Binary readers: swap the bytes of floats with a single byteswap

byte_swap reversed float and double values byte by byte. GCC does not
merge that loop into one bswap, and C++23's std::byteswap accepts only
integers. Overloads for float and double now copy the bits into a
uint32_t/uint64_t, call detail::byteswap, and copy them back. This
applies to every binary reader that uses get_number.

In the CBOR reader, the single- and double-precision float cases call a
non-inlined helper. Without it, GCC stopped inlining the stream
adapter's get_character() into parse_cbor_internal, which made reading
from a std::istream about 0.5 % slower.

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

include/nlohmann/detail/input/binary_reader.hpp

@@ -22,6 +22,7 @@
     #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>
@@ -741,11 +742,13 @@ class binary_reader
     bool get_cbor_negative_integer()
     {
         NumberType number{};
-        if (JSON_HEDLEY_UNLIKELY(!get_number(number)))
-        {
-            return false;
-        }
+        return get_number(number) && emit_cbor_negative_integer(number);
+    }
 
+    /// 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
@@ -970,7 +973,7 @@ class binary_reader
             case 0x95:
             case 0x96:
             case 0x97:
-                return enter_array(conditional_static_cast<std::size_t>(static_cast<unsigned int>(current) & 0x1Fu));
+                return enter_cbor_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)
@@ -979,7 +982,7 @@ class binary_reader
             {
                 std::uint64_t len{};
                 std::size_t size{};
-                return get_cbor_argument(len) && get_cbor_container_size(len, size, "array") && enter_array(size);
+                return get_cbor_argument(len) && get_cbor_container_size(len, size, "array") && enter_cbor_array(size);
             }
 
             case 0x9F: // array (indefinite length)
@@ -1133,16 +1136,10 @@ class binary_reader
                 return get_half_float(false);
 
             case 0xFA: // Single-Precision Float (four-byte IEEE 754)
-            {
-                float number{};
-                return get_number(number) && emit_float(number);
-            }
+                return get_cbor_float<float>();
 
             case 0xFB: // Double-Precision Float (eight-byte IEEE 754)
-            {
-                double number{};
-                return get_number(number) && emit_float(number);
-            }
+                return get_cbor_float<double>();
 
             default: // anything else (0xFF is handled inside the other types)
             {
@@ -1151,6 +1148,16 @@ 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
@@ -1676,6 +1683,157 @@ 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
 
@@ -1705,6 +1863,7 @@ 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)
@@ -1716,7 +1875,7 @@ class binary_reader
                     {
                         // claim the element about to be read
                         --container_stack.back().remaining;
-                        if (top.is_object)
+                        if (is_object)
                         {
                             get();
                         }
@@ -1729,7 +1888,7 @@ 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 = top.is_object;
+                    fetch = is_object;
                 }
 
                 if (at_end)
@@ -1746,7 +1905,7 @@ class binary_reader
                     continue;
                 }
 
-                if (top.is_object)
+                if (is_object)
                 {
                     if (JSON_HEDLEY_UNLIKELY(!skip_cbor_key_tags(tag_handler)))
                     {
@@ -3691,13 +3850,13 @@ class binary_reader
                 return sax->null();
 
             case 0xFB:
-                return sax->number_float(static_cast<number_float_t>(-1.0), "");
+                return sax->number_float(static_cast<number_float_t>(-1.0), no_source);
 
             case 0xFC:
-                return sax->number_float(static_cast<number_float_t>(0.0), "");
+                return sax->number_float(static_cast<number_float_t>(0.0), no_source);
 
             case 0xFD:
-                return sax->number_float(static_cast<number_float_t>(1.0), "");
+                return sax->number_float(static_cast<number_float_t>(1.0), no_source);
 
             case 0xFF: // empty string
             {
@@ -4066,6 +4225,27 @@ 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)
     {
@@ -4201,7 +4381,7 @@ class binary_reader
         {
             return out_of_range_error(exception_id::number_overflow, "number overflow", "value");
         }
-        return sax->number_float(result, "");
+        return sax->number_float(result, no_source);
     }
 
