Unflatten in time and memory linear in the pointer depth (#5793)

* Unflatten in time and memory linear in the pointer depth

#5443 made unflatten() decide between arrays and objects independently
of the iteration order by collecting the pointer prefixes that have a
reference token 0 below them in a std::set<std::vector<string_t>>.
Every such prefix was stored as a copy of all its reference tokens, and
get_and_create() compared whole prefix vectors at every step, so
unflattening a pointer of depth d took time and memory quadratic in d:
a 10,000-level array pointer took 18 s and 1.3 GB, a 100,000-level one
did not finish.

The prefixes are now numbered nodes of a tree, so each is stored once
and get_and_create() follows the tree token by token. The result is
unchanged, including its independence of the iteration order.

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

* Initialize prefix_tree members to satisfy -Weffc++

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

* Move prefix_tree setup and child insertion into member functions

The constructor now creates the root node, add_child() inserts a
reference token below a prefix and returns the child's number, and
find_child() looks one up for get_and_create().

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

---------

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

docs/mkdocs/docs/api/basic_json/binary_t.md

@@ -64,18 +64,7 @@ values of that type directly to a `basic_json` instance, and they will automatic
 rather than arrays:
 
 ```cpp
-using custom_json = nlohmann::basic_json<
-    nlohmann::ordered_map,  // ObjectType
-    std::vector,            // ArrayType
-    std::string,            // StringType
-    bool,                   // BooleanType
-    std::int64_t,           // NumberIntegerType
-    std::uint64_t,          // NumberUnsignedType
-    double,                 // NumberFloatType
-    std::allocator,         // AllocatorType
-    nlohmann::adl_serializer,
-    std::vector<std::byte>  // Custom BinaryType
->;
+using custom_json = nlohmann::ordered_json::with_binary_t<std::vector<std::byte>>;
 
 std::vector<std::byte> data{std::byte{1}, std::byte{2}, std::byte{3}};
 custom_json j = data;  // Creates a binary value, not an array

docs/mkdocs/docs/api/basic_json/object_t.md

@@ -26,7 +26,8 @@ To store objects in C++, a type is defined by the template parameters described
 
 `StringType`
 :   the type of the keys or names (e.g., `std::string`). The comparison function `std::less<StringType>` is used to
-    order elements inside the container.
+    order elements inside the container. `object_t::key_type` must be implicitly convertible to `string_t` (required by the
+    binary formats).
 
 `AllocatorType`
 :   the allocator to use for objects (e.g., `std::allocator`)

docs/mkdocs/docs/examples/as_base_class.cpp

@@ -15,19 +15,7 @@ class base_class_with_hidden_members
     }
 };
 
-using json = nlohmann::basic_json <
-             std::map,
-             std::vector,
-             std::string,
-             bool,
-             std::int64_t,
-             std::uint64_t,
-             double,
-             std::allocator,
-             nlohmann::adl_serializer,
-             std::vector<std::uint8_t>,
-             base_class_with_hidden_members
-             >;
+using json = nlohmann::json::with_base_class_t<base_class_with_hidden_members>;
 
 int main()
 {

include/nlohmann/detail/json_pointer.hpp

@@ -16,8 +16,8 @@
     #include <iosfwd> // ostream
 #endif  // JSON_NO_IO
 #include <limits> // max
+#include <map> // map
 #include <numeric> // accumulate
-#include <set> // set
 #include <string> // string
 #include <utility> // move
 #include <vector> // vector
@@ -359,33 +359,82 @@ class json_pointer
 
   private:
     /*!
-    @brief the reference token sequences that denote arrays
+    @brief the pointer prefixes of a flattened object, and which of them denote arrays
 
     @ref unflatten collects the pointer prefixes that have a reference token 0
     among their children; @ref get_and_create creates arrays exactly below
     those prefixes and objects everywhere else. Deciding this up front keeps
     the result independent of the order in which the flattened object is
     iterated, which is unspecified for some object types.
+
+    The prefixes form a tree and are numbered, so each of them is stored only
+    once (as a node) rather than as a copy of all of its reference tokens.
     */
-    using array_parents_t = std::set<std::vector<string_t>>;
+    struct prefix_tree
+    {
+        // children[id] maps a reference token to the number of the prefix
+        // extended by that token; number 0 is the empty prefix
+        std::vector<std::map<string_t, std::size_t>> children;
+        // is_array[id] is true iff some flattened key has the reference token
+        // 0 directly below the prefix with number id
+        std::vector<bool> is_array;
+
+        // start with the empty prefix only
+        prefix_tree()
+            : children(1)
+            , is_array(1, false)
+        {}
+
+        // return the number of the prefix with number id extended by
+        // reference_token, adding it if it is new
+        std::size_t add_child(std::size_t id, string_t&& reference_token)
+        {
+            if (reference_token == "0")
+            {
+                is_array[id] = true;
+            }
+
+            // read the number before the emplace_back below, which may
+            // reallocate children and invalidate the iterator
+            const std::size_t next = children.size();
+            const auto inserted = children[id].emplace(std::move(reference_token), next);
+            const std::size_t child = inserted.first->second;
+            if (inserted.second)
+            {
+                children.emplace_back();
+                is_array.push_back(false);
+            }
+            return child;
+        }
+
+        // return the number of the prefix with number id extended by
+        // reference_token, which must have been added before
+        std::size_t find_child(std::size_t id, const string_t& reference_token) const
+        {
+            const auto it = children[id].find(reference_token);
+            JSON_ASSERT(it != children[id].end());
+            return it->second;
+        }
+    };
 
     /*!
     @brief create and return a reference to the pointed to value
 
-    Complexity: Linear in the number of reference tokens.
+    Complexity: Linear in the number of reference tokens (times the logarithm
+    of the number of siblings for the prefix lookup).
 
     @throw parse_error.106 if an array index begins with '0'
     @throw parse_error.109 if array index is not a number
     @throw type_error.313 if value cannot be unflattened
     */
     template<typename BasicJsonType>
-    BasicJsonType& get_and_create(BasicJsonType& j, const array_parents_t& array_parents) const
+    BasicJsonType& get_and_create(BasicJsonType& j, const prefix_tree& tree) const
     {
         auto* result = &j;
 
-        // the reference tokens that have been consumed so far; used to look up
-        // whether the value to be created below is an array or an object
-        std::vector<string_t> prefix;
+        // the number of the prefix consumed so far; used to look up whether
+        // the value to be created below is an array or an object
+        std::size_t id = 0;
 
         // in case no reference tokens exist, return a reference to the JSON value
         // j which will be overwritten by a primitive value
@@ -395,7 +444,7 @@ class json_pointer
             {
                 case detail::value_t::null:
                 {
-                    if (array_parents.find(prefix) != array_parents.end())
+                    if (tree.is_array[id])
                     {
                         // some reference token below this position is 0, so the
                         // value is an array
@@ -440,7 +489,7 @@ class json_pointer
                     JSON_THROW(detail::type_error::create(313, "invalid value to unflatten", &j));
             }
 
-            prefix.push_back(reference_token);
+            id = tree.find_child(id, reference_token);
         }
 
         return *result;
@@ -878,64 +927,131 @@ class json_pointer
     @param[in,out] result        the result object to insert values to
 
     @note Empty objects or arrays are flattened to `null`.
+
+    The value is walked with an explicit stack rather than the call stack, so
+    arbitrarily deeply nested values can be flattened.
+
+    @sa https://github.com/nlohmann/json/issues/5393
     */
     template<typename BasicJsonType>
     static void flatten(const string_t& reference_string,
                         const BasicJsonType& value,
                         BasicJsonType& result)
     {
-        switch (value.type())
+        using object_const_iterator = typename BasicJsonType::object_t::const_iterator;
+
+        // an array or object being walked: the container, the array index or
+        // object iterator of the next child, and the length of the path of the
+        // container itself
+        struct frame
         {
-            case detail::value_t::array:
-            {
-                if (value.m_data.m_value.array->empty())
-                {
-                    // flatten empty array as null
-                    result[reference_string] = nullptr;
-                }
-                else
-                {
-                    // iterate array and use index as a reference string
-                    for (std::size_t i = 0; i < value.m_data.m_value.array->size(); ++i)
-                    {
-                        flatten(detail::concat<string_t>(reference_string, '/', std::to_string(i)),
-                                value.m_data.m_value.array->operator[](i), result);
-                    }
-                }
-                break;
-            }
+            frame(const BasicJsonType* container_, object_const_iterator member_, const std::size_t path_length_) noexcept
+                : container(container_), member(std::move(member_)), path_length(path_length_)
+            {}
 
-            case detail::value_t::object:
-            {
-                if (value.m_data.m_value.object->empty())
-                {
-                    // flatten empty object as null
-                    result[reference_string] = nullptr;
-                }
-                else
-                {
-                    // iterate object and use keys as reference string
-                    for (const auto& element : *value.m_data.m_value.object)
-                    {
-                        flatten(detail::concat<string_t>(reference_string, '/', detail::escape(element.first)), element.second, result);
-                    }
-                }
-                break;
-            }
+            const BasicJsonType* container;
+            std::size_t index = 0;
+            object_const_iterator member;
+            std::size_t path_length;
+        };
 
-            case detail::value_t::null:
-            case detail::value_t::string:
-            case detail::value_t::boolean:
-            case detail::value_t::number_integer:
-            case detail::value_t::number_unsigned:
-            case detail::value_t::number_float:
-            case detail::value_t::binary:
-            case detail::value_t::discarded:
-            default:
+        // The containers being flattened are kept on an explicit stack, and
+        // every child is flattened completely before the next one, so the
+        // entries come out in the same order as with a recursive walk. The
+        // path of the value being flattened is kept in one buffer that grows
+        // and shrinks with the stack, rather than in a new string per level.
