Mark the parse callback in the new test noexcept

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

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

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

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

include/nlohmann/detail/input/json_sax.hpp

@@ -8,6 +8,7 @@
 
 #pragma once
 
+#include <algorithm> // min
 #include <cstddef>
 #include <string> // string
 #include <type_traits> // enable_if_t
@@ -17,6 +18,7 @@
 #include <nlohmann/detail/exceptions.hpp>
 #include <nlohmann/detail/input/lexer.hpp>
 #include <nlohmann/detail/macro_scope.hpp>
+#include <nlohmann/detail/meta/cpp_future.hpp>
 #include <nlohmann/detail/string_concat.hpp>
 NLOHMANN_JSON_NAMESPACE_BEGIN
 
@@ -150,6 +152,29 @@ constexpr std::size_t unknown_size()
     return (std::numeric_limits<std::size_t>::max)();
 }
 
+/*!
+@brief reserve capacity for @a len elements in array @a arr
+
+Reserving upfront avoids repeated reallocations while the elements are added,
+but the reservation is capped so a bogus/hostile length (which is not bounded
+by max_size(), unlike e.g. std::vector) cannot trigger an oversized allocation
+for a small or truncated input.
+
+The overload below is selected for array types without reserve() (e.g.,
+std::deque), which are then left untouched.
+*/
+template<typename ArrayType>
+auto reserve_array(ArrayType& arr, std::size_t len, priority_tag<1> /*unused*/)
+-> decltype(arr.reserve(len), void())
+{
+    constexpr std::size_t reserve_cap = 16384;
+    arr.reserve((std::min)(len, reserve_cap));
+}
+
+template<typename ArrayType>
+inline void reserve_array(ArrayType& /*arr*/, std::size_t /*len*/, priority_tag<0> /*unused*/)
+{}
+
 /*!
 @brief SAX implementation to create a JSON value from SAX events
 
@@ -305,6 +330,11 @@ class json_sax_dom_parser
             JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
         }
 
+        if (len != detail::unknown_size())
+        {
+            reserve_array(*ref_stack.back()->m_data.m_value.array, len, priority_tag<1> {});
+        }
+
         return true;
     }
 
@@ -683,6 +713,11 @@ class json_sax_dom_callback_parser
             {
                 JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
             }
+
+            if (len != detail::unknown_size())
+            {
+                reserve_array(*ref_stack.back()->m_data.m_value.array, len, priority_tag<1> {});
+            }
         }
 
         return true;

include/nlohmann/detail/output/output_adapters.hpp

@@ -13,7 +13,6 @@
 #include <iterator> // back_inserter
 #include <memory> // shared_ptr, make_shared
 #include <string> // basic_string
-#include <utility> // move
 #include <vector> // vector
 
 #ifndef JSON_NO_IO
@@ -45,32 +44,22 @@ template<typename CharType> struct output_adapter_protocol
 template<typename CharType>
 using output_adapter_t = std::shared_ptr<output_adapter_protocol<CharType>>;
 
-/// @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.
+/// output adapter for byte vectors
 template<typename CharType, typename AllocatorType = std::allocator<CharType>>
-class output_vector_sink
+class output_vector_adapter : public output_adapter_protocol<CharType>
 {
   public:
-    explicit output_vector_sink(std::vector<CharType, AllocatorType>& vec) noexcept
+    explicit output_vector_adapter(std::vector<CharType, AllocatorType>& vec) noexcept
         : v(vec)
     {}
 
-    void write_character(CharType c)
+    void write_character(CharType c) override
     {
         v.push_back(c);
     }
 
