Add benchmarks for SAX parsing, value operations, JSON Pointer, and conversions

Squashed onto develop cd6b428ef (CI fixes from #5860). Original commits:

- Add benchmarks for SAX parsing, value operations, JSON Pointer, and conversions
- Time copies together with their destruction in the benchmarks
- Time destroying the json in ToJsonStrings

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

tests/CMakeLists.txt

@@ -118,7 +118,7 @@ endif()
 
 if (CMAKE_CXX_COMPILER_ID STREQUAL "MSVC")
     # avoid stack overflow, see https://github.com/nlohmann/json/issues/2955
-    json_test_set_test_options("test-bon8;test-cbor;test-msgpack;test-ubjson;test-bjdata;test-binary_formats" LINK_OPTIONS /STACK:4000000)
+    json_test_set_test_options("test-bon8;test-cbor;test-msgpack;test-ubjson;test-bjdata;test-bjdata_round_trip_draft2;test-bjdata_round_trip_draft3;test-binary_formats" LINK_OPTIONS /STACK:4000000)
 endif()
 
 # disable exceptions for test-disabled_exceptions

tests/benchmarks/README.md

@@ -16,6 +16,15 @@ Micro-benchmarks for parsing, serialization and the binary formats, written with
 | `FromBinaryBuffer`, `FromBinaryFile` | read CBOR, MessagePack, UBJSON, BJData and BSON from a buffer or a `FILE*` |
 | `FromBinaryShape` | read deeply nested, container-heavy and scalar-heavy documents in every binary format |
 | `FromCborChunkedString` | read CBOR strings split into indefinite-length chunks |
+| `SaxParse` | parse with a SAX handler that only counts events, so no values are built |
+| `Copy`, `CopyAssign`, `CopyRing` | copy a parsed document and destroy a copy, both timed: a temporary copy, an assignment over an earlier copy, and replacing the oldest of eight live copies |
+| `CopyOnly`, `DestroyOnly` | only the copy or only the destruction, the other half untimed; a fast destructor can leave work to the next allocations, so these tell the halves apart but do not compare versions |
+| `Equal`, `Iterate` | compare a parsed document with a copy, or visit every value with range-based `for` loops |
+| `Flatten`, `FlattenOrdered`, `Unflatten` | `flatten()` for `json` and `ordered_json`, and `unflatten()` |
+| `Diff`, `Patch` | `diff()` against the document with every eighth scalar changed, and applying that patch |
+| `JsonPointerParse`, `JsonPointerToString`, `JsonPointerAt`, `JsonPointerContains` | the JSON pointers of every scalar in a document: parse them from strings, turn them back into strings, look them up with `at()` and `contains()` |
+| `GetVectorInt`, `GetVectorDouble`, `GetMap` | `get<std::vector<std::int64_t>>()`, `get<std::vector<double>>()` and `get<std::map<std::string, json>>()` on large arrays and a large flat object |
+| `ToJsonStrings` | create a `json` array from a `std::vector` of 100,000 strings, copied or moved, and destroy it again |
 
 The input files are those of [nativejson-benchmark](https://github.com/miloyip/nativejson-benchmark) (`canada`,
 `citm_catalog`, `twitter`), a large `jeopardy` file, and number-heavy files (`floats`, `signed_ints`, ...).

tests/benchmarks/src/benchmarks.cpp

@@ -8,11 +8,14 @@
 
 #include <benchmark/benchmark.h>
 #include <nlohmann/json.hpp>
-#include <fstream>
 #include <array>
+#include <cstdint>
 #include <deque>
+#include <fstream>
+#include <map>
 #include <numeric>
 #include <set>
+#include <string>
 #include <vector>
 #include <test_data.hpp>
 
@@ -624,6 +627,584 @@ static void FromCborChunkedString(benchmark::State& state, const std::size_t chu
 
 BENCHMARK_CAPTURE(FromCborChunkedString, 10000 chunks, 10000);
 