+        std::vector<frame> stack;
+        string_t path = reference_string;
+
+        // flatten `v`, whose path is `path`: primitives and empty containers
+        // are added to the result right away; other containers get a frame
+        const auto enter = [&stack, &path, &result](const BasicJsonType & v)
+        {
+            switch (v.type())
             {
-                // add a primitive value with its reference string
-                result[reference_string] = value;
-                break;
+                case detail::value_t::array:
+                {
+                    if (v.m_data.m_value.array->empty())
+                    {
+                        // flatten empty array as null
+                        result[path] = nullptr;
+                    }
+                    else
+                    {
+                        stack.emplace_back(&v, object_const_iterator(), path.size());
+                    }
+                    return;
+                }
+
+                case detail::value_t::object:
+                {
+                    if (v.m_data.m_value.object->empty())
+                    {
+                        // flatten empty object as null
+                        result[path] = nullptr;
+                    }
+                    else
+                    {
+                        stack.emplace_back(&v, v.m_data.m_value.object->begin(), path.size());
+                    }
+                    return;
+                }
+
+                case detail::value_t::null:
+                case detail::value_t::string:
+                case detail::value_t::boolean:
+                case detail::value_t::number_integer:
+                case detail::value_t::number_unsigned:
+                case detail::value_t::number_float:
+                case detail::value_t::binary:
+                case detail::value_t::discarded:
+                default:
+                {
+                    // add a primitive value with its reference string
+                    result[path] = v;
+                    return;
+                }
+            }
+        };
+
+        enter(value);
+        while (!stack.empty())
+        {
+            // the frame is changed through stack.back(): enter() may push a
+            // frame, which would invalidate a reference to it
+            const BasicJsonType* const container = stack.back().container;
+
+            // drop the path of the previous child
+            path.resize(stack.back().path_length);
+
+            if (container->is_array())
+            {
+                const auto& array = *container->m_data.m_value.array;
+                const std::size_t i = stack.back().index;
+                if (i == array.size())
+                {
+                    stack.pop_back();
+                    continue;
+                }
+
+                // iterate array and use index as a reference string
+                ++stack.back().index;
+                detail::concat_into(path, '/', detail::to_string<string_t>(i));
+                enter(array[i]);
+            }
+            else
+            {
+                const object_const_iterator it = stack.back().member;
+                if (it == container->m_data.m_value.object->end())
+                {
+                    stack.pop_back();
+                    continue;
+                }
+
+                // iterate object and use keys as reference string
+                ++stack.back().member;
+                detail::concat_into(path, '/', detail::escape(it->first));
+                enter(it->second);
             }
         }
     }
@@ -963,19 +1079,15 @@ class json_pointer
 
         // collect the pointer prefixes that have a reference token 0 among
         // their children; the values below them are arrays, all others are
-        // objects (see array_parents_t)
-        array_parents_t array_parents;
+        // objects (see prefix_tree)
+        prefix_tree tree;
         for (const auto& element : *value.m_data.m_value.object)
         {
             json_pointer ptr(element.first);
-            std::vector<string_t> prefix;
+            std::size_t id = 0;
             for (auto& reference_token : ptr.reference_tokens)
             {
-                if (reference_token == "0")
-                {
-                    array_parents.insert(prefix);
-                }
-                prefix.push_back(std::move(reference_token));
+                id = tree.add_child(id, std::move(reference_token));
             }
         }
 
@@ -991,7 +1103,7 @@ class json_pointer
             // that if the JSON pointer is "" (i.e., points to the whole value),
             // function get_and_create returns a reference to the result itself.
             // An assignment will then create a primitive value.
-            json_pointer(element.first).get_and_create(result, array_parents) = element.second;
+            json_pointer(element.first).get_and_create(result, tree) = element.second;
         }
 
         return result;

include/nlohmann/detail/output/binary_writer.hpp

@@ -85,6 +85,12 @@ template<typename BasicJsonType, typename CharType, typename OutputSinkType = ou
 class binary_writer
 {
     using string_t = typename BasicJsonType::string_t;
+
+    /// an object key as string_t: a reference when object_t::key_type already is
+    /// string_t, otherwise a converted copy that outlives sanitize_utf8_for_write's result
+    using object_key_string_t = typename std::conditional <
+                                std::is_same<typename BasicJsonType::object_t::key_type, string_t>::value,
+                                const string_t&, string_t >::type;
     using binary_t = typename BasicJsonType::binary_t;
     using number_float_t = typename BasicJsonType::number_float_t;
 
@@ -244,16 +250,7 @@ class binary_writer
 
             case value_t::string:
             {
-                string_t storage;
-                const string_t& value = sanitize_utf8_for_write(*j.m_data.m_value.string, j, storage);
-
-                // step 1: write control byte and the string length
-                write_cbor_head(0x60, value.size());
-
-                // step 2: write the string
-                oa.write_characters(
-                      reinterpret_cast<const CharType*>(value.data()),
-                      value.size());
+                write_cbor_string(*j.m_data.m_value.string, j);
                 break;
             }
 
@@ -316,23 +313,20 @@ class binary_writer
 
             case value_t::object:
             {
+                static_assert(
+                    std::is_convertible <
+                    typename BasicJsonType::object_t::key_type,
+                    string_t >::value,
+                    "object_t::key_type must be implicitly convertible to string_t");
+
                 // step 1: write control byte and the object size
                 write_cbor_head(0xA0, j.m_data.m_value.object->size());
 
                 for (const auto& el : *j.m_data.m_value.object)
                 {
-                    // el.first is checked here, against the object as
-                    // diagnostics context, because write_cbor(el.first)
-                    // converts it to a temporary basic_json that would be
-                    // used as the context instead; for error_handler_t::keep
-                    // and ::replace/::ignore the recursive write_cbor(el.first)
-                    // call below handles the key like any other string, so no
-                    // separate check is needed here for those
-                    if (error_handler == error_handler_t::strict)
-                    {
-                        check_utf8(el.first, j);
-                    }
-                    write_cbor(el.first);
+                    // el.first is written directly (not via a temporary
+                    // basic_json), with the object as diagnostics context
+                    write_cbor_string(el.first, j);
                     write_cbor(el.second, depth + 1);
                 }
                 break;
@@ -491,39 +485,7 @@ class binary_writer
 
             case value_t::string:
             {
-                string_t storage;
-                const string_t& value = sanitize_utf8_for_write(*j.m_data.m_value.string, j, storage);
-
-                // step 1: write control byte and the string length
-                const auto N = to_msgpack_length(value.size(), j);
-                if (N <= 31)
-                {
-                    // fixstr
-                    write_number(static_cast<std::uint8_t>(0xA0 | N));
-                }
-                else if (N <= (std::numeric_limits<std::uint8_t>::max)())
-                {
-                    // str 8
-                    oa.write_character(to_char_type(0xD9));
-                    write_number(static_cast<std::uint8_t>(N));
-                }
-                else if (N <= (std::numeric_limits<std::uint16_t>::max)())
-                {
-                    // str 16
-                    oa.write_character(to_char_type(0xDA));
-                    write_number(static_cast<std::uint16_t>(N));
-                }
-                else
-                {
-                    // str 32
-                    oa.write_character(to_char_type(0xDB));
-                    write_number(static_cast<std::uint32_t>(N));
-                }
-
-                // step 2: write the string
-                oa.write_characters(
-                      reinterpret_cast<const CharType*>(value.data()),
-                      value.size());
+                write_msgpack_string(*j.m_data.m_value.string, j);
                 break;
             }
 
@@ -629,19 +591,20 @@ class binary_writer
 
             case value_t::object:
             {
+                static_assert(
+                    std::is_convertible <
+                    typename BasicJsonType::object_t::key_type,
+                    string_t >::value,
+                    "object_t::key_type must be implicitly convertible to string_t");
+
                 // step 1: write control byte and the object size
                 write_msgpack_object_prefix(j.m_data.m_value.object->size(), j);
 
                 for (const auto& el : *j.m_data.m_value.object)
                 {
-                    // as in write_cbor, el.first is checked here against the
-                    // object as diagnostics context; the recursive call below
-                    // handles keep/replace/ignore like any other string
-                    if (error_handler == error_handler_t::strict)
-                    {
