Reserve output capacity up front for binary serialization

The vector-returning to_cbor/to_msgpack/to_ubjson/to_bjdata/to_bson grew
the output buffer purely by geometric reallocation. Reserving an estimate
up front avoids the early reallocations, which is the dominant per-byte
cost for array/object-heavy output.

The estimate (binary_reserve_hint) is deliberately conservative and safe
against untrusted input: it consults only the top-level element count
(O(1), no walk of the DOM), guards the multiplication against overflow,
and clamps the result to a fixed 1 MiB ceiling, so a large or hostile DOM
can never force an oversized allocation here. The buffer still grows
geometrically past the hint, so an underestimate only costs a few later
reallocations; scalars/strings/binary are written in one shot and get no
hint. Reserving capacity does not change the bytes produced.

Throughput (g++/clang -O3, vs the previous commit):
  cbor int array     +10% / +13%
  cbor object array  +20% / +38%

Output is byte-for-byte identical to develop across the binary
differential corpus.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XAYM1qhSA2FDaDcGfPW3fG
Signed-off-by: Niels Lohmann <mail@nlohmann.me>

.github/workflows/codeql-analysis.yml

@@ -38,14 +38,14 @@ jobs:
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@54f647b7e1bb85c95cddabcd46b0c578ec92bc1a # v4.36.3
+      uses: github/codeql-action/init@99df26d4f13ea111d4ec1a7dddef6063f76b97e9 # v4.37.0
       with:
         languages: c-cpp
 
     # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
     # If this step fails, then you should remove it and run the build manually (see below)
     - name: Autobuild
-      uses: github/codeql-action/autobuild@54f647b7e1bb85c95cddabcd46b0c578ec92bc1a # v4.36.3
+      uses: github/codeql-action/autobuild@99df26d4f13ea111d4ec1a7dddef6063f76b97e9 # v4.37.0
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@54f647b7e1bb85c95cddabcd46b0c578ec92bc1a # v4.36.3
+      uses: github/codeql-action/analyze@99df26d4f13ea111d4ec1a7dddef6063f76b97e9 # v4.37.0

.github/workflows/flawfinder.yml

@@ -43,6 +43,6 @@ jobs:
           output: 'flawfinder_results.sarif'
 
       - name: Upload analysis results to GitHub Security tab
-        uses: github/codeql-action/upload-sarif@54f647b7e1bb85c95cddabcd46b0c578ec92bc1a # v4.36.3
+        uses: github/codeql-action/upload-sarif@99df26d4f13ea111d4ec1a7dddef6063f76b97e9 # v4.37.0
         with:
           sarif_file: ${{github.workspace}}/flawfinder_results.sarif

.github/workflows/scorecards.yml

@@ -76,6 +76,6 @@ jobs:
 
       # Upload the results to GitHub's code scanning dashboard.
       - name: "Upload to code-scanning"
-        uses: github/codeql-action/upload-sarif@54f647b7e1bb85c95cddabcd46b0c578ec92bc1a # v4.36.3
+        uses: github/codeql-action/upload-sarif@99df26d4f13ea111d4ec1a7dddef6063f76b97e9 # v4.37.0
         with:
           sarif_file: results.sarif

.github/workflows/semgrep.yml

@@ -61,7 +61,7 @@ jobs:
 
       # Upload SARIF file generated in previous step
       - name: Upload SARIF file
-        uses: github/codeql-action/upload-sarif@54f647b7e1bb85c95cddabcd46b0c578ec92bc1a # v4.36.3
+        uses: github/codeql-action/upload-sarif@99df26d4f13ea111d4ec1a7dddef6063f76b97e9 # v4.37.0
         with:
           sarif_file: semgrep.sarif
         if: always()

.github/workflows/stale.yml

@@ -20,7 +20,7 @@ jobs:
         with:
           egress-policy: audit
 
-      - uses: actions/stale@eb5cf3af3ac0a1aa4c9c45633dd1ae542a27a899 # v10.3.0
+      - uses: actions/stale@1e223db275d687790206a7acac4d1a11bd6fe629 # v10.4.0
         with:
           stale-issue-label: 'state: stale'
           stale-pr-label: 'state: stale'

include/nlohmann/detail/input/binary_reader.hpp

@@ -1846,6 +1846,29 @@ class binary_reader
         return get_ubjson_value(get_char ? get_ignore_noop() : current);
     }
 