+//////////////////////////////////////////////////////////////////////////////
+// SAX-parse JSON from string
+//
+// sax_parse() with a handler that does next to nothing runs the lexer and
+// parser without building values, so the gap to ParseString above is the cost
+// of building the DOM.
+//////////////////////////////////////////////////////////////////////////////
+
+static std::string read_file(const char* filename)
+{
+    std::ifstream f(filename);
+    return std::string((std::istreambuf_iterator<char>(f)), std::istreambuf_iterator<char>());
+}
+
+static json load_json(const char* filename)
+{
+    return json::parse(read_file(filename));
+}
+
+/// SAX handler that only counts the events, so that the handler costs next to nothing
+class counting_sax : public nlohmann::json_sax<json>
+{
+  public:
+    std::size_t events = 0;
+
+    bool null() override
+    {
+        return count();
+    }
+    bool boolean(bool /*val*/) override
+    {
+        return count();
+    }
+    bool number_integer(number_integer_t /*val*/) override
+    {
+        return count();
+    }
+    bool number_unsigned(number_unsigned_t /*val*/) override
+    {
+        return count();
+    }
+    bool number_float(number_float_t /*val*/, const string_t& /*s*/) override
+    {
+        return count();
+    }
+    bool string(string_t& /*val*/) override
+    {
+        return count();
+    }
+    bool binary(binary_t& /*val*/) override
+    {
+        return count();
+    }
+    bool start_object(std::size_t /*elements*/) override
+    {
+        return count();
+    }
+    bool key(string_t& /*val*/) override
+    {
+        return count();
+    }
+    bool end_object() override
+    {
+        return count();
+    }
+    bool start_array(std::size_t /*elements*/) override
+    {
+        return count();
+    }
+    bool end_array() override
+    {
+        return count();
+    }
+    bool parse_error(std::size_t /*position*/, const std::string& /*last_token*/, const json::exception& /*ex*/) override
+    {
+        return false;
+    }
+
+  private:
+    bool count()
+    {
+        ++events;
+        return true;
+    }
+};
+
+static void SaxParse(benchmark::State& state, const char* filename)
+{
+    const std::string str = read_file(filename);
+
+    for (auto _ : state)
+    {
+        counting_sax sax;
+        bool result = json::sax_parse(str, &sax);
+        benchmark::DoNotOptimize(result);
+        benchmark::DoNotOptimize(sax.events);
+    }
+
+    state.SetBytesProcessed(state.iterations() * str.size());
+}
+BENCHMARK_CAPTURE(SaxParse, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
+BENCHMARK_CAPTURE(SaxParse, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(SaxParse, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+//////////////////////////////////////////////////////////////////////////////
+// work with values: copy, destroy, compare, iterate
+//
+// The parsed test files stand in for a document an application keeps around.
+// Each benchmark times one whole-document operation; setup and cleanup run
+// outside the timed section.
+//
+// A copy is always destroyed again, and how a document is freed shapes the
+// heap the next copy allocates from: a destructor that frees quickly can leave
+// work to the allocator's next calls. Copy, CopyAssign and CopyRing therefore
+// time the copy together with the destruction of a copy; CopyOnly and
+// DestroyOnly time one half each and are meant for telling the halves apart,
+// not for comparing versions.
+//////////////////////////////////////////////////////////////////////////////
+
+/// copy a document and destroy the copy again, as a temporary copy is used
+static void Copy(benchmark::State& state, const char* filename)
+{
+    const json j = load_json(filename);
+
+    for (auto _ : state)
+    {
+        json copy = j;
+        benchmark::DoNotOptimize(copy);
+    }
+}
+BENCHMARK_CAPTURE(Copy, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
+BENCHMARK_CAPTURE(Copy, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(Copy, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+/// copy-assign a document over an earlier copy of it, which is freed in the process
+static void CopyAssign(benchmark::State& state, const char* filename)
+{
+    const json j = load_json(filename);
+    json target = j;
+
+    for (auto _ : state)
+    {
+        target = j;
+        benchmark::DoNotOptimize(target);
+    }
+}
+BENCHMARK_CAPTURE(CopyAssign, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
+BENCHMARK_CAPTURE(CopyAssign, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(CopyAssign, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+/// keep eight copies alive and replace the oldest one, as a cache or an undo
+/// history does, so that the copy is not made from memory just freed by an
+/// identical document
+static void CopyRing(benchmark::State& state, const char* filename)
+{
+    const json j = load_json(filename);
+    std::vector<json> ring(8, j);
+    std::size_t oldest = 0;
+
+    for (auto _ : state)
+    {
+        ring[oldest] = j;
+        benchmark::DoNotOptimize(ring[oldest]);
+        oldest = (oldest + 1) % ring.size();
+    }
+}
+BENCHMARK_CAPTURE(CopyRing, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
+BENCHMARK_CAPTURE(CopyRing, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(CopyRing, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+/// only the copy; the copy is destroyed with the timer paused (diagnostic)
+static void CopyOnly(benchmark::State& state, const char* filename)
+{
+    const json j = load_json(filename);
+
+    for (auto _ : state)
+    {
+        auto* copy = new json(j);
+
+        state.PauseTiming();
+        delete copy;
+        state.ResumeTiming();
+    }
+}
+BENCHMARK_CAPTURE(CopyOnly, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
+BENCHMARK_CAPTURE(CopyOnly, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(CopyOnly, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+/// only the destruction; the copy is made with the timer paused (diagnostic)
+static void DestroyOnly(benchmark::State& state, const char* filename)
+{
+    const json j = load_json(filename);
+
+    for (auto _ : state)
+    {
+        state.PauseTiming();
+        auto* copy = new json(j);
+        state.ResumeTiming();
+
+        delete copy;
+    }
+}
+BENCHMARK_CAPTURE(DestroyOnly, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
+BENCHMARK_CAPTURE(DestroyOnly, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(DestroyOnly, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+static void Equal(benchmark::State& state, const char* filename)
+{
+    // two separate values, so that the comparison cannot stop at identical addresses
+    const json j = load_json(filename);
+    const json copy = j;
+
+    for (auto _ : state)
+    {
+        bool result = (j == copy);
+        benchmark::DoNotOptimize(result);
+    }
+}
+BENCHMARK_CAPTURE(Equal, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
+BENCHMARK_CAPTURE(Equal, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(Equal, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+/// visit every value with range-based for loops, as client code walks a document
+static std::size_t count_values(const json& j)
+{
+    std::size_t result = 1;
+    if (j.is_structured())
+    {
+        for (const auto& element : j)
+        {
+            result += count_values(element);
+        }
+    }
+    return result;
+}
+
+static void Iterate(benchmark::State& state, const char* filename)
+{
+    const json j = load_json(filename);
+
+    for (auto _ : state)
+    {
+        std::size_t result = count_values(j);
+        benchmark::DoNotOptimize(result);
+    }
+
+    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(count_values(j)));
+}
+BENCHMARK_CAPTURE(Iterate, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
+BENCHMARK_CAPTURE(Iterate, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(Iterate, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+//////////////////////////////////////////////////////////////////////////////
+// flatten and unflatten
+//////////////////////////////////////////////////////////////////////////////
+
+static void Flatten(benchmark::State& state, const char* filename)
+{
+    const json j = load_json(filename);
+
+    for (auto _ : state)
+    {
+        json flat = j.flatten();
+        benchmark::DoNotOptimize(flat);
+    }
+}
+BENCHMARK_CAPTURE(Flatten, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
+BENCHMARK_CAPTURE(Flatten, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(Flatten, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+// ordered_json objects look keys up linearly, which flatten() used to do for
+// every value; canada (330,000 values in one flat object) is left out, as it
+// would take minutes with such versions
+static void FlattenOrdered(benchmark::State& state, const char* filename)
+{
+    const nlohmann::ordered_json j = nlohmann::ordered_json::parse(read_file(filename));
+
+    for (auto _ : state)
+    {
+        nlohmann::ordered_json flat = j.flatten();
+        benchmark::DoNotOptimize(flat);
+    }
+}
+BENCHMARK_CAPTURE(FlattenOrdered, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(FlattenOrdered, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+static void Unflatten(benchmark::State& state, const char* filename)
+{
+    const json flat = load_json(filename).flatten();
+
+    for (auto _ : state)
+    {
+        json j = flat.unflatten();
+        benchmark::DoNotOptimize(j);
+    }
+}
+BENCHMARK_CAPTURE(Unflatten, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
+BENCHMARK_CAPTURE(Unflatten, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(Unflatten, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+//////////////////////////////////////////////////////////////////////////////
+// diff and patch
+//
+// The target is the document with every eighth scalar changed, so the patch
+// has one "replace" operation per changed value and the structure stays the
+// same.
+//////////////////////////////////////////////////////////////////////////////
+
+static void change_every_eighth_scalar(json& j, std::size_t& counter)
+{
+    if (j.is_structured())
+    {
+        for (auto& element : j)
+        {
+            change_every_eighth_scalar(element, counter);
+        }
+        return;
+    }
+
+    if (++counter % 8 != 0)
+    {
+        return;
+    }
+
+    switch (j.type())
+    {
+        case json::value_t::number_integer:
+            j = j.get<json::number_integer_t>() + 1;
+            break;
+        case json::value_t::number_unsigned:
+            j = j.get<json::number_unsigned_t>() + 1;
+            break;
+        case json::value_t::number_float:
+            j = j.get<json::number_float_t>() + 0.5;
+            break;
+        case json::value_t::string:
+            j = j.get<std::string>() + "!";
+            break;
+        case json::value_t::boolean:
+            j = !j.get<bool>();
+            break;
+        case json::value_t::null:
+        case json::value_t::object:
+        case json::value_t::array:
+        case json::value_t::binary:
+        case json::value_t::discarded:
+        default:
+            j = 0;
+            break;
+    }
+}
+
+static json changed_copy(const json& j)
+{
+    json result = j;
+    std::size_t counter = 0;
+    change_every_eighth_scalar(result, counter);
+    return result;
+}
+
+static void Diff(benchmark::State& state, const char* filename)
+{
+    const json source = load_json(filename);
+    const json target = changed_copy(source);
+
+    for (auto _ : state)
+    {
+        json patch = json::diff(source, target);
+        benchmark::DoNotOptimize(patch);
+    }
+
+    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(json::diff(source, target).size()));
+}
+BENCHMARK_CAPTURE(Diff, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
+BENCHMARK_CAPTURE(Diff, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(Diff, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+static void Patch(benchmark::State& state, const char* filename)
+{
+    const json source = load_json(filename);
+    const json patch = json::diff(source, changed_copy(source));
+
+    for (auto _ : state)
+    {
+        json result = source.patch(patch);
+        benchmark::DoNotOptimize(result);
+    }
+
+    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(patch.size()));
+}
+BENCHMARK_CAPTURE(Patch, canada,       TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json");
+BENCHMARK_CAPTURE(Patch, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(Patch, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+//////////////////////////////////////////////////////////////////////////////
+// JSON Pointer
+//
+// The pointers are those of every scalar in the document, i.e., the keys of
+// its flattened form.
+//////////////////////////////////////////////////////////////////////////////
+
+static std::vector<std::string> pointer_strings(const json& j)
+{
+    std::vector<std::string> result;
+    const json flat = j.flatten();
+    result.reserve(flat.size());
+    for (auto it = flat.begin(); it != flat.end(); ++it)
+    {
+        result.push_back(it.key());
+    }
+    return result;
+}
+
+static std::vector<json::json_pointer> pointers(const json& j)
+{
+    const std::vector<std::string> strings = pointer_strings(j);
+    std::vector<json::json_pointer> result;
+    result.reserve(strings.size());
+    for (const auto& s : strings)
+    {
+        result.emplace_back(s);
+    }
+    return result;
+}
+
+static void JsonPointerParse(benchmark::State& state, const char* filename)
+{
+    const std::vector<std::string> strings = pointer_strings(load_json(filename));
+
+    for (auto _ : state)
+    {
+        for (const auto& s : strings)
+        {
+            json::json_pointer ptr(s);
+            benchmark::DoNotOptimize(ptr);
+        }
+    }
+
+    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(strings.size()));
+}
+BENCHMARK_CAPTURE(JsonPointerParse, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(JsonPointerParse, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+static void JsonPointerToString(benchmark::State& state, const char* filename)
+{
+    const std::vector<json::json_pointer> ptrs = pointers(load_json(filename));
+
+    for (auto _ : state)
+    {
+        for (const auto& ptr : ptrs)
+        {
+            std::string s = ptr.to_string();
+            benchmark::DoNotOptimize(s);
+        }
+    }
+
+    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(ptrs.size()));
+}
+BENCHMARK_CAPTURE(JsonPointerToString, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(JsonPointerToString, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+static void JsonPointerAt(benchmark::State& state, const char* filename)
+{
+    const json j = load_json(filename);
+    const std::vector<json::json_pointer> ptrs = pointers(j);
+
+    for (auto _ : state)
+    {
+        for (const auto& ptr : ptrs)
+        {
+            const json& value = j.at(ptr);
+            benchmark::DoNotOptimize(&value);
+        }
+    }
+
+    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(ptrs.size()));
+}
+BENCHMARK_CAPTURE(JsonPointerAt, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(JsonPointerAt, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+static void JsonPointerContains(benchmark::State& state, const char* filename)
+{
+    const json j = load_json(filename);
+    const std::vector<json::json_pointer> ptrs = pointers(j);
+
+    for (auto _ : state)
+    {
+        for (const auto& ptr : ptrs)
+        {
+            bool result = j.contains(ptr);
+            benchmark::DoNotOptimize(result);
+        }
+    }
+
+    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(ptrs.size()));
+}
+BENCHMARK_CAPTURE(JsonPointerContains, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+BENCHMARK_CAPTURE(JsonPointerContains, twitter,      TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json");
+
+//////////////////////////////////////////////////////////////////////////////
+// conversions from and to C++ containers
+//////////////////////////////////////////////////////////////////////////////
+
+static void GetVectorInt(benchmark::State& state, const char* filename)
+{
+    const json j = load_json(filename);
+
+    for (auto _ : state)
+    {
+        auto v = j.get<std::vector<std::int64_t>>();
+        benchmark::DoNotOptimize(v);
+    }
+
+    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(j.size()));
+}
+BENCHMARK_CAPTURE(GetVectorInt, signed_ints, TEST_DATA_DIRECTORY "/regression/signed_ints.json");
+
+static void GetVectorDouble(benchmark::State& state, const char* filename)
+{
+    const json j = load_json(filename);
+
+    for (auto _ : state)
+    {
+        auto v = j.get<std::vector<double>>();
+        benchmark::DoNotOptimize(v);
+    }
+
+    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(j.size()));
+}
+BENCHMARK_CAPTURE(GetVectorDouble, floats, TEST_DATA_DIRECTORY "/regression/floats.json");
+
+// a large flat object: the flattened document, one member per scalar
+static void GetMap(benchmark::State& state, const char* filename)
+{
+    const json j = load_json(filename).flatten();
+
+    for (auto _ : state)
+    {
+        auto m = j.get<std::map<std::string, json>>();
+        benchmark::DoNotOptimize(m);
+    }
+
+    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(j.size()));
+}
+BENCHMARK_CAPTURE(GetMap, citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json");
+
+/// 100,000 strings, each too long for the small string optimization
+static std::vector<std::string> make_strings()
+{
+    std::vector<std::string> result;
+    result.reserve(100000);
+    for (std::size_t i = 0; i < 100000; ++i)
+    {
+        result.push_back("a string that does not fit in place: " + std::to_string(i));
+    }
+    return result;
+}
+
+static void ToJsonStrings(benchmark::State& state, const bool move)
+{
+    const std::vector<std::string> strings = make_strings();
+
+    for (auto _ : state)
+    {
+        state.PauseTiming();
+        std::vector<std::string> input = strings;
+        state.ResumeTiming();
+
+        // destroyed inside the timed section, like the copies above
+        auto* j = move ? new json(std::move(input)) : new json(input);
+        delete j;
+    }
+
+    state.SetItemsProcessed(state.iterations() * static_cast<std::int64_t>(strings.size()));
+}
+BENCHMARK_CAPTURE(ToJsonStrings, copy, false);
+BENCHMARK_CAPTURE(ToJsonStrings, move, true);
+
 // conversion of a JSON array into standard containers
 template<typename Container>
 static void GetArray(benchmark::State& state)

