Mark the parse callback in the new test noexcept

GCC's -Wnoexcept (part of the ci_test_gcc warning set) rejects the
lambda passed to parse() because it cannot throw but is not declared
noexcept, matching the existing callback in unit-regression2.cpp.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

docs/mkdocs/docs/api/basic_json/swap.md

@@ -34,10 +34,14 @@ void swap(typename binary_t::container_type& other);
 ```
 
 1. Exchanges the contents of the JSON value with those of `other`. Does not invoke any move, copy, or swap operations on
-   individual elements. All iterators and references remain valid. The past-the-end iterator is invalidated. 
+   individual elements. All iterators and references remain valid. The past-the-end iterator is invalidated. If macro
+   [`JSON_DIAGNOSTIC_POSITIONS`](../macros/json_diagnostic_positions.md) is defined to `#!cpp 1`, the
+   [`start_pos()`](start_pos.md)/[`end_pos()`](end_pos.md) diagnostic positions are exchanged along with the value.
 2. Exchanges the contents of the JSON value from `left` with those of `right`. Does not invoke any move, copy, or swap
    operations on individual elements. All iterators and references remain valid. The past-the-end iterator is
-   invalidated. Implemented as a friend function callable via ADL.
+   invalidated. Implemented as a friend function callable via ADL. If macro
+   [`JSON_DIAGNOSTIC_POSITIONS`](../macros/json_diagnostic_positions.md) is defined to `#!cpp 1`, the
+   [`start_pos()`](start_pos.md)/[`end_pos()`](end_pos.md) diagnostic positions are exchanged along with the value.
 3. Exchanges the contents of a JSON array with those of `other`. Does not invoke any move, copy, or swap operations on
    individual elements. All iterators and references remain valid. The past-the-end iterator is invalidated. 
 4. Exchanges the contents of a JSON object with those of `other`. Does not invoke any move, copy, or swap operations on

include/nlohmann/detail/input/json_sax.hpp

@@ -8,16 +8,17 @@
 
 #pragma once
 
-#include <algorithm> // find_if
+#include <algorithm> // min
 #include <cstddef>
 #include <string> // string
 #include <type_traits> // enable_if_t
-#include <utility> // move, pair
+#include <utility> // move
 #include <vector> // vector
 
 #include <nlohmann/detail/exceptions.hpp>
 #include <nlohmann/detail/input/lexer.hpp>
 #include <nlohmann/detail/macro_scope.hpp>
+#include <nlohmann/detail/meta/cpp_future.hpp>
 #include <nlohmann/detail/string_concat.hpp>
 NLOHMANN_JSON_NAMESPACE_BEGIN
 
@@ -151,6 +152,29 @@ constexpr std::size_t unknown_size()
     return (std::numeric_limits<std::size_t>::max)();
 }
 
+/*!
+@brief reserve capacity for @a len elements in array @a arr
+
+Reserving upfront avoids repeated reallocations while the elements are added,
+but the reservation is capped so a bogus/hostile length (which is not bounded
+by max_size(), unlike e.g. std::vector) cannot trigger an oversized allocation
+for a small or truncated input.
+
+The overload below is selected for array types without reserve() (e.g.,
+std::deque), which are then left untouched.
+*/
+template<typename ArrayType>
+auto reserve_array(ArrayType& arr, std::size_t len, priority_tag<1> /*unused*/)
+-> decltype(arr.reserve(len), void())
+{
+    constexpr std::size_t reserve_cap = 16384;
+    arr.reserve((std::min)(len, reserve_cap));
+}
+
+template<typename ArrayType>
+inline void reserve_array(ArrayType& /*arr*/, std::size_t /*len*/, priority_tag<0> /*unused*/)
+{}
+
 /*!
 @brief SAX implementation to create a JSON value from SAX events
 
@@ -306,6 +330,11 @@ class json_sax_dom_parser
             JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
         }
 
+        if (len != detail::unknown_size())
+        {
+            reserve_array(*ref_stack.back()->m_data.m_value.array, len, priority_tag<1> {});
+        }
+
         return true;
     }
 
@@ -602,17 +631,7 @@ class json_sax_dom_callback_parser
         // add discarded value at the given key and store the reference for later
         if (keep && ref_stack.back())
         {
-            auto& obj = *ref_stack.back()->m_data.m_value.object;
-            const auto it = obj.find(val);
-            if (it != obj.end())
-            {
-                // this is a duplicate key (legal in JSON); remember its
-                // current value so it can be restored later if the new
-                // value is rejected by the callback, instead of being
-                // erased together with the discarded placeholder
-                duplicate_key_stash.emplace_back(&(it->second), it->second);
-            }
-            object_element = &(obj[val] = discarded);
+            object_element = &(ref_stack.back()->m_data.m_value.object->operator[](val) = discarded);
         }
 
         return true;
@@ -624,18 +643,13 @@ class json_sax_dom_callback_parser
         {
             if (!callback(static_cast<int>(ref_stack.size()) - 1, parse_event_t::object_end, *ref_stack.back()))
             {
-                // discard object, unless this slot holds a duplicate key's
-                // previous value pending restoration, in which case that
-                // value is restored instead of being discarded
-                if (!resolve_duplicate_key_stash(ref_stack.back(), true))
-                {
-                    *ref_stack.back() = discarded;
+                // discard object
+                *ref_stack.back() = discarded;
 
 #if JSON_DIAGNOSTIC_POSITIONS
-                    // Set start/end positions for discarded object.
-                    handle_diagnostic_positions_for_json_value(*ref_stack.back());
+                // Set start/end positions for discarded object.
+                handle_diagnostic_positions_for_json_value(*ref_stack.back());
 #endif
-                }
             }
             else
             {
@@ -649,10 +663,6 @@ class json_sax_dom_callback_parser
 #endif
 
                 ref_stack.back()->set_parents();
-                // this object is finally, definitively kept; drop any
-                // pending duplicate-key stash entry for its slot since it
-                // can no longer be restored
-                resolve_duplicate_key_stash(ref_stack.back(), false);
             }
         }
 
@@ -703,6 +713,11 @@ class json_sax_dom_callback_parser
             {
                 JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
             }
+
+            if (len != detail::unknown_size())
+            {
+                reserve_array(*ref_stack.back()->m_data.m_value.array, len, priority_tag<1> {});
+            }
         }
 
         return true;
@@ -728,25 +743,16 @@ class json_sax_dom_callback_parser
 #endif
 
                 ref_stack.back()->set_parents();
-                // this array is finally, definitively kept; drop any
-                // pending duplicate-key stash entry for its slot since it
-                // can no longer be restored
-                resolve_duplicate_key_stash(ref_stack.back(), false);
             }
             else
             {
-                // discard array, unless this slot holds a duplicate key's
-                // previous value pending restoration, in which case that
-                // value is restored instead of being discarded
-                if (!resolve_duplicate_key_stash(ref_stack.back(), true))
-                {
-                    *ref_stack.back() = discarded;
+                // discard array
+                *ref_stack.back() = discarded;
 
 #if JSON_DIAGNOSTIC_POSITIONS
-                    // Set start/end positions for discarded array.
-                    handle_diagnostic_positions_for_json_value(*ref_stack.back());
+                // Set start/end positions for discarded array.
