Merge branch 'develop' into claude/issue-5387-duplicate-check-bd7853

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-10-04 22:05:41 +01:00 · 2026-09-23 20:01:45 +02:00
parent c3ccb3e962 1054b2097e
commit a4c0df3c14
14 changed files with 1713 additions and 484 deletions
@@ -8,11 +8,11 @@

 #pragma once

-#include <algorithm> // min
+#include <algorithm> // find_if, min
 #include <cstddef>
 #include <string> // string
 #include <type_traits> // enable_if_t
-#include <utility> // move
+#include <utility> // move, pair
 #include <vector> // vector

 #include <nlohmann/detail/exceptions.hpp>
@@ -278,7 +278,7 @@ class json_sax_dom_parser

        if (JSON_HEDLEY_UNLIKELY(len != detail::unknown_size() && len > ref_stack.back()->max_size()))
        {
-            JSON_THROW(out_of_range::create(408, concat("excessive object size: ", std::to_string(len)), ref_stack.back()));
+            return parse_error(0, "", out_of_range::create(408, concat("excessive object size: ", std::to_string(len)), ref_stack.back()));
        }

        return true;
@@ -327,7 +327,7 @@ class json_sax_dom_parser

        if (JSON_HEDLEY_UNLIKELY(len != detail::unknown_size() && len > ref_stack.back()->max_size()))
        {
-            JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
+            return parse_error(0, "", out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
        }

        if (len != detail::unknown_size())
@@ -611,7 +611,7 @@ class json_sax_dom_callback_parser
            // check object limit
            if (JSON_HEDLEY_UNLIKELY(len != detail::unknown_size() && len > ref_stack.back()->max_size()))
            {
-                JSON_THROW(out_of_range::create(408, concat("excessive object size: ", std::to_string(len)), ref_stack.back()));
+                return parse_error(0, "", out_of_range::create(408, concat("excessive object size: ", std::to_string(len)), ref_stack.back()));
            }
        }
        return true;
@@ -631,7 +631,17 @@ class json_sax_dom_callback_parser
        // add discarded value at the given key and store the reference for later
        if (keep && ref_stack.back())
        {
-            object_element = &(ref_stack.back()->m_data.m_value.object->operator[](val) = discarded);
+            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);
        }

        return true;
@@ -643,13 +653,18 @@ 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
-                *ref_stack.back() = discarded;
+                // 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;

 #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
            {
@@ -663,6 +678,10 @@ 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);
            }
        }

@@ -711,7 +730,7 @@ class json_sax_dom_callback_parser
            // check array limit
            if (JSON_HEDLEY_UNLIKELY(len != detail::unknown_size() && len > ref_stack.back()->max_size()))
            {
-                JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
+                return parse_error(0, "", out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
            }

            if (len != detail::unknown_size())
@@ -743,16 +762,25 @@ 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
-                *ref_stack.back() = discarded;
+                // 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;

 #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
+                }
            }
        }

@@ -869,6 +897,35 @@ class json_sax_dom_callback_parser
    }
 #endif

+    /// 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 the key the value now being handled will be stored under

@@ -887,7 +944,9 @@ class json_sax_dom_callback_parser
    }

    /*!
-    @brief remove the discarded value the callback rejected from its parent
+    @brief remove the discarded value the callback rejected from its parent,
+    unless it is a duplicate key's slot with a stashed previous value, in
+    which case that previous value is restored instead

    A rejected value can only ever be the one most recently added to @a parent:
    the last element of an array, or the placeholder key() stored under @a key
@@ -902,7 +961,7 @@ class json_sax_dom_callback_parser
    @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
    */
-    static void remove_discarded_value(BasicJsonType& parent, const string_t& key)
+    void remove_discarded_value(BasicJsonType& parent, const string_t& key)
    {
        if (parent.is_array())
        {
@@ -918,7 +977,12 @@ class json_sax_dom_callback_parser
            const auto it = object.find(key);
            if (it != object.end() && it->second.is_discarded())
            {
-                object.erase(it);
+                // a duplicate key's slot has a stashed previous value that
+                // must be restored instead of being erased
+                if (!resolve_duplicate_key_stash(&it->second, true))
+                {
+                    object.erase(it);
+                }
            }
        }
    }
@@ -1020,6 +1084,16 @@ 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};
    }