tests/src/bjdata_round_trip.hpp

@@ -0,0 +1,103 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  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
+
+#pragma once
+
+#include <cstdint> // uint8_t
+#include <vector> // vector
+
+#include "doctest_compatibility.h"
+
+#include <nlohmann/json.hpp>
+
+#include "round_trip_corpus.hpp"
+
+// The BJData round-trip invariants, split by the BJData version that turns a
+// corpus value into j1 (unit-bjdata_round_trip_draft2.cpp and
+// unit-bjdata_round_trip_draft3.cpp). They were part of unit-bjdata.cpp, but
+// took 80 % of its time; as separate tests, both halves run in parallel and
+// stay below the ctest timeout under Valgrind.
+namespace utils
+{
+
+// This checks what the parse_bjdata_fuzzer driver checks (see
+// tests/src/fuzzer-parse_bjdata.cpp), so that a regression shows up in CI
+// rather than as an OSS-Fuzz report: every value from_bjdata() returns
+// (j1) can be serialized with any combination of options, the result can
+// be parsed back (j2), and serializing j2 again with the same options
+// yields a value-equal result.
+//
+// Beyond the driver, this also checks that j2 equals j1 and that
+// serializing j2 reproduces the exact bytes, both except for values that
+// contain a binary value: a binary value is only written as a binary
+// value with Draft 3's optimized binary array, and otherwise read back as
+// an array of integers, for which the writer may choose different (but
+// equally valid) type markers when it is serialized again (see #5494).
+//
+// Values are compared with dump() rather than operator==, because a NaN
+// never compares equal to itself.
+//
+// Only the corpus values written with @a initial_version become j1; each j1
+// is then serialized with every combination of options, both versions
+// included.
+inline void check_bjdata_round_trip(const nlohmann::json::bjdata_version_t initial_version)
+{
+    using nlohmann::json;
+
+    struct options
+    {
+        bool use_size;
+        bool use_type;
+        json::bjdata_version_t version;
+    };
+    const std::vector<options> all_options =
+    {
+        {false, false, json::bjdata_version_t::draft2},
+        {true, false, json::bjdata_version_t::draft2},
+        {true, true, json::bjdata_version_t::draft2},
+        {false, false, json::bjdata_version_t::draft3},
+        {true, false, json::bjdata_version_t::draft3},
+        {true, true, json::bjdata_version_t::draft3},
+    };
+
+    for (const auto& j0 : utils::round_trip_corpus::values())
+    {
+        // turn the corpus value into a value as from_bjdata() returns it
+        for (const auto& initial : all_options)
+        {
+            if (initial.version != initial_version)
+            {
+                continue;
+            }
+
+            const json j1 = json::from_bjdata(json::to_bjdata(j0, initial.use_size, initial.use_type, initial.version));
+            const bool has_binary = utils::round_trip_corpus::contains_binary(j1);
+
+            for (const auto& o : all_options)
+            {
+                INFO("j1 = " << j1.dump() << ", use_size = " << o.use_size << ", use_type = " << o.use_type
+                     << ", draft3 = " << (o.version == json::bjdata_version_t::draft3));
+
+                const std::vector<std::uint8_t> vec = json::to_bjdata(j1, o.use_size, o.use_type, o.version);
+                json j2;
+                // anything the library writes must be parsable by the library
+                REQUIRE_NOTHROW(j2 = json::from_bjdata(vec));
+                const std::vector<std::uint8_t> vec2 = json::to_bjdata(j2, o.use_size, o.use_type, o.version);
+                CHECK(json::from_bjdata(vec2).dump() == j2.dump());
+
+                if (!has_binary)
+                {
+                    CHECK(j2.dump() == j1.dump());
+                    CHECK(vec2 == vec);
+                }
+            }
+        }
+    }
+}
+
+} // namespace utils

tests/src/unit-bjdata.cpp

@@ -28,7 +28,6 @@ using ordered_json = nlohmann::ordered_json;
 #include <fstream>
 #include <set>
 #include "make_test_data_available.hpp"
-#include "round_trip_corpus.hpp"
 #include "test_utils.hpp"
 #include "sax_countdown.hpp"
 using utils::SaxCountdown;
@@ -4441,70 +4440,6 @@ TEST_CASE("BJData use_type requires use_size")
     }
 }
 
