcept
+    {
+        return true;
+    }
+
+    template<typename TargetType, typename NumberType>
+    static constexpr bool integer_fits_max(const NumberType n, std::true_type /*may_exceed*/) noexcept
+    {
+        // NumberType has more digits than TargetType, so it can hold its maximum
+        return n <= static_cast<NumberType>((std::numeric_limits<TargetType>::max)());
+    }
+
+    /*!
+    @brief whether integer @a n is not below the minimum of @a TargetType;
+           constant true if NumberType cannot hold such a value
+    */
+    template<typename TargetType, typename NumberType>
+    static constexpr bool integer_fits_min(const NumberType n) noexcept
+    {
+        return integer_fits_min<TargetType>(n, std::integral_constant < bool, std::numeric_limits<NumberType>::is_signed &&
+                                            (!std::numeric_limits<TargetType>::is_signed || std::numeric_limits<NumberType>::digits > std::numeric_limits<TargetType>::digits) > ());
+    }
+
+    template<typename TargetType, typename NumberType>
+    static constexpr bool integer_fits_min(const NumberType /*unused*/, std::false_type /*may_fall_below*/) noexcept
+    {
+        return true;
+    }
+
+    template<typename TargetType, typename NumberType>
+    static constexpr bool integer_fits_min(const NumberType n, std::true_type /*may_fall_below*/) noexcept
+    {
+        // NumberType is signed and either TargetType is unsigned (minimum 0)
+        // or NumberType has more digits, so it can hold the minimum
+        return n >= static_cast<NumberType>((std::numeric_limits<TargetType>::min)());
+    }
+
+    /*!
+    @brief whether integer @a n lies in the range of @a TargetType
+    */
+    template<typename TargetType, typename NumberType>
+    static constexpr bool integer_fits(const NumberType n) noexcept
+    {
+        return integer_fits_min<TargetType>(n) && integer_fits_max<TargetType>(n);
+    }
+
+    /*!
+    @brief the decimal digits of the non-negative integer @a n
+    */
+    template<typename NumberType>
+    static std::string integer_to_string(NumberType n, std::false_type /*is_signed*/)
+    {
+        std::string result;
+        do
+        {
+            result.push_back(static_cast<char>('0' + (n % 10)));
+            n = static_cast<NumberType>(n / 10);
+        }
+        while (n != 0);
+        std::reverse(result.begin(), result.end());
+        return result;
+    }
+
+    /*!
+    @brief the decimal digits of the integer @a n, with a leading '-' if it
+           is negative
+    */
+    template<typename NumberType>
+    static std::string integer_to_string(NumberType n, std::true_type /*is_signed*/)
+    {
+        // the remainder of a negative n is not positive; each digit is
+        // negated on its own, because negating the minimum of NumberType
+        // as a whole would overflow
+        const bool negative = n < 0;
+        std::string result;
+        do
+        {
+            const auto remainder = n % 10;
+            result.push_back(static_cast<char>('0' + (remainder < 0 ? -remainder : remainder)));
+            n = static_cast<NumberType>(n / 10);
+        }
+        while (n != 0);
+        if (negative)
+        {
+            result.push_back('-');
+        }
+        std::reverse(result.begin(), result.end());
+        return result;
+    }
+
+    /*!
+    @brief throws because the integer @a j is too large for @a format_name
+    @throw out_of_range.407 always
+    */
+    JSON_HEDLEY_NO_RETURN static void throw_integer_out_of_range(const BasicJsonType& j, const char* format_name, const char* range)
+    {
+        // neither std::to_string(), which has no overload for integer types
+        // wider than 64 bits, nor dump(), which would also instantiate the
+        // serializer for objects and fail for key types it cannot write
+        using integer_limits = std::numeric_limits<typename BasicJsonType::number_integer_t>;
+        using unsigned_limits = std::numeric_limits<typename BasicJsonType::number_unsigned_t>;
+        const std::string number = j.is_number_unsigned()
+                                   ? integer_to_string(j.m_data.m_value.number_unsigned, std::integral_constant<bool, unsigned_limits::is_signed>())
+                                   : integer_to_string(j.m_data.m_value.number_integer, std::integral_constant<bool, integer_limits::is_signed>());
+        static_cast<void>(number); // unused when JSON_NOEXCEPTION is defined
+        static_cast<void>(format_name);
+        static_cast<void>(range);
+        JSON_THROW(out_of_range::create(exception_id::integer_too_large, concat("integer number ", number, " cannot be represented by ", format_name, " as it does not fit ", range), &j));
+    }
+
     void write_msgpack_array_prefix(const std::size_t N, const BasicJsonType& j)
     {
         const auto n = to_msgpack_length(N, j);
@@ -1580,6 +1731,8 @@ class binary_writer
             is neither an object nor an array
     @throw out_of_range.415 if @a j is binary with a subtype that does not fit
            into a byte, before anything is written
+    @throw out_of_range.407 if @a j is an integer that does not fit the 64 bits
+           of a BSON integer, before anything is written
     @throw type_error.316 if @a j is a string that is not valid UTF-8, before
            anything is written
     @throw type_error.321 if @a j is discarded
@@ -1598,9 +1751,17 @@ class binary_writer
                 return 8ul;
 
             case value_t::number_integer:
-                return calc_bson_integer_size(j.m_data.m_value.number_integer);
+                if (JSON_HEDLEY_UNLIKELY(!integer_fits<std::int64_t>(j.m_data.m_value.number_integer)))
+                {
+                    throw_integer_out_of_range(j, "BSON", "int64");
+                }
+                return calc_bson_integer_size(static_cast<std::int64_t>(j.m_data.m_value.number_integer));
 
             case value_t::number_unsigned:
+                if (JSON_HEDLEY_UNLIKELY(!integer_fits_max<std::uint64_t>(j.m_data.m_value.number_unsigned)))
+                {
+                    throw_integer_out_of_range(j, "BSON", "uint64");
+                }
                 return calc_bson_unsigned_size(conditional_static_cast<std::uint64_t>(j.m_data.m_value.number_unsigned));
 
             case value_t::string:
@@ -1639,8 +1800,9 @@ class binary_writer
             case value_t::number_float:
                 return write_bson_double(name, j.m_data.m_value.number_float);
 
+            // calc_bson_value_size() checked that integers fit 64 bits
             case value_t::number_integer:
-                return write_bson_integer(name, j.m_data.m_value.number_integer);
+                return write_bson_integer(name, static_cast<std::int64_t>(j.m_data.m_value.number_integer));
 
             case value_t::number_unsigned:
                 return write_bson_unsigned(name, conditional_static_cast<std::uint64_t>(j.m_data.m_value.number_unsigned));
@@ -2147,7 +2309,7 @@ class binary_writer
         {
             return 'L';
         }
-        if (use_bjdata && std::is_unsigned<NumberType>::value)
+        if (use_bjdata && std::is_unsigned<NumberType>::value && integer_fits_max<std::uint64_t>(n))
         {
             return 'M';
         }
@@ -2272,14 +2434,16 @@ class binary_writer
     @brief checks whether a JSON number fits into @a TargetType
     @param[in] el a JSON number of either the signed or unsigned integer kind
     @return whether @a el's value can be represented by @a TargetType without
-            wrapping, regardless of which of the two kinds it is stored as
+            wrapping, regardless of which of the two kinds it is stored as;
+            false for a value that does not even fit the 64-bit type it is
+            read as (possible for number types wider than 64 bits)
     */
     template<typename TargetType>
     static bool bjdata_ndarray_value_in_range(const BasicJsonType& el)
     {
         return el.is_number_unsigned()
-               ? value_in_range_of<TargetType>(el.template get<std::uint64_t>())
-               : value_in_range_of<TargetType>(el.template get<std::int64_t>());
+               ? integer_fits_max<std::uint64_t>(el.m_data.m_value.number_unsigned) && value_in_range_of<TargetType>(el.template get<std::uint64_t>())
+               : integer_fits<std::int64_t>(el.m_data.m_value.number_integer) && value_in_range_of<TargetType>(el.template get<std::int64_t>());
     }
 
     /*!
@@ -2511,10 +2675,11 @@ class binary_writer
         for (const auto& el : dims)
         {
             // a dimension is read as an unsigned value below, so anything that
-            // is not a non-negative integer is rejected: a non-integer entry
-            // would pun unrelated bytes as the dimension, and a negative one
-            // would wrap into a nonsensical length
-            if (!el.is_number_integer() || (!el.is_number_unsigned() && el.template get<std::int64_t>() < 0))
+            // is not a non-negative integer in the range of std::uint64_t is
+            // rejected: a non-integer entry would pun unrelated bytes as the
+            // dimension, and a negative or wider one would wrap into a
+            // nonsensical length
+            if (!el.is_number_integer() || !bjdata_ndarray_value_in_range<std::uint64_t>(el))
             {
                 return true;
             }
@@ -2646,9 +2811,9 @@ class binary_writer
 
             case value_t::number_unsigned:
             {
-                if (j.m_data.m_value.number_unsigned > static_cast<typename BasicJsonType::number_unsigned_t>((std::numeric_limits<std::int64_t>::max)()))
+                if (JSON_HEDLEY_UNLIKELY(!integer_fits_max<std::int64_t>(j.m_data.m_value.number_unsigned)))
                 {
-                    JSON_THROW(out_of_range::create(exception_id::integer_too_large, concat("integer number ", std::to_string(j.m_data.m_value.number_unsigned), " cannot be represented by BON8 as it does not fit int64"), &j));
+                    throw_integer_out_of_range(j, "BON8", "int64");
                 }
                 write_bon8_integer(static_cast<std::int64_t>(j.m_data.m_value.number_unsigned));
                 string_open = false;
@@ -2657,6 +2822,10 @@ class binary_writer
 
             case value_t::number_integer:
             {
+                if (JSON_HEDLEY_UNLIKELY(!integer_fits<std::int64_t>(j.m_data.m_value.number_integer)))
+                {
+                    throw_integer_out_of_range(j, "BON8", "int64");
+                }
                 write_bon8_integer(static_cast<std::int64_t>(j.m_data.m_value.number_integer));
                 string_open = false;
                 break;

include/nlohmann/detail/output/serializer.hpp

@@ -1525,7 +1525,7 @@ class serializer
         // without leading zeros
         if (abs_value < 10000000000000000u)
         {
-            const std::uint64_t value = abs_value;
+            const auto value = static_cast<std::uint64_t>(abs_value); // fits: abs_value < 10^16
             const std::uint64_t upper = value / 100000000u;
             const std::uint64_t first = dtoa_impl::eight_digit_bytes(upper != 0 ? upper : value);
             const auto leading = static_cast<unsigned>(count_leading_zeros(first) / 8); // (first is not 0)

include/nlohmann/detail/value_t.hpp

@@ -14,7 +14,6 @@
 #include <cstdint> // uint8_t
 #include <limits> // numeric_limits
 #include <string> // string
-#include <type_traits> // is_signed
 
