Route the -Wduplicated-branches pragma through Hedley

Match #5485, which moved the binary writer's hand-rolled diagnostic
pragmas onto JSON_HEDLEY_PRAGMA (merged into develop while this branch
was open). The devirtualization's -Wduplicated-branches suppression in
write_compact_float was the one raw '#pragma GCC diagnostic' left; it
now uses JSON_HEDLEY_PRAGMA like the adjacent -Wfloat-equal line, still
guarded to GCC >= 7 and non-clang (the warning exists only there).

Co-Authored-By: Claude <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XAYM1qhSA2FDaDcGfPW3fG
Signed-off-by: Niels Lohmann <mail@nlohmann.me>

include/nlohmann/detail/input/binary_reader.hpp

@@ -1434,7 +1434,7 @@ 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
-                container_frame top = container_stack.back();
+                const container_frame top = container_stack.back();
                 bool at_end = false;
 
                 if (top.remaining != npos)
@@ -2211,7 +2211,7 @@ class binary_reader
             // would otherwise alias.
             for (;;)
             {
-                container_frame top = container_stack.back();
+                const container_frame top = container_stack.back();
 
                 if (top.remaining != npos)
                 {

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
 {

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>
+    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>;
@@ -4374,7 +4382,8 @@ 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;
     }
 
@@ -4397,7 +4406,8 @@ 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;
     }
 
@@ -4422,7 +4432,8 @@ 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;
     }
 
@@ -4450,7 +4461,8 @@ 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;
     }
 
@@ -4477,7 +4489,8 @@ 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;
     }
 

tests/benchmarks/src/benchmarks.cpp

@@ -252,4 +252,323 @@ 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-binary_writer_sinks.cpp

@@ -0,0 +1,198 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  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-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(j.dump(), "[json.exception.type_error.316] invalid UTF-8 byte at index 5: 0xFF", json::type_error&);
+        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(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\"");