Document why the digit-count fast path is safe regardless of number_unsigned_t/number_integer_t width

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

include/nlohmann/detail/input/json_sax.hpp

@@ -301,16 +301,6 @@ 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(len < reserve_cap ? len : reserve_cap);
-        }
-
         return true;
     }
 
@@ -671,16 +661,6 @@ 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(len < reserve_cap ? len : reserve_cap);
-            }
         }
 
         return true;

include/nlohmann/detail/input/lexer.hpp

@@ -149,10 +149,11 @@ class lexer : public lexer_base<BasicJsonType>
   public:
     using token_type = typename lexer_base<BasicJsonType>::token_type;
 
-    explicit lexer(InputAdapterType&& adapter, bool ignore_comments_ = false) noexcept
+    explicit lexer(InputAdapterType&& adapter, bool ignore_comments_ = false, bool discard_number_values_ = false) noexcept
         : ia(std::move(adapter))
         , ignore_comments(ignore_comments_)
         , decimal_point_char(static_cast<char_int_type>(get_decimal_point()))
+        , discard_number_values(discard_number_values_)
     {}
 
     // deleted because of pointer members
@@ -1279,6 +1280,58 @@ scan_number_done:
         // we are done scanning a number)
         unget();
 
+        // If the caller does not need the converted value (only whether the
+        // input is syntactically valid; see json_sax_acceptor/accept()), an
+        // unsigned/integer token can be reported without calling
+        // strtoull()/strtoll() at all, *provided* we can already tell from
+        // the digit count alone that the conversion cannot overflow 64 bits.
+        // Such tokens are always finite and are accepted unconditionally by
+        // the parser regardless of their actual value (parser::sax_parse_internal()
+        // never checks finiteness for value_unsigned/value_integer), so the
+        // classification below is all that is needed.
+        //
+        // A decimal number with up to 18 digits is always representable in
+        // both std::uint64_t and std::int64_t (18 nines is ~1e18, well below
+        // both UINT64_MAX ~1.8e19 and INT64_MAX ~9.2e18), so strtoull()/strtoll()
+        // could not have set errno to ERANGE for it. Numbers with more digits
+        // (rare in practice) fall through to the exact code below, unchanged,
+        // so their handling -- including reclassification to value_float when
+        // the value overflows 64 bits, and rejection when it is not even
+        // finite as a double -- is bit-for-bit identical to before this
+        // optimization.
+        //
+        // Note this reasons about std::uint64_t/std::int64_t, not about
+        // number_unsigned_t/number_integer_t (BasicJsonType's own, possibly
+        // narrower, template parameters -- e.g. std::uint32_t). That is fine
+        // *only* because discard_number_values is exclusively set by
+        // accept() (see json.hpp), and accept() always parses through the
+        // library's own json_sax_acceptor -- never a user-supplied SAX
+        // consumer -- whose number_unsigned()/number_integer()/number_float()
+        // callbacks unconditionally discard their argument and return true.
+        // So for every caller that can reach this branch, neither the token
+        // classification below nor the eventual (possibly narrowed, and on
+        // this fast path left stale/unset) value_unsigned/value_integer is
+        // ever consulted -- an unsigned/integer token is accepted outright,
+        // and even a >18-digit token that this fast path deliberately falls
+        // through for is, once reclassified to value_float, still finite
+        // (and thus accepted) for any digit count that fits in number_unsigned_t
+        // or number_integer_t regardless of that type's width. If this
+        // function is ever taught to run with discard_number_values true for
+        // a caller that *does* read the converted value, this reasoning (and
+        // the fast path below) would need to be revisited.
+        if (discard_number_values)
+        {
+            constexpr std::size_t safe_digit_count = 18;
+            if (number_type == token_type::value_unsigned && token_buffer.size() <= safe_digit_count)
+            {
+                return token_type::value_unsigned;
+            }
+            if (number_type == token_type::value_integer && token_buffer.size() - 1 <= safe_digit_count)
+            {
+                return token_type::value_integer;
+            }
+        }
+
         char* endptr = nullptr; // NOLINT(misc-const-correctness,cppcoreguidelines-pro-type-vararg,hicpp-vararg)
         errno = 0;
 
@@ -1754,6 +1807,13 @@ scan_number_done:
     const char_int_type decimal_point_char = '.';
     /// the position of the decimal point in the input
     std::size_t decimal_point_position = std::string::npos;
+
+    /// whether the caller (e.g. accept()/json_sax_acceptor) only needs the
+    /// token classification and never looks at the converted numeric value;
+    /// when set, scan_number() may skip strtoull()/strtoll() for
+    /// value_unsigned/value_integer tokens whose digit count guarantees they
+    /// fit into 64 bits (see scan_number())
+    const bool discard_number_values = false;
 };
 