-                        check_utf8(el.first, j);
-                    }
-                    write_msgpack(el.first);
+                    // as in write_cbor, el.first is written directly with the
+                    // object as diagnostics context
+                    write_msgpack_string(el.first, j);
                     write_msgpack(el.second, depth + 1);
                 }
                 break;
@@ -819,8 +782,10 @@ class binary_writer
 
                 for (const auto& el : *j.m_data.m_value.object)
                 {
+                    // a converted key must outlive the reference returned by sanitize_utf8_for_write
+                    const object_key_string_t key_string = el.first;
                     string_t storage;
-                    const string_t& key = sanitize_utf8_for_write(el.first, j, storage);
+                    const string_t& key = sanitize_utf8_for_write(key_string, j, storage);
                     write_number_with_ubjson_prefix(key.size(), true, use_bjdata);
                     oa.write_characters(
                           reinterpret_cast<const CharType*>(key.data()),
@@ -1025,13 +990,9 @@ class binary_writer
                     continue;
                 }
 
-                // el.first is checked here, against the object as diagnostics
-                // context, like the matching check in write_cbor's object case
-                if (error_handler == error_handler_t::strict)
-                {
-                    check_utf8(current.object_it->first, *current.value);
-                }
-                write_cbor(current.object_it->first);
+                // the key is written directly (not via a temporary basic_json),
+                // with the object as diagnostics context, as in write_cbor
+                write_cbor_string(current.object_it->first, *current.value);
                 const BasicJsonType* child = &(current.object_it->second);
                 ++stack.back().object_it;
                 write_cbor_value_or_push(*child, stack);
@@ -1106,11 +1067,9 @@ class binary_writer
                     continue;
                 }
 
-                if (error_handler == error_handler_t::strict)
-                {
-                    check_utf8(current.object_it->first, *current.value);
-                }
-                write_msgpack(current.object_it->first);
+                // as in write_cbor_iterative, the key is written directly with
+                // the object as diagnostics context
+                write_msgpack_string(current.object_it->first, *current.value);
                 const BasicJsonType* child = &(current.object_it->second);
                 ++stack.back().object_it;
                 write_msgpack_value_or_push(*child, stack);
@@ -1366,8 +1325,10 @@ class binary_writer
                     continue;
                 }
 
+                // a converted key must outlive the reference returned by sanitize_utf8_for_write
+                const object_key_string_t key_string = current.object_it->first;
                 string_t storage;
-                const string_t& key = sanitize_utf8_for_write(current.object_it->first, j, storage);
+                const string_t& key = sanitize_utf8_for_write(key_string, j, storage);
                 write_number_with_ubjson_prefix(key.size(), true, use_bjdata);
                 oa.write_characters(
                       reinterpret_cast<const CharType*>(key.data()),
@@ -1988,6 +1949,85 @@ class binary_writer
         }
     }
 
+    /*!
+    @brief write a CBOR text string
+
+    @a value is checked or sanitized according to @ref error_handler, with
+    @a context (the string value itself, or the object a key belongs to) used
+    as diagnostics context; this avoids converting object keys to a temporary
+    basic_json just to write them
+
+    @note When object_t::key_type is not string_t, @a value is a temporary
+          string_t converted from the key, which lives only until the end of
+          the caller's statement. The reference returned by
+          @ref sanitize_utf8_for_write may refer to it, so it must not escape
+          this function.
+    */
+    void write_cbor_string(const string_t& value, const BasicJsonType& context)
+    {
+        string_t storage;
+        const string_t& sanitized = sanitize_utf8_for_write(value, context, storage);
+
+        // step 1: write control byte and the string length
+        write_cbor_head(0x60, sanitized.size());
+
+        // step 2: write the string
+        oa.write_characters(
+              reinterpret_cast<const CharType*>(sanitized.data()),
+              sanitized.size());
+    }
+
+    /////////////
+    // MsgPack //
+    /////////////
+
+    /*!
+    @brief write a MessagePack str
+
+    @a value is checked or sanitized according to @ref error_handler, with
+    @a context used as diagnostics context, as in @ref write_cbor_string
+
+    @note As in @ref write_cbor_string, @a value may be a temporary string_t
+          converted from a key, so the reference returned by
+          @ref sanitize_utf8_for_write must not escape this function.
+    */
+    void write_msgpack_string(const string_t& value, const BasicJsonType& context)
+    {
+        string_t storage;
+        const string_t& sanitized = sanitize_utf8_for_write(value, context, storage);
+
+        // step 1: write control byte and the string length
+        const auto N = to_msgpack_length(sanitized.size(), context);
+        if (N <= 31)
+        {
+            // fixstr
+            write_number(static_cast<std::uint8_t>(0xA0 | N));
+        }
+        else if (N <= (std::numeric_limits<std::uint8_t>::max)())
+        {
+            // str 8
+            oa.write_character(to_char_type(0xD9));
+            write_number(static_cast<std::uint8_t>(N));
+        }
+        else if (N <= (std::numeric_limits<std::uint16_t>::max)())
+        {
+            // str 16
+            oa.write_character(to_char_type(0xDA));
+            write_number(static_cast<std::uint16_t>(N));
+        }
+        else
+        {
+            // str 32
+            oa.write_character(to_char_type(0xDB));
+            write_number(static_cast<std::uint32_t>(N));
+        }
+
+        // step 2: write the string
+        oa.write_characters(
+              reinterpret_cast<const CharType*>(sanitized.data()),
+              sanitized.size());
+    }
+
     ////////////
     // UBJSON //
     ////////////
@@ -2730,6 +2770,11 @@ class binary_writer
     itself in every case but a sanitized `replace`/`ignore` one, so @a
     storage must outlive the returned reference only then.
 
+    @a s must be an lvalue that outlives the returned reference. An object key
+    whose `key_type` is not @ref string_t must therefore first be converted
+    into a named string_t (see @ref object_key_string_t); the deleted overload
+    below enforces this at compile time.
+
     @param[in] s        the string (value or object key) to write
     @param[in] context  the value @a s belongs to (for diagnostics)
     @param[out] storage  backing storage for a sanitized copy
@@ -2759,6 +2804,10 @@ class binary_writer
         }
     }
 
+    /// deleted: anything but a string_t would bind a temporary that dies before the returned reference is used
+    template < typename T, enable_if_t < !std::is_same<T, string_t>::value, int > = 0 >
+    const string_t& sanitize_utf8_for_write(const T& /*s*/, const BasicJsonType& /*context*/, string_t& /*storage*/) const = delete; // NOLINT(hicpp-use-equals-delete,modernize-use-equals-delete): a private helper's guard, not part of the interface
+
     /*!
     @brief write an integer in the shortest encoding
 

single_include/nlohmann/json.hpp

@@ -19928,8 +19928,8 @@ NLOHMANN_JSON_NAMESPACE_END
     #include <iosfwd> // ostream
 #endif  // JSON_NO_IO
 #include <limits> // max
+#include <map> // map
 #include <numeric> // accumulate
-#include <set> // set
 #include <string> // string
 #include <utility> // move
 #include <vector> // vector
@@ -20277,33 +20277,82 @@ class json_pointer
 
   private:
     /*!
-    @brief the reference token sequences that denote arrays
+    @brief the pointer prefixes of a flattened object, and which of them denote arrays
 
     @ref unflatten collects the pointer prefixes that have a reference token 0
     among their children; @ref get_and_create creates arrays exactly below
     those prefixes and objects everywhere else. Deciding this up front keeps
     the result independent of the order in which the flattened object is
     iterated, which is unspecified for some object types.
+
+    The prefixes form a tree and are numbered, so each of them is stored only
+    once (as a node) rather than as a copy of all of its reference tokens.
     */
-    using array_parents_t = std::set<std::vector<string_t>>;
+    struct prefix_tree
+    {
+        // children[id] maps a reference token to the number of the prefix
+        // extended by that token; number 0 is the empty prefix
+        std::vector<std::map<string_t, std::size_t>> children;
+        // is_array[id] is true iff some flattened key has the reference token
+        // 0 directly below the prefix with number id
+        std::vector<bool> is_array;
+
+        // start with the empty prefix only
+        prefix_tree()
+            : children(1)
+            , is_array(1, false)
+        {}
+
+        // return the number of the prefix with number id extended by
+        // reference_token, adding it if it is new
+        std::size_t add_child(std::size_t id, string_t&& reference_token)
+        {
+            if (reference_token == "0")
+            {
+                is_array[id] = true;
+            }
+
+            // read the number before the emplace_back below, which may
+            // reallocate children and invalidate the iterator
+            const std::size_t next = children.size();
+            const auto inserted = children[id].emplace(std::move(reference_token), next);
+            const std::size_t child = inserted.first->second;
+            if (inserted.second)
+            {
+                children.emplace_back();
+                is_array.push_back(false);
+            }
+            return child;
+        }
+
+        // return the number of the prefix with number id extended by
+        // reference_token, which must have been added before
+        std::size_t find_child(std::size_t id, const string_t& reference_token) const
+        {
+            const auto it = children[id].find(reference_token);
+            JSON_ASSERT(it != children[id].end());
+            return it->second;
+        }
+    };
 
     /*!