-TEST_CASE("BJData round-trip invariants")
-{
-    // This checks what the parse_bjdata_fuzzer driver checks (see
-    // tests/src/fuzzer-parse_bjdata.cpp), so that a regression shows up in CI
-    // rather than as an OSS-Fuzz report: every value from_bjdata() returns
-    // (j1) can be serialized with any combination of options, the result can
-    // be parsed back (j2), and serializing j2 again with the same options
-    // yields a value-equal result.
-    //
-    // Beyond the driver, this also checks that j2 equals j1 and that
-    // serializing j2 reproduces the exact bytes, both except for values that
-    // contain a binary value: a binary value is only written as a binary
-    // value with Draft 3's optimized binary array, and otherwise read back as
-    // an array of integers, for which the writer may choose different (but
-    // equally valid) type markers when it is serialized again (see #5494).
-    //
-    // Values are compared with dump() rather than operator==, because a NaN
-    // never compares equal to itself.
-    struct options
-    {
-        bool use_size;
-        bool use_type;
-        json::bjdata_version_t version;
-    };
-    const std::vector<options> all_options =
-    {
-        {false, false, json::bjdata_version_t::draft2},
-        {true, false, json::bjdata_version_t::draft2},
-        {true, true, json::bjdata_version_t::draft2},
-        {false, false, json::bjdata_version_t::draft3},
-        {true, false, json::bjdata_version_t::draft3},
-        {true, true, json::bjdata_version_t::draft3},
-    };
-
-    for (const auto& j0 : utils::round_trip_corpus::values())
-    {
-        // turn the corpus value into a value as from_bjdata() returns it
-        for (const auto& initial : all_options)
-        {
-            const json j1 = json::from_bjdata(json::to_bjdata(j0, initial.use_size, initial.use_type, initial.version));
-            const bool has_binary = utils::round_trip_corpus::contains_binary(j1);
-
-            for (const auto& o : all_options)
-            {
-                INFO("j1 = " << j1.dump() << ", use_size = " << o.use_size << ", use_type = " << o.use_type
-                     << ", draft3 = " << (o.version == json::bjdata_version_t::draft3));
-
-                const std::vector<std::uint8_t> vec = json::to_bjdata(j1, o.use_size, o.use_type, o.version);
-                json j2;
-                // anything the library writes must be parsable by the library
-                REQUIRE_NOTHROW(j2 = json::from_bjdata(vec));
-                const std::vector<std::uint8_t> vec2 = json::to_bjdata(j2, o.use_size, o.use_type, o.version);
-                CHECK(json::from_bjdata(vec2).dump() == j2.dump());
-
-                if (!has_binary)
-                {
-                    CHECK(j2.dump() == j1.dump());
-                    CHECK(vec2 == vec);
-                }
-            }
-        }
-    }
-}
-
 TEST_CASE("BJData round trip of a binary value is value-stable, not byte-stable")
 {
     // OSS-Fuzz issue 474480402: a Draft 3 optimized binary array is read as a

tests/src/unit-bjdata_round_trip_draft2.cpp

@@ -0,0 +1,22 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  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 "bjdata_round_trip.hpp"
+
+// split from unit-bjdata.cpp, see bjdata_round_trip.hpp; the other half is in
+// unit-bjdata_round_trip_draft3.cpp
+
+TEST_CASE("BJData round-trip invariants (j1 written with Draft 2)")
+{
+    utils::check_bjdata_round_trip(json::bjdata_version_t::draft2);
+}

tests/src/unit-bjdata_round_trip_draft3.cpp

@@ -0,0 +1,22 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  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 "bjdata_round_trip.hpp"
+
+// split from unit-bjdata.cpp, see bjdata_round_trip.hpp; the other half is in
+// unit-bjdata_round_trip_draft2.cpp
+
+TEST_CASE("BJData round-trip invariants (j1 written with Draft 3)")
+{
+    utils::check_bjdata_round_trip(json::bjdata_version_t::draft3);
+}

tests/src/unit-large_json.cpp

@@ -13,8 +13,6 @@ using nlohmann::json;
 
 #include <algorithm>
 #include <string>
-#include <utility>
-#include <vector>
 
 TEST_CASE("tests on very large JSONs")
 {
@@ -55,24 +53,6 @@ const json* innermost_value(const json& j, std::size_t& depth)
     return current;
 }
 
-// The text of a value nested depth levels deep around the number 0. Level i is
-// an array if pattern[i % pattern.size()] is '[', and otherwise an object with
-// the single member "a", which every object type enumerates in the same order.
-std::string nested_text(std::size_t depth, const std::string& pattern)
-{
-    std::string text;
-    std::string closing;
-    for (std::size_t i = 0; i < depth; ++i)
-    {
-        const bool array = pattern[i % pattern.size()] == '[';
-        text += array ? "[" : "{\"a\":";
-        closing += array ? ']' : '}';
-    }
-    text += '0';
-    text.append(closing.rbegin(), closing.rend());
-    return text;
-}
-
 } // namespace
 
