🐛 fix BSON conformance issue

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

include/nlohmann/detail/input/binary_reader.hpp

@@ -432,7 +432,21 @@ class binary_reader
                                     exception_message(input_format_t::bson, concat("string length must be at least 1, is ", std::to_string(len)), "string"), nullptr));
         }
 
-        return get_string(input_format_t::bson, len - static_cast<NumberType>(1), result) && get() != char_traits<char_type>::eof();
+        if (JSON_HEDLEY_UNLIKELY(!get_string(input_format_t::bson, len - static_cast<NumberType>(1), result)))
+        {
+            return false;
+        }
+
+        if (JSON_HEDLEY_UNLIKELY(get() != 0x00))
+        {
+            auto last_token = get_token_string();
+            return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
+                                    exception_message(input_format_t::bson,
+                                            "BSON string is not null-terminated",
+                                            "string"), nullptr));
+        }
+
+        return true;
     }
 
     /*!
@@ -550,8 +564,6 @@ class binary_reader
         }
     }
 
-
-
     //////////
     // CBOR //
     //////////
@@ -1434,7 +1446,7 @@ class binary_reader
                 // a copy, not a reference: it must stay valid across the
                 // pop_back() below, which destroys the container_stack element
                 // it would otherwise alias
-                const container_frame top = container_stack.back();
+                container_frame top = container_stack.back();
                 bool at_end = false;
 
                 if (top.remaining != npos)
@@ -2211,7 +2223,7 @@ class binary_reader
             // would otherwise alias.
             for (;;)
             {
-                const container_frame top = container_stack.back();
+                container_frame top = container_stack.back();
 
                 if (top.remaining != npos)
                 {

include/nlohmann/detail/input/json_sax.hpp

@@ -8,11 +8,10 @@
 
 #pragma once
 
-#include <algorithm> // find_if
 #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>
@@ -254,7 +253,7 @@ class json_sax_dom_parser
 
         if (JSON_HEDLEY_UNLIKELY(len != detail::unknown_size() && len > ref_stack.back()->max_size()))
         {
-            return parse_error(0, "", out_of_range::create(408, concat("excessive object size: ", std::to_string(len)), ref_stack.back()));
+            JSON_THROW(out_of_range::create(408, concat("excessive object size: ", std::to_string(len)), ref_stack.back()));
         }
 
         return true;
@@ -303,7 +302,7 @@ class json_sax_dom_parser
 
         if (JSON_HEDLEY_UNLIKELY(len != detail::unknown_size() && len > ref_stack.back()->max_size()))
         {
-            return parse_error(0, "", out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
+            JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
         }
 
         return true;
@@ -582,7 +581,7 @@ class json_sax_dom_callback_parser
             // check object limit
             if (JSON_HEDLEY_UNLIKELY(len != detail::unknown_size() && len > ref_stack.back()->max_size()))
             {
-                return parse_error(0, "", out_of_range::create(408, concat("excessive object size: ", std::to_string(len)), ref_stack.back()));
+                JSON_THROW(out_of_range::create(408, concat("excessive object size: ", std::to_string(len)), ref_stack.back()));
             }
         }
         return true;
@@ -602,17 +601,7 @@ 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;
+            object_element = &(ref_stack.back()->m_data.m_value.object->operator[](val) = discarded);
-            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);
         }
 
         return true;
@@ -624,11 +613,7 @@ 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
+                // discard object
-                // 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;
 
 #if JSON_DIAGNOSTIC_POSITIONS
@@ -636,7 +621,6 @@ class json_sax_dom_callback_parser
                 handle_diagnostic_positions_for_json_value(*ref_stack.back());
 #endif
             }
-            }
             else
             {
 
@@ -649,10 +633,6 @@ 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);
             }
         }
 
@@ -701,7 +681,7 @@ class json_sax_dom_callback_parser
             // check array limit
             if (JSON_HEDLEY_UNLIKELY(len != detail::unknown_size() && len > ref_stack.back()->max_size()))
             {
-                return parse_error(0, "", out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
+                JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
             }
         }
 
@@ -728,18 +708,10 @@ 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
+                // discard array
-                // 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;
 
 #if JSON_DIAGNOSTIC_POSITIONS
@@ -748,7 +720,6 @@ class json_sax_dom_callback_parser
 #endif
             }
         }
-        }
 
         JSON_ASSERT(!ref_stack.empty());
         JSON_ASSERT(!keep_stack.empty());
@@ -880,35 +851,6 @@ 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 +862,12 @@ 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
+    nothing to remove.
-    stashed previous value pending restoration, that value is restored instead
-    of the slot being erased.
 