     /*!
@@ -4261,7 +4441,7 @@ class binary_reader
         }();
         return sax->number_float((half & 0x8000u) != 0
                                  ? static_cast<number_float_t>(-val)
-                                 : static_cast<number_float_t>(val), "");
+                                 : static_cast<number_float_t>(val), no_source);
     }
 
     /*!
@@ -4586,6 +4766,10 @@ 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/input/lexer.hpp

@@ -268,10 +268,10 @@ 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_values_ = false) noexcept
+    explicit lexer(InputAdapterType&& adapter, bool ignore_comments_ = false, bool discard_number_values_ = false) noexcept
         : ia(std::move(adapter))
         , ignore_comments(ignore_comments_)
-        , discard_values(discard_values_)
+        , discard_number_values(discard_number_values_)
     {
         // the token string of an error before the first token is everything
         // read so far
@@ -388,8 +388,6 @@ class lexer : public lexer_base<BasicJsonType>
     checks if it is inside the range. If a violation was detected, set up an
     error message and return false. Otherwise, return true.
 
-    @param[in] keep    whether the bytes are added to token_buffer (false for
-                       accept(), see scan())
     @param[in] ranges  list of integers; interpreted as list of pairs of
                        inclusive lower and upper bound, respectively
 
@@ -398,18 +396,17 @@ class lexer : public lexer_base<BasicJsonType>
 
     @return true if and only if no range violation was detected
     */
-    template<bool Keep>
-    bool next_byte_in_range(std::integral_constant<bool, Keep> keep, std::initializer_list<char_int_type> ranges)
+    bool next_byte_in_range(std::initializer_list<char_int_type> ranges)
     {
         JSON_ASSERT(ranges.size() == 2 || ranges.size() == 4 || ranges.size() == 6);
-        add_string_char(keep, current);
+        add(current);
 
         for (auto range = ranges.begin(); range != ranges.end(); ++range)
         {
             get();
             if (JSON_HEDLEY_LIKELY(*range <= current && current <= *(++range))) // NOLINT(bugprone-inc-dec-in-conditions)
             {
-                add_string_char(keep, current);
+                add(current);
             }
             else
             {
@@ -422,16 +419,14 @@ class lexer : public lexer_base<BasicJsonType>
     }
 
     /// contiguous input: bulk-append the run of ordinary characters and complete
-    /// well-formed UTF-8 sequences starting at the current read position (only
-    /// skip it if @a keep is false), then
+    /// well-formed UTF-8 sequences starting at the current read position, then
     /// read the first byte that needs individual handling (the closing quote, an
     /// escape, a control character, or an ill-formed UTF-8 byte) like get().
     /// That byte is taken from the buffer that was just scanned. Through get(),
     /// Apple Clang merged this read with the other get() calls of the scan
     /// function, which load the read position again right after it was stored
     /// (3% of json::accept() on jeopardy.json on Apple M1).
-    template<bool Keep>
-    char_int_type get_after_string_run(std::true_type /*bulk*/, std::integral_constant<bool, Keep> keep)
+    char_int_type get_after_string_run(std::true_type /*bulk*/)
     {
         // a pending unget must be consumed through the normal path first
         if (next_unget)
@@ -449,7 +444,7 @@ class lexer : public lexer_base<BasicJsonType>
         const std::size_t pos = lexer_string_bulk_run(data, remaining);
         if (pos != 0)
         {
-            append_string_run(keep, data, pos);
+            token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), pos);
             bulk_consume(reinterpret_cast<const char*>(data), pos);
         }
         if (pos == remaining)
@@ -493,8 +488,7 @@ class lexer : public lexer_base<BasicJsonType>
     }
 
     /// streaming input: no bulk fast path
-    template<bool Keep>
-    char_int_type get_after_string_run(std::false_type /*bulk*/, std::integral_constant<bool, Keep> /*keep*/)
+    char_int_type get_after_string_run(std::false_type /*bulk*/)
     {
         return get();
     }
@@ -508,18 +502,13 @@ class lexer : public lexer_base<BasicJsonType>
     may contain \0 bytes), and token_buffer.size() is the number of bytes in the
     string.
 