     @brief create and return a reference to the pointed to value
 
-    Complexity: Linear in the number of reference tokens.
+    Complexity: Linear in the number of reference tokens (times the logarithm
+    of the number of siblings for the prefix lookup).
 
     @throw parse_error.106 if an array index begins with '0'
     @throw parse_error.109 if array index is not a number
     @throw type_error.313 if value cannot be unflattened
     */
     template<typename BasicJsonType>
-    BasicJsonType& get_and_create(BasicJsonType& j, const array_parents_t& array_parents) const
+    BasicJsonType& get_and_create(BasicJsonType& j, const prefix_tree& tree) const
     {
         auto* result = &j;
 
-        // the reference tokens that have been consumed so far; used to look up
-        // whether the value to be created below is an array or an object
-        std::vector<string_t> prefix;
+        // the number of the prefix consumed so far; used to look up whether
+        // the value to be created below is an array or an object
+        std::size_t id = 0;
 
         // in case no reference tokens exist, return a reference to the JSON value
         // j which will be overwritten by a primitive value
@@ -20313,7 +20362,7 @@ class json_pointer
             {
                 case detail::value_t::null:
                 {
-                    if (array_parents.find(prefix) != array_parents.end())
+                    if (tree.is_array[id])
                     {
                         // some reference token below this position is 0, so the
                         // value is an array
@@ -20358,7 +20407,7 @@ class json_pointer
                     JSON_THROW(detail::type_error::create(313, "invalid value to unflatten", &j));
             }
 
-            prefix.push_back(reference_token);
+            id = tree.find_child(id, reference_token);
         }
 
         return *result;
@@ -20796,64 +20845,131 @@ class json_pointer
     @param[in,out] result        the result object to insert values to
 
     @note Empty objects or arrays are flattened to `null`.
+
+    The value is walked with an explicit stack rather than the call stack, so
+    arbitrarily deeply nested values can be flattened.
+
+    @sa https://github.com/nlohmann/json/issues/5393
     */
     template<typename BasicJsonType>
     static void flatten(const string_t& reference_string,
                         const BasicJsonType& value,
                         BasicJsonType& result)
     {
-        switch (value.type())
+        using object_const_iterator = typename BasicJsonType::object_t::const_iterator;
+
+        // an array or object being walked: the container, the array index or
+        // object iterator of the next child, and the length of the path of the
+        // container itself
+        struct frame
         {
-            case detail::value_t::array:
-            {
-                if (value.m_data.m_value.array->empty())
-                {
-                    // flatten empty array as null
-                    result[reference_string] = nullptr;
-                }
-                else
-                {
-                    // iterate array and use index as a reference string
-                    for (std::size_t i = 0; i < value.m_data.m_value.array->size(); ++i)
-                    {
-                        flatten(detail::concat<string_t>(reference_string, '/', std::to_string(i)),
-                                value.m_data.m_value.array->operator[](i), result);
-                    }
-                }
-                break;
-            }
+            frame(const BasicJsonType* container_, object_const_iterator member_, const std::size_t path_length_) noexcept
+                : container(container_), member(std::move(member_)), path_length(path_length_)
+            {}
 
-            case detail::value_t::object:
-            {
-                if (value.m_data.m_value.object->empty())
-                {
-                    // flatten empty object as null
-                    result[reference_string] = nullptr;
-                }
-                else
-                {
-                    // iterate object and use keys as reference string
-                    for (const auto& element : *value.m_data.m_value.object)
-                    {
-                        flatten(detail::concat<string_t>(reference_string, '/', detail::escape(element.first)), element.second, result);
-                    }
-                }
-                break;
-            }
+            const BasicJsonType* container;
+            std::size_t index = 0;
+            object_const_iterator member;
+            std::size_t path_length;
+        };
 
-            case detail::value_t::null:
-            case detail::value_t::string:
-            case detail::value_t::boolean:
-            case detail::value_t::number_integer:
-            case detail::value_t::number_unsigned:
-            case detail::value_t::number_float:
-            case detail::value_t::binary:
-            case detail::value_t::discarded:
-            default:
+        // The containers being flattened are kept on an explicit stack, and
+        // every child is flattened completely before the next one, so the
+        // entries come out in the same order as with a recursive walk. The
+        // path of the value being flattened is kept in one buffer that grows
+        // and shrinks with the stack, rather than in a new string per level.
+        std::vector<frame> stack;
+        string_t path = reference_string;
+
+        // flatten `v`, whose path is `path`: primitives and empty containers
+        // are added to the result right away; other containers get a frame
+        const auto enter = [&stack, &path, &result](const BasicJsonType & v)
+        {
+            switch (v.type())
             {
-                // add a primitive value with its reference string
-                result[reference_string] = value;
-                break;
+                case detail::value_t::array:
+                {
+                    if (v.m_data.m_value.array->empty())
+                    {
+                        // flatten empty array as null
+                        result[path] = nullptr;
+                    }
+                    else
+                    {
+                        stack.emplace_back(&v, object_const_iterator(), path.size());
+                    }
+                    return;
+                }
+
+                case detail::value_t::object:
+                {
+                    if (v.m_data.m_value.object->empty())
+                    {
+                        // flatten empty object as null
+                        result[path] = nullptr;
+                    }
+                    else
+                    {
+                        stack.emplace_back(&v, v.m_data.m_value.object->begin(), path.size());
+                    }
+                    return;
+                }
+
+                case detail::value_t::null:
+                case detail::value_t::string:
+                case detail::value_t::boolean:
+                case detail::value_t::number_integer:
+                case detail::value_t::number_unsigned:
+                case detail::value_t::number_float:
+                case detail::value_t::binary:
+                case detail::value_t::discarded:
+                default:
+                {
+                    // add a primitive value with its reference string
+                    result[path] = v;
+                    return;
+                }
+            }
+        };
+
+        enter(value);
+        while (!stack.empty())
+        {
+            // the frame is changed through stack.back(): enter() may push a
+            // frame, which would invalidate a reference to it
+            const BasicJsonType* const container = stack.back().container;
+
+            // drop the path of the previous child
+            path.resize(stack.back().path_length);
+
+            if (container->is_array())
+            {
+                const auto& array = *container->m_data.m_value.array;
+                const std::size_t i = stack.back().index;
+                if (i == array.size())
+                {
+                    stack.pop_back();
+                    continue;
+                }
+
+                // iterate array and use index as a reference string
+                ++stack.back().index;
+                detail::concat_into(path, '/', detail::to_string<string_t>(i));
+                enter(array[i]);
+            }
+            else
+            {
+                const object_const_iterator it = stack.back().member;
+                if (it == container->m_data.m_value.object->end())
+                {
+                    stack.pop_back();
+                    continue;
+                }
+
+                // iterate object and use keys as reference string
+                ++stack.back().member;
+                detail::concat_into(path, '/', detail::escape(it->first));
+                enter(it->second);
             }
         }
     }
@@ -20881,19 +20997,15 @@ class json_pointer
 
         // collect the pointer prefixes that have a reference token 0 among
         // their children; the values below them are arrays, all others are
-        // objects (see array_parents_t)
-        array_parents_t array_parents;
+        // objects (see prefix_tree)
+        prefix_tree tree;
         for (const auto& element : *value.m_data.m_value.object)
         {
             json_pointer ptr(element.first);
-            std::vector<string_t> prefix;
+            std::size_t id = 0;
             for (auto& reference_token : ptr.reference_tokens)
             {
-                if (reference_token == "0")
-                {
-                    array_parents.insert(prefix);
-                }
-                prefix.push_back(std::move(reference_token));
+                id = tree.add_child(id, std::move(reference_token));
             }
         }
 
@@ -20909,7 +21021,7 @@ class json_pointer
             // that if the JSON pointer is "" (i.e., points to the whole value),
             // function get_and_create returns a reference to the result itself.
             // An assignment will then create a primitive value.
