Use (std::min)(len, reserve_cap) instead of a ternary in start_array()

Addresses review feedback from @gregmarr on PR #5476.

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

include/nlohmann/detail/input/binary_reader.hpp

@@ -1434,7 +1434,7 @@ class binary_reader
                 // a copy, not a reference: it must stay valid across the
                 // pop_back() below, which destroys the container_stack element
                 // it would otherwise alias
-                container_frame top = container_stack.back();
+                const container_frame top = container_stack.back();
                 bool at_end = false;
 
                 if (top.remaining != npos)
@@ -2211,7 +2211,7 @@ class binary_reader
             // would otherwise alias.
             for (;;)
             {
-                container_frame top = container_stack.back();
+                const container_frame top = container_stack.back();
 
                 if (top.remaining != npos)
                 {

include/nlohmann/detail/input/json_sax.hpp

@@ -8,6 +8,7 @@
 
 #pragma once
 
+#include <algorithm> // min
 #include <cstddef>
 #include <string> // string
 #include <type_traits> // enable_if_t
@@ -305,6 +306,16 @@ class json_sax_dom_parser
             JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
         }
 
+        if (len != detail::unknown_size())
+        {
+            // reserve upfront to avoid repeated reallocations while adding elements,
+            // but cap the reservation so a bogus/hostile length (which is not bounded
+            // by max_size(), unlike e.g. std::vector) cannot trigger an oversized
+            // allocation for a small or truncated input
+            constexpr std::size_t reserve_cap = 16384;
+            ref_stack.back()->m_data.m_value.array->reserve((std::min)(len, reserve_cap));
+        }
+
         return true;
     }
 
@@ -683,6 +694,16 @@ class json_sax_dom_callback_parser
             {
                 JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
             }
+
+            if (len != detail::unknown_size())
+            {
+                // reserve upfront to avoid repeated reallocations while adding elements,
+                // but cap the reservation so a bogus/hostile length (which is not bounded
+                // by max_size(), unlike e.g. std::vector) cannot trigger an oversized
+                // allocation for a small or truncated input
+                constexpr std::size_t reserve_cap = 16384;
+                ref_stack.back()->m_data.m_value.array->reserve((std::min)(len, reserve_cap));
+            }
         }
 
         return true;

single_include/nlohmann/json.hpp

@@ -7892,6 +7892,7 @@ NLOHMANN_JSON_NAMESPACE_END
 
 
 
+#include <algorithm> // min
 #include <cstddef>
 #include <string> // string
 #include <type_traits> // enable_if_t
@@ -11018,6 +11019,16 @@ class json_sax_dom_parser
             JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
         }
 
+        if (len != detail::unknown_size())
+        {
+            // reserve upfront to avoid repeated reallocations while adding elements,
+            // but cap the reservation so a bogus/hostile length (which is not bounded
+            // by max_size(), unlike e.g. std::vector) cannot trigger an oversized
+            // allocation for a small or truncated input
+            constexpr std::size_t reserve_cap = 16384;
+            ref_stack.back()->m_data.m_value.array->reserve((std::min)(len, reserve_cap));
+        }
+
         return true;
     }
 
@@ -11396,6 +11407,16 @@ class json_sax_dom_callback_parser
             {
                 JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
             }
+
+            if (len != detail::unknown_size())
+            {
+                // reserve upfront to avoid repeated reallocations while adding elements,
+                // but cap the reservation so a bogus/hostile length (which is not bounded
+                // by max_size(), unlike e.g. std::vector) cannot trigger an oversized
+                // allocation for a small or truncated input
+                constexpr std::size_t reserve_cap = 16384;
+                ref_stack.back()->m_data.m_value.array->reserve((std::min)(len, reserve_cap));
+            }
         }
 
         return true;
@@ -13383,7 +13404,7 @@ class binary_reader
                 // a copy, not a reference: it must stay valid across the
                 // pop_back() below, which destroys the container_stack element
                 // it would otherwise alias
-                container_frame top = container_stack.back();
+                const container_frame top = container_stack.back();
                 bool at_end = false;
 