-    @param[in] keep  whether the string is copied into token_buffer; if false
-                     (accept(), see scan()), it is only checked, with the same
-                     errors, and token_buffer stays empty
-
     @return token_type::value_string if string could be successfully scanned,
             token_type::parse_error otherwise
 
     @note In case of errors, variable error_message contains a textual
           description.
     */
-    template<bool Keep>
-    token_type scan_string(std::integral_constant<bool, Keep> keep)
+    token_type scan_string()
     {
         // reset token_buffer (ignore opening quote)
         reset();
@@ -531,7 +520,7 @@ class lexer : public lexer_base<BasicJsonType>
         {
             // bulk-consume ordinary characters from contiguous input, then
             // get the next character, the one that ends the run
-            switch (get_after_string_run(std::integral_constant<bool, bulk_scan>(), keep))
+            switch (get_after_string_run(std::integral_constant<bool, bulk_scan>()))
             {
                 // end of file while parsing the string
                 case char_traits<char_type>::eof():
@@ -553,35 +542,35 @@ class lexer : public lexer_base<BasicJsonType>
                     {
                         // quotation mark
                         case '\"':
-                            add_string_char(keep, '\"');
+                            add('\"');
                             break;
                         // reverse solidus
                         case '\\':
-                            add_string_char(keep, '\\');
+                            add('\\');
                             break;
                         // solidus
                         case '/':
-                            add_string_char(keep, '/');
+                            add('/');
                             break;
                         // backspace
                         case 'b':
-                            add_string_char(keep, '\b');
+                            add('\b');
                             break;
                         // form feed
                         case 'f':
-                            add_string_char(keep, '\f');
+                            add('\f');
                             break;
                         // line feed
                         case 'n':
-                            add_string_char(keep, '\n');
+                            add('\n');
                             break;
                         // carriage return
                         case 'r':
-                            add_string_char(keep, '\r');
+                            add('\r');
                             break;
                         // tab
                         case 't':
-                            add_string_char(keep, '\t');
+                            add('\t');
                             break;
 
                         // unicode escapes
@@ -649,7 +638,10 @@ class lexer : public lexer_base<BasicJsonType>
                             JSON_ASSERT(0x00 <= codepoint && codepoint <= 0x10FFFF);
 
                             // translate codepoint into bytes
-                            add_codepoint(keep, codepoint);
+                            encode_utf8(static_cast<std::uint32_t>(codepoint), [this](std::uint32_t byte)
+                            {
+                                add(static_cast<char_int_type>(byte));
+                            });
 
                             break;
                         }
@@ -832,7 +824,7 @@ class lexer : public lexer_base<BasicJsonType>
                 case 0x7E:
                 case 0x7F:
                 {
-                    add_string_char(keep, current);
+                    add(current);
                     break;
                 }
 