 TEST_CASE("tests on deeply nested JSONs")
@@ -244,385 +224,4 @@ TEST_CASE("tests on deeply nested JSONs")
             CHECK(*innermost_value(j, unused) == 0);
         }
     }
-
-    SECTION("issue #5650 - stack overflow converting between specializations")
-    {
-        const std::vector<std::string> patterns = {"[", "{", "[{"};
-
-        SECTION("json to ordered_json")
-        {
-            for (const auto& pattern : patterns)
-            {
-                CAPTURE(pattern)
-                const std::string text = nested_text(depth, pattern);
-                const json j = json::parse(text);
-
-                const nlohmann::ordered_json converted = j;
-                CHECK(converted.dump() == text);
-            }
-        }
-
-        SECTION("ordered_json to json")
-        {
-            for (const auto& pattern : patterns)
-            {
-                CAPTURE(pattern)
-                const std::string text = nested_text(depth, pattern);
-                const nlohmann::ordered_json o = nlohmann::ordered_json::parse(text);
-
-                const json converted = o;
-                CHECK(converted.dump() == text);
-            }
-        }
-
-        SECTION("get<ordered_json>()")
-        {
-            for (const auto& pattern : patterns)
-            {
-                CAPTURE(pattern)
-                const std::string text = nested_text(depth, pattern);
-                const json j = json::parse(text);
-
-                CHECK(j.get<nlohmann::ordered_json>().dump() == text);
-            }
-        }
-
-        SECTION("depths around the bound of the recursive descent")
-        {
-            for (std::size_t d = 1; d <= 300; ++d)
-            {
-                CAPTURE(d)
-                for (const auto& pattern : patterns)
-                {
-                    CAPTURE(pattern)
-                    const std::string text = nested_text(d, pattern);
-                    const json j = json::parse(text);
-
-                    const nlohmann::ordered_json converted = j;
-                    CHECK(converted.dump() == text);
-                    const json back = converted;
-                    CHECK(back.dump() == text);
-                }
-            }
-        }
-
-        SECTION("values below the bound are converted as values above it")
-        {
-            // Bury a value below the bound, where it is converted without the
-            // call stack, and compare it with the same value converted on its
-            // own by the containers' range constructors. Its objects have
-            // members that the two object types enumerate in different orders.
-            const auto bury = [](nlohmann::ordered_json value)
-            {
-                for (std::size_t i = 0; i < 200; ++i)
-                {
-                    value = nlohmann::ordered_json::array({std::move(value)});
-                }
-                return value;
-            };
-            const auto dig = [](const json & value)
-            {
-                const json* current = &value;
-                for (std::size_t i = 0; i < 200; ++i)
-                {
-                    current = &current->at(0);
-                }
-                return current;
-            };
-
-            nlohmann::ordered_json value = nlohmann::ordered_json::object();
-            value["z"] = {1, -2, 3U, 4.5, true, nullptr, "six", nlohmann::ordered_json::binary({7, 8}, 9),
-                          nlohmann::ordered_json::binary({10}), nlohmann::ordered_json::array(), nlohmann::ordered_json::object()
-                         };
-            value["y"] = {{"x", {{"w", 1}, {"v", 2}}}, {"u", {3, {{"t", 4}, {"s", 5}}}}};
-            value["r"] = nlohmann::ordered_json::array({nlohmann::ordered_json(nlohmann::ordered_json::value_t::discarded)});
-
-            const json converted_above = value;
-            const json buried = bury(value);
-            const json& converted_below = *dig(buried);
-
-            CHECK(converted_below.dump() == converted_above.dump());
-            CHECK(converted_below.at("z").at(7).get_binary().subtype() == 9);
-            CHECK_FALSE(converted_below.at("z").at(8).get_binary().has_subtype());
-            CHECK(converted_below.at("r").at(0).is_discarded());
-
-            // a discarded value is never equal to anything, so compare the rest
-            value.erase("r");
-            const json without_discarded_above = value;
-            const json without_discarded_buried = bury(value);
-            CHECK(*dig(without_discarded_buried) == without_discarded_above);
-        }
-    }
 }
-
-namespace
-{
-json nested_array(const std::size_t depth, json leaf)
-{
-    json j = std::move(leaf);
-    for (std::size_t i = 0; i < depth; ++i)
-    {
-        json a = json::array();
-        a.push_back(std::move(j));
-        j = std::move(a);
-    }
-    return j;
-}
-
-json nested_object(const std::size_t depth, json leaf)
-{
-    json j = std::move(leaf);
-    for (std::size_t i = 0; i < depth; ++i)
-    {
-        json o = json::object();
-        o["k"] = std::move(j);
-        j = std::move(o);
-    }
-    return j;
-}
-} // namespace
-
-TEST_CASE("issue #5392 - binary writers on deeply nested values")
-{
-    // 200 is past the point where the writers stop recursing, and still
-    // shallow enough that from_* and operator== (which still recurse) are fine.
-    const json deep_array = nested_array(200, json(0));
-    const json deep_object = nested_object(200, json("x"));
-    const json empty_array = nested_array(200, json::array());
-    const json empty_object = nested_object(200, json::object());
-    const json mixed = nested_object(80, nested_array(80, json(true)));
-
-    SECTION("roundtrip past the recursion bound")
-    {
-        CHECK(json::from_cbor(json::to_cbor(deep_array)) == deep_array);
-        CHECK(json::from_msgpack(json::to_msgpack(deep_array)) == deep_array);
-        CHECK(json::from_ubjson(json::to_ubjson(deep_array)) == deep_array);
-        CHECK(json::from_ubjson(json::to_ubjson(deep_array, true, false)) == deep_array);
-        CHECK(json::from_ubjson(json::to_ubjson(deep_array, true, true)) == deep_array);
-        CHECK(json::from_bjdata(json::to_bjdata(deep_array)) == deep_array);
-        CHECK(json::from_bon8(json::to_bon8(deep_array)) == deep_array);
-
-        CHECK(json::from_cbor(json::to_cbor(deep_object)) == deep_object);
-        CHECK(json::from_msgpack(json::to_msgpack(deep_object)) == deep_object);
-        CHECK(json::from_ubjson(json::to_ubjson(deep_object)) == deep_object);
-        CHECK(json::from_ubjson(json::to_ubjson(deep_object, true, true)) == deep_object);
-        CHECK(json::from_bjdata(json::to_bjdata(deep_object)) == deep_object);
-        CHECK(json::from_bon8(json::to_bon8(deep_object)) == deep_object);
-
-        CHECK(json::from_cbor(json::to_cbor(empty_array)) == empty_array);
-        CHECK(json::from_msgpack(json::to_msgpack(empty_array)) == empty_array);
-        CHECK(json::from_ubjson(json::to_ubjson(empty_array)) == empty_array);
-        CHECK(json::from_ubjson(json::to_ubjson(empty_array, true, true)) == empty_array);
-        CHECK(json::from_bon8(json::to_bon8(empty_array)) == empty_array);
-
-        CHECK(json::from_cbor(json::to_cbor(empty_object)) == empty_object);
-        CHECK(json::from_msgpack(json::to_msgpack(empty_object)) == empty_object);
-        CHECK(json::from_ubjson(json::to_ubjson(empty_object)) == empty_object);
-        CHECK(json::from_bon8(json::to_bon8(empty_object)) == empty_object);
-
-        CHECK(json::from_cbor(json::to_cbor(mixed)) == mixed);
-        CHECK(json::from_msgpack(json::to_msgpack(mixed)) == mixed);
-        CHECK(json::from_ubjson(json::to_ubjson(mixed)) == mixed);
-        CHECK(json::from_bjdata(json::to_bjdata(mixed)) == mixed);
-        CHECK(json::from_bon8(json::to_bon8(mixed)) == mixed);
-    }
-
-    SECTION("the two ways of writing a value meet at the bound")
-    {
-        for (std::size_t depth = 120; depth <= 140; ++depth)
-        {
-            CAPTURE(depth)
-
-            const json array = nested_array(depth, json(7));
-            CHECK(json::from_cbor(json::to_cbor(array)) == array);
-            CHECK(json::from_msgpack(json::to_msgpack(array)) == array);
-            CHECK(json::from_ubjson(json::to_ubjson(array, true, true)) == array);
-            CHECK(json::from_bon8(json::to_bon8(array)) == array);
-
-            const json object = nested_object(depth, json(7));
-            CHECK(json::from_cbor(json::to_cbor(object)) == object);
-            CHECK(json::from_msgpack(json::to_msgpack(object)) == object);