                 if (top.remaining != npos)
@@ -14160,7 +14181,7 @@ class binary_reader
             // would otherwise alias.
             for (;;)
             {
-                container_frame top = container_stack.back();
+                const container_frame top = container_stack.back();
 
                 if (top.remaining != npos)
                 {

tests/benchmarks/src/benchmarks.cpp

@@ -252,4 +252,323 @@ static void BinaryToCbor(benchmark::State& state)
 }
 BENCHMARK(BinaryToCbor)->RangeMultiplier(2)->Range(8, 8 << 12);
 
+//////////////////////////////////////////////////////////////////////////////
+// parse binary formats
+//////////////////////////////////////////////////////////////////////////////
+
+// Only MessagePack had a read benchmark (FromMsgpack above, left untouched so
+// its numbers stay comparable across releases). The benchmarks below cover the
+// other formats, and read from a contiguous buffer as well as from a FILE*:
+// most callers pass a container, and the two adapters compile to different
+// code. The test data repository ships JSON only, so the input for each is
+// derived at setup time by serializing a parsed test file.
+
+/// binary format to benchmark; the _optimized variants add UBJSON/BJData size
+/// and type annotations, which the readers handle in a separate code path
+enum class binary_format
+{
+    cbor,
+    msgpack,
+    ubjson,
+    ubjson_optimized,
+    bjdata,
+    bjdata_optimized,
+    bson
+};
+
+static std::vector<std::uint8_t> to_binary(const json& j, const binary_format format)
+{
+    switch (format)
+    {
+        case binary_format::cbor:
+            return json::to_cbor(j);
+        case binary_format::msgpack:
+            return json::to_msgpack(j);
+        case binary_format::ubjson:
+            return json::to_ubjson(j);
+        case binary_format::ubjson_optimized:
+            return json::to_ubjson(j, true, true);
+        case binary_format::bjdata:
+            return json::to_bjdata(j);
+        case binary_format::bjdata_optimized:
+            return json::to_bjdata(j, true, true);
+        case binary_format::bson:
+        default:
+            return json::to_bson(j);
+    }
+}
+
+static json from_binary(const std::vector<std::uint8_t>& bytes, const binary_format format)
+{
+    switch (format)
+    {
+        case binary_format::cbor:
+            return json::from_cbor(bytes);
+        case binary_format::msgpack:
+            return json::from_msgpack(bytes);
+        case binary_format::ubjson:
+        case binary_format::ubjson_optimized:
+            return json::from_ubjson(bytes);
+        case binary_format::bjdata:
+        case binary_format::bjdata_optimized:
+            return json::from_bjdata(bytes);
+        case binary_format::bson:
+        default:
+            return json::from_bson(bytes);
+    }
+}
+
+static json from_binary(std::FILE* file, const binary_format format)
+{
+    switch (format)
+    {
+        case binary_format::cbor:
+            return json::from_cbor(file);
+        case binary_format::msgpack:
+            return json::from_msgpack(file);
+        case binary_format::ubjson:
+        case binary_format::ubjson_optimized:
+            return json::from_ubjson(file);
+        case binary_format::bjdata:
+        case binary_format::bjdata_optimized:
+            return json::from_bjdata(file);
+        case binary_format::bson:
+        default:
+            return json::from_bson(file);
+    }
+}
+
+/*!
+@brief serialize a parsed test file to @a format
+
+Returns an empty vector and marks the benchmark as skipped if the file cannot
+be represented in the format, rather than letting the exception escape: BSON
+requires an object at the top level, and several test files are arrays.