 #include <nlohmann/detail/macro_scope.hpp>
 #if JSON_HAS_THREE_WAY_COMPARISON
@@ -175,13 +174,16 @@ FloatType compare_integer_with_float(const IntegerType i, const FloatType f) noe
 
     // values of IntegerType lie in [-bound, bound) when signed and in
     // [0, bound) when unsigned; digits excludes the sign bit, so bound is a
-    // power of two that the float represents exactly
-    const FloatType bound = std::ldexp(static_cast<FloatType>(1), std::numeric_limits<IntegerType>::digits);
+    // power of two that the float represents exactly; the signedness comes
+    // from numeric_limits as well, because std::is_signed is false for class
+    // types such as 128-bit or multiprecision integers
+    using limits = std::numeric_limits<IntegerType>;
+    const FloatType bound = std::ldexp(static_cast<FloatType>(1), limits::digits);
     if (f >= bound)
     {
         return ordered(-1);
     }
-    if (std::is_signed<IntegerType>::value ? (f < -bound) : (f < static_cast<FloatType>(0)))
+    if (limits::is_signed ? (f < -bound) : (f < static_cast<FloatType>(0)))
     {
         return ordered(1);
     }

single_include/nlohmann/json.hpp

@@ -289,7 +289,6 @@
 #include <cstdint> // uint8_t
 #include <limits> // numeric_limits
 #include <string> // string
-#include <type_traits> // is_signed
 
 // #include <nlohmann/detail/macro_scope.hpp>
 //     __ _____ _____ _____
@@ -3396,13 +3395,16 @@ FloatType compare_integer_with_float(const IntegerType i, const FloatType f) noe
 
     // values of IntegerType lie in [-bound, bound) when signed and in
     // [0, bound) when unsigned; digits excludes the sign bit, so bound is a
-    // power of two that the float represents exactly
-    const FloatType bound = std::ldexp(static_cast<FloatType>(1), std::numeric_limits<IntegerType>::digits);
+    // power of two that the float represents exactly; the signedness comes
+    // from numeric_limits as well, because std::is_signed is false for class
+    // types such as 128-bit or multiprecision integers
+    using limits = std::numeric_limits<IntegerType>;
+    const FloatType bound = std::ldexp(static_cast<FloatType>(1), limits::digits);
     if (f >= bound)
     {
         return ordered(-1);
     }
-    if (std::is_signed<IntegerType>::value ? (f < -bound) : (f < static_cast<FloatType>(0)))
+    if (limits::is_signed ? (f < -bound) : (f < static_cast<FloatType>(0)))
     {
         return ordered(1);
     }
@@ -23122,6 +23124,10 @@ class binary_writer
             {
                 if (j.m_data.m_value.number_integer >= 0)
                 {
+                    if (JSON_HEDLEY_UNLIKELY(!integer_fits_max<std::uint64_t>(j.m_data.m_value.number_integer)))
+                    {
+                        throw_integer_out_of_range(j, "CBOR", "[-2^64, 2^64-1]");
+                    }
                     // CBOR does not differentiate between positive signed
                     // integers and unsigned integers
                     write_cbor_head(0x00, static_cast<std::uint64_t>(j.m_data.m_value.number_integer));
@@ -23129,6 +23135,10 @@ class binary_writer
                 else
                 {
                     // a negative integer n is encoded as -1 - n
+                    if (JSON_HEDLEY_UNLIKELY(!integer_fits_max<std::uint64_t>(-1 - j.m_data.m_value.number_integer)))
+                    {
+                        throw_integer_out_of_range(j, "CBOR", "[-2^64, 2^64-1]");
+                    }
                     write_cbor_head(0x20, static_cast<std::uint64_t>(-1 - j.m_data.m_value.number_integer));
                 }
                 break;
@@ -23136,6 +23146,10 @@ class binary_writer
 
             case value_t::number_unsigned:
             {
+                if (JSON_HEDLEY_UNLIKELY(!integer_fits_max<std::uint64_t>(j.m_data.m_value.number_unsigned)))
+                {
+                    throw_integer_out_of_range(j, "CBOR", "uint64");
+                }
                 write_cbor_head(0x00, conditional_static_cast<std::uint64_t>(j.m_data.m_value.number_unsigned));
                 break;
             }
@@ -23338,12 +23352,20 @@ class binary_writer
             {
                 if (j.m_data.m_value.number_integer >= 0)
                 {
+                    if (JSON_HEDLEY_UNLIKELY(!integer_fits_max<std::uint64_t>(j.m_data.m_value.number_integer)))
+                    {
+                        throw_integer_out_of_range(j, "MessagePack", "[-2^63, 2^64-1]");
+                    }
                     // MessagePack does not differentiate between positive
                     // signed integers and unsigned integers.
                     write_msgpack_unsigned(static_cast<std::uint64_t>(j.m_data.m_value.number_integer));
                 }
                 else
                 {
+                    if (JSON_HEDLEY_UNLIKELY(!integer_fits_min<std::int64_t>(j.m_data.m_value.number_integer)))
+                    {
+                        throw_integer_out_of_range(j, "MessagePack", "[-2^63, 2^64-1]");
+                    }
                     if (j.m_data.m_value.number_integer >= -32)
                     {
                         // negative fixnum
@@ -23382,6 +23404,10 @@ class binary_writer
 
             case value_t::number_unsigned:
             {
+                if (JSON_HEDLEY_UNLIKELY(!integer_fits_max<std::uint64_t>(j.m_data.m_value.number_unsigned)))
+                {
+                    throw_integer_out_of_range(j, "MessagePack", "uint64");
+                }
                 write_msgpack_unsigned(static_cast<std::uint64_t>(j.m_data.m_value.number_unsigned));
                 break;
             }
@@ -23739,6 +23765,133 @@ class binary_writer
         JSON_THROW(type_error::create(exception_id::discarded_value_used, concat("cannot serialize discarded value to ", format_name), &j));
     }
 
+    /*!
+    @brief whether integer @a n does not exceed the maximum of @a TargetType
+
+    The binary formats store integers in at most 64 bits, but number_integer_t
+    and number_unsigned_t may be wider (e.g., __int128). The range of the
+    integer is taken from std::numeric_limits, so a number type whose range
+    fits into @a TargetType is never checked: the function is then constant
+    true, and the default int64_t/uint64_t types pay nothing.
+    */
+    template<typename TargetType, typename NumberType>
+    static constexpr bool integer_fits_max(const NumberType n) noexcept
+    {
+        return integer_fits_max<TargetType>(n, std::integral_constant < bool,
+                                            (std::numeric_limits<NumberType>::digits > std::numeric_limits<TargetType>::digits) > ());
+    }
+
+    template<typename TargetType, typename NumberType>
+    static constexpr bool integer_fits_max(const NumberType /*unused*/, std::false_type /*may_exceed*/) noexcept
+    {
+        return true;
+    }
+
+    template<typename TargetType, typename NumberType>
+    static constexpr bool integer_fits_max(const NumberType n, std::true_type /*may_exceed*/) noexcept
+    {
+        // NumberType has more digits than TargetType, so it can hold its maximum
+        return n <= static_cast<NumberType>((std::numeric_limits<TargetType>::max)());
+    }
+
+    /*!
+    @brief whether integer @a n is not below the minimum of @a TargetType;
+           constant true if NumberType cannot hold such a value
+    */
+    template<typename TargetType, typename NumberType>
+    static constexpr bool integer_fits_min(const NumberType n) noexcept
+    {
+        return integer_fits_min<TargetType>(n, std::integral_constant < bool, std::numeric_limits<NumberType>::is_signed &&
+                                            (!std::numeric_limits<TargetType>::is_signed || std::numeric_limits<NumberType>::digits > std::numeric_limits<TargetType>::digits) > ());
+    }
+
+    template<typename TargetType, typename NumberType>
+    static constexpr bool integer_fits_min(const NumberType /*unused*/, std::false_type /*may_fall_below*/) noexcept
+    {
+        return true;
+    }
+
+    template<typename TargetType, typename NumberType>
+    static constexpr bool integer_fits_min(const NumberType n, std::true_type /*may_fall_below*/) noexcept
+    {
+        // NumberType is signed and either TargetType is unsigned (minimum 0)
+        // or NumberType has more digits, so it can hold the minimum
+        return n >= static_cast<NumberType>((std::numeric_limits<TargetType>::min)());
+    }
+
+    /*!
+    @brief whether integer @a n lies in the range of @a TargetType
+    */
+    template<typename TargetType, typename NumberType>
+    static constexpr bool integer_fits(const NumberType n) noexcept
+    {
+        return integer_fits_min<TargetType>(n) && integer_fits_max<TargetType>(n);
+    }
+
+    /*!
+    @brief the decimal digits of the non-negative integer @a n
+    */
+    template<typename NumberType>
+    static std::string integer_to_string(NumberType n, std::false_type /*is_signed*/)
+    {
+        std::string result;
+        do
+        {
+            result.push_back(static_cast<char>('0' + (n % 10)));
+            n = static_cast<NumberType>(n / 10);
+        }
+        while (n != 0);
+        std::reverse(result.begin(), result.end());
+        return result;
+    }
+
+    /*!
+    @brief the decimal digits of the integer @a n, with a leading '-' if it
+           is negative
+    */
+    template<typename NumberType>
+    static std::string integer_to_string(NumberType n, std::true_type /*is_signed*/)
+    {
+        // the remainder of a negative n is not positive; each digit is
+        // negated on its own, because negating the minimum of NumberType
+        // as a whole would overflow
+        const bool negative = n < 0;
+        std::string result;
+        do
+        {
+            const auto remainder = n % 10;
+            result.push_back(static_cast<char>('0' + (remainder < 0 ? -remainder : remainder)));
+            n = static_cast<NumberType>(n / 10);
+        }
+        while (n != 0);
+        if (negative)
+        {
+            result.push_back('-');
+        }
+        std::reverse(result.begin(), result.end());
+        return result;
+    }
+
+    /*!
+    @brief throws because the integer @a j is too large for @a format_name
+    @throw out_of_range.407 always
+    */
+    JSON_HEDLEY_NO_RETURN static void throw_integer_out_of_range(const BasicJsonType& j, const char* format_name, const char* range)
+    {
+        // neither std::to_string(), which has no overload for integer types
+        // wider than 64 bits, nor dump(), which would also instantiate the
+        // serializer for objects and fail for key types it cannot write
+        using integer_limits = std::numeric_limits<typename BasicJsonType::number_integer_t>;
+        using unsigned_limits = std::numeric_limits<typename BasicJsonType::number_unsigned_t>;
+        const std::string number = j.is_number_unsigned()
+                                   ? integer_to_string(j.m_data.m_value.number_unsigned, std::integral_constant<bool, unsigned_limits::is_signed>())
+                                   : integer_to_string(j.m_data.m_value.number_integer, std::integral_constant<bool, integer_limits::is_signed>());
+        static_cast<void>(number); // unused when JSON_NOEXCEPTION is defined
+        static_cast<void>(format_name);
+        static_cast<void>(range);
+        JSON_THROW(out_of_range::create(exception_id::integer_too_large, concat("integer number ", number, " cannot be represented by ", format_name, " as it does not fit ", range), &j));
+    }
+
     void write_msgpack_array_prefix(const std::size_t N, const BasicJsonType& j)
     {
         const auto n = to_msgpack_length(N, j);
@@ -24495,6 +24648,8 @@ class binary_writer
             is neither an object nor an array
     @throw out_of_range.415 if @a j is binary with a subtype that does not fit
            into a byte, before anything is written
+    @throw out_of_range.407 if @a j is an integer that does not fit the 64 bits
+           of a BSON integer, before anything is written
     @throw type_error.316 if @a j is a string that is not valid UTF-8, before
            anything is written
     @throw type_error.321 if @a j is discarded
@@ -24513,9 +24668,17 @@ class binary_writer
                 return 8ul;
 