     @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())
         {
@@ -942,14 +882,11 @@ class json_sax_dom_callback_parser
             auto& object = *parent.m_data.m_value.object;
             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);
             }
         }
     }
-    }
 
     /*!
     @param[in] v  value to add to the JSON value we build during parsing
@@ -1048,16 +985,6 @@ 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 +1004,6 @@ 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

@@ -3602,7 +3602,6 @@ 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 +3618,6 @@ 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 +5268,34 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
             case value_t::object:
             {
-                // first pass: record, for every source key, whether it is
+                // first pass: traverse this object's elements
-                // 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;
                 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());
+                        // 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
+                    {
+                        // found a key that is not in o -> remove it
+                        result.push_back(object(
+                        {
+                            {"op", "remove"}, {"path", path_key}
+                        }));
                     }
                 }
 
-                // second pass: find keys that were added (i.e., in target but
+                // second pass: traverse other object's elements
-                // 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;
+                        // found a key that is not in this -> add it
-                        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()}
-                        });
-                    }
-                    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()));
-                        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)
-                    {
                         const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
                         result.push_back(
                         {

single_include/nlohmann/json.hpp

@@ -7892,11 +7892,10 @@ NLOHMANN_JSON_NAMESPACE_END
 
 
 
-#include <algorithm> // find_if
 #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>
@@ -10967,7 +10966,7 @@ class json_sax_dom_parser
 
         if (JSON_HEDLEY_UNLIKELY(len != detail::unknown_size() && len > ref_stack.back()->max_size()))
         {
-            return parse_error(0, "", out_of_range::create(408, concat("excessive object size: ", std::to_string(len)), ref_stack.back()));
+            JSON_THROW(out_of_range::create(408, concat("excessive object size: ", std::to_string(len)), ref_stack.back()));
         }
 
         return true;
@@ -11016,7 +11015,7 @@ class json_sax_dom_parser
 
         if (JSON_HEDLEY_UNLIKELY(len != detail::unknown_size() && len > ref_stack.back()->max_size()))
         {
-            return parse_error(0, "", out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
+            JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
         }
 
         return true;
@@ -11295,7 +11294,7 @@ class json_sax_dom_callback_parser
             // check object limit
             if (JSON_HEDLEY_UNLIKELY(len != detail::unknown_size() && len > ref_stack.back()->max_size()))
             {
-                return parse_error(0, "", out_of_range::create(408, concat("excessive object size: ", std::to_string(len)), ref_stack.back()));
+                JSON_THROW(out_of_range::create(408, concat("excessive object size: ", std::to_string(len)), ref_stack.back()));
             }
         }
         return true;
@@ -11315,17 +11314,7 @@ 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;
+            object_element = &(ref_stack.back()->m_data.m_value.object->operator[](val) = discarded);
-            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);
         }
 
         return true;
@@ -11337,11 +11326,7 @@ 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
+                // discard object
-                // 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;
 
 #if JSON_DIAGNOSTIC_POSITIONS
@@ -11349,7 +11334,6 @@ class json_sax_dom_callback_parser
                 handle_diagnostic_positions_for_json_value(*ref_stack.back());
 #endif
             }
-            }
             else
             {
 
@@ -11362,10 +11346,6 @@ 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);
             }
         }
 
@@ -11414,7 +11394,7 @@ class json_sax_dom_callback_parser
             // check array limit
             if (JSON_HEDLEY_UNLIKELY(len != detail::unknown_size() && len > ref_stack.back()->max_size()))
             {
-                return parse_error(0, "", out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
+                JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
             }
         }
 
@@ -11441,18 +11421,10 @@ 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
+                // discard array
-                // 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;
 
 #if JSON_DIAGNOSTIC_POSITIONS
@@ -11461,7 +11433,6 @@ class json_sax_dom_callback_parser
 #endif
             }
         }
-        }
 
         JSON_ASSERT(!ref_stack.empty());
         JSON_ASSERT(!keep_stack.empty());
@@ -11593,35 +11564,6 @@ 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 +11575,12 @@ 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
+    nothing to remove.
-    stashed previous value pending restoration, that value is restored instead
-    of the slot being erased.
 