@@ -1039,6 +1113,12 @@ 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
@@ -13,6 +13,7 @@
 #include <iterator> // back_inserter
 #include <memory> // shared_ptr, make_shared
 #include <string> // basic_string
+#include <utility> // move
 #include <vector> // vector

 #ifndef JSON_NO_IO
@@ -44,22 +45,32 @@ template<typename CharType> struct output_adapter_protocol
 template<typename CharType>
 using output_adapter_t = std::shared_ptr<output_adapter_protocol<CharType>>;

-/// output adapter for byte vectors
+/// @brief non-virtual output sink writing into a std::vector
+///
+/// This sink is not part of the virtual output_adapter_protocol hierarchy: it is
+/// passed to binary_writer by value as a template parameter, so
+/// write_character()/write_characters() are ordinary (inlinable) calls with no
+/// vtable lookup and no shared_ptr. It is used for the common
+/// `to_cbor`/`to_msgpack`/... into a std::vector. output_vector_adapter below
+/// wraps this same sink to provide the virtual interface.
 template<typename CharType, typename AllocatorType = std::allocator<CharType>>
-class output_vector_adapter : public output_adapter_protocol<CharType>
+class output_vector_sink
 {
  public:
-    explicit output_vector_adapter(std::vector<CharType, AllocatorType>& vec) noexcept
+    explicit output_vector_sink(std::vector<CharType, AllocatorType>& vec) noexcept
        : v(vec)
    {}

-    void write_character(CharType c) override
+    void write_character(CharType c)
    {
        v.push_back(c);
    }

-    JSON_HEDLEY_NON_NULL(2)
-    void write_characters(const CharType* s, std::size_t length) override
+    // no JSON_HEDLEY_NON_NULL here: binary_writer legitimately passes a null
+    // pointer with length 0 for empty strings/binary values. Appending an empty
+    // range is a no-op; the type-erased path tolerates this via the (unattributed)
+    // virtual base, and the concrete sink must do the same.
+    void write_characters(const CharType* s, std::size_t length)
    {
        v.insert(v.end(), s, s + length);
    }
@@ -68,6 +79,34 @@ class output_vector_adapter : public output_adapter_protocol<CharType>
    std::vector<CharType, AllocatorType>& v;
 };

+/// output adapter for byte vectors
+///
+/// The appending itself lives in output_vector_sink; this class only adds the
+/// virtual output_adapter_protocol interface on top of it, so both the
+/// type-erased and the templated path share one implementation.
+template<typename CharType, typename AllocatorType = std::allocator<CharType>>
+class output_vector_adapter : public output_adapter_protocol<CharType>
+{
+  public:
+    explicit output_vector_adapter(std::vector<CharType, AllocatorType>& vec) noexcept
+        : sink(vec)
+    {}
+
+    void write_character(CharType c) override
+    {
+        sink.write_character(c);
+    }
+
+    JSON_HEDLEY_NON_NULL(2)
+    void write_characters(const CharType* s, std::size_t length) override
+    {
+        sink.write_characters(s, length);
+    }
+
+  private:
+    output_vector_sink<CharType, AllocatorType> sink;
+};
+
 #ifndef JSON_NO_IO
 /// output adapter for output streams
 template<typename CharType>
@@ -118,6 +157,39 @@ class output_string_adapter : public output_adapter_protocol<CharType>
    StringType& str;
 };

