Add benchmarks for the binary readers

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

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

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

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

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

.github/workflows/check_amalgamation.yml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 
@@ -34,7 +34,7 @@ jobs:
 
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 

.github/workflows/cifuzz.yml

@@ -9,7 +9,7 @@ jobs:
     runs-on: ubuntu-22.04
     steps:
     - name: Harden Runner
-      uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
+      uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
       with:
         egress-policy: audit
 

.github/workflows/codeql-analysis.yml

@@ -27,7 +27,7 @@ jobs:
 
     steps:
     - name: Harden Runner
-      uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
+      uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
       with:
         egress-policy: audit
 

.github/workflows/comment_check_amalgamation.yml

@@ -19,7 +19,7 @@ jobs:
       pull-requests: write
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 

.github/workflows/dependency-review.yml

@@ -17,7 +17,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 

.github/workflows/flawfinder.yml

@@ -27,7 +27,7 @@ jobs:
       security-events: write
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 

.github/workflows/labeler.yml

@@ -17,7 +17,7 @@ jobs:
 
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 

.github/workflows/publish_documentation.yml

@@ -26,7 +26,7 @@ jobs:
     runs-on: ubuntu-22.04
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 

.github/workflows/scorecards.yml

@@ -36,7 +36,7 @@ jobs:
 
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 

.github/workflows/semgrep.yml

@@ -32,7 +32,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 

.github/workflows/stale.yml

@@ -16,7 +16,7 @@ jobs:
 
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 

.github/workflows/ubuntu.yml

@@ -35,7 +35,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 
@@ -60,7 +60,7 @@ jobs:
         target: [ci_test_amalgamation, ci_test_single_header, ci_cppcheck, ci_cpplint, ci_reproducible_tests, ci_non_git_tests, ci_offline_testdata, ci_reuse_compliance, ci_test_valgrind]
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 
@@ -118,7 +118,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 
@@ -369,7 +369,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 
@@ -392,7 +392,7 @@ jobs:
         target: [ci_test_examples, ci_test_build_documentation]
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
+        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
         with:
           egress-policy: audit
 

include/nlohmann/detail/input/lexer.hpp

@@ -149,11 +149,10 @@ class lexer : public lexer_base<BasicJsonType>
   public:
     using token_type = typename lexer_base<BasicJsonType>::token_type;
 
-    explicit lexer(InputAdapterType&& adapter, bool ignore_comments_ = false, bool discard_number_values_ = false) noexcept
+    explicit lexer(InputAdapterType&& adapter, bool ignore_comments_ = 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
@@ -1280,58 +1279,6 @@ 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;
 
@@ -1807,13 +1754,6 @@ 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

@@ -72,10 +72,9 @@ 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, discard_number_values_)
+        , m_lexer(std::move(adapter), ignore_comments)
         , allow_exceptions(allow_exceptions_)
         , ignore_trailing_commas(ignore_trailing_commas_)
     {

include/nlohmann/json.hpp

@@ -164,12 +164,11 @@ 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, discard_number_values);
+               std::move(cb), allow_exceptions, ignore_comments, ignore_trailing_commas);
     }
 
   private:
@@ -4134,7 +4133,7 @@ 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, true).accept(true);
+        return parser(detail::input_adapter(std::forward<InputType>(i)), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true);
     }
 
     /// @brief check if the input is valid JSON (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4145,7 +4144,7 @@ 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, true).accept(true);
+        return parser(detail::input_adapter(std::move(first), std::move(last)), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true);
     }
 
     JSON_HEDLEY_WARN_UNUSED_RESULT
@@ -4154,7 +4153,7 @@ 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, true).accept(true);
+        return parser(i.get(), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true);
     }
 
     /// @brief generate SAX events

single_include/nlohmann/json.hpp

@@ -7932,11 +7932,10 @@ class lexer : public lexer_base<BasicJsonType>
   public:
     using token_type = typename lexer_base<BasicJsonType>::token_type;
 