     @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())
         {
@@ -11655,14 +11595,11 @@ class json_sax_dom_callback_parser
             auto& object = *parent.m_data.m_value.object;
             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);
             }
         }
     }
-    }
 
     /*!
     @param[in] v  value to add to the JSON value we build during parsing
@@ -11761,16 +11698,6 @@ 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 +11717,6 @@ 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
@@ -12460,7 +12381,21 @@ class binary_reader
                                     exception_message(input_format_t::bson, concat("string length must be at least 1, is ", std::to_string(len)), "string"), nullptr));
         }
 
-        return get_string(input_format_t::bson, len - static_cast<NumberType>(1), result) && get() != char_traits<char_type>::eof();
+        if (JSON_HEDLEY_UNLIKELY(!get_string(input_format_t::bson, len - static_cast<NumberType>(1), result)))
+        {
+            return false;
+        }
+
+        if (JSON_HEDLEY_UNLIKELY(get() != 0x00))
+        {
+            auto last_token = get_token_string();
+            return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
+                                    exception_message(input_format_t::bson,
+                                            "BSON string is not null-terminated",
+                                            "string"), nullptr));
+        }
+
+        return true;
     }
 
     /*!
@@ -12578,8 +12513,6 @@ class binary_reader
         }
     }
 
-
-
     //////////
     // CBOR //
     //////////
@@ -13462,7 +13395,7 @@ class binary_reader
                 // a copy, not a reference: it must stay valid across the
                 // pop_back() below, which destroys the container_stack element
                 // it would otherwise alias
-                const container_frame top = container_stack.back();
+                container_frame top = container_stack.back();
                 bool at_end = false;
 
                 if (top.remaining != npos)
@@ -14239,7 +14172,7 @@ class binary_reader
             // would otherwise alias.
             for (;;)
             {
-                const container_frame top = container_stack.back();
+                container_frame top = container_stack.back();
 
                 if (top.remaining != npos)
                 {
@@ -27414,7 +27347,6 @@ 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 +27363,6 @@ 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 +29013,34 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
             case value_t::object:
             {
-                // first pass: record, for every source key, whether it is
+                // first pass: traverse this object's elements
-                // 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;
                 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());
+                        // 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
+                    {
+                        // found a key that is not in o -> remove it
+                        result.push_back(object(
+                        {
+                            {"op", "remove"}, {"path", path_key}
+                        }));
                     }
                 }
 
-                // second pass: find keys that were added (i.e., in target but
+                // second pass: traverse other object's elements
-                // 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;
+                        // found a key that is not in this -> add it
-                        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()}
-                        });
-                    }
-                    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()));
-                        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)
-                    {
                         const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
                         result.push_back(
                         {

tests/benchmarks/src/benchmarks.cpp

@@ -252,323 +252,4 @@ static void BinaryToCbor(benchmark::State& state)
 }
 BENCHMARK(BinaryToCbor)->RangeMultiplier(2)->Range(8, 8 << 12);
 