-            json_pointer(element.first).get_and_create(result, array_parents) = element.second;
+            json_pointer(element.first).get_and_create(result, tree) = element.second;
         }
 
         return result;
@@ -21590,6 +21702,12 @@ template<typename BasicJsonType, typename CharType, typename OutputSinkType = ou
 class binary_writer
 {
     using string_t = typename BasicJsonType::string_t;
+
+    /// an object key as string_t: a reference when object_t::key_type already is
+    /// string_t, otherwise a converted copy that outlives sanitize_utf8_for_write's result
+    using object_key_string_t = typename std::conditional <
+                                std::is_same<typename BasicJsonType::object_t::key_type, string_t>::value,
+                                const string_t&, string_t >::type;
     using binary_t = typename BasicJsonType::binary_t;
     using number_float_t = typename BasicJsonType::number_float_t;
 
@@ -21749,16 +21867,7 @@ class binary_writer
 
             case value_t::string:
             {
-                string_t storage;
-                const string_t& value = sanitize_utf8_for_write(*j.m_data.m_value.string, j, storage);
-
-                // step 1: write control byte and the string length
-                write_cbor_head(0x60, value.size());
-
-                // step 2: write the string
-                oa.write_characters(
-                      reinterpret_cast<const CharType*>(value.data()),
-                      value.size());
+                write_cbor_string(*j.m_data.m_value.string, j);
                 break;
             }
 
@@ -21821,23 +21930,20 @@ class binary_writer
 
             case value_t::object:
             {
+                static_assert(
+                    std::is_convertible <
+                    typename BasicJsonType::object_t::key_type,
+                    string_t >::value,
+                    "object_t::key_type must be implicitly convertible to string_t");
+
                 // step 1: write control byte and the object size
                 write_cbor_head(0xA0, j.m_data.m_value.object->size());
 
                 for (const auto& el : *j.m_data.m_value.object)
                 {
-                    // el.first is checked here, against the object as
-                    // diagnostics context, because write_cbor(el.first)
-                    // converts it to a temporary basic_json that would be
-                    // used as the context instead; for error_handler_t::keep
-                    // and ::replace/::ignore the recursive write_cbor(el.first)
-                    // call below handles the key like any other string, so no
-                    // separate check is needed here for those
-                    if (error_handler == error_handler_t::strict)
-                    {
-                        check_utf8(el.first, j);
-                    }
-                    write_cbor(el.first);
+                    // el.first is written directly (not via a temporary
+                    // basic_json), with the object as diagnostics context
+                    write_cbor_string(el.first, j);
                     write_cbor(el.second, depth + 1);
                 }
                 break;
@@ -21996,39 +22102,7 @@ class binary_writer
 
             case value_t::string:
             {
-                string_t storage;
-                const string_t& value = sanitize_utf8_for_write(*j.m_data.m_value.string, j, storage);
-
-                // step 1: write control byte and the string length
-                const auto N = to_msgpack_length(value.size(), j);
-                if (N <= 31)
-                {
-                    // fixstr
-                    write_number(static_cast<std::uint8_t>(0xA0 | N));
-                }
-                else if (N <= (std::numeric_limits<std::uint8_t>::max)())
-                {
-                    // str 8
-                    oa.write_character(to_char_type(0xD9));
-                    write_number(static_cast<std::uint8_t>(N));
-                }
-                else if (N <= (std::numeric_limits<std::uint16_t>::max)())
-                {
-                    // str 16
-                    oa.write_character(to_char_type(0xDA));
-                    write_number(static_cast<std::uint16_t>(N));
-                }
-                else
-                {
-                    // str 32
-                    oa.write_character(to_char_type(0xDB));
-                    write_number(static_cast<std::uint32_t>(N));
-                }
-
-                // step 2: write the string
-                oa.write_characters(
-                      reinterpret_cast<const CharType*>(value.data()),
-                      value.size());
+                write_msgpack_string(*j.m_data.m_value.string, j);
                 break;
             }
 
@@ -22134,19 +22208,20 @@ class binary_writer
 
             case value_t::object:
             {
+                static_assert(
+                    std::is_convertible <
+                    typename BasicJsonType::object_t::key_type,
+                    string_t >::value,
+                    "object_t::key_type must be implicitly convertible to string_t");
+
                 // step 1: write control byte and the object size
                 write_msgpack_object_prefix(j.m_data.m_value.object->size(), j);
 
                 for (const auto& el : *j.m_data.m_value.object)
                 {
-                    // as in write_cbor, el.first is checked here against the
-                    // object as diagnostics context; the recursive call below
-                    // handles keep/replace/ignore like any other string
-                    if (error_handler == error_handler_t::strict)
-                    {
-                        check_utf8(el.first, j);
-                    }
-                    write_msgpack(el.first);
+                    // as in write_cbor, el.first is written directly with the
+                    // object as diagnostics context
+                    write_msgpack_string(el.first, j);
                     write_msgpack(el.second, depth + 1);
                 }
                 break;
@@ -22324,8 +22399,10 @@ class binary_writer
 
                 for (const auto& el : *j.m_data.m_value.object)
                 {
+                    // a converted key must outlive the reference returned by sanitize_utf8_for_write
+                    const object_key_string_t key_string = el.first;
                     string_t storage;
-                    const string_t& key = sanitize_utf8_for_write(el.first, j, storage);
+                    const string_t& key = sanitize_utf8_for_write(key_string, j, storage);
                     write_number_with_ubjson_prefix(key.size(), true, use_bjdata);
                     oa.write_characters(
                           reinterpret_cast<const CharType*>(key.data()),
@@ -22530,13 +22607,9 @@ class binary_writer
                     continue;
                 }
 
-                // el.first is checked here, against the object as diagnostics
-                // context, like the matching check in write_cbor's object case
-                if (error_handler == error_handler_t::strict)
-                {
-                    check_utf8(current.object_it->first, *current.value);
-                }
-                write_cbor(current.object_it->first);
+                // the key is written directly (not via a temporary basic_json),
+                // with the object as diagnostics context, as in write_cbor
+                write_cbor_string(current.object_it->first, *current.value);
                 const BasicJsonType* child = &(current.object_it->second);
                 ++stack.back().object_it;
                 write_cbor_value_or_push(*child, stack);
@@ -22611,11 +22684,9 @@ class binary_writer
                     continue;
                 }
 
-                if (error_handler == error_handler_t::strict)
-                {
-                    check_utf8(current.object_it->first, *current.value);
-                }
-                write_msgpack(current.object_it->first);
+                // as in write_cbor_iterative, the key is written directly with
+                // the object as diagnostics context
+                write_msgpack_string(current.object_it->first, *current.value);
                 const BasicJsonType* child = &(current.object_it->second);
                 ++stack.back().object_it;
                 write_msgpack_value_or_push(*child, stack);
@@ -22871,8 +22942,10 @@ class binary_writer
                     continue;
                 }
 
+                // a converted key must outlive the reference returned by sanitize_utf8_for_write
+                const object_key_string_t key_string = current.object_it->first;
                 string_t storage;
-                const string_t& key = sanitize_utf8_for_write(current.object_it->first, j, storage);
+                const string_t& key = sanitize_utf8_for_write(key_string, j, storage);
                 write_number_with_ubjson_prefix(key.size(), true, use_bjdata);
                 oa.write_characters(
                       reinterpret_cast<const CharType*>(key.data()),
@@ -23493,6 +23566,85 @@ class binary_writer
         }
     }
 
+    /*!
+    @brief write a CBOR text string
+
+    @a value is checked or sanitized according to @ref error_handler, with
+    @a context (the string value itself, or the object a key belongs to) used
+    as diagnostics context; this avoids converting object keys to a temporary
+    basic_json just to write them
+
+    @note When object_t::key_type is not string_t, @a value is a temporary
+          string_t converted from the key, which lives only until the end of
+          the caller's statement. The reference returned by
+          @ref sanitize_utf8_for_write may refer to it, so it must not escape
+          this function.
+    */
+    void write_cbor_string(const string_t& value, const BasicJsonType& context)
+    {
+        string_t storage;
+        const string_t& sanitized = sanitize_utf8_for_write(value, context, storage);
+
+        // step 1: write control byte and the string length
+        write_cbor_head(0x60, sanitized.size());
+
+        // step 2: write the string
+        oa.write_characters(
+              reinterpret_cast<const CharType*>(sanitized.data()),
+              sanitized.size());
+    }
+
+    /////////////
+    // MsgPack //
+    /////////////
+
+    /*!
+    @brief write a MessagePack str
+
+    @a value is checked or sanitized according to @ref error_handler, with
+    @a context used as diagnostics context, as in @ref write_cbor_string
+
+    @note As in @ref write_cbor_string, @a value may be a temporary string_t
+          converted from a key, so the reference returned by
+          @ref sanitize_utf8_for_write must not escape this function.