-    explicit lexer(InputAdapterType&& adapter, bool ignore_comments_ = false, bool discard_number_values_ = false) noexcept
+    explicit lexer(InputAdapterType&& adapter, bool ignore_comments_ = 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
@@ -9063,58 +9062,6 @@ 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;
 
@@ -9590,13 +9537,6 @@ 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
@@ -14103,10 +14043,9 @@ 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, discard_number_values_)
+        , m_lexer(std::move(adapter), ignore_comments)
         , allow_exceptions(allow_exceptions_)
         , ignore_trailing_commas(ignore_trailing_commas_)
     {
@@ -21653,12 +21592,11 @@ 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, discard_number_values);
+            std::move(cb), allow_exceptions, ignore_comments, ignore_trailing_commas);
     }
 
   private:
@@ -25623,7 +25561,7 @@ 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, true).accept(true);
+        return parser(detail::input_adapter(std::forward<InputType>(i)), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true);
     }
 
     /// @brief check if the input is valid JSON (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -25634,7 +25572,7 @@ 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, true).accept(true);
+        return parser(detail::input_adapter(std::move(first), std::move(last)), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true);
     }
 
     JSON_HEDLEY_WARN_UNUSED_RESULT
@@ -25643,7 +25581,7 @@ 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, true).accept(true);
+        return parser(i.get(), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true);
     }
 
     /// @brief generate SAX events

tests/benchmarks/src/benchmarks.cpp

@@ -214,4 +214,323 @@ static void BinaryToCbor(benchmark::State& state)
 }
 BENCHMARK(BinaryToCbor)->RangeMultiplier(2)->Range(8, 8 << 12);
 