-//////////////////////////////////////////////////////////////////////////////
-// parse binary formats
-//////////////////////////////////////////////////////////////////////////////
-
-// Only MessagePack had a read benchmark (FromMsgpack above, left untouched so
-// its numbers stay comparable across releases). The benchmarks below cover the
-// other formats, and read from a contiguous buffer as well as from a FILE*:
-// most callers pass a container, and the two adapters compile to different
-// code. The test data repository ships JSON only, so the input for each is
-// derived at setup time by serializing a parsed test file.
-
-/// binary format to benchmark; the _optimized variants add UBJSON/BJData size
-/// and type annotations, which the readers handle in a separate code path
-enum class binary_format
-{
-    cbor,
-    msgpack,
-    ubjson,
-    ubjson_optimized,
-    bjdata,
-    bjdata_optimized,
-    bson
-};
-
-static std::vector<std::uint8_t> to_binary(const json& j, const binary_format format)
-{
-    switch (format)
-    {
-        case binary_format::cbor:
-            return json::to_cbor(j);
-        case binary_format::msgpack:
-            return json::to_msgpack(j);
-        case binary_format::ubjson:
-            return json::to_ubjson(j);
-        case binary_format::ubjson_optimized:
-            return json::to_ubjson(j, true, true);
-        case binary_format::bjdata:
-            return json::to_bjdata(j);
-        case binary_format::bjdata_optimized:
-            return json::to_bjdata(j, true, true);
-        case binary_format::bson:
-        default:
-            return json::to_bson(j);
-    }
-}
-
-static json from_binary(const std::vector<std::uint8_t>& bytes, const binary_format format)
-{
-    switch (format)
-    {
-        case binary_format::cbor:
-            return json::from_cbor(bytes);
-        case binary_format::msgpack:
-            return json::from_msgpack(bytes);
-        case binary_format::ubjson:
-        case binary_format::ubjson_optimized:
-            return json::from_ubjson(bytes);
-        case binary_format::bjdata:
-        case binary_format::bjdata_optimized:
-            return json::from_bjdata(bytes);
-        case binary_format::bson:
-        default:
-            return json::from_bson(bytes);
-    }
-}
-
-static json from_binary(std::FILE* file, const binary_format format)
-{
-    switch (format)
-    {
-        case binary_format::cbor:
-            return json::from_cbor(file);
-        case binary_format::msgpack:
-            return json::from_msgpack(file);
-        case binary_format::ubjson:
-        case binary_format::ubjson_optimized:
-            return json::from_ubjson(file);
-        case binary_format::bjdata:
-        case binary_format::bjdata_optimized:
-            return json::from_bjdata(file);
-        case binary_format::bson:
-        default:
-            return json::from_bson(file);
-    }
-}
-
-/*!
-@brief serialize a parsed test file to @a format
-
-Returns an empty vector and marks the benchmark as skipped if the file cannot
-be represented in the format, rather than letting the exception escape: BSON
-requires an object at the top level, and several test files are arrays.
-*/
-static std::vector<std::uint8_t> binary_input(benchmark::State& state, const char* filename, const binary_format format)
-{
-    std::ifstream f(filename);
-    std::string const str((std::istreambuf_iterator<char>(f)), std::istreambuf_iterator<char>());
-    const json j = json::parse(str);
-
-    if (format == binary_format::bson && !j.is_object())
-    {
-        state.SkipWithError("BSON requires an object at the top level");
-        return {};
-    }
-
-    return to_binary(j, format);
-}
-
-static void FromBinaryBuffer(benchmark::State& state, const char* filename, const binary_format format)
-{
-    const std::vector<std::uint8_t> bytes = binary_input(state, filename, format);
-    if (bytes.empty())
-    {
-        return;
-    }
-
-    for (auto _ : state)
-    {
-        // the value is destroyed outside the timed section, because destroying
-        // a large DOM is not what this benchmark measures
-        state.PauseTiming();
-        auto* j = new json();
-        state.ResumeTiming();
-
-        *j = from_binary(bytes, format);
-
-        state.PauseTiming();
-        delete j;
-        state.ResumeTiming();
-    }
-
-    state.SetBytesProcessed(state.iterations() * bytes.size());
