Fix clang-tidy modernize-raw-string-literal in unit-json_view_builder.cpp

Fixes the ci_clang_tidy failure of the PR (10 escaped string literals).

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
+function runs the document's builder, which checks the text as [`parse()`](parse.md) does, while
-parser with a handler that ignores every event. Use this one if you go on to parse the same input with
+`BasicJsonType::accept()` runs the SAX parser with a handler that ignores every event. Use this one if you go on to
-[`parse()`](parse.md) anyway, so that both use the same code; either is fine for a plain yes/no answer.
+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/lexer.hpp

@@ -209,13 +209,8 @@ constexpr bool input_adapter_bulk_window(std::false_type /*detected*/)
 @brief lexical analysis
 
 This class organizes the lexical analysis during JSON deserialization.
-
-DiscardValues: the caller only needs the token types and never looks at the values of number and string tokens (only
-accept(), which parses through json_sax_acceptor). A template parameter rather than a member, so that the lexer of
-parse() is compiled without the paths of accept(): with both string scans in one scan(), parse() was up to 2 % slower
-on Apple M1.
 */
-template<typename BasicJsonType, typename InputAdapterType, bool DiscardValues = false>
+template<typename BasicJsonType, typename InputAdapterType>
 class lexer : public lexer_base<BasicJsonType>
 {
     using number_integer_t = typename BasicJsonType::number_integer_t;
@@ -273,9 +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) noexcept
+    explicit lexer(InputAdapterType&& adapter, bool ignore_comments_ = false, bool discard_number_values_ = false) noexcept
         : ia(std::move(adapter))
         , ignore_comments(ignore_comments_)
+        , discard_number_values(discard_number_values_)
     {
         // the token string of an error before the first token is everything
         // read so far
@@ -392,8 +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
 
@@ -402,18 +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::initializer_list<char_int_type> ranges)
-    bool next_byte_in_range(std::integral_constant<bool, Keep> keep, 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
             {
@@ -426,16 +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
+    /// well-formed UTF-8 sequences starting at the current read position, then
-    /// skip it if @a keep is false), 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*/)
-    char_int_type get_after_string_run(std::true_type /*bulk*/, std::integral_constant<bool, Keep> keep)
     {
         // a pending unget must be consumed through the normal path first
         if (next_unget)
@@ -453,7 +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)
@@ -497,8 +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*/)
-    char_int_type get_after_string_run(std::false_type /*bulk*/, std::integral_constant<bool, Keep> /*keep*/)
     {
         return get();
     }
@@ -512,18 +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()
-    token_type scan_string(std::integral_constant<bool, Keep> keep)
     {
         // reset token_buffer (ignore opening quote)
         reset();
@@ -535,7 +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():
@@ -557,35 +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
@@ -653,7 +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;
                         }
@@ -836,7 +824,7 @@ class lexer : public lexer_base<BasicJsonType>
                 case 0x7E:
                 case 0x7F:
                 {
-                    add_string_char(keep, current);
+                    add(current);
                     break;
                 }
 
@@ -872,7 +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;
                     }
@@ -882,7 +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;
                     }
@@ -906,7 +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;
                     }
@@ -916,7 +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;
                     }
@@ -926,7 +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;
                     }
@@ -938,7 +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;
                     }
@@ -948,7 +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;
                     }
@@ -1439,7 +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
@@ -1454,7 +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
@@ -1462,7 +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)
@@ -1713,7 +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;
@@ -2045,34 +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
@@ -2467,9 +2427,7 @@ scan_number_done:
 
             // string
             case '\"':
-                // accept() (DiscardValues) checks strings without copying them
+                return scan_string();
-                // into token_buffer
-                return scan_string(keep_strings {});
 