+//////////////////////////////////////////////////////////////////////////////
+// parse binary formats
+//////////////////////////////////////////////////////////////////////////////
+
+// Only MessagePack had a read benchmark (FromMsgpack above, left untouched so
+// its numbers stay comparable across releases). The benchmarks below cover the
+// other formats, and read from a contiguous buffer as well as from a FILE*:
+// most callers pass a container, and the two adapters compile to different
+// code. The test data repository ships JSON only, so the input for each is
+// derived at setup time by serializing a parsed test file.
+
+/// binary format to benchmark; the _optimized variants add UBJSON/BJData size
+/// and type annotations, which the readers handle in a separate code path
+enum class binary_format
+{
+    cbor,
+    msgpack,
+    ubjson,
+    ubjson_optimized,
+    bjdata,
+    bjdata_optimized,
+    bson
+};
+
+static std::vector<std::uint8_t> to_binary(const json& j, const binary_format format)
+{
+    switch (format)
+    {
+        case binary_format::cbor:
+            return json::to_cbor(j);
+        case binary_format::msgpack:
+            return json::to_msgpack(j);
+        case binary_format::ubjson:
+            return json::to_ubjson(j);
+        case binary_format::ubjson_optimized:
+            return json::to_ubjson(j, true, true);
+        case binary_format::bjdata:
+            return json::to_bjdata(j);
+        case binary_format::bjdata_optimized:
+            return json::to_bjdata(j, true, true);
+        case binary_format::bson:
+        default:
+            return json::to_bson(j);
+    }
+}
+
+static json from_binary(const std::vector<std::uint8_t>& bytes, const binary_format format)
+{
+    switch (format)
+    {
+        case binary_format::cbor:
+            return json::from_cbor(bytes);
+        case binary_format::msgpack:
+            return json::from_msgpack(bytes);
+        case binary_format::ubjson:
+        case binary_format::ubjson_optimized:
+            return json::from_ubjson(bytes);
+        case binary_format::bjdata:
+        case binary_format::bjdata_optimized:
+            return json::from_bjdata(bytes);
+        case binary_format::bson:
+        default:
+            return json::from_bson(bytes);
+    }
+}
+
+static json from_binary(std::FILE* file, const binary_format format)
+{
+    switch (format)
+    {
+        case binary_format::cbor:
+            return json::from_cbor(file);
+        case binary_format::msgpack:
+            return json::from_msgpack(file);
+        case binary_format::ubjson:
+        case binary_format::ubjson_optimized:
+            return json::from_ubjson(file);
+        case binary_format::bjdata:
+        case binary_format::bjdata_optimized:
+            return json::from_bjdata(file);
+        case binary_format::bson:
+        default:
+            return json::from_bson(file);
+    }
+}
+
+/*!
+@brief serialize a parsed test file to @a format
+
+Returns an empty vector and marks the benchmark as skipped if the file cannot
+be represented in the format, rather than letting the exception escape: BSON
+requires an object at the top level, and several test files are arrays.
+*/
+static std::vector<std::uint8_t> binary_input(benchmark::State& state, const char* filename, const binary_format format)
+{
+    std::ifstream f(filename);
+    std::string const str((std::istreambuf_iterator<char>(f)), std::istreambuf_iterator<char>());
+    const json j = json::parse(str);
+
+    if (format == binary_format::bson && !j.is_object())
+    {
+        state.SkipWithError("BSON requires an object at the top level");
+        return {};
+    }
+
+    return to_binary(j, format);
+}
+
+static void FromBinaryBuffer(benchmark::State& state, const char* filename, const binary_format format)
+{
+    const std::vector<std::uint8_t> bytes = binary_input(state, filename, format);
+    if (bytes.empty())
+    {
+        return;
+    }
+
+    for (auto _ : state)
+    {
+        // the value is destroyed outside the timed section, because destroying
+        // a large DOM is not what this benchmark measures
+        state.PauseTiming();
+        auto* j = new json();
+        state.ResumeTiming();
+
+        *j = from_binary(bytes, format);
+
+        state.PauseTiming();
+        delete j;
+        state.ResumeTiming();
+    }
+
+    state.SetBytesProcessed(state.iterations() * bytes.size());
+}
+
+BENCHMARK_CAPTURE(FromBinaryBuffer, cbor / jeopardy, TEST_DATA_DIRECTORY "/jeopardy/jeopardy.json", binary_format::cbor);
