Keep the serializer's buffers out of -Weffc++ and cpplint warnings

GCC's -Weffc++ asks for the three buffers in the member initialization
list, which would zero them again. They are now of a type with an empty
user-provided constructor (as the json_view builder's frame stack), so
they are listed there and stay uninitialized.

The 8-to-31-byte branch of the short-string writer no longer spans an
#if with a dangling else, which cpplint read as an else body without
braces.

dump() instructions (Apple clang, twitter/citm/canada, compact and
indented) are unchanged within noise (-0.3 % to +0.6 %).

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

docs/mkdocs/docs/api/basic_json_view/at.md

@@ -80,8 +80,7 @@ None of these exceptions carry a [`JSON_DIAGNOSTICS`](../macros/json_diagnostics
    Objects with 128 or more members get a hash index of their keys while parsing, so that a lookup in them takes
    constant time on average.
 2. Linear in `idx`: elements are skipped one at a time from the first one, since they are not a fixed size in the
-   index (unlike `BasicJsonType`'s array, which is random-access). Constant if no element of the array is an array
-   or object, since the elements are then adjacent in the index.
+   index (unlike `BasicJsonType`'s array, which is random-access).
 3. Linear in the number of reference tokens of `ptr` and, for each token, in the number of members of the object at
    that level (as 1.) or the index into the array (as 2.).
 

docs/mkdocs/docs/api/basic_json_view/back.md

@@ -28,8 +28,7 @@ This exception does not carry a [`JSON_DIAGNOSTICS`](../macros/json_diagnostics.
 
 Linear in the size of the array or object: unlike [`front()`](front.md), which only ever looks at the first
 element, `back()` has to walk every element to find where they end, since elements are not a fixed size in the
-index. Constant for an array none of whose elements is an array or object, since the elements are then adjacent
-in the index.
+index.
 
 ## Notes
 

docs/mkdocs/docs/api/basic_json_view/operator[].md

@@ -86,8 +86,7 @@ None of these exceptions carry a [`JSON_DIAGNOSTICS`](../macros/json_diagnostics
    Objects with 128 or more members get a hash index of their keys while parsing, so that a lookup in them takes
    constant time on average.
 2. Linear in `idx`: elements are skipped one at a time from the first one, since they are not a fixed size in the
-   index (unlike `BasicJsonType`'s array, which is random-access). Constant if no element of the array is an array
-   or object, since the elements are then adjacent in the index.
+   index (unlike `BasicJsonType`'s array, which is random-access).
 3. Linear in the number of reference tokens of `ptr` and, for each token, in the number of members of the object at
    that level (as 1.) or the index into the array (as 2.).
 

include/nlohmann/detail/macro_unscope.hpp

@@ -33,6 +33,7 @@
 #undef JSON_SCAN_SSSE3_TARGET
 #undef JSON_SCAN_VECTOR
 #undef JSON_SCAN_VECTOR_UTF8
+#undef JSON_DUMP_SHORT_STRINGS
 
 #ifndef JSON_TEST_KEEP_MACROS
     #undef JSON_CATCH

include/nlohmann/detail/output/serializer.hpp

@@ -34,6 +34,14 @@
 #include <nlohmann/detail/string_utils.hpp>
 #include <nlohmann/detail/value_t.hpp>
 
+// the short-string fast path of the serializer assembles words from little-endian
+// loads, see serializer::put_short_quoted()
+#if defined(_MSC_VER) || defined(__x86_64__) || defined(__i386__) || (defined(__BYTE_ORDER__) && defined(__ORDER_LITTLE_ENDIAN__) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__)
+    #define JSON_DUMP_SHORT_STRINGS 1
+#else
+    #define JSON_DUMP_SHORT_STRINGS 0
+#endif
+
 NLOHMANN_JSON_NAMESPACE_BEGIN
 namespace detail
 {
@@ -80,11 +88,14 @@ class serializer
                const std::size_t indent_step_ = 0,
                error_handler_t error_handler_ = error_handler_t::strict)
         : o(&s)
+        , number_buffer() // NOLINT(readability-redundant-member-init)
+        , string_buffer() // NOLINT(readability-redundant-member-init)
         , indent_char(ichar)
         , pretty_print(pretty_print_)
         , ensure_ascii(ensure_ascii_)
         , indent_step(indent_step_)
         , error_handler(error_handler_)
+        , write_buffer() // NOLINT(readability-redundant-member-init)
     {}
 
     // deleted because of pointer members
@@ -159,34 +170,27 @@ class serializer
 
                 if (pretty_print)
                 {
-                    put_literal("{\n");
-
                     // variable to hold indentation for recursive calls
                     const auto new_indent = next_indent(current_indent, indent_step);
 
+                    put_literal_indent("{\n", new_indent);
+
                     // first n-1 elements
                     auto i = val.m_data.m_value.object->cbegin();
                     for (std::size_t cnt = 0; cnt < val.m_data.m_value.object->size() - 1; ++cnt, ++i)
                     {
-                        put_indent(new_indent);
-                        put_char('"');
-                        dump_escaped(i->first);
-                        put_literal("\": ");
-                        dump_internal(i->second, new_indent, depth + 1);
-                        put_literal(",\n");
+                        put_quoted(i->first, "\": ");
+                        dump_element(i->second, new_indent, depth + 1);
+                        put_literal_indent(",\n", new_indent);
                     }
 
                     // last element
                     JSON_ASSERT(i != val.m_data.m_value.object->cend());
                     JSON_ASSERT(std::next(i) == val.m_data.m_value.object->cend());
-                    put_indent(new_indent);
-                    put_char('"');
-                    dump_escaped(i->first);
-                    put_literal("\": ");
-                    dump_internal(i->second, new_indent, depth + 1);
+                    put_quoted(i->first, "\": ");
+                    dump_element(i->second, new_indent, depth + 1);
 
-                    put_char('\n');
-                    put_indent(current_indent);
+                    put_literal_indent("\n", current_indent);
                     put_char('}');
                 }
                 else
@@ -197,20 +201,16 @@ class serializer
                     auto i = val.m_data.m_value.object->cbegin();
                     for (std::size_t cnt = 0; cnt < val.m_data.m_value.object->size() - 1; ++cnt, ++i)
                     {
-                        put_char('"');
-                        dump_escaped(i->first);
-                        put_literal("\":");
-                        dump_internal(i->second, current_indent, depth + 1);
+                        put_quoted(i->first, "\":");
+                        dump_element(i->second, current_indent, depth + 1);
                         put_char(',');
                     }
 
                     // last element
                     JSON_ASSERT(i != val.m_data.m_value.object->cend());
                     JSON_ASSERT(std::next(i) == val.m_data.m_value.object->cend());
-                    put_char('"');
-                    dump_escaped(i->first);
-                    put_literal("\":");
-                    dump_internal(i->second, current_indent, depth + 1);
+                    put_quoted(i->first, "\":");
+                    dump_element(i->second, current_indent, depth + 1);
 
                     put_char('}');
                 }
@@ -234,27 +234,24 @@ class serializer
 
                 if (pretty_print)
                 {
-                    put_literal("[\n");
-
                     // variable to hold indentation for recursive calls
                     const auto new_indent = next_indent(current_indent, indent_step);
 
+                    put_literal_indent("[\n", new_indent);
+
                     // first n-1 elements
                     for (auto i = val.m_data.m_value.array->cbegin();
                             i != val.m_data.m_value.array->cend() - 1; ++i)
                     {
-                        put_indent(new_indent);
-                        dump_internal(*i, new_indent, depth + 1);
-                        put_literal(",\n");
+                        dump_element(*i, new_indent, depth + 1);
+                        put_literal_indent(",\n", new_indent);
                     }
 