 }  // namespace detail

include/nlohmann/detail/input/parser.hpp

@@ -72,9 +72,10 @@ class parser
                     parser_callback_t<BasicJsonType> cb = nullptr,
                     const bool allow_exceptions_ = true,
                     const bool ignore_comments = false,
-                    const bool ignore_trailing_commas_ = false)
+                    const bool ignore_trailing_commas_ = false,
+                    const bool discard_number_values_ = false)
         : callback(std::move(cb))
-        , m_lexer(std::move(adapter), ignore_comments)
+        , m_lexer(std::move(adapter), ignore_comments, discard_number_values_)
         , allow_exceptions(allow_exceptions_)
         , ignore_trailing_commas(ignore_trailing_commas_)
     {

include/nlohmann/json.hpp

@@ -164,11 +164,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         detail::parser_callback_t<basic_json>cb = nullptr,
         const bool allow_exceptions = true,
         const bool ignore_comments = false,
-        const bool ignore_trailing_commas = false
+        const bool ignore_trailing_commas = false,
+        const bool discard_number_values = false
     )
     {
         return ::nlohmann::detail::parser<basic_json, InputAdapterType>(std::move(adapter),
-               std::move(cb), allow_exceptions, ignore_comments, ignore_trailing_commas);
+               std::move(cb), allow_exceptions, ignore_comments, ignore_trailing_commas, discard_number_values);
     }
 
   private:
@@ -4133,7 +4134,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
                        const bool ignore_comments = false,
                        const bool ignore_trailing_commas = false)
     {
-        return parser(detail::input_adapter(std::forward<InputType>(i)), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true);
+        return parser(detail::input_adapter(std::forward<InputType>(i)), nullptr, false, ignore_comments, ignore_trailing_commas, true).accept(true);
     }
 
     /// @brief check if the input is valid JSON (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4144,7 +4145,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
                        const bool ignore_comments = false,
                        const bool ignore_trailing_commas = false)
     {
-        return parser(detail::input_adapter(std::move(first), std::move(last)), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true);
+        return parser(detail::input_adapter(std::move(first), std::move(last)), nullptr, false, ignore_comments, ignore_trailing_commas, true).accept(true);
     }
 
     JSON_HEDLEY_WARN_UNUSED_RESULT
@@ -4153,7 +4154,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
                        const bool ignore_comments = false,
                        const bool ignore_trailing_commas = false)
     {
-        return parser(i.get(), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true);
+        return parser(i.get(), nullptr, false, ignore_comments, ignore_trailing_commas, true).accept(true);
     }
 
     /// @brief generate SAX events

single_include/nlohmann/json.hpp

@@ -7932,10 +7932,11 @@ class lexer : public lexer_base<BasicJsonType>
   public:
     using token_type = typename lexer_base<BasicJsonType>::token_type;
 
-    explicit lexer(InputAdapterType&& adapter, bool ignore_comments_ = false) noexcept
+    explicit lexer(InputAdapterType&& adapter, bool ignore_comments_ = false, bool discard_number_values_ = false) noexcept
         : ia(std::move(adapter))
         , ignore_comments(ignore_comments_)
         , decimal_point_char(static_cast<char_int_type>(get_decimal_point()))
+        , discard_number_values(discard_number_values_)
     {}
 
     // deleted because of pointer members
@@ -9062,6 +9063,58 @@ scan_number_done:
         // we are done scanning a number)
         unget();
 