+    /*!
+    @brief reject a negative UBJSON/BJData string length
+
+    String and key lengths are written with signed integer markers (i, I, l,
+    L). A negative value is malformed; without this check get_string() would
+    silently treat it as an empty string and leave the following bytes to be
+    misread as the next value. This mirrors the non-negative check the
+    optimized-container count path already performs in get_ubjson_size_value.
+
+    @param[in] len  the string length read from the input
+    @return whether the length is valid (non-negative)
+    */
+    template<typename NumberType>
+    bool check_ubjson_string_length(const NumberType len)
+    {
+        if (JSON_HEDLEY_UNLIKELY(len < 0))
+        {
+            return sax->parse_error(chars_read, get_token_string(), parse_error::create(113, chars_read,
+                                    exception_message(input_format, "string length must not be negative", "string"), nullptr));
+        }
+        return true;
+    }
+
     /*!
     @brief reads a UBJSON string
 
@@ -1883,25 +1906,25 @@ class binary_reader
             case 'i':
             {
                 std::int8_t len{};
-                return get_number(input_format, len) && get_string(input_format, len, result);
+                return get_number(input_format, len) && check_ubjson_string_length(len) && get_string(input_format, len, result);
             }
 
             case 'I':
             {
                 std::int16_t len{};
-                return get_number(input_format, len) && get_string(input_format, len, result);
+                return get_number(input_format, len) && check_ubjson_string_length(len) && get_string(input_format, len, result);
             }
 
             case 'l':
             {
                 std::int32_t len{};
-                return get_number(input_format, len) && get_string(input_format, len, result);
+                return get_number(input_format, len) && check_ubjson_string_length(len) && get_string(input_format, len, result);
             }
 
             case 'L':
             {
                 std::int64_t len{};
-                return get_number(input_format, len) && get_string(input_format, len, result);
+                return get_number(input_format, len) && check_ubjson_string_length(len) && get_string(input_format, len, result);
             }
 
             case 'u':

include/nlohmann/detail/input/input_adapters.hpp

@@ -395,17 +395,30 @@ struct wide_string_input_helper<BaseInputAdapter, 2>
             }
             else
             {
-                if (JSON_HEDLEY_UNLIKELY(!input.empty()))
+                // A supplementary code point is a high surrogate (0xD800..0xDBFF)
+                // followed by a low surrogate (0xDC00..0xDFFF). A lone low
+                // surrogate, a high surrogate at the end of the input, or a high
+                // surrogate followed by any other unit is malformed UTF-16. In
+                // that case the offending unit is passed through unchanged so the
+                // UTF-8 decoder rejects it, matching how \uXXXX surrogate escapes
+                // are handled in the lexer.
+                bool valid_pair = false;
+                if (wc <= 0xDBFF && JSON_HEDLEY_UNLIKELY(!input.empty()))
                 {
                     const auto wc2 = static_cast<unsigned int>(input.get_character());
-                    const auto charcode = 0x10000u + (((static_cast<unsigned int>(wc) & 0x3FFu) << 10u) | (wc2 & 0x3FFu));
-                    utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(0xF0u | (charcode >> 18u));
-                    utf8_bytes[1] = static_cast<std::char_traits<char>::int_type>(0x80u | ((charcode >> 12u) & 0x3Fu));
-                    utf8_bytes[2] = static_cast<std::char_traits<char>::int_type>(0x80u | ((charcode >> 6u) & 0x3Fu));
-                    utf8_bytes[3] = static_cast<std::char_traits<char>::int_type>(0x80u | (charcode & 0x3Fu));
-                    utf8_bytes_filled = 4;
+                    if (0xDC00 <= wc2 && wc2 <= 0xDFFF)
+                    {
+                        const auto charcode = 0x10000u + (((static_cast<unsigned int>(wc) & 0x3FFu) << 10u) | (wc2 & 0x3FFu));
+                        utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(0xF0u | (charcode >> 18u));
+                        utf8_bytes[1] = static_cast<std::char_traits<char>::int_type>(0x80u | ((charcode >> 12u) & 0x3Fu));
+                        utf8_bytes[2] = static_cast<std::char_traits<char>::int_type>(0x80u | ((charcode >> 6u) & 0x3Fu));
+                        utf8_bytes[3] = static_cast<std::char_traits<char>::int_type>(0x80u | (charcode & 0x3Fu));
+                        utf8_bytes_filled = 4;
+                        valid_pair = true;
+                    }
                 }
-                else
+
+                if (!valid_pair)
                 {
                     utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(wc);
                     utf8_bytes_filled = 1;

include/nlohmann/detail/output/output_adapters.hpp

@@ -13,6 +13,7 @@
 #include <iterator> // back_inserter
 #include <memory> // shared_ptr, make_shared
 #include <string> // basic_string
+#include <utility> // move
 #include <vector> // vector
 