+                handle_diagnostic_positions_for_json_value(*ref_stack.back());
 #endif
-                }
             }
         }
 
@@ -880,35 +886,6 @@ class json_sax_dom_callback_parser
         return string_t{};
     }
 
-    /// if there is a pending duplicate-key stash entry for this exact slot,
-    /// remove it from the stash; if restore_value is true, the stashed
-    /// previous value is moved back into the slot first (use this when the
-    /// new value at that slot was rejected); otherwise the stash entry is
-    /// simply dropped (use this when the new value was accepted, so it
-    /// correctly supersedes the old one and no restore should ever happen
-    /// for this slot again)
-    /// @return whether a matching stash entry was found (and processed)
-    bool resolve_duplicate_key_stash(BasicJsonType* slot, bool restore_value)
-    {
-        const auto it = std::find_if(duplicate_key_stash.begin(), duplicate_key_stash.end(),
-                                     [slot](const std::pair<BasicJsonType*, BasicJsonType>& entry)
-        {
-            return entry.first == slot;
-        });
-
-        if (it == duplicate_key_stash.end())
-        {
-            return false;
-        }
-
-        if (restore_value)
-        {
-            *slot = std::move(it->second);
-        }
-        duplicate_key_stash.erase(it);
-        return true;
-    }
-
     /*!
     @brief remove the discarded value the callback rejected from its parent
 
@@ -920,14 +897,12 @@ class json_sax_dom_callback_parser
 
     Finding no discarded value there means none was stored in the first place -
     the callback rejected the value before it reached its parent - so there is
-    nothing to remove. If the discarded slot instead holds a duplicate key's
-    stashed previous value pending restoration, that value is restored instead
-    of the slot being erased.
+    nothing to remove.
 
     @param[in,out] parent  the container to remove the rejected value from
     @param[in] key  the key the value was stored under; unused for arrays
     */
-    void remove_discarded_value(BasicJsonType& parent, const string_t& key)
+    static void remove_discarded_value(BasicJsonType& parent, const string_t& key)
     {
         if (parent.is_array())
         {
@@ -943,10 +918,7 @@ class json_sax_dom_callback_parser
             const auto it = object.find(key);
             if (it != object.end() && it->second.is_discarded())
             {
-                if (!resolve_duplicate_key_stash(&(it->second), true))
-                {
-                    object.erase(it);
-                }
+                object.erase(it);
             }
         }
     }
@@ -1048,16 +1020,6 @@ class json_sax_dom_callback_parser
 
         JSON_ASSERT(object_element);
         *object_element = std::move(value);
-        if (!skip_callback)
-        {
-            // this scalar value finally, definitively replaces whatever was
-            // at this slot; drop any pending duplicate-key stash entry for
-            // it since it can no longer be restored (a container value at
-            // this slot is resolved later, in end_object()/end_array(),
-            // since skip_callback is true for the placeholder handling that
-            // happens here for those)
-            resolve_duplicate_key_stash(object_element, false);
-        }
         return {true, object_element};
     }
 
@@ -1077,12 +1039,6 @@ class json_sax_dom_callback_parser
     std::vector<string_t> container_key_stack {}; // NOLINT(readability-redundant-member-init)
     /// helper to hold the reference for the next object element
     BasicJsonType* object_element = nullptr;
-    /// stash of (slot pointer, previous value) for object members that
-    /// already existed when key() was called again for the same key
-    /// (duplicate keys); used to restore the previous value if the new
-    /// value is later rejected by the callback, instead of erasing the
-    /// member entirely
-    std::vector<std::pair<BasicJsonType*, BasicJsonType>> duplicate_key_stash {};
     /// whether a syntax error occurred
     bool errored = false;
     /// callback function

include/nlohmann/json.hpp

@@ -3576,6 +3576,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         std::swap(m_data.m_type, other.m_data.m_type);
         std::swap(m_data.m_value, other.m_data.m_value);
 
+#if JSON_DIAGNOSTIC_POSITIONS
+        std::swap(start_position, other.start_position);
+        std::swap(end_position, other.end_position);
+#endif
+
         set_parents();
         other.set_parents();
         assert_invariant();
@@ -3602,7 +3607,6 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         {
             using std::swap;
             swap(*(m_data.m_value.array), other);
-            set_parents();
         }
         else
         {
@@ -3619,7 +3623,6 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         {
             using std::swap;
             swap(*(m_data.m_value.object), other);
-            set_parents();
         }
         else
         {
@@ -5270,139 +5273,34 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
             case value_t::object:
             {
-                // first pass: record, for every source key, whether it is
-                // common to both objects (in source's iteration order) or
-                // was deleted (i.e., in source but not in target) -- this is
-                // a by-product of the target.find() call already needed to
-                // tell the two cases apart, so it adds no extra lookups. The
-                // "remove" ops themselves are emitted later, interleaved
-                // with the recursive per-key diffs in the fast path below,
-                // to match source's original iteration order (as the
-                // original, pre-reordering-aware implementation did) instead
-                // of grouping all removes before all recursive diffs.
-                std::vector<typename object_t::key_type> common_keys_source_order;
+                // first pass: traverse this object's elements
                 for (auto it = source.cbegin(); it != source.cend(); ++it)
                 {
+                    // escape the key name to be used in a JSON patch
+                    const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
+
                     if (target.find(it.key()) != target.end())
                     {
-                        common_keys_source_order.push_back(it.key());
-                    }
-                }
-
-                // second pass: find keys that were added (i.e., in target but
-                // not in source), and record the keys common to both, in
-                // target's iteration order -- again a by-product of the
-                // source.find() call already needed to detect added keys. At
-                // the same time, determine whether every added key comes
-                // after every common key in target's order (a precondition
-                // for the fast path below, which only ever appends new keys
-                // at the very end): for an object_t whose iteration order is
-                // a pure function of the key set (e.g. the default std::map,
-                // which always iterates in sorted key order), the order
-                // check further below is always true and this whole
-                // mechanism is effectively a no-op; it only matters for a
-                // reorderable object_t such as the one backing `ordered_json`.
-                // patch ops for keys that were added (i.e., in target but not
-                // in source); built here so the fast path below can reuse
-                // them without a second source.find() per target key. Only
-                // used by the fast path -- the slow (reordering) path
-                // rebuilds "add" ops for every key itself.
-                std::vector<typename object_t::key_type> common_keys_target_order;
-                basic_json added_ops(value_t::array);
-                bool new_keys_form_suffix = true;
-                bool seen_new_key = false;
-                for (auto it = target.cbegin(); it != target.cend(); ++it)
-                {
-                    if (source.find(it.key()) == source.end())
-                    {
-                        seen_new_key = true;
-                        const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
-                        added_ops.push_back(
-                        {
-                            {"op", "add"}, {"path", path_key},
-                            {"value", it.value()}
-                        });
+                        // recursive call to compare object values at key it
+                        auto temp_diff = diff(it.value(), target[it.key()], path_key);
+                        result.insert(result.end(), temp_diff.begin(), temp_diff.end());
                     }
                     else
                     {
-                        common_keys_target_order.push_back(it.key());
-                        if (seen_new_key)
-                        {
-                            new_keys_form_suffix = false;
-                        }
-                    }
-                }
-
-                if (common_keys_source_order == common_keys_target_order && new_keys_form_suffix)
-                {
-                    // fast path: order of common keys already matches (or the
-                    // object_t's iteration order does not depend on
-                    // insertion history), so a plain per-key recursive diff
-                    // is correct and minimal, as before. common_keys_source_order
-                    // is, by construction, the subsequence of source's keys
-                    // that are common to both objects, in source's iteration
-                    // order -- so it can be walked in lockstep with `source`
-                    // using a cheap key comparison instead of another lookup.
-                    // Deleted keys (those source keys not in common_keys_source_order)
-                    // are interleaved here too, in source's original order, to
-                    // match the historical (pre-reordering-aware) output order.