+*/
+static std::vector<std::uint8_t> binary_input(benchmark::State& state, const char* filename, const binary_format format)
+{
+    std::ifstream f(filename);
+    std::string const str((std::istreambuf_iterator<char>(f)), std::istreambuf_iterator<char>());
+    const json j = json::parse(str);
+
+    if (format == binary_format::bson && !j.is_object())
+    {
+        state.SkipWithError("BSON requires an object at the top level");
+        return {};
+    }
+
+    return to_binary(j, format);
+}
+
+static void FromBinaryBuffer(benchmark::State& state, const char* filename, const binary_format format)
+{
+    const std::vector<std::uint8_t> bytes = binary_input(state, filename, format);
+    if (bytes.empty())
+    {
+        return;
+    }
+
+    for (auto _ : state)
+    {
+        // the value is destroyed outside the timed section, because destroying
+        // a large DOM is not what this benchmark measures
+        state.PauseTiming();
+        auto* j = new json();
+        state.ResumeTiming();
+
+        *j = from_binary(bytes, format);
+
+        state.PauseTiming();
+        delete j;
+        state.ResumeTiming();
+    }
+
+    state.SetBytesProcessed(state.iterations() * bytes.size());
+}
+
+BENCHMARK_CAPTURE(FromBinaryBuffer, cbor / jeopardy, TEST_DATA_DIRECTORY "/jeopardy/jeopardy.json", binary_format::cbor);
+BENCHMARK_CAPTURE(FromBinaryBuffer, cbor / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::cbor);
+BENCHMARK_CAPTURE(FromBinaryBuffer, cbor / citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json", binary_format::cbor);
+BENCHMARK_CAPTURE(FromBinaryBuffer, cbor / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::cbor);
+BENCHMARK_CAPTURE(FromBinaryBuffer, cbor / floats, TEST_DATA_DIRECTORY "/regression/floats.json", binary_format::cbor);
+BENCHMARK_CAPTURE(FromBinaryBuffer, cbor / signed_ints, TEST_DATA_DIRECTORY "/regression/signed_ints.json", binary_format::cbor);
+BENCHMARK_CAPTURE(FromBinaryBuffer, msgpack / jeopardy, TEST_DATA_DIRECTORY "/jeopardy/jeopardy.json", binary_format::msgpack);
+BENCHMARK_CAPTURE(FromBinaryBuffer, msgpack / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::msgpack);
+BENCHMARK_CAPTURE(FromBinaryBuffer, msgpack / citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json", binary_format::msgpack);
+BENCHMARK_CAPTURE(FromBinaryBuffer, msgpack / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::msgpack);
+BENCHMARK_CAPTURE(FromBinaryBuffer, ubjson / jeopardy, TEST_DATA_DIRECTORY "/jeopardy/jeopardy.json", binary_format::ubjson);
+BENCHMARK_CAPTURE(FromBinaryBuffer, ubjson / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::ubjson);
+BENCHMARK_CAPTURE(FromBinaryBuffer, ubjson / citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json", binary_format::ubjson);
+BENCHMARK_CAPTURE(FromBinaryBuffer, ubjson / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::ubjson);
+BENCHMARK_CAPTURE(FromBinaryBuffer, ubjson_optimized / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::ubjson_optimized);
+BENCHMARK_CAPTURE(FromBinaryBuffer, ubjson_optimized / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::ubjson_optimized);
+BENCHMARK_CAPTURE(FromBinaryBuffer, bjdata / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::bjdata);
+BENCHMARK_CAPTURE(FromBinaryBuffer, bjdata / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::bjdata);
+BENCHMARK_CAPTURE(FromBinaryBuffer, bjdata_optimized / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::bjdata_optimized);
+BENCHMARK_CAPTURE(FromBinaryBuffer, bjdata_optimized / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::bjdata_optimized);
+// BSON requires an object at the top level, so the array-rooted test files
