Add benchmarks for the binary readers

The benchmark suite covered parsing JSON text, dumping, and serializing to
CBOR, but only one binary read: FromMsgpack. Nothing measured from_cbor,
from_ubjson, from_bjdata or from_bson, so a change to binary_reader.hpp had
no baseline to be compared against.

Add read benchmarks for every format, in the two shapes that matter: from a
contiguous buffer, which is what most callers pass, and from a FILE*, which
is what FromMsgpack already measures and which compiles to different code.
FromMsgpack itself is left untouched so its numbers stay comparable across
releases. The input is derived at setup time by serializing a parsed test
file, because the test data repository ships JSON only.

The test files are wide and shallow, but the readers' cost is per container,
so add three value shapes they do not cover -- deeply nested containers, many
sibling containers, and one flat array of numbers -- plus an indefinite-length
CBOR string, a form the writer never emits and which therefore has to be
assembled by hand. UBJSON and BJData are also captured in their size- and
type-annotated form, which the readers handle in a separate code path.

BSON requires an object at the top level, so it cannot reuse the array-rooted
test files; it is captured on the object-rooted ones, and the shapes are
wrapped in an object so every format measures the same value. The setup marks
the benchmark as skipped rather than letting the exception escape if that
requirement is ever violated.

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

tests/benchmarks/src/benchmarks.cpp

@@ -214,4 +214,323 @@ 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-ordered_json2.cpp