-                    auto common_it = common_keys_source_order.cbegin();
-                    for (auto it = source.cbegin(); it != source.cend(); ++it)
-                    {
-                        if (common_it != common_keys_source_order.cend() && it.key() == *common_it)
-                        {
-                            const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
-                            auto temp_diff = diff(it.value(), target[it.key()], path_key);
-                            result.insert(result.end(), temp_diff.begin(), temp_diff.end());
-                            ++common_it;
-                        }
-                        else
-                        {
-                            // found a key that is not in target -> remove it
-                            const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
-                            result.push_back(object(
-                            {
-                                {"op", "remove"}, {"path", path_key}
-                            }));
-                        }
-                    }
-
-                    // append the "add" ops for brand-new keys collected above
-                    // during the pass over target -- no second source.find()
-                    // per target key needed
-                    result.insert(result.end(), added_ops.begin(), added_ops.end());
-                }
-                else
-                {
-                    // slow path: the common keys are in a different relative
-                    // order in source and target (only possible for a
-                    // reorderable object_t like ordered_map). Building a
-                    // minimal reordering patch is a nontrivial (LCS-like)
-                    // problem; instead, remove every source key -- both
-                    // deleted keys (which must be removed regardless) and
-                    // common keys (removed so they can be re-added in
-                    // target's order) -- and re-add every key that should
-                    // remain, with its final target value, in target's
-                    // order. basic_json::patch()'s "add" operation on an
-                    // object uses operator[], which appends at the end for a
-                    // vector-backed insertion-ordered map when the key does
-                    // not already exist -- so removing a key and then adding
-                    // it moves it to the end, fixing its position.
-                    for (auto it = source.cbegin(); it != source.cend(); ++it)
-                    {
-                        const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
+                        // found a key that is not in o -> remove it
                         result.push_back(object(
                         {
                             {"op", "remove"}, {"path", path_key}
                         }));
                     }
+                }
 
-                    // add every key that is either common (just removed
-                    // above) or brand new, in target's iteration order, so
-                    // that the final order after applying the patch matches
-                    // target exactly
-                    for (auto it = target.cbegin(); it != target.cend(); ++it)
+                // second pass: traverse other object's elements
+                for (auto it = target.cbegin(); it != target.cend(); ++it)
+                {
+                    if (source.find(it.key()) == source.end())
                     {
+                        // found a key that is not in this -> add it
                         const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
                         result.push_back(
                         {

single_include/nlohmann/json.hpp

@@ -7892,11 +7892,11 @@ NLOHMANN_JSON_NAMESPACE_END
 
 
 
-#include <algorithm> // find_if
+#include <algorithm> // min
 #include <cstddef>
 #include <string> // string
 #include <type_traits> // enable_if_t
-#include <utility> // move, pair
+#include <utility> // move
 #include <vector> // vector
 
 // #include <nlohmann/detail/exceptions.hpp>
@@ -10730,6 +10730,8 @@ NLOHMANN_JSON_NAMESPACE_END
 
 // #include <nlohmann/detail/macro_scope.hpp>
 
+// #include <nlohmann/detail/meta/cpp_future.hpp>
+
 // #include <nlohmann/detail/string_concat.hpp>
 
 NLOHMANN_JSON_NAMESPACE_BEGIN
@@ -10864,6 +10866,29 @@ constexpr std::size_t unknown_size()
     return (std::numeric_limits<std::size_t>::max)();
 }
 
+/*!
+@brief reserve capacity for @a len elements in array @a arr
+
+Reserving upfront avoids repeated reallocations while the elements are added,
+but the reservation is capped so a bogus/hostile length (which is not bounded
+by max_size(), unlike e.g. std::vector) cannot trigger an oversized allocation
+for a small or truncated input.
+
+The overload below is selected for array types without reserve() (e.g.,
+std::deque), which are then left untouched.
+*/
+template<typename ArrayType>
+auto reserve_array(ArrayType& arr, std::size_t len, priority_tag<1> /*unused*/)
+-> decltype(arr.reserve(len), void())
+{
+    constexpr std::size_t reserve_cap = 16384;
+    arr.reserve((std::min)(len, reserve_cap));
+}
+
+template<typename ArrayType>
+inline void reserve_array(ArrayType& /*arr*/, std::size_t /*len*/, priority_tag<0> /*unused*/)
+{}
+
 /*!
 @brief SAX implementation to create a JSON value from SAX events
 
@@ -11019,6 +11044,11 @@ class json_sax_dom_parser
             JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
         }
 
+        if (len != detail::unknown_size())
+        {
+            reserve_array(*ref_stack.back()->m_data.m_value.array, len, priority_tag<1> {});
+        }
+
         return true;
     }
 
@@ -11315,17 +11345,7 @@ class json_sax_dom_callback_parser
         // add discarded value at the given key and store the reference for later
         if (keep && ref_stack.back())
         {
-            auto& obj = *ref_stack.back()->m_data.m_value.object;
-            const auto it = obj.find(val);
-            if (it != obj.end())
-            {
-                // this is a duplicate key (legal in JSON); remember its
-                // current value so it can be restored later if the new
-                // value is rejected by the callback, instead of being
-                // erased together with the discarded placeholder
-                duplicate_key_stash.emplace_back(&(it->second), it->second);
-            }
-            object_element = &(obj[val] = discarded);
+            object_element = &(ref_stack.back()->m_data.m_value.object->operator[](val) = discarded);
         }
 
         return true;
@@ -11337,18 +11357,13 @@ class json_sax_dom_callback_parser
         {
             if (!callback(static_cast<int>(ref_stack.size()) - 1, parse_event_t::object_end, *ref_stack.back()))
             {
-                // discard object, unless this slot holds a duplicate key's
-                // previous value pending restoration, in which case that
-                // value is restored instead of being discarded
-                if (!resolve_duplicate_key_stash(ref_stack.back(), true))
-                {
-                    *ref_stack.back() = discarded;
+                // discard object
+                *ref_stack.back() = discarded;
 
 #if JSON_DIAGNOSTIC_POSITIONS
-                    // Set start/end positions for discarded object.
-                    handle_diagnostic_positions_for_json_value(*ref_stack.back());
+                // Set start/end positions for discarded object.
+                handle_diagnostic_positions_for_json_value(*ref_stack.back());
 #endif
-                }
             }
             else
             {
@@ -11362,10 +11377,6 @@ class json_sax_dom_callback_parser
 #endif
 
                 ref_stack.back()->set_parents();
-                // this object is finally, definitively kept; drop any
-                // pending duplicate-key stash entry for its slot since it
-                // can no longer be restored
-                resolve_duplicate_key_stash(ref_stack.back(), false);
             }
         }
 
@@ -11416,6 +11427,11 @@ class json_sax_dom_callback_parser
             {
                 JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
             }
+
+            if (len != detail::unknown_size())
+            {
+                reserve_array(*ref_stack.back()->m_data.m_value.array, len, priority_tag<1> {});
+            }
         }
 
         return true;
@@ -11441,25 +11457,16 @@ class json_sax_dom_callback_parser
 #endif
 
                 ref_stack.back()->set_parents();
-                // this array is finally, definitively kept; drop any
-                // pending duplicate-key stash entry for its slot since it
-                // can no longer be restored
-                resolve_duplicate_key_stash(ref_stack.back(), false);
             }
             else
             {
-                // discard array, unless this slot holds a duplicate key's
-                // previous value pending restoration, in which case that
-                // value is restored instead of being discarded
-                if (!resolve_duplicate_key_stash(ref_stack.back(), true))
-                {
-                    *ref_stack.back() = discarded;
+                // discard array
+                *ref_stack.back() = discarded;
 
 #if JSON_DIAGNOSTIC_POSITIONS
-                    // Set start/end positions for discarded array.
-                    handle_diagnostic_positions_for_json_value(*ref_stack.back());
+                // Set start/end positions for discarded array.