             // number
             case '-':
@@ -2554,19 +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; DiscardValues, set only by accept(), which parses
+    /// converted numeric values; set only by accept(), which parses through
-    /// through json_sax_acceptor. When set, convert_number() skips converting
+    /// json_sax_acceptor. When set, convert_number() skips converting integer
-    /// integer tokens whose digit count guarantees that they fit into 64 bits
+    /// tokens whose digit count guarantees that they fit into 64 bits (see
-    /// (see there), floats are converted only when they may overflow (see
+    /// there)
-    /// convert_accumulated_float()), and strings are checked without being
+    const bool discard_number_values = false;
-    /// copied into token_buffer (see scan())
-    static bool discard_values() noexcept
-    {
-        return DiscardValues;
-    }
-
-    /// the tag of scan_string(): whether string tokens are kept
-    using keep_strings = typename std::conditional<DiscardValues, std::false_type, std::true_type>::type;
 };
 
 }  // namespace detail

include/nlohmann/detail/input/parser.hpp

@@ -72,14 +72,14 @@ This class implements a parser for JSON text. Nested arrays and objects are trac
 stack instead of recursion, so deeply nested input does not exhaust the call stack, and what is read
 is reported as SAX events.
 */
-template<typename BasicJsonType, typename InputAdapterType, bool DiscardValues = false>
+template<typename BasicJsonType, typename InputAdapterType>
 class parser
 {
     using number_integer_t = typename BasicJsonType::number_integer_t;
     using number_unsigned_t = typename BasicJsonType::number_unsigned_t;
     using number_float_t = typename BasicJsonType::number_float_t;
     using string_t = typename BasicJsonType::string_t;
-    using lexer_t = lexer<BasicJsonType, InputAdapterType, DiscardValues>;
+    using lexer_t = lexer<BasicJsonType, InputAdapterType>;
     using token_type = typename lexer_t::token_type;
 
   public:
@@ -88,9 +88,10 @@ class parser
                     parser_callback_t<BasicJsonType> cb = nullptr,
                     const bool allow_exceptions_ = true,
                     const bool ignore_comments = false,
-                    const bool ignore_trailing_commas_ = false)
+                    const bool ignore_trailing_commas_ = false,
+                    const bool discard_number_values_ = false)
         : callback(std::move(cb))
-        , m_lexer(std::move(adapter), ignore_comments)
+        , m_lexer(std::move(adapter), ignore_comments, discard_number_values_)
         , allow_exceptions(allow_exceptions_)
         , ignore_trailing_commas(ignore_trailing_commas_)
     {

include/nlohmann/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)));
+            if (enabled(Store))
-            base = cold.m_doc.nodes;
+            {
-            out = base;
+                cold.m_doc.reserve(estimate_nodes(reinterpret_cast<const char*>(b), static_cast<std::size_t>(e - b)));
-            cap = base + cold.m_doc.node_capacity;
+                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];
+            if (enabled(Store))
-            n.len = cur_count;
+            {
-            n.next = static_cast<std::uint32_t>(out - base) - cur_idx;
+                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)
+        return trailing_commas ? build_with<FloatType, true, true, NulIsEnd, true>(d, src, size, sentinel, failure)
-               : build_with<FloatType, true, false, NulIsEnd>(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)
+    return trailing_commas ? build_with<FloatType, false, true, NulIsEnd, true>(d, src, size, sentinel, failure)
-           : build_with<FloatType, false, false, NulIsEnd>(d, src, size, sentinel, failure);
+           : build_with<FloatType, false, false, NulIsEnd, true>(d, src, size, sentinel, failure);
 }
 
 }  // namespace view

include/nlohmann/detail/view/macro_scope.hpp

@@ -40,6 +40,15 @@
     #define NLOHMANN_VIEW_NOINLINE
 #endif
 
+// GCC: a function compiled as written, without the clones in which interprocedural
+// constant propagation drops an argument that every caller passes as the same constant
+// (calling such a clone changes the code GCC generates for the parse loop that calls it)
+#if defined(__GNUC__) && !defined(__clang__)
+    #define NLOHMANN_VIEW_NOCLONE __attribute__((noclone))
+#else
+    #define NLOHMANN_VIEW_NOCLONE
+#endif
+
 #if defined(__GNUC__) || defined(__clang__)
     #define NLOHMANN_VIEW_NODISCARD __attribute__((warn_unused_result))
 #elif defined(_MSC_VER)

