json_view: keep accept()'s string check out of run()

Clang 23 made run() slower on files without escapes (mesh.pretty +15 %) when
the check-only string path was a separate call target. Dispatch inside
slow_string() instead, so the call in run() is the same as before, and skip
the SIMD run scan between escapes that follow each other (twitterescaped
1.11 -> 0.82 against the previous commit).

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

docs/mkdocs/docs/api/basic_json_document/accept.md

@@ -13,9 +13,15 @@ function never throws an exception for invalid input, and the returned `#!cpp bo
 is returned.
 
 The result is the same as that of `BasicJsonType::accept()` by design; the difference is how the check is made. This
-function runs the document's index builder (and discards the index), while `BasicJsonType::accept()` runs the SAX
-parser with a handler that ignores every event. Use this one if you go on to parse the same input with
-[`parse()`](parse.md) anyway, so that both use the same code; either is fine for a plain yes/no answer.
+function runs the document's builder, which checks the text as [`parse()`](parse.md) does, while
+`BasicJsonType::accept()` runs the SAX parser with a handler that ignores every event. Use this one if you go on to
+parse the same input with [`parse()`](parse.md) anyway, so that both use the same code; either is fine for a plain
+yes/no answer.
+
+When both `ignore_comments` and `ignore_trailing_commas` are `#!cpp false` (the default), the builder writes no index.
+With either option set, it builds the index as [`parse()`](parse.md) does and discards it: the result is the same, only
+the time differs. (Neither option needs the index; the variant that skips it exists only for the default options to
+keep the code size down.)
 
 ## Template parameters
 

include/nlohmann/detail/input/binary_reader.hpp

@@ -22,7 +22,6 @@
     #include <bit>  //byteswap
 #endif
 
-#include <nlohmann/detail/bit_ops.hpp>
 #include <nlohmann/detail/exceptions.hpp>
 #include <nlohmann/detail/input/input_adapters.hpp>
 #include <nlohmann/detail/input/json_sax.hpp>
@@ -742,13 +741,11 @@ class binary_reader
     bool get_cbor_negative_integer()
     {
         NumberType number{};
-        return get_number(number) && emit_cbor_negative_integer(number);
-    }
+        if (JSON_HEDLEY_UNLIKELY(!get_number(number)))
+        {
+            return false;
+        }
 
-    /// pass the CBOR negative integer -1 - @a number to the SAX parser
-    template<typename NumberType>
-    bool emit_cbor_negative_integer(const NumberType number)
-    {
         // the value is -1 - number, which fits into number_integer_t
         // whenever number does; the outer cast undoes the integral promotion
         // for number_integer_t types narrower than int
@@ -973,7 +970,7 @@ class binary_reader
             case 0x95:
             case 0x96:
             case 0x97:
-                return enter_cbor_array(conditional_static_cast<std::size_t>(static_cast<unsigned int>(current) & 0x1Fu));
+                return enter_array(conditional_static_cast<std::size_t>(static_cast<unsigned int>(current) & 0x1Fu));
 
             case 0x98: // array (one-byte uint8_t for n follows)
             case 0x99: // array (two-byte uint16_t for n follow)
@@ -982,7 +979,7 @@ class binary_reader
             {
                 std::uint64_t len{};
                 std::size_t size{};
-                return get_cbor_argument(len) && get_cbor_container_size(len, size, "array") && enter_cbor_array(size);
+                return get_cbor_argument(len) && get_cbor_container_size(len, size, "array") && enter_array(size);
             }
 
             case 0x9F: // array (indefinite length)
@@ -1136,10 +1133,16 @@ class binary_reader
                 return get_half_float(false);
 
             case 0xFA: // Single-Precision Float (four-byte IEEE 754)
-                return get_cbor_float<float>();
+            {
+                float number{};
+                return get_number(number) && emit_float(number);
+            }
 
             case 0xFB: // Double-Precision Float (eight-byte IEEE 754)
-                return get_cbor_float<double>();
+            {
+                double number{};
+                return get_number(number) && emit_float(number);
+            }
 
             default: // anything else (0xFF is handled inside the other types)
             {
@@ -1148,16 +1151,6 @@ class binary_reader
         }
     }
 
-    /// read a single- or double-precision float (kept out of
-    /// parse_cbor_value, which is inlined into parse_cbor_internal)
-    template<typename NumberType>
-    JSON_HEDLEY_NEVER_INLINE
-    bool get_cbor_float()
-    {
-        NumberType number{};
-        return get_number(number) && emit_float(number);
-    }
-
     /*!
     @brief reports a nested indefinite-length CBOR string or byte array
     @param[in] type_name  name of the rejected string type
@@ -1683,157 +1676,6 @@ class binary_reader
         return true;
     }
 
-    /*!
-    @brief read a big-endian number of type @a NumberType at @a data
-    */
-    template<typename NumberType>
-    NumberType load_big_endian(const unsigned char* data) const noexcept
-    {
-        NumberType result{};
-        std::memcpy(&result, data, sizeof(NumberType));
-        if (is_little_endian)
-        {
-            byte_swap(result);
-        }
-        return result;
-    }
-
-    /*!
-    @brief read the integers, floats, booleans, and nulls that follow in a
-           definite-length array, without the per-element bookkeeping of
-           @ref parse_cbor_internal
-
-    Stops at the end of the array, at any other kind of value, and when fewer
-    than 9 bytes (the longest of these values) are left in the input, leaving
-    those to @ref parse_cbor_value, which reads them the same way.
-
-    @param[in,out] remaining  the number of elements of the array not yet read
-    @return whether the SAX parser accepted the values
-    */
-    bool parse_cbor_scalar_run(std::size_t& remaining)
-    {
-        while (remaining != 0 && ia.bulk_remaining() >= 9)
-        {
-            const auto* const data = reinterpret_cast<const unsigned char*>(ia.bulk_data());
-            const unsigned char head = data[0];
-            std::size_t size = 0;
-            bool accepted = true;
-            switch (head)
-            {
-                case 0x18:
-                    size = 2;
-                    accepted = emit_unsigned(data[1]);
-                    break;
-                case 0x19:
-                    size = 3;
-                    accepted = emit_unsigned(load_big_endian<std::uint16_t>(data + 1));
-                    break;
-                case 0x1A:
-                    size = 5;
-                    accepted = emit_unsigned(load_big_endian<std::uint32_t>(data + 1));
-                    break;
-                case 0x1B:
-                    size = 9;
-                    accepted = emit_unsigned(load_big_endian<std::uint64_t>(data + 1));
-                    break;
-                case 0x38:
-                    size = 2;
-                    accepted = emit_cbor_negative_integer(data[1]);
-                    break;
-                case 0x39:
-                    size = 3;
-                    accepted = emit_cbor_negative_integer(load_big_endian<std::uint16_t>(data + 1));
-                    break;
-                case 0x3A:
-                    size = 5;
-                    accepted = emit_cbor_negative_integer(load_big_endian<std::uint32_t>(data + 1));
-                    break;
-                case 0x3B:
-                    size = 9;
-                    accepted = emit_cbor_negative_integer(load_big_endian<std::uint64_t>(data + 1));
-                    break;
-                case 0xF4:
-                    size = 1;
-                    accepted = sax->boolean(false);
-                    break;
-                case 0xF5:
-                    size = 1;
-                    accepted = sax->boolean(true);
-                    break;
-                case 0xF6:
-                    size = 1;
-                    accepted = sax->null();
-                    break;
-                case 0xFA:
-                    size = 5;
-                    accepted = emit_float(load_big_endian<float>(data + 1));
-                    break;
-                case 0xFB:
-                    size = 9;
-                    accepted = emit_float(load_big_endian<double>(data + 1));
-                    break;
-                default:
-                    if (head <= 0x17)
-                    {
-                        size = 1;
-                        accepted = sax->number_unsigned(static_cast<number_unsigned_t>(head));
-                    }
-                    else if (head >= 0x20 && head <= 0x37)
-                    {
-                        size = 1;
-                        accepted = sax->number_integer(static_cast<std::int8_t>(0x20 - 1 - head));
-                    }
-                    else
-                    {
-                        // any other value is read by parse_cbor_value
-                        return true;
-                    }
-                    break;
-            }
-            // as if read by get() and get_number(): current is the head byte
-            ia.bulk_skip(size);
-            chars_read += size;
-            current = head;
-            --remaining;
-            if (JSON_HEDLEY_UNLIKELY(!accepted))
-            {
-                return false;
-            }
-        }
-        return true;
-    }
-
-    /*!
-    @brief open a definite-length array and read the scalars it begins with
-           (see @ref parse_cbor_scalar_run)
-
-    Only the start of an array is tried, which covers arrays of numbers
-    (e.g. coordinates) but costs arrays of other values only one test, not one
-    per element.
-
-    @param[in] len  the number of elements
-    @return whether the SAX parser accepted the array and the values read
-    */
-    bool enter_cbor_array(const std::size_t len)
-    {
-        return enter_array(len) && (len == 0 || parse_cbor_array_start(std::integral_constant<bool, bulk_scan> {}));
-    }
-
-    /// read the scalars the array just opened begins with; out of line, so
-    /// that @ref parse_cbor_value stays small enough to be inlined into
-    /// @ref parse_cbor_internal
-    JSON_HEDLEY_NEVER_INLINE
-    bool parse_cbor_array_start(std::true_type /*bulk*/)
-    {
-        return parse_cbor_scalar_run(container_stack.back().remaining);
-    }
-
-    /// input that is not contiguous: every value is read by parse_cbor_value
-    bool parse_cbor_array_start(std::false_type /*bulk*/) const noexcept
-    {
-        return true;
-    }
-
     /*!
     @brief read a CBOR value and everything nested inside it
 
@@ -1863,7 +1705,6 @@ class binary_reader
                 // pop_back() below, which destroys the container_stack element
                 // it would otherwise alias
                 const container_frame top = container_stack.back();
-                const bool is_object = top.is_object;
                 bool at_end = false;
 
                 if (top.remaining != npos)
@@ -1875,7 +1716,7 @@ class binary_reader
                     {
                         // claim the element about to be read
                         --container_stack.back().remaining;
-                        if (is_object)
+                        if (top.is_object)
                         {
                             get();
                         }
@@ -1888,7 +1729,7 @@ class binary_reader
                     // Testing for it consumes a byte, which is the first byte
                     // of the next element when it is not one.
                     at_end = (get() == 0xFF);
-                    fetch = is_object;
+                    fetch = top.is_object;
                 }
 
                 if (at_end)
@@ -1905,7 +1746,7 @@ class binary_reader
                     continue;
                 }
 