+/// @brief output sink forwarding to a type-erased output adapter
+///
+/// Wraps the polymorphic output_adapter_t so the same binary_writer template can
+/// also target arbitrary adapters (output streams, strings, user-provided
+/// adapters) via the `output_adapter`-based overloads. Each write still goes
+/// through one virtual call, exactly as before; only the concrete sinks above
+/// avoid it.
+template<typename CharType>
+class output_adapter_sink
+{
+  public:
+    explicit output_adapter_sink(output_adapter_t<CharType> adapter)
+        : oa(std::move(adapter))
+    {
+        JSON_ASSERT(oa);
+    }
+
+    void write_character(CharType c)
+    {
+        oa->write_character(c);
+    }
+
+    // no JSON_HEDLEY_NON_NULL: forwards (null, 0) for empty payloads, exactly as
+    // the type-erased path already did before this sink existed
+    void write_characters(const CharType* s, std::size_t length)
+    {
+        oa->write_characters(s, length);
+    }
+
+  private:
+    output_adapter_t<CharType> oa;
+};
+
 template<typename CharType, typename StringType = std::basic_string<CharType>>
 class output_adapter
 {
@@ -140,7 +140,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
    friend ::nlohmann::detail::serializer<basic_json>;
    template<typename BasicJsonType>
    friend class ::nlohmann::detail::iter_impl;
-    template<typename BasicJsonType, typename CharType>
+    template<typename BasicJsonType, typename CharType, typename OutputSinkType>
    friend class ::nlohmann::detail::binary_writer;
    template<typename BasicJsonType, typename InputType, typename SAX>
    friend class ::nlohmann::detail::binary_reader;
@@ -188,6 +188,14 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
    template<typename InputType>
    using binary_reader = ::nlohmann::detail::binary_reader<basic_json, InputType>;
    template<typename CharType> using binary_writer = ::nlohmann::detail::binary_writer<basic_json, CharType>;
+    // binary_writer over a concrete (non-virtual) sink appending into a std::vector,
+    // used by the vector-returning to_* overloads
+    template<typename CharType> using vector_binary_writer =
+        ::nlohmann::detail::binary_writer<basic_json, CharType, ::nlohmann::detail::output_vector_sink<CharType>>;
+    template<typename CharType> static vector_binary_writer<CharType> vector_writer(std::vector<CharType>& v)
+    {
+        return vector_binary_writer<CharType>(::nlohmann::detail::output_vector_sink<CharType>(v));
+    }

  JSON_PRIVATE_UNLESS_TESTED:
    using serializer = ::nlohmann::detail::serializer<basic_json>;
@@ -3812,6 +3820,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
            JSON_THROW(invalid_iterator::create(211, "passed iterators may not belong to container", this));
        }

+        // passed iterators must belong to arrays
+        if (JSON_HEDLEY_UNLIKELY(!first.m_object->is_array()))
+        {
+            JSON_THROW(invalid_iterator::create(202, "iterators first and last must point to arrays", this));
+        }
+
        // insert to array and return iterator
        return insert_iterator(pos, first.m_it.array_iterator, last.m_it.array_iterator);
    }
@@ -4739,7 +4753,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
    static std::vector<std::uint8_t> to_cbor(const basic_json& j)
    {
        std::vector<std::uint8_t> result;
-        to_cbor(j, result);
+        result.reserve(detail::binary_reserve_hint(j));
+        vector_writer(result).write_cbor(j);
        return result;
    }

@@ -4762,7 +4777,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
    static std::vector<std::uint8_t> to_msgpack(const basic_json& j)
    {
        std::vector<std::uint8_t> result;
-        to_msgpack(j, result);
+        result.reserve(detail::binary_reserve_hint(j));
+        vector_writer(result).write_msgpack(j);
        return result;
    }

@@ -4787,7 +4803,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
            const bool use_type = false)
    {
        std::vector<std::uint8_t> result;
-        to_ubjson(j, result, use_size, use_type);
+        result.reserve(detail::binary_reserve_hint(j));
+        vector_writer(result).write_ubjson(j, use_size, use_type);
        return result;
    }

@@ -4815,7 +4832,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
            const bjdata_version_t version = bjdata_version_t::draft2)
    {
        std::vector<std::uint8_t> result;
-        to_bjdata(j, result, use_size, use_type, version);
+        result.reserve(detail::binary_reserve_hint(j));
+        vector_writer(result).write_ubjson(j, use_size, use_type, true, true, version);
        return result;
    }

@@ -4842,7 +4860,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
    static std::vector<std::uint8_t> to_bson(const basic_json& j)
    {
        std::vector<std::uint8_t> result;
-        to_bson(j, result);
+        result.reserve(detail::binary_reserve_hint(j));
+        vector_writer(result).write_bson(j);
        return result;
    }

@@ -5633,34 +5652,139 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec

            case value_t::object:
            {
-                // first pass: traverse this object's elements
+                // 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;
                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())
                    {
-                        // 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());
+                        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()}
+                        });
                    }
                    else
                    {
-                        // found a key that is not in o -> remove it
+                        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}
                        }));
                    }
-                }

-                // second pass: traverse other object's elements
-                for (auto it = target.cbegin(); it != target.cend(); ++it)
-                {
-                    if (source.find(it.key()) == source.end())
+                    // 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)
                    {
-                        // 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(
                        {