include/nlohmann/detail/view/macro_unscope.hpp

@@ -15,6 +15,7 @@
 #undef NLOHMANN_VIEW_UNLIKELY
 #undef NLOHMANN_VIEW_ALWAYS_INLINE
 #undef NLOHMANN_VIEW_NOINLINE
+#undef NLOHMANN_VIEW_NOCLONE
 #undef NLOHMANN_VIEW_NODISCARD
 #undef NLOHMANN_VIEW_THROW
 #undef NLOHMANN_VIEW_LITTLE_ENDIAN

include/nlohmann/detail/view/simd.hpp

@@ -289,9 +289,12 @@ compares, and the UTF-8 check covers the bytes up to it. Returns where the
 string scan stops, like scan_string_run: before ill-formed UTF-8 and for the
 last bytes of the input, the bytes are checked one sequence at a time. Out of
 line, so that no constants of the check occupy registers in the parse loop.
-On x86-64, it is compiled for SSSE3 (see cpu_has_ssse3()).
+On x86-64, it is compiled for SSSE3 (see cpu_has_ssse3()). Not cloned: with
+the calls of accept()'s builder, GCC 16 would clone it without plain (always
+string_plain()), and calling the clone made json_document::parse() run 0.7-1.2 %
+more instructions.
 */
-NLOHMANN_VIEW_SSSE3_TARGET NLOHMANN_VIEW_NOINLINE inline const unsigned char* scan_string_vector(const unsigned char* p, const unsigned char* e, const std::uint8_t* plain) noexcept
+NLOHMANN_VIEW_SSSE3_TARGET NLOHMANN_VIEW_NOINLINE NLOHMANN_VIEW_NOCLONE inline const unsigned char* scan_string_vector(const unsigned char* p, const unsigned char* e, const std::uint8_t* plain) noexcept
 {
     using lookup = utf8_lookup4<>;
     const unsigned char* block = p;

include/nlohmann/json.hpp

@@ -150,7 +150,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     // can be restored when json_pointer backwards compatibility is removed
     // friend ::nlohmann::json_pointer<StringType>;
 
-    template<typename BasicJsonType, typename InputType, bool DiscardValues>
+    template<typename BasicJsonType, typename InputType>
     friend class ::nlohmann::detail::parser;
     friend ::nlohmann::detail::serializer<basic_json>;
     template<typename BasicJsonType>
@@ -183,11 +183,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         detail::parser_callback_t<basic_json>cb = nullptr,
         const bool allow_exceptions = true,
         const bool ignore_comments = false,
-        const bool ignore_trailing_commas = false
+        const bool ignore_trailing_commas = false,
+        const bool discard_number_values = false
     )
     {
         return ::nlohmann::detail::parser<basic_json, InputAdapterType>(std::move(adapter),
-               std::move(cb), allow_exceptions, ignore_comments, ignore_trailing_commas);
+               std::move(cb), allow_exceptions, ignore_comments, ignore_trailing_commas, discard_number_values);
     }
 
   private:
@@ -3116,9 +3117,7 @@ public:
                             const bool ignore_comments,
                             const bool ignore_trailing_commas)
     {
-        // the parser and lexer that discard the values of tokens (see lexer)
+        return parser(std::forward<InputAdapterType>(adapter), nullptr, false, ignore_comments, ignore_trailing_commas, true).accept(true);
-        return ::nlohmann::detail::parser<basic_json, typename std::decay<InputAdapterType>::type, true>(std::forward<InputAdapterType>(adapter),
-                nullptr, false, ignore_comments, ignore_trailing_commas).accept(true);
     }
 
     /// generate SAX events from the input behind an already created adapter

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.hpp

@@ -13065,13 +13065,8 @@ constexpr bool input_adapter_bulk_window(std::false_type /*detected*/)
 @brief lexical analysis
 