                     // last element
                     JSON_ASSERT(!val.m_data.m_value.array->empty());
-                    put_indent(new_indent);
-                    dump_internal(val.m_data.m_value.array->back(), new_indent, depth + 1);
+                    dump_element(val.m_data.m_value.array->back(), new_indent, depth + 1);
 
-                    put_char('\n');
-                    put_indent(current_indent);
+                    put_literal_indent("\n", current_indent);
                     put_char(']');
                 }
                 else
@@ -265,13 +262,13 @@ class serializer
                     for (auto i = val.m_data.m_value.array->cbegin();
                             i != val.m_data.m_value.array->cend() - 1; ++i)
                     {
-                        dump_internal(*i, current_indent, depth + 1);
+                        dump_element(*i, current_indent, depth + 1);
                         put_char(',');
                     }
 
                     // last element
                     JSON_ASSERT(!val.m_data.m_value.array->empty());
-                    dump_internal(val.m_data.m_value.array->back(), current_indent, depth + 1);
+                    dump_element(val.m_data.m_value.array->back(), current_indent, depth + 1);
 
                     put_char(']');
                 }
@@ -294,6 +291,27 @@ class serializer
     }
 
   private:
+    /*!
+    @brief serialize an element of a container
+
+    Most elements are scalars, which need none of the state dump_internal() keeps
+    for a container; writing them from here spares each the entry and exit of
+    that function.
+    */
+    JSON_HEDLEY_ALWAYS_INLINE void dump_element(const BasicJsonType& val,
+            const std::size_t current_indent,
+            const std::size_t depth)
+    {
+        if (val.m_data.m_type == value_t::object || val.m_data.m_type == value_t::array)
+        {
+            dump_internal(val, current_indent, depth);
+        }
+        else
+        {
+            dump_scalar(val, current_indent);
+        }
+    }
+
     /*!
     @brief write out @a val and everything below it without the call stack
 
@@ -353,16 +371,13 @@ class serializer
                     put_indent(frame.child_indent);
                 }
 
-                put_char('"');
-                dump_escaped(frame.object_it->first);
-
                 if (pretty_print)
                 {
-                    put_literal("\": ");
+                    put_quoted(frame.object_it->first, "\": ");
                 }
                 else
                 {
-                    put_literal("\":");
+                    put_quoted(frame.object_it->first, "\":");
                 }
 
                 const BasicJsonType& element = frame.object_it->second;
@@ -537,78 +552,13 @@ class serializer
         {
             case value_t::string:
             {
-                put_char('"');
-                dump_escaped(*val.m_data.m_value.string);
-                put_char('"');
+                dump_string_value(*val.m_data.m_value.string);
                 return;
             }
 
             case value_t::binary:
             {
-                if (pretty_print)
-                {
-                    put_literal("{\n");
-
-                    // variable to hold indentation for the bytes
-                    const auto new_indent = next_indent(current_indent, indent_step);
-
-                    put_indent(new_indent);
-
-                    put_literal("\"bytes\": [");
-
-                    if (!val.m_data.m_value.binary->empty())
-                    {
-                        for (auto i = val.m_data.m_value.binary->cbegin();
-                                i != val.m_data.m_value.binary->cend() - 1; ++i)
-                        {
-                            dump_byte(*i);
-                            put_literal(", ");
-                        }
-                        dump_byte(val.m_data.m_value.binary->back());
-                    }
-
-                    put_literal("],\n");
-                    put_indent(new_indent);
-
-                    put_literal("\"subtype\": ");
-                    if (val.m_data.m_value.binary->has_subtype())
-                    {
-                        dump_integer(val.m_data.m_value.binary->subtype());
-                    }
-                    else
-                    {
-                        put_literal("null");
-                    }
-                    put_char('\n');
-                    put_indent(current_indent);
-                    put_char('}');
-                }
-                else
-                {
-                    put_literal("{\"bytes\":[");
-
-                    if (!val.m_data.m_value.binary->empty())
-                    {
-                        for (auto i = val.m_data.m_value.binary->cbegin();
-                                i != val.m_data.m_value.binary->cend() - 1; ++i)
-                        {
-                            dump_byte(*i);
-                            put_char(',');
-                        }
-                        dump_byte(val.m_data.m_value.binary->back());
-                    }
-
-                    put_literal("],\"subtype\":");
-                    if (val.m_data.m_value.binary->has_subtype())
-                    {
-                        dump_integer(val.m_data.m_value.binary->subtype());
-                        put_char('}');
-                    }
-                    else
-                    {
-                        put_literal("null}");
-                    }
-                }
+                dump_binary_value(current_indent, *val.m_data.m_value.binary);
                 return;
             }
 
@@ -627,19 +577,19 @@ class serializer
 
             case value_t::number_integer:
             {
-                dump_integer(val.m_data.m_value.number_integer);
+                dump_signed_value(val.m_data.m_value.number_integer);
                 return;
             }
 
             case value_t::number_unsigned:
             {
-                dump_integer(val.m_data.m_value.number_unsigned);
+                dump_unsigned_value(val.m_data.m_value.number_unsigned);
                 return;
             }
 
             case value_t::number_float:
             {
-                dump_float(val.m_data.m_value.number_float);
+                dump_float_value(val.m_data.m_value.number_float);
                 return;
             }
 
@@ -662,6 +612,107 @@ class serializer
         }
     }
 
+    /// @brief write the string @a s in quotes; kept out of line, so that the
+    /// other scalars do not pay for its register needs (and the other way round)
+    JSON_HEDLEY_NEVER_INLINE void dump_string_value(const string_t& s)
+    {
+#if JSON_DUMP_SHORT_STRINGS
+        if (s.size() <= short_string_max && put_short_quoted(s, "\""))
+        {
+            return;
+        }
+#endif
+        put_char('"');
+        dump_escaped(s);
+        put_char('"');
+    }
+
+    // The numbers, and the rest of what dump_scalar() writes, are left to
+    // functions of their own as well: a single function holding all of them
+    // saves and restores every register any of them needs, on every call. Now
+    // dump_scalar() only dispatches, and each writer pays for what it uses.
+    JSON_HEDLEY_NEVER_INLINE void dump_signed_value(const number_integer_t x)
+    {
+        dump_integer(x);
+    }
+
+    JSON_HEDLEY_NEVER_INLINE void dump_unsigned_value(const number_unsigned_t x)
+    {
+        dump_integer(x);
+    }
+
+    JSON_HEDLEY_NEVER_INLINE void dump_float_value(const number_float_t x)
+    {
+        dump_float(x);
+    }
+
+    JSON_HEDLEY_NEVER_INLINE void dump_binary_value(const std::size_t current_indent, const typename BasicJsonType::binary_t& binary)
+    {
+        if (pretty_print)
+        {
+            put_literal("{\n");
+
+            // variable to hold indentation for the bytes
+            const auto new_indent = next_indent(current_indent, indent_step);
+
+            put_indent(new_indent);
+
+            put_literal("\"bytes\": [");
+
+            if (!binary.empty())
+            {
+                for (auto i = binary.cbegin();
+                        i != binary.cend() - 1; ++i)
+                {
+                    dump_byte(*i);
+                    put_literal(", ");
+                }
+                dump_byte(binary.back());
+            }
+
+            put_literal("],\n");
+            put_indent(new_indent);
+
+            put_literal("\"subtype\": ");
+            if (binary.has_subtype())
+            {
+                dump_integer(binary.subtype());
+            }
+            else
+            {
+                put_literal("null");
+            }
+            put_char('\n');
+            put_indent(current_indent);
+            put_char('}');
+        }
+        else
+        {
+            put_literal("{\"bytes\":[");
+
+            if (!binary.empty())
+            {
+                for (auto i = binary.cbegin();
+                        i != binary.cend() - 1; ++i)
+                {
+                    dump_byte(*i);
+                    put_char(',');
+                }
+                dump_byte(binary.back());
+            }
+
+            put_literal("],\"subtype\":");
+            if (binary.has_subtype())
+            {
+                dump_integer(binary.subtype());
+                put_char('}');
+            }
+            else
+            {
+                put_literal("null}");
+            }
+        }
+    }
 