-            CHECK(json::from_bjdata(json::to_bjdata(object)) == object);
-            CHECK(json::from_bon8(json::to_bon8(object)) == object);
-        }
-    }
-
-    SECTION("a BJData ndarray below the bound is still an ndarray")
-    {
-        const json ndarray = json({{"_ArrayType_", "uint8"}, {"_ArraySize_", {2, 3}}, {"_ArrayData_", {1, 2, 3, 4, 5, 6}}});
-        const json invalid = json({{"_ArrayType_", "nope"}, {"_ArraySize_", {1}}, {"_ArrayData_", {1}}});
-
-        const json deep_ndarray = nested_array(140, ndarray);
-        const json deep_invalid = nested_array(140, invalid);
-
-        CHECK(json::from_bjdata(json::to_bjdata(deep_ndarray)) == deep_ndarray);
-        CHECK(json::from_bjdata(json::to_bjdata(deep_invalid)) == deep_invalid);
-        CHECK(json::from_bjdata(json::to_bjdata(ndarray)) == ndarray);
-    }
-
-    SECTION("byte-exact across the switch-over")
-    {
-        // nested one-element arrays around the recursion bound: the exact
-        // bytes a writer produces do not depend on whether it stayed on the
-        // call stack or moved to the heap one partway through
-        for (const std::size_t depth :
-                {
-                    nlohmann::detail::recursion_depth_limit() - 1, nlohmann::detail::recursion_depth_limit(),
-                    nlohmann::detail::recursion_depth_limit() + 1, nlohmann::detail::recursion_depth_limit() + 2
-                })
-        {
-            CAPTURE(depth)
-            const json array = nested_array(depth, json(0));
-
-            std::vector<std::uint8_t> expected_cbor(depth, 0x81);
-            expected_cbor.push_back(0x00);
-            CHECK(json::to_cbor(array) == expected_cbor);
-
-            std::vector<std::uint8_t> expected_msgpack(depth, 0x91);
-            expected_msgpack.push_back(0x00);
-            CHECK(json::to_msgpack(array) == expected_msgpack);
-
-            std::string expected_ubjson(depth, '[');
-            expected_ubjson += "i";
-            expected_ubjson += '\0';
-            expected_ubjson.append(depth, ']');
-            const auto packed_ubjson = json::to_ubjson(array);
-            CHECK(std::string(packed_ubjson.begin(), packed_ubjson.end()) == expected_ubjson);
-
-            std::vector<std::uint8_t> expected_bon8(depth, 0x81);
-            expected_bon8.push_back(0x90);
-            CHECK(json::to_bon8(array) == expected_bon8);
-        }
-    }
-
-    SECTION("a deep object, and a BJData ndarray, past the recursion bound")
-    {
-        const std::size_t depth = nlohmann::detail::recursion_depth_limit() + 50;
-
-        const json object = nested_object(depth, json(42));
-        CHECK(json::from_cbor(json::to_cbor(object)) == object);
-        CHECK(json::from_msgpack(json::to_msgpack(object)) == object);
-        CHECK(json::from_ubjson(json::to_ubjson(object, true, true)) == object);
-        CHECK(json::from_bjdata(json::to_bjdata(object)) == object);
-        CHECK(json::from_bon8(json::to_bon8(object)) == object);
-
-        const json ndarray = json({{"_ArrayType_", "uint8"}, {"_ArraySize_", {2, 3}}, {"_ArrayData_", {1, 2, 3, 4, 5, 6}}});
-        const json deep_ndarray = nested_array(depth, ndarray);
-        CHECK(json::from_bjdata(json::to_bjdata(deep_ndarray)) == deep_ndarray);
-    }
-
-    SECTION("a discarded value past the recursion bound still throws type_error.321")
-    {
-        const std::size_t depth = nlohmann::detail::recursion_depth_limit() + 50;
-        const json discarded_leaf(json::value_t::discarded);
-        const json deep_discarded = nested_array(depth, discarded_leaf);
-
-        // with diagnostics, the message names the path to the discarded leaf
-#if JSON_DIAGNOSTICS
-        std::string path;
-        for (std::size_t i = 0; i < depth; ++i)
-        {
-            path += "/0";
-        }
-        const std::string prefix = "[json.exception.type_error.321] (" + path + ") ";
-#else
-        const std::string prefix = "[json.exception.type_error.321] ";
-#endif
-
-        CHECK_THROWS_WITH_AS(json::to_cbor(deep_discarded), (prefix + "cannot serialize discarded value to CBOR").c_str(), json::type_error);
-        CHECK_THROWS_WITH_AS(json::to_msgpack(deep_discarded), (prefix + "cannot serialize discarded value to MessagePack").c_str(), json::type_error);
-        CHECK_THROWS_WITH_AS(json::to_ubjson(deep_discarded), (prefix + "cannot serialize discarded value to UBJSON").c_str(), json::type_error);
-        CHECK_THROWS_WITH_AS(json::to_bjdata(deep_discarded), (prefix + "cannot serialize discarded value to BJData").c_str(), json::type_error);
-    }
-
-    SECTION("BON8 past the recursion bound: discarded values and errors")
-    {
-        const std::size_t depth = nlohmann::detail::recursion_depth_limit() + 50;
-
-        // BON8 rejects a discarded value (type_error.321), deep or not
-        const json deep_discarded = nested_array(depth, json(json::value_t::discarded));
-        CHECK_THROWS_AS(json::to_bon8(deep_discarded), json::type_error);
-
-        // errors are thrown from below the bound as from above it
-        const json deep_invalid_string = nested_array(depth, json(std::string("\x80")));
-        CHECK_THROWS_AS(json::to_bon8(deep_invalid_string), json::type_error);
-
-        json deep_invalid_key = json::object();
-        deep_invalid_key[std::string("\x80")] = 1;
-        deep_invalid_key = nested_object(depth, deep_invalid_key);
-        CHECK_THROWS_AS(json::to_bon8(deep_invalid_key), json::type_error);
-
-        const json deep_too_large = nested_array(depth, json(9223372036854775808u));
-        CHECK_THROWS_AS(json::to_bon8(deep_too_large), json::out_of_range);
-    }
-
-    SECTION("does not overflow the C++ stack")
-    {
-        const std::size_t depth = 100000;
-        const json j = json::parse(std::string(depth, '[') + "0" + std::string(depth, ']'));
-
-        std::vector<std::uint8_t> packed;
-        CHECK_NOTHROW(packed = json::to_cbor(j));
-        CHECK(json::from_cbor(packed) == j);
-
-        CHECK_NOTHROW(packed = json::to_msgpack(j));
-        CHECK(json::from_msgpack(packed) == j);
-
-        CHECK_NOTHROW(packed = json::to_ubjson(j));
-        CHECK(json::from_ubjson(packed) == j);
-
-        CHECK_NOTHROW(packed = json::to_ubjson(j, true, false));
-        CHECK(json::from_ubjson(packed) == j);
-
-        CHECK_NOTHROW(packed = json::to_bjdata(j));
-        CHECK(json::from_bjdata(packed) == j);
-
-        CHECK_NOTHROW(packed = json::to_bon8(j));
-        CHECK(json::from_bon8(packed) == j);
-    }
-
-    SECTION("BON8 containers with more than four elements past the recursion bound")
-    {
-        // such containers are closed with 0xFE, which the iterative writer
-        // must emit when it leaves them; strings next to each other must
-        // still be separated with 0xFF
-        const std::size_t depth = nlohmann::detail::recursion_depth_limit() + 50;
-        json wide_array = json::array({1, "a", "b", json::array(), 5});
-        json wide_object = json({{"k1", "v"}, {"k2", 2}, {"k3", ""}, {"k4", json::object()}, {"k5", nullptr}});
-        for (std::size_t i = 0; i < depth; ++i)
-        {
-            wide_array = json::array({"s", wide_array, "t", wide_object, true});
-            wide_object = json({{"a", wide_object}, {"b", "x"}, {"c", "y"}, {"d", wide_array.size()}, {"e", "z"}});
-        }
-
-        CHECK(json::from_bon8(json::to_bon8(wide_array)) == wide_array);
-        CHECK(json::from_bon8(json::to_bon8(wide_object)) == wide_object);
-    }
-
-    SECTION("regression test for https://issues.oss-fuzz.com/issues/566583014")
-    {
-        // 200000 nested one-element CBOR arrays, the innermost holding null;
-        // round-tripping this used to recurse once per level on the way back
-        // out through to_cbor(), deep enough to overflow the stack
-        std::vector<std::uint8_t> v(200000, 0x81);
-        v.push_back(0xf6);
-        const json j = json::from_cbor(v);
-        CHECK(json::to_cbor(j) == v);
-
-        // the MessagePack analogue: fixarray of 1 nesting down to nil
-        std::vector<std::uint8_t> v_msgpack(200000, 0x91);
-        v_msgpack.push_back(0xc0);
-        const json j_msgpack = json::from_msgpack(v_msgpack);
-        CHECK(json::to_msgpack(j_msgpack) == v_msgpack);
-    }
-
-    SECTION("regression test for https://issues.oss-fuzz.com/issues/572238015")
-    {
-        // the BON8 analogue: 200000 nested one-element arrays down to null
-        std::vector<std::uint8_t> v(200000, 0x81);
-        v.push_back(0xFA);
-        const json j = json::from_bon8(v);
-        CHECK(json::to_bon8(j) == v);
-    }
-}
-