 This class organizes the lexical analysis during JSON deserialization.
-
-DiscardValues: the caller only needs the token types and never looks at the values of number and string tokens (only
-accept(), which parses through json_sax_acceptor). A template parameter rather than a member, so that the lexer of
-parse() is compiled without the paths of accept(): with both string scans in one scan(), parse() was up to 2 % slower
-on Apple M1.
 */
-template<typename BasicJsonType, typename InputAdapterType, bool DiscardValues = false>
+template<typename BasicJsonType, typename InputAdapterType>
 class lexer : public lexer_base<BasicJsonType>
 {
     using number_integer_t = typename BasicJsonType::number_integer_t;
@@ -13129,9 +13124,10 @@ class lexer : public lexer_base<BasicJsonType>
   public:
     using token_type = typename lexer_base<BasicJsonType>::token_type;
 
-    explicit lexer(InputAdapterType&& adapter, bool ignore_comments_ = false) noexcept
+    explicit lexer(InputAdapterType&& adapter, bool ignore_comments_ = false, bool discard_number_values_ = false) noexcept
         : ia(std::move(adapter))
         , ignore_comments(ignore_comments_)
+        , discard_number_values(discard_number_values_)
     {
         // the token string of an error before the first token is everything
         // read so far
@@ -13248,8 +13244,6 @@ 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
 
@@ -13258,18 +13252,17 @@ 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::initializer_list<char_int_type> ranges)
-    bool next_byte_in_range(std::integral_constant<bool, Keep> keep, 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
             {
@@ -13282,16 +13275,14 @@ 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
+    /// well-formed UTF-8 sequences starting at the current read position, then
-    /// skip it if @a keep is false), 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*/)
-    char_int_type get_after_string_run(std::true_type /*bulk*/, std::integral_constant<bool, Keep> keep)
     {
         // a pending unget must be consumed through the normal path first
         if (next_unget)
@@ -13309,7 +13300,7 @@ 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)
@@ -13353,8 +13344,7 @@ 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*/)
-    char_int_type get_after_string_run(std::false_type /*bulk*/, std::integral_constant<bool, Keep> /*keep*/)
     {
         return get();
     }
@@ -13368,18 +13358,13 @@ 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()
-    token_type scan_string(std::integral_constant<bool, Keep> keep)
     {
         // reset token_buffer (ignore opening quote)
         reset();
@@ -13391,7 +13376,7 @@ 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():
@@ -13413,35 +13398,35 @@ 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
@@ -13509,7 +13494,10 @@ 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;
                         }
@@ -13692,7 +13680,7 @@ class lexer : public lexer_base<BasicJsonType>
                 case 0x7E:
                 case 0x7F:
                 {
-                    add_string_char(keep, current);
+                    add(current);
                     break;
                 }
 
@@ -13728,7 +13716,7 @@ 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;
                     }
@@ -13738,7 +13726,7 @@ 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;
                     }
@@ -13762,7 +13750,7 @@ 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;
                     }
@@ -13772,7 +13760,7 @@ 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;
                     }
@@ -13782,7 +13770,7 @@ 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;
                     }
@@ -13794,7 +13782,7 @@ 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;
                     }
@@ -13804,7 +13792,7 @@ 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;
                     }
@@ -14295,7 +14283,7 @@ 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
@@ -14310,7 +14298,7 @@ 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
@@ -14318,7 +14306,7 @@ 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)
@@ -14569,7 +14557,7 @@ 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;
@@ -14901,34 +14889,6 @@ 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
@@ -15323,9 +15283,7 @@ scan_number_done:
 
             // string
             case '\"':
-                // accept() (DiscardValues) checks strings without copying them
+                return scan_string();
-                // into token_buffer
-                return scan_string(keep_strings {});
 
