Reserve capped array capacity for definite-length binary arrays

CBOR, MessagePack, and the optimized [$type#count UBJSON/BJData form all
pass an exact element count to sax->start_array(len), but
json_sax_dom_parser::start_array() (and the callback variant) only used
len for an overflow check against max_size() and never reserved the
underlying vector, so each element triggered a reallocation cascade via
emplace_back().

Reserve upfront, but cap the reservation at 16384 elements: max_size()
for a std::vector is far larger than any realistic input, so an
unbounded reserve(len) would let a crafted/truncated header (e.g. CBOR
0x9A + a huge uint32 count with no data) trigger a multi-gigabyte
allocation attempt instead of the normal graceful parse_error. With the
cap, a hostile length still fails fast with the existing parse_error,
while realistic arrays get a single up-front allocation.

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

tests/src/unit-bjdata.cpp

@@ -3489,6 +3489,65 @@ TEST_CASE("BJData")
     }
 }
 
+TEST_CASE("issue #5405 - array reserve for definite-length BJData arrays")
+{
+    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};
+        CHECK_THROWS_WITH_AS(_ = json::from_bjdata(input),
+                             "[json.exception.parse_error.110] parse error at byte 10: syntax error while parsing BJData number: unexpected end of input",
+                             json::parse_error&);
+        CHECK(json::from_bjdata(input, true, false).is_discarded());
+    }
+
+    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

@@ -2035,6 +2035,60 @@ TEST_CASE("CBOR definite length equal to the indefinite-length sentinel")
     }
 }
 
+TEST_CASE("issue #5405 - array reserve for definite-length CBOR arrays")
+{
+    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};
+        CHECK_THROWS_WITH_AS(_ = json::from_cbor(input),
+                             "[json.exception.parse_error.110] parse error at byte 6: syntax error while parsing CBOR value: unexpected end of input",
+                             json::parse_error&);
+        CHECK(json::from_cbor(input, true, false).is_discarded());
+    }
+
+    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 +1597,60 @@ TEST_CASE("MessagePack")
     }
 }
 
+TEST_CASE("issue #5405 - array reserve for definite-length MessagePack arrays")
+{
+    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};
+        CHECK_THROWS_WITH_AS(_ = json::from_msgpack(input),
+                             "[json.exception.parse_error.110] parse error at byte 6: syntax error while parsing MessagePack value: unexpected end of input",
+                             json::parse_error&);
+        CHECK(json::from_msgpack(input, true, false).is_discarded());
+    }
+
+    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("single MessagePack roundtrip")
 {

tests/src/unit-ubjson.cpp

@@ -2149,6 +2149,65 @@ TEST_CASE("UBJSON")
     }
 }
 
+TEST_CASE("issue #5405 - array reserve for definite-length UBJSON arrays")
+{
+    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};
+        CHECK_THROWS_WITH_AS(_ = json::from_ubjson(input),
+                             "[json.exception.parse_error.110] parse error at byte 10: syntax error while parsing UBJSON number: unexpected end of input",
+                             json::parse_error&);
+        CHECK(json::from_ubjson(input, true, false).is_discarded());
+    }
+
+    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")