-}
-
-BENCHMARK_CAPTURE(FromBinaryBuffer, cbor / jeopardy, TEST_DATA_DIRECTORY "/jeopardy/jeopardy.json", binary_format::cbor);
-BENCHMARK_CAPTURE(FromBinaryBuffer, cbor / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::cbor);
-BENCHMARK_CAPTURE(FromBinaryBuffer, cbor / citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json", binary_format::cbor);
-BENCHMARK_CAPTURE(FromBinaryBuffer, cbor / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::cbor);
-BENCHMARK_CAPTURE(FromBinaryBuffer, cbor / floats, TEST_DATA_DIRECTORY "/regression/floats.json", binary_format::cbor);
-BENCHMARK_CAPTURE(FromBinaryBuffer, cbor / signed_ints, TEST_DATA_DIRECTORY "/regression/signed_ints.json", binary_format::cbor);
-BENCHMARK_CAPTURE(FromBinaryBuffer, msgpack / jeopardy, TEST_DATA_DIRECTORY "/jeopardy/jeopardy.json", binary_format::msgpack);
-BENCHMARK_CAPTURE(FromBinaryBuffer, msgpack / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::msgpack);
-BENCHMARK_CAPTURE(FromBinaryBuffer, msgpack / citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json", binary_format::msgpack);
-BENCHMARK_CAPTURE(FromBinaryBuffer, msgpack / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::msgpack);
-BENCHMARK_CAPTURE(FromBinaryBuffer, ubjson / jeopardy, TEST_DATA_DIRECTORY "/jeopardy/jeopardy.json", binary_format::ubjson);
-BENCHMARK_CAPTURE(FromBinaryBuffer, ubjson / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::ubjson);
-BENCHMARK_CAPTURE(FromBinaryBuffer, ubjson / citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json", binary_format::ubjson);
-BENCHMARK_CAPTURE(FromBinaryBuffer, ubjson / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::ubjson);
-BENCHMARK_CAPTURE(FromBinaryBuffer, ubjson_optimized / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::ubjson_optimized);
-BENCHMARK_CAPTURE(FromBinaryBuffer, ubjson_optimized / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::ubjson_optimized);
-BENCHMARK_CAPTURE(FromBinaryBuffer, bjdata / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::bjdata);
-BENCHMARK_CAPTURE(FromBinaryBuffer, bjdata / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::bjdata);
-BENCHMARK_CAPTURE(FromBinaryBuffer, bjdata_optimized / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::bjdata_optimized);
-BENCHMARK_CAPTURE(FromBinaryBuffer, bjdata_optimized / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::bjdata_optimized);
-// BSON requires an object at the top level, so the array-rooted test files
-// (jeopardy and the regression files) cannot be captured here
-BENCHMARK_CAPTURE(FromBinaryBuffer, bson / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::bson);
-BENCHMARK_CAPTURE(FromBinaryBuffer, bson / citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json", binary_format::bson);
-BENCHMARK_CAPTURE(FromBinaryBuffer, bson / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::bson);
-
-static void FromBinaryFile(benchmark::State& state, const char* filename, const binary_format format)
-{
-    const std::vector<std::uint8_t> bytes = binary_input(state, filename, format);
-    if (bytes.empty())
-    {
-        return;
-    }
-
-    const char* tmp = "benchmark_input.bin";
-    std::ofstream o(tmp, std::ios::binary);
-    o.write(reinterpret_cast<const char*>(bytes.data()), static_cast<std::streamsize>(bytes.size()));
-    o.flush();
-    o.close();
-
-    for (auto _ : state)
-    {
-        state.PauseTiming();
-        auto* j = new json();
-        auto* file = std::fopen(tmp, "rb");
-        state.ResumeTiming();
-
-        *j = from_binary(file, format);
-
-        state.PauseTiming();
-        std::fclose(file);
-        delete j;
-        state.ResumeTiming();
-    }
-
-    state.SetBytesProcessed(state.iterations() * bytes.size());
-}
-
-BENCHMARK_CAPTURE(FromBinaryFile, cbor / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::cbor);
-BENCHMARK_CAPTURE(FromBinaryFile, cbor / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::cbor);
-BENCHMARK_CAPTURE(FromBinaryFile, ubjson / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::ubjson);
-BENCHMARK_CAPTURE(FromBinaryFile, ubjson / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::ubjson);
-BENCHMARK_CAPTURE(FromBinaryFile, bjdata / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::bjdata);
-BENCHMARK_CAPTURE(FromBinaryFile, bson / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::bson);
-