             // number
             case '-':
@@ -15410,19 +15368,11 @@ 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; DiscardValues, set only by accept(), which parses
+    /// converted numeric values; set only by accept(), which parses through
-    /// through json_sax_acceptor. When set, convert_number() skips converting
+    /// json_sax_acceptor. When set, convert_number() skips converting integer
-    /// integer tokens whose digit count guarantees that they fit into 64 bits
+    /// tokens whose digit count guarantees that they fit into 64 bits (see
-    /// (see there), floats are converted only when they may overflow (see
+    /// there)
-    /// convert_accumulated_float()), and strings are checked without being
+    const bool discard_number_values = false;
-    /// copied into token_buffer (see scan())
-    static bool discard_values() noexcept
-    {
-        return DiscardValues;
-    }
-
-    /// the tag of scan_string(): whether string tokens are kept
-    using keep_strings = typename std::conditional<DiscardValues, std::false_type, std::true_type>::type;
 };
 
 }  // namespace detail
@@ -22614,14 +22564,14 @@ This class implements a parser for JSON text. Nested arrays and objects are trac
 stack instead of recursion, so deeply nested input does not exhaust the call stack, and what is read
 is reported as SAX events.
 */
-template<typename BasicJsonType, typename InputAdapterType, bool DiscardValues = false>
+template<typename BasicJsonType, typename InputAdapterType>
 class parser
 {
     using number_integer_t = typename BasicJsonType::number_integer_t;
     using number_unsigned_t = typename BasicJsonType::number_unsigned_t;
     using number_float_t = typename BasicJsonType::number_float_t;
     using string_t = typename BasicJsonType::string_t;
-    using lexer_t = lexer<BasicJsonType, InputAdapterType, DiscardValues>;
+    using lexer_t = lexer<BasicJsonType, InputAdapterType>;
     using token_type = typename lexer_t::token_type;
 
   public:
@@ -22630,9 +22580,10 @@ class parser
                     parser_callback_t<BasicJsonType> cb = nullptr,
                     const bool allow_exceptions_ = true,
                     const bool ignore_comments = false,
-                    const bool ignore_trailing_commas_ = false)
+                    const bool ignore_trailing_commas_ = false,
+                    const bool discard_number_values_ = false)
         : callback(std::move(cb))
-        , m_lexer(std::move(adapter), ignore_comments)
+        , m_lexer(std::move(adapter), ignore_comments, discard_number_values_)
         , allow_exceptions(allow_exceptions_)
         , ignore_trailing_commas(ignore_trailing_commas_)
     {
@@ -36995,7 +36946,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     // can be restored when json_pointer backwards compatibility is removed
     // friend ::nlohmann::json_pointer<StringType>;
 
-    template<typename BasicJsonType, typename InputType, bool DiscardValues>
+    template<typename BasicJsonType, typename InputType>
     friend class ::nlohmann::detail::parser;
     friend ::nlohmann::detail::serializer<basic_json>;
     template<typename BasicJsonType>
@@ -37028,11 +36979,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         detail::parser_callback_t<basic_json>cb = nullptr,
         const bool allow_exceptions = true,
         const bool ignore_comments = false,
-        const bool ignore_trailing_commas = false
+        const bool ignore_trailing_commas = false,
+        const bool discard_number_values = false
                                  )
     {
         return ::nlohmann::detail::parser<basic_json, InputAdapterType>(std::move(adapter),
-            std::move(cb), allow_exceptions, ignore_comments, ignore_trailing_commas);
+            std::move(cb), allow_exceptions, ignore_comments, ignore_trailing_commas, discard_number_values);
     }
 
   private:
@@ -39961,9 +39913,7 @@ public:
                             const bool ignore_comments,
                             const bool ignore_trailing_commas)
     {
-        // the parser and lexer that discard the values of tokens (see lexer)
+        return parser(std::forward<InputAdapterType>(adapter), nullptr, false, ignore_comments, ignore_trailing_commas, true).accept(true);
-        return ::nlohmann::detail::parser<basic_json, typename std::decay<InputAdapterType>::type, true>(std::forward<InputAdapterType>(adapter),
-                nullptr, false, ignore_comments, ignore_trailing_commas).accept(true);
     }
 