             case value_t::number_integer:
-                return calc_bson_integer_size(j.m_data.m_value.number_integer);
+                if (JSON_HEDLEY_UNLIKELY(!integer_fits<std::int64_t>(j.m_data.m_value.number_integer)))
+                {
+                    throw_integer_out_of_range(j, "BSON", "int64");
+                }
+                return calc_bson_integer_size(static_cast<std::int64_t>(j.m_data.m_value.number_integer));
 
             case value_t::number_unsigned:
+                if (JSON_HEDLEY_UNLIKELY(!integer_fits_max<std::uint64_t>(j.m_data.m_value.number_unsigned)))
+                {
+                    throw_integer_out_of_range(j, "BSON", "uint64");
+                }
                 return calc_bson_unsigned_size(conditional_static_cast<std::uint64_t>(j.m_data.m_value.number_unsigned));
 
             case value_t::string:
@@ -24554,8 +24717,9 @@ class binary_writer
             case value_t::number_float:
                 return write_bson_double(name, j.m_data.m_value.number_float);
 
+            // calc_bson_value_size() checked that integers fit 64 bits
             case value_t::number_integer:
-                return write_bson_integer(name, j.m_data.m_value.number_integer);
+                return write_bson_integer(name, static_cast<std::int64_t>(j.m_data.m_value.number_integer));
 
             case value_t::number_unsigned:
                 return write_bson_unsigned(name, conditional_static_cast<std::uint64_t>(j.m_data.m_value.number_unsigned));
@@ -25062,7 +25226,7 @@ class binary_writer
         {
             return 'L';
         }
-        if (use_bjdata && std::is_unsigned<NumberType>::value)
+        if (use_bjdata && std::is_unsigned<NumberType>::value && integer_fits_max<std::uint64_t>(n))
         {
             return 'M';
         }
@@ -25187,14 +25351,16 @@ class binary_writer
     @brief checks whether a JSON number fits into @a TargetType
     @param[in] el a JSON number of either the signed or unsigned integer kind
     @return whether @a el's value can be represented by @a TargetType without
-            wrapping, regardless of which of the two kinds it is stored as
+            wrapping, regardless of which of the two kinds it is stored as;
+            false for a value that does not even fit the 64-bit type it is
+            read as (possible for number types wider than 64 bits)
     */
     template<typename TargetType>
     static bool bjdata_ndarray_value_in_range(const BasicJsonType& el)
     {
         return el.is_number_unsigned()
-               ? value_in_range_of<TargetType>(el.template get<std::uint64_t>())
-               : value_in_range_of<TargetType>(el.template get<std::int64_t>());
+               ? integer_fits_max<std::uint64_t>(el.m_data.m_value.number_unsigned) && value_in_range_of<TargetType>(el.template get<std::uint64_t>())
+               : integer_fits<std::int64_t>(el.m_data.m_value.number_integer) && value_in_range_of<TargetType>(el.template get<std::int64_t>());
     }
 
     /*!
@@ -25426,10 +25592,11 @@ class binary_writer
         for (const auto& el : dims)
         {
             // a dimension is read as an unsigned value below, so anything that
-            // is not a non-negative integer is rejected: a non-integer entry
-            // would pun unrelated bytes as the dimension, and a negative one
-            // would wrap into a nonsensical length
-            if (!el.is_number_integer() || (!el.is_number_unsigned() && el.template get<std::int64_t>() < 0))
+            // is not a non-negative integer in the range of std::uint64_t is
+            // rejected: a non-integer entry would pun unrelated bytes as the
+            // dimension, and a negative or wider one would wrap into a
+            // nonsensical length
+            if (!el.is_number_integer() || !bjdata_ndarray_value_in_range<std::uint64_t>(el))
             {
                 return true;
             }
@@ -25561,9 +25728,9 @@ class binary_writer
 
             case value_t::number_unsigned:
             {
-                if (j.m_data.m_value.number_unsigned > static_cast<typename BasicJsonType::number_unsigned_t>((std::numeric_limits<std::int64_t>::max)()))
+                if (JSON_HEDLEY_UNLIKELY(!integer_fits_max<std::int64_t>(j.m_data.m_value.number_unsigned)))
                 {
-                    JSON_THROW(out_of_range::create(exception_id::integer_too_large, concat("integer number ", std::to_string(j.m_data.m_value.number_unsigned), " cannot be represented by BON8 as it does not fit int64"), &j));
+                    throw_integer_out_of_range(j, "BON8", "int64");
                 }
                 write_bon8_integer(static_cast<std::int64_t>(j.m_data.m_value.number_unsigned));
                 string_open = false;
@@ -25572,6 +25739,10 @@ class binary_writer
 
             case value_t::number_integer:
             {
+                if (JSON_HEDLEY_UNLIKELY(!integer_fits<std::int64_t>(j.m_data.m_value.number_integer)))
+                {
+                    throw_integer_out_of_range(j, "BON8", "int64");
+                }
                 write_bon8_integer(static_cast<std::int64_t>(j.m_data.m_value.number_integer));
                 string_open = false;
                 break;
@@ -29456,7 +29627,7 @@ class serializer
         // without leading zeros
         if (abs_value < 10000000000000000u)
         {
-            const std::uint64_t value = abs_value;
+            const auto value = static_cast<std::uint64_t>(abs_value); // fits: abs_value < 10^16
             const std::uint64_t upper = value / 100000000u;
             const std::uint64_t first = dtoa_impl::eight_digit_bytes(upper != 0 ? upper : value);
             const auto leading = static_cast<unsigned>(count_leading_zeros(first) / 8); // (first is not 0)

tests/benchmarks/README.md

@@ -16,13 +16,6 @@ Micro-benchmarks for parsing, serialization and the binary formats, written with
 | `FromBinaryBuffer`, `FromBinaryFile` | read CBOR, MessagePack, UBJSON, BJData and BSON from a buffer or a `FILE*` |
 | `FromBinaryShape` | read deeply nested, container-heavy and scalar-heavy documents in every binary format |
 | `FromCborChunkedString` | read CBOR strings split into indefinite-length chunks |
-| `SaxParse` | parse with a SAX handler that only counts events, so no values are built |
-| `Copy`, `Destroy`, `Equal`, `Iterate` | copy, destroy, or compare a parsed document, or visit every value with range-based `for` loops |
-| `Flatten`, `FlattenOrdered`, `Unflatten` | `flatten()` for `json` and `ordered_json`, and `unflatten()` |
-| `Diff`, `Patch` | `diff()` against the document with every eighth scalar changed, and applying that patch |
-| `JsonPointerParse`, `JsonPointerToString`, `JsonPointerAt`, `JsonPointerContains` | the JSON pointers of every scalar in a document: parse them from strings, turn them back into strings, look them up with `at()` and `contains()` |
-| `GetVectorInt`, `GetVectorDouble`, `GetMap` | `get<std::vector<std::int64_t>>()`, `get<std::vector<double>>()` and `get<std::map<std::string, json>>()` on large arrays and a large flat object |
-| `ToJsonStrings` | create a `json` array from a `std::vector` of 100,000 strings, copied or moved |
 
 The input files are those of [nativejson-benchmark](https://github.com/miloyip/nativejson-benchmark) (`canada`,
 `citm_catalog`, `twitter`), a large `jeopardy` file, and number-heavy files (`floats`, `signed_ints`, ...).

tests/benchmarks/src/benchmarks.cpp

@@ -8,14 +8,11 @@
 
 #include <benchmark/benchmark.h>
 #include <nlohmann/json.hpp>
-#include <array>
-#include <cstdint>
-#include <deque>
 #include <fstream>
-#include <map>
+#include <array>
+#include <deque>
 #include <numeric>
 #include <set>
-#include <string>
 #include <vector>
 #include <test_data.hpp>
 
@@ -627,526 +624,6 @@ static void FromCborChunkedString(benchmark::State& state, const std::size_t chu
 
 BENCHMARK_CAPTURE(FromCborChunkedString, 10000 chunks, 10000);
 