tests/src/unit-large_json_binary_writers.cpp

@@ -0,0 +1,294 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  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 <cstddef>
+#include <cstdint>
+#include <string>
+#include <utility>
+#include <vector>
+
+// split from unit-large_json.cpp so that both run in parallel and stay below
+// the ctest timeout under Valgrind
+
+namespace
+{
+json nested_array(const std::size_t depth, json leaf)
+{
+    json j = std::move(leaf);
+    for (std::size_t i = 0; i < depth; ++i)
+    {
+        json a = json::array();
+        a.push_back(std::move(j));
+        j = std::move(a);
+    }
+    return j;
+}
+
+json nested_object(const std::size_t depth, json leaf)
+{
+    json j = std::move(leaf);
+    for (std::size_t i = 0; i < depth; ++i)
+    {
+        json o = json::object();
+        o["k"] = std::move(j);
+        j = std::move(o);
+    }
+    return j;
+}
+} // namespace
+
+TEST_CASE("issue #5392 - binary writers on deeply nested values")
+{
+    // 200 is past the point where the writers stop recursing, and still
+    // shallow enough that from_* and operator== (which still recurse) are fine.
+    const json deep_array = nested_array(200, json(0));
+    const json deep_object = nested_object(200, json("x"));
+    const json empty_array = nested_array(200, json::array());
+    const json empty_object = nested_object(200, json::object());
+    const json mixed = nested_object(80, nested_array(80, json(true)));
+
+    SECTION("roundtrip past the recursion bound")
+    {
+        CHECK(json::from_cbor(json::to_cbor(deep_array)) == deep_array);
+        CHECK(json::from_msgpack(json::to_msgpack(deep_array)) == deep_array);
+        CHECK(json::from_ubjson(json::to_ubjson(deep_array)) == deep_array);
+        CHECK(json::from_ubjson(json::to_ubjson(deep_array, true, false)) == deep_array);
+        CHECK(json::from_ubjson(json::to_ubjson(deep_array, true, true)) == deep_array);
+        CHECK(json::from_bjdata(json::to_bjdata(deep_array)) == deep_array);
+        CHECK(json::from_bon8(json::to_bon8(deep_array)) == deep_array);
+
+        CHECK(json::from_cbor(json::to_cbor(deep_object)) == deep_object);
+        CHECK(json::from_msgpack(json::to_msgpack(deep_object)) == deep_object);
+        CHECK(json::from_ubjson(json::to_ubjson(deep_object)) == deep_object);
+        CHECK(json::from_ubjson(json::to_ubjson(deep_object, true, true)) == deep_object);
+        CHECK(json::from_bjdata(json::to_bjdata(deep_object)) == deep_object);
+        CHECK(json::from_bon8(json::to_bon8(deep_object)) == deep_object);
+
+        CHECK(json::from_cbor(json::to_cbor(empty_array)) == empty_array);
+        CHECK(json::from_msgpack(json::to_msgpack(empty_array)) == empty_array);
+        CHECK(json::from_ubjson(json::to_ubjson(empty_array)) == empty_array);
+        CHECK(json::from_ubjson(json::to_ubjson(empty_array, true, true)) == empty_array);
+        CHECK(json::from_bon8(json::to_bon8(empty_array)) == empty_array);
+
+        CHECK(json::from_cbor(json::to_cbor(empty_object)) == empty_object);
+        CHECK(json::from_msgpack(json::to_msgpack(empty_object)) == empty_object);
+        CHECK(json::from_ubjson(json::to_ubjson(empty_object)) == empty_object);
+        CHECK(json::from_bon8(json::to_bon8(empty_object)) == empty_object);
+
+        CHECK(json::from_cbor(json::to_cbor(mixed)) == mixed);
+        CHECK(json::from_msgpack(json::to_msgpack(mixed)) == mixed);
+        CHECK(json::from_ubjson(json::to_ubjson(mixed)) == mixed);
+        CHECK(json::from_bjdata(json::to_bjdata(mixed)) == mixed);
+        CHECK(json::from_bon8(json::to_bon8(mixed)) == mixed);
+    }
+
+    SECTION("the two ways of writing a value meet at the bound")
+    {
+        for (std::size_t depth = 120; depth <= 140; ++depth)
+        {
+            CAPTURE(depth)
+
+            const json array = nested_array(depth, json(7));
+            CHECK(json::from_cbor(json::to_cbor(array)) == array);
+            CHECK(json::from_msgpack(json::to_msgpack(array)) == array);
+            CHECK(json::from_ubjson(json::to_ubjson(array, true, true)) == array);
+            CHECK(json::from_bon8(json::to_bon8(array)) == array);
+
+            const json object = nested_object(depth, json(7));
+            CHECK(json::from_cbor(json::to_cbor(object)) == object);
+            CHECK(json::from_msgpack(json::to_msgpack(object)) == object);
+            CHECK(json::from_bjdata(json::to_bjdata(object)) == object);
+            CHECK(json::from_bon8(json::to_bon8(object)) == object);
+        }
+    }
+
+    SECTION("a BJData ndarray below the bound is still an ndarray")
+    {
+        const json ndarray = json({{"_ArrayType_", "uint8"}, {"_ArraySize_", {2, 3}}, {"_ArrayData_", {1, 2, 3, 4, 5, 6}}});
+        const json invalid = json({{"_ArrayType_", "nope"}, {"_ArraySize_", {1}}, {"_ArrayData_", {1}}});
+
+        const json deep_ndarray = nested_array(140, ndarray);
+        const json deep_invalid = nested_array(140, invalid);
+
+        CHECK(json::from_bjdata(json::to_bjdata(deep_ndarray)) == deep_ndarray);
+        CHECK(json::from_bjdata(json::to_bjdata(deep_invalid)) == deep_invalid);
+        CHECK(json::from_bjdata(json::to_bjdata(ndarray)) == ndarray);
+    }
+
+    SECTION("byte-exact across the switch-over")
+    {
+        // nested one-element arrays around the recursion bound: the exact
+        // bytes a writer produces do not depend on whether it stayed on the
+        // call stack or moved to the heap one partway through
+        for (const std::size_t depth :
+                {
+                    nlohmann::detail::recursion_depth_limit() - 1, nlohmann::detail::recursion_depth_limit(),
+                    nlohmann::detail::recursion_depth_limit() + 1, nlohmann::detail::recursion_depth_limit() + 2
+                })
+        {
+            CAPTURE(depth)
+            const json array = nested_array(depth, json(0));
+
+            std::vector<std::uint8_t> expected_cbor(depth, 0x81);
+            expected_cbor.push_back(0x00);
+            CHECK(json::to_cbor(array) == expected_cbor);
+
+            std::vector<std::uint8_t> expected_msgpack(depth, 0x91);
+            expected_msgpack.push_back(0x00);
+            CHECK(json::to_msgpack(array) == expected_msgpack);
+
+            std::string expected_ubjson(depth, '[');
+            expected_ubjson += "i";
+            expected_ubjson += '\0';
+            expected_ubjson.append(depth, ']');
+            const auto packed_ubjson = json::to_ubjson(array);
+            CHECK(std::string(packed_ubjson.begin(), packed_ubjson.end()) == expected_ubjson);
+
+            std::vector<std::uint8_t> expected_bon8(depth, 0x81);
+            expected_bon8.push_back(0x90);
+            CHECK(json::to_bon8(array) == expected_bon8);
+        }
+    }
+
+    SECTION("a deep object, and a BJData ndarray, past the recursion bound")
+    {
+        const std::size_t depth = nlohmann::detail::recursion_depth_limit() + 50;
+
+        const json object = nested_object(depth, json(42));
+        CHECK(json::from_cbor(json::to_cbor(object)) == object);
+        CHECK(json::from_msgpack(json::to_msgpack(object)) == object);
+        CHECK(json::from_ubjson(json::to_ubjson(object, true, true)) == object);
+        CHECK(json::from_bjdata(json::to_bjdata(object)) == object);
+        CHECK(json::from_bon8(json::to_bon8(object)) == object);
+
+        const json ndarray = json({{"_ArrayType_", "uint8"}, {"_ArraySize_", {2, 3}}, {"_ArrayData_", {1, 2, 3, 4, 5, 6}}});
+        const json deep_ndarray = nested_array(depth, ndarray);
+        CHECK(json::from_bjdata(json::to_bjdata(deep_ndarray)) == deep_ndarray);
+    }
+
+    SECTION("a discarded value past the recursion bound still throws type_error.321")
+    {
+        const std::size_t depth = nlohmann::detail::recursion_depth_limit() + 50;
+        const json discarded_leaf(json::value_t::discarded);
+        const json deep_discarded = nested_array(depth, discarded_leaf);
+
+        // with diagnostics, the message names the path to the discarded leaf
+#if JSON_DIAGNOSTICS
+        std::string path;
+        for (std::size_t i = 0; i < depth; ++i)
+        {
+            path += "/0";
+        }
+        const std::string prefix = "[json.exception.type_error.321] (" + path + ") ";
+#else
+        const std::string prefix = "[json.exception.type_error.321] ";
+#endif
+
+        CHECK_THROWS_WITH_AS(json::to_cbor(deep_discarded), (prefix + "cannot serialize discarded value to CBOR").c_str(), json::type_error);
+        CHECK_THROWS_WITH_AS(json::to_msgpack(deep_discarded), (prefix + "cannot serialize discarded value to MessagePack").c_str(), json::type_error);
+        CHECK_THROWS_WITH_AS(json::to_ubjson(deep_discarded), (prefix + "cannot serialize discarded value to UBJSON").c_str(), json::type_error);
+        CHECK_THROWS_WITH_AS(json::to_bjdata(deep_discarded), (prefix + "cannot serialize discarded value to BJData").c_str(), json::type_error);
+    }
+
+    SECTION("BON8 past the recursion bound: discarded values and errors")
+    {
+        const std::size_t depth = nlohmann::detail::recursion_depth_limit() + 50;
+
+        // BON8 rejects a discarded value (type_error.321), deep or not
+        const json deep_discarded = nested_array(depth, json(json::value_t::discarded));
+        CHECK_THROWS_AS(json::to_bon8(deep_discarded), json::type_error);
+
+        // errors are thrown from below the bound as from above it
+        const json deep_invalid_string = nested_array(depth, json(std::string("\x80")));
+        CHECK_THROWS_AS(json::to_bon8(deep_invalid_string), json::type_error);
+
+        json deep_invalid_key = json::object();
+        deep_invalid_key[std::string("\x80")] = 1;
+        deep_invalid_key = nested_object(depth, deep_invalid_key);
+        CHECK_THROWS_AS(json::to_bon8(deep_invalid_key), json::type_error);
+
+        const json deep_too_large = nested_array(depth, json(9223372036854775808u));
+        CHECK_THROWS_AS(json::to_bon8(deep_too_large), json::out_of_range);
+    }
+
+    SECTION("does not overflow the C++ stack")
+    {
+        const std::size_t depth = 100000;
+        const json j = json::parse(std::string(depth, '[') + "0" + std::string(depth, ']'));
+
+        std::vector<std::uint8_t> packed;
+        CHECK_NOTHROW(packed = json::to_cbor(j));
+        CHECK(json::from_cbor(packed) == j);
+
+        CHECK_NOTHROW(packed = json::to_msgpack(j));
+        CHECK(json::from_msgpack(packed) == j);
+
+        CHECK_NOTHROW(packed = json::to_ubjson(j));
+        CHECK(json::from_ubjson(packed) == j);
+
+        CHECK_NOTHROW(packed = json::to_ubjson(j, true, false));
+        CHECK(json::from_ubjson(packed) == j);
+
+        CHECK_NOTHROW(packed = json::to_bjdata(j));
+        CHECK(json::from_bjdata(packed) == j);
+
+        CHECK_NOTHROW(packed = json::to_bon8(j));
+        CHECK(json::from_bon8(packed) == j);
+    }
+
+    SECTION("BON8 containers with more than four elements past the recursion bound")
+    {
+        // such containers are closed with 0xFE, which the iterative writer
+        // must emit when it leaves them; strings next to each other must
+        // still be separated with 0xFF
+        const std::size_t depth = nlohmann::detail::recursion_depth_limit() + 50;
+        json wide_array = json::array({1, "a", "b", json::array(), 5});
+        json wide_object = json({{"k1", "v"}, {"k2", 2}, {"k3", ""}, {"k4", json::object()}, {"k5", nullptr}});
+        for (std::size_t i = 0; i < depth; ++i)
+        {
+            wide_array = json::array({"s", wide_array, "t", wide_object, true});
+            wide_object = json({{"a", wide_object}, {"b", "x"}, {"c", "y"}, {"d", wide_array.size()}, {"e", "z"}});
+        }
+
+        CHECK(json::from_bon8(json::to_bon8(wide_array)) == wide_array);
+        CHECK(json::from_bon8(json::to_bon8(wide_object)) == wide_object);
+    }
+
+    SECTION("regression test for https://issues.oss-fuzz.com/issues/566583014")
+    {
+        // 200000 nested one-element CBOR arrays, the innermost holding null;
+        // round-tripping this used to recurse once per level on the way back
+        // out through to_cbor(), deep enough to overflow the stack
+        std::vector<std::uint8_t> v(200000, 0x81);
+        v.push_back(0xf6);
+        const json j = json::from_cbor(v);
+        CHECK(json::to_cbor(j) == v);
+
+        // the MessagePack analogue: fixarray of 1 nesting down to nil
+        std::vector<std::uint8_t> v_msgpack(200000, 0x91);
+        v_msgpack.push_back(0xc0);
+        const json j_msgpack = json::from_msgpack(v_msgpack);
+        CHECK(json::to_msgpack(j_msgpack) == v_msgpack);
+    }
+
+    SECTION("regression test for https://issues.oss-fuzz.com/issues/572238015")
+    {
+        // the BON8 analogue: 200000 nested one-element arrays down to null
+        std::vector<std::uint8_t> v(200000, 0x81);
+        v.push_back(0xFA);
+        const json j = json::from_bon8(v);
+        CHECK(json::to_bon8(j) == v);
+    }
+}
+