-    // 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)
+    JSON_HEDLEY_NON_NULL(2)
+    void write_characters(const CharType* s, std::size_t length) override
     {
         v.insert(v.end(), s, s + length);
     }
@@ -79,34 +68,6 @@ class output_vector_sink
     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>
@@ -157,39 +118,6 @@ 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
 {

include/nlohmann/json.hpp

@@ -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, typename OutputSinkType>
+    template<typename BasicJsonType, typename CharType>
     friend class ::nlohmann::detail::binary_writer;
     template<typename BasicJsonType, typename InputType, typename SAX>
     friend class ::nlohmann::detail::binary_reader;
@@ -188,14 +188,6 @@ 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>;
@@ -3584,6 +3576,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         std::swap(m_data.m_type, other.m_data.m_type);
         std::swap(m_data.m_value, other.m_data.m_value);
 
+#if JSON_DIAGNOSTIC_POSITIONS
+        std::swap(start_position, other.start_position);
+        std::swap(end_position, other.end_position);
+#endif
+
         set_parents();
         other.set_parents();
         assert_invariant();
@@ -4382,8 +4379,7 @@ 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;
-        result.reserve(detail::binary_reserve_hint(j));
-        vector_writer(result).write_cbor(j);
+        to_cbor(j, result);
         return result;
     }
 
@@ -4406,8 +4402,7 @@ 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;
-        result.reserve(detail::binary_reserve_hint(j));
-        vector_writer(result).write_msgpack(j);
+        to_msgpack(j, result);
         return result;
     }
 
@@ -4432,8 +4427,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
             const bool use_type = false)
     {
         std::vector<std::uint8_t> result;
-        result.reserve(detail::binary_reserve_hint(j));
-        vector_writer(result).write_ubjson(j, use_size, use_type);
+        to_ubjson(j, result, use_size, use_type);
         return result;
     }
 
@@ -4461,8 +4455,7 @@ 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;
-        result.reserve(detail::binary_reserve_hint(j));
-        vector_writer(result).write_ubjson(j, use_size, use_type, true, true, version);
+        to_bjdata(j, result, use_size, use_type, version);
         return result;
     }
 
@@ -4489,8 +4482,7 @@ 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;
-        result.reserve(detail::binary_reserve_hint(j));
-        vector_writer(result).write_bson(j);
+        to_bson(j, result);
         return result;
     }
 