-                if (is_object)
+                if (top.is_object)
                 {
                     if (JSON_HEDLEY_UNLIKELY(!skip_cbor_key_tags(tag_handler)))
                     {
@@ -2130,7 +1971,7 @@ class binary_reader
             case 0x9D:
             case 0x9E:
             case 0x9F:
-                return enter_msgpack_array(conditional_static_cast<std::size_t>(static_cast<unsigned int>(current) & 0x0Fu));
+                return enter_array(conditional_static_cast<std::size_t>(static_cast<unsigned int>(current) & 0x0Fu));
 
             // fixstr
             case 0xA0:
@@ -2261,13 +2102,13 @@ class binary_reader
             case 0xDC: // array 16
             {
                 std::uint16_t len{};
-                return get_number(len) && enter_msgpack_array(static_cast<std::size_t>(len));
+                return get_number(len) && enter_array(static_cast<std::size_t>(len));
             }
 
             case 0xDD: // array 32
             {
                 std::uint32_t len{};
-                return get_number(len) && enter_msgpack_array(conditional_static_cast<std::size_t>(len));
+                return get_number(len) && enter_array(conditional_static_cast<std::size_t>(len));
             }
 
             case 0xDE: // map 16
@@ -2609,138 +2450,6 @@ class binary_reader
         }
     }
 
-    /*!
-    @brief read the integers, floats, booleans, and nils that follow in a
-           MessagePack array, without the per-element bookkeeping of
-           @ref parse_msgpack_internal
-
-    Stops at the end of the array, at any other kind of value, and when fewer
-    than 9 bytes (the longest of these values) are left in the input, leaving
-    those to @ref parse_msgpack_value, which reads them the same way.
-
-    @param[in,out] remaining  the number of elements of the array not yet read
-    @return whether the SAX parser accepted the values
-    */
-    bool parse_msgpack_scalar_run(std::size_t& remaining)
-    {
-        while (remaining != 0 && ia.bulk_remaining() >= 9)
-        {
-            const auto* const data = reinterpret_cast<const unsigned char*>(ia.bulk_data());
-            const unsigned char head = data[0];
-            std::size_t size = 0;
-            bool accepted = true;
-            switch (head)
-            {
-                case 0xC0: // nil
-                    size = 1;
-                    accepted = sax->null();
-                    break;
-                case 0xC2: // false
-                    size = 1;
-                    accepted = sax->boolean(false);
-                    break;
-                case 0xC3: // true
-                    size = 1;
-                    accepted = sax->boolean(true);
-                    break;
-                case 0xCA: // float 32
-                    size = 5;
-                    accepted = emit_float(load_big_endian<float>(data + 1));
-                    break;
-                case 0xCB: // float 64
-                    size = 9;
-                    accepted = emit_float(load_big_endian<double>(data + 1));
-                    break;
-                case 0xCC: // uint 8
-                    size = 2;
-                    accepted = emit_unsigned(data[1]);
-                    break;
-                case 0xCD: // uint 16
-                    size = 3;
-                    accepted = emit_unsigned(load_big_endian<std::uint16_t>(data + 1));
-                    break;
-                case 0xCE: // uint 32
-                    size = 5;
-                    accepted = emit_unsigned(load_big_endian<std::uint32_t>(data + 1));
-                    break;
-                case 0xCF: // uint 64
-                    size = 9;
-                    accepted = emit_unsigned(load_big_endian<std::uint64_t>(data + 1));
-                    break;
-                case 0xD0: // int 8
-                    size = 2;
-                    accepted = emit_signed(static_cast<std::int8_t>(data[1]));
-                    break;
-                case 0xD1: // int 16
-                    size = 3;
-                    accepted = emit_signed(load_big_endian<std::int16_t>(data + 1));
-                    break;
-                case 0xD2: // int 32
-                    size = 5;
-                    accepted = emit_signed(load_big_endian<std::int32_t>(data + 1));
-                    break;
-                case 0xD3: // int 64
-                    size = 9;
-                    accepted = emit_signed(load_big_endian<std::int64_t>(data + 1));
-                    break;
-                default:
-                    if (head <= 0x7F)
-                    {
-                        // positive fixint
-                        size = 1;
-                        accepted = sax->number_unsigned(static_cast<number_unsigned_t>(head));
-                    }
-                    else if (head >= 0xE0)
-                    {
-                        // negative fixint
-                        size = 1;
-                        accepted = sax->number_integer(static_cast<std::int8_t>(head));
-                    }
-                    else
-                    {
-                        // any other value is read by parse_msgpack_value
-                        return true;
-                    }
-                    break;
-            }
-            // as if read by get() and get_number(): current is the last byte
-            ia.bulk_skip(size);
-            chars_read += size;
-            current = data[size - 1];
-            --remaining;
-            if (JSON_HEDLEY_UNLIKELY(!accepted))
-            {
-                return false;
-            }
-        }
-        return true;
-    }
-
-    /*!
-    @brief open a MessagePack array and read the scalars it begins with (see
-           @ref parse_msgpack_scalar_run)
-    @param[in] len  the number of elements
-    @return whether the SAX parser accepted the array and the values read
-    */
-    bool enter_msgpack_array(const std::size_t len)
-    {
-        return enter_array(len) && (len == 0 || parse_msgpack_array_start(std::integral_constant<bool, bulk_scan> {}));
-    }
-
-    /// read the scalars the array just opened begins with; out of line, so
-    /// that @ref parse_msgpack_value stays small enough to be inlined
-    JSON_HEDLEY_NEVER_INLINE
-    bool parse_msgpack_array_start(std::true_type /*bulk*/)
-    {
-        return parse_msgpack_scalar_run(container_stack.back().remaining);
-    }
-
-    /// input that is not contiguous: every value is read by parse_msgpack_value
-    bool parse_msgpack_array_start(std::false_type /*bulk*/) const noexcept
-    {
-        return true;
-    }
-
     /*!
     @brief read a MessagePack value and everything nested inside it
 
@@ -3546,107 +3255,6 @@ class binary_reader
         return unexpected_byte("invalid byte", "value");
     }
 
-    /*!
-    @brief read the elements of an optimized array of numbers (type marker
-           @a type) that are in the input, in one loop, without the
-           per-element bookkeeping of @ref parse_ubjson_internal
-
-    Values are emitted as @ref get_ubjson_value emits them. Types other than
-    the fixed-size integers and floats are left to @ref get_ubjson_value, as
-    are the elements the input ends before.
-
-    @param[in,out] remaining  the number of elements not yet read
-    @param[in] type  the type marker of the elements
-    @return whether the SAX parser accepted the values
-    */
-    JSON_HEDLEY_NEVER_INLINE
-    bool parse_ubjson_typed_run(std::size_t& remaining, const char_int_type type, std::true_type /*bulk*/)
-    {
-        const bool bjdata = input_format == input_format_t::bjdata;
-        switch (type)
-        {
-            case 'U':
-                return parse_ubjson_typed_run<std::uint8_t>(remaining);
-            case 'i':
-                return parse_ubjson_typed_run<std::int8_t>(remaining);
-            case 'I':
-                return parse_ubjson_typed_run<std::int16_t>(remaining);
-            case 'l':
-                return parse_ubjson_typed_run<std::int32_t>(remaining);
-            case 'L':
-                return parse_ubjson_typed_run<std::int64_t>(remaining);
-            case 'u':
-                return !bjdata || parse_ubjson_typed_run<std::uint16_t>(remaining);
-            case 'm':
-                return !bjdata || parse_ubjson_typed_run<std::uint32_t>(remaining);
-            case 'M':
-                return !bjdata || parse_ubjson_typed_run<std::uint64_t>(remaining);
-            case 'd':
-                return parse_ubjson_typed_run<float>(remaining);
-            case 'D':
-                return parse_ubjson_typed_run<double>(remaining);
-            default:
-                return true;
-        }
-    }
-
-    /// input that is not contiguous: every element is read by get_ubjson_value
-    bool parse_ubjson_typed_run(std::size_t& /*remaining*/, const char_int_type /*type*/, std::false_type /*bulk*/) const noexcept
-    {
-        return true;
-    }
-
-    template<typename NumberType>
-    bool parse_ubjson_typed_run(std::size_t& remaining)
-    {
-        constexpr std::size_t size = sizeof(NumberType);
-        const std::size_t count = (std::min)(remaining, ia.bulk_remaining() / size);
-        if (count == 0)
-        {
-            return true;
-        }
-        const auto* const data = reinterpret_cast<const unsigned char*>(ia.bulk_data());
-        // UBJSON stores numbers big-endian, BJData little-endian
-        const bool swap = is_little_endian != (input_format == input_format_t::bjdata);
-        std::size_t read = 0;
-        bool accepted = true;
-        while (read < count && accepted)
-        {
-            NumberType number{};
-            std::memcpy(&number, data + (read * size), size);
-            if (swap)
-            {
-                byte_swap(number);
-            }
-            ++read;
-            accepted = emit_ubjson_number(number);
-        }
-        // as if read by get_number(): current is the last byte read
-        ia.bulk_skip(read * size);
-        chars_read += read * size;
-        current = data[(read * size) - 1];
-        remaining -= read;
-        return accepted;
-    }
-
-    template<typename NumberType, enable_if_t<std::is_floating_point<NumberType>::value, int> = 0>
-    bool emit_ubjson_number(const NumberType number)
-    {
-        return emit_float(number);
-    }
-
-    template < typename NumberType, enable_if_t < std::is_integral<NumberType>::value&& std::is_signed<NumberType>::value, int > = 0 >
-    bool emit_ubjson_number(const NumberType number)
-    {
-        return emit_signed(number);
-    }
-
-    template < typename NumberType, enable_if_t < std::is_integral<NumberType>::value&& !std::is_signed<NumberType>::value, int > = 0 >
-    bool emit_ubjson_number(const NumberType number)
-    {
-        return emit_unsigned(number);
-    }
-
     /*!
     @return whether array creation completed
     */
@@ -3682,15 +3290,7 @@ class binary_reader
                 return false;
             }
 
-            // the numbers that are in the input, in one loop; the rest (if
-            // the input ends early) one by one below
-            std::size_t remaining = size_and_type.first;
-            if (!nd_is_char && JSON_HEDLEY_UNLIKELY(!parse_ubjson_typed_run(remaining, size_and_type.second, std::integral_constant<bool, bulk_scan> {})))
-            {
-                return false;
-            }
-
-            for (std::size_t i = size_and_type.first - remaining; i < size_and_type.first; ++i)
+            for (std::size_t i = 0; i < size_and_type.first; ++i)
             {
                 if (nd_is_char)
                 {
@@ -3750,8 +3350,7 @@ class binary_reader
                 container_stack.back().remaining = 0;
             }
 
