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

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

include/nlohmann/detail/input/json_sax.hpp

@@ -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

include/nlohmann/detail/output/output_adapters.hpp

@@ -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
 {