     /*!
     @brief the indentation level to use for the children of the current value
@@ -678,6 +729,217 @@ class serializer
         return new_indent;
     }
 
+  private:
+    /*!
+    @brief append the string @a s in quotes, followed by @a tail
+
+    The quote, the string and @a tail (the closing quote, possibly with the
+    colon of an object key) are the bulk of what most documents consist of, and
+    most keys and many values are short and plain. Those are handled in one go
+    by put_short_quoted(); everything else takes the general path.
+    */
+    template<std::size_t N>
+    void put_quoted(const string_t& s, const char (&tail)[N]) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
+    {
+#if JSON_DUMP_SHORT_STRINGS
+        if (put_short_quoted(s, tail))
+        {
+            return;
+        }
+#endif
+        put_char('"');
+        dump_escaped(s);
+        put_literal(tail);
+    }
+
+#if JSON_DUMP_SHORT_STRINGS
+    /// the longest string put_short_quoted() takes
+    static constexpr std::size_t short_string_max = JSON_SCAN_VECTOR ? 32 : 16;
+
+    /// the high bit of every byte of @a v that is not printable ASCII or is a
+    /// quote, a backslash, or DEL (zero if the bytes can be copied as they are)
+    static std::uint64_t swar_not_plain(const std::uint64_t v) noexcept
+    {
+        constexpr std::uint64_t ones = 0x0101010101010101ull;
+        const std::uint64_t q = v ^ 0x2222222222222222ull; // '"'
+        const std::uint64_t b = v ^ 0x5C5C5C5C5C5C5C5Cull; // '\\'
+        return (((q - ones) & ~q) | ((b - ones) & ~b)         // == '"', == '\\'
+                | ((v - 0x2020202020202020ull) & ~v)          // < 0x20
+                | v | (v + ones))                             // >= 0x7F
+               & 0x8080808080808080ull;
+    }
+
+    template<typename WordType>
+    static WordType load_word(const char* p) noexcept
+    {
+        WordType w;
+        std::memcpy(&w, p, sizeof(w));
+        return w;
+    }
+
+    template<typename WordType>
+    static void store_word(char* p, const WordType w) noexcept
+    {
+        std::memcpy(p, &w, sizeof(w));
+    }
+
+    /*!
+    @brief write `"`, @a s and @a tail if @a s is short and needs no escaping
+
+    A string of up to 16 (32 with vector instructions) printable ASCII
+    characters (no quote, backslash, or DEL) is read with two overlapping loads
+    and written with two overlapping stores, instead of scanning it and calling
+    memcpy with a length that is only known at run time. Returns false, having
+    changed nothing, if @a s does not qualify or the write buffer lacks the
+    room.
+    */
+    template<std::size_t N>
+    bool put_short_quoted(const string_t& s, const char (&tail)[N]) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
+    {
+        const std::size_t n = s.size();
+        if (n > short_string_max || write_buffer_pos + n + N > write_buffer.size())
+        {
+            return false;
+        }
+
+        char* d = write_buffer.data() + write_buffer_pos + 1;
+        const char* const p = s.data();
+
+        if (n >= 8)
+        {
+#if JSON_SCAN_VECTOR
+            if (!(n >= 16 ? copy_plain_vectors(d, p, n) : copy_plain_halves(d, p, n)))
+            {
+                return false;
+            }
+#else
+            const auto a = load_word<std::uint64_t>(p);
+            const auto b = load_word<std::uint64_t>(p + n - 8);
+            if ((swar_not_plain(a) | swar_not_plain(b)) != 0)
+            {
+                return false;
+            }
+            store_word(d, a);
+            store_word(d + n - 8, b);
+#endif
+        }
+        else if (n >= 4)
+        {
+            const auto a = load_word<std::uint32_t>(p);
+            const auto b = load_word<std::uint32_t>(p + n - 4);
+            // the bytes above the string are filled with a plain character
+            const std::uint64_t w = a | (static_cast<std::uint64_t>(b) << (8 * (n - 4)))
+                                    | (0x4141414141414141ull << (8 * n));
+            if (swar_not_plain(w) != 0)
+            {
+                return false;
+            }
+            store_word(d, a);
+            store_word(d + n - 4, b);
+        }
+        else if (n >= 2)
+        {
+            const auto a = load_word<std::uint16_t>(p);
+            const auto b = load_word<std::uint16_t>(p + n - 2);
+            const std::uint64_t w = a | (static_cast<std::uint64_t>(b) << (8 * (n - 2)))
+                                    | (0x4141414141414141ull << (8 * n));
+            if (swar_not_plain(w) != 0)
+            {
+                return false;
+            }
+            store_word(d, a);
+            store_word(d + n - 2, b);
+        }
+        else if (n == 1)
+        {
+            const std::uint64_t w = static_cast<std::uint64_t>(static_cast<unsigned char>(p[0])) | (0x4141414141414141ull << 8u);
+            if (swar_not_plain(w) != 0)
+            {
+                return false;
+            }
+            *d = p[0];
+        }
+
+        d[-1] = '"';
+        std::memcpy(d + n, tail, N - 1);
+        write_buffer_pos += n + N;
+        return true;
+    }
+
+#if JSON_SCAN_VECTOR
+    /// copy the 8 to 15 bytes [@a p, @a p + @a n) to @a d with two overlapping
+    /// words, tested together as one vector, see copy_plain_vectors()
+    static bool copy_plain_halves(char* d, const char* p, const std::size_t n) noexcept
+    {
+#if JSON_SCAN_NEON
+        const uint8x8_t lo = vld1_u8(reinterpret_cast<const std::uint8_t*>(p));
+        const uint8x8_t hi = vld1_u8(reinterpret_cast<const std::uint8_t*>(p + n - 8));
+        const uint8x16_t in = vcombine_u8(lo, hi);
+        const uint8x16_t special = vorrq_u8(vorrq_u8(vceqq_u8(in, vdupq_n_u8('"')), vceqq_u8(in, vdupq_n_u8('\\'))),
+                                            vorrq_u8(vcltq_s8(vreinterpretq_s8_u8(in), vdupq_n_s8(0x20)), vceqq_u8(in, vdupq_n_u8(0x7F))));
+        if (vmaxvq_u8(special) != 0)
+        {
+            return false;
+        }
+        vst1_u8(reinterpret_cast<std::uint8_t*>(d), lo);
+        vst1_u8(reinterpret_cast<std::uint8_t*>(d + n - 8), hi);
+#else
+        const __m128i lo = _mm_loadl_epi64(static_cast<const __m128i*>(static_cast<const void*>(p))); // NOLINT(bugprone-casting-through-void)
+        const __m128i hi = _mm_loadl_epi64(static_cast<const __m128i*>(static_cast<const void*>(p + n - 8))); // NOLINT(bugprone-casting-through-void)
+        const __m128i in = _mm_unpacklo_epi64(lo, hi);
+        const __m128i special = _mm_or_si128(_mm_or_si128(_mm_cmpeq_epi8(in, _mm_set1_epi8('"')), _mm_cmpeq_epi8(in, _mm_set1_epi8('\\'))),
+                                             _mm_or_si128(_mm_cmplt_epi8(in, _mm_set1_epi8(0x20)), _mm_cmpeq_epi8(in, _mm_set1_epi8(0x7F))));
+        if (_mm_movemask_epi8(special) != 0)
+        {
+            return false;
+        }
+        _mm_storel_epi64(static_cast<__m128i*>(static_cast<void*>(d)), lo); // NOLINT(bugprone-casting-through-void)
+        _mm_storel_epi64(static_cast<__m128i*>(static_cast<void*>(d + n - 8)), hi); // NOLINT(bugprone-casting-through-void)
+#endif
+        return true;
+    }
+
+    /// copy the 16 to 32 bytes [@a p, @a p + @a n) to @a d with two overlapping
+    /// vectors, unless one of them is a quote, a backslash, a control
+    /// character, DEL or not ASCII
+    static bool copy_plain_vectors(char* d, const char* p, const std::size_t n) noexcept
+    {
+#if JSON_SCAN_NEON
+        const uint8x16_t a = vld1q_u8(reinterpret_cast<const std::uint8_t*>(p));
+        const uint8x16_t b = vld1q_u8(reinterpret_cast<const std::uint8_t*>(p + n - 16));
+        const uint8x16_t special = vorrq_u8(vorrq_u8(vorrq_u8(vceqq_u8(a, vdupq_n_u8('"')), vceqq_u8(a, vdupq_n_u8('\\'))),
+                                            vorrq_u8(vceqq_u8(b, vdupq_n_u8('"')), vceqq_u8(b, vdupq_n_u8('\\')))),
+                                            vorrq_u8(vorrq_u8(vcltq_s8(vreinterpretq_s8_u8(a), vdupq_n_s8(0x20)), vcltq_s8(vreinterpretq_s8_u8(b), vdupq_n_s8(0x20))),
+                                                vorrq_u8(vceqq_u8(a, vdupq_n_u8(0x7F)), vceqq_u8(b, vdupq_n_u8(0x7F)))));
+        if (vmaxvq_u8(special) != 0)
+        {
+            return false;
+        }
+        vst1q_u8(reinterpret_cast<std::uint8_t*>(d), a);
+        vst1q_u8(reinterpret_cast<std::uint8_t*>(d + n - 16), b);
+#else
+        const __m128i a = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(p))); // NOLINT(bugprone-casting-through-void)
+        const __m128i b = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(p + n - 16))); // NOLINT(bugprone-casting-through-void)
+        const __m128i quote = _mm_set1_epi8('"');
+        const __m128i backslash = _mm_set1_epi8('\\');
+        const __m128i space = _mm_set1_epi8(0x20);
+        const __m128i del = _mm_set1_epi8(0x7F);
+        const __m128i special = _mm_or_si128(_mm_or_si128(_mm_or_si128(_mm_cmpeq_epi8(a, quote), _mm_cmpeq_epi8(a, backslash)),
+                                             _mm_or_si128(_mm_cmpeq_epi8(b, quote), _mm_cmpeq_epi8(b, backslash))),
+                                             _mm_or_si128(_mm_or_si128(_mm_cmplt_epi8(a, space), _mm_cmplt_epi8(b, space)),
+                                                 _mm_or_si128(_mm_cmpeq_epi8(a, del), _mm_cmpeq_epi8(b, del))));
+        if (_mm_movemask_epi8(special) != 0)
+        {
+            return false;
+        }
+        _mm_storeu_si128(static_cast<__m128i*>(static_cast<void*>(d)), a); // NOLINT(bugprone-casting-through-void)
+        _mm_storeu_si128(static_cast<__m128i*>(static_cast<void*>(d + n - 16)), b); // NOLINT(bugprone-casting-through-void)
+#endif
+        return true;
+    }
+#endif
+#endif
+
   JSON_PRIVATE_UNLESS_TESTED:
     /*!
     @brief dump escaped string
@@ -690,14 +952,23 @@ class serializer
     @param[in] s  the string to escape
 