-            return size_and_type.second == 0
-                   || parse_ubjson_typed_run(container_stack.back().remaining, size_and_type.second, std::integral_constant<bool, bulk_scan> {});
+            return true;
         }
 
         return enter_array(detail::unknown_size());
@@ -4092,13 +3691,13 @@ class binary_reader
                 return sax->null();
 
             case 0xFB:
-                return sax->number_float(static_cast<number_float_t>(-1.0), no_source);
+                return sax->number_float(static_cast<number_float_t>(-1.0), "");
 
             case 0xFC:
-                return sax->number_float(static_cast<number_float_t>(0.0), no_source);
+                return sax->number_float(static_cast<number_float_t>(0.0), "");
 
             case 0xFD:
-                return sax->number_float(static_cast<number_float_t>(1.0), no_source);
+                return sax->number_float(static_cast<number_float_t>(1.0), "");
 
             case 0xFF: // empty string
             {
@@ -4467,27 +4066,6 @@ class binary_reader
         return current;
     }
 
-    /// reverse the byte order of a double with a single byteswap(): GCC does
-    /// not merge the byte-wise swap of the generic version into one
-    static void byte_swap(double& number) noexcept
-    {
-        static_assert(sizeof(double) == sizeof(std::uint64_t), "double must have 64 bits");
-        std::uint64_t bits{};
-        std::memcpy(&bits, &number, sizeof(bits));
-        bits = byteswap(bits);
-        std::memcpy(&number, &bits, sizeof(bits));
-    }
-
-    /// reverse the byte order of a float with a single byteswap()
-    static void byte_swap(float& number) noexcept
-    {
-        static_assert(sizeof(float) == sizeof(std::uint32_t), "float must have 32 bits");
-        std::uint32_t bits{};
-        std::memcpy(&bits, &number, sizeof(bits));
-        bits = byteswap(bits);
-        std::memcpy(&number, &bits, sizeof(bits));
-    }
-
     template<class NumberType>
     static void byte_swap(NumberType& number)
     {
@@ -4623,7 +4201,7 @@ class binary_reader
         {
             return out_of_range_error(exception_id::number_overflow, "number overflow", "value");
         }
-        return sax->number_float(result, no_source);
+        return sax->number_float(result, "");
     }
 
     /*!
@@ -4683,7 +4261,7 @@ class binary_reader
         }();
         return sax->number_float((half & 0x8000u) != 0
                                  ? static_cast<number_float_t>(-val)
-                                 : static_cast<number_float_t>(val), no_source);
+                                 : static_cast<number_float_t>(val), "");
     }
 
     /*!
@@ -5008,10 +4586,6 @@ class binary_reader
     /// the SAX parser
     json_sax_t* sax = nullptr;
 
-    /// the (empty) source text of every number_float event: binary formats
-    /// have none, and a string_t built for each float would cost more
-    const string_t no_source{};
-
     /// the containers that have been opened and not closed yet; see @ref container_frame
     std::vector<container_frame> container_stack{};
 

include/nlohmann/detail/view/builder.hpp

@@ -69,7 +69,8 @@ struct parse_failure
 };
 
 /// FloatType: the number_float_t of the document, whose overflow parse() rejects
-template<typename FloatType, bool Comments, bool TrailingCommas, bool NulIsEnd, bool Sentinel>
+/// Store: false for accept(): the grammar, number, string and UTF-8 checks run as for parse(), but no node is written
+template<typename FloatType, bool Comments, bool TrailingCommas, bool NulIsEnd, bool Sentinel, bool Store>
 class builder
 {
   public:
@@ -245,11 +246,87 @@ class builder
         return p;
     }
 
+    /// the string from p, the first backslash, control character, ill-formed UTF-8 byte, or the end, checked and not
+    /// decoded (accept() stores nothing, so the arena is not written): the checks, errors and error positions of
+    /// slow_string(), for everything up to the closing quote
+    NLOHMANN_VIEW_NOINLINE decoded check_string(const unsigned char* p)
+    {
+        const unsigned char* const end = m_end;
+        for (;;)
+        {
+            if (p == end)
+            {
+                return failed(error_code::string_missing_quote, p);
+            }
+            const unsigned char c = *p;
+            if (c == '"')
+            {
+                ++p;
+                return decoded{p, 0, 0};
+            }
+            if (c != '\\')
+            {
+                return failed(c < 0x20 ? error_code::string_control_character : error_code::string_utf8, p);
+            }
+            ++p;
+            if (p == end)
+            {
+                return failed(error_code::string_missing_quote, p);
+            }
+            const unsigned char d = *p++;
+            if (d == 'u')
+            {
+                const int cp = hex4(p); // (moves p past the four digits)
+                if (NLOHMANN_VIEW_UNLIKELY(cp < 0))
+                {
+                    return failed(error_code::string_unicode_hex, p);
+                }
+                if (NLOHMANN_VIEW_UNLIKELY((cp & 0xF800) == 0xD800)) // a surrogate
+                {
+                    if (cp >= 0xDC00)
+                    {
+                        return failed(error_code::string_surrogate_low, p);
+                    }
+                    if (end - p < 2 || p[0] != '\\' || p[1] != 'u')
+                    {
+                        return failed(error_code::string_surrogate_high, p);
+                    }
+                    p += 2;
+                    const int lo = hex4(p); // (moves p past the four digits)
+                    if (lo < 0)
+                    {
+                        return failed(error_code::string_unicode_hex, p);
+                    }
+                    if (lo < 0xDC00 || lo > 0xDFFF)
+                    {
+                        return failed(error_code::string_surrogate_high, p);
+                    }
+                }
+            }
+            else if (!(d == '"' || d == '\\' || d == '/' || d == 'b' || d == 'f' || d == 'n' || d == 'r' || d == 't'))
+            {
+                --p;
+                return failed(error_code::string_escape, p);
+            }
+            if (p != end && *p == '\\')
+            {
+                continue; // (escapes in a row: no run of text between them)
+            }
+            p = scan_string_run(p, end); // the text up to the next backslash, quote, control character, or ill-formed UTF-8
+        }
+    }
+
     /// s points to the start of the string, p to a backslash, a control
     /// character, an ill-formed UTF-8 byte, or the end: decode the string into
     /// the arena
     NLOHMANN_VIEW_NOINLINE decoded slow_string(const unsigned char* s, const unsigned char* p)
     {
+        if (!enabled(Store))
+        {
+            // (accept(): the string is checked, not decoded)
+            static_cast<void>(s);
+            return check_string(p);
+        }
         // single-character escapes; 0: invalid (and 'u', handled separately)
         static const std::array<char, 128> simple_escape =
         {
@@ -610,10 +687,13 @@ run_found:
 
         NLOHMANN_VIEW_ALWAYS_INLINE bool run()
         {
-            cold.m_doc.reserve(estimate_nodes(reinterpret_cast<const char*>(b), static_cast<std::size_t>(e - b)));
-            base = cold.m_doc.nodes;
-            out = base;
-            cap = base + cold.m_doc.node_capacity;
+            if (enabled(Store))
+            {
+                cold.m_doc.reserve(estimate_nodes(reinterpret_cast<const char*>(b), static_cast<std::size_t>(e - b)));
+                base = cold.m_doc.nodes;
+                out = base;
+                cap = base + cold.m_doc.node_capacity;
+            }
 
             if (e - p >= 3 && p[0] == 0xEF && p[1] == 0xBB && p[2] == 0xBF)
             {
@@ -797,7 +877,10 @@ close_object:
             // an array pays nothing for this)
             if (NLOHMANN_VIEW_UNLIKELY(cur_count >= document_data::index_min_members))
             {
-                cold.note_large_object(cur_idx);
+                if (enabled(Store))
+                {
+                    cold.note_large_object(cur_idx);
+                }
             }
 
 close_container:
@@ -957,6 +1040,12 @@ indent_done:
         /// an integer's value); two stores on little-endian targets
         NLOHMANN_VIEW_ALWAYS_INLINE node* push_node(node_kind k, std::uint8_t flags, std::uint16_t extra, std::size_t off, std::uint64_t second)
         {
+            if (!enabled(Store))
+            {
+                // accept(): nothing is stored, so what computes the arguments is not run either. base and out stay
+                // null: their difference, which open() takes, is 0.
+                return out;
+            }
             if (NLOHMANN_VIEW_UNLIKELY(out == cap))
             {
                 const auto n = static_cast<std::size_t>(out - base);
@@ -1015,9 +1104,12 @@ indent_done:
 
         NLOHMANN_VIEW_ALWAYS_INLINE void close()
         {
-            node& n = base[cur_idx];
-            n.len = cur_count;
-            n.next = static_cast<std::uint32_t>(out - base) - cur_idx;
+            if (enabled(Store))
+            {
+                node& n = base[cur_idx];
+                n.len = cur_count;
+                n.next = static_cast<std::uint32_t>(out - base) - cur_idx;
+            }
             if (--depth != 0)
             {
                 if (NLOHMANN_VIEW_LIKELY(depth <= 64))
@@ -1192,34 +1284,44 @@ indent_done:
 };
 
 /// run the builder with compile-time options
-template<typename FloatType, bool Comments, bool TrailingCommas, bool NulIsEnd>
+template<typename FloatType, bool Comments, bool TrailingCommas, bool NulIsEnd, bool Store>
 inline bool build_with(document_data& d, const char* src, std::size_t size, bool sentinel, parse_failure& failure)
 {
     if (sentinel)
     {
-        builder<FloatType, Comments, TrailingCommas, NulIsEnd, true> bld(d, src, size);
+        builder<FloatType, Comments, TrailingCommas, NulIsEnd, true, Store> bld(d, src, size);
         const bool ok = bld.run();
         failure = bld.failure();
         return ok;
     }
-    builder<FloatType, Comments, TrailingCommas, NulIsEnd, false> bld(d, src, size);
+    builder<FloatType, Comments, TrailingCommas, NulIsEnd, false, Store> bld(d, src, size);
     const bool ok = bld.run();
     failure = bld.failure();
     return ok;
 }
 
 /// sentinel: src[size] is readable and 0 (e.g. std::string); FloatType: the
-/// number_float_t of the document
+/// number_float_t of the document; validate_only: accept(), only the result is
+/// used
 template<typename FloatType, bool NulIsEnd>
-inline bool build(document_data& d, const char* src, std::size_t size, bool comments, bool trailing_commas, bool sentinel, parse_failure& failure)
+inline bool build(document_data& d, const char* src, std::size_t size, bool comments, bool trailing_commas, bool sentinel, bool validate_only,
+                  parse_failure& failure)
 {
+    if (validate_only && !comments && !trailing_commas)
+    {
+        // accept() of plain JSON: nothing is stored. The other option sets
+        // could skip the stores just as well; they keep the builder that
+        // stores only so that there are two more instantiations of the parse
+        // loop, not eight.
+        return build_with<FloatType, false, false, NulIsEnd, false>(d, src, size, sentinel, failure);
+    }
     if (comments)
     {
-        return trailing_commas ? build_with<FloatType, true, true, NulIsEnd>(d, src, size, sentinel, failure)
-               : build_with<FloatType, true, false, NulIsEnd>(d, src, size, sentinel, failure);
+        return trailing_commas ? build_with<FloatType, true, true, NulIsEnd, true>(d, src, size, sentinel, failure)
+               : build_with<FloatType, true, false, NulIsEnd, true>(d, src, size, sentinel, failure);
     }
-    return trailing_commas ? build_with<FloatType, false, true, NulIsEnd>(d, src, size, sentinel, failure)
-           : build_with<FloatType, false, false, NulIsEnd>(d, src, size, sentinel, failure);
+    return trailing_commas ? build_with<FloatType, false, true, NulIsEnd, true>(d, src, size, sentinel, failure)
+           : build_with<FloatType, false, false, NulIsEnd, true>(d, src, size, sentinel, failure);
 }
 