+    */
+    void write_msgpack_string(const string_t& value, const BasicJsonType& context)
+    {
+        string_t storage;
+        const string_t& sanitized = sanitize_utf8_for_write(value, context, storage);
+
+        // step 1: write control byte and the string length
+        const auto N = to_msgpack_length(sanitized.size(), context);
+        if (N <= 31)
+        {
+            // fixstr
+            write_number(static_cast<std::uint8_t>(0xA0 | N));
+        }
+        else if (N <= (std::numeric_limits<std::uint8_t>::max)())
+        {
+            // str 8
+            oa.write_character(to_char_type(0xD9));
+            write_number(static_cast<std::uint8_t>(N));
+        }
+        else if (N <= (std::numeric_limits<std::uint16_t>::max)())
+        {
+            // str 16
+            oa.write_character(to_char_type(0xDA));
+            write_number(static_cast<std::uint16_t>(N));
+        }
+        else
+        {
+            // str 32
+            oa.write_character(to_char_type(0xDB));
+            write_number(static_cast<std::uint32_t>(N));
+        }
+
+        // step 2: write the string
+        oa.write_characters(
+              reinterpret_cast<const CharType*>(sanitized.data()),
+              sanitized.size());
+    }
+
     ////////////
     // UBJSON //
     ////////////
@@ -24235,6 +24387,11 @@ class binary_writer
     itself in every case but a sanitized `replace`/`ignore` one, so @a
     storage must outlive the returned reference only then.
 
+    @a s must be an lvalue that outlives the returned reference. An object key
+    whose `key_type` is not @ref string_t must therefore first be converted
+    into a named string_t (see @ref object_key_string_t); the deleted overload
+    below enforces this at compile time.
+
     @param[in] s        the string (value or object key) to write
     @param[in] context  the value @a s belongs to (for diagnostics)
     @param[out] storage  backing storage for a sanitized copy
@@ -24264,6 +24421,10 @@ class binary_writer
         }
     }
 
+    /// deleted: anything but a string_t would bind a temporary that dies before the returned reference is used
+    template < typename T, enable_if_t < !std::is_same<T, string_t>::value, int > = 0 >
+    const string_t& sanitize_utf8_for_write(const T& /*s*/, const BasicJsonType& /*context*/, string_t& /*storage*/) const = delete; // NOLINT(hicpp-use-equals-delete,modernize-use-equals-delete): a private helper's guard, not part of the interface
+
     /*!
     @brief write an integer in the shortest encoding
 

tests/src/custom_object_key_type.hpp

@@ -0,0 +1,75 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  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
+
+#pragma once
+
+#include <map>
+#include <memory>
+#include <string>
+#include <utility>
+#include <nlohmann/json.hpp>
+
+namespace custom_object_key_test
+{
+class key
+{
+  public:
+    key() = default;
+
+    key(const char* value)
+        : m_value(value)
+    {}
+
+    key(std::string value)
+        : m_value(std::move(value))
+    {}
+
+    operator std::string() const
+    {
+        return m_value;
+    }
+
+    // Required by JSON_DIAGNOSTICS, which reads object keys through data()
+    // when building the path of an exception.
+    const char* data() const noexcept
+    {
+        return m_value.data();
+    }
+
+    friend bool operator<(const key& lhs, const key& rhs)
+    {
+        return lhs.m_value < rhs.m_value;
+    }
+
+  private:
+    std::string m_value;
+};
+
+template<typename Key, typename Value, typename Compare, typename Allocator>
+class object
+    : public std::map <
+      key,
+      Value,
+      std::less<key>, // NOLINT(modernize-use-transparent-functors)
+      typename std::allocator_traits<Allocator>::template rebind_alloc <
+          std::pair<const key, Value >>>
+{
+  private:
+    using allocator_type =
+    typename std::allocator_traits<Allocator>::template rebind_alloc <
+        std::pair<const key, Value >>;
+
+    using base_type =
+        std::map<key, Value, std::less<key>, allocator_type>; // NOLINT(modernize-use-transparent-functors)
+
+  public:
+    using base_type::base_type;
+};
+
+using json = nlohmann::basic_json<object>;
+} // namespace custom_object_key_test

tests/src/unit-binary_utf8_error_handler.cpp

@@ -12,7 +12,11 @@
 #include <nlohmann/json.hpp>
 using nlohmann::json;
 
+#include <array>
+#include <map>
+#include <memory>
 #include <string>
+#include <utility>
 #include <vector>
 
 namespace
@@ -55,6 +59,53 @@ std::string dump_and_parse(const std::string& raw, eh error_handler)
     return json::parse(json(raw).dump(-1, ' ', false, error_handler)).get<std::string>();
 }
 
+// an object key type that is not string_t, but converts implicitly to it;
+// data() is only used when JSON_DIAGNOSTICS is enabled
+DOCTEST_CLANG_SUPPRESS_WARNING_PUSH
+DOCTEST_CLANG_SUPPRESS_WARNING("-Wunused-member-function")
+class converting_key
+{
+  public:
+    converting_key(const char* s) : m_value(s) {} // NOLINT(google-explicit-constructor,hicpp-explicit-conversions)
+    converting_key(std::string s) : m_value(std::move(s)) {} // NOLINT(google-explicit-constructor,hicpp-explicit-conversions)
+
+    // the conversion yields a temporary string_t
+    operator std::string() const // NOLINT(google-explicit-constructor,hicpp-explicit-conversions)
+    {
+        return m_value;
+    }
+
+    // read by the exception messages when JSON_DIAGNOSTICS is enabled
+    const char* data() const noexcept
+    {
+        return m_value.data();
+    }
+
+    friend bool operator<(const converting_key& lhs, const converting_key& rhs)
+    {
+        return lhs.m_value < rhs.m_value;
+    }
+
+  private:
+    std::string m_value;
+};
+DOCTEST_CLANG_SUPPRESS_WARNING_POP
+
+// ObjectType using converting_key; the Key template argument is ignored
+template<typename Key, typename Value, typename Compare, typename Allocator>
+class converting_key_object : public std::map<converting_key, Value, std::less<converting_key>, // NOLINT(modernize-use-transparent-functors)
+    typename std::allocator_traits<Allocator>::template rebind_alloc<std::pair<const converting_key, Value>>>
+{
+    using base_type = std::map<converting_key, Value, std::less<converting_key>, // NOLINT(modernize-use-transparent-functors)
+                               typename std::allocator_traits<Allocator>::template rebind_alloc<std::pair<const converting_key, Value>>>;
+
+                             public:
+                               using base_type::base_type;
+                               using base_type::operator=;
+};
+
+using converting_key_json = nlohmann::basic_json<converting_key_object>;
+
 } // namespace
 
 TEST_CASE("UTF-8 error_handler for the binary readers and writers")
@@ -370,3 +421,109 @@ TEST_CASE("UTF-8 error_handler for the binary readers and writers")
         CHECK(json::from_bson(bson_bytes)["k"].get<std::string>() == ill_formed_cases()[0].bytes);
     }
 }
+
+// The UBJSON and BJData writers bind the (possibly sanitized) key to a const
+// string_t&. If key_type is not string_t but converts to it, the converted
+// temporary must outlive that reference; this was a use-after-scope found by
+// AddressSanitizer. Keys exceed the small string optimization on purpose.