+// (jeopardy and the regression files) cannot be captured here
+BENCHMARK_CAPTURE(FromBinaryBuffer, bson / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::bson);
+BENCHMARK_CAPTURE(FromBinaryBuffer, bson / citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json", binary_format::bson);
+BENCHMARK_CAPTURE(FromBinaryBuffer, bson / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::bson);
+
+static void FromBinaryFile(benchmark::State& state, const char* filename, const binary_format format)
+{
+    const std::vector<std::uint8_t> bytes = binary_input(state, filename, format);
+    if (bytes.empty())
+    {
+        return;
+    }
+
+    const char* tmp = "benchmark_input.bin";
+    std::ofstream o(tmp, std::ios::binary);
+    o.write(reinterpret_cast<const char*>(bytes.data()), static_cast<std::streamsize>(bytes.size()));
+    o.flush();
+    o.close();
+
+    for (auto _ : state)
+    {
+        state.PauseTiming();
+        auto* j = new json();
+        auto* file = std::fopen(tmp, "rb");
+        state.ResumeTiming();
+
+        *j = from_binary(file, format);
+
+        state.PauseTiming();
+        std::fclose(file);
+        delete j;
+        state.ResumeTiming();
+    }
+
+    state.SetBytesProcessed(state.iterations() * bytes.size());
+}
+
+BENCHMARK_CAPTURE(FromBinaryFile, cbor / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::cbor);
+BENCHMARK_CAPTURE(FromBinaryFile, cbor / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::cbor);
+BENCHMARK_CAPTURE(FromBinaryFile, ubjson / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::ubjson);
+BENCHMARK_CAPTURE(FromBinaryFile, ubjson / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::ubjson);
+BENCHMARK_CAPTURE(FromBinaryFile, bjdata / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::bjdata);
+BENCHMARK_CAPTURE(FromBinaryFile, bson / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::bson);
+
+//////////////////////////////////////////////////////////////////////////////
+// parse binary formats: value shapes
+//////////////////////////////////////////////////////////////////////////////
+
+// The test files above are wide and shallow, but the readers' cost is per
+// container, so these cover the shapes that stress the container handling
+// itself. Every shape is wrapped in an object so that BSON, which requires an
+// object at the top level, measures the same value as the other formats.
+
+/// deeply nested arrays: one container per level, no other work
+static json make_nested()
+{
+    json nested = json::array();
+    json* p = &nested;
+    for (std::size_t i = 1; i < 1000; ++i)
+    {
+        p->push_back(json::array());
+        p = &p->operator[](0);
+    }
+
+    json j = json::object();
+    j["data"] = std::move(nested);
+    return j;
+}
+
+/// many sibling containers: maximum container churn, minimum nesting
+static json make_containers()
+{
+    json data = json::array();
+    for (std::size_t i = 0; i < 100000; ++i)
+    {
+        data.push_back(json::array({1, 2}));
+    }
+
+    json j = json::object();
+    j["data"] = std::move(data);
+    return j;
+}
+
+/// one flat array of numbers: the scalar decoding path, which must not move
+static json make_scalars()
+{
+    json data = json::array();
+    for (std::size_t i = 0; i < 1000000; ++i)
+    {
+        data.push_back(i);
+    }
+
+    json j = json::object();
+    j["data"] = std::move(data);
+    return j;
+}
+
+static void FromBinaryShape(benchmark::State& state, json (*build)(), const binary_format format)
+{
+    const std::vector<std::uint8_t> bytes = to_binary(build(), format);
+
+    for (auto _ : state)
+    {
+        state.PauseTiming();
+        auto* j = new json();
+        state.ResumeTiming();
+