@@ -868,7 +860,7 @@ class lexer : public lexer_base<BasicJsonType>
                 case 0xDE:
                 case 0xDF:
                 {
-                    if (JSON_HEDLEY_UNLIKELY(!next_byte_in_range(keep, {0x80, 0xBF})))
+                    if (JSON_HEDLEY_UNLIKELY(!next_byte_in_range({0x80, 0xBF})))
                     {
                         return token_type::parse_error;
                     }
@@ -878,7 +870,7 @@ class lexer : public lexer_base<BasicJsonType>
                 // U+0800..U+0FFF: bytes E0 A0..BF 80..BF
                 case 0xE0:
                 {
-                    if (JSON_HEDLEY_UNLIKELY(!(next_byte_in_range(keep, {0xA0, 0xBF, 0x80, 0xBF}))))
+                    if (JSON_HEDLEY_UNLIKELY(!(next_byte_in_range({0xA0, 0xBF, 0x80, 0xBF}))))
                     {
                         return token_type::parse_error;
                     }
@@ -902,7 +894,7 @@ class lexer : public lexer_base<BasicJsonType>
                 case 0xEE:
                 case 0xEF:
                 {
-                    if (JSON_HEDLEY_UNLIKELY(!(next_byte_in_range(keep, {0x80, 0xBF, 0x80, 0xBF}))))
+                    if (JSON_HEDLEY_UNLIKELY(!(next_byte_in_range({0x80, 0xBF, 0x80, 0xBF}))))
                     {
                         return token_type::parse_error;
                     }
@@ -912,7 +904,7 @@ class lexer : public lexer_base<BasicJsonType>
                 // U+D000..U+D7FF: bytes ED 80..9F 80..BF
                 case 0xED:
                 {
-                    if (JSON_HEDLEY_UNLIKELY(!(next_byte_in_range(keep, {0x80, 0x9F, 0x80, 0xBF}))))
+                    if (JSON_HEDLEY_UNLIKELY(!(next_byte_in_range({0x80, 0x9F, 0x80, 0xBF}))))
                     {
                         return token_type::parse_error;
                     }
@@ -922,7 +914,7 @@ class lexer : public lexer_base<BasicJsonType>
                 // U+10000..U+3FFFF F0 90..BF 80..BF 80..BF
                 case 0xF0:
                 {
-                    if (JSON_HEDLEY_UNLIKELY(!(next_byte_in_range(keep, {0x90, 0xBF, 0x80, 0xBF, 0x80, 0xBF}))))
+                    if (JSON_HEDLEY_UNLIKELY(!(next_byte_in_range({0x90, 0xBF, 0x80, 0xBF, 0x80, 0xBF}))))
                     {
                         return token_type::parse_error;
                     }
@@ -934,7 +926,7 @@ class lexer : public lexer_base<BasicJsonType>
                 case 0xF2:
                 case 0xF3:
                 {
-                    if (JSON_HEDLEY_UNLIKELY(!(next_byte_in_range(keep, {0x80, 0xBF, 0x80, 0xBF, 0x80, 0xBF}))))
+                    if (JSON_HEDLEY_UNLIKELY(!(next_byte_in_range({0x80, 0xBF, 0x80, 0xBF, 0x80, 0xBF}))))
                     {
                         return token_type::parse_error;
                     }
@@ -944,7 +936,7 @@ class lexer : public lexer_base<BasicJsonType>
                 // U+100000..U+10FFFF F4 80..8F 80..BF 80..BF
                 case 0xF4:
                 {
-                    if (JSON_HEDLEY_UNLIKELY(!(next_byte_in_range(keep, {0x80, 0x8F, 0x80, 0xBF, 0x80, 0xBF}))))
+                    if (JSON_HEDLEY_UNLIKELY(!(next_byte_in_range({0x80, 0x8F, 0x80, 0xBF, 0x80, 0xBF}))))
                     {
                         return token_type::parse_error;
                     }
@@ -1435,7 +1427,7 @@ scan_number_done:
     token_type convert_number(token_type number_type, std::size_t mantissa_end)
     {
         // accept() only needs to know whether the input is valid, so it sets
-        // discard_values (see json.hpp), and an integer token whose
+        // discard_number_values (see json.hpp), and an integer token whose
         // digit count shows that it fits is reported without calling
         // convert_integer(). A number with up to 18 digits always fits into
         // both std::uint64_t and std::int64_t (18 nines is about 1e18, below
@@ -1450,7 +1442,7 @@ scan_number_done:
         // json_sax_acceptor, whose number callbacks discard their argument and
         // return true, and the parser rejects neither integers nor finite
         // floats. value_unsigned/value_integer are left unset here, so a caller
-        // that reads the converted value must not set discard_values.
+        // that reads the converted value must not set discard_number_values.
         //
         // On contiguous input, scan_number_bulk_contiguous() converts integer
         // tokens itself and does not pass them to this function, unless
@@ -1458,7 +1450,7 @@ scan_number_done:
         // reached for input without bulk access (e.g. streams), with
         // JSON_DIAGNOSTIC_POSITIONS, or when scan_number_bulk_contiguous()
         // falls back to scan_number().
-        if (discard_values)
+        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)
@@ -1709,7 +1701,7 @@ scan_number_done:
         // w < 10^19, so a value below 10^max_exponent10 cannot overflow, and a
         // value that underflows is a finite number as well. Only a token that
         // may overflow has to be converted to find out.
-        if (JSON_HEDLEY_UNLIKELY(discard_values && s.exponent + 19 <= std::numeric_limits<number_float_t>::max_exponent10))
+        if (JSON_HEDLEY_UNLIKELY(discard_number_values && s.exponent + 19 <= std::numeric_limits<number_float_t>::max_exponent10))
         {
             value_float = 0;
             return true;
@@ -2041,34 +2033,6 @@ scan_number_done:
         token_buffer.push_back(static_cast<typename string_t::value_type>(c));
     }
 