-//////////////////////////////////////////////////////////////////////////////
-// parse binary formats: value shapes
-//////////////////////////////////////////////////////////////////////////////
-
-// The test files above are wide and shallow, but the readers' cost is per
-// container, so these cover the shapes that stress the container handling
-// itself. Every shape is wrapped in an object so that BSON, which requires an
-// object at the top level, measures the same value as the other formats.
-
-/// deeply nested arrays: one container per level, no other work
-static json make_nested()
-{
-    json nested = json::array();
-    json* p = &nested;
-    for (std::size_t i = 1; i < 1000; ++i)
-    {
-        p->push_back(json::array());
-        p = &p->operator[](0);
-    }
-
-    json j = json::object();
-    j["data"] = std::move(nested);
-    return j;
-}
-
-/// many sibling containers: maximum container churn, minimum nesting
-static json make_containers()
-{
-    json data = json::array();
-    for (std::size_t i = 0; i < 100000; ++i)
-    {
-        data.push_back(json::array({1, 2}));
-    }
-
-    json j = json::object();
-    j["data"] = std::move(data);
-    return j;
-}
-
-/// one flat array of numbers: the scalar decoding path, which must not move
-static json make_scalars()
-{
-    json data = json::array();
-    for (std::size_t i = 0; i < 1000000; ++i)
-    {
-        data.push_back(i);
-    }
-
-    json j = json::object();
-    j["data"] = std::move(data);
-    return j;
-}
-
-static void FromBinaryShape(benchmark::State& state, json (*build)(), const binary_format format)
-{
-    const std::vector<std::uint8_t> bytes = to_binary(build(), format);
-
-    for (auto _ : state)
-    {
-        state.PauseTiming();
-        auto* j = new json();
-        state.ResumeTiming();
-
-        *j = from_binary(bytes, format);
-
-        state.PauseTiming();
-        delete j;
-        state.ResumeTiming();
-    }
-
-    state.SetBytesProcessed(state.iterations() * bytes.size());
-}
-
-BENCHMARK_CAPTURE(FromBinaryShape, nested / cbor, make_nested, binary_format::cbor);
-BENCHMARK_CAPTURE(FromBinaryShape, nested / msgpack, make_nested, binary_format::msgpack);
-BENCHMARK_CAPTURE(FromBinaryShape, nested / ubjson, make_nested, binary_format::ubjson);
-BENCHMARK_CAPTURE(FromBinaryShape, nested / bjdata, make_nested, binary_format::bjdata);
-BENCHMARK_CAPTURE(FromBinaryShape, nested / bson, make_nested, binary_format::bson);
-BENCHMARK_CAPTURE(FromBinaryShape, containers / cbor, make_containers, binary_format::cbor);
-BENCHMARK_CAPTURE(FromBinaryShape, containers / msgpack, make_containers, binary_format::msgpack);
-BENCHMARK_CAPTURE(FromBinaryShape, containers / ubjson, make_containers, binary_format::ubjson);
-BENCHMARK_CAPTURE(FromBinaryShape, containers / ubjson_optimized, make_containers, binary_format::ubjson_optimized);
-BENCHMARK_CAPTURE(FromBinaryShape, containers / bjdata, make_containers, binary_format::bjdata);
-BENCHMARK_CAPTURE(FromBinaryShape, containers / bson, make_containers, binary_format::bson);
-// BSON names every array element, so a large array measures key generation
-// rather than scalar decoding and is left out here
-BENCHMARK_CAPTURE(FromBinaryShape, scalars / cbor, make_scalars, binary_format::cbor);
-BENCHMARK_CAPTURE(FromBinaryShape, scalars / msgpack, make_scalars, binary_format::msgpack);
-BENCHMARK_CAPTURE(FromBinaryShape, scalars / ubjson, make_scalars, binary_format::ubjson);
-BENCHMARK_CAPTURE(FromBinaryShape, scalars / bjdata, make_scalars, binary_format::bjdata);
-
-/*!
-@brief parse an indefinite-length CBOR string
-
-The writer never emits this form, so the input is assembled by hand: 0x7F
-opens the string, each chunk is a one-character string, and 0xFF closes it.
-*/
-static void FromCborChunkedString(benchmark::State& state, const std::size_t chunks)
-{
-    std::vector<std::uint8_t> bytes;
-    bytes.reserve(2 * chunks + 2);
-    bytes.push_back(0x7F);
-    for (std::size_t i = 0; i < chunks; ++i)
-    {
-        bytes.push_back(0x61); // string of length 1
-        bytes.push_back(0x61); // 'a'
-    }
-    bytes.push_back(0xFF);
-
-    for (auto _ : state)
-    {
-        json j = json::from_cbor(bytes);
-        benchmark::DoNotOptimize(j);
-    }
-
-    state.SetBytesProcessed(state.iterations() * bytes.size());
-}
-
-BENCHMARK_CAPTURE(FromCborChunkedString, 10000 chunks, 10000);
-
 BENCHMARK_MAIN();