+                handle_diagnostic_positions_for_json_value(*ref_stack.back());
 #endif
-                }
             }
         }
 
@@ -11593,35 +11600,6 @@ class json_sax_dom_callback_parser
         return string_t{};
     }
 
-    /// if there is a pending duplicate-key stash entry for this exact slot,
-    /// remove it from the stash; if restore_value is true, the stashed
-    /// previous value is moved back into the slot first (use this when the
-    /// new value at that slot was rejected); otherwise the stash entry is
-    /// simply dropped (use this when the new value was accepted, so it
-    /// correctly supersedes the old one and no restore should ever happen
-    /// for this slot again)
-    /// @return whether a matching stash entry was found (and processed)
-    bool resolve_duplicate_key_stash(BasicJsonType* slot, bool restore_value)
-    {
-        const auto it = std::find_if(duplicate_key_stash.begin(), duplicate_key_stash.end(),
-                                     [slot](const std::pair<BasicJsonType*, BasicJsonType>& entry)
-        {
-            return entry.first == slot;
-        });
-
-        if (it == duplicate_key_stash.end())
-        {
-            return false;
-        }
-
-        if (restore_value)
-        {
-            *slot = std::move(it->second);
-        }
-        duplicate_key_stash.erase(it);
-        return true;
-    }
-
     /*!
     @brief remove the discarded value the callback rejected from its parent
 
@@ -11633,14 +11611,12 @@ class json_sax_dom_callback_parser
 
     Finding no discarded value there means none was stored in the first place -
     the callback rejected the value before it reached its parent - so there is
-    nothing to remove. If the discarded slot instead holds a duplicate key's
-    stashed previous value pending restoration, that value is restored instead
-    of the slot being erased.
+    nothing to remove.
 
     @param[in,out] parent  the container to remove the rejected value from
     @param[in] key  the key the value was stored under; unused for arrays
     */
-    void remove_discarded_value(BasicJsonType& parent, const string_t& key)
+    static void remove_discarded_value(BasicJsonType& parent, const string_t& key)
     {
         if (parent.is_array())
         {
@@ -11656,10 +11632,7 @@ class json_sax_dom_callback_parser
             const auto it = object.find(key);
             if (it != object.end() && it->second.is_discarded())
             {
-                if (!resolve_duplicate_key_stash(&(it->second), true))
-                {
-                    object.erase(it);
-                }
+                object.erase(it);
             }
         }
     }
@@ -11761,16 +11734,6 @@ class json_sax_dom_callback_parser
 
         JSON_ASSERT(object_element);
         *object_element = std::move(value);
-        if (!skip_callback)
-        {
-            // this scalar value finally, definitively replaces whatever was
-            // at this slot; drop any pending duplicate-key stash entry for
-            // it since it can no longer be restored (a container value at
-            // this slot is resolved later, in end_object()/end_array(),
-            // since skip_callback is true for the placeholder handling that
-            // happens here for those)
-            resolve_duplicate_key_stash(object_element, false);
-        }
         return {true, object_element};
     }
 
@@ -11790,12 +11753,6 @@ class json_sax_dom_callback_parser
     std::vector<string_t> container_key_stack {}; // NOLINT(readability-redundant-member-init)
     /// helper to hold the reference for the next object element
     BasicJsonType* object_element = nullptr;
-    /// stash of (slot pointer, previous value) for object members that
-    /// already existed when key() was called again for the same key
-    /// (duplicate keys); used to restore the previous value if the new
-    /// value is later rejected by the callback, instead of erasing the
-    /// member entirely
-    std::vector<std::pair<BasicJsonType*, BasicJsonType>> duplicate_key_stash {};
     /// whether a syntax error occurred
     bool errored = false;
     /// callback function
@@ -27388,6 +27345,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         std::swap(m_data.m_type, other.m_data.m_type);
         std::swap(m_data.m_value, other.m_data.m_value);
 
+#if JSON_DIAGNOSTIC_POSITIONS
+        std::swap(start_position, other.start_position);
+        std::swap(end_position, other.end_position);
+#endif
+
         set_parents();
         other.set_parents();
         assert_invariant();
@@ -27414,7 +27376,6 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         {
             using std::swap;
             swap(*(m_data.m_value.array), other);
-            set_parents();
         }
         else
         {
@@ -27431,7 +27392,6 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         {
             using std::swap;
             swap(*(m_data.m_value.object), other);
-            set_parents();
         }
         else
         {
@@ -29082,139 +29042,34 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
             case value_t::object:
             {
-                // first pass: record, for every source key, whether it is
-                // common to both objects (in source's iteration order) or
-                // was deleted (i.e., in source but not in target) -- this is
-                // a by-product of the target.find() call already needed to
-                // tell the two cases apart, so it adds no extra lookups. The
-                // "remove" ops themselves are emitted later, interleaved
-                // with the recursive per-key diffs in the fast path below,
-                // to match source's original iteration order (as the
-                // original, pre-reordering-aware implementation did) instead
-                // of grouping all removes before all recursive diffs.
-                std::vector<typename object_t::key_type> common_keys_source_order;
+                // first pass: traverse this object's elements
                 for (auto it = source.cbegin(); it != source.cend(); ++it)
                 {
+                    // escape the key name to be used in a JSON patch
+                    const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
+
                     if (target.find(it.key()) != target.end())
                     {
-                        common_keys_source_order.push_back(it.key());
-                    }
-                }
-
-                // second pass: find keys that were added (i.e., in target but
-                // not in source), and record the keys common to both, in
-                // target's iteration order -- again a by-product of the
-                // source.find() call already needed to detect added keys. At
-                // the same time, determine whether every added key comes
-                // after every common key in target's order (a precondition
-                // for the fast path below, which only ever appends new keys
-                // at the very end): for an object_t whose iteration order is
-                // a pure function of the key set (e.g. the default std::map,
-                // which always iterates in sorted key order), the order
-                // check further below is always true and this whole
-                // mechanism is effectively a no-op; it only matters for a
-                // reorderable object_t such as the one backing `ordered_json`.
-                // patch ops for keys that were added (i.e., in target but not
-                // in source); built here so the fast path below can reuse
-                // them without a second source.find() per target key. Only
-                // used by the fast path -- the slow (reordering) path
-                // rebuilds "add" ops for every key itself.
-                std::vector<typename object_t::key_type> common_keys_target_order;
-                basic_json added_ops(value_t::array);
-                bool new_keys_form_suffix = true;
-                bool seen_new_key = false;
-                for (auto it = target.cbegin(); it != target.cend(); ++it)
-                {
-                    if (source.find(it.key()) == source.end())
-                    {
-                        seen_new_key = true;
-                        const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
-                        added_ops.push_back(
-                        {
-                            {"op", "add"}, {"path", path_key},
-                            {"value", it.value()}
-                        });
+                        // recursive call to compare object values at key it
+                        auto temp_diff = diff(it.value(), target[it.key()], path_key);
+                        result.insert(result.end(), temp_diff.begin(), temp_diff.end());
                     }
                     else
                     {
-                        common_keys_target_order.push_back(it.key());
-                        if (seen_new_key)
-                        {
-                            new_keys_form_suffix = false;
-                        }
-                    }
-                }
-
-                if (common_keys_source_order == common_keys_target_order && new_keys_form_suffix)
-                {
-                    // fast path: order of common keys already matches (or the
-                    // object_t's iteration order does not depend on
-                    // insertion history), so a plain per-key recursive diff
-                    // is correct and minimal, as before. common_keys_source_order
-                    // is, by construction, the subsequence of source's keys
-                    // that are common to both objects, in source's iteration
-                    // order -- so it can be walked in lockstep with `source`
-                    // using a cheap key comparison instead of another lookup.
-                    // Deleted keys (those source keys not in common_keys_source_order)
-                    // are interleaved here too, in source's original order, to
-                    // match the historical (pre-reordering-aware) output order.