 #ifndef JSON_NO_IO
@@ -118,6 +119,72 @@ class output_string_adapter : public output_adapter_protocol<CharType>
     StringType& str;
 };
 
+/// @brief non-virtual output sink writing into a std::vector
+///
+/// Unlike output_vector_adapter, this sink is not part of the virtual
+/// output_adapter_protocol hierarchy: it is passed to binary_writer by value as
+/// a template parameter, so write_character()/write_characters() are ordinary
+/// (inlinable) calls with no vtable lookup and no shared_ptr. It is used for the
+/// common `to_cbor`/`to_msgpack`/... into a std::vector.
+template<typename CharType, typename AllocatorType = std::allocator<CharType>>
+class output_vector_sink
+{
+  public:
+    explicit output_vector_sink(std::vector<CharType, AllocatorType>& vec) noexcept
+        : v(vec)
+    {}
+
+    void write_character(CharType c)
+    {
+        v.push_back(c);
+    }
+
+    // no JSON_HEDLEY_NON_NULL here: binary_writer legitimately passes a null
+    // pointer with length 0 for empty strings/binary values. Appending an empty
+    // range is a no-op; the type-erased path tolerates this via the (unattributed)
+    // virtual base, and the concrete sink must do the same.
+    void write_characters(const CharType* s, std::size_t length)
+    {
+        v.insert(v.end(), s, s + length);
+    }
+
+  private:
+    std::vector<CharType, AllocatorType>& v;
+};
+
+/// @brief output sink forwarding to a type-erased output adapter
+///
+/// Wraps the polymorphic output_adapter_t so the same binary_writer template can
+/// also target arbitrary adapters (output streams, strings, user-provided
+/// adapters) via the `output_adapter`-based overloads. Each write still goes
+/// through one virtual call, exactly as before; only the concrete sinks above
+/// avoid it.
+template<typename CharType>
+class output_adapter_sink
+{
+  public:
+    explicit output_adapter_sink(output_adapter_t<CharType> adapter)
+        : oa(std::move(adapter))
+    {
+        JSON_ASSERT(oa);
+    }
+
+    void write_character(CharType c)
+    {
+        oa->write_character(c);
+    }
+
+    // no JSON_HEDLEY_NON_NULL: forwards (null, 0) for empty payloads, exactly as
+    // the type-erased path already did before this sink existed
+    void write_characters(const CharType* s, std::size_t length)
+    {
+        oa->write_characters(s, length);
+    }
+
+  private:
+    output_adapter_t<CharType> oa = nullptr;
+};
+
 template<typename CharType, typename StringType = std::basic_string<CharType>>
 class output_adapter
 {

include/nlohmann/json.hpp

@@ -140,7 +140,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     friend ::nlohmann::detail::serializer<basic_json>;
     template<typename BasicJsonType>
     friend class ::nlohmann::detail::iter_impl;
-    template<typename BasicJsonType, typename CharType>
+    template<typename BasicJsonType, typename CharType, typename OutputSinkType>
     friend class ::nlohmann::detail::binary_writer;
     template<typename BasicJsonType, typename InputType, typename SAX>
     friend class ::nlohmann::detail::binary_reader;
@@ -4327,7 +4327,9 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     static std::vector<std::uint8_t> to_cbor(const basic_json& j)
     {
         std::vector<std::uint8_t> result;
-        to_cbor(j, result);
+        result.reserve(detail::binary_reserve_hint(j));
+        detail::binary_writer<basic_json, std::uint8_t, detail::output_vector_sink<std::uint8_t>>(
+            detail::output_vector_sink<std::uint8_t>(result)).write_cbor(j);
         return result;
     }
 
@@ -4350,7 +4352,9 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     static std::vector<std::uint8_t> to_msgpack(const basic_json& j)
     {
         std::vector<std::uint8_t> result;
-        to_msgpack(j, result);
+        result.reserve(detail::binary_reserve_hint(j));
+        detail::binary_writer<basic_json, std::uint8_t, detail::output_vector_sink<std::uint8_t>>(
+            detail::output_vector_sink<std::uint8_t>(result)).write_msgpack(j);
         return result;
     }
 