tests/src/unit-bson.cpp

@@ -1688,3 +1688,76 @@ TEST_CASE("BSON roundtrips" * doctest::skip())
         }
     }
 }
+
+TEST_CASE("Invalid document size handling")
+{
+    SECTION("document size must be at least 5")
+    {
+        std::vector<std::uint8_t> const v = {0x04, 0x00, 0x00, 0x00, 0x00};
+        json _;
+        CHECK_THROWS_WITH_AS(_ = json::from_bson(v), "[json.exception.parse_error.112] parse error at byte 5: syntax error while parsing BSON document: document size 4 does not match the number of bytes read (5)", json::parse_error&);
+        CHECK(json::from_bson(v, true, false).is_discarded());
+    }
+
+    SECTION("declared document size must match consumed bytes (extra trailing element)")
+    {
+        // Declares 5-byte empty document but appends an int32 element after the declared end.
+        std::vector<std::uint8_t> const v =
+        {
+            0x05, 0x00, 0x00, 0x00,
+            0x10, 'a', 'd', 'm', 'i', 'n', 0x00,
+            0x01, 0x00, 0x00, 0x00,
+            0x00
+        };
+        json _;
+        CHECK_THROWS_WITH_AS(_ = json::from_bson(v), "[json.exception.parse_error.112] parse error at byte 16: syntax error while parsing BSON document: document size 5 does not match the number of bytes read (16)", json::parse_error&);
+        CHECK(json::from_bson(v, true, false).is_discarded());
+    }
+
+    SECTION("declared document size must match consumed bytes (premature terminator)")
+    {
+        // Declares 32-byte document but only contains the size field followed by an immediate terminator.
+        std::vector<std::uint8_t> const v =
+        {
+            0x20, 0x00, 0x00, 0x00,
+            0x00
+        };
+        json _;
+        CHECK_THROWS_WITH_AS(_ = json::from_bson(v), "[json.exception.parse_error.112] parse error at byte 5: syntax error while parsing BSON document: document size 32 does not match the number of bytes read (5)", json::parse_error&);
+        CHECK(json::from_bson(v, true, false).is_discarded());
+    }
+
+    SECTION("array declared size must match consumed bytes")
+    {
+        // Outer object contains an array "a" that declares 5 bytes (empty) but
+        // actually contains an int32 element before its terminator.
+        std::vector<std::uint8_t> const v =
+        {
+            0x14, 0x00, 0x00, 0x00,                         // object size = 20
+            0x04, 'a', 0x00,                                // key "a", array type
+            0x05, 0x00, 0x00, 0x00,                         // array declared size = 5 (empty)
+            0x10, '0', 0x00, 0x01, 0x00, 0x00, 0x00,        // extra int32 element "0" = 1
+            0x00,                                           // array terminator
+            0x00                                            // object terminator
+        };
+        json _;
+        CHECK_THROWS_WITH_AS(_ = json::from_bson(v), "[json.exception.parse_error.112] parse error at byte 19: syntax error while parsing BSON document: document size 5 does not match the number of bytes read (12)", json::parse_error&);
+        CHECK(json::from_bson(v, true, false).is_discarded());
+    }
+
+    SECTION("BSON string must end with 0x00")
+    {
+        // Length-prefixed string whose terminator byte is 'X' (0x58), not 0x00.
+        std::vector<std::uint8_t> const v =
+        {
+            0x0F, 0x00, 0x00, 0x00,
+            0x02, 's', 0x00,
+            0x02, 0x00, 0x00, 0x00,
+            'A', 'X',
+            0x00
+        };
+        json _;
+        CHECK_THROWS_WITH_AS(_ = json::from_bson(v), "[json.exception.parse_error.112] parse error at byte 13: syntax error while parsing BSON string: BSON string is not null-terminated", json::parse_error&);
+        CHECK(json::from_bson(v, true, false).is_discarded());
+    }
+}

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-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-regression2.cpp