-//////////////////////////////////////////////////////////////////////////////
-// SAX-parse JSON from string
-//
-// sax_parse() with a handler that does next to nothing runs the lexer and
-// parser without building values, so the gap to ParseString above is the cost
-// of building the DOM.
-//////////////////////////////////////////////////////////////////////////////
-
-static std::string read_file(const char* filename)
-{
-    std::ifstream f(filename);
-    return std::string((std::istreambuf_iterator<char>(f)), std::istreambuf_iterator<char>());
-}
-
-static json load_json(const char* filename)
-{
-    return json::parse(read_file(filename));
-}
-
-/// SAX handler that only counts the events, so that the handler costs next to nothing
-class counting_sax : public nlohmann::json_sax<json>
-{
-  public:
-    std::size_t events = 0;
-
-    bool null() override
-    {
-        return count();
-    }
-    bool boolean(bool /*val*/) override
-    {
-        return count();
-    }
-    bool number_integer(number_integer_t /*val*/) override
-    {
-        return count();
-    }
-    bool number_unsigned(number_unsigned_t /*val*/) override
-    {
-        return count();
-    }
-    bool number_float(number_float_t /*val*/, const string_t& /*s*/) override
-    {
-        return count();
-    }
-    bool string(string_t& /*val*/) override
-    {
-        return count();
-    }
-    bool binary(binary_t& /*val*/) override
-    {
-        return count();
-    }
-    bool start_object(std::size_t /*elements*/) override
-    {
-        return count();
-    }
-    bool key(string_t& /*val*/) override
-    {
-        return count();
-    }
-    bool end_object() override
-    {
-        return count();
-    }
-    bool start_array(std::size_t /*elements*/) override
-    {
-        return count();
-    }
-    bool end_array() override
-    {
-        return count();
-    }
-    bool parse_error(std::size_t /*position*/, const std::string& /*last_token*/, const json::exception& /*ex*/) override
-    {
-        return false;
-    }
-
-  private:
-    bool count()
-    {
-        ++events;
-        return true;
-    }
-};
-
-static void SaxParse(benchmark::State& state, const char* filename)
-{
-    const std::string str = read_file(filename);
-
-    for (auto _ : state)
-    {
-        counting_sax sax;
-        bool result = json::sax_parse(str, &sax);
-        benchmark::DoNotOptimize(result);
-        benchmark::DoNotOptimize(sax.events);
-    }
-
-    state.SetBytesProcessed(state.iterations() * str.size());
-}
-BENCHMARK_CAPTURE(SaxParse, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
-BENCHMARK_CAPTURE(SaxParse, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
-BENCHMARK_CAPTURE(SaxParse, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
-
-//////////////////////////////////////////////////////////////////////////////
-// work with values: copy, destroy, compare, iterate
-//
-// The parsed test files stand in for a document an application keeps around.
-// Each benchmark times one whole-document operation; setup and cleanup run
-// outside the timed section.
-//////////////////////////////////////////////////////////////////////////////
-
-static void Copy(benchmark::State& state, const char* filename)
-{
-    const json j = load_json(filename);
-
-    for (auto _ : state)
-    {
-        auto* copy = new json(j);
-
-        state.PauseTiming();
-        delete copy;
-        state.ResumeTiming();
-    }
-}
-BENCHMARK_CAPTURE(Copy, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
-BENCHMARK_CAPTURE(Copy, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
-BENCHMARK_CAPTURE(Copy, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
-
-static void Destroy(benchmark::State& state, const char* filename)
-{
-    const json j = load_json(filename);
-
-    for (auto _ : state)
-    {
-        state.PauseTiming();
-        auto* copy = new json(j);
-        state.ResumeTiming();
-
-        delete copy;
-    }
-}
-BENCHMARK_CAPTURE(Destroy, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
-BENCHMARK_CAPTURE(Destroy, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
-BENCHMARK_CAPTURE(Destroy, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
-
-static void Equal(benchmark::State& state, const char* filename)
-{
-    // two separate values, so that the comparison cannot stop at identical addresses
-    const json j = load_json(filename);
-    const json copy = j;
-
-    for (auto _ : state)
-    {
-        bool result = (j == copy);
-        benchmark::DoNotOptimize(result);
-    }
-}
-BENCHMARK_CAPTURE(Equal, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
-BENCHMARK_CAPTURE(Equal, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
-BENCHMARK_CAPTURE(Equal, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
-
-/// visit every value with range-based for loops, as client code walks a document
-static std::size_t count_values(const json& j)
-{
-    std::size_t result = 1;
-    if (j.is_structured())
-    {
-        for (const auto& element : j)
-        {
-            result += count_values(element);
-        }
-    }
-    return result;
-}
-
-static void Iterate(benchmark::State& state, const char* filename)
-{
-    const json j = load_json(filename);
-
-    for (auto _ : state)
-    {
-        std::size_t result = count_values(j);
-        benchmark::DoNotOptimize(result);
-    }
-
-    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(count_values(j)));
-}
-BENCHMARK_CAPTURE(Iterate, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
-BENCHMARK_CAPTURE(Iterate, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
-BENCHMARK_CAPTURE(Iterate, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
-
-//////////////////////////////////////////////////////////////////////////////
-// flatten and unflatten
-//////////////////////////////////////////////////////////////////////////////
-
-static void Flatten(benchmark::State& state, const char* filename)
-{
-    const json j = load_json(filename);
-
-    for (auto _ : state)
-    {
-        json flat = j.flatten();
-        benchmark::DoNotOptimize(flat);
-    }
-}
-BENCHMARK_CAPTURE(Flatten, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
-BENCHMARK_CAPTURE(Flatten, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
-BENCHMARK_CAPTURE(Flatten, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
-
-// ordered_json objects look keys up linearly, which flatten() used to do for
-// every value; canada (330,000 values in one flat object) is left out, as it
-// would take minutes with such versions
-static void FlattenOrdered(benchmark::State& state, const char* filename)
-{
-    const nlohmann::ordered_json j = nlohmann::ordered_json::parse(read_file(filename));
-
-    for (auto _ : state)
-    {
-        nlohmann::ordered_json flat = j.flatten();
-        benchmark::DoNotOptimize(flat);
-    }
-}
-BENCHMARK_CAPTURE(FlattenOrdered, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
-BENCHMARK_CAPTURE(FlattenOrdered, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
-
-static void Unflatten(benchmark::State& state, const char* filename)
-{
-    const json flat = load_json(filename).flatten();
-
-    for (auto _ : state)
-    {
-        json j = flat.unflatten();
-        benchmark::DoNotOptimize(j);
-    }
-}
-BENCHMARK_CAPTURE(Unflatten, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
-BENCHMARK_CAPTURE(Unflatten, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
-BENCHMARK_CAPTURE(Unflatten, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
-
-//////////////////////////////////////////////////////////////////////////////
-// diff and patch
-//
-// The target is the document with every eighth scalar changed, so the patch
-// has one "replace" operation per changed value and the structure stays the
-// same.
-//////////////////////////////////////////////////////////////////////////////
-
-static void change_every_eighth_scalar(json& j, std::size_t& counter)
-{
-    if (j.is_structured())
-    {
-        for (auto& element : j)
-        {
-            change_every_eighth_scalar(element, counter);
-        }
-        return;
-    }
-
-    if (++counter % 8 != 0)
-    {
-        return;
-    }
-
-    switch (j.type())
-    {
-        case json::value_t::number_integer:
-            j = j.get<json::number_integer_t>() + 1;
-            break;
-        case json::value_t::number_unsigned:
-            j = j.get<json::number_unsigned_t>() + 1;
-            break;
-        case json::value_t::number_float:
-            j = j.get<json::number_float_t>() + 0.5;
-            break;
-        case json::value_t::string:
-            j = j.get<std::string>() + "!";
-            break;
-        case json::value_t::boolean:
-            j = !j.get<bool>();
-            break;
-        case json::value_t::null:
-        case json::value_t::object:
-        case json::value_t::array:
-        case json::value_t::binary:
-        case json::value_t::discarded:
-        default:
-            j = 0;
-            break;
-    }
-}
-
-static json changed_copy(const json& j)
-{
-    json result = j;
-    std::size_t counter = 0;
-    change_every_eighth_scalar(result, counter);
-    return result;
-}
-
-static void Diff(benchmark::State& state, const char* filename)
-{
-    const json source = load_json(filename);
-    const json target = changed_copy(source);
-
-    for (auto _ : state)
-    {
-        json patch = json::diff(source, target);
-        benchmark::DoNotOptimize(patch);
-    }
-
-    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(json::diff(source, target).size()));
-}
-BENCHMARK_CAPTURE(Diff, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
-BENCHMARK_CAPTURE(Diff, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
-BENCHMARK_CAPTURE(Diff, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
-
-static void Patch(benchmark::State& state, const char* filename)
-{
-    const json source = load_json(filename);
-    const json patch = json::diff(source, changed_copy(source));
-
-    for (auto _ : state)
-    {
-        json result = source.patch(patch);
-        benchmark::DoNotOptimize(result);
-    }
-
-    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(patch.size()));
-}
-BENCHMARK_CAPTURE(Patch, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
-BENCHMARK_CAPTURE(Patch, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
-BENCHMARK_CAPTURE(Patch, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
-
-//////////////////////////////////////////////////////////////////////////////
-// JSON Pointer
-//
-// The pointers are those of every scalar in the document, i.e., the keys of
-// its flattened form.
-//////////////////////////////////////////////////////////////////////////////
-
-static std::vector<std::string> pointer_strings(const json& j)
-{
-    std::vector<std::string> result;
-    const json flat = j.flatten();
-    result.reserve(flat.size());
-    for (auto it = flat.begin(); it != flat.end(); ++it)
-    {
-        result.push_back(it.key());
-    }
-    return result;
-}
-
-static std::vector<json::json_pointer> pointers(const json& j)
-{
-    const std::vector<std::string> strings = pointer_strings(j);
-    std::vector<json::json_pointer> result;
-    result.reserve(strings.size());
-    for (const auto& s : strings)
-    {
-        result.emplace_back(s);
-    }
-    return result;
-}
-
-static void JsonPointerParse(benchmark::State& state, const char* filename)
-{
-    const std::vector<std::string> strings = pointer_strings(load_json(filename));
-
-    for (auto _ : state)
-    {
-        for (const auto& s : strings)
-        {
-            json::json_pointer ptr(s);
-            benchmark::DoNotOptimize(ptr);
-        }
-    }
-
-    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(strings.size()));
-}
-BENCHMARK_CAPTURE(JsonPointerParse, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
-BENCHMARK_CAPTURE(JsonPointerParse, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
-
-static void JsonPointerToString(benchmark::State& state, const char* filename)
-{
-    const std::vector<json::json_pointer> ptrs = pointers(load_json(filename));
-
-    for (auto _ : state)
-    {
-        for (const auto& ptr : ptrs)
-        {
-            std::string s = ptr.to_string();
-            benchmark::DoNotOptimize(s);
-        }
-    }
-
-    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(ptrs.size()));
-}
-BENCHMARK_CAPTURE(JsonPointerToString, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
-BENCHMARK_CAPTURE(JsonPointerToString, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
-
-static void JsonPointerAt(benchmark::State& state, const char* filename)
-{
-    const json j = load_json(filename);
-    const std::vector<json::json_pointer> ptrs = pointers(j);
-
-    for (auto _ : state)
-    {
-        for (const auto& ptr : ptrs)
-        {
-            const json& value = j.at(ptr);
-            benchmark::DoNotOptimize(&value);
-        }
-    }
-
-    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(ptrs.size()));
-}
-BENCHMARK_CAPTURE(JsonPointerAt, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
-BENCHMARK_CAPTURE(JsonPointerAt, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
-
-static void JsonPointerContains(benchmark::State& state, const char* filename)
-{
-    const json j = load_json(filename);
-    const std::vector<json::json_pointer> ptrs = pointers(j);
-
-    for (auto _ : state)
-    {
-        for (const auto& ptr : ptrs)
-        {
-            bool result = j.contains(ptr);
-            benchmark::DoNotOptimize(result);
-        }
-    }
-
-    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(ptrs.size()));
-}
-BENCHMARK_CAPTURE(JsonPointerContains, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
-BENCHMARK_CAPTURE(JsonPointerContains, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
-
-//////////////////////////////////////////////////////////////////////////////
-// conversions from and to C++ containers
-//////////////////////////////////////////////////////////////////////////////
-
-static void GetVectorInt(benchmark::State& state, const char* filename)
-{
-    const json j = load_json(filename);
-
-    for (auto _ : state)
-    {
-        auto v = j.get<std::vector<std::int64_t>>();
-        benchmark::DoNotOptimize(v);
-    }
-
-    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(j.size()));
-}
-BENCHMARK_CAPTURE(GetVectorInt, signed_ints, TEST_DATA_DIRECTORY "/regression/signed_ints.json");
-
-static void GetVectorDouble(benchmark::State& state, const char* filename)
-{
-    const json j = load_json(filename);
-
-    for (auto _ : state)
-    {
-        auto v = j.get<std::vector<double>>();
-        benchmark::DoNotOptimize(v);
-    }
-
-    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(j.size()));
-}
-BENCHMARK_CAPTURE(GetVectorDouble, floats, TEST_DATA_DIRECTORY "/regression/floats.json");
-
-// a large flat object: the flattened document, one member per scalar
-static void GetMap(benchmark::State& state, const char* filename)
-{
-    const json j = load_json(filename).flatten();
-
-    for (auto _ : state)
-    {
-        auto m = j.get<std::map<std::string, json>>();
-        benchmark::DoNotOptimize(m);
-    }
-
-    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(j.size()));
-}
-BENCHMARK_CAPTURE(GetMap, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
-
-/// 100,000 strings, each too long for the small string optimization
-static std::vector<std::string> make_strings()
-{
-    std::vector<std::string> result;
-    result.reserve(100000);
-    for (std::size_t i = 0; i < 100000; ++i)
-    {
-        result.push_back("a string that does not fit in place: " + std::to_string(i));
-    }
-    return result;
-}
-
-static void ToJsonStrings(benchmark::State& state, const bool move)
-{
-    const std::vector<std::string> strings = make_strings();
-
-    for (auto _ : state)
-    {
-        state.PauseTiming();
-        std::vector<std::string> input = strings;
-        state.ResumeTiming();
-
-        auto* j = move ? new json(std::move(input)) : new json(input);
-
-        state.PauseTiming();
-        delete j;
-        state.ResumeTiming();
-    }
-
-    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(strings.size()));
-}
-BENCHMARK_CAPTURE(ToJsonStrings, copy, false);
-BENCHMARK_CAPTURE(ToJsonStrings, move, true);
-
 // conversion of a JSON array into standard containers
 template<typename Container>
 static void GetArray(benchmark::State& state)

tests/src/unit-custom-array-type.cpp

@@ -9,7 +9,9 @@
 #include "doctest_compatibility.h"
 