+BENCHMARK_CAPTURE(FromBinaryBuffer, cbor / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::cbor);
+BENCHMARK_CAPTURE(FromBinaryBuffer, cbor / citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json", binary_format::cbor);
+BENCHMARK_CAPTURE(FromBinaryBuffer, cbor / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::cbor);
+BENCHMARK_CAPTURE(FromBinaryBuffer, cbor / floats, TEST_DATA_DIRECTORY "/regression/floats.json", binary_format::cbor);
+BENCHMARK_CAPTURE(FromBinaryBuffer, cbor / signed_ints, TEST_DATA_DIRECTORY "/regression/signed_ints.json", binary_format::cbor);
+BENCHMARK_CAPTURE(FromBinaryBuffer, msgpack / jeopardy, TEST_DATA_DIRECTORY "/jeopardy/jeopardy.json", binary_format::msgpack);
+BENCHMARK_CAPTURE(FromBinaryBuffer, msgpack / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::msgpack);
+BENCHMARK_CAPTURE(FromBinaryBuffer, msgpack / citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json", binary_format::msgpack);
+BENCHMARK_CAPTURE(FromBinaryBuffer, msgpack / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::msgpack);
+BENCHMARK_CAPTURE(FromBinaryBuffer, ubjson / jeopardy, TEST_DATA_DIRECTORY "/jeopardy/jeopardy.json", binary_format::ubjson);
+BENCHMARK_CAPTURE(FromBinaryBuffer, ubjson / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::ubjson);
+BENCHMARK_CAPTURE(FromBinaryBuffer, ubjson / citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json", binary_format::ubjson);
+BENCHMARK_CAPTURE(FromBinaryBuffer, ubjson / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::ubjson);
+BENCHMARK_CAPTURE(FromBinaryBuffer, ubjson_optimized / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::ubjson_optimized);
+BENCHMARK_CAPTURE(FromBinaryBuffer, ubjson_optimized / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::ubjson_optimized);
+BENCHMARK_CAPTURE(FromBinaryBuffer, bjdata / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::bjdata);
+BENCHMARK_CAPTURE(FromBinaryBuffer, bjdata / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::bjdata);
+BENCHMARK_CAPTURE(FromBinaryBuffer, bjdata_optimized / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::bjdata_optimized);
+BENCHMARK_CAPTURE(FromBinaryBuffer, bjdata_optimized / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::bjdata_optimized);
+// BSON requires an object at the top level, so the array-rooted test files
+// (jeopardy and the regression files) cannot be captured here
+BENCHMARK_CAPTURE(FromBinaryBuffer, bson / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::bson);
+BENCHMARK_CAPTURE(FromBinaryBuffer, bson / citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json", binary_format::bson);
+BENCHMARK_CAPTURE(FromBinaryBuffer, bson / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::bson);
+
+static void FromBinaryFile(benchmark::State& state, const char* filename, const binary_format format)
+{
+    const std::vector<std::uint8_t> bytes = binary_input(state, filename, format);
+    if (bytes.empty())
+    {
+        return;
+    }
+
+    const char* tmp = "benchmark_input.bin";
+    std::ofstream o(tmp, std::ios::binary);
+    o.write(reinterpret_cast<const char*>(bytes.data()), static_cast<std::streamsize>(bytes.size()));
+    o.flush();
+    o.close();
+
+    for (auto _ : state)
+    {
+        state.PauseTiming();
+        auto* j = new json();
+        auto* file = std::fopen(tmp, "rb");
+        state.ResumeTiming();
+
+        *j = from_binary(file, format);
+
+        state.PauseTiming();
+        std::fclose(file);
+        delete j;
+        state.ResumeTiming();
+    }
+
+    state.SetBytesProcessed(state.iterations() * bytes.size());
+}
+
+BENCHMARK_CAPTURE(FromBinaryFile, cbor / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::cbor);
+BENCHMARK_CAPTURE(FromBinaryFile, cbor / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::cbor);
+BENCHMARK_CAPTURE(FromBinaryFile, ubjson / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::ubjson);
+BENCHMARK_CAPTURE(FromBinaryFile, ubjson / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::ubjson);
+BENCHMARK_CAPTURE(FromBinaryFile, bjdata / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::bjdata);
+BENCHMARK_CAPTURE(FromBinaryFile, bson / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::bson);
+
+//////////////////////////////////////////////////////////////////////////////
+// parse binary formats: value shapes
+//////////////////////////////////////////////////////////////////////////////
+
+// The test files above are wide and shallow, but the readers' cost is per