     Complexity: Linear in the length of string @a s.
+
+    @note kept out of line: with the short-string attempts in front of it gone
+          from here, compilers would otherwise inline it into @ref put_quoted
+          and then no longer into the loops that call that
     */
-    void dump_escaped(const string_t& s)
+    JSON_HEDLEY_NEVER_INLINE void dump_escaped(const string_t& s)
     {
         // Short strings of printable ASCII - most object keys and many values -
         // are checked byte by byte against a table and then copied in one go.
         // For them, this is cheaper than starting the vector scanner below,
         // whose setup costs more than such a string takes to scan. The same
         // check serves both values of ensure_ascii.
+        //
+        // Where put_short_quoted() exists and takes strings of up to 32 bytes,
+        // the callers have tried it already, and repeating the attempt only
+        // costs time for strings that need escaping or are not ASCII.
+#if !(JSON_DUMP_SHORT_STRINGS && JSON_SCAN_VECTOR)
         if (s.size() <= 32)
         {
             const auto& copyable = ascii_copyable();
@@ -719,6 +990,7 @@ class serializer
                 return;
             }
         }
+#endif
 
         // dispatch once here rather than test the flag inside the loop: it does
         // not change while a string is written, and folding it lets each of the
@@ -796,7 +1068,7 @@ class serializer
                         put_buffer(string_buffer, bytes);
                         bytes = 0;
                     }
-                    put_string(s, i, i + run);
+                    put_run(s, i, run);
                     bytes_after_last_accept = 0;
                     undumped_chars = 0;
                     i += run;
@@ -836,6 +1108,27 @@ class serializer
 
             const auto byte = static_cast<std::uint8_t>(s[i]);
 
+            if (EnsureAscii && state == UTF8_ACCEPT && byte >= 0x80)
+            {
+                // a run of well-formed multi-byte characters is escaped
+                // straight into the write buffer; an ill-formed sequence
+                // ends the run and is left to the byte-at-a-time path
+                if (bytes != 0)
+                {
+                    put_buffer(string_buffer, bytes);
+                    bytes = 0;
+                    bytes_after_last_accept = 0;
+                }
+                const std::size_t escaped = write_u_escapes(reinterpret_cast<const unsigned char*>(s.data()) + i, s.size() - i);
+                if (escaped != 0)
+                {
+                    bytes_after_last_accept = 0;
+                    undumped_chars = 0;
+                    i += escaped - 1;
+                    continue;
+                }
+            }
+
             switch (decode(state, codepoint, byte))
             {
                 case UTF8_ACCEPT:  // decode found a new code point
@@ -1113,6 +1406,21 @@ class serializer
             return;
         }
 
+        // the usual indentation: four words of the indentation character are
+        // stored unconditionally and only the part wanted is claimed, which
+        // spares the call of memset
+        if (JSON_HEDLEY_LIKELY(indent <= 32 && write_buffer_pos + 32 <= write_buffer.size()))
+        {
+            const std::uint64_t word = 0x0101010101010101ull * static_cast<unsigned char>(indent_char);
+            char* const d = write_buffer.data() + write_buffer_pos;
+            std::memcpy(d, &word, sizeof(word));
+            std::memcpy(d + 8, &word, sizeof(word));
+            std::memcpy(d + 16, &word, sizeof(word));
+            std::memcpy(d + 24, &word, sizeof(word));
+            write_buffer_pos += indent;
+            return;
+        }
+
         const std::size_t capacity = write_buffer.size();
 