@@ -4375,7 +4379,9 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
             const bool use_type = false)
     {
         std::vector<std::uint8_t> result;
-        to_ubjson(j, result, use_size, use_type);
+        result.reserve(detail::binary_reserve_hint(j));
+        detail::binary_writer<basic_json, std::uint8_t, detail::output_vector_sink<std::uint8_t>>(
+            detail::output_vector_sink<std::uint8_t>(result)).write_ubjson(j, use_size, use_type);
         return result;
     }
 
@@ -4403,7 +4409,9 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
             const bjdata_version_t version = bjdata_version_t::draft2)
     {
         std::vector<std::uint8_t> result;
-        to_bjdata(j, result, use_size, use_type, version);
+        result.reserve(detail::binary_reserve_hint(j));
+        detail::binary_writer<basic_json, std::uint8_t, detail::output_vector_sink<std::uint8_t>>(
+            detail::output_vector_sink<std::uint8_t>(result)).write_ubjson(j, use_size, use_type, true, true, version);
         return result;
     }
 
@@ -4430,7 +4438,9 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     static std::vector<std::uint8_t> to_bson(const basic_json& j)
     {
         std::vector<std::uint8_t> result;
-        to_bson(j, result);
+        result.reserve(detail::binary_reserve_hint(j));
+        detail::binary_writer<basic_json, std::uint8_t, detail::output_vector_sink<std::uint8_t>>(
+            detail::output_vector_sink<std::uint8_t>(result)).write_bson(j);
         return result;
     }
 

tests/src/unit-bjdata.cpp

@@ -2721,6 +2721,19 @@ TEST_CASE("BJData")
                 CHECK_THROWS_WITH_AS(_ = json::from_bjdata(v), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing BJData string: expected length type specification (U, i, u, I, m, l, M, L); last byte: 0x31", json::parse_error&);
             }
 
+            SECTION("negative length")
+            {
+                json _;
+
+                std::vector<uint8_t> const vi = {'S', 'i', 0xFF};
+                CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vi), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing BJData string: string length must not be negative", json::parse_error&);
+                CHECK(json::from_bjdata(vi, true, false).is_discarded());
+
+                std::vector<uint8_t> const vl = {'S', 'l', 0xFF, 0xFF, 0xFF, 0xFF};
+                CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vl), "[json.exception.parse_error.113] parse error at byte 6: syntax error while parsing BJData string: string length must not be negative", json::parse_error&);
+                CHECK(json::from_bjdata(vl, true, false).is_discarded());
+            }
+
             SECTION("parse bjdata markers in ubjson")
             {
                 // create a single-character string for all number types

tests/src/unit-ubjson.cpp

@@ -1862,6 +1862,31 @@ TEST_CASE("UBJSON")
                 json _;
                 CHECK_THROWS_WITH_AS(_ = json::from_ubjson(v), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing UBJSON string: expected length type specification (U, i, I, l, L); last byte: 0x31", json::parse_error&);
             }
+
+            SECTION("negative length")
+            {
+                json _;
+
+                std::vector<uint8_t> const vi = {'S', 'i', 0xFF};
+                CHECK_THROWS_WITH_AS(_ = json::from_ubjson(vi), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing UBJSON string: string length must not be negative", json::parse_error&);
+                CHECK(json::from_ubjson(vi, true, false).is_discarded());
+
+                std::vector<uint8_t> const vI = {'S', 'I', 0xFF, 0xFF};
+                CHECK_THROWS_WITH_AS(_ = json::from_ubjson(vI), "[json.exception.parse_error.113] parse error at byte 4: syntax error while parsing UBJSON string: string length must not be negative", json::parse_error&);
+                CHECK(json::from_ubjson(vI, true, false).is_discarded());
+
+                std::vector<uint8_t> const vl = {'S', 'l', 0xFF, 0xFF, 0xFF, 0xFF};
+                CHECK_THROWS_WITH_AS(_ = json::from_ubjson(vl), "[json.exception.parse_error.113] parse error at byte 6: syntax error while parsing UBJSON string: string length must not be negative", json::parse_error&);
+                CHECK(json::from_ubjson(vl, true, false).is_discarded());
+
+                std::vector<uint8_t> const vL = {'S', 'L', 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF};
+                CHECK_THROWS_WITH_AS(_ = json::from_ubjson(vL), "[json.exception.parse_error.113] parse error at byte 10: syntax error while parsing UBJSON string: string length must not be negative", json::parse_error&);
+                CHECK(json::from_ubjson(vL, true, false).is_discarded());
+
+                // a length of zero remains valid and yields an empty string
+                std::vector<uint8_t> const v0 = {'S', 'i', 0};
+                CHECK(json::from_ubjson(v0) == json(""));
+            }
         }
 