-                    auto common_it = common_keys_source_order.cbegin();
-                    for (auto it = source.cbegin(); it != source.cend(); ++it)
-                    {
-                        if (common_it != common_keys_source_order.cend() && it.key() == *common_it)
-                        {
-                            const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
-                            auto temp_diff = diff(it.value(), target[it.key()], path_key);
-                            result.insert(result.end(), temp_diff.begin(), temp_diff.end());
-                            ++common_it;
-                        }
-                        else
-                        {
-                            // found a key that is not in target -> remove it
-                            const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
-                            result.push_back(object(
-                            {
-                                {"op", "remove"}, {"path", path_key}
-                            }));
-                        }
-                    }
-
-                    // append the "add" ops for brand-new keys collected above
-                    // during the pass over target -- no second source.find()
-                    // per target key needed
-                    result.insert(result.end(), added_ops.begin(), added_ops.end());
-                }
-                else
-                {
-                    // slow path: the common keys are in a different relative
-                    // order in source and target (only possible for a
-                    // reorderable object_t like ordered_map). Building a
-                    // minimal reordering patch is a nontrivial (LCS-like)
-                    // problem; instead, remove every source key -- both
-                    // deleted keys (which must be removed regardless) and
-                    // common keys (removed so they can be re-added in
-                    // target's order) -- and re-add every key that should
-                    // remain, with its final target value, in target's
-                    // order. basic_json::patch()'s "add" operation on an
-                    // object uses operator[], which appends at the end for a
-                    // vector-backed insertion-ordered map when the key does
-                    // not already exist -- so removing a key and then adding
-                    // it moves it to the end, fixing its position.
-                    for (auto it = source.cbegin(); it != source.cend(); ++it)
-                    {
-                        const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
+                        // found a key that is not in o -> remove it
                         result.push_back(object(
                         {
                             {"op", "remove"}, {"path", path_key}
                         }));
                     }
+                }
 
-                    // add every key that is either common (just removed
-                    // above) or brand new, in target's iteration order, so
-                    // that the final order after applying the patch matches
-                    // target exactly
-                    for (auto it = target.cbegin(); it != target.cend(); ++it)
+                // second pass: traverse other object's elements
+                for (auto it = target.cbegin(); it != target.cend(); ++it)
+                {
+                    if (source.find(it.key()) == source.end())
                     {
+                        // found a key that is not in this -> add it
                         const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
                         result.push_back(
                         {

tests/src/unit-bjdata.cpp

@@ -3551,6 +3551,111 @@ TEST_CASE("BJData")
     }
 }
 
+TEST_CASE("issue #5405 - array reserve for definite-length BJData arrays")
+{
+#if !defined(JSON_NOEXCEPTION)
+    // this SECTION relies on catching a thrown exception to distinguish
+    // which of two acceptable, bounded rejections a hostile header took;
+    // under JSON_NOEXCEPTION, JSON_THROW never produces a catchable C++
+    // exception (it aborts instead), so this cannot be tested that way here
+    SECTION("a huge claimed length with no element data must not over-allocate")
+    {
+        // optimized form [$type#count: type 'i' (int8), count as a four-byte
+        // little-endian 'l' (int32) of 0x7FFFFFFF (2147483647), but no
+        // element data at all. max_size() for a std::vector is far larger
+        // than this count, so it does not reject the header outright; the
+        // (capped) reservation must not attempt to allocate space for
+        // billions of elements before the missing data is detected.
+        json _;
+        const std::vector<uint8_t> input = {'[', '$', 'i', '#', 'l', 0xFF, 0xFF, 0xFF, 0x7F};
+        // On a platform where std::vector<json>::max_size() is smaller than
+        // the claimed count (e.g. 32-bit, where max_size() is bounded by a
+        // 32-bit SIZE_MAX divided by sizeof(json)), the SAX consumer's own
+        // check rejects the header outright (out_of_range.408, with the
+        // claimed count in the message) instead of accepting it and only
+        // finding it short of data once the (capped) reservation looks for
+        // element bytes that were never provided (parse_error.110). Either
+        // is an acceptable, bounded rejection of the hostile header -- the
+        // property under test is that no path attempts to allocate space
+        // for billions of elements.
+        bool threw = false;
+        try
+        {
+            _ = json::from_bjdata(input);
+        }
+        catch (const json::parse_error& e)
+        {
+            threw = true;
+            CHECK(e.id == 110);
+            CHECK(std::string(e.what()) == "[json.exception.parse_error.110] parse error at byte 10: syntax error while parsing BJData number: unexpected end of input");
+        }
+        catch (const json::out_of_range& e)
+        {
+            threw = true;
+            CHECK(e.id == 408);
+            CHECK(std::string(e.what()).find("excessive array size") != std::string::npos);
+        }
+        CHECK(threw);
+
+        // json_sax_dom_parser::start_array()'s max_size() check (unlike the
+        // scanner's own parse_error path) throws unconditionally via
+        // JSON_THROW rather than going through sax->parse_error(), so it is
+        // not gated by allow_exceptions=false on a platform where this
+        // header hits that check (e.g. 32-bit, see above) -- allow either
+        // a discarded result or the same out_of_range it throws with
+        // exceptions enabled.
+        try
+        {
+            CHECK(json::from_bjdata(input, true, false).is_discarded());
+        }
+        catch (const json::out_of_range& e)
+        {
+            CHECK(e.id == 408);
+        }
+    }
+#endif
+
+    SECTION("arrays of various sizes decode to the same value as before the reserve optimization")
+    {
+        for (const auto size :
+                {
+                    std::size_t{0}, std::size_t{1}, std::size_t{5}, // small
+                    std::size_t{16384},                             // exactly at the reserve cap
+                    std::size_t{20000}                              // above the reserve cap
+                })
+        {
+            CAPTURE(size)
+            json j = json::array();
+            for (std::size_t i = 0; i < size; ++i)
+            {
+                j.push_back(static_cast<int>(i % 1000));
+            }
+
+            // exercise both the plain and the optimized [$type#count encoding
+            const auto packed_plain = json::to_bjdata(j);
+            CHECK(json::from_bjdata(packed_plain) == j);
+
+            const auto packed_optimized = json::to_bjdata(j, true, true);
+            CHECK(json::from_bjdata(packed_optimized) == j);
+        }
+    }
+
+    SECTION("a user-defined SAX consumer is unaffected by the internal DOM reserve optimization")
+    {
+        // the reserve() call is local to json_sax_dom_parser / json_sax_dom_callback_parser;
+        // a custom SAX consumer that does not touch a DOM array sees identical events
+        json j = json::array();
+        for (int i = 0; i < 100; ++i)
+        {
+            j.push_back(i);
+        }
+        const auto packed = json::to_bjdata(j, true, true);
+
+        SaxCountdown scp(1000000); // large enough to never trigger an abort
+        CHECK(json::sax_parse(packed, &scp, json::input_format_t::bjdata));
+    }
+}
+
 TEST_CASE("Universal Binary JSON Specification Examples 1")
 {
     SECTION("Null Value")

tests/src/unit-cbor.cpp

@@ -2174,6 +2174,92 @@ TEST_CASE("CBOR indefinite-length strings do not recurse per chunk")
     }
 }
 
+TEST_CASE("issue #5405 - array reserve for definite-length CBOR arrays")
+{
+#if !defined(JSON_NOEXCEPTION)
+    // this SECTION relies on catching a thrown exception to distinguish
+    // which of two acceptable, bounded rejections a hostile header took;
+    // under JSON_NOEXCEPTION, JSON_THROW never produces a catchable C++
+    // exception (it aborts instead), so this cannot be tested that way here
+    SECTION("a huge claimed length with no element data must not over-allocate")
+    {
+        // 0x9A: array with a four-byte length; claims 0xFFFFFFFF (4294967295)
+        // elements but provides none. max_size() for a std::vector is far
+        // larger than this count, so it does not reject the header outright;
+        // the (capped) reservation must not attempt to allocate space for
+        // billions of elements before the missing data is detected.
+        json _;
+        const std::vector<uint8_t> input = {0x9A, 0xFF, 0xFF, 0xFF, 0xFF};
+        // On a platform where std::size_t is narrower than 64 bits (e.g.