     /// generate SAX events from the input behind an already created adapter

single_include/nlohmann/json_view.hpp

@@ -157,6 +157,15 @@
     #define NLOHMANN_VIEW_NOINLINE
 #endif
 
+// GCC: a function compiled as written, without the clones in which interprocedural
+// constant propagation drops an argument that every caller passes as the same constant
+// (calling such a clone changes the code GCC generates for the parse loop that calls it)
+#if defined(__GNUC__) && !defined(__clang__)
+    #define NLOHMANN_VIEW_NOCLONE __attribute__((noclone))
+#else
+    #define NLOHMANN_VIEW_NOCLONE
+#endif
+
 #if defined(__GNUC__) || defined(__clang__)
     #define NLOHMANN_VIEW_NODISCARD __attribute__((warn_unused_result))
 #elif defined(_MSC_VER)
@@ -948,9 +957,12 @@ compares, and the UTF-8 check covers the bytes up to it. Returns where the
 string scan stops, like scan_string_run: before ill-formed UTF-8 and for the
 last bytes of the input, the bytes are checked one sequence at a time. Out of
 line, so that no constants of the check occupy registers in the parse loop.
-On x86-64, it is compiled for SSSE3 (see cpu_has_ssse3()).
+On x86-64, it is compiled for SSSE3 (see cpu_has_ssse3()). Not cloned: with
+the calls of accept()'s builder, GCC 16 would clone it without plain (always
+string_plain()), and calling the clone made json_document::parse() run 0.7-1.2 %
+more instructions.
 */
-NLOHMANN_VIEW_SSSE3_TARGET NLOHMANN_VIEW_NOINLINE inline const unsigned char* scan_string_vector(const unsigned char* p, const unsigned char* e, const std::uint8_t* plain) noexcept
+NLOHMANN_VIEW_SSSE3_TARGET NLOHMANN_VIEW_NOINLINE NLOHMANN_VIEW_NOCLONE inline const unsigned char* scan_string_vector(const unsigned char* p, const unsigned char* e, const std::uint8_t* plain) noexcept
 {
     using lookup = utf8_lookup4<>;
     const unsigned char* block = p;
@@ -1311,7 +1323,8 @@ 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 +1500,87 @@ 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 +1941,13 @@ 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)));
+            if (enabled(Store))
-            base = cold.m_doc.nodes;
+            {
-            out = base;
+                cold.m_doc.reserve(estimate_nodes(reinterpret_cast<const char*>(b), static_cast<std::size_t>(e - b)));
-            cap = base + cold.m_doc.node_capacity;
+                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 +2131,10 @@ 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 +2294,12 @@ 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 +2358,12 @@ indent_done:
 
         NLOHMANN_VIEW_ALWAYS_INLINE void close()
         {
-            node& n = base[cur_idx];
+            if (enabled(Store))
-            n.len = cur_count;
+            {
-            n.next = static_cast<std::uint32_t>(out - base) - cur_idx;
+                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 +2538,44 @@ 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)
+        return trailing_commas ? build_with<FloatType, true, true, NulIsEnd, true>(d, src, size, sentinel, failure)
-               : build_with<FloatType, true, false, NulIsEnd>(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)
+    return trailing_commas ? build_with<FloatType, false, true, NulIsEnd, true>(d, src, size, sentinel, failure)
-           : build_with<FloatType, false, false, NulIsEnd>(d, src, size, sentinel, failure);
+           : build_with<FloatType, false, false, NulIsEnd, true>(d, src, size, sentinel, failure);
 }
 