+TEST_CASE("UBJSON and BJData writers with an object_t whose key_type is not string_t")
+{
+    const std::string long_prefix(70, 'k');
+
+    SECTION("well-formed keys, every error_handler")
+    {
+        const std::string key1 = long_prefix + "-first";
+        const std::string key2 = long_prefix + "-second";
+
+        converting_key_json::object_t o;
+        o.emplace(converting_key(key1), 1);
+        o.emplace(converting_key(key2), "value");
+        const converting_key_json v(std::move(o));
+
+        json expected;
+        expected[key1] = 1;
+        expected[key2] = "value";
+
+        const std::array<std::pair<bool, bool>, 3> combos = {{{false, false}, {true, false}, {true, true}}};
+        for (const auto h : all_handlers())
+        {
+            CAPTURE(static_cast<int>(h))
+            for (const auto& combo : combos)
+            {
+                const bool use_count = combo.first;
+                const bool use_type = combo.second;
+                CAPTURE(use_count)
+                CAPTURE(use_type)
+
+                CHECK(json::from_ubjson(converting_key_json::to_ubjson(v, use_count, use_type, h)) == expected);
+                CHECK(json::from_bjdata(converting_key_json::to_bjdata(v, use_count, use_type, json::bjdata_version_t::draft2, h)) == expected);
+                CHECK(json::from_bjdata(converting_key_json::to_bjdata(v, use_count, use_type, json::bjdata_version_t::draft3, h)) == expected);
+            }
+        }
+    }
+
+    SECTION("ill-formed keys")
+    {
+        for (const auto& c : ill_formed_cases())
+        {
+            CAPTURE(c.name)
+            const std::string key = long_prefix + c.bytes;
+
+            converting_key_json::object_t o;
+            o.emplace(converting_key(key), 1);
+            const converting_key_json v(std::move(o));
+
+            CHECK_THROWS_AS(converting_key_json::to_ubjson(v, false, false, eh::strict), converting_key_json::type_error&);
+            CHECK_THROWS_AS(converting_key_json::to_bjdata(v, false, false, json::bjdata_version_t::draft2, eh::strict), converting_key_json::type_error&);
+
+            for (const auto h :
+                    {
+                        eh::replace, eh::ignore
+                    })
+            {
+                CAPTURE(static_cast<int>(h))
+                const std::string expected = dump_and_parse(key, h);
+
+                CHECK(json::from_ubjson(converting_key_json::to_ubjson(v, false, false, h)).begin().key() == expected);
+                CHECK(json::from_bjdata(converting_key_json::to_bjdata(v, false, false, json::bjdata_version_t::draft2, h)).begin().key() == expected);
+            }
+
+            CHECK(json::from_ubjson(converting_key_json::to_ubjson(v, false, false, eh::keep)).begin().key() == key);
+            CHECK(json::from_bjdata(converting_key_json::to_bjdata(v, false, false, json::bjdata_version_t::draft2, eh::keep)).begin().key() == key);
+        }
+    }
+
+    SECTION("nested deeper than the recursion limit")
+    {
+        // wrap the previous value, innermost first
+        converting_key_json v = 42;
+        json expected = 42;
+        for (int i = 199; i >= 0; --i)
+        {
+            const std::string key = "level-" + std::to_string(i) + "-" + std::string(64, 'x');
+
+            converting_key_json::object_t o;
+            o.emplace(converting_key(key), std::move(v));
+            v = converting_key_json(std::move(o));
+
+            json e;
+            e[key] = std::move(expected);
+            expected = std::move(e);
+        }
+
+        for (const auto h : all_handlers())
+        {
+            CAPTURE(static_cast<int>(h))
+            for (const bool use_count :
+                    {
+                        false, true
+                    })
+            {
+                CAPTURE(use_count)
+
+                CHECK(json::from_ubjson(converting_key_json::to_ubjson(v, use_count, false, h)) == expected);
+                CHECK(json::from_bjdata(converting_key_json::to_bjdata(v, use_count, false, json::bjdata_version_t::draft2, h)) == expected);
+            }
+        }
+    }
+}

tests/src/unit-bson.cpp

@@ -46,9 +46,7 @@ class huge_binary_t : public std::vector<std::uint8_t>
     }
 };
 
-using huge_binary_json = nlohmann::basic_json <
-                         std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t,
-                         double, std::allocator, nlohmann::adl_serializer, huge_binary_t, void >;
+using huge_binary_json = nlohmann::json::with_binary_t<huge_binary_t>;
 
 // a string type that can be made to report a size beyond INT32_MAX without
 // allocating that much memory, so BSON length overflow can be tested for
@@ -96,9 +94,7 @@ class huge_string_t : public std::string
     bool pretend_huge = false;
 };
 
-using huge_string_json = nlohmann::basic_json <
-                         std::map, std::vector, huge_string_t, bool, std::int64_t, std::uint64_t,
-                         double, std::allocator, nlohmann::adl_serializer, std::vector<std::uint8_t>, void >;
+using huge_string_json = nlohmann::json::with_string_t<huge_string_t>;
 } // namespace
 
 TEST_CASE("BSON")

tests/src/unit-cbor.cpp

@@ -28,6 +28,7 @@ using nlohmann::json;
 #include "make_test_data_available.hpp"
 #include "round_trip_corpus.hpp"
 #include "test_utils.hpp"
+#include "custom_object_key_type.hpp"
 #include "sax_countdown.hpp"
 using utils::SaxCountdown;
 
@@ -3357,3 +3358,55 @@ TEST_CASE("CBOR large strings and binaries (chunked reader)")
         }
     }
 }
+
+TEST_CASE("CBOR supports custom object key types")
+{
+    using custom_json = custom_object_key_test::json;
+    using custom_key = custom_object_key_test::key;
+
+    custom_json::object_t object;
+    object.emplace(custom_key{"short"}, 1);
+    object.emplace(
+              custom_key{"a key longer than twenty-three characters"},
+              2);
+
+    const custom_json value(std::move(object));
+    const auto encoded = custom_json::to_cbor(value);
+
+    CHECK(nlohmann::json::from_cbor(encoded) == nlohmann::json
+    {
+        {"short", 1},
+        {"a key longer than twenty-three characters", 2}
+    });
+}
+
+TEST_CASE("CBOR supports custom object key types nested deeper than the recursion depth limit")
+{
+    // below detail::recursion_depth_limit(), keys are written by
+    // write_cbor_iterative instead of write_cbor
+    using custom_json = custom_object_key_test::json;
+    using custom_key = custom_object_key_test::key;
+
+    const std::size_t depth = nlohmann::detail::recursion_depth_limit() + 10;
+
+    custom_json value = 1;
+    nlohmann::json expected = 1;
+    for (std::size_t i = 0; i < depth; ++i)
+    {
+        // alternate short keys with ones long enough to need a length byte
+        const std::string name = (i % 2 == 0) ? "k" + std::to_string(i)
+                                 : "a key longer than thirty-one characters " + std::to_string(i);
+
+        custom_json::object_t object;
+        object.emplace(custom_key{name}, std::move(value));
+        value = custom_json(std::move(object));
+
+        nlohmann::json::object_t expected_object;
+        expected_object.emplace(name, std::move(expected));
+        expected = nlohmann::json(std::move(expected_object));
+    }
+
+    const auto encoded = custom_json::to_cbor(value);
+    CHECK(encoded == nlohmann::json::to_cbor(expected));
+    CHECK(nlohmann::json::from_cbor(encoded) == expected);
+}

tests/src/unit-custom-base-class.cpp

@@ -400,20 +400,7 @@ class base_class_with_hidden_members
     std::size_t m_size = 42;
 };
 
-using json_with_hidden_base_members =
-    nlohmann::basic_json <
-    std::map,
-    std::vector,
-    std::string,
-    bool,
-    std::int64_t,
-    std::uint64_t,
-    double,
-    std::allocator,
-    nlohmann::adl_serializer,
-    std::vector<std::uint8_t>,
-    base_class_with_hidden_members
-    >;
+using json_with_hidden_base_members = nlohmann::json::with_base_class_t<base_class_with_hidden_members>;
 
 TEST_CASE("JSON Node as_base_class")
 {
@@ -459,19 +446,7 @@ struct const_member_base
     const int id = 7; // NOLINT(misc-non-private-member-variables-in-classes)
 };
 
-using json_with_const_base = nlohmann::basic_json <
-                             std::map,
-                             std::vector,
-                             std::string,
-                             bool,
-                             std::int64_t,
-                             std::uint64_t,
-                             double,
-                             std::allocator,
-                             nlohmann::adl_serializer,
-                             std::vector<std::uint8_t>,
-                             const_member_base
-                             >;
+using json_with_const_base = nlohmann::json::with_base_class_t<const_member_base>;
 
 // build an array nested @a depth levels deep, with the innermost value 1;
 // every level is constructed (never assigned), since const_member_base does

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

@@ -26,15 +26,11 @@ namespace
 
 // a BinaryType whose value type is signed: the elements must still be
 // processed as the numbers 0..255
-using char_binary_json = nlohmann::basic_json <
-                         std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t,
-                         double, std::allocator, nlohmann::adl_serializer, std::vector<char>, void >;
+using char_binary_json = nlohmann::json::with_binary_t<std::vector<char>>;
 
 #ifdef JSON_HAS_CPP_17
     // a BinaryType whose value type is not an integer type at all
-    using byte_binary_json = nlohmann::basic_json <
-    std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t,
-    double, std::allocator, nlohmann::adl_serializer, std::vector<std::byte>, void >;
+    using byte_binary_json = nlohmann::json::with_binary_t<std::vector<std::byte>>;
 #endif
 
 } // namespace

tests/src/unit-json_pointer.cpp

@@ -939,3 +939,114 @@ TEST_CASE("unescaping keeps a '~' that does not start an escape sequence")
     nlohmann::detail::unescape(s);
     CHECK(s == "~/~");
 }