 }  // namespace view

include/nlohmann/json_view.hpp

@@ -1060,7 +1060,7 @@ class basic_json_document
                                      const bool ignore_trailing_commas = false)
     {
         basic_json_document d;
-        d.read_range(first, last, allow_exceptions, ignore_comments, ignore_trailing_commas);
+        d.read_range(first, last, error_mode(allow_exceptions), ignore_comments, ignore_trailing_commas);
         return d;
     }
 
@@ -1075,7 +1075,7 @@ class basic_json_document
         basic_json_document d;
         std::string buf;
         append_input(buf, std::forward<InputType>(input));
-        d.build_owned(std::move(buf), allow_exceptions, ignore_comments, ignore_trailing_commas);
+        d.build_owned(std::move(buf), error_mode(allow_exceptions), ignore_comments, ignore_trailing_commas);
         return d;
     }
 
@@ -1088,7 +1088,8 @@ class basic_json_document
     static bool accept(InputType&& input, const bool ignore_comments = false, const bool ignore_trailing_commas = false)
     {
         basic_json_document d;
-        d.read(std::forward<InputType>(input), false, ignore_comments, ignore_trailing_commas);
+        d.read_kind(std::forward<InputType>(input), on_error::validate, ignore_comments, ignore_trailing_commas,
+                    std::integral_constant<detail::view::input_kind, detail::view::classify_input<InputType>::value> {});
         return !d.is_discarded();
     }
 
@@ -1104,7 +1105,7 @@ class basic_json_document
               const bool ignore_comments = false,
               const bool ignore_trailing_commas = false)
     {
-        read_kind(std::forward<InputType>(input), allow_exceptions, ignore_comments, ignore_trailing_commas,
+        read_kind(std::forward<InputType>(input), error_mode(allow_exceptions), ignore_comments, ignore_trailing_commas,
                   std::integral_constant<detail::view::input_kind, detail::view::classify_input<InputType>::value> {});
     }
 
@@ -1463,6 +1464,22 @@ class basic_json_document
         return idx;
     }
 
+    /// what a failed parse does
+    enum class on_error : std::uint8_t
+    {
+        discard, ///< the document is discarded
+        raise,   ///< parse_error is thrown
+        validate ///< accept(): the document is discarded, and no node is stored while parsing
+    };
+
+    static on_error error_mode(bool allow_exceptions) noexcept
+    {
+        return allow_exceptions ? on_error::raise : on_error::discard;
+    }
+
+    /// NulIsEnd of the builder: a null byte ends the input unless strict_nul_handling
+    static constexpr bool nul_is_end = !detail::abi_config::strict_nul_handling;
+
     /// create the storage (sized for the input) on first use
     void ensure_data(const char* src, std::size_t size)
     {
@@ -1474,7 +1491,7 @@ class basic_json_document
 
     /// parse a buffer the document takes ownership of (it replaces the
     /// previous owned copy)
-    void build_owned(std::string&& buf, bool allow_exceptions, bool comments, bool trailing_commas)
+    void build_owned(std::string&& buf, on_error allow_exceptions, bool comments, bool trailing_commas)
     {
         ensure_data(buf.data(), buf.size());
         m_data->owned = std::move(buf);
@@ -1484,7 +1501,7 @@ class basic_json_document
     /// parse a copy of the input; the copy is appended to the cleared owned
     /// buffer, so that its capacity is reused
     template<typename T>
-    void build_copy(T&& input, bool allow_exceptions, bool comments, bool trailing_commas)
+    void build_copy(T&& input, on_error allow_exceptions, bool comments, bool trailing_commas)
     {
         if (!m_data)
         {
@@ -1505,7 +1522,7 @@ class basic_json_document
     }
 
     /// sentinel: src[size] is readable and 0 (std::string, C strings)
-    void build(const char* src, std::size_t size, bool allow_exceptions, bool comments, bool trailing_commas, bool owned, bool sentinel)
+    void build(const char* src, std::size_t size, on_error allow_exceptions, bool comments, bool trailing_commas, bool owned, bool sentinel)
     {
         ensure_data(src, size);
         document_data& d = *m_data;
@@ -1532,7 +1549,8 @@ class basic_json_document
         }
         else
         {
-            ok = detail::view::build < typename BasicJsonType::number_float_t, !detail::abi_config::strict_nul_handling > (d, src, size, comments, trailing_commas, sentinel, failure);
+            ok = detail::view::build<typename BasicJsonType::number_float_t, nul_is_end>(d, src, size, comments, trailing_commas, sentinel,
+                 allow_exceptions == on_error::validate, failure);
         }
         if (NLOHMANN_VIEW_LIKELY(ok))
         {
@@ -1545,7 +1563,7 @@ class basic_json_document
             return;
         }
         std::vector<std::uint32_t>().swap(d.large_objects);
-        if (allow_exceptions)
+        if (allow_exceptions == on_error::raise)
         {
             detail::view::throw_parse_failure<BasicJsonType>(failure, src, size, comments, trailing_commas);
         }
@@ -1553,13 +1571,13 @@ class basic_json_document
 
     // --- input dispatch (see detail::view::input_kind) ---
 
-    void read_kind(std::string&& s, bool ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::move_string> /*unused*/)
+    void read_kind(std::string&& s, on_error ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::move_string> /*unused*/)
     {
         build_owned(std::move(s), ae, c, tc);
     }
 
     template<typename CharT>
-    void read_kind(CharT* s, bool ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::c_string> /*unused*/)
+    void read_kind(CharT* s, on_error ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::c_string> /*unused*/)
     {
         if (s == nullptr)
         {
@@ -1573,7 +1591,7 @@ class basic_json_document
     }
 
     template<typename Array>
-    void read_kind(Array& a, bool ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::char_array> /*unused*/)
+    void read_kind(Array& a, on_error ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::char_array> /*unused*/)
     {
         using CharT = typename std::remove_cv<typename std::remove_extent<Array>::type>::type;
         const std::size_t n = std::extent<Array>::value;
@@ -1584,7 +1602,7 @@ class basic_json_document
     }
 
     template<typename T>
-    void read_kind(const T& s, bool ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::borrow_range> /*unused*/)
+    void read_kind(const T& s, on_error ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::borrow_range> /*unused*/)
     {
         // std::basic_string guarantees data()[size()] == 0: use it as sentinel
         const auto size = static_cast<std::size_t>(s.size());
@@ -1593,13 +1611,13 @@ class basic_json_document
     }
 
     template<typename T>
-    void read_kind(const T& s, bool ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::copy_range> /*unused*/)
+    void read_kind(const T& s, on_error ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::copy_range> /*unused*/)
     {
         build_copy(s, ae, c, tc);
     }
 
     template<typename CharT>
-    void read_kind(CharT* s, bool ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::wide_c_string> /*unused*/)
+    void read_kind(CharT* s, on_error ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::wide_c_string> /*unused*/)
     {
         if (s == nullptr)
         {
@@ -1611,13 +1629,13 @@ class basic_json_document
     }
 
     template<typename T>
-    void read_kind(T&& input, bool ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::adapter> /*unused*/)
+    void read_kind(T&& input, on_error ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::adapter> /*unused*/)
     {
         build_copy(std::forward<T>(input), ae, c, tc);
     }
 
     template<typename IteratorType>
-    void read_range(IteratorType first, IteratorType last, bool ae, bool c, bool tc)
+    void read_range(IteratorType first, IteratorType last, on_error ae, bool c, bool tc)
     {
         using value_type = typename std::remove_cv<typename std::iterator_traits<IteratorType>::value_type>::type;
         // borrow the range where the library's input adapter scans it as one
@@ -1628,14 +1646,14 @@ class basic_json_document
     }
 
     template<typename IteratorType>
-    void read_range_impl(IteratorType first, IteratorType last, bool ae, bool c, bool tc, std::true_type /*contiguous bytes*/)
+    void read_range_impl(IteratorType first, IteratorType last, on_error ae, bool c, bool tc, std::true_type /*contiguous bytes*/)
     {
         const auto size = static_cast<std::size_t>(std::distance(first, last));
         build(size == 0 ? "" : reinterpret_cast<const char*>(&*first), size, ae, c, tc, false, size == 0); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
     }
 
     template<typename IteratorType>
-    void read_range_impl(IteratorType first, IteratorType last, bool ae, bool c, bool tc, std::false_type /*other*/)
+    void read_range_impl(IteratorType first, IteratorType last, on_error ae, bool c, bool tc, std::false_type /*other*/)
     {
         build_copy(detail::view::make_adapter_input(detail::input_adapter(first, last)), ae, c, tc);
     }

single_include/nlohmann/json_view.hpp

@@ -1311,7 +1311,8 @@ struct parse_failure
 };
 
 /// FloatType: the number_float_t of the document, whose overflow parse() rejects
-template<typename FloatType, bool Comments, bool TrailingCommas, bool NulIsEnd, bool Sentinel>
+/// Store: false for accept(): the grammar, number, string and UTF-8 checks run as for parse(), but no node is written
+template<typename FloatType, bool Comments, bool TrailingCommas, bool NulIsEnd, bool Sentinel, bool Store>
 class builder
 {
   public:
@@ -1487,11 +1488,87 @@ class builder
         return p;
     }
 