+        // If the caller does not need the converted value (only whether the
+        // input is syntactically valid; see json_sax_acceptor/accept()), an
+        // unsigned/integer token can be reported without calling
+        // strtoull()/strtoll() at all, *provided* we can already tell from
+        // the digit count alone that the conversion cannot overflow 64 bits.
+        // Such tokens are always finite and are accepted unconditionally by
+        // the parser regardless of their actual value (parser::sax_parse_internal()
+        // never checks finiteness for value_unsigned/value_integer), so the
+        // classification below is all that is needed.
+        //
+        // A decimal number with up to 18 digits is always representable in
+        // both std::uint64_t and std::int64_t (18 nines is ~1e18, well below
+        // both UINT64_MAX ~1.8e19 and INT64_MAX ~9.2e18), so strtoull()/strtoll()
+        // could not have set errno to ERANGE for it. Numbers with more digits
+        // (rare in practice) fall through to the exact code below, unchanged,
+        // so their handling -- including reclassification to value_float when
+        // the value overflows 64 bits, and rejection when it is not even
+        // finite as a double -- is bit-for-bit identical to before this
+        // optimization.
+        //
+        // Note this reasons about std::uint64_t/std::int64_t, not about
+        // number_unsigned_t/number_integer_t (BasicJsonType's own, possibly
+        // narrower, template parameters -- e.g. std::uint32_t). That is fine
+        // *only* because discard_number_values is exclusively set by
+        // accept() (see json.hpp), and accept() always parses through the
+        // library's own json_sax_acceptor -- never a user-supplied SAX
+        // consumer -- whose number_unsigned()/number_integer()/number_float()
+        // callbacks unconditionally discard their argument and return true.
+        // So for every caller that can reach this branch, neither the token
+        // classification below nor the eventual (possibly narrowed, and on
+        // this fast path left stale/unset) value_unsigned/value_integer is
+        // ever consulted -- an unsigned/integer token is accepted outright,
+        // and even a >18-digit token that this fast path deliberately falls
+        // through for is, once reclassified to value_float, still finite
+        // (and thus accepted) for any digit count that fits in number_unsigned_t
+        // or number_integer_t regardless of that type's width. If this
+        // function is ever taught to run with discard_number_values true for
+        // a caller that *does* read the converted value, this reasoning (and
+        // the fast path below) would need to be revisited.
+        if (discard_number_values)
+        {
+            constexpr std::size_t safe_digit_count = 18;
+            if (number_type == token_type::value_unsigned && token_buffer.size() <= safe_digit_count)
+            {
+                return token_type::value_unsigned;
+            }
+            if (number_type == token_type::value_integer && token_buffer.size() - 1 <= safe_digit_count)
+            {
+                return token_type::value_integer;
+            }
+        }
+
         char* endptr = nullptr; // NOLINT(misc-const-correctness,cppcoreguidelines-pro-type-vararg,hicpp-vararg)
         errno = 0;
 
@@ -9537,6 +9590,13 @@ scan_number_done:
     const char_int_type decimal_point_char = '.';
     /// the position of the decimal point in the input
     std::size_t decimal_point_position = std::string::npos;
+
+    /// whether the caller (e.g. accept()/json_sax_acceptor) only needs the
+    /// token classification and never looks at the converted numeric value;
+    /// when set, scan_number() may skip strtoull()/strtoll() for
+    /// value_unsigned/value_integer tokens whose digit count guarantees they
+    /// fit into 64 bits (see scan_number())
+    const bool discard_number_values = false;
 };
 
 }  // namespace detail
@@ -9829,16 +9889,6 @@ 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(len < reserve_cap ? len : reserve_cap);
-        }
-
         return true;
     }
 
@@ -10199,16 +10249,6 @@ 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(len < reserve_cap ? len : reserve_cap);
-            }
         }
 
         return true;
@@ -14063,9 +14103,10 @@ class parser
                     parser_callback_t<BasicJsonType> cb = nullptr,
                     const bool allow_exceptions_ = true,
                     const bool ignore_comments = false,
-                    const bool ignore_trailing_commas_ = false)
+                    const bool ignore_trailing_commas_ = false,
+                    const bool discard_number_values_ = false)
         : callback(std::move(cb))
-        , m_lexer(std::move(adapter), ignore_comments)
+        , m_lexer(std::move(adapter), ignore_comments, discard_number_values_)
         , allow_exceptions(allow_exceptions_)
         , ignore_trailing_commas(ignore_trailing_commas_)
     {
@@ -21612,11 +21653,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         detail::parser_callback_t<basic_json>cb = nullptr,
         const bool allow_exceptions = true,
         const bool ignore_comments = false,
-        const bool ignore_trailing_commas = false
+        const bool ignore_trailing_commas = false,
+        const bool discard_number_values = false
                                  )
     {
         return ::nlohmann::detail::parser<basic_json, InputAdapterType>(std::move(adapter),
-            std::move(cb), allow_exceptions, ignore_comments, ignore_trailing_commas);
+            std::move(cb), allow_exceptions, ignore_comments, ignore_trailing_commas, discard_number_values);
     }
 
   private:
@@ -25581,7 +25623,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
                        const bool ignore_comments = false,
                        const bool ignore_trailing_commas = false)
     {
-        return parser(detail::input_adapter(std::forward<InputType>(i)), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true);
+        return parser(detail::input_adapter(std::forward<InputType>(i)), nullptr, false, ignore_comments, ignore_trailing_commas, true).accept(true);
     }
 
     /// @brief check if the input is valid JSON (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -25592,7 +25634,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
                        const bool ignore_comments = false,
                        const bool ignore_trailing_commas = false)
     {
-        return parser(detail::input_adapter(std::move(first), std::move(last)), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true);
+        return parser(detail::input_adapter(std::move(first), std::move(last)), nullptr, false, ignore_comments, ignore_trailing_commas, true).accept(true);
     }
 