 }  // namespace view
@@ -10101,7 +10215,7 @@ 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 +10230,7 @@ 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 +10243,8 @@ 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 +10260,7 @@ 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 +10619,22 @@ 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 +10646,7 @@ 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 +10656,7 @@ 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 +10677,7 @@ 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 +10704,8 @@ 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 +10718,7 @@ 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 +10726,13 @@ 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 +10746,7 @@ 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 +10757,7 @@ 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 +10766,13 @@ 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 +10784,13 @@ 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 +10801,14 @@ 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);
     }
@@ -10807,6 +10939,7 @@ class tuple_element<N, ::nlohmann::detail::view::view_item<View>> // NOLINT(cert
 #undef NLOHMANN_VIEW_UNLIKELY
 #undef NLOHMANN_VIEW_ALWAYS_INLINE
 #undef NLOHMANN_VIEW_NOINLINE
+#undef NLOHMANN_VIEW_NOCLONE
 #undef NLOHMANN_VIEW_NODISCARD
 #undef NLOHMANN_VIEW_THROW
 #undef NLOHMANN_VIEW_LITTLE_ENDIAN

tests/src/unit-class_parser.cpp

@@ -2982,67 +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", R"(\"\\\/\b\f\n\r\t)", R"(\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;
-            std::string opened = "\"";
-            opened += str;
-            std::string closed = opened;
-            closed += '"';
-            std::vector<std::string> texts;
-            texts.push_back(closed);
-            texts.emplace_back("[");
-            texts.back() += closed;
-            texts.back() += ']';
-            texts.emplace_back("{");
-            texts.back() += closed;
-            texts.back() += ":1}";
-            texts.emplace_back("{\"k\":");
-            texts.back() += closed;
-            texts.back() += ',';
-            texts.back() += closed;
-            texts.back() += ":[";
-            texts.back() += closed;
-            texts.back() += "]}";
-            texts.emplace_back("[");
-            texts.back() += opened;
-            for (const std::string& text : texts)
-            {
-                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

tests/src/unit-json_view_builder.cpp

@@ -13,6 +13,7 @@
     #include <nlohmann/detail/view/builder.hpp>
     #include <nlohmann/detail/view/materialize.hpp>
     #include <nlohmann/detail/view/string_ref.hpp>
+    #include <nlohmann/json_view.hpp> // json_document::accept
 #else
     #include <nlohmann/json_view.hpp> // the single header contains the internal headers
 #endif
@@ -59,7 +60,8 @@ 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 +174,22 @@ 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 +441,133 @@ 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\\", R"(["\u12"])", R"(["\ud800"])", "[\"\x01\"]", "[\"\xff\"]", "[01]", "[1.]",
+                    "[.5]", "[-]", "[1e]", "// c\n[1]", "/* c */ {\"a\" /* x */ : 1}", "/* c", "[1] // c", "1e400", "-1e400", "123456789012345678901234567890",
+                    R"({"a":1,"a":2})", "[[[]]]", R"("\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 :
+                {
+                    63u, 64u, 65u, 66u, 200u, 1000u
+                })
+        {
+            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]", R"({"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", R"(\n\t\\)", R"(\u00e9\u00e9\u4e2d)", "\\u00e9\\u00e", "\\u00e9\\", "\\n\\q", R"(\n\ud83d\ude00\n)",
+                    R"(\ud83d\ude00\ud83d)", R"(\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-json_view_macros.cpp

@@ -25,7 +25,7 @@
 #endif
 
 // the view's own macros do not leak
-#if defined(NLOHMANN_VIEW_LIKELY) || defined(NLOHMANN_VIEW_UNLIKELY) || defined(NLOHMANN_VIEW_ALWAYS_INLINE) || defined(NLOHMANN_VIEW_NOINLINE) \
+#if defined(NLOHMANN_VIEW_LIKELY) || defined(NLOHMANN_VIEW_UNLIKELY) || defined(NLOHMANN_VIEW_ALWAYS_INLINE) || defined(NLOHMANN_VIEW_NOINLINE) || defined(NLOHMANN_VIEW_NOCLONE) \
     || defined(NLOHMANN_VIEW_NODISCARD) || defined(NLOHMANN_VIEW_THROW) || defined(NLOHMANN_VIEW_HAS_CPP_17) || defined(NLOHMANN_VIEW_LITTLE_ENDIAN) \
     || defined(NLOHMANN_VIEW_REPEAT16)
     #error "json_view.hpp leaks a macro"