+    /// the string from p, the first backslash, control character, ill-formed UTF-8 byte, or the end, checked and not
+    /// decoded (accept() stores nothing, so the arena is not written): the checks, errors and error positions of
+    /// slow_string(), for everything up to the closing quote
+    NLOHMANN_VIEW_NOINLINE decoded check_string(const unsigned char* p)
+    {
+        const unsigned char* const end = m_end;
+        for (;;)
+        {
+            if (p == end)
+            {
+                return failed(error_code::string_missing_quote, p);
+            }
+            const unsigned char c = *p;
+            if (c == '"')
+            {
+                ++p;
+                return decoded{p, 0, 0};
+            }
+            if (c != '\\')
+            {
+                return failed(c < 0x20 ? error_code::string_control_character : error_code::string_utf8, p);
+            }
+            ++p;
+            if (p == end)
+            {
+                return failed(error_code::string_missing_quote, p);
+            }
+            const unsigned char d = *p++;
+            if (d == 'u')
+            {
+                const int cp = hex4(p); // (moves p past the four digits)
+                if (NLOHMANN_VIEW_UNLIKELY(cp < 0))
+                {
+                    return failed(error_code::string_unicode_hex, p);
+                }
+                if (NLOHMANN_VIEW_UNLIKELY((cp & 0xF800) == 0xD800)) // a surrogate
+                {
+                    if (cp >= 0xDC00)
+                    {
+                        return failed(error_code::string_surrogate_low, p);
+                    }
+                    if (end - p < 2 || p[0] != '\\' || p[1] != 'u')
+                    {
+                        return failed(error_code::string_surrogate_high, p);
+                    }
+                    p += 2;
+                    const int lo = hex4(p); // (moves p past the four digits)
+                    if (lo < 0)
+                    {
+                        return failed(error_code::string_unicode_hex, p);
+                    }
+                    if (lo < 0xDC00 || lo > 0xDFFF)
+                    {
+                        return failed(error_code::string_surrogate_high, p);
+                    }
+                }
+            }
+            else if (!(d == '"' || d == '\\' || d == '/' || d == 'b' || d == 'f' || d == 'n' || d == 'r' || d == 't'))
+            {
+                --p;
+                return failed(error_code::string_escape, p);
+            }
+            if (p != end && *p == '\\')
+            {
+                continue; // (escapes in a row: no run of text between them)
+            }
+            p = scan_string_run(p, end); // the text up to the next backslash, quote, control character, or ill-formed UTF-8
+        }
+    }
+
     /// s points to the start of the string, p to a backslash, a control
     /// character, an ill-formed UTF-8 byte, or the end: decode the string into
     /// the arena
     NLOHMANN_VIEW_NOINLINE decoded slow_string(const unsigned char* s, const unsigned char* p)
     {
+        if (!enabled(Store))
+        {
+            // (accept(): the string is checked, not decoded)
+            static_cast<void>(s);
+            return check_string(p);
+        }
         // single-character escapes; 0: invalid (and 'u', handled separately)
         static const std::array<char, 128> simple_escape =
         {
@@ -1852,10 +1929,13 @@ run_found:
 
         NLOHMANN_VIEW_ALWAYS_INLINE bool run()
         {
-            cold.m_doc.reserve(estimate_nodes(reinterpret_cast<const char*>(b), static_cast<std::size_t>(e - b)));
-            base = cold.m_doc.nodes;
-            out = base;
-            cap = base + cold.m_doc.node_capacity;
+            if (enabled(Store))
+            {
+                cold.m_doc.reserve(estimate_nodes(reinterpret_cast<const char*>(b), static_cast<std::size_t>(e - b)));
+                base = cold.m_doc.nodes;
+                out = base;
+                cap = base + cold.m_doc.node_capacity;
+            }
 
             if (e - p >= 3 && p[0] == 0xEF && p[1] == 0xBB && p[2] == 0xBF)
             {
@@ -2039,7 +2119,10 @@ close_object:
             // an array pays nothing for this)
             if (NLOHMANN_VIEW_UNLIKELY(cur_count >= document_data::index_min_members))
             {
-                cold.note_large_object(cur_idx);
+                if (enabled(Store))
+                {
+                    cold.note_large_object(cur_idx);
+                }
             }
 
 close_container:
@@ -2199,6 +2282,12 @@ indent_done:
         /// an integer's value); two stores on little-endian targets
         NLOHMANN_VIEW_ALWAYS_INLINE node* push_node(node_kind k, std::uint8_t flags, std::uint16_t extra, std::size_t off, std::uint64_t second)
         {
+            if (!enabled(Store))
+            {
+                // accept(): nothing is stored, so what computes the arguments is not run either. base and out stay
+                // null: their difference, which open() takes, is 0.
+                return out;
+            }
             if (NLOHMANN_VIEW_UNLIKELY(out == cap))
             {
                 const auto n = static_cast<std::size_t>(out - base);
@@ -2257,9 +2346,12 @@ indent_done:
 
         NLOHMANN_VIEW_ALWAYS_INLINE void close()
         {
-            node& n = base[cur_idx];
-            n.len = cur_count;
-            n.next = static_cast<std::uint32_t>(out - base) - cur_idx;
+            if (enabled(Store))
+            {
+                node& n = base[cur_idx];
+                n.len = cur_count;
+                n.next = static_cast<std::uint32_t>(out - base) - cur_idx;
+            }
             if (--depth != 0)
             {
                 if (NLOHMANN_VIEW_LIKELY(depth <= 64))
@@ -2434,34 +2526,44 @@ indent_done:
 };
 
 /// run the builder with compile-time options
-template<typename FloatType, bool Comments, bool TrailingCommas, bool NulIsEnd>
+template<typename FloatType, bool Comments, bool TrailingCommas, bool NulIsEnd, bool Store>
 inline bool build_with(document_data& d, const char* src, std::size_t size, bool sentinel, parse_failure& failure)
 {
     if (sentinel)
     {
-        builder<FloatType, Comments, TrailingCommas, NulIsEnd, true> bld(d, src, size);
+        builder<FloatType, Comments, TrailingCommas, NulIsEnd, true, Store> bld(d, src, size);
         const bool ok = bld.run();
         failure = bld.failure();
         return ok;
     }
-    builder<FloatType, Comments, TrailingCommas, NulIsEnd, false> bld(d, src, size);
+    builder<FloatType, Comments, TrailingCommas, NulIsEnd, false, Store> bld(d, src, size);
     const bool ok = bld.run();
     failure = bld.failure();
     return ok;
 }
 
 /// sentinel: src[size] is readable and 0 (e.g. std::string); FloatType: the
-/// number_float_t of the document
+/// number_float_t of the document; validate_only: accept(), only the result is
+/// used
 template<typename FloatType, bool NulIsEnd>
-inline bool build(document_data& d, const char* src, std::size_t size, bool comments, bool trailing_commas, bool sentinel, parse_failure& failure)
+inline bool build(document_data& d, const char* src, std::size_t size, bool comments, bool trailing_commas, bool sentinel, bool validate_only,
+                  parse_failure& failure)
 {
+    if (validate_only && !comments && !trailing_commas)
+    {
+        // accept() of plain JSON: nothing is stored. The other option sets
+        // could skip the stores just as well; they keep the builder that
+        // stores only so that there are two more instantiations of the parse
+        // loop, not eight.
+        return build_with<FloatType, false, false, NulIsEnd, false>(d, src, size, sentinel, failure);
+    }
     if (comments)
     {
-        return trailing_commas ? build_with<FloatType, true, true, NulIsEnd>(d, src, size, sentinel, failure)
-               : build_with<FloatType, true, false, NulIsEnd>(d, src, size, sentinel, failure);
+        return trailing_commas ? build_with<FloatType, true, true, NulIsEnd, true>(d, src, size, sentinel, failure)
+               : build_with<FloatType, true, false, NulIsEnd, true>(d, src, size, sentinel, failure);
     }
-    return trailing_commas ? build_with<FloatType, false, true, NulIsEnd>(d, src, size, sentinel, failure)
-           : build_with<FloatType, false, false, NulIsEnd>(d, src, size, sentinel, failure);
+    return trailing_commas ? build_with<FloatType, false, true, NulIsEnd, true>(d, src, size, sentinel, failure)
+           : build_with<FloatType, false, false, NulIsEnd, true>(d, src, size, sentinel, failure);
 }
 
 }  // namespace view
@@ -10101,7 +10203,7 @@ class basic_json_document
                                      const bool ignore_trailing_commas = false)
     {
         basic_json_document d;
-        d.read_range(first, last, allow_exceptions, ignore_comments, ignore_trailing_commas);
+        d.read_range(first, last, error_mode(allow_exceptions), ignore_comments, ignore_trailing_commas);
         return d;
     }
 
@@ -10116,7 +10218,7 @@ class basic_json_document
         basic_json_document d;
         std::string buf;
         append_input(buf, std::forward<InputType>(input));
-        d.build_owned(std::move(buf), allow_exceptions, ignore_comments, ignore_trailing_commas);
+        d.build_owned(std::move(buf), error_mode(allow_exceptions), ignore_comments, ignore_trailing_commas);
         return d;
     }
 
@@ -10129,7 +10231,8 @@ class basic_json_document
     static bool accept(InputType&& input, const bool ignore_comments = false, const bool ignore_trailing_commas = false)
     {
         basic_json_document d;
-        d.read(std::forward<InputType>(input), false, ignore_comments, ignore_trailing_commas);
+        d.read_kind(std::forward<InputType>(input), on_error::validate, ignore_comments, ignore_trailing_commas,
+                    std::integral_constant<detail::view::input_kind, detail::view::classify_input<InputType>::value> {});
         return !d.is_discarded();
     }
 
@@ -10145,7 +10248,7 @@ class basic_json_document
               const bool ignore_comments = false,
               const bool ignore_trailing_commas = false)
     {
-        read_kind(std::forward<InputType>(input), allow_exceptions, ignore_comments, ignore_trailing_commas,
+        read_kind(std::forward<InputType>(input), error_mode(allow_exceptions), ignore_comments, ignore_trailing_commas,
                   std::integral_constant<detail::view::input_kind, detail::view::classify_input<InputType>::value> {});
     }
 
@@ -10504,6 +10607,22 @@ class basic_json_document
         return idx;
     }
 
+    /// what a failed parse does
+    enum class on_error : std::uint8_t
+    {
+        discard, ///< the document is discarded
+        raise,   ///< parse_error is thrown
+        validate ///< accept(): the document is discarded, and no node is stored while parsing
+    };
+
+    static on_error error_mode(bool allow_exceptions) noexcept
+    {
+        return allow_exceptions ? on_error::raise : on_error::discard;
+    }
+
+    /// NulIsEnd of the builder: a null byte ends the input unless strict_nul_handling
+    static constexpr bool nul_is_end = !detail::abi_config::strict_nul_handling;
+
     /// create the storage (sized for the input) on first use
     void ensure_data(const char* src, std::size_t size)
     {
@@ -10515,7 +10634,7 @@ class basic_json_document
 
     /// parse a buffer the document takes ownership of (it replaces the
     /// previous owned copy)
-    void build_owned(std::string&& buf, bool allow_exceptions, bool comments, bool trailing_commas)
+    void build_owned(std::string&& buf, on_error allow_exceptions, bool comments, bool trailing_commas)
     {
         ensure_data(buf.data(), buf.size());
         m_data->owned = std::move(buf);
@@ -10525,7 +10644,7 @@ class basic_json_document
     /// parse a copy of the input; the copy is appended to the cleared owned
     /// buffer, so that its capacity is reused
     template<typename T>
-    void build_copy(T&& input, bool allow_exceptions, bool comments, bool trailing_commas)
+    void build_copy(T&& input, on_error allow_exceptions, bool comments, bool trailing_commas)
     {
         if (!m_data)
         {
@@ -10546,7 +10665,7 @@ class basic_json_document
     }
 