         // fill whatever room is left in the buffer; this is the whole job
@@ -1146,6 +1454,32 @@ class serializer
         write_buffer_pos = indent;
     }
 
+    /*!
+    @brief append a string literal and then @a indent indentation characters
+
+    The usual line break and indentation go into the buffer with one check of
+    its room and four stores of the indentation, see @ref put_indent.
+    */
+    template<std::size_t N>
+    JSON_HEDLEY_ALWAYS_INLINE void put_literal_indent(const char (&s)[N], const std::size_t indent) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
+    {
+        constexpr std::size_t length = N - 1;
+        if (JSON_HEDLEY_LIKELY(indent <= 32 && write_buffer_pos + length + 32 <= write_buffer.size()))
+        {
+            const std::uint64_t word = 0x0101010101010101ull * static_cast<unsigned char>(indent_char);
+            char* const d = write_buffer.data() + write_buffer_pos;
+            std::memcpy(d, s, length);
+            std::memcpy(d + length, &word, sizeof(word));
+            std::memcpy(d + length + 8, &word, sizeof(word));
+            std::memcpy(d + length + 16, &word, sizeof(word));
+            std::memcpy(d + length + 24, &word, sizeof(word));
+            write_buffer_pos += length + indent;
+            return;
+        }
+        put_literal(s);
+        put_indent(indent);
+    }
+
     /*!
     @brief append a string literal to the write buffer
 
@@ -1170,6 +1504,28 @@ class serializer
         write_buffer_pos += length;
     }
 
+    /*!
+    @brief append the characters of @a str in [@a start, @a start + @a length)
+
+    A run of up to 16 characters with 16 or more in the string from @a start on
+    and in the write buffer from its end on is copied as a whole block of 16,
+    which spares the call of memcpy with a length known only at run time; the
+    surplus characters in the buffer are overwritten by what follows.
+    */
+    template<typename StringType>
+    void put_run(const StringType& str, const std::size_t start, const std::size_t length)
+    {
+        // a short run is the exception in text without escapes (CJK, accented
+        // Latin), for which this keeps the long path the fast one
+        if (JSON_HEDLEY_UNLIKELY(length <= 16 && start + 16 <= str.size() && write_buffer_pos + 16 <= write_buffer.size()))
+        {
+            std::memcpy(write_buffer.data() + write_buffer_pos, str.data() + start, 16);
+            write_buffer_pos += length;
+            return;
+        }
+        put_string(str, start, start + length);
+    }
+
     /*!
     @brief append the characters of @a str in [@a start, @a end)
 
@@ -1412,6 +1768,75 @@ class serializer
         return escapes;
     }
 
+    /*!
+    @brief escape the well-formed multi-byte characters at the start of @a data
+
+    Writes the "\\uXXXX" escape of each character (two of them for a character
+    above U+FFFF) straight into the write buffer, which is why the caller must
+    have written out what is pending in @ref string_buffer. Stops at the first
+    byte that is below 0x80 or starts an ill-formed or truncated sequence, which
+    the caller handles.
+
+    @return the number of bytes of @a data that have been escaped
+    */
+    JSON_HEDLEY_NEVER_INLINE std::size_t write_u_escapes(const unsigned char* data, std::size_t n)
+    {
+        constexpr const char* nibble_to_hex = "0123456789abcdef";
+        std::size_t i = 0;
+        while (i < n && data[i] >= 0x80)
+        {
+            const std::size_t length = validate_one_utf8(data + i, n - i);
+            if (length == 0)
+            {
+                break;
+            }
+
+            const auto b0 = static_cast<std::uint32_t>(data[i]);
+            const auto b1 = static_cast<std::uint32_t>(data[i + 1]);
+            std::uint32_t codepoint = 0;
+            switch (length)
+            {
+                case 2:
+                    codepoint = ((b0 & 0x1Fu) << 6u) | (b1 & 0x3Fu);
+                    break;
+                case 3:
+                    codepoint = ((b0 & 0x0Fu) << 12u) | ((b1 & 0x3Fu) << 6u) | (static_cast<std::uint32_t>(data[i + 2]) & 0x3Fu);
+                    break;
+                default:
+                    codepoint = ((b0 & 0x07u) << 18u) | ((b1 & 0x3Fu) << 12u) | ((static_cast<std::uint32_t>(data[i + 2]) & 0x3Fu) << 6u) | (static_cast<std::uint32_t>(data[i + 3]) & 0x3Fu);
+                    break;
+            }
+
+            // at most two escapes of six bytes each
+            if (JSON_HEDLEY_UNLIKELY(write_buffer.size() - write_buffer_pos < 12))
+            {
+                flush();
+            }
+            char* d = write_buffer.data() + write_buffer_pos;
+            if (codepoint > 0xFFFFu)
+            {
+                d = put_u_escape(d, static_cast<std::uint16_t>(0xD7C0u + (codepoint >> 10u)), nibble_to_hex);
+                codepoint = 0xDC00u + (codepoint & 0x3FFu);
+            }
+            d = put_u_escape(d, static_cast<std::uint16_t>(codepoint), nibble_to_hex);
+            write_buffer_pos = static_cast<std::size_t>(d - write_buffer.data());
+            i += length;
+        }
+        return i;
+    }
+
+    static char* put_u_escape(char* d, const std::uint16_t codeunit, const char* nibble_to_hex) noexcept
+    {
+        const auto unit = static_cast<std::uint32_t>(codeunit);
+        d[0] = '\\';
+        d[1] = 'u';
+        d[2] = nibble_to_hex[(unit >> 12u) & 0x0Fu];
+        d[3] = nibble_to_hex[(unit >> 8u) & 0x0Fu];
+        d[4] = nibble_to_hex[(unit >> 4u) & 0x0Fu];
+        d[5] = nibble_to_hex[unit & 0x0Fu];
+        return d + 6;
+    }
+
     /*!
      * @brief write a lowercase "\\uXXXX" escape sequence into @a string_buffer
      *
@@ -1769,11 +2194,22 @@ class serializer
     /// the output of the serializer (non-owning; the adapter lives at the call site)
     output_adapter_protocol<char>* o = nullptr;
 
+    /// a character buffer left uninitialized: the buffers below are written
+    /// before they are read (only the part written is ever read), and zeroing
+    /// 1.6 KiB took more than half of what dumping a small value costs (the
+    /// user-provided constructor keeps the member initialization, which
+    /// -Weffc++ asks for, from zeroing them)
+    template<std::size_t N>
+    struct uninitialized_buffer : std::array<char, N>
+    {
+        uninitialized_buffer() noexcept {} // NOLINT(modernize-use-equals-default,hicpp-use-equals-default,cppcoreguidelines-pro-type-member-init,hicpp-member-init): see above
+    };
+
     /// a (hopefully) large enough character buffer
-    std::array<char, 64> number_buffer{{}};
+    uninitialized_buffer<64> number_buffer;
 
     /// string buffer
-    std::array<char, 512> string_buffer{{}};
+    uninitialized_buffer<512> string_buffer;
 