tests/src/unit-large_json_conversions.cpp

@@ -0,0 +1,156 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  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 <cstddef>
+#include <string>
+#include <utility>
+#include <vector>
+
+// split from unit-large_json.cpp so that both run in parallel and stay below
+// the ctest timeout under Valgrind
+
+namespace
+{
+
+// The text of a value nested depth levels deep around the number 0. Level i is
+// an array if pattern[i % pattern.size()] is '[', and otherwise an object with
+// the single member "a", which every object type enumerates in the same order.
+std::string nested_text(std::size_t depth, const std::string& pattern)
+{
+    std::string text;
+    std::string closing;
+    for (std::size_t i = 0; i < depth; ++i)
+    {
+        const bool array = pattern[i % pattern.size()] == '[';
+        text += array ? "[" : "{\"a\":";
+        closing += array ? ']' : '}';
+    }
+    text += '0';
+    text.append(closing.rbegin(), closing.rend());
+    return text;
+}
+
+} // namespace
+
+TEST_CASE("issue #5650 - stack overflow converting between specializations")
+{
+    // deep enough to exhaust the call stack, but small enough to stay cheap:
+    // parsing is iterative, so building the values below costs little
+    const std::size_t depth = 100000;
+
+    const std::vector<std::string> patterns = {"[", "{", "[{"};
+
+    SECTION("json to ordered_json")
+    {
+        for (const auto& pattern : patterns)
+        {
+            CAPTURE(pattern)
+            const std::string text = nested_text(depth, pattern);
+            const json j = json::parse(text);
+
+            const nlohmann::ordered_json converted = j;
+            CHECK(converted.dump() == text);
+        }
+    }
+
+    SECTION("ordered_json to json")
+    {
+        for (const auto& pattern : patterns)
+        {
+            CAPTURE(pattern)
+            const std::string text = nested_text(depth, pattern);
+            const nlohmann::ordered_json o = nlohmann::ordered_json::parse(text);
+
+            const json converted = o;
+            CHECK(converted.dump() == text);
+        }
+    }
+
+    SECTION("get<ordered_json>()")
+    {
+        for (const auto& pattern : patterns)
+        {
+            CAPTURE(pattern)
+            const std::string text = nested_text(depth, pattern);
+            const json j = json::parse(text);
+
+            CHECK(j.get<nlohmann::ordered_json>().dump() == text);
+        }
+    }
+
+    SECTION("depths around the bound of the recursive descent")
+    {
+        for (std::size_t d = 1; d <= 300; ++d)
+        {
+            CAPTURE(d)
+            for (const auto& pattern : patterns)
+            {
+                CAPTURE(pattern)
+                const std::string text = nested_text(d, pattern);
+                const json j = json::parse(text);
+
+                const nlohmann::ordered_json converted = j;
+                CHECK(converted.dump() == text);
+                const json back = converted;
+                CHECK(back.dump() == text);
+            }
+        }
+    }
+
+    SECTION("values below the bound are converted as values above it")
+    {
+        // Bury a value below the bound, where it is converted without the
+        // call stack, and compare it with the same value converted on its
+        // own by the containers' range constructors. Its objects have
+        // members that the two object types enumerate in different orders.
+        const auto bury = [](nlohmann::ordered_json value)
+        {
+            for (std::size_t i = 0; i < 200; ++i)
+            {
+                value = nlohmann::ordered_json::array({std::move(value)});
+            }
+            return value;
+        };
+        const auto dig = [](const json & value)
+        {
+            const json* current = &value;
+            for (std::size_t i = 0; i < 200; ++i)
+            {
+                current = &current->at(0);
+            }
+            return current;
+        };
+
+        nlohmann::ordered_json value = nlohmann::ordered_json::object();
+        value["z"] = {1, -2, 3U, 4.5, true, nullptr, "six", nlohmann::ordered_json::binary({7, 8}, 9),
+                      nlohmann::ordered_json::binary({10}), nlohmann::ordered_json::array(), nlohmann::ordered_json::object()
+                     };
+        value["y"] = {{"x", {{"w", 1}, {"v", 2}}}, {"u", {3, {{"t", 4}, {"s", 5}}}}};
+        value["r"] = nlohmann::ordered_json::array({nlohmann::ordered_json(nlohmann::ordered_json::value_t::discarded)});
+
+        const json converted_above = value;
+        const json buried = bury(value);
+        const json& converted_below = *dig(buried);
+
+        CHECK(converted_below.dump() == converted_above.dump());
+        CHECK(converted_below.at("z").at(7).get_binary().subtype() == 9);
+        CHECK_FALSE(converted_below.at("z").at(8).get_binary().has_subtype());
+        CHECK(converted_below.at("r").at(0).is_discarded());
+
+        // a discarded value is never equal to anything, so compare the rest
+        value.erase("r");
+        const json without_discarded_above = value;
+        const json without_discarded_buried = bury(value);
+        CHECK(*dig(without_discarded_buried) == without_discarded_above);
+    }
+}