 #include <nlohmann/json.hpp>
+using nlohmann::json;
 
+#include <cstdint>
 #include <deque>
 #include <map>
 #include <memory>
@@ -164,3 +166,47 @@ TEST_CASE("array type without at()")
     CHECK(j.at(no_at_json::json_pointer("/1")) == 2);
     CHECK_THROWS_AS(j.at(no_at_json::json_pointer("/3")), no_at_json::out_of_range);
 }
+
+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
+    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);
+        CHECK(deque_json::from_bon8(deque_json::to_bon8(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());
+    }
+}

tests/src/unit-custom-number-types.cpp

@@ -0,0 +1,367 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  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
+
+#include "doctest_compatibility.h"
+
+#include <nlohmann/json.hpp>
+
+#include <cstdint>
+#include <limits>
+#include <map>
+#include <string>
+#include <type_traits>
+#include <vector>
+
+#if JSON_HAS_THREE_WAY_COMPARISON
+    #include <compare>
+#endif
+
+namespace custom_number_types
+{
+
+// a signed integer of class type: std::is_signed is only true for arithmetic
+// types, so the library has to take the signedness from std::numeric_limits,
+// as it does for 128-bit and multiprecision integer classes such as
+// absl::int128 or boost::multiprecision::cpp_int
+class class_int
+{
+  public:
+    // trivial, like the 128-bit integer classes: the value is stored in a union
+    class_int() = default;
+
+    // implicit from built-in integers and explicit from floats, like absl::int128;
+    // non-template overloads (as absl::int128 has) because clang 3.4 and 3.5
+    // reject basic_json's defaulted data() for a number type with template
+    // constructors
+    class_int(int v) : value(v) {} // NOLINT(google-explicit-constructor,hicpp-explicit-conversions)
+    class_int(unsigned v) : value(v) {} // NOLINT(google-explicit-constructor,hicpp-explicit-conversions)
+    class_int(long v) : value(v) {} // NOLINT(google-explicit-constructor,hicpp-explicit-conversions)
+    class_int(unsigned long v) : value(static_cast<std::int64_t>(v)) {} // NOLINT(google-explicit-constructor,hicpp-explicit-conversions)
+    class_int(long long v) : value(v) {} // NOLINT(google-explicit-constructor,hicpp-explicit-conversions)
+    class_int(unsigned long long v) : value(static_cast<std::int64_t>(v)) {} // NOLINT(google-explicit-constructor,hicpp-explicit-conversions)
+    explicit class_int(double v) : value(static_cast<std::int64_t>(v)) {}
+
+    template<typename T, typename std::enable_if<std::is_arithmetic<T>::value, int>::type = 0>
+    explicit operator T() const
+    {
+        return static_cast<T>(value);
+    }
+
+    friend bool operator==(class_int lhs, class_int rhs)
+    {
+        return lhs.value == rhs.value;
+    }
+    friend bool operator!=(class_int lhs, class_int rhs)
+    {
+        return lhs.value != rhs.value;
+    }
+    friend bool operator<(class_int lhs, class_int rhs)
+    {
+        return lhs.value < rhs.value;
+    }
+#if JSON_HAS_THREE_WAY_COMPARISON
+    friend std::strong_ordering operator<=>(class_int lhs, class_int rhs) // *NOPAD*
+    {
+        return lhs.value <=> rhs.value; // *NOPAD*
+    }
+#endif
+
+  private:
+    std::int64_t value;
+};
+
+} // namespace custom_number_types
+
+using custom_number_types::class_int;
+
+namespace std
+{
+// only the members the library uses
+template<>
+class numeric_limits<class_int>
+{
+  public:
+    static constexpr bool is_signed = true;
+    static constexpr int digits = std::numeric_limits<std::int64_t>::digits;
+};
+} // namespace std
+
+namespace
+{
+
+using class_int_json = nlohmann::basic_json<std::map, std::vector, std::string, bool, class_int, std::uint64_t, double>;
+
+class_int_json make_class_int(std::int64_t v)
+{
+    class_int_json j(class_int_json::value_t::number_integer);
+    j.get_ref<class_int&>() = class_int(v);
+    return j;
+}
+
+} // namespace
+
+// the serializer cannot print an integer of class type, so doctest must not
+// try when an assertion fails
+namespace doctest
+{
+template<>
+struct StringMaker<class_int_json>
+{
+    static String convert(const class_int_json& j)
+    {
+        return j.type_name();
+    }
+};
+} // namespace doctest
+
+// __int128 as number type needs the std::numeric_limits (for the range checks)
+// and std::is_integral (for the serializer) specializations, which libc++
+// always provides and libstdc++ only outside strict ISO modes; the MSVC
+// standard library has none
+#if defined(__SIZEOF_INT128__) && (defined(_LIBCPP_VERSION) || defined(__GLIBCXX_TYPE_INT_N_0))
+    #define JSON_TEST_INT128_NUMBER_TYPES 1
+#else
+    #define JSON_TEST_INT128_NUMBER_TYPES 0
+#endif
+
+#if JSON_TEST_INT128_NUMBER_TYPES
+namespace
+{
+
+// __extension__ keeps -Wpedantic from flagging the non-standard type
+__extension__ typedef __int128 int128; // NOLINT(modernize-use-using)
+__extension__ typedef unsigned __int128 uint128; // NOLINT(modernize-use-using)
+
+static_assert(std::numeric_limits<int128>::digits == 127 && std::numeric_limits<uint128>::digits == 128 &&
+              std::is_integral<int128>::value && std::is_integral<uint128>::value, // NOLINT(misc-redundant-expression)
+              "__int128 is not fully supported by the standard library");
+
+using wide_json = nlohmann::basic_json<std::map, std::vector, std::string, bool, int128, uint128, double>;
+
+wide_json make_int(int128 v)
+{
+    wide_json j(wide_json::value_t::number_integer);
+    j.get_ref<int128&>() = v;
+    return j;
+}
+
+wide_json make_uint(uint128 v)
+{
+    wide_json j(wide_json::value_t::number_unsigned);
+    j.get_ref<uint128&>() = v;
+    return j;
+}
+
+wide_json wrap(const wide_json& value)
+{
+    wide_json o(wide_json::value_t::object);
+    o["v"] = value;
+    return o;
+}
+
+} // namespace
+
+TEST_CASE("custom number types: integers beyond 64 bits")
+{
+    using out_of_range = wide_json::out_of_range;
+
+    const int128 two_64 = static_cast<int128>(1) << 64;
+    const int128 two_100 = static_cast<int128>(1) << 100;
+    const int128 max_int64 = (std::numeric_limits<std::int64_t>::max)();
+    const int128 min_int64 = (std::numeric_limits<std::int64_t>::min)();
+    const uint128 max_uint64 = (std::numeric_limits<std::uint64_t>::max)();
+
+    // before the range checks, these values were silently truncated, e.g.,
+    // 2^100 was written as 0
+    const wide_json int_big = make_int(two_100);
+    const wide_json int_big_negative = make_int(-two_100);
+    const wide_json uint_big = make_uint(static_cast<uint128>(two_100));
+    std::vector<std::uint8_t> _;
+
+    SECTION("CBOR")
+    {
+        CHECK_THROWS_WITH_AS(_ = wide_json::to_cbor(int_big), "[json.exception.out_of_range.407] integer number 1267650600228229401496703205376 cannot be represented by CBOR as it does not fit [-2^64, 2^64-1]", out_of_range&);
+        CHECK_THROWS_WITH_AS(_ = wide_json::to_cbor(int_big_negative), "[json.exception.out_of_range.407] integer number -1267650600228229401496703205376 cannot be represented by CBOR as it does not fit [-2^64, 2^64-1]", out_of_range&);
+        CHECK_THROWS_WITH_AS(_ = wide_json::to_cbor(uint_big), "[json.exception.out_of_range.407] integer number 1267650600228229401496703205376 cannot be represented by CBOR as it does not fit uint64", out_of_range&);
+        // the extremes of the 128-bit types, whose digits are produced without
+        // negating the minimum as a whole
+        CHECK_THROWS_WITH_AS(_ = wide_json::to_cbor(make_int((std::numeric_limits<int128>::min)())), "[json.exception.out_of_range.407] integer number -170141183460469231731687303715884105728 cannot be represented by CBOR as it does not fit [-2^64, 2^64-1]", out_of_range&);
+        CHECK_THROWS_WITH_AS(_ = wide_json::to_cbor(make_int((std::numeric_limits<int128>::max)())), "[json.exception.out_of_range.407] integer number 170141183460469231731687303715884105727 cannot be represented by CBOR as it does not fit [-2^64, 2^64-1]", out_of_range&);
+        CHECK_THROWS_WITH_AS(_ = wide_json::to_cbor(make_uint((std::numeric_limits<uint128>::max)())), "[json.exception.out_of_range.407] integer number 340282366920938463463374607431768211455 cannot be represented by CBOR as it does not fit uint64", out_of_range&);
+        CHECK_THROWS_AS(_ = wide_json::to_cbor(make_int(two_64)), out_of_range&);
+        CHECK_THROWS_AS(_ = wide_json::to_cbor(make_int(-two_64 - 1)), out_of_range&);
+        CHECK_THROWS_AS(_ = wide_json::to_cbor(make_uint(static_cast<uint128>(max_uint64) + 1)), out_of_range&);
+
+        // CBOR's integers cover [-2^64, 2^64-1]
+        CHECK(wide_json::to_cbor(make_int(two_64 - 1)) == std::vector<std::uint8_t>({0x1B, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF}));
+        CHECK(wide_json::to_cbor(make_int(-two_64)) == std::vector<std::uint8_t>({0x3B, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF}));
+        CHECK(wide_json::to_cbor(make_uint(max_uint64)) == std::vector<std::uint8_t>({0x1B, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF}));
+    }
+
+    SECTION("MessagePack")
+    {
+        CHECK_THROWS_WITH_AS(_ = wide_json::to_msgpack(int_big), "[json.exception.out_of_range.407] integer number 1267650600228229401496703205376 cannot be represented by MessagePack as it does not fit [-2^63, 2^64-1]", out_of_range&);
+        CHECK_THROWS_WITH_AS(_ = wide_json::to_msgpack(int_big_negative), "[json.exception.out_of_range.407] integer number -1267650600228229401496703205376 cannot be represented by MessagePack as it does not fit [-2^63, 2^64-1]", out_of_range&);