tests/src/unit-binary_writer_sinks.cpp

@@ -1,198 +0,0 @@
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  JSON for Modern C++ (supporting code)
-// |  |  |__   |  |  | | | |  version 3.12.0
-// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
-//
-// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
-// SPDX-License-Identifier: MIT
-
-#include "doctest_compatibility.h"
-
-#include <nlohmann/json.hpp>
-using nlohmann::json;
-
-#include <cstdint>
-#include <string>
-#include <vector>
-
-namespace
-{
-
-// a spread of values exercising every writer path: scalars of each width, the
-// float paths, strings, binary, and containers big enough to reallocate
-std::vector<json> test_values()
-{
-    json big_array = json::array();
-    for (int i = 0; i < 5000; ++i)
-    {
-        big_array.push_back(i);
-    }
-
-    json big_object = json::object();
-    for (int i = 0; i < 1000; ++i)
-    {
-        big_object[std::to_string(i)] = i;
-    }
-
-    return
-    {
-        json(nullptr), json(true), json(false),
-        json(0), json(-1), json(255), json(-129), json(65535), json(-32769),
-        json(4294967295U), json(-2147483649LL), json(18446744073709551615ULL),
-        json(0.0), json(-0.5), json(3.1415926535897932),
-        json(""), json("hello"), json(std::string(1000, 'x')),
-        json::binary({0x00, 0x01, 0x02}, 42),
-        json::array(), json::object(),
-        json::array({1, 2, 3}), json({{"a", 1}, {"b", nullptr}}),
-        json({{"nested", {{"deep", json::array({1, "two", 3.0, nullptr})}}}}),
-        big_array, big_object
-    };
-}
-
-// values to_bson() accepts: the document must be an object
-std::vector<json> bson_values()
-{
-    json big_object = json::object();
-    for (int i = 0; i < 1000; ++i)
-    {
-        big_object[std::to_string(i)] = i;
-    }
-
-    return
-    {
-        json::object(),
-        json({{"a", 1}, {"b", nullptr}, {"c", true}, {"d", 2.5}, {"e", "text"}}),
-        json({{"arr", json::array({1, 2, 3})}, {"obj", {{"k", "v"}}}}),
-        big_object
-    };
-}
-
-} // namespace
-
-// The vector-returning to_*(j) overloads write through the non-virtual
-// output_vector_sink, while to_*(j, adapter) goes through output_adapter_sink.
-// The two are separate code paths that must stay byte-for-byte identical; these
-// checks fail if either overload is ever changed without the other.
-TEST_CASE("binary writer output sinks")
-{
-    SECTION("vector sink and adapter sink agree")
-    {
-        // note: no SUBCASE inside these loops - doctest keys subcases by
-        // name/file/line, so a subcase in a loop body would only ever run for
-        // the first iteration
-        for (const auto& j : test_values())
-        {
-            CAPTURE(j.dump(-1, ' ', false, json::error_handler_t::replace));
-
-            std::vector<std::uint8_t> cbor;
-            json::to_cbor(j, cbor);
-            CHECK(json::to_cbor(j) == cbor);
-
-            std::vector<std::uint8_t> msgpack;
-            json::to_msgpack(j, msgpack);
-            CHECK(json::to_msgpack(j) == msgpack);
-
-            for (const bool use_size :
-                    {
-                        false, true
-                    })
-            {
-                for (const bool use_type :
-                        {
-                            false, true
-                        })
-                {
-                    if (use_type && !use_size)
-                    {
-                        continue; // not a supported combination
-                    }
-                    CAPTURE(use_size);
-                    CAPTURE(use_type);
-                    std::vector<std::uint8_t> ubjson;
-                    json::to_ubjson(j, ubjson, use_size, use_type);
-                    CHECK(json::to_ubjson(j, use_size, use_type) == ubjson);
-                }
-            }
-
-            for (const auto version :
-                    {
-                        json::bjdata_version_t::draft2, json::bjdata_version_t::draft3
-                    })
-            {
-                std::vector<std::uint8_t> bjdata;
-                json::to_bjdata(j, bjdata, false, false, version);
-                CHECK(json::to_bjdata(j, false, false, version) == bjdata);
-            }
-        }
-
-        for (const auto& j : bson_values())
-        {
-            CAPTURE(j.dump());
-            std::vector<std::uint8_t> bson;
-            json::to_bson(j, bson);
-            CHECK(json::to_bson(j) == bson);
-        }
-    }
-
-    SECTION("the char adapter produces the same bytes")
-    {
-        for (const auto& j : test_values())
-        {
-            CAPTURE(j.dump(-1, ' ', false, json::error_handler_t::replace));
-
-            const std::vector<std::uint8_t> expected = json::to_cbor(j);
-            std::vector<char> as_char;
-            json::to_cbor(j, as_char);
-
-            REQUIRE(as_char.size() == expected.size());
-            std::vector<std::uint8_t> as_bytes;
-            as_bytes.reserve(as_char.size());
-            for (const char c : as_char)
-            {
-                as_bytes.push_back(static_cast<std::uint8_t>(c));
-            }
-            CHECK(as_bytes == expected);
-        }
-    }
-}
-
-// binary_reserve_hint() is documented as a *lower* bound on the serialized size,
-// so that reserving it up front can never leave the returned vector holding
-// capacity beyond what the value actually needs.
-TEST_CASE("binary_reserve_hint never over-reserves")
-{
-    for (const auto& j : test_values())
-    {
-        CAPTURE(j.dump(-1, ' ', false, json::error_handler_t::replace));
-
-        const std::size_t hint = nlohmann::detail::binary_reserve_hint(j);
-
-        CHECK(hint <= json::to_cbor(j).size());
-        CHECK(hint <= json::to_msgpack(j).size());
-        CHECK(hint <= json::to_ubjson(j).size());
-        CHECK(hint <= json::to_ubjson(j, true, true).size());
-        CHECK(hint <= json::to_bjdata(j).size());
-    }
-
-    for (const auto& j : bson_values())
-    {
-        CAPTURE(j.dump());
-        CHECK(nlohmann::detail::binary_reserve_hint(j) <= json::to_bson(j).size());
-    }
-
-    SECTION("scalars get no hint")
-    {
-        CHECK(nlohmann::detail::binary_reserve_hint(json(nullptr)) == 0);
-        CHECK(nlohmann::detail::binary_reserve_hint(json(42)) == 0);
-        CHECK(nlohmann::detail::binary_reserve_hint(json("a string")) == 0);
-        CHECK(nlohmann::detail::binary_reserve_hint(json::binary({0x01})) == 0);
-    }
-
-    SECTION("containers are hinted from their element count")
-    {
-        CHECK(nlohmann::detail::binary_reserve_hint(json::array()) == 1);
-        CHECK(nlohmann::detail::binary_reserve_hint(json::array({1, 2, 3})) == 4);
-        CHECK(nlohmann::detail::binary_reserve_hint(json::object()) == 1);
-        CHECK(nlohmann::detail::binary_reserve_hint(json({{"a", 1}, {"b", 2}})) == 5);
-    }
-}