@@ -1,489 +0,0 @@
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  JSON for Modern C++ (supporting code)
-// |  |  |__   |  |  | | | |  version 3.12.0
-// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
-//
-// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
-// SPDX-FileCopyrightText: 2018 Vitaliy Manushkin <agri@akamo.info>
-// SPDX-License-Identifier: MIT
-
-// This file closes a test-coverage gap described in GitHub issue #5421:
-// nlohmann::ordered_json (and other non-default basic_json specializations,
-// such as the alt_string-based one from unit-alt-string.cpp) were never
-// exercised through the binary formats (CBOR/MessagePack/UBJSON/BSON/BJData)
-// or through flatten()/unflatten()/diff()/patch()/merge_patch().
-
-#include "doctest_compatibility.h"
-
-#include <nlohmann/json.hpp>
-
-#include <cstdint>
-#include <string>
-#include <utility>
-#include <vector>
-
-using nlohmann::json;
-using nlohmann::ordered_json;
-
-/////////////////////////////////////////////////////////////////////////////
-// alt_json: a second, independent copy of the custom-string_t basic_json
-// specialization defined in unit-alt-string.cpp.
-//
-// It is duplicated here (rather than shared via a header) because every
-// unit-*.cpp file in this test suite is compiled into its own standalone
-// executable (see tests/CMakeLists.txt), so there is no ODR concern in
-// having the same class name defined in multiple translation units.
-//
-// Two members had to be added relative to the original alt_string
-// (a constructor from std::string, and a find(char, pos) overload) because
-// the original type was never used with the binary writers/readers before
-// this file: BSON's array/document writer converts std::to_string() results
-// and checks for embedded NUL characters via find(char), and the UBJSON/BSON
-// high-precision-number path constructs the SAX string_t argument from a
-// std::string. Neither path is exercised anywhere else in the test suite for
-// this type, which is presumably why the gap was never noticed.
-/////////////////////////////////////////////////////////////////////////////
-
-class alt_string;
-bool operator<(const char* op1, const alt_string& op2) noexcept; // NOLINT(misc-use-internal-linkage)
-void int_to_string(alt_string& target, std::size_t value); // NOLINT(misc-use-internal-linkage)
-
-class alt_string
-{
-  public:
-    using value_type = std::string::value_type;
-
-    static constexpr auto npos = (std::numeric_limits<std::size_t>::max)();
-
-    alt_string(const char* str): str_impl(str) {}
-    alt_string(const char* str, std::size_t count): str_impl(str, count) {}
-    alt_string(std::string str): str_impl(std::move(str)) {}
-    alt_string(size_t count, char chr): str_impl(count, chr) {}
-    alt_string() = default;
-
-    alt_string& append(char ch)
-    {
-        str_impl.push_back(ch);
-        return *this;
-    }
-
-    alt_string& append(const alt_string& str)
-    {
-        str_impl.append(str.str_impl);
-        return *this;
-    }
-
-    alt_string& append(const char* s, std::size_t length)
-    {
-        str_impl.append(s, length);
-        return *this;
-    }
-
-    void push_back(char c)
-    {
-        str_impl.push_back(c);
-    }
-
-    template <typename op_type>
-    bool operator==(const op_type& op) const
-    {
-        return str_impl == op;
-    }
-
-    bool operator==(const alt_string& op) const
-    {
-        return str_impl == op.str_impl;
-    }
-
-    template <typename op_type>
-    bool operator!=(const op_type& op) const
-    {
-        return str_impl != op;
-    }
-
-    bool operator!=(const alt_string& op) const
-    {
-        return str_impl != op.str_impl;
-    }
-
-    std::size_t size() const noexcept
-    {
-        return str_impl.size();
-    }
-
-    void resize(std::size_t n)
-    {
-        str_impl.resize(n);
-    }
-
-    void resize(std::size_t n, char c)
-    {
-        str_impl.resize(n, c);
-    }
-
-    template <typename op_type>
-    bool operator<(const op_type& op) const noexcept
-    {
-        return str_impl < op;
-    }
-
-    bool operator<(const alt_string& op) const noexcept
-    {
-        return str_impl < op.str_impl;
-    }
-
-    const char* c_str() const
-    {
-        return str_impl.c_str();
-    }
-
-    char& operator[](std::size_t index)
-    {
-        return str_impl[index];
-    }
-
-    const char& operator[](std::size_t index) const
-    {
-        return str_impl[index];
-    }
-
-    char& back()
-    {
-        return str_impl.back();
-    }
-
-    const char& back() const
-    {
-        return str_impl.back();
-    }
-
-    void clear()
-    {
-        str_impl.clear();
-    }
-
-    const value_type* data() const
-    {
-        return str_impl.data();
-    }
-
-    bool empty() const
-    {
-        return str_impl.empty();
-    }
-
-    std::size_t find(const alt_string& str, std::size_t pos = 0) const
-    {
-        return str_impl.find(str.str_impl, pos);
-    }
-
-    // needed by binary_writer's BSON support, which probes string keys for
-    // embedded NUL characters via find(char)
-    std::size_t find(char c, std::size_t pos = 0) const
-    {
-        return str_impl.find(c, pos);
-    }
-
-    std::size_t find_first_of(char c, std::size_t pos = 0) const
-    {