+        CHECK_THROWS_WITH_AS(_ = wide_json::to_msgpack(uint_big), "[json.exception.out_of_range.407] integer number 1267650600228229401496703205376 cannot be represented by MessagePack as it does not fit uint64", out_of_range&);
+        CHECK_THROWS_AS(_ = wide_json::to_msgpack(make_int(two_64)), out_of_range&);
+        CHECK_THROWS_AS(_ = wide_json::to_msgpack(make_int(min_int64 - 1)), out_of_range&);
+
+        // MessagePack's integers cover [-2^63, 2^64-1]
+        CHECK(wide_json::to_msgpack(make_int(two_64 - 1)) == std::vector<std::uint8_t>({0xCF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF}));
+        CHECK(wide_json::to_msgpack(make_int(min_int64)) == std::vector<std::uint8_t>({0xD3, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}));
+        CHECK(wide_json::to_msgpack(make_uint(max_uint64)) == std::vector<std::uint8_t>({0xCF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF}));
+    }
+
+    SECTION("BSON")
+    {
+        // wrap() stores the value at /v, which JSON_DIAGNOSTICS adds to the message
+#if JSON_DIAGNOSTICS
+        CHECK_THROWS_WITH_AS(_ = wide_json::to_bson(wrap(int_big)), "[json.exception.out_of_range.407] (/v) integer number 1267650600228229401496703205376 cannot be represented by BSON as it does not fit int64", out_of_range&);
+        CHECK_THROWS_WITH_AS(_ = wide_json::to_bson(wrap(int_big_negative)), "[json.exception.out_of_range.407] (/v) integer number -1267650600228229401496703205376 cannot be represented by BSON as it does not fit int64", out_of_range&);
+        CHECK_THROWS_WITH_AS(_ = wide_json::to_bson(wrap(uint_big)), "[json.exception.out_of_range.407] (/v) integer number 1267650600228229401496703205376 cannot be represented by BSON as it does not fit uint64", out_of_range&);
+#else
+        CHECK_THROWS_WITH_AS(_ = wide_json::to_bson(wrap(int_big)), "[json.exception.out_of_range.407] integer number 1267650600228229401496703205376 cannot be represented by BSON as it does not fit int64", out_of_range&);
+        CHECK_THROWS_WITH_AS(_ = wide_json::to_bson(wrap(int_big_negative)), "[json.exception.out_of_range.407] integer number -1267650600228229401496703205376 cannot be represented by BSON as it does not fit int64", out_of_range&);
+        CHECK_THROWS_WITH_AS(_ = wide_json::to_bson(wrap(uint_big)), "[json.exception.out_of_range.407] integer number 1267650600228229401496703205376 cannot be represented by BSON as it does not fit uint64", out_of_range&);
+#endif
+        CHECK_THROWS_AS(_ = wide_json::to_bson(wrap(make_int(max_int64 + 1))), out_of_range&);
+        CHECK_THROWS_AS(_ = wide_json::to_bson(wrap(make_int(min_int64 - 1))), out_of_range&);
+
+        // nested values are checked as well, before anything is written
+        wide_json nested(wide_json::value_t::object);
+        nested["a"] = wide_json::array({wrap(int_big)});
+        std::vector<std::uint8_t> out;
+        CHECK_THROWS_AS(wide_json::to_bson(nested, out), out_of_range&);
+        CHECK(out.empty());
+
+        CHECK(wide_json::from_bson(wide_json::to_bson(wrap(make_int(max_int64)))) == wrap(make_int(max_int64)));
+        CHECK(wide_json::from_bson(wide_json::to_bson(wrap(make_int(min_int64)))) == wrap(make_int(min_int64)));
+        CHECK_NOTHROW(wide_json::to_bson(wrap(make_uint(max_uint64))));
+    }
+
+    SECTION("BON8")
+    {
+        CHECK_THROWS_WITH_AS(_ = wide_json::to_bon8(int_big), "[json.exception.out_of_range.407] integer number 1267650600228229401496703205376 cannot be represented by BON8 as it does not fit int64", out_of_range&);
+        CHECK_THROWS_WITH_AS(_ = wide_json::to_bon8(int_big_negative), "[json.exception.out_of_range.407] integer number -1267650600228229401496703205376 cannot be represented by BON8 as it does not fit int64", out_of_range&);
+        CHECK_THROWS_WITH_AS(_ = wide_json::to_bon8(uint_big), "[json.exception.out_of_range.407] integer number 1267650600228229401496703205376 cannot be represented by BON8 as it does not fit int64", out_of_range&);
+        CHECK_THROWS_AS(_ = wide_json::to_bon8(make_int(max_int64 + 1)), out_of_range&);
+        CHECK_THROWS_AS(_ = wide_json::to_bon8(make_int(min_int64 - 1)), out_of_range&);
+
+        CHECK(wide_json::from_bon8(wide_json::to_bon8(make_int(max_int64))) == make_int(max_int64));
+        CHECK(wide_json::from_bon8(wide_json::to_bon8(make_int(min_int64))) == make_int(min_int64));
+    }
+
+    SECTION("UBJSON and BJData")
+    {
+        // integers beyond 64 bits are written exactly as high-precision numbers
+        const std::string digits = "1267650600228229401496703205376";
+        std::vector<std::uint8_t> expected = {'H', 'i', static_cast<std::uint8_t>(digits.size())};
+        expected.insert(expected.end(), digits.begin(), digits.end());
+        CHECK(wide_json::to_ubjson(int_big) == expected);
+        CHECK(wide_json::to_ubjson(uint_big) == expected);
+        CHECK(wide_json::to_bjdata(int_big) == expected);
+        // BJData's uint64 marker 'M' was used for any unsigned value beyond
+        // int64, which truncated the ones beyond 64 bits
+        CHECK(wide_json::to_bjdata(uint_big) == expected);
+
+        // the uint64 marker is still used where the value fits
+        CHECK(wide_json::to_bjdata(make_uint(max_uint64)) == std::vector<std::uint8_t>({'M', 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF}));
+
+        // the elements of an optimized container are written the same way;
+        // BJData does not allow 'H' as the type of an optimized container
+        std::vector<std::uint8_t> expected_ubjson_array = {'[', '$', 'H', '#', 'i', 2};
+        std::vector<std::uint8_t> expected_bjdata_array = {'[', '#', 'i', 2};
+        for (int i = 0; i < 2; ++i)
+        {
+            expected_ubjson_array.insert(expected_ubjson_array.end(), expected.begin() + 1, expected.end());
+            expected_bjdata_array.insert(expected_bjdata_array.end(), expected.begin(), expected.end());
+        }
+        CHECK(wide_json::to_ubjson(wide_json::array({uint_big, uint_big}), true, true) == expected_ubjson_array);
+        CHECK(wide_json::to_bjdata(wide_json::array({uint_big, uint_big}), true, true) == expected_bjdata_array);
+    }
+
+    SECTION("BJData ND-array")
+    {
+        // an ND-array element beyond 64 bits does not fit any dtype, so the
+        // annotated object is written as a plain object instead of truncating
+        // the element into range
+        wide_json element(wide_json::value_t::object);
+        element["_ArrayType_"] = "uint8";
+        element["_ArraySize_"] = wide_json::array({make_uint(2), make_uint(1)});
+        element["_ArrayData_"] = wide_json::array({make_uint(1), make_uint(static_cast<uint128>(two_64) + 1)});
+        const auto element_bytes = wide_json::to_bjdata(element, true, true);
+        REQUIRE(!element_bytes.empty());
+        CHECK(element_bytes[0] == '{');
+
+        wide_json signed_element = element;
+        signed_element["_ArrayType_"] = "int8";
+        signed_element["_ArrayData_"] = wide_json::array({make_int(1), make_int(-two_64 + 1)});
+        const auto signed_element_bytes = wide_json::to_bjdata(signed_element, true, true);
+        REQUIRE(!signed_element_bytes.empty());
+        CHECK(signed_element_bytes[0] == '{');
+
+        // the same for a dimension beyond 64 bits, which wrapped into a
+        // dimension matching the size of _ArrayData_ (here: 1)
+        wide_json dimension = element;
+        dimension["_ArraySize_"] = wide_json::array({make_uint(2), make_uint(static_cast<uint128>(two_64) + 1)});
+        dimension["_ArrayData_"] = wide_json::array({make_uint(1), make_uint(2)});
+        const auto dimension_bytes = wide_json::to_bjdata(dimension, true, true);
+        REQUIRE(!dimension_bytes.empty());
+        CHECK(dimension_bytes[0] == '{');
+
+        // in range, the ND-array is still written
+        wide_json fits = element;
+        fits["_ArrayData_"] = wide_json::array({make_uint(1), make_uint(2)});
+        const auto fits_bytes = wide_json::to_bjdata(fits, true, true);
+        REQUIRE(!fits_bytes.empty());
+        CHECK(fits_bytes[0] == '[');
+    }
+}
+
+#endif
+
+TEST_CASE("custom number types")
+{
+    SECTION("signed integer of class type compared with a float")
+    {
+        // std::is_signed is false for a class type, which made the comparison
+        // treat any float below zero as less than every integer
+        const class_int_json minus_five = make_class_int(-5);
+        const class_int_json minus_two = make_class_int(-2);
+        const class_int_json five = make_class_int(5);
+        const class_int_json minus_two_and_a_half = -2.5;
+        const class_int_json two_and_a_half = 2.5;
+        const class_int_json huge_negative = -1e30;
+        const class_int_json huge_positive = 1e30;
+
+        CHECK(minus_five < minus_two_and_a_half);
+        CHECK_FALSE(minus_two_and_a_half < minus_five);
+        CHECK(minus_two_and_a_half > minus_five);
+        CHECK(minus_five <= minus_two_and_a_half);
+        CHECK(minus_two_and_a_half >= minus_five);
+        CHECK(minus_five != minus_two_and_a_half);
+
+        CHECK(minus_two_and_a_half < minus_two);
+        CHECK_FALSE(minus_two < minus_two_and_a_half);
+
+        CHECK(two_and_a_half < five);
+        CHECK(minus_five < two_and_a_half);
+
+        // floats beyond the integer's range
+        CHECK(huge_negative < minus_five);
+        CHECK_FALSE(minus_five < huge_negative);
+        CHECK(five < huge_positive);
+        CHECK_FALSE(huge_positive < five);
+
+        // equality
+        const class_int_json minus_two_float = -2.0;
+        CHECK(minus_two == minus_two_float);
+        CHECK(minus_two_float == minus_two);
+    }
+
+}