     /// the indentation character
     const char indent_char;
@@ -1793,7 +2229,7 @@ class serializer
     /// buffer collecting output before it is flushed to the output adapter, so
     /// that the many small structural writes become few bulk writes
     static constexpr std::size_t write_buffer_size = 1024;
-    std::array<char, write_buffer_size> write_buffer{{}};
+    uninitialized_buffer<write_buffer_size> write_buffer;
     /// number of valid bytes currently held in @ref write_buffer
     std::size_t write_buffer_pos = 0;
 };

include/nlohmann/detail/view/builder.hpp

@@ -275,41 +275,11 @@ class builder
                 0, 0, '\b', 0, 0, 0, '\f', 0, 0, 0, 0, 0, 0, 0, '\n', 0, 0, 0, '\r', 0, '\t', 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
             }
         };
-        // The write position is kept in locals: the stores of characters into
-        // the arena may alias the members of the builder, which would then be
-        // reloaded after every one. It is stored back where the arena grows
-        // and at the end.
-        const unsigned char* const end = m_end;
         const std::size_t start = arena_used();
-        char* w = m_arena_write;
-        const char* w_end = m_arena_end;
-#define NLOHMANN_VIEW_ENSURE(n)                                                       \
-    if (NLOHMANN_VIEW_UNLIKELY(static_cast<std::size_t>(w_end - w) < (n)))            \
-    {                                                                                 \
-        m_arena_write = w;                                                            \
-        arena_grow(n);                                                                \
-        w = m_arena_write;                                                            \
-        w_end = m_arena_end;                                                          \
-    }
-        {
-            const auto n = static_cast<std::size_t>(p - s);
-            if (n <= 16 && end - s >= 16)
-            {
-                NLOHMANN_VIEW_ENSURE(16)
-                std::memcpy(w, s, 16);
-            }
-            else if (n != 0)
-            {
-                // (an empty run leaves an empty arena unallocated, and memcpy()
-                // must not be passed its null pointer even for zero bytes)
-                NLOHMANN_VIEW_ENSURE(n)
-                std::memcpy(w, s, n);
-            }
-            w += n;
-        }
+        arena_run(s, static_cast<std::size_t>(p - s));
         for (;;)
         {
-            if (p == end)
+            if (p == m_end)
             {
                 return failed(error_code::string_missing_quote, p);
             }
@@ -317,7 +287,6 @@ class builder
             if (c == '"')
             {
                 ++p;
-                m_arena_write = w;
                 return decoded{p, start, arena_used() - start};
             }
             if (c != '\\')
@@ -328,7 +297,7 @@ class builder
                 return failed(c < 0x20 ? error_code::string_control_character : error_code::string_utf8, p);
             }
             ++p;
-            if (p == end)
+            if (p == m_end)
             {
                 return failed(error_code::string_missing_quote, p);
             }
@@ -346,7 +315,7 @@ class builder
                     {
                         return failed(error_code::string_surrogate_low, p);
                     }
-                    if (end - p < 2 || p[0] != '\\' || p[1] != 'u')
+                    if (m_end - p < 2 || p[0] != '\\' || p[1] != 'u')
                     {
                         return failed(error_code::string_surrogate_high, p);
                     }
@@ -362,108 +331,27 @@ class builder
                     }
                     cp = 0x10000 + ((cp - 0xD800) << 10) + (lo - 0xDC00);
                 }
-                NLOHMANN_VIEW_ENSURE(4)
-                w = put_utf8(w, cp);
+                arena_ensure(4);
+                m_arena_write = put_utf8(m_arena_write, cp);
             }
             else if (NLOHMANN_VIEW_LIKELY(d < 128 && simple_escape[d] != 0))
             {
-                NLOHMANN_VIEW_ENSURE(1)
-                *w++ = simple_escape[d];
+                arena_ensure(1);
+                *m_arena_write++ = simple_escape[d];
             }
             else
             {
                 --p;
                 return failed(error_code::string_escape, p);
             }
-#if NLOHMANN_VIEW_NEON
-            if (p != end && *p == '\\')
+            if (p != m_end && *p == '\\')
             {
                 continue; // consecutive escapes ("\u00e4\u00f6"): no run in between
             }
-            // The first 16 bytes of the run are checked one by one, in predicted branches, and copied
-            // as one block: where the runs between escapes are short, the vector step below would put
-            // its longer dependency chain (load, compare, mask, count, add) on p for each of them,
-            // and be slower than these steps (the scanner of the keys works the same way)
-            {
-                if (end - p >= 16)
-                {
-                    const std::uint8_t* const plain = string_plain();
-                    std::size_t steps = 16;
-#define NLOHMANN_VIEW_STEP(i) if (NLOHMANN_VIEW_LIKELY(plain[p[i]] != 0)) {} else { steps = (i); goto run_found; }
-                    NLOHMANN_VIEW_REPEAT16(NLOHMANN_VIEW_STEP)
-#undef NLOHMANN_VIEW_STEP
-run_found:
-                    NLOHMANN_VIEW_ENSURE(16)
-                    std::memcpy(w, p, 16); // (only the first `steps` bytes are kept)
-                    w += steps;
-                    p += steps;
-                    if (steps < 16)
-                    {
-                        if (*p >= 0x80)
-                        {
-                            // non-ASCII: the UTF-8 check, and the rest of the run
-                            const unsigned char* const r = p;
-                            p = scan_string_run(p, end);
-                            const auto n = static_cast<std::size_t>(p - r);
-                            NLOHMANN_VIEW_ENSURE(n)
-                            std::memcpy(w, r, n);
-                            w += n;
-                        }
-                        continue;
-                    }
-                }
-            }
-#else
-            if (p != end && (*p == '\\' || *p == '"'))
-            {
-                continue; // consecutive escapes ("\u00e4\u00f6"), or the end of the string: no run in between
-            }
-#endif
-#if NLOHMANN_VIEW_VECTOR
-            // the plain bytes up to the next quote, backslash, or control
-            // character are copied as they are scanned, 16 bytes at a time
-            for (;;)
-            {
-                if (NLOHMANN_VIEW_UNLIKELY(end - p < 16))
-                {
-                    const unsigned char* const r = p;
-                    p = scan_string_run(p, end);
-                    const auto n = static_cast<std::size_t>(p - r);
-                    NLOHMANN_VIEW_ENSURE(n)
-                    std::memcpy(w, r, n);
-                    w += n;
-                    break;
-                }
-                NLOHMANN_VIEW_ENSURE(16)
-                const unsigned k = copy_plain_run16(p, w);
-                w += k;
-                p += k;
-                if (k == 16)
-                {
-                    continue;
-                }
-                if (NLOHMANN_VIEW_UNLIKELY(*p >= 0x80))
-                {
-                    // non-ASCII: the UTF-8 check, and the rest of the run
-                    const unsigned char* const r = p;
-                    p = scan_string_run(p, end);
-                    const auto n = static_cast<std::size_t>(p - r);
-                    NLOHMANN_VIEW_ENSURE(n)
-                    std::memcpy(w, r, n);
-                    w += n;
-                }
-                break;
-            }
-#else
             const unsigned char* const r = p;
-            p = scan_string_run(p, end);
-            const auto n = static_cast<std::size_t>(p - r);
-            NLOHMANN_VIEW_ENSURE(n)
-            std::memcpy(w, r, n);
-            w += n;
-#endif
+            p = scan_string_run(p, m_end);
+            arena_run(r, static_cast<std::size_t>(p - r));
         }
-#undef NLOHMANN_VIEW_ENSURE
     }
 