     /// sentinel: src[size] is readable and 0 (std::string, C strings)
-    void build(const char* src, std::size_t size, bool allow_exceptions, bool comments, bool trailing_commas, bool owned, bool sentinel)
+    void build(const char* src, std::size_t size, on_error allow_exceptions, bool comments, bool trailing_commas, bool owned, bool sentinel)
     {
         ensure_data(src, size);
         document_data& d = *m_data;
@@ -10573,7 +10692,8 @@ class basic_json_document
         }
         else
         {
-            ok = detail::view::build < typename BasicJsonType::number_float_t, !detail::abi_config::strict_nul_handling > (d, src, size, comments, trailing_commas, sentinel, failure);
+            ok = detail::view::build<typename BasicJsonType::number_float_t, nul_is_end>(d, src, size, comments, trailing_commas, sentinel,
+                 allow_exceptions == on_error::validate, failure);
         }
         if (NLOHMANN_VIEW_LIKELY(ok))
         {
@@ -10586,7 +10706,7 @@ class basic_json_document
             return;
         }
         std::vector<std::uint32_t>().swap(d.large_objects);
-        if (allow_exceptions)
+        if (allow_exceptions == on_error::raise)
         {
             detail::view::throw_parse_failure<BasicJsonType>(failure, src, size, comments, trailing_commas);
         }
@@ -10594,13 +10714,13 @@ class basic_json_document
 
     // --- input dispatch (see detail::view::input_kind) ---
 
-    void read_kind(std::string&& s, bool ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::move_string> /*unused*/)
+    void read_kind(std::string&& s, on_error ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::move_string> /*unused*/)
     {
         build_owned(std::move(s), ae, c, tc);
     }
 
     template<typename CharT>
-    void read_kind(CharT* s, bool ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::c_string> /*unused*/)
+    void read_kind(CharT* s, on_error ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::c_string> /*unused*/)
     {
         if (s == nullptr)
         {
@@ -10614,7 +10734,7 @@ class basic_json_document
     }
 
     template<typename Array>
-    void read_kind(Array& a, bool ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::char_array> /*unused*/)
+    void read_kind(Array& a, on_error ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::char_array> /*unused*/)
     {
         using CharT = typename std::remove_cv<typename std::remove_extent<Array>::type>::type;
         const std::size_t n = std::extent<Array>::value;
@@ -10625,7 +10745,7 @@ class basic_json_document
     }
 
     template<typename T>
-    void read_kind(const T& s, bool ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::borrow_range> /*unused*/)
+    void read_kind(const T& s, on_error ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::borrow_range> /*unused*/)
     {
         // std::basic_string guarantees data()[size()] == 0: use it as sentinel
         const auto size = static_cast<std::size_t>(s.size());
@@ -10634,13 +10754,13 @@ class basic_json_document
     }
 
     template<typename T>
-    void read_kind(const T& s, bool ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::copy_range> /*unused*/)
+    void read_kind(const T& s, on_error ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::copy_range> /*unused*/)
     {
         build_copy(s, ae, c, tc);
     }
 
     template<typename CharT>
-    void read_kind(CharT* s, bool ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::wide_c_string> /*unused*/)
+    void read_kind(CharT* s, on_error ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::wide_c_string> /*unused*/)
     {
         if (s == nullptr)
         {
@@ -10652,13 +10772,13 @@ class basic_json_document
     }
 
     template<typename T>
-    void read_kind(T&& input, bool ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::adapter> /*unused*/)
+    void read_kind(T&& input, on_error ae, bool c, bool tc, std::integral_constant<input_kind, input_kind::adapter> /*unused*/)
     {
         build_copy(std::forward<T>(input), ae, c, tc);
     }
 
     template<typename IteratorType>
-    void read_range(IteratorType first, IteratorType last, bool ae, bool c, bool tc)
+    void read_range(IteratorType first, IteratorType last, on_error ae, bool c, bool tc)
     {
         using value_type = typename std::remove_cv<typename std::iterator_traits<IteratorType>::value_type>::type;
         // borrow the range where the library's input adapter scans it as one
@@ -10669,14 +10789,14 @@ class basic_json_document
     }
 
     template<typename IteratorType>
-    void read_range_impl(IteratorType first, IteratorType last, bool ae, bool c, bool tc, std::true_type /*contiguous bytes*/)
+    void read_range_impl(IteratorType first, IteratorType last, on_error ae, bool c, bool tc, std::true_type /*contiguous bytes*/)
     {
         const auto size = static_cast<std::size_t>(std::distance(first, last));
         build(size == 0 ? "" : reinterpret_cast<const char*>(&*first), size, ae, c, tc, false, size == 0); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
     }
 
     template<typename IteratorType>
-    void read_range_impl(IteratorType first, IteratorType last, bool ae, bool c, bool tc, std::false_type /*other*/)
+    void read_range_impl(IteratorType first, IteratorType last, on_error ae, bool c, bool tc, std::false_type /*other*/)
     {
         build_copy(detail::view::make_adapter_input(detail::input_adapter(first, last)), ae, c, tc);
     }

tests/src/unit-bjdata.cpp

@@ -26,14 +26,11 @@ using nlohmann::ordered_json;
 #include <limits>
 #include <iostream>
 #include <fstream>
-#include <list>
 #include <set>
 #include "make_test_data_available.hpp"
 #include "test_utils.hpp"
 #include "sax_countdown.hpp"
-#include "sax_event_loggers.hpp"
 using utils::SaxCountdown;
-using utils::SaxEventLogger;
 
 
 // trait_test_arg and the "value_in_range_of trait" TEST_CASE_TEMPLATE_DEFINE
@@ -4749,75 +4746,3 @@ TEST_CASE("BJData optimized container type marker is validated for count 0")
         CHECK(json::from_bjdata(vb) == json::binary({}));
     }
 }
-
-TEST_CASE("BJData optimized arrays from contiguous and non-contiguous input")
-{
-    // contiguous input reads the numbers of an array with a type marker in
-    // one loop, other input number by number; both must give the same events,
-    // value, or error for the complete document and for every truncation of
-    // it, and stop at every event a SAX handler rejects
-    json document =
-    {
-        {"u8", {0, 200, 255}},
-        {"i8", {-5, 100, -128}},
-        {"i16", {-30000, 1000, 30000}},
-        {"i32", {-2000000000, 5, 70000}},
-        {"i64", {-9000000000000000000LL, 1, 5000000000LL}},
-        {"f64", {1.5, -0.1, 2.5}},
-        {"pairs", {{1.25, -3.75}, {1.25, -3.75}, json::array()}},
-        {"mixed", {1, "a", 2.5, nullptr}},
-        {"u16", {40000, 1, 65535}},
-        {"u32", {4000000000U, 1, 70000}},
-        {"u64", {18446744073709551615ULL, 1, 5000000000ULL}},
-        {"nd", {{"_ArrayType_", "double"}, {"_ArraySize_", {2, 2}}, {"_ArrayData_", {1.5, -2.5, 3.5, -4.5}}}},
-        {"nd8", {{"_ArrayType_", "uint8"}, {"_ArraySize_", {3}}, {"_ArrayData_", {1, 2, 3}}}},
-    };
-    const std::vector<std::uint8_t> encoded = json::to_bjdata(document, true, true);
-    CHECK(json::from_bjdata(encoded) == document);
-
-    for (std::size_t length = 0; length <= encoded.size(); ++length)
-    {
-        CAPTURE(length)
-        const std::vector<std::uint8_t> contiguous(encoded.begin(), encoded.begin() + static_cast<std::ptrdiff_t>(length));
-        const std::list<std::uint8_t> bytewise(contiguous.begin(), contiguous.end());
-
-        CHECK(json::from_bjdata(contiguous, true, false).dump() == json::from_bjdata(bytewise.begin(), bytewise.end(), true, false).dump());
-#if !defined(JSON_NOEXCEPTION)
-        std::string contiguous_error;
-        std::string bytewise_error;
-        try
-        {
-            static_cast<void>(json::from_bjdata(contiguous));
-        }
-        catch (const json::exception& e)
-        {
-            contiguous_error = e.what();
-        }
-        try
-        {
-            static_cast<void>(json::from_bjdata(bytewise.begin(), bytewise.end()));
-        }
-        catch (const json::exception& e)
-        {
-            bytewise_error = e.what();
-        }
-        CHECK(contiguous_error == bytewise_error);
-#endif
-
-        SaxEventLogger from_contiguous;
-        SaxEventLogger from_bytewise;
-        CHECK(json::sax_parse(contiguous, &from_contiguous, json::input_format_t::bjdata)
-              == json::sax_parse(bytewise.begin(), bytewise.end(), &from_bytewise, json::input_format_t::bjdata));
-        CHECK(from_contiguous.events == from_bytewise.events);
-    }
-
-    for (int events = 0; events <= 80; ++events)
-    {
-        CAPTURE(events)
-        const std::list<std::uint8_t> bytewise(encoded.begin(), encoded.end());
-        SaxCountdown from_contiguous(events);
-        SaxCountdown from_bytewise(events);
-        CHECK(json::sax_parse(encoded, &from_contiguous, json::input_format_t::bjdata)
-              == json::sax_parse(bytewise.begin(), bytewise.end(), &from_bytewise, json::input_format_t::bjdata));
-    }
-}

tests/src/unit-cbor.cpp

@@ -29,9 +29,7 @@ using nlohmann::json;
 #include "round_trip_corpus.hpp"
 #include "test_utils.hpp"
 #include "sax_countdown.hpp"
-#include "sax_event_loggers.hpp"
 using utils::SaxCountdown;
-using utils::SaxEventLogger;
 
 
 TEST_CASE("CBOR")
@@ -2448,78 +2446,6 @@ TEST_CASE("CBOR SAX parsing stops at every event")
     CHECK(count_events(std::vector<std::uint8_t>({0xBF, 0x61, 'a', 0x9F, 0x01, 0xFF, 0xFF})) == 6);
 }
 