-        return str_impl.find_first_of(c, pos);
-    }
-
-    alt_string substr(std::size_t pos = 0, std::size_t count = npos) const
-    {
-        const std::string s = str_impl.substr(pos, count);
-        return {s.data(), s.size()};
-    }
-
-    alt_string& replace(std::size_t pos, std::size_t count, const alt_string& str)
-    {
-        str_impl.replace(pos, count, str.str_impl);
-        return *this;
-    }
-
-    void reserve(std::size_t new_cap = 0)
-    {
-        str_impl.reserve(new_cap);
-    }
-
-  private:
-    std::string str_impl {}; // NOLINT(readability-redundant-member-init)
-
-    friend bool operator<(const char* /*op1*/, const alt_string& /*op2*/) noexcept;
-};
-
-void int_to_string(alt_string& target, std::size_t value)
-{
-    target = std::to_string(value).c_str();
-}
-
-using alt_json = nlohmann::basic_json <
-                 std::map,
-                 std::vector,
-                 alt_string,
-                 bool,
-                 std::int64_t,
-                 std::uint64_t,
-                 double,
-                 std::allocator,
-                 nlohmann::adl_serializer >;
-
-bool operator<(const char* op1, const alt_string& op2) noexcept
-{
-    return op1 < op2.str_impl;
-}
-
-namespace
-{
-
-// collects the object keys of j, in iteration order
-std::vector<std::string> collect_keys(const ordered_json& j)
-{
-    std::vector<std::string> result;
-    for (auto it = j.cbegin(); it != j.cend(); ++it)
-    {
-        result.push_back(it.key());
-    }
-    return result;
-}
-
-// a nested object/array value with keys inserted in non-alphabetical order,
-// used to check both round-trip equality and (for ordered_json) that
-// insertion order survives a trip through a binary format
-ordered_json make_rich_ordered_json()
-{
-    ordered_json j;
-    j["zebra"] = 1;
-    j["apple"] = ordered_json::array({1, 2, 3});
-    j["mango"]["z_nested"] = true;
-    j["mango"]["a_nested"] = nullptr;
-    j["banana"] = "some text";
-    j["cherry"] = 3.14;
-    return j;
-}
-
-alt_json make_rich_alt_json()
-{
-    alt_json j;
-    j["zebra"] = 1;
-    j["apple"] = alt_json::array({1, 2, 3});
-    j["mango"]["z_nested"] = true;
-    j["mango"]["a_nested"] = nullptr;
-    j["banana"] = "some text";
-    j["cherry"] = 3.14;
-    return j;
-}
-
-} // namespace
-
-TEST_CASE("ordered_json across binary formats")
-{
-    const ordered_json original = make_rich_ordered_json();
-    const std::vector<std::string> original_keys = collect_keys(original);
-    const std::vector<std::string> original_mango_keys = collect_keys(original["mango"]);
-
-    SECTION("CBOR")
-    {
-        const auto bytes = ordered_json::to_cbor(original);
-        const auto restored = ordered_json::from_cbor(bytes);
-        CHECK(restored == original);
-        CHECK(collect_keys(restored) == original_keys);
-        CHECK(collect_keys(restored["mango"]) == original_mango_keys);
-    }
-
-    SECTION("MessagePack")
-    {
-        const auto bytes = ordered_json::to_msgpack(original);
-        const auto restored = ordered_json::from_msgpack(bytes);
-        CHECK(restored == original);
-        CHECK(collect_keys(restored) == original_keys);
-        CHECK(collect_keys(restored["mango"]) == original_mango_keys);
-    }
-
-    SECTION("UBJSON")
-    {
-        const auto bytes = ordered_json::to_ubjson(original);
-        const auto restored = ordered_json::from_ubjson(bytes);
-        CHECK(restored == original);
-        CHECK(collect_keys(restored) == original_keys);
-        CHECK(collect_keys(restored["mango"]) == original_mango_keys);
-    }
-
-    SECTION("BSON")
-    {
-        const auto bytes = ordered_json::to_bson(original);
-        const auto restored = ordered_json::from_bson(bytes);
-        CHECK(restored == original);
-        CHECK(collect_keys(restored) == original_keys);
-        CHECK(collect_keys(restored["mango"]) == original_mango_keys);
-    }
-
-    SECTION("BJData")
-    {
-        const auto bytes = ordered_json::to_bjdata(original);
-        const auto restored = ordered_json::from_bjdata(bytes);
-        CHECK(restored == original);
-        CHECK(collect_keys(restored) == original_keys);
-        CHECK(collect_keys(restored["mango"]) == original_mango_keys);
-    }
-}
-
-TEST_CASE("alt_json (custom string_t) across binary formats")
-{
-    const alt_json original = make_rich_alt_json();
-
-    SECTION("CBOR")
-    {
-        const auto bytes = alt_json::to_cbor(original);
-        const auto restored = alt_json::from_cbor(bytes);
-        CHECK(restored == original);
-    }
-
-    SECTION("MessagePack")
-    {
-        const auto bytes = alt_json::to_msgpack(original);
-        const auto restored = alt_json::from_msgpack(bytes);
-        CHECK(restored == original);
-    }
-
-    SECTION("UBJSON")
-    {
-        const auto bytes = alt_json::to_ubjson(original);
-        const auto restored = alt_json::from_ubjson(bytes);
-        CHECK(restored == original);
-    }
-
-    SECTION("BSON")
-    {
-        const auto bytes = alt_json::to_bson(original);
-        const auto restored = alt_json::from_bson(bytes);
-        CHECK(restored == original);
-    }
-
-    SECTION("BJData")
-    {
-        const auto bytes = alt_json::to_bjdata(original);
-        const auto restored = alt_json::from_bjdata(bytes);