tests/src/unit-msgpack-custom-types.cpp

@@ -0,0 +1,296 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  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
+
+// MessagePack tests with basic_json specializations other than nlohmann::json;
+// they are kept apart from unit-msgpack.cpp because every specialization adds
+// many sections to the object file, and MinGW cannot link objects with more
+// than 65535 sections (see the clang job in .github/workflows/windows.yml)
+
+#include "doctest_compatibility.h"
+
+#include <nlohmann/json.hpp>
+using nlohmann::json;
+
+#include <cstdint> // SIZE_MAX, UINT32_MAX
+#include <functional>
+#include <limits>
+#include <map>
+#include <memory>
+#include <string>
+#include <utility>
+#include <vector>
+
+// the fake sizes below do not fit into a 32-bit std::size_t
+// with clang and libstdc++ 10, the std::filesystem::path conversion that
+// C++17 builds consider for every string type is ambiguous for a class
+// derived from std::string, so the string case is not tested there
+#if !(defined(__clang__) && defined(_GLIBCXX_RELEASE) && _GLIBCXX_RELEASE < 11)
+    #define JSON_TEST_BEYOND_UINT32_STRING 1
+#endif
+
+#if SIZE_MAX > UINT32_MAX
+template<typename T, typename A = std::allocator<T>>
+struct huge_array : std::vector<T, A>
+{
+    using base = std::vector<T, A>;
+    using base::base;
+
+    bool fake_size = false;
+
+    std::size_t size() const noexcept
+    {
+        if (fake_size)
+        {
+            return (std::numeric_limits<std::uint32_t>::max)() + 1ULL;
+        }
+
+        return base::size();
+    }
+};
+
+using huge_array_json = nlohmann::json::with_array_t<huge_array>;
+
+TEST_CASE("MessagePack Size above uint32 for array")
+{
+    huge_array_json j = huge_array_json::array();
+
+    j.push_back(1);
+    j.push_back(2);
+    j.push_back(3);
+
+    auto& array = j.get_ref<huge_array_json::array_t&>();
+    array.fake_size = true;
+
+    // write into a caller-owned vector: to_msgpack(j) reserves space based on
+    // the (faked) element count, which fails with bad_alloc on Windows
+    std::vector<std::uint8_t> result;
+    CHECK_THROWS_WITH_AS(
+        huge_array_json::to_msgpack(j, result),
+        "[json.exception.out_of_range.412] MessagePack length 4294967296 exceeds maximum of 4294967295",
+        json::out_of_range&);
+
+    array.fake_size = false;
+}
+
+template<typename K, typename V,
+         typename C = std::less<K>,
+         typename A = std::allocator<std::pair<const K, V>>>
+                                     struct huge_map : std::map<K, V, C, A>
+{
+    using base = std::map<K, V, C, A>;
+    using base::base;
+
+    bool fake_size = false;
+
+    std::size_t size() const noexcept
+    {
+        if (fake_size)
+        {
+            return static_cast<std::size_t>(UINT32_MAX) + 1ULL;
+        }
+
+        return base::size();
+    }
+};
+
+using huge_object_json = nlohmann::json::with_object_t<huge_map>;
+
+TEST_CASE("MessagePack Size above uint32 for object")
+{
+
+    huge_object_json j = huge_object_json::object();
+
+    j["one"] = 1;
+    j["two"] = 2;
+
+    auto& object = j.get_ref<huge_object_json::object_t&>();
+    object.fake_size = true;
+
+    // write into a caller-owned vector: to_msgpack(j) reserves space based on
+    // the (faked) element count, which fails with bad_alloc on Windows
+    std::vector<std::uint8_t> result;
+    CHECK_THROWS_WITH_AS(
+        huge_object_json::to_msgpack(j, result),
+        "[json.exception.out_of_range.412] MessagePack length 4294967296 exceeds maximum of 4294967295",
+        json::out_of_range&);
+
+    object.fake_size = false;
+}
+
+#ifdef JSON_TEST_BEYOND_UINT32_STRING
+struct huge_string : std::string
+{
+    using std::string::string;
+
+    std::size_t size() const noexcept // NOLINT(readability-convert-member-functions-to-static)
+    {
+        return static_cast<std::size_t>(UINT32_MAX) + 1ULL;
+    }
+};
+
+using huge_string_json = nlohmann::json::with_string_t<huge_string>;
+
+TEST_CASE("MessagePack Size above uint32 for string")
+{
+    const huge_string_json j = "hello";
+
+    CHECK_THROWS_WITH_AS(
+        huge_string_json::to_msgpack(j),
+        "[json.exception.out_of_range.412] MessagePack length 4294967296 exceeds maximum of 4294967295",
+        json::out_of_range&);
+}
+#endif
+
+struct huge_binary : std::vector<std::uint8_t>
+{
+    using std::vector<std::uint8_t>::vector;
+
+    std::size_t size() const noexcept // NOLINT(readability-convert-member-functions-to-static)
+    {
+        return static_cast<std::size_t>(UINT32_MAX) + 1ULL;
+    }
+};
+
+using huge_binary_json = nlohmann::json::with_binary_t<huge_binary>;
+
+TEST_CASE("MessagePack Size above uint32 for binary")
+{
+
+    huge_binary_json j = huge_binary_json::binary(huge_binary{});
+
+    j.get_binary().push_back(0x01);
+    j.get_binary().push_back(0x02);
+
+    CHECK_THROWS_WITH_AS(
+        huge_binary_json::to_msgpack(j),
+        "[json.exception.out_of_range.412] MessagePack length 4294967296 exceeds maximum of 4294967295",
+        json::out_of_range&);
+}
+#endif
+
+namespace
+{
+// types that report a size beyond UINT32_MAX without allocating that much
+// memory, so the MessagePack length limit can be tested cheaply; see the
+// similar types in unit-bson.cpp
+std::size_t beyond_uint32_size()
+{
+    return static_cast<std::size_t>((std::numeric_limits<std::uint32_t>::max)()) + 1;
+}
+
+class beyond_uint32_binary_t : public std::vector<std::uint8_t>
+{
+  public:
+    using std::vector<std::uint8_t>::vector;
+
+    size_type size() const noexcept // NOLINT(readability-convert-member-functions-to-static)
+    {
+        return beyond_uint32_size();
+    }
+};
+
+#ifdef JSON_TEST_BEYOND_UINT32_STRING
+class beyond_uint32_string_t : public std::string
+{
+  public:
+    using std::string::string;
+
+    size_type size() const noexcept // NOLINT(readability-convert-member-functions-to-static)
+    {
+        return beyond_uint32_size();
+    }
+};
+
+using beyond_uint32_string_json = nlohmann::json::with_string_t<beyond_uint32_string_t>;
+#endif
+
+using beyond_uint32_binary_json = nlohmann::json::with_binary_t<beyond_uint32_binary_t>;
+} // namespace
+
+TEST_CASE("MessagePack lengths beyond UINT32_MAX cannot be serialized")
+{
+    // MessagePack stores the length of a string, binary value, array, or
+    // object in at most 32 bits; a larger one used to be written without any
+    // length at all
+#if SIZE_MAX > UINT32_MAX
+    {
+        const char* const expected = "[json.exception.out_of_range.412] MessagePack length 4294967296 exceeds maximum of 4294967295";
+
+        const beyond_uint32_binary_json binary = beyond_uint32_binary_json::binary(beyond_uint32_binary_t{});
+        CHECK_THROWS_WITH_AS(beyond_uint32_binary_json::to_msgpack(binary), expected, beyond_uint32_binary_json::out_of_range&);
+
+        const beyond_uint32_binary_json ext = beyond_uint32_binary_json::binary(beyond_uint32_binary_t{}, 42);
+        CHECK_THROWS_WITH_AS(beyond_uint32_binary_json::to_msgpack(ext), expected, beyond_uint32_binary_json::out_of_range&);
+
+#ifdef JSON_TEST_BEYOND_UINT32_STRING
+        // created from its type rather than from a beyond_uint32_string_t:
+        // that would consider the std::filesystem::path conversion, which
+        // libstdc++ 10 cannot decide for a class derived from std::string
+        const beyond_uint32_string_json string(beyond_uint32_string_json::value_t::string);
+        CHECK_THROWS_WITH_AS(beyond_uint32_string_json::to_msgpack(string), expected, beyond_uint32_string_json::out_of_range&);
+#endif
+    }
+#endif
+}
+
+TEST_CASE("MessagePack numbers use the active union member (see #5644)")
+{
+    // when number_integer_t is narrower than number_unsigned_t, to_msgpack()
+    // used to read the union member that was not the active one, writing
+    // wrong bytes for some values; std::int64_t/std::uint64_t (the default
+    // types, where both members have the same width) were not affected
+    using int32_json = nlohmann::json::with_integers_t<std::int32_t, std::uint64_t>;
+    using int16_json = nlohmann::json::with_integers_t<std::int16_t, std::uint64_t>;
+
+    SECTION("number_integer_t = std::int32_t")
+    {
+        SECTION("6442450944 (uint 64; the low 32 bits used to be sign-extended)")
+        {
+            const int32_json j = 6442450944ULL;
+            CHECK(j.is_number_unsigned());
+
+            std::vector<uint8_t> const expected{0xcf, 0x00, 0x00, 0x00, 0x01, 0x80, 0x00, 0x00, 0x00};
+            const auto result = int32_json::to_msgpack(j);
+            CHECK(result == expected);
+            CHECK(int32_json::from_msgpack(result) == j);
+        }
+
+        SECTION("4294967496 (uint 64; the low 32 bits used to be the whole value)")
+        {
+            const int32_json j = 4294967496ULL;
+            CHECK(j.is_number_unsigned());
+
+            std::vector<uint8_t> const expected{0xcf, 0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0xc8};
+            const auto result = int32_json::to_msgpack(j);
+            CHECK(result == expected);
+            CHECK(int32_json::from_msgpack(result) == j);
+        }
+    }
+
+    SECTION("number_integer_t = std::int16_t, 98304 (uint 32)")
+    {
+        const int16_json j = 98304ULL;
+        CHECK(j.is_number_unsigned());
+
+        std::vector<uint8_t> const expected{0xce, 0x00, 0x01, 0x80, 0x00};
+        const auto result = int16_json::to_msgpack(j);
+        CHECK(result == expected);
+        CHECK(int16_json::from_msgpack(result) == j);
+    }
+
+    SECTION("default types (std::int64_t/std::uint64_t) are unaffected")
+    {
+        const json j = 4294967496ULL;
+        CHECK(j.is_number_unsigned());
+
+        std::vector<uint8_t> const expected{0xcf, 0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0xc8};
+        const auto result = json::to_msgpack(j);
+        CHECK(result == expected);
+        CHECK(json::from_msgpack(result) == j);
+    }
+}

tests/src/unit-msgpack.cpp

@@ -2173,276 +2173,6 @@ TEST_CASE("MessagePack roundtrips" * doctest::skip())
     }
 }
 