+// container, so these cover the shapes that stress the container handling
+// itself. Every shape is wrapped in an object so that BSON, which requires an
+// object at the top level, measures the same value as the other formats.
+
+/// deeply nested arrays: one container per level, no other work
+static json make_nested()
+{
+    json nested = json::array();
+    json* p = &nested;
+    for (std::size_t i = 1; i < 1000; ++i)
+    {
+        p->push_back(json::array());
+        p = &p->operator[](0);
+    }
+
+    json j = json::object();
+    j["data"] = std::move(nested);
+    return j;
+}
+
+/// many sibling containers: maximum container churn, minimum nesting
+static json make_containers()
+{
+    json data = json::array();
+    for (std::size_t i = 0; i < 100000; ++i)
+    {
+        data.push_back(json::array({1, 2}));
+    }
+
+    json j = json::object();
+    j["data"] = std::move(data);
+    return j;
+}
+
+/// one flat array of numbers: the scalar decoding path, which must not move
+static json make_scalars()
+{
+    json data = json::array();
+    for (std::size_t i = 0; i < 1000000; ++i)
+    {
+        data.push_back(i);
+    }
+
+    json j = json::object();
+    j["data"] = std::move(data);
+    return j;
+}
+
+static void FromBinaryShape(benchmark::State& state, json (*build)(), const binary_format format)
+{
+    const std::vector<std::uint8_t> bytes = to_binary(build(), format);
+
+    for (auto _ : state)
+    {
+        state.PauseTiming();
+        auto* j = new json();
+        state.ResumeTiming();
+
+        *j = from_binary(bytes, format);
+
+        state.PauseTiming();
+        delete j;
+        state.ResumeTiming();
+    }
+
+    state.SetBytesProcessed(state.iterations() * bytes.size());
+}
+
+BENCHMARK_CAPTURE(FromBinaryShape, nested / cbor, make_nested, binary_format::cbor);
+BENCHMARK_CAPTURE(FromBinaryShape, nested / msgpack, make_nested, binary_format::msgpack);
+BENCHMARK_CAPTURE(FromBinaryShape, nested / ubjson, make_nested, binary_format::ubjson);
+BENCHMARK_CAPTURE(FromBinaryShape, nested / bjdata, make_nested, binary_format::bjdata);
+BENCHMARK_CAPTURE(FromBinaryShape, nested / bson, make_nested, binary_format::bson);
+BENCHMARK_CAPTURE(FromBinaryShape, containers / cbor, make_containers, binary_format::cbor);
+BENCHMARK_CAPTURE(FromBinaryShape, containers / msgpack, make_containers, binary_format::msgpack);
+BENCHMARK_CAPTURE(FromBinaryShape, containers / ubjson, make_containers, binary_format::ubjson);
+BENCHMARK_CAPTURE(FromBinaryShape, containers / ubjson_optimized, make_containers, binary_format::ubjson_optimized);
+BENCHMARK_CAPTURE(FromBinaryShape, containers / bjdata, make_containers, binary_format::bjdata);
+BENCHMARK_CAPTURE(FromBinaryShape, containers / bson, make_containers, binary_format::bson);
+// BSON names every array element, so a large array measures key generation
+// rather than scalar decoding and is left out here
+BENCHMARK_CAPTURE(FromBinaryShape, scalars / cbor, make_scalars, binary_format::cbor);
+BENCHMARK_CAPTURE(FromBinaryShape, scalars / msgpack, make_scalars, binary_format::msgpack);
+BENCHMARK_CAPTURE(FromBinaryShape, scalars / ubjson, make_scalars, binary_format::ubjson);
+BENCHMARK_CAPTURE(FromBinaryShape, scalars / bjdata, make_scalars, binary_format::bjdata);
+
+/*!
+@brief parse an indefinite-length CBOR string
+
+The writer never emits this form, so the input is assembled by hand: 0x7F
+opens the string, each chunk is a one-character string, and 0xFF closes it.
+*/
+static void FromCborChunkedString(benchmark::State& state, const std::size_t chunks)
+{
+    std::vector<std::uint8_t> bytes;
+    bytes.reserve(2 * chunks + 2);
+    bytes.push_back(0x7F);
+    for (std::size_t i = 0; i < chunks; ++i)
+    {
+        bytes.push_back(0x61); // string of length 1
+        bytes.push_back(0x61); // 'a'
+    }
+    bytes.push_back(0xFF);
+
+    for (auto _ : state)
+    {
+        json j = json::from_cbor(bytes);
+        benchmark::DoNotOptimize(j);
+    }
+
+    state.SetBytesProcessed(state.iterations() * bytes.size());
+}
+
+BENCHMARK_CAPTURE(FromCborChunkedString, 10000 chunks, 10000);
+
 BENCHMARK_MAIN();

tests/src/unit-class_parser.cpp

@@ -930,98 +930,6 @@ 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
-                    std::string wrapped = "[";
-                    wrapped += number;
-                    wrapped += ",";
-                    wrapped += number;
-                    wrapped += "]";
-                    CHECK(json::accept(wrapped) == expected);
-                }
-            }
         }
     }