-        CHECK(restored == original);
-    }
-}
-
-TEST_CASE("ordered_json operator== is sensitive to key order")
-{
-    // Unlike nlohmann::json (whose object_t is a std::map, so equality never
-    // depends on insertion order), ordered_json's object_t (ordered_map) is a
-    // std::vector<std::pair<Key, T>> under the hood, and does not define its
-    // own operator==: it inherits std::vector's element-wise comparison. As a
-    // result, two ordered_json objects holding the very same key/value pairs
-    // in different insertion order compare *unequal*. This is the property
-    // that makes the round-trip `CHECK(restored == original)` checks above a
-    // meaningful order-preservation check by themselves (the explicit
-    // collect_keys() comparisons make that check explicit/readable, and
-    // guard against this operator== behavior ever changing).
-    ordered_json a;
-    a["x"] = 1;
-    a["y"] = 2;
-
-    ordered_json b;
-    b["y"] = 2;
-    b["x"] = 1;
-
-    CHECK(a.size() == b.size());
-    CHECK(a["x"] == b["x"]);
-    CHECK(a["y"] == b["y"]);
-    CHECK_FALSE(a == b);
-}
-
-TEST_CASE("duplicate keys in a binary-encoded object")
-{
-    // CBOR encoding of a map with two entries under the same key "a": {"a": 1, "a": 2}
-    const std::vector<std::uint8_t> cbor_bytes
-    {
-        0xA2, 0x61, 'a', 0x01, 0x61, 'a', 0x02
-    };
-
-    // Both json (std::map, via operator[]) and ordered_json (ordered_map, via
-    // operator[]) build binary-decoded objects by looking up/creating the
-    // entry for each incoming key and then assigning the value into it. This
-    // means a repeated key does *not* produce two entries in either case;
-    // instead, the *first* occurrence's position is kept (relevant only for
-    // ordered_json) while the *last* occurrence's value wins (for both) --
-    // this matches operator[]'s "assign the referenced slot" semantics, and
-    // is worth noting because it differs from the initializer-list
-    // construction path (`ordered_json{{"a",1},{"a",2}}`), which builds
-    // through insert()/emplace() and therefore keeps the *first* value, not
-    // the last (see the "There are no dup keys..." case in
-    // unit-ordered_json.cpp).
-    const auto j = json::from_cbor(cbor_bytes);
-    const auto oj = ordered_json::from_cbor(cbor_bytes);
-
-    CHECK(j.size() == 1);
-    CHECK(oj.size() == 1);
-    CHECK(j["a"] == 2);
-    CHECK(oj["a"] == 2);
-    CHECK(j == json(oj));
-}
-
-TEST_CASE("ordered_json through flatten/unflatten")
-{
-    const ordered_json original = make_rich_ordered_json();
-    const std::vector<std::string> original_keys = collect_keys(original);
-    const std::vector<std::string> original_mango_keys = collect_keys(original["mango"]);
-
-    const ordered_json flat = original.flatten();
-    const ordered_json unflattened = flat.unflatten();
-
-    CHECK(unflattened == original);
-    // flatten() walks the value depth-first in iteration order and
-    // unflatten() re-inserts each flattened key via operator[] in the flat
-    // object's iteration order, so for ordered_json the original key order
-    // (both top-level and nested) is preserved end-to-end.
-    CHECK(collect_keys(unflattened) == original_keys);
-    CHECK(collect_keys(unflattened["mango"]) == original_mango_keys);
-}
-
-TEST_CASE("ordered_json through diff/patch/patch_inplace")
-{
-    ordered_json original;
-    original["one"] = 1;
-    original["two"] = 2;
-    original["three"] = 3;
-
-    ordered_json target = original;
-    target["one"] = 100;      // replace
-    target.erase("two");      // remove
-    target["four"] = 4;       // add
-
-    const ordered_json patch = ordered_json::diff(original, target);
-
-    SECTION("patch")
-    {
-        const ordered_json patched = original.patch(patch);
-        CHECK(patched == target);
-    }
-
-    SECTION("patch_inplace")
-    {
-        ordered_json copy = original;
-        copy.patch_inplace(patch);
-        CHECK(copy == target);
-    }
-}
-
-TEST_CASE("ordered_json through merge_patch")
-{
-    ordered_json original;
-    original["a"] = 1;
-    original["b"] = 2;
-
-    const ordered_json patch = {{"b", nullptr}, {"c", 3}};
-
-    original.merge_patch(patch);
-
-    ordered_json expected;
-    expected["a"] = 1;
-    expected["c"] = 3;
-
-    CHECK(original == expected);
-    CHECK(collect_keys(original) == collect_keys(expected));
-}

tests/src/unit-std-format.cpp

@@ -17,7 +17,6 @@
 
 #include <nlohmann/json.hpp>
 using json = nlohmann::json;
-using ordered_json = nlohmann::ordered_json;
 
 // JSON_HAS_CPP_20 (do not remove; see note at top of file)
 #if JSON_HAS_STD_FORMAT
@@ -94,16 +93,4 @@ TEST_CASE("std::formatter<nlohmann::json>")
     }
 }
 
-TEST_CASE("std::formatter<nlohmann::ordered_json>")
-{
-    // spot-check a non-default basic_json instantiation, since the formatter
-    // is written against the generic NLOHMANN_BASIC_JSON_TPL_DECLARATION
-    // template and must actually instantiate (and behave correctly) for
-    // template arguments other than nlohmann::json
-    const ordered_json j = {{"foo", 1}, {"bar", {1, 2, 3}}};
-    CHECK(std::format("{}", j) == j.dump());
-    CHECK(std::format("{:#}", j) == j.dump(4));
-    CHECK(std::format("{:2}", j) == j.dump(2));
-}
-
 #endif