@@ -763,35 +763,4 @@ TEST_CASE("regression tests 2")
 
 }
 
-TEST_CASE("regression test - excessive binary container size honors allow_exceptions=false")
-{
-    // CBOR array with declared length 2^63
-    const std::vector<std::uint8_t> cbor = {0x9b, 0x80, 0, 0, 0, 0, 0, 0, 0};
-    // CBOR map with declared length 2^63
-    const std::vector<std::uint8_t> cbor_m = {0xbb, 0x80, 0, 0, 0, 0, 0, 0, 0};
-    // UBJSON array with declared length 2^63-1
-    const std::vector<std::uint8_t> ubj = {'[', '#', 'L', 0x7f, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
-    // BJData array with declared length 2^63-1 (little endian)
-    const std::vector<std::uint8_t> bjd = {'[', '#', 'L', 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f};
-
-    // allow_exceptions=false must report failure instead of throwing/aborting
-    CHECK(json::from_cbor(cbor, true, false).is_discarded());
-    CHECK(json::from_cbor(cbor_m, true, false).is_discarded());
-    CHECK(json::from_ubjson(ubj, true, false).is_discarded());
-    CHECK(json::from_bjdata(bjd, true, false).is_discarded());
-
-    // allow_exceptions=true (the default) must still throw exactly as before.
-    // The exact message text is not checked here: on platforms where
-    // std::size_t is 32-bit, the CBOR reader's own length-narrowing check
-    // (get_cbor_container_size(), unrelated to this fix) intercepts a
-    // declared length of 2^63 before it ever reaches the check this test
-    // targets, with different (but equally valid, and already correct)
-    // wording -- see unit-cbor.cpp for coverage of that message.
-    json _;
-    CHECK_THROWS_AS(_ = json::from_cbor(cbor), json::out_of_range);
-
-    // regression guard: a genuinely truncated CBOR input must remain discarded
-    CHECK(json::from_cbor(std::vector<std::uint8_t> {0x9b, 0, 0, 0, 0, 0, 0, 0, 0x02}, true, false).is_discarded());
-}
-
 DOCTEST_CLANG_SUPPRESS_WARNING_POP

tests/src/unit-regression3.cpp

@@ -895,76 +895,5 @@ 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")
-{
-    // 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);
-    };
-
-    SECTION("duplicate key, second (scalar) value rejected - prior value is restored")
-    {
-        const json j = json::parse(R"({"a":1,"a":2})", drop_value_2);
-        CHECK(j.dump() == "{\"a\":1}");
-    }
-
-    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}");
-    }
-
-    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
-        {
-            return true;
-        });
-        CHECK(j.dump() == "{\"a\":2}");
-    }
-
-    SECTION("duplicate key, second value accepted (object) - last value wins")
-    {
-        const json j = json::parse(R"({"a":1,"a":{"x":2}})", [](int, json::parse_event_t, json&) noexcept
-        {
-            return true;
-        });
-        CHECK(j.dump() == "{\"a\":{\"x\":2}}");
-    }
-
-    SECTION("brand new (non-duplicate) key, value rejected - member is fully absent")
-    {
-        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}");
-    }
-}
-
 
 DOCTEST_CLANG_SUPPRESS_WARNING_POP

tests/src/unit-serialization.cpp

@@ -469,7 +469,7 @@ TEST_CASE("serialization of strings (bulk fast path)")
     SECTION("invalid UTF-8 handling is unaffected by the fast path")
     {
         const json j = std::string("valid\xff" "more");
-        CHECK_THROWS_WITH_AS(utils::ignore_return_value(j.dump()), "[json.exception.type_error.316] invalid UTF-8 byte at index 5: 0xFF", json::type_error&);
+        CHECK_THROWS_WITH_AS(j.dump(), "[json.exception.type_error.316] invalid UTF-8 byte at index 5: 0xFF", json::type_error&);
         CHECK(j.dump(-1, ' ', false, json::error_handler_t::replace) == "\"valid\xef\xbf\xbd" "more\"");
         CHECK(j.dump(-1, ' ', true, json::error_handler_t::replace) == "\"valid\\ufffdmore\"");
         CHECK(j.dump(-1, ' ', false, json::error_handler_t::ignore) == "\"validmore\"");