-TEST_CASE("CBOR arrays of scalars from contiguous and non-contiguous input")
-{
-    // contiguous input reads the integers, floats, booleans, and nulls an
-    // array begins with in one loop, other input value by value; both must
-    // give the same events, value, or error for the complete document and for
-    // every truncation of it, and stop at every event a SAX handler rejects
-    const std::vector<std::uint8_t> cbor =
-    {
-        0xA3,                                                       // map(3)
-        0x61, 'a',                                                  // "a"
-        0x98, 0x16,                                                 // array(22)
-        0x00, 0x17, 0x18, 0xFF, 0x19, 0x01, 0x00,                   // 0, 23, 255, 256
-        0x1A, 0x00, 0x01, 0x00, 0x00,                               // 65536
-        0x1B, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,       // 18446744073709551615
-        0x20, 0x37, 0x38, 0xFF, 0x39, 0x01, 0x00,                   // -1, -24, -256, -257
-        0x3A, 0x00, 0x01, 0x00, 0x00,                               // -65537
-        0x3B, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,       // -18446744073709551616 (a float)
-        0x3B, 0x7F, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,       // -9223372036854775808
-        0xF4, 0xF5, 0xF6,                                           // false, true, null
-        0xFA, 0x3F, 0xC0, 0x00, 0x00,                               // 1.5 (float32)
-        0xFB, 0xBF, 0xB9, 0x99, 0x99, 0x99, 0x99, 0x99, 0x9A,       // -0.1
-        0xF9, 0x3C, 0x00,                                           // 1.0 (float16, ends the loop)
-        0x01, 0x61, 'a',                                            // 1, "a"
-        0xFB, 0x40, 0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,       // 2.5
-        0x61, 'b',                                                  // "b"
-        0x83,                                                       // array(3)
-        0x82, 0xFB, 0x3F, 0xF4, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // [1.25,
-        0xFB, 0xC0, 0x0E, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,       //  -3.75]
-        0x82, 0xFB, 0x3F, 0xF4, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // [1.25,
-        0xFB, 0xC0, 0x0E, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,       //  -3.75]
-        0x80,                                                       // []
-        0x61, 'c',                                                  // "c"
-        0x84, 0xA0, 0x01, 0xC1, 0x02, 0x81, 0x03                    // [{}, 1, tag(1) 2, [3]]
-    };
-    const auto tags = json::cbor_tag_handler_t::ignore;
-
-    const json j = json::from_cbor(cbor, true, true, tags);
-    CHECK(j["a"].size() == 22);
-    CHECK(j["a"][5] == 18446744073709551615u);
-    CHECK(j["a"][11].is_number_float());
-    CHECK(j["a"][11] == -18446744073709551616.0);
-    CHECK(j["a"][12] == (std::numeric_limits<std::int64_t>::min)());
-    CHECK(j["a"][17] == -0.1);
-    CHECK(j["b"] == json::parse("[[1.25, -3.75], [1.25, -3.75], []]"));
-    CHECK(j["c"] == json::parse("[{}, 1, 2, [3]]"));
-
-    for (std::size_t length = 0; length <= cbor.size(); ++length)
-    {
-        CAPTURE(length)
-        const std::vector<std::uint8_t> contiguous(cbor.begin(), cbor.begin() + static_cast<std::ptrdiff_t>(length));
-        const std::list<std::uint8_t> bytewise(contiguous.begin(), contiguous.end());
-
-        CHECK(json::from_cbor(contiguous, true, false, tags).dump() == json::from_cbor(bytewise.begin(), bytewise.end(), true, false, tags).dump());
-
-        SaxEventLogger from_contiguous;
-        SaxEventLogger from_bytewise;
-        CHECK(json::sax_parse(contiguous, &from_contiguous, json::input_format_t::cbor, true, false, false, tags)
-              == json::sax_parse(bytewise.begin(), bytewise.end(), &from_bytewise, json::input_format_t::cbor, true, false, false, tags));
-        CHECK(from_contiguous.events == from_bytewise.events);
-    }
-
-    for (int events = 0; events <= 60; ++events)
-    {
-        CAPTURE(events)
-        const std::list<std::uint8_t> bytewise(cbor.begin(), cbor.end());
-        SaxCountdown from_contiguous(events);
-        SaxCountdown from_bytewise(events);
-        CHECK(json::sax_parse(cbor, &from_contiguous, json::input_format_t::cbor, true, false, false, tags)
-              == json::sax_parse(bytewise.begin(), bytewise.end(), &from_bytewise, json::input_format_t::cbor, true, false, false, tags));
-    }
-}
-
 TEST_CASE("CBOR indefinite-length strings do not recurse per chunk")
 {
     // Reading an indefinite-length string or byte array used to call itself

tests/src/unit-json_view_builder.cpp

@@ -59,7 +59,8 @@ built build(const std::string& text, bool comments, bool trailing_commas, bool s
         r.copy.assign(text.begin(), text.end());
         src = r.copy.data();
     }
-    r.ok = nlohmann::detail::view::build < FloatType, !nlohmann::detail::abi_config::strict_nul_handling > (*r.data, src, text.size(), comments, trailing_commas, sentinel, r.failure);
+    constexpr bool nul_is_end = !nlohmann::detail::abi_config::strict_nul_handling;
+    r.ok = nlohmann::detail::view::build<FloatType, nul_is_end>(*r.data, src, text.size(), comments, trailing_commas, sentinel, false, r.failure);
     r.data->src = src;
     r.data->base[0] = src;
     r.data->base[1] = r.data->arena.data();
@@ -172,6 +173,22 @@ void check_string(const std::string& content)
     }
 }
 
+// accept() stores no nodes: it must accept and reject what json::accept does, for all options and for inputs with
+// and without a terminating NUL
+void check_accept(const std::string& text)
+{
+    CAPTURE(text)
+    const std::vector<char> bytes(text.begin(), text.end());
+    for (int options = 0; options < 4; ++options)
+    {
+        const bool comments = (options & 1) != 0;
+        const bool trailing_commas = (options & 2) != 0;
+        const bool accepted = json::accept(text, comments, trailing_commas);
+        CHECK(nlohmann::json_document::accept(text, comments, trailing_commas) == accepted);
+        CHECK(nlohmann::json_document::accept(bytes, comments, trailing_commas) == accepted);
+    }
+}
+
 // a small deterministic generator of documents
 struct generator
 {
@@ -423,6 +440,133 @@ TEST_CASE("json_view builder")
         }
     }
 
+    SECTION("accept() without an index")
+    {
+        for (const char* text :
+                {
+                    "", " ", "\n", "null", "nul", "true", "[", "]", "[]", "{}", "[1,2,3]", "[1,2,3", "[1,2,3,]", "{\"a\":1,}", "{\"a\"}", "{\"a\":}",
+                    "[1] x", "[1][2]", "\xEF\xBB\xBF[1]", "[\"a\\", "[\"\\u12\"]", "[\"\\ud800\"]", "[\"\x01\"]", "[\"\xff\"]", "[01]", "[1.]",
+                    "[.5]", "[-]", "[1e]", "// c\n[1]", "/* c */ {\"a\" /* x */ : 1}", "/* c", "[1] // c", "1e400", "-1e400", "123456789012345678901234567890",
+                    "{\"a\":1,\"a\":2}", "[[[]]]", "\"\\u00e4\\n\\ud83d\\ude00\""
+                })
+        {
+            check_accept(text);
+        }
+        // a null byte inside the text, and after it
+        check_accept(std::string("[1,\0]", 5));
+        check_accept(std::string("[1]\0", 4));
+        check_accept(std::string("\0", 1));
+
+        // generated documents and damaged copies, as for the builder above
+        generator g;
+        for (int i = 0; i < 2000; ++i)
+        {
+            std::string text;
+            g.value(text, 0);
+            check_accept(text);
+            std::string damaged = text;
+            const auto at = static_cast<std::size_t>(g.r(static_cast<int>(damaged.size())));
+            static const char replacements[] = {'x', '"', '\\', ',', ':', ']', '}', '[', '{', '1', '-', '.', 'e', '\0', '\n', '/'}; // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
+            damaged[at] = replacements[g.r(16)];
+            check_accept(damaged);
+            check_accept(text.substr(0, at));
+        }
+
+        // nesting beyond the 64 levels that are kept on the builder's own stack, closed and not closed
+        for (const std::size_t depth :
+                {
+                    63, 64, 65, 66, 200, 1000
+                })
+        {
+            check_accept(std::string(depth, '[') + std::string(depth, ']'));
+            check_accept(std::string(depth, '[') + std::string(depth - 1, ']'));
+            std::string objects;
+            for (std::size_t i = 0; i < depth; ++i)
+            {
+                objects += "{\"k\":";
+            }
+            objects += "1" + std::string(depth, '}');
+            check_accept(objects);
+            check_accept(objects.substr(0, objects.size() - 1));
+        }
+
+        // objects with enough members to get a hash index when they are indexed (and duplicate keys)
+        std::string large = "{";
+        for (int i = 0; i < 300; ++i)
+        {
+            large += (i == 0 ? "\"k" : ",\"k") + std::to_string(i % 200) + "\":" + std::to_string(i);
+        }
+        check_accept(large + "}");
+        check_accept(large);
+        check_accept("[" + large + "},{" + large.substr(1) + "}]");
+
+        // the overflow check uses the floating-point type of the document
+        using float_json = nlohmann::basic_json<std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t, float>;
+        for (const char* text :
+                {
+                    "1e39", "-1e39", "3.4028235e38", "3.4028236e38", "[1.5e38, 3.5e38]", "{\"a\": 1e-50, \"b\": 1e39}", "340282356779733661637539395458142568448"
+                })
+        {
+            CAPTURE(text)
+            CHECK(nlohmann::basic_json_document<float_json>::accept(text) == float_json::accept(text));
+        }
+
+        // strings are checked and not decoded: runs of text of every length from 0 to 40 between valid and invalid
+        // escapes, UTF-8 sequences and control characters, in values and in keys, cut near the end of the text
+        const std::array<const char*, 9> valid = {{"\\n", "\\\"", "\\\\", "\\/", "\\t", "\\u00e4", "\\u20ac", "\\ud83d\\ude00", "\\u0000"}};
+        const std::array<const char*, 12> invalid = {{"\\x", "\\ud800", "\\udc00", "\\u12G4", "\\u12", "\\ud83dx", "\\ud83d\\u0041", "\\ud83d\\ud83d", "\\", "\x01", "\x1f", "\x7f"}};
+        const std::array<const char*, 6> utf8 = {{"\xc3\xa4", "\xe2\x82\xac", "\xf0\x9f\x98\x80", "\xc3", "\xff", "\x80"}};
+        std::mt19937 rng(2029); // NOLINT(cert-msc32-c,cert-msc51-cpp,bugprone-random-generator-seed): reproducible
+        for (std::size_t run = 0; run <= 40; ++run)
+        {
+            for (int i = 0; i < 30; ++i)
+            {
+                std::string content = std::string(rng() % 20, 'a');
+                const auto pieces = 1 + (rng() % 6);
+                for (unsigned k = 0; k < pieces; ++k)
+                {
+                    content += valid[rng() % valid.size()];
+                    content += std::string(k == 0 ? run : rng() % 41, static_cast<char>('b' + (rng() % 20)));
+                    switch (rng() % 8)
+                    {
+                        case 0:
+                            content += utf8[rng() % 3];
+                            break;
+                        case 1:
+                            content += utf8[rng() % utf8.size()];
+                            break;
+                        case 2:
+                            content += invalid[rng() % invalid.size()];
+                            break;
+                        default:
+                            break;
+                    }
+                }
+                for (const std::string& text :
+                        {
+                            "[\"" + content + "\"]", "{\"" + content + "\":1}", "[\"" + content, "[\"" + content.substr(0, content.size() - (rng() % 4)) + "\"]"
+                        })
+                {
+                    check_accept(text);
+                }
+            }
+        }
+    }
+
+    SECTION("escapes in a row")
+    {
+        for (const char* content :
+                {
+                    "\\n", "\\n\\t\\\\", "\\u00e9\\u00e9\\u4e2d", "\\u00e9\\u00e", "\\u00e9\\", "\\n\\q", "\\n\\ud83d\\ude00\\n",
+                    "\\ud83d\\ude00\\ud83d", "\\n\\n\\n abc \\n\\n", "\\n\x01", "\\n\xC3\x28", "\\n\\"
+                })
+        {
+            check_accept(std::string("[\"") + content + "\"]");
+            check_accept(std::string("[\"") + content);
+            check_accept(std::string("{\"") + content + "\":1}");
+        }
+    }
+
     SECTION("test files")
     {
         for (const char* name :