     JSON_HEDLEY_WARN_UNUSED_RESULT
@@ -25601,7 +25643,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
                        const bool ignore_comments = false,
                        const bool ignore_trailing_commas = false)
     {
-        return parser(i.get(), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true);
+        return parser(i.get(), nullptr, false, ignore_comments, ignore_trailing_commas, true).accept(true);
     }
 
     /// @brief generate SAX events

tests/src/unit-bjdata.cpp

@@ -3489,65 +3489,6 @@ 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

@@ -2035,60 +2035,6 @@ 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-class_parser.cpp

@@ -930,6 +930,94 @@ TEST_CASE("parser class")
                 CHECK(accept_helper("+1") == false);
                 CHECK(accept_helper("+0") == false);
             }
+
+            SECTION("issue #5411 - skip conversion when accept() does not need the numeric value")
+            {
+                // lexer::scan_number() may skip strtoull()/strtoll() for
+                // value_unsigned/value_integer tokens when the caller (e.g.
+                // json::accept()) does not need the converted value, as long
+                // as the digit count alone guarantees no 64-bit overflow (see
+                // the "safe_digit_count" fast path in scan_number()). This
+                // differential test checks that json::accept() (which enables
+                // the fast path) and json::parse() (which never does) always
+                // agree, over a corpus that exercises both the fast path
+                // (<=18 digits) and the untouched, exact fallback path (>=19
+                // digits) -- including reclassification of huge digit-only
+                // integers to a (possibly non-finite) floating-point value.
+                const std::vector<std::pair<std::string, bool>> cases =
+                {
+                    // normal small/large integers, both signs
+                    {"0", true}, {"1", true}, {"-1", true}, {"42", true}, {"-42", true},
+                    {"123456789", true}, {"-123456789", true},
+
+                    // digit-count boundary around the 18-digit safe cutoff (both signs)
+                    {std::string(17, '9'), true},
+                    {std::string(18, '9'), true},
+                    {std::string(19, '9'), true},
+                    {std::string(20, '9'), true},
+                    {"-" + std::string(17, '9'), true},
+                    {"-" + std::string(18, '9'), true},
+                    {"-" + std::string(19, '9'), true},
+                    {"-" + std::string(20, '9'), true},
+
+                    // 64-bit boundaries
+                    {"9223372036854775807", true},    // INT64_MAX
+                    {"-9223372036854775808", true},   // INT64_MIN
+                    {"18446744073709551615", true},   // UINT64_MAX
+                    {"18446744073709551616", true},   // UINT64_MAX + 1 (overflows uint64_t, finite double)
+
+                    // the 28-digit example from the issue: overflows uint64_t
+                    // but is finite as a double, so the scanner reclassifies
+                    // it to value_float and it is accepted
+                    {"9999999999999999999999999999", true},
+
+                    // huge digit-only integers that overflow even a double -> rejected
+                    {std::string(309, '9'), false},
+                    {std::string(400, '9'), false},
+                    {"1" + std::string(400, '0'), false},
+
+                    // 1e999 / 1e400 style overflow -> rejected
+                    {"1e999", false},
+                    {"1e400", false},
+                    {"-1e999", false},
+                    {"1E999", false},
+
+                    // values straddling DBL_MAX
+                    {"1.7976931348623157e308", true},   // <= DBL_MAX, finite
+                    {"1.7976931348623159e308", false},  // > DBL_MAX, overflows to inf
+
+                    // a mix of other valid/invalid numeric syntax
+                    {"3.14159", true},
+                    {"-0.0", true},
+                    {"1.0e10", true},
+                    {"01", false},
+                    {"-", false},
+                    {"1.", false},
+                    {"1e", false},
+                    {"+1", false},
+                };
+
+                for (const auto& c : cases)
+                {
+                    const std::string& number = c.first;
+                    const bool expected = c.second;
+                    CAPTURE(number)
+                    CAPTURE(expected)
+
+                    // accept() takes the fast path (skips conversion when possible)
+                    CHECK(json::accept(number) == expected);
+
+                    // parse() always performs the full conversion; it must agree
+                    json j;
+                    CHECK_NOTHROW(json::parser(nlohmann::detail::input_adapter(number), nullptr, false).parse(true, j));
+                    CHECK(!j.is_discarded() == expected);
+
+                    // wrap in an array so get_token() is exercised beyond the
+                    // very first (constructor-time) scan as well
+                    const std::string wrapped = "[" + number + "," + number + "]";
+                    CHECK(json::accept(wrapped) == expected);
+                }
+            }
         }
     }
 

tests/src/unit-msgpack.cpp

@@ -1597,60 +1597,6 @@ 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

@@ -2149,65 +2149,6 @@ 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")