tests/src/unit-bjdata.cpp

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

tests/src/unit-cbor.cpp

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

tests/src/unit-class_parser.cpp

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

tests/src/unit-msgpack.cpp

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

tests/src/unit-regression3.cpp

@@ -27,6 +27,7 @@ using ordered_json = nlohmann::ordered_json;
 #endif
 
 #include <cstdio>
+#include <deque>
 #include <list>
 #include <type_traits>
 #include <utility>
@@ -896,4 +897,49 @@ TEST_CASE("issue #5402 - update(merge_objects=true) overwrites a primitive with
 }
 
 
+TEST_CASE("regression test #5476 - array type without reserve()")
+{
+    // the capacity reserved for definite-length arrays must not require the
+    // array type to have a reserve() member function
+    using deque_json = nlohmann::basic_json<std::map, std::deque>;
+
+    SECTION("std::deque")
+    {
+        const auto j = deque_json::parse(R"({"a":[1,[2,3]],"b":[]})");
+        CHECK(j.dump() == R"({"a":[1,[2,3]],"b":[]})");
+
+        // the binary formats pass a definite length to start_array()
+        CHECK(deque_json::from_cbor(deque_json::to_cbor(j)) == j);
+        CHECK(deque_json::from_msgpack(deque_json::to_msgpack(j)) == j);
+
+        // parse() instantiates the callback parser as well, which reserves too
+        const auto with_callback = deque_json::parse(R"([1,2,3])", [](int /*depth*/, deque_json::parse_event_t /*event*/, deque_json& /*parsed*/) noexcept
+        {
+            return true;
+        });
+        CHECK(with_callback == deque_json({1, 2, 3}));
+    }
+
+    SECTION("std::vector still reserves")
+    {
+        json array = json::array();
+        for (int i = 0; i < 100; ++i)
+        {
+            array.push_back(i);
+        }
+
+        const auto j = json::from_cbor(json::to_cbor(array));
+        CHECK(j == array);
+        CHECK(j.get_ref<const json::array_t&>().capacity() >= 100);
+    }
+
+    SECTION("the reservation stays capped")
+    {
+        // CBOR array announcing 2^32-1 elements, but truncated right after the
+        // header: the input must be rejected without reserving that capacity
+        const std::vector<std::uint8_t> truncated = {0x9A, 0xFF, 0xFF, 0xFF, 0xFF};
+        CHECK(json::from_cbor(truncated, true, false).is_discarded());
+    }
+}
+
 DOCTEST_CLANG_SUPPRESS_WARNING_POP

tests/src/unit-ubjson.cpp

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