-    /// add a character of a string token; accept() checks the string but does
-    /// not keep its value (@a keep is false)
-    void add_string_char(std::true_type /*keep*/, char_int_type c)
-    {
-        token_buffer.push_back(static_cast<typename string_t::value_type>(c));
-    }
-
-    static void add_string_char(std::false_type /*keep*/, char_int_type /*c*/) noexcept {}
-
-    /// add the UTF-8 bytes of a code point from a \\u escape to a string token
-    void add_codepoint(std::true_type /*keep*/, int codepoint)
-    {
-        encode_utf8(static_cast<std::uint32_t>(codepoint), [this](std::uint32_t byte)
-        {
-            add(static_cast<char_int_type>(byte));
-        });
-    }
-
-    static void add_codepoint(std::false_type /*keep*/, int /*codepoint*/) noexcept {}
-
-    /// append a run of ordinary string characters (see get_after_string_run())
-    void append_string_run(std::true_type /*keep*/, const unsigned char* data, std::size_t n)
-    {
-        token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), n);
-    }
-
-    static void append_string_run(std::false_type /*keep*/, const unsigned char* /*data*/, std::size_t /*n*/) noexcept {}
-
   public:
     /////////////////////
     // value getters
@@ -2463,11 +2427,7 @@ scan_number_done:
 
             // string
             case '\"':
-                // accept() (discard_values) checks strings without copying them
-                // into token_buffer. The choice is made once per string: a
-                // check inside the string loop made number-heavy documents up
-                // to 3 % slower (mesh.json, Apple M1)
-                return discard_values ? scan_string(std::false_type {}) : scan_string(std::true_type {});
+                return scan_string();
 
             // number
             case '-':
@@ -2552,13 +2512,11 @@ scan_number_done:
     std::size_t decimal_point_position = std::string::npos;
 
     /// whether the caller only needs the token types and never looks at the
-    /// values of number and string tokens; set only by accept(), which parses
-    /// through json_sax_acceptor. When set, convert_number() skips converting
-    /// integer tokens whose digit count guarantees that they fit into 64 bits
-    /// (see there), floats are converted only when they may overflow (see
-    /// convert_accumulated_float()), and strings are checked without being
-    /// copied into token_buffer (see scan())
-    const bool discard_values = false;
+    /// converted numeric values; set only by accept(), which parses through
+    /// json_sax_acceptor. When set, convert_number() skips converting integer
+    /// tokens whose digit count guarantees that they fit into 64 bits (see
+    /// there)
+    const bool discard_number_values = false;
 };
 