+        // 32-bit), the claimed count 0xFFFFFFFF coincides with that
+        // platform's detail::unknown_size() sentinel (SIZE_MAX), so the
+        // format-level size check rejects it outright (out_of_range.408,
+        // "excessive ... size") before the SAX consumer's own max_size()
+        // check would even run; on a 64-bit platform it passes both of
+        // those checks and is only found short of data once the (capped)
+        // reservation looks for element bytes that were never provided
+        // (parse_error.110). Either is an acceptable, bounded rejection of
+        // the hostile header -- the property under test is that no path
+        // attempts to allocate space for billions of elements.
+        bool threw = false;
+        try
+        {
+            _ = json::from_cbor(input);
+        }
+        catch (const json::parse_error& e)
+        {
+            threw = true;
+            CHECK(e.id == 110);
+            CHECK(std::string(e.what()) == "[json.exception.parse_error.110] parse error at byte 6: syntax error while parsing CBOR value: unexpected end of input");
+        }
+        catch (const json::out_of_range& e)
+        {
+            threw = true;
+            CHECK(e.id == 408);
+            CHECK(std::string(e.what()).find("excessive") != std::string::npos);
+        }
+        CHECK(threw);
+        CHECK(json::from_cbor(input, true, false).is_discarded());
+    }
+#endif
+
+    SECTION("arrays of various sizes decode to the same value as before the reserve optimization")
+    {
+        for (const auto size :
+                {
+                    std::size_t{0}, std::size_t{1}, std::size_t{5}, // small
+                    std::size_t{16384},                             // exactly at the reserve cap
+                    std::size_t{20000}                              // above the reserve cap
+                })
+        {
+            CAPTURE(size)
+            json j = json::array();
+            for (std::size_t i = 0; i < size; ++i)
+            {
+                j.push_back(static_cast<int>(i % 1000));
+            }
+
+            const auto packed = json::to_cbor(j);
+            CHECK(json::from_cbor(packed) == j);
+        }
+    }
+
+    SECTION("a user-defined SAX consumer is unaffected by the internal DOM reserve optimization")
+    {
+        // the reserve() call is local to json_sax_dom_parser / json_sax_dom_callback_parser;
+        // a custom SAX consumer that does not touch a DOM array sees identical events
+        json j = json::array();
+        for (int i = 0; i < 100; ++i)
+        {
+            j.push_back(i);
+        }
+        const auto packed = json::to_cbor(j);
+
+        SaxCountdown scp(1000000); // large enough to never trigger an abort
+        CHECK(json::sax_parse(packed, &scp, json::input_format_t::cbor));
+    }
+}
+
 TEST_CASE("CBOR roundtrips" * doctest::skip())
 {
     SECTION("input from flynn")

tests/src/unit-class_parser.cpp

@@ -2259,6 +2259,86 @@ TEST_CASE("parser class")
 #endif
 }
 
+#if JSON_DIAGNOSTIC_POSITIONS
+
+TEST_CASE("diagnostic positions: value lifetime")
+{
+    SECTION("copy constructor copies positions, recursively")
+    {
+        const std::string s = R"({"a":1,"b":[1,2,3]})";
+        const json a = json::parse(s);
+        const json b = a; // NOLINT(performance-unnecessary-copy-initialization)
+
+        CHECK(b.start_pos() == a.start_pos());
+        CHECK(b.end_pos() == a.end_pos());
+        CHECK(b["b"].start_pos() == a["b"].start_pos());
+        CHECK(b["b"].end_pos() == a["b"].end_pos());
+    }
+
+    SECTION("move constructor resets the moved-from value to npos")
+    {
+        const std::string s = R"({"a":1,"b":[1,2,3]})";
+        json a = json::parse(s);
+        const auto a_start = a.start_pos();
+        const auto a_end = a.end_pos();
+
+        const json b(std::move(a));
+
+        CHECK(b.start_pos() == a_start);
+        CHECK(b.end_pos() == a_end);
+
+        CHECK(a.start_pos() == std::string::npos); // NOLINT(bugprone-use-after-move,clang-analyzer-cplusplus.Move)
+        CHECK(a.end_pos() == std::string::npos); // NOLINT(bugprone-use-after-move,clang-analyzer-cplusplus.Move)
+    }
+
+    SECTION("swap() exchanges positions along with the values")
+    {
+        // basic_json::swap() (and the friend swap() that forwards to it) used
+        // to swap only m_data.m_type/m_data.m_value, leaving
+        // start_position/end_position untouched -- unlike copy-assignment's
+        // operator=(basic_json), which swaps positions as part of its
+        // copy-and-swap implementation. After swap(a, b), each value ended up
+        // with the *other* value's content but its *own* original position.
+        // This is now fixed so that swap() is consistent with copy-assignment.
+        json a = json::parse(R"({"a":1})");
+        json b = json::parse(R"([1,2,3,4,5])");
+        const auto a_start = a.start_pos();
+        const auto a_end = a.end_pos();
+        const auto b_start = b.start_pos();
+        const auto b_end = b.end_pos();
+        // lengths (and thus end positions) differ, which is enough to tell
+        // after the swap whether positions actually moved with the values
+        CHECK(a_end != b_end);
+
+        using std::swap;
+        swap(a, b);
+
+        CHECK(a == json::parse(R"([1,2,3,4,5])"));
+        CHECK(b == json::parse(R"({"a":1})"));
+
+        CHECK(a.start_pos() == b_start);
+        CHECK(a.end_pos() == b_end);
+        CHECK(b.start_pos() == a_start);
+        CHECK(b.end_pos() == a_end);
+
+        // member swap() behaves the same as the free function
+        json c = json::parse(R"({"a":1})");
+        json d = json::parse(R"([1,2,3,4,5])");
+        const auto c_start = c.start_pos();
+        const auto c_end = c.end_pos();
+        const auto d_start = d.start_pos();
+        const auto d_end = d.end_pos();
+
+        c.swap(d);
+
+        CHECK(c.start_pos() == d_start);
+        CHECK(c.end_pos() == d_end);
+        CHECK(d.start_pos() == c_start);
+        CHECK(d.end_pos() == c_end);
+    }
+}
+#endif
+
 // this test relies on parse errors being thrown, so it is skipped when
 // exceptions are disabled (json::parse aborts instead of throwing there)
 #if !defined(JSON_NOEXCEPTION)

tests/src/unit-diagnostics.cpp

@@ -273,36 +273,5 @@ TEST_CASE("Regression tests for extended diagnostics")
         CHECK(j1["numbers"]["two"] == 2);
         CHECK(j1["string"] == "t");
     }
-
-    SECTION("Regression test - swap(array_t&)/swap(object_t&) must update JSON_DIAGNOSTICS parent pointers")
-    {
-        // swap(array_t&)
-        {
-            json j = json::array();
-            json::array_t arr = {json::array({1})};
-            j.swap(arr);
-
-            // parent pointers of the moved-in elements must point into j, not
-            // into the now-defunct free-standing array_t
-            CHECK_THROWS_WITH_AS(j[0][0].get<std::string>(), "[json.exception.type_error.302] (/0/0) type must be string, but is number", json::type_error);
-
-            // must not trigger assert_invariant() in a debug/assert-enabled build
-            json const k = j;
-            CHECK(k == j);
-        }
-
-        // swap(object_t&)
-        {
-            json o = json::object();
-            json::object_t obj = {{"a", json::array({1})}};
-            o.swap(obj);
-
-            CHECK_THROWS_WITH_AS(o["a"][0].get<std::string>(), "[json.exception.type_error.302] (/a/0) type must be string, but is number", json::type_error);
-
-            // must not trigger assert_invariant() in a debug/assert-enabled build
-            json const p = o;
-            CHECK(p == o);
-        }
-    }
 }
 

tests/src/unit-msgpack.cpp

@@ -1597,6 +1597,91 @@ TEST_CASE("MessagePack")
     }
 }
 
+TEST_CASE("issue #5405 - array reserve for definite-length MessagePack arrays")
+{
+#if !defined(JSON_NOEXCEPTION)
+    // this SECTION relies on catching a thrown exception to distinguish
+    // which of two acceptable, bounded rejections a hostile header took;
+    // under JSON_NOEXCEPTION, JSON_THROW never produces a catchable C++
+    // exception (it aborts instead), so this cannot be tested that way here
+    SECTION("a huge claimed length with no element data must not over-allocate")
+    {
+        // 0xdd: array 32 (four-byte length); claims 0xFFFFFFFF (4294967295)
+        // elements but provides none. max_size() for a std::vector is far
+        // larger than this count, so it does not reject the header outright;
+        // the (capped) reservation must not attempt to allocate space for
+        // billions of elements before the missing data is detected.