+        *j = from_binary(bytes, format);
+
+        state.PauseTiming();
+        delete j;
+        state.ResumeTiming();
+    }
+
+    state.SetBytesProcessed(state.iterations() * bytes.size());
+}
+
+BENCHMARK_CAPTURE(FromBinaryShape, nested / cbor, make_nested, binary_format::cbor);
+BENCHMARK_CAPTURE(FromBinaryShape, nested / msgpack, make_nested, binary_format::msgpack);
+BENCHMARK_CAPTURE(FromBinaryShape, nested / ubjson, make_nested, binary_format::ubjson);
+BENCHMARK_CAPTURE(FromBinaryShape, nested / bjdata, make_nested, binary_format::bjdata);
+BENCHMARK_CAPTURE(FromBinaryShape, nested / bson, make_nested, binary_format::bson);
+BENCHMARK_CAPTURE(FromBinaryShape, containers / cbor, make_containers, binary_format::cbor);
+BENCHMARK_CAPTURE(FromBinaryShape, containers / msgpack, make_containers, binary_format::msgpack);
+BENCHMARK_CAPTURE(FromBinaryShape, containers / ubjson, make_containers, binary_format::ubjson);
+BENCHMARK_CAPTURE(FromBinaryShape, containers / ubjson_optimized, make_containers, binary_format::ubjson_optimized);
+BENCHMARK_CAPTURE(FromBinaryShape, containers / bjdata, make_containers, binary_format::bjdata);
+BENCHMARK_CAPTURE(FromBinaryShape, containers / bson, make_containers, binary_format::bson);
+// BSON names every array element, so a large array measures key generation
+// rather than scalar decoding and is left out here
+BENCHMARK_CAPTURE(FromBinaryShape, scalars / cbor, make_scalars, binary_format::cbor);
+BENCHMARK_CAPTURE(FromBinaryShape, scalars / msgpack, make_scalars, binary_format::msgpack);
+BENCHMARK_CAPTURE(FromBinaryShape, scalars / ubjson, make_scalars, binary_format::ubjson);
+BENCHMARK_CAPTURE(FromBinaryShape, scalars / bjdata, make_scalars, binary_format::bjdata);
+
+/*!
+@brief parse an indefinite-length CBOR string
+
+The writer never emits this form, so the input is assembled by hand: 0x7F
+opens the string, each chunk is a one-character string, and 0xFF closes it.
+*/
+static void FromCborChunkedString(benchmark::State& state, const std::size_t chunks)
+{
+    std::vector<std::uint8_t> bytes;
+    bytes.reserve(2 * chunks + 2);
+    bytes.push_back(0x7F);
+    for (std::size_t i = 0; i < chunks; ++i)
+    {
+        bytes.push_back(0x61); // string of length 1
+        bytes.push_back(0x61); // 'a'
+    }
+    bytes.push_back(0xFF);
+
+    for (auto _ : state)
+    {
+        json j = json::from_cbor(bytes);
+        benchmark::DoNotOptimize(j);
+    }
+
+    state.SetBytesProcessed(state.iterations() * bytes.size());
+}
+
+BENCHMARK_CAPTURE(FromCborChunkedString, 10000 chunks, 10000);
+
 BENCHMARK_MAIN();

tests/src/unit-bjdata.cpp

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

tests/src/unit-cbor.cpp

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

tests/src/unit-msgpack.cpp

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

tests/src/unit-serialization.cpp

@@ -469,7 +469,7 @@ TEST_CASE("serialization of strings (bulk fast path)")
     SECTION("invalid UTF-8 handling is unaffected by the fast path")
     {
         const json j = std::string("valid\xff" "more");
-        CHECK_THROWS_WITH_AS(j.dump(), "[json.exception.type_error.316] invalid UTF-8 byte at index 5: 0xFF", json::type_error&);
+        CHECK_THROWS_WITH_AS(utils::ignore_return_value(j.dump()), "[json.exception.type_error.316] invalid UTF-8 byte at index 5: 0xFF", json::type_error&);
         CHECK(j.dump(-1, ' ', false, json::error_handler_t::replace) == "\"valid\xef\xbf\xbd" "more\"");
         CHECK(j.dump(-1, ' ', true, json::error_handler_t::replace) == "\"valid\\ufffdmore\"");
         CHECK(j.dump(-1, ' ', false, json::error_handler_t::ignore) == "\"validmore\"");

tests/src/unit-ubjson.cpp

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