-// the fake sizes below do not fit into a 32-bit std::size_t
-// with clang and libstdc++ 10, the std::filesystem::path conversion that
-// C++17 builds consider for every string type is ambiguous for a class
-// derived from std::string, so the string case is not tested there
-#if !(defined(__clang__) && defined(_GLIBCXX_RELEASE) && _GLIBCXX_RELEASE < 11)
-    #define JSON_TEST_BEYOND_UINT32_STRING 1
-#endif
-
-#if SIZE_MAX > UINT32_MAX
-template<typename T, typename A = std::allocator<T>>
-struct huge_array : std::vector<T, A>
-{
-    using base = std::vector<T, A>;
-    using base::base;
-
-    bool fake_size = false;
-
-    std::size_t size() const noexcept
-    {
-        if (fake_size)
-        {
-            return (std::numeric_limits<std::uint32_t>::max)() + 1ULL;
-        }
-
-        return base::size();
-    }
-};
-
-using huge_array_json = nlohmann::json::with_array_t<huge_array>;
-
-TEST_CASE("MessagePack Size above uint32 for array")
-{
-    huge_array_json j = huge_array_json::array();
-
-    j.push_back(1);
-    j.push_back(2);
-    j.push_back(3);
-
-    auto& array = j.get_ref<huge_array_json::array_t&>();
-    array.fake_size = true;
-
-    // write into a caller-owned vector: to_msgpack(j) reserves space based on
-    // the (faked) element count, which fails with bad_alloc on Windows
-    std::vector<std::uint8_t> result;
-    CHECK_THROWS_WITH_AS(
-        huge_array_json::to_msgpack(j, result),
-        "[json.exception.out_of_range.412] MessagePack length 4294967296 exceeds maximum of 4294967295",
-        json::out_of_range&);
-
-    array.fake_size = false;
-}
-
-template<typename K, typename V,
-         typename C = std::less<K>,
-         typename A = std::allocator<std::pair<const K, V>>>
-                                     struct huge_map : std::map<K, V, C, A>
-{
-    using base = std::map<K, V, C, A>;
-    using base::base;
-
-    bool fake_size = false;
-
-    std::size_t size() const noexcept
-    {
-        if (fake_size)
-        {
-            return static_cast<std::size_t>(UINT32_MAX) + 1ULL;
-        }
-
-        return base::size();
-    }
-};
-
-using huge_object_json = nlohmann::json::with_object_t<huge_map>;
-
-TEST_CASE("MessagePack Size above uint32 for object")
-{
-
-    huge_object_json j = huge_object_json::object();
-
-    j["one"] = 1;
-    j["two"] = 2;
-
-    auto& object = j.get_ref<huge_object_json::object_t&>();
-    object.fake_size = true;
-
-    // write into a caller-owned vector: to_msgpack(j) reserves space based on
-    // the (faked) element count, which fails with bad_alloc on Windows
-    std::vector<std::uint8_t> result;
-    CHECK_THROWS_WITH_AS(
-        huge_object_json::to_msgpack(j, result),
-        "[json.exception.out_of_range.412] MessagePack length 4294967296 exceeds maximum of 4294967295",
-        json::out_of_range&);
-
-    object.fake_size = false;
-}
-
-#ifdef JSON_TEST_BEYOND_UINT32_STRING
-struct huge_string : std::string
-{
-    using std::string::string;
-
-    std::size_t size() const noexcept // NOLINT(readability-convert-member-functions-to-static)
-    {
-        return static_cast<std::size_t>(UINT32_MAX) + 1ULL;
-    }
-};
-
-using huge_string_json = nlohmann::json::with_string_t<huge_string>;
-
-TEST_CASE("MessagePack Size above uint32 for string")
-{
-    const huge_string_json j = "hello";
-
-    CHECK_THROWS_WITH_AS(
-        huge_string_json::to_msgpack(j),
-        "[json.exception.out_of_range.412] MessagePack length 4294967296 exceeds maximum of 4294967295",
-        json::out_of_range&);
-}
-#endif
-
-struct huge_binary : std::vector<std::uint8_t>
-{
-    using std::vector<std::uint8_t>::vector;
-
-    std::size_t size() const noexcept // NOLINT(readability-convert-member-functions-to-static)
-    {
-        return static_cast<std::size_t>(UINT32_MAX) + 1ULL;
-    }
-};
-
-using huge_binary_json = nlohmann::json::with_binary_t<huge_binary>;
-
-TEST_CASE("MessagePack Size above uint32 for binary")
-{
-
-    huge_binary_json j = huge_binary_json::binary(huge_binary{});
-
-    j.get_binary().push_back(0x01);
-    j.get_binary().push_back(0x02);
-
-    CHECK_THROWS_WITH_AS(
-        huge_binary_json::to_msgpack(j),
-        "[json.exception.out_of_range.412] MessagePack length 4294967296 exceeds maximum of 4294967295",
-        json::out_of_range&);
-}
-#endif
-
-namespace
-{
-// types that report a size beyond UINT32_MAX without allocating that much
-// memory, so the MessagePack length limit can be tested cheaply; see the
-// similar types in unit-bson.cpp
-std::size_t beyond_uint32_size()
-{
-    return static_cast<std::size_t>((std::numeric_limits<std::uint32_t>::max)()) + 1;
-}
-
-class beyond_uint32_binary_t : public std::vector<std::uint8_t>
-{
-  public:
-    using std::vector<std::uint8_t>::vector;
-
-    size_type size() const noexcept // NOLINT(readability-convert-member-functions-to-static)
-    {
-        return beyond_uint32_size();
-    }
-};
-
-#ifdef JSON_TEST_BEYOND_UINT32_STRING
-class beyond_uint32_string_t : public std::string
-{
-  public:
-    using std::string::string;
-
-    size_type size() const noexcept // NOLINT(readability-convert-member-functions-to-static)
-    {
-        return beyond_uint32_size();
-    }
-};
-
-using beyond_uint32_string_json = nlohmann::json::with_string_t<beyond_uint32_string_t>;
-#endif
-
-using beyond_uint32_binary_json = nlohmann::json::with_binary_t<beyond_uint32_binary_t>;
-} // namespace
-
-TEST_CASE("MessagePack lengths beyond UINT32_MAX cannot be serialized")
-{
-    // MessagePack stores the length of a string, binary value, array, or
-    // object in at most 32 bits; a larger one used to be written without any
-    // length at all
-#if SIZE_MAX > UINT32_MAX
-    {
-        const char* const expected = "[json.exception.out_of_range.412] MessagePack length 4294967296 exceeds maximum of 4294967295";
-
-        const beyond_uint32_binary_json binary = beyond_uint32_binary_json::binary(beyond_uint32_binary_t{});
-        CHECK_THROWS_WITH_AS(beyond_uint32_binary_json::to_msgpack(binary), expected, beyond_uint32_binary_json::out_of_range&);
-
-        const beyond_uint32_binary_json ext = beyond_uint32_binary_json::binary(beyond_uint32_binary_t{}, 42);
-        CHECK_THROWS_WITH_AS(beyond_uint32_binary_json::to_msgpack(ext), expected, beyond_uint32_binary_json::out_of_range&);
-
-#ifdef JSON_TEST_BEYOND_UINT32_STRING
-        // created from its type rather than from a beyond_uint32_string_t:
-        // that would consider the std::filesystem::path conversion, which
-        // libstdc++ 10 cannot decide for a class derived from std::string
-        const beyond_uint32_string_json string(beyond_uint32_string_json::value_t::string);
-        CHECK_THROWS_WITH_AS(beyond_uint32_string_json::to_msgpack(string), expected, beyond_uint32_string_json::out_of_range&);
-#endif
-    }
-#endif
-}
-
-TEST_CASE("MessagePack numbers use the active union member (see #5644)")
-{
-    // when number_integer_t is narrower than number_unsigned_t, to_msgpack()
-    // used to read the union member that was not the active one, writing
-    // wrong bytes for some values; std::int64_t/std::uint64_t (the default
-    // types, where both members have the same width) were not affected
-    using int32_json = nlohmann::json::with_integers_t<std::int32_t, std::uint64_t>;
-    using int16_json = nlohmann::json::with_integers_t<std::int16_t, std::uint64_t>;
-
-    SECTION("number_integer_t = std::int32_t")
-    {
-        SECTION("6442450944 (uint 64; the low 32 bits used to be sign-extended)")
-        {
-            const int32_json j = 6442450944ULL;
-            CHECK(j.is_number_unsigned());
-
-            std::vector<uint8_t> const expected{0xcf, 0x00, 0x00, 0x00, 0x01, 0x80, 0x00, 0x00, 0x00};
-            const auto result = int32_json::to_msgpack(j);
-            CHECK(result == expected);
-            CHECK(int32_json::from_msgpack(result) == j);
-        }
-
-        SECTION("4294967496 (uint 64; the low 32 bits used to be the whole value)")
-        {
-            const int32_json j = 4294967496ULL;
-            CHECK(j.is_number_unsigned());
-
-            std::vector<uint8_t> const expected{0xcf, 0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0xc8};
-            const auto result = int32_json::to_msgpack(j);
-            CHECK(result == expected);
-            CHECK(int32_json::from_msgpack(result) == j);
-        }
-    }
-
-    SECTION("number_integer_t = std::int16_t, 98304 (uint 32)")
-    {
-        const int16_json j = 98304ULL;
-        CHECK(j.is_number_unsigned());
-
-        std::vector<uint8_t> const expected{0xce, 0x00, 0x01, 0x80, 0x00};
-        const auto result = int16_json::to_msgpack(j);
-        CHECK(result == expected);
-        CHECK(int16_json::from_msgpack(result) == j);
-    }
-
-    SECTION("default types (std::int64_t/std::uint64_t) are unaffected")
-    {
-        const json j = 4294967496ULL;
-        CHECK(j.is_number_unsigned());
-
-        std::vector<uint8_t> const expected{0xcf, 0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0xc8};
-        const auto result = json::to_msgpack(j);
-        CHECK(result == expected);
-        CHECK(json::from_msgpack(result) == j);
-    }
-}
-
 TEST_CASE("MessagePack large strings and binaries (chunked reader)")
 {
     // get_msgpack_string()/get_msgpack_binary() both read through get_binary(),

tests/src/unit-regression3.cpp

@@ -43,7 +43,6 @@ using ordered_json = nlohmann::ordered_json;
 #endif
 
 #include <cstdio>
-#include <deque>
 #include <list>
 #include <type_traits>
 #include <utility>
@@ -867,52 +866,6 @@ 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::json::with_array_t<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);
-        CHECK(deque_json::from_bon8(deque_json::to_bon8(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());
-    }
-}
-
 TEST_CASE("issue #5317 - nested indefinite-length CBOR string chunks are rejected")
 {
     json _;