+        json _;
+        const std::vector<uint8_t> input = {0xdd, 0xFF, 0xFF, 0xFF, 0xFF};
+        // On a platform where std::size_t is narrower than 64 bits (e.g.
+        // 32-bit), the claimed count 0xFFFFFFFF coincides with that
+        // platform's SIZE_MAX, which some size-narrowing checks treat the
+        // same as detail::unknown_size(); it may then be rejected before
+        // the SAX consumer's own max_size() check (out_of_range.408) rather
+        // than being accepted and only found short of data once the
+        // (capped) reservation looks for element bytes that were never
+        // provided (parse_error.110). Either is an acceptable, bounded
+        // rejection of the hostile header -- the property under test is
+        // that no path attempts to allocate space for billions of elements.
+        bool threw = false;
+        try
+        {
+            _ = json::from_msgpack(input);
+        }
+        catch (const json::parse_error& e)
+        {
+            threw = true;
+            CHECK(e.id == 110);
+            CHECK(std::string(e.what()) == "[json.exception.parse_error.110] parse error at byte 6: syntax error while parsing MessagePack value: unexpected end of input");
+        }
+        catch (const json::out_of_range& e)
+        {
+            threw = true;
+            CHECK(e.id == 408);
+            CHECK(std::string(e.what()).find("excessive") != std::string::npos);
+        }
+        CHECK(threw);
+        CHECK(json::from_msgpack(input, true, false).is_discarded());
+    }
+#endif
+
+    SECTION("arrays of various sizes decode to the same value as before the reserve optimization")
+    {
+        for (const auto size :
+                {
+                    std::size_t{0}, std::size_t{1}, std::size_t{5}, // small
+                    std::size_t{16384},                             // exactly at the reserve cap
+                    std::size_t{20000}                              // above the reserve cap
+                })
+        {
+            CAPTURE(size)
+            json j = json::array();
+            for (std::size_t i = 0; i < size; ++i)
+            {
+                j.push_back(static_cast<int>(i % 1000));
+            }
+
+            const auto packed = json::to_msgpack(j);
+            CHECK(json::from_msgpack(packed) == j);
+        }
+    }
+
+    SECTION("a user-defined SAX consumer is unaffected by the internal DOM reserve optimization")
+    {
+        // the reserve() call is local to json_sax_dom_parser / json_sax_dom_callback_parser;
+        // a custom SAX consumer that does not touch a DOM array sees identical events
+        json j = json::array();
+        for (int i = 0; i < 100; ++i)
+        {
+            j.push_back(i);
+        }
+        const auto packed = json::to_msgpack(j);
+
+        SaxCountdown scp(1000000); // large enough to never trigger an abort
+        CHECK(json::sax_parse(packed, &scp, json::input_format_t::msgpack));
+    }
+}
+
 // use this testcase outside [hide] to run it with Valgrind
 TEST_CASE("MessagePack nesting does not consume the call stack")
 {

tests/src/unit-ordered_json.cpp

@@ -81,84 +81,3 @@ TEST_CASE("regression test for issue #3732 - iteration_proxy_value<iter_impl<ord
     };
     static_cast<void>(fn);
 }
-
-TEST_CASE("regression test - diff() must account for ordered_json member order")
-{
-    SECTION("pure reorder, no value changes")
-    {
-        ordered_json a = {{"a", 1}, {"b", 2}};
-        ordered_json b = {{"b", 2}, {"a", 1}};
-        CHECK(a != b); // order-sensitive equality
-        CHECK(a.patch(ordered_json::diff(a, b)) == b);
-    }
-
-    SECTION("new key must land at the front")
-    {
-        ordered_json c = {{"b", 2}};
-        ordered_json e = {{"a", 1}, {"b", 2}};
-        CHECK(c.patch(ordered_json::diff(c, e)) == e);
-    }
-
-    SECTION("reorder plus a value change on one of the reordered keys")
-    {
-        ordered_json a = {{"a", 1}, {"b", 2}};
-        ordered_json b = {{"b", 20}, {"a", 1}};
-        CHECK(a != b);
-        CHECK(a.patch(ordered_json::diff(a, b)) == b);
-    }
-
-    SECTION("reorder plus a deleted key")
-    {
-        ordered_json a = {{"a", 1}, {"b", 2}, {"c", 3}};
-        ordered_json b = {{"b", 2}, {"a", 1}};
-        CHECK(a != b);
-        CHECK(a.patch(ordered_json::diff(a, b)) == b);
-    }
-
-    SECTION("reorder plus a nested value that itself needs a recursive diff")
-    {
-        ordered_json a = {{"a", {{"x", 1}, {"y", 2}}}, {"b", 2}};
-        ordered_json b = {{"b", 2}, {"a", {{"x", 1}, {"y", 99}}}};
-        CHECK(a != b);
-        CHECK(a.patch(ordered_json::diff(a, b)) == b);
-    }
-
-    SECTION("three or more keys shuffled into a different order")
-    {
-        ordered_json a = {{"a", 1}, {"b", 2}, {"c", 3}, {"d", 4}};
-        ordered_json b = {{"d", 4}, {"b", 2}, {"a", 1}, {"c", 3}};
-        CHECK(a != b);
-        CHECK(a.patch(ordered_json::diff(a, b)) == b);
-    }
-
-    SECTION("matching order still produces a minimal patch (fast path unaffected)")
-    {
-        ordered_json a = {{"a", 1}, {"b", 2}, {"c", 3}};
-        ordered_json b = {{"a", 1}, {"b", 20}, {"c", 3}};
-        auto p = ordered_json::diff(a, b);
-        // only the changed value should be touched, not a wholesale remove+add
-        CHECK(p.size() == 1);
-        CHECK(p[0]["op"] == "replace");
-        CHECK(p[0]["path"] == "/b");
-        CHECK(a.patch(p) == b);
-    }
-
-    SECTION("plain json (std::map-backed) is unaffected by same-key-different-insertion-order")
-    {
-        json a;
-        a["b"] = 2;
-        a["a"] = 1;
-
-        json b;
-        b["a"] = 1;
-        b["b"] = 2;
-
-        // std::map iteration is always sorted by key, so a == b regardless of
-        // insertion order, and diff() must still produce the same minimal
-        // (empty) result as before this fix
-        CHECK(a == b);
-        auto p = json::diff(a, b);
-        CHECK(p.empty());
-        CHECK(a.patch(p) == b);
-    }
-}

tests/src/unit-regression3.cpp

@@ -27,6 +27,7 @@ using ordered_json = nlohmann::ordered_json;
 #endif
 
 #include <cstdio>
+#include <deque>
 #include <list>
 #include <type_traits>
 #include <utility>
@@ -895,76 +896,50 @@ TEST_CASE("issue #5402 - update(merge_objects=true) overwrites a primitive with
     CHECK(mixed == json({{"keep", {{"a", 1}, {"b", 2}}}, {"replace", {{"x", 2}}}}));
 }
 
-TEST_CASE("regression test - parser callback must not lose a duplicate key's prior value")
+
+TEST_CASE("regression test #5476 - array type without reserve()")
 {
-    // a callback that rejects only the scalar value 2
-    const json::parser_callback_t drop_value_2 = [](int /*depth*/, json::parse_event_t ev, json & v) noexcept
-    {
-        return !(ev == json::parse_event_t::value && v == 2);
-    };
+    // the capacity reserved for definite-length arrays must not require the
+    // array type to have a reserve() member function
+    using deque_json = nlohmann::basic_json<std::map, std::deque>;
 
-    SECTION("duplicate key, second (scalar) value rejected - prior value is restored")
+    SECTION("std::deque")
     {
-        const json j = json::parse(R"({"a":1,"a":2})", drop_value_2);
-        CHECK(j.dump() == "{\"a\":1}");
-    }
+        const auto j = deque_json::parse(R"({"a":[1,[2,3]],"b":[]})");
+        CHECK(j.dump() == R"({"a":[1,[2,3]],"b":[]})");
 
-    SECTION("duplicate key, second value is an object rejected at object_end - prior value is restored")