         SECTION("array")

tests/src/unit-wstring.cpp

@@ -53,6 +53,27 @@ TEST_CASE("wide strings")
             std::wstring const w = L"\"\xDBFF";
             json _;
             CHECK_THROWS_AS(_ = json::parse(w), json::parse_error&);
+
+            // the exact message depends on the width of wchar_t: a 16-bit
+            // wchar_t passes the lone surrogate to the UTF-8 decoder unchanged
+            // (rejected as a single ill-formed byte at column 2), while a
+            // 32-bit wchar_t first encodes it as an ill-formed three-byte
+            // sequence (rejected one byte later, at column 3)
+            const char* const error_low_surrogate = sizeof(wchar_t) == 2
+                                                    ? "[json.exception.parse_error.101] parse error at line 1, column 2: syntax error while parsing value - invalid string: ill-formed UTF-8 byte; last read: '\"<U+0000>'"
+                                                    : "[json.exception.parse_error.101] parse error at line 1, column 3: syntax error while parsing value - invalid string: ill-formed UTF-8 byte; last read: '\"\xED\xB0'";
+            const char* const error_high_surrogate = sizeof(wchar_t) == 2
+                ? "[json.exception.parse_error.101] parse error at line 1, column 2: syntax error while parsing value - invalid string: ill-formed UTF-8 byte; last read: '\"<U+0000>'"
+                : "[json.exception.parse_error.101] parse error at line 1, column 3: syntax error while parsing value - invalid string: ill-formed UTF-8 byte; last read: '\"\xED\xA0'";
+
+            // a lone low surrogate cannot start a pair
+            CHECK_THROWS_WITH_AS(_ = json::parse(std::wstring{L'"', static_cast<wchar_t>(0xDC00), L'"'}), error_low_surrogate, json::parse_error&);
+            // a high surrogate followed by a non-low-surrogate unit is invalid
+            CHECK_THROWS_WITH_AS(_ = json::parse(std::wstring{L'"', static_cast<wchar_t>(0xD800), L'a', L'"'}), error_high_surrogate, json::parse_error&);
+            // a lone low surrogate must not swallow the following unit: pairing
+            // it with any second unit would produce valid UTF-8, so the error
+            // has to report an ill-formed byte at the surrogate's own position
+            CHECK_THROWS_WITH_AS(_ = json::parse(std::wstring{L'"', static_cast<wchar_t>(0xDC00), L'a', L'"'}), error_low_surrogate, json::parse_error&);
         }
     }
 
@@ -68,11 +89,22 @@ TEST_CASE("wide strings")
 
     SECTION("invalid std::u16string")
     {
-        if (wstring_is_utf16())
+        if (u16string_is_utf16())
         {
             std::u16string const w = u"\"\xDBFF";
             json _;
             CHECK_THROWS_AS(_ = json::parse(w), json::parse_error&);
+
+            // a lone low surrogate cannot start a pair
+            CHECK_THROWS_WITH_AS(_ = json::parse(std::u16string{u'"', 0xDC00, u'"'}), "[json.exception.parse_error.101] parse error at line 1, column 2: syntax error while parsing value - invalid string: ill-formed UTF-8 byte; last read: '\"<U+0000>'", json::parse_error&);
+            // a high surrogate followed by a non-low-surrogate unit is invalid
+            CHECK_THROWS_WITH_AS(_ = json::parse(std::u16string{u'"', 0xD800, u'a', u'"'}), "[json.exception.parse_error.101] parse error at line 1, column 2: syntax error while parsing value - invalid string: ill-formed UTF-8 byte; last read: '\"<U+0000>'", json::parse_error&);
+            // a lone low surrogate must not swallow the following unit: pairing
+            // it with any second unit would produce valid UTF-8, so the error
+            // has to report an ill-formed byte at the surrogate's own position
+            CHECK_THROWS_WITH_AS(_ = json::parse(std::u16string{u'"', 0xDC00, u'a', u'"'}), "[json.exception.parse_error.101] parse error at line 1, column 2: syntax error while parsing value - invalid string: ill-formed UTF-8 byte; last read: '\"<U+0000>'", json::parse_error&);
+            // a valid surrogate pair is still decoded (U+1F600)
+            CHECK(json::parse(std::u16string{u'"', 0xD83D, 0xDE00, u'"'}).get<std::string>() == "\xF0\x9F\x98\x80");
         }
     }