+
+TEST_CASE("flatten of structured values")
+{
+    SECTION("values nested too deeply for the call stack (#5393)")
+    {
+        // flatten() used to recurse once per nesting level
+        const std::size_t depth = 100000;
+        for (const bool objects :
+                {
+                    false, true
+                })
+        {
+            CAPTURE(objects)
+            std::string text;
+            std::string path;
+            for (std::size_t i = 0; i < depth; ++i)
+            {
+                text += objects ? "{\"a\":" : "[";
+                path += objects ? "/a" : "/0";
+            }
+            text += "0";
+            text += std::string(depth, objects ? '}' : ']');
+            const auto value = json::parse(text);
+
+            const auto flat = value.flatten();
+            REQUIRE(flat.size() == 1);
+            REQUIRE(flat.begin().key().size() == path.size());
+            CHECK(flat.begin().key() == path);
+            CHECK(flat.begin().value() == 0);
+
+            // unflatten() is linear in the depth, so the value roundtrips
+            CHECK(flat.unflatten() == value);
+        }
+    }
+
+    SECTION("unflatten of a deeply nested pointer")
+    {
+        const std::size_t depth = 100000;
+        for (const bool objects :
+                {
+                    false, true
+                })
+        {
+            CAPTURE(objects)
+            std::string path;
+            for (std::size_t i = 0; i < depth; ++i)
+            {
+                path += objects ? "/a" : "/0";
+            }
+
+            json flat = json::object();
+            flat[path] = 1;
+            const json value = flat.unflatten();
+
+            // walk down iteratively
+            std::size_t levels = 0;
+            const json* current = &value;
+            while (objects ? current->is_object() : current->is_array())
+            {
+                REQUIRE(current->size() == 1);
+                current = objects ? &current->at("a") : &current->at(0);
+                ++levels;
+            }
+            CHECK(levels == depth);
+            CHECK(*current == 1);
+        }
+    }
+
+    SECTION("unflatten does not depend on the iteration order")
+    {
+        // the "0" key comes after its sibling in iteration order
+        const nlohmann::ordered_json flat_array = nlohmann::ordered_json::parse(R"({"/a/1": 2, "/a/0": 1})");
+        CHECK(flat_array.unflatten() == nlohmann::ordered_json::parse(R"({"a": [1, 2]})"));
+
+        const nlohmann::ordered_json flat_object = nlohmann::ordered_json::parse(R"({"/b/1": 2})");
+        CHECK(flat_object.unflatten() == nlohmann::ordered_json::parse(R"({"b": {"1": 2}})"));
+    }
+
+    SECTION("objects and arrays interleaved")
+    {
+        const json value =
+        {
+            {"a", {1, {{"b", json::array()}, {"c", json::object()}}, json::array({{{"x~/", {true, nullptr}}}})}},
+            {"a/b", {{"~", 1}}},
+            {"z", "s"}
+        };
+
+        const json expected =
+        {
+            {"/a/0", 1},
+            {"/a/1/b", nullptr},
+            {"/a/1/c", nullptr},
+            {"/a/2/0/x~0~1/0", true},
+            {"/a/2/0/x~0~1/1", nullptr},
+            {"/a~1b/~0", 1},
+            {"/z", "s"}
+        };
+
+        CHECK(value.flatten() == expected);
+    }
+
+    SECTION("order of the entries of an ordered_json")
+    {
+        const auto value = nlohmann::ordered_json::parse(
+                               R"({"z":"s","a/b":{"~":1,"k":[]},"a":[1,{"c":{},"b":[]},[{"x~/":[true,null],"w":2}]]})");
+
+        const auto flat = value.flatten();
+        CHECK(flat.dump() ==
+              R"({"/z":"s","/a~1b/~0":1,"/a~1b/k":null,"/a/0":1,"/a/1/c":null,"/a/1/b":null,"/a/2/0/x~0~1/0":true,"/a/2/0/x~0~1/1":null,"/a/2/0/w":2})");
+    }
+}

tests/src/unit-msgpack.cpp

@@ -31,6 +31,7 @@ using nlohmann::json;
 #include "make_test_data_available.hpp"
 #include "round_trip_corpus.hpp"
 #include "test_utils.hpp"
+#include "custom_object_key_type.hpp"
 #include "sax_countdown.hpp"
 using utils::SaxCountdown;
 
@@ -2201,10 +2202,7 @@ struct huge_array : std::vector<T, A>
     }
 };
 
-using huge_array_json = nlohmann::basic_json <
-                        std::map, huge_array, std::string, bool, std::int64_t, std::uint64_t,
-                        double, std::allocator, nlohmann::adl_serializer,
-                        std::vector<std::uint8_t>, void >;
+using huge_array_json = nlohmann::json::with_array_t<huge_array>;
 
 TEST_CASE("MessagePack Size above uint32 for array")
 {
@@ -2249,18 +2247,7 @@ template<typename K, typename V,
     }
 };
 
-using huge_object_json = nlohmann::basic_json <
-                         huge_map,
-                         std::vector,
-                         std::string,
-                         bool,
-                         std::int64_t,
-                         std::uint64_t,
-                         double,
-                         std::allocator,
-                         nlohmann::adl_serializer,
-                         std::vector<std::uint8_t>,
-                         void >;
+using huge_object_json = nlohmann::json::with_object_t<huge_map>;
 
 TEST_CASE("MessagePack Size above uint32 for object")
 {
@@ -2295,18 +2282,7 @@ struct huge_string : std::string
     }
 };
 
-using huge_string_json = nlohmann::basic_json <
-                         std::map,
-                         std::vector,
-                         huge_string,
-                         bool,
-                         std::int64_t,
-                         std::uint64_t,
-                         double,
-                         std::allocator,
-                         nlohmann::adl_serializer,
-                         std::vector<std::uint8_t>,
-                         void >;
+using huge_string_json = nlohmann::json::with_string_t<huge_string>;
 
 TEST_CASE("MessagePack Size above uint32 for string")
 {
@@ -2329,18 +2305,7 @@ struct huge_binary : std::vector<std::uint8_t>
     }
 };
 
-using huge_binary_json = nlohmann::basic_json <
-                         std::map,
-                         std::vector,
-                         std::string,
-                         bool,
-                         std::int64_t,
-                         std::uint64_t,
-                         double,
-                         std::allocator,
-                         nlohmann::adl_serializer,
-                         huge_binary,
-                         void >;
+using huge_binary_json = nlohmann::json::with_binary_t<huge_binary>;
 
 TEST_CASE("MessagePack Size above uint32 for binary")
 {
@@ -2390,14 +2355,10 @@ class beyond_uint32_string_t : public std::string
     }
 };
 
-using beyond_uint32_string_json = nlohmann::basic_json <
-                                  std::map, std::vector, beyond_uint32_string_t, bool, std::int64_t, std::uint64_t,
-                                  double, std::allocator, nlohmann::adl_serializer, std::vector<std::uint8_t>, void >;
+using beyond_uint32_string_json = nlohmann::json::with_string_t<beyond_uint32_string_t>;
 #endif
 
-using beyond_uint32_binary_json = nlohmann::basic_json <
-                                  std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t,
-                                  double, std::allocator, nlohmann::adl_serializer, beyond_uint32_binary_t, void >;
+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")
@@ -2522,3 +2483,55 @@ TEST_CASE("MessagePack large strings and binaries (chunked reader)")
         }
     }
 }
+
+TEST_CASE("MessagePack supports custom object key types")
+{
+    using custom_json = custom_object_key_test::json;
+    using custom_key = custom_object_key_test::key;
+
+    custom_json::object_t object;
+    object.emplace(custom_key{"short"}, 1);
+    object.emplace(
+              custom_key{"a key longer than thirty-one characters"},
+              2);
+
+    const custom_json value(std::move(object));
+    const auto encoded = custom_json::to_msgpack(value);
+
+    CHECK(nlohmann::json::from_msgpack(encoded) == nlohmann::json
+    {
+        {"short", 1},
+        {"a key longer than thirty-one characters", 2}
+    });
+}
+
+TEST_CASE("MessagePack supports custom object key types nested deeper than the recursion depth limit")
+{
+    // below detail::recursion_depth_limit(), keys are written by
+    // write_msgpack_iterative instead of write_msgpack
+    using custom_json = custom_object_key_test::json;
+    using custom_key = custom_object_key_test::key;
+
+    const std::size_t depth = nlohmann::detail::recursion_depth_limit() + 10;
+
+    custom_json value = 1;
+    nlohmann::json expected = 1;
+    for (std::size_t i = 0; i < depth; ++i)
+    {
+        // alternate short keys with ones long enough to need a length byte
+        const std::string name = (i % 2 == 0) ? "k" + std::to_string(i)
+                                 : "a key longer than thirty-one characters " + std::to_string(i);
+
+        custom_json::object_t object;
+        object.emplace(custom_key{name}, std::move(value));
+        value = custom_json(std::move(object));
+
+        nlohmann::json::object_t expected_object;
+        expected_object.emplace(name, std::move(expected));
+        expected = nlohmann::json(std::move(expected_object));
+    }
+
+    const auto encoded = custom_json::to_msgpack(value);
+    CHECK(encoded == nlohmann::json::to_msgpack(expected));
+    CHECK(nlohmann::json::from_msgpack(encoded) == expected);
+}

tests/src/unit-ordered_json2.cpp

@@ -217,16 +217,7 @@ void int_to_string(alt_string& target, std::size_t value)
     target = std::to_string(value).c_str();
 }
 
-using alt_json = nlohmann::basic_json <
-                 std::map,
-                 std::vector,
-                 alt_string,
-                 bool,
-                 std::int64_t,
-                 std::uint64_t,
-                 double,
-                 std::allocator,
-                 nlohmann::adl_serializer >;
+using alt_json = nlohmann::json::with_string_t<alt_string>;
 
 bool operator<(const char* op1, const alt_string& op2) noexcept
 {