     /// does the float token [s, p) overflow FloatType? (parse() rejects it)
@@ -509,6 +397,14 @@ run_found:
         return m_arena_write != nullptr ? static_cast<std::size_t>(m_arena_write - m_doc.arena.data()) : 0;
     }
 
+    NLOHMANN_VIEW_ALWAYS_INLINE void arena_ensure(std::size_t n)
+    {
+        if (NLOHMANN_VIEW_UNLIKELY(static_cast<std::size_t>(m_arena_end - m_arena_write) < n))
+        {
+            arena_grow(n);
+        }
+    }
+
     NLOHMANN_VIEW_NOINLINE void arena_grow(std::size_t n)
     {
         const std::size_t used = arena_used();
@@ -517,6 +413,25 @@ run_found:
         m_arena_end = m_doc.arena.data() + m_doc.arena.size();
     }
 
+    /// append the run [r, r + n) to the arena; short runs as one fixed-size
+    /// 16-byte move when both sides have the room (no library call)
+    NLOHMANN_VIEW_ALWAYS_INLINE void arena_run(const unsigned char* r, std::size_t n)
+    {
+        if (n <= 16 && m_end - r >= 16)
+        {
+            arena_ensure(16);
+            std::memcpy(m_arena_write, r, 16);
+        }
+        else if (n != 0)
+        {
+            // (an empty run leaves an empty arena unallocated, and memcpy()
+            // must not be passed its null pointer even for zero bytes)
+            arena_ensure(n);
+            std::memcpy(m_arena_write, r, n);
+        }
+        m_arena_write += n;
+    }
+
     /// UTF-8 encoding of cp at w (room for 4 bytes); returns the position after
     /// it. (A returned pointer stays in a register; writing through a
     /// reference to m_arena_write would store and reload it around every byte.)
@@ -1039,11 +954,11 @@ indent_done:
                 ++p;
             }
             const unsigned char* const int_start = p;
-            if (cur() == '0')
+            if (p != e && *p == '0')
             {
                 ++p;
             }
-            else if (NLOHMANN_VIEW_LIKELY(cur() >= '1' && cur() <= '9'))
+            else if (NLOHMANN_VIEW_LIKELY(p != e && *p >= '1' && *p <= '9'))
             {
                 p = skip_digits(p + 1, e);
             }
@@ -1054,7 +969,7 @@ indent_done:
             const auto int_digits = static_cast<std::size_t>(p - int_start);
             std::size_t frac_digits = 0;
             bool is_float = false;
-            if (cur() == '.')
+            if (p != e && *p == '.')
             {
                 ++p;
                 const unsigned char* const f0 = p;
@@ -1067,20 +982,20 @@ indent_done:
                 is_float = true;
             }
             std::int64_t exponent = 0;
-            if ((cur() | 0x20) == 'e')
+            if (p != e && (*p | 0x20) == 'e')
             {
                 ++p;
                 bool exp_negative = false;
-                if (cur() == '+' || cur() == '-')
+                if (p != e && (*p == '+' || *p == '-'))
                 {
                     exp_negative = *p == '-';
                     ++p;
                 }
-                if (NLOHMANN_VIEW_UNLIKELY(!is_digit(cur())))
+                if (NLOHMANN_VIEW_UNLIKELY(p == e || !is_digit(*p)))
                 {
                     return fail(error_code::number_after_exponent);
                 }
-                while (is_digit(cur()))
+                while (p != e && is_digit(*p))
                 {
                     if (exponent < 100000)
                     {
@@ -1142,7 +1057,7 @@ indent_done:
             ++p; // opening quote
             const unsigned char* const s = p;
             p = scan_string_run<Value>(p, e);
-            if (NLOHMANN_VIEW_LIKELY(cur() == '"'))
+            if (NLOHMANN_VIEW_LIKELY(p != e && *p == '"'))
             {
                 push_node(value_t::string, 0, 0, static_cast<std::size_t>(s - b), static_cast<std::uint64_t>(p - s));
                 ++p;

include/nlohmann/detail/view/input.hpp

@@ -10,9 +10,6 @@
 
 #include <algorithm> // max
 #include <cstddef> // size_t
-#ifndef JSON_NO_IO
-    #include <cstdio> // FILE, fread
-#endif
 #include <istream> // istream, streambuf
 #include <string> // basic_string, char_traits, string
 #include <type_traits> // decay, integral_constant, is_array, is_const, is_integral, is_lvalue_reference, is_pointer, is_same, remove_cv, remove_extent, remove_pointer, remove_reference
@@ -157,37 +154,6 @@ inline void append_stream(std::string& buf, std::istream& is)
     is.clear(is.rdstate() | std::ios::eofbit);
 }
 
-/// a pointer to a C stream (never with JSON_NO_IO, which leaves out <cstdio>)
-template<typename T>
-struct is_c_stream
-#ifndef JSON_NO_IO
-    : std::is_same<T, std::FILE*>
-#else
-    : std::false_type
-#endif
-{};
-
-#ifndef JSON_NO_IO
-/// append the rest of a C stream: in blocks with fread, not character by
-/// character (the library's file adapter reads with fgetc);
-/// f is not null
-inline void append_file(std::string& buf, std::FILE* f)
-{
-    for (;;)
-    {
-        const std::size_t used = buf.size();
-        const std::size_t room = (std::max)(buf.capacity() - used, std::size_t{4096});
-        buf.resize(used + room);
-        const std::size_t got = std::fread(&buf[used], 1, room, f);
-        buf.resize(used + got);
-        if (got < room)
-        {
-            break; // end of file, or an error (as fgetc, which returns EOF for both)
-        }
-    }
-}
-#endif
-
 }  // namespace view
 }  // namespace detail
 NLOHMANN_JSON_NAMESPACE_END

include/nlohmann/detail/view/iterator.hpp

@@ -147,21 +147,20 @@ class view_item
 
     view_item(const iterator& it, std::size_t index)
         : m_it(it)
-        , m_position(index)
-    {}
+    {
+        if (!it.is_object_iterator())
+        {
+            m_index = std::to_string(index);
+        }
+    }
 
-    /// the member key, or the element index for arrays (as text made on the
-    /// first call, so that iterating over the values pays nothing for it)
+    /// the member key, or the element index for arrays
     string_view_t key() const
     {
         if (m_it.is_object_iterator())
         {
             return m_it.key();
         }
-        if (m_index.empty())
-        {
-            m_index = std::to_string(m_position);
-        }
         return string_view_t(m_index.data(), m_index.size());
     }
 
@@ -184,8 +183,7 @@ class view_item
 
   private:
     iterator m_it;
-    std::size_t m_position; ///< the index of an array element
-    mutable std::string m_index{}; ///< the text of m_position, once key() was called // NOLINT(readability-redundant-member-init)
+    std::string m_index{}; // NOLINT(readability-redundant-member-init)
 };
 