 }  // namespace detail

include/nlohmann/detail/input/parser.hpp

@@ -89,9 +89,9 @@ class parser
                     const bool allow_exceptions_ = true,
                     const bool ignore_comments = false,
                     const bool ignore_trailing_commas_ = false,
-                    const bool discard_values_ = false)
+                    const bool discard_number_values_ = false)
         : callback(std::move(cb))
-        , m_lexer(std::move(adapter), ignore_comments, discard_values_)
+        , m_lexer(std::move(adapter), ignore_comments, discard_number_values_)
         , allow_exceptions(allow_exceptions_)
         , ignore_trailing_commas(ignore_trailing_commas_)
     {

include/nlohmann/json.hpp

@@ -184,11 +184,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         const bool allow_exceptions = true,
         const bool ignore_comments = false,
         const bool ignore_trailing_commas = false,
-        const bool discard_values = 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_values);
+               std::move(cb), allow_exceptions, ignore_comments, ignore_trailing_commas, discard_number_values);
     }
 
   private:

tests/src/unit-cbor.cpp

@@ -29,7 +29,9 @@ 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")
@@ -2446,6 +2448,78 @@ 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-class_parser.cpp

@@ -2982,50 +2982,6 @@ TEST_CASE("accept() agrees with parse() on floats around the overflow limit")
     }
 }
 
-TEST_CASE("accept() agrees with parse() on strings, which it checks without copying them")
-{
-    // accept() scans strings and object keys with a separate instantiation of
-    // the string scanner that does not copy them into the token buffer; it
-    // must accept and reject exactly what parse() does
-    const std::vector<std::string> pieces =
-    {
-        "", "abc", "\\\"\\\\\\/\\b\\f\\n\\r\\t", "\\u0041\\u00e4\\u20AC", "\\ud83d\\ude00", "\\uD83D\\uDE00",
-        "\\ud800", "\\udc00", "\\ud800\\u0041", "\\ud800x", "\\udbff\\udfff", "\\u12", "\\u12g4", "\\x", "\\",
-        "\xc3\xa4", "\xe2\x82\xac", "\xf0\x9f\x98\x80", "\xf4\x8f\xbf\xbf", "\xc0\xaf", "\xed\xa0\x80", "\xf4\x90\x80\x80",
-        "\xff", "\xe2\x82", "\xc3", "\x01", "\x1f", "\x7f", "\n", std::string(1, '\0')
-    };
-
-    for (std::size_t run = 0; run <= 70; ++run)
-    {
-        for (const std::string& piece : pieces)
-        {
-            // a run of ordinary characters puts the piece at every offset of the bulk scanners
-            const std::string str = std::string(run, 'a') + piece;
-            for (const std::string& text :
-                    {
-                        "\"" + str + "\"", "[\"" + str + "\"]", "{\"" + str + "\":1}", "{\"k\":\"" + str + "\",\"" + str + "\":[\"" + str + "\"]}",
-                        "[\"" + str
-                    })
-            {
-                CAPTURE(text)
-                for (int options = 0; options < 4; ++options)
-                {
-                    const bool ignore_comments = (options & 1) != 0;
-                    const bool ignore_trailing_commas = (options & 2) != 0;
-                    const bool parses = !json::parse(text, nullptr, false, ignore_comments, ignore_trailing_commas).is_discarded();
-                    CHECK(json::accept(text, ignore_comments, ignore_trailing_commas) == parses);
-
-                    std::istringstream stream(text);
-                    CHECK(json::accept(stream, ignore_comments, ignore_trailing_commas) == parses);
-
-                    const std::list<char> chars(text.begin(), text.end());
-                    CHECK(json::accept(chars.begin(), chars.end(), ignore_comments, ignore_trailing_commas) == parses);
-                }
-            }
-        }
-    }
-}
-
 namespace
 {
 // a DOM parser that reports parse errors without throwing, as in the sax_no_exception example