tests/src/unit-msgpack.cpp

@@ -27,15 +27,12 @@ using nlohmann::json;
 #include <sstream>
 #include <iomanip>
 #include <limits>
-#include <list>
 #include <set>
 #include "make_test_data_available.hpp"
 #include "round_trip_corpus.hpp"
 #include "test_utils.hpp"
 #include "sax_countdown.hpp"
-#include "sax_event_loggers.hpp"
 using utils::SaxCountdown;
-using utils::SaxEventLogger;
 
 
 TEST_CASE("MessagePack")
@@ -2215,97 +2212,3 @@ TEST_CASE("MessagePack large strings and binaries (chunked reader)")
         }
     }
 }
-
-TEST_CASE("MessagePack arrays of scalars from contiguous and non-contiguous input")
-{
-    // contiguous input reads the integers, floats, booleans, and nils an
-    // array begins with in one loop, other input value by value; both must
-    // give the same events, value, or error for the complete document and for
-    // every truncation of it, and stop at every event a SAX handler rejects
-    const std::vector<std::uint8_t> msgpack =
-    {
-        0x83,                                                       // map(3)
-        0xA1, 'a',                                                  // "a"
-        0xDC, 0x00, 0x16,                                           // array 16 (22)
-        0x00, 0x7F, 0xCC, 0xFF, 0xCD, 0x01, 0x00,                   // 0, 127, 255, 256
-        0xCE, 0x00, 0x01, 0x00, 0x00,                               // 65536
-        0xCF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,       // 18446744073709551615
-        0xFF, 0xE0, 0xD0, 0x80, 0xD1, 0xFF, 0x00,                   // -1, -32, -128, -256
-        0xD2, 0xFF, 0xFE, 0xFF, 0xFF,                               // -65537
-        0xD3, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,       // -9223372036854775808
-        0xC2, 0xC3, 0xC0,                                           // false, true, nil
-        0xCA, 0x3F, 0xC0, 0x00, 0x00,                               // 1.5 (float 32)
-        0xCB, 0xBF, 0xB9, 0x99, 0x99, 0x99, 0x99, 0x99, 0x9A,       // -0.1
-        0xA1, 'x',                                                  // "x" (ends the loop)
-        0x01,                                                       // 1
-        0xCB, 0x40, 0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,       // 2.5
-        0xD9, 0x01, 'y',                                            // "y" (str 8)
-        0xC0,                                                       // nil
-        0xA1, 'b',                                                  // "b"
-        0x93,                                                       // fixarray(3)
-        0x92, 0xCB, 0x3F, 0xF4, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // [1.25,
-        0xCB, 0xC0, 0x0E, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,       //  -3.75]
-        0x92, 0xCB, 0x3F, 0xF4, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // [1.25,
-        0xCB, 0xC0, 0x0E, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,       //  -3.75]
-        0x90,                                                       // []
-        0xA1, 'c',                                                  // "c"
-        0x94, 0x80, 0x01, 0xC4, 0x01, 0x05, 0x91, 0x03              // [{}, 1, bin 8, [3]]
-    };
-
-    const json j = json::from_msgpack(msgpack);
-    CHECK(j["a"].size() == 22);
-    CHECK(j["a"][5] == 18446744073709551615u);
-    CHECK(j["a"][7] == -32);
-    CHECK(j["a"][11] == (std::numeric_limits<std::int64_t>::min)());
-    CHECK(j["a"][15] == 1.5);
-    CHECK(j["a"][16] == -0.1);
-    CHECK(j["a"][17] == "x");
-    CHECK(j["b"] == json::parse("[[1.25, -3.75], [1.25, -3.75], []]"));
-    CHECK(j["c"][2].is_binary());
-
-    for (std::size_t length = 0; length <= msgpack.size(); ++length)
-    {
-        CAPTURE(length)
-        const std::vector<std::uint8_t> contiguous(msgpack.begin(), msgpack.begin() + static_cast<std::ptrdiff_t>(length));
-        const std::list<std::uint8_t> bytewise(contiguous.begin(), contiguous.end());
-
-        CHECK(json::from_msgpack(contiguous, true, false).dump() == json::from_msgpack(bytewise.begin(), bytewise.end(), true, false).dump());
-#if !defined(JSON_NOEXCEPTION)
-        std::string contiguous_error;
-        std::string bytewise_error;
-        try
-        {
-            static_cast<void>(json::from_msgpack(contiguous));
-        }
-        catch (const json::parse_error& e)
-        {
-            contiguous_error = e.what();
-        }
-        try
-        {
-            static_cast<void>(json::from_msgpack(bytewise.begin(), bytewise.end()));
-        }
-        catch (const json::parse_error& e)
-        {
-            bytewise_error = e.what();
-        }
-        CHECK(contiguous_error == bytewise_error);
-#endif
-
-        SaxEventLogger from_contiguous;
-        SaxEventLogger from_bytewise;
-        CHECK(json::sax_parse(contiguous, &from_contiguous, json::input_format_t::msgpack)
-              == json::sax_parse(bytewise.begin(), bytewise.end(), &from_bytewise, json::input_format_t::msgpack));
-        CHECK(from_contiguous.events == from_bytewise.events);
-    }
-
-    for (int events = 0; events <= 60; ++events)
-    {
-        CAPTURE(events)
-        const std::list<std::uint8_t> bytewise(msgpack.begin(), msgpack.end());
-        SaxCountdown from_contiguous(events);
-        SaxCountdown from_bytewise(events);
-        CHECK(json::sax_parse(msgpack, &from_contiguous, json::input_format_t::msgpack)
-              == json::sax_parse(bytewise.begin(), bytewise.end(), &from_bytewise, json::input_format_t::msgpack));
-    }
-}

tests/src/unit-ubjson.cpp

@@ -21,15 +21,12 @@ using nlohmann::json;
 
 #include <iostream>
 #include <fstream>
-#include <list>
 #include <set>
 #include "make_test_data_available.hpp"
 #include "round_trip_corpus.hpp"
 #include "test_utils.hpp"
 #include "sax_countdown.hpp"
-#include "sax_event_loggers.hpp"
 using utils::SaxCountdown;
-using utils::SaxEventLogger;
 
 
 TEST_CASE("UBJSON")
@@ -3403,70 +3400,3 @@ TEST_CASE("UBJSON optimized container type marker is validated for count 0")
         }
     }
 }
-
-TEST_CASE("UBJSON optimized arrays from contiguous and non-contiguous input")
-{
-    // contiguous input reads the numbers of an array with a type marker in
-    // one loop, other input number by number; both must give the same events,
-    // value, or error for the complete document and for every truncation of
-    // it, and stop at every event a SAX handler rejects
-    json document =
-    {
-        {"u8", {0, 200, 255}},
-        {"i8", {-5, 100, -128}},
-        {"i16", {-30000, 1000, 30000}},
-        {"i32", {-2000000000, 5, 70000}},
-        {"i64", {-9000000000000000000LL, 1, 5000000000LL}},
-        {"f64", {1.5, -0.1, 2.5}},
-        {"pairs", {{1.25, -3.75}, {1.25, -3.75}, json::array()}},
-        {"mixed", {1, "a", 2.5, nullptr}},
-    };
-    const std::vector<std::uint8_t> encoded = json::to_ubjson(document, true, true);
-    CHECK(json::from_ubjson(encoded) == document);
-
-    for (std::size_t length = 0; length <= encoded.size(); ++length)
-    {
-        CAPTURE(length)
-        const std::vector<std::uint8_t> contiguous(encoded.begin(), encoded.begin() + static_cast<std::ptrdiff_t>(length));
-        const std::list<std::uint8_t> bytewise(contiguous.begin(), contiguous.end());
-
-        CHECK(json::from_ubjson(contiguous, true, false).dump() == json::from_ubjson(bytewise.begin(), bytewise.end(), true, false).dump());
-#if !defined(JSON_NOEXCEPTION)
-        std::string contiguous_error;
-        std::string bytewise_error;
-        try
-        {
-            static_cast<void>(json::from_ubjson(contiguous));
-        }
-        catch (const json::exception& e)
-        {
-            contiguous_error = e.what();
-        }
-        try
-        {
-            static_cast<void>(json::from_ubjson(bytewise.begin(), bytewise.end()));
-        }
-        catch (const json::exception& e)
-        {
-            bytewise_error = e.what();
-        }
-        CHECK(contiguous_error == bytewise_error);
-#endif
-
-        SaxEventLogger from_contiguous;
-        SaxEventLogger from_bytewise;
-        CHECK(json::sax_parse(contiguous, &from_contiguous, json::input_format_t::ubjson)
-              == json::sax_parse(bytewise.begin(), bytewise.end(), &from_bytewise, json::input_format_t::ubjson));
-        CHECK(from_contiguous.events == from_bytewise.events);
-    }
-
-    for (int events = 0; events <= 80; ++events)
-    {
-        CAPTURE(events)
-        const std::list<std::uint8_t> bytewise(encoded.begin(), encoded.end());
-        SaxCountdown from_contiguous(events);
-        SaxCountdown from_bytewise(events);
-        CHECK(json::sax_parse(encoded, &from_contiguous, json::input_format_t::ubjson)
-              == json::sax_parse(bytewise.begin(), bytewise.end(), &from_bytewise, json::input_format_t::ubjson));
-    }
-}