-    {
-        const json j = json::parse(R"({"a":1,"a":{"x":2}})",
-                                   [](int depth, json::parse_event_t ev, json& /*parsed*/) noexcept
-        {
-            return !(ev == json::parse_event_t::object_end && depth == 1);
-        });
-        CHECK(j.dump() == "{\"a\":1}");
-    }
+        // 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);
 
-    SECTION("duplicate key, second value is an array rejected at array_end - prior value is restored")
-    {
-        const json j = json::parse(R"({"a":1,"a":[9,9]})",
-                                   [](int depth, json::parse_event_t ev, json& /*parsed*/) noexcept
-        {
-            return !(ev == json::parse_event_t::array_end && depth == 1);
-        });
-        CHECK(j.dump() == "{\"a\":1}");
-    }
-
-    SECTION("duplicate key, second value accepted (scalar) - last value wins")
-    {
-        const json j = json::parse(R"({"a":1,"a":2})", [](int, json::parse_event_t, json&) noexcept
+        // 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(j.dump() == "{\"a\":2}");
+        CHECK(with_callback == deque_json({1, 2, 3}));
     }
 
-    SECTION("duplicate key, second value accepted (object) - last value wins")
+    SECTION("std::vector still reserves")
     {
-        const json j = json::parse(R"({"a":1,"a":{"x":2}})", [](int, json::parse_event_t, json&) noexcept
+        json array = json::array();
+        for (int i = 0; i < 100; ++i)
         {
-            return true;
-        });
-        CHECK(j.dump() == "{\"a\":{\"x\":2}}");
+            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("brand new (non-duplicate) key, value rejected - member is fully absent")
+    SECTION("the reservation stays capped")
     {
-        const json j = json::parse(R"({"a":1,"b":2})", drop_value_2);
-        CHECK(j.dump() == "{\"a\":1}");
-    }
-
-    SECTION("duplicate key nested two levels deep")
-    {
-        const json j = json::parse(R"({"outer":{"a":1,"a":2}})", drop_value_2);
-        CHECK(j.dump() == "{\"outer\":{\"a\":1}}");
-    }
-
-    SECTION("three occurrences of the same key - middle rejected, last accepted")
-    {
-        const json j = json::parse(R"({"k":1,"k":2,"k":3})", drop_value_2);
-        CHECK(j.dump() == "{\"k\":3}");
+        // 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());
     }
 }
 
-
 DOCTEST_CLANG_SUPPRESS_WARNING_POP

tests/src/unit-ubjson.cpp

@@ -2315,6 +2315,112 @@ TEST_CASE("UBJSON optimized arrays of a valueless type are bounded")
     }
 }
 
+TEST_CASE("issue #5405 - array reserve for definite-length UBJSON arrays")
+{
+#if !defined(JSON_NOEXCEPTION)
+    // this SECTION relies on catching a thrown exception to distinguish
+    // which of two acceptable, bounded rejections a hostile header took;
+    // under JSON_NOEXCEPTION, JSON_THROW never produces a catchable C++
+    // exception (it aborts instead), so this cannot be tested that way here
+    SECTION("a huge claimed length with no element data must not over-allocate")
+    {
+        // optimized form [$type#count: type 'i' (int8), count as a four-byte
+        // 'l' (int32) of 0x7FFFFFFF (2147483647), but no element data at all.
+        // max_size() for a std::vector is far larger than this count, so it
+        // does not reject the header outright; the (capped) reservation must
+        // not attempt to allocate space for billions of elements before the
+        // missing data is detected.
+        json _;
+        const std::vector<uint8_t> input = {'[', '$', 'i', '#', 'l', 0x7F, 0xFF, 0xFF, 0xFF};
+        // On a platform where std::vector<json>::max_size() is smaller than
+        // the claimed count (e.g. 32-bit, where max_size() is bounded by a
+        // 32-bit SIZE_MAX divided by sizeof(json)), the SAX consumer's own
+        // check rejects the header outright (out_of_range.408, with the
+        // claimed count in the message) instead of accepting it and only
+        // finding it short of data once the (capped) reservation looks for
+        // element bytes that were never provided (parse_error.110). Either
+        // is an acceptable, bounded rejection of the hostile header -- the
+        // property under test is that no path attempts to allocate space
+        // for billions of elements.
+        bool threw = false;
+        try
+        {
+            _ = json::from_ubjson(input);
+        }
+        catch (const json::parse_error& e)
+        {
+            threw = true;
+            CHECK(e.id == 110);
+            CHECK(std::string(e.what()) == "[json.exception.parse_error.110] parse error at byte 10: syntax error while parsing UBJSON number: unexpected end of input");
+        }
+        catch (const json::out_of_range& e)
+        {
+            threw = true;
+            CHECK(e.id == 408);
+            CHECK(std::string(e.what()).find("excessive array size") != std::string::npos);
+        }
+        CHECK(threw);
+
+        // json_sax_dom_parser::start_array()'s max_size() check (unlike the
+        // scanner's own parse_error path) throws unconditionally via
+        // JSON_THROW rather than going through sax->parse_error(), so it is
+        // not gated by allow_exceptions=false on a platform where this
+        // header hits that check (e.g. 32-bit, see above) -- allow either
+        // a discarded result or the same out_of_range it throws with
+        // exceptions enabled.
+        try
+        {
+            CHECK(json::from_ubjson(input, true, false).is_discarded());
+        }
+        catch (const json::out_of_range& e)
+        {
+            CHECK(e.id == 408);
+        }
+    }
+#endif
+
+    SECTION("arrays of various sizes decode to the same value as before the reserve optimization")
+    {
+        for (const auto size :
+                {
+                    std::size_t{0}, std::size_t{1}, std::size_t{5}, // small
+                    std::size_t{16384},                             // exactly at the reserve cap
+                    std::size_t{20000}                              // above the reserve cap
+                })
+        {
+            CAPTURE(size)
+            json j = json::array();
+            for (std::size_t i = 0; i < size; ++i)
+            {
+                j.push_back(static_cast<int>(i % 1000));
+            }
+
+            // exercise both the plain and the optimized [$type#count encoding
+            const auto packed_plain = json::to_ubjson(j);
+            CHECK(json::from_ubjson(packed_plain) == j);
+
+            const auto packed_optimized = json::to_ubjson(j, true, true);
+            CHECK(json::from_ubjson(packed_optimized) == j);
+        }
+    }
+
+    SECTION("a user-defined SAX consumer is unaffected by the internal DOM reserve optimization")
+    {
+        // the reserve() call is local to json_sax_dom_parser / json_sax_dom_callback_parser;
+        // a custom SAX consumer that does not touch a DOM array sees identical events
+        json j = json::array();
+        for (int i = 0; i < 100; ++i)
+        {
+            j.push_back(i);
+        }
+        const auto packed = json::to_ubjson(j, true, true);
+
+        SaxCountdown scp(1000000); // large enough to never trigger an abort
+        CHECK(json::sax_parse(packed, &scp, json::input_format_t::ubjson));
+    }
+}
+
+
 TEST_CASE("Universal Binary JSON Specification Examples 1")
 {
     SECTION("Null Value")