 /// the range returned by basic_json_view::items()

include/nlohmann/detail/view/lookup.hpp

@@ -166,10 +166,6 @@ const node* element_at(const document_data& d, const node* array, std::size_t id
     {
         return e + idx; // a growable block: one link per element
     }
-    if (array->next == array->len + 1u && (!nav::editable() || (array->flags & node_flags::moved) == 0))
-    {
-        return e + idx; // no element has a subtree: the elements are the nodes after the array
-    }
     for (std::size_t i = 0; i < idx; ++i)
     {
         e = document_data::after(e);
@@ -185,10 +181,6 @@ const node* last_child(const document_data& d, const node* container) noexcept
     const std::size_t value_offset = container->kind == static_cast<std::uint8_t>(value_t::object) ? 1 : 0;
     const node* const end = navigation<Editable>::end(d, container);
     const node* last = navigation<Editable>::first(d, container);
-    if (value_offset == 0 && container->next == container->len + 1u && (!navigation<Editable>::editable() || (container->flags & node_flags::moved) == 0))
-    {
-        return last + (container->len - 1u); // an array without subtrees: the elements are the nodes after it
-    }
     for (const node* c = document_data::after(last + value_offset); c != end; c = document_data::after(c + value_offset))
     {
         last = c;

include/nlohmann/detail/view/materialize.hpp

@@ -8,7 +8,7 @@
 
 #pragma once
 
-#include <array> // array
+#include <algorithm> // max
 #include <cstddef> // size_t
 #include <cstdint> // int64_t, uint8_t
 #include <string> // string
@@ -44,9 +44,8 @@ BasicJsonType materialize(const document_data& d, const node* n)
     using nav = navigation<Editable>;
 
     // the open containers: their next element (or key of the next member),
-    // their end, and whether they are objects; for the first 16 levels on the
-    // stack, else sized once from the document's deepest nesting (for a
-    // subtree an upper bound)
+    // their end, and whether they are objects; sized once from the
+    // document's deepest nesting (for a subtree an upper bound)
     struct frame
     {
         const node* pos;
@@ -54,43 +53,10 @@ BasicJsonType materialize(const document_data& d, const node* n)
         bool object;
     };
 
-    // a scalar needs neither the handler nor the stack of open containers
-    switch (static_cast<value_t>(n->kind))
-    {
-        case value_t::string:
-            return BasicJsonType(string_t(d.str(*n), n->len));
-        case value_t::number_integer:
-            return BasicJsonType(static_cast<typename BasicJsonType::number_integer_t>(static_cast<std::int64_t>(integer_bits(*n))));
-        case value_t::number_unsigned:
-            return BasicJsonType(static_cast<typename BasicJsonType::number_unsigned_t>(integer_bits(*n)));
-        case value_t::number_float:
-            return BasicJsonType(float_value<typename BasicJsonType::number_float_t>(d, *n));
-        case value_t::boolean:
-            return BasicJsonType((n->flags & node_flags::is_true) != 0);
-        case value_t::null:
-            return BasicJsonType(nullptr);
-        case value_t::object:
-        case value_t::array:
-        case value_t::binary:
-        case value_t::discarded:
-        default:
-            break;
-    }
-
     BasicJsonType result;
     sax_t sax(result, true);
     const string_t no_token{};
-    // (shallow subtrees on the stack: a call for a small value then allocates only for the value)
-    std::array<frame, 16> shallow; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): filled as containers open
-    std::vector<frame> deep{};
-    frame* open = shallow.data();
-    std::size_t capacity = shallow.size();
-    if (d.max_depth > capacity)
-    {
-        deep.resize(d.max_depth);
-        open = deep.data();
-        capacity = deep.size();
-    }
+    std::vector<frame> open((std::max)(d.max_depth, std::size_t{1}));
     std::size_t depth = 0;
     for (;;)
     {
@@ -110,13 +76,9 @@ BasicJsonType materialize(const document_data& d, const node* n)
                 {
                     sax.start_array(n->len);
                 }
-                if (NLOHMANN_VIEW_UNLIKELY(depth == capacity))
+                if (NLOHMANN_VIEW_UNLIKELY(depth == open.size()))
                 {
-                    // (deeper than the recorded nesting, e.g. after edits)
-                    deep.assign(open, open + depth);
-                    deep.resize(depth * 2);
-                    open = deep.data();
-                    capacity = deep.size();
+                    open.resize(depth * 2); // (deeper than the recorded nesting, e.g. after edits)
                 }
                 open[depth++] = frame{nav::first(d, n), nav::end(d, n), object};
                 break;

include/nlohmann/detail/view/object_index.hpp

@@ -47,96 +47,27 @@ constexpr std::size_t index_max_displacement = 64;
 static_assert(document_data::index_min_members >= 2 * index_max_displacement,
               "a table must be much larger than the probe window of a lookup");
 
-/// hash of a key: its bytes, eight at a time (in a fixed byte order), where the
-/// last word may overlap the one before (so that no loop over single bytes is
-/// needed); a key of fewer than eight bytes is read as two overlapping words of
-/// four or two bytes (in the native byte order: the hash is not stored, and the
-/// same on both sides of a lookup)
+/// hash of a key: its bytes, eight at a time, in a fixed byte order
 inline std::uint64_t key_hash(const char* s, std::size_t n) noexcept
 {
     std::uint64_t h = 0x9E3779B97F4A7C15u * (n + 1);
     const auto* p = reinterpret_cast<const unsigned char*>(s); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
+    while (n >= 8)
+    {
+        h = (h ^ read_eight_bytes(p)) * 0xBF58476D1CE4E5B9u;
+        h ^= h >> 29u;
+        p += 8;
+        n -= 8;
+    }
     std::uint64_t w = 0;
-    if (n >= 8)
+    for (std::size_t i = 0; i < n; ++i)
     {
-        const unsigned char* const last = p + n - 8;
-        while (p < last)
-        {
-            h = (h ^ read_eight_bytes(p)) * 0xBF58476D1CE4E5B9u;
-            h ^= h >> 29u;
-            p += 8;
-        }
-        w = read_eight_bytes(last);
+        w |= static_cast<std::uint64_t>(p[i]) << (8u * i);
     }
-    else if (n >= 4)
-    {
-        std::uint32_t head = 0;
-        std::uint32_t tail = 0;
-        std::memcpy(&head, p, 4);
-        std::memcpy(&tail, p + n - 4, 4);
-        w = static_cast<std::uint64_t>(head) | (static_cast<std::uint64_t>(tail) << 32u);
-    }
-    else if (n >= 2)
-    {
-        std::uint16_t head = 0;
-        std::uint16_t tail = 0;
-        std::memcpy(&head, p, 2);
-        std::memcpy(&tail, p + n - 2, 2);
-        w = static_cast<std::uint64_t>(head) | (static_cast<std::uint64_t>(tail) << 16u);
-    }
-    else if (n == 1)
-    {
-        w = p[0];
-    }
-    // (a product only carries bits upwards, and the slot is taken from the low
-    // bits: the high bits of the last word are folded down before the multiplication)
-    h = (h ^ w ^ (w >> 29u)) * 0x94D049BB133111EBu;
+    h = (h ^ w) * 0x94D049BB133111EBu;
     return h ^ (h >> 31u);
 }
 
-/// whether the n <= 16 bytes at a and b are equal, as two overlapping words
-/// (the first and the last 8, 4, or 2 bytes) and without a call
-NLOHMANN_VIEW_ALWAYS_INLINE bool same_short_bytes(const unsigned char* a, const unsigned char* b, std::size_t n) noexcept
-{
-    if (n >= 8)
-    {
-        std::uint64_t x0 = 0;
-        std::uint64_t x1 = 0;
-        std::uint64_t y0 = 0;
-        std::uint64_t y1 = 0;
-        std::memcpy(&x0, a, 8);
-        std::memcpy(&x1, a + n - 8, 8);
-        std::memcpy(&y0, b, 8);
-        std::memcpy(&y1, b + n - 8, 8);
-        return x0 == y0 && x1 == y1;
-    }
-    if (n >= 4)
-    {
-        std::uint32_t x0 = 0;
-        std::uint32_t x1 = 0;
-        std::uint32_t y0 = 0;
-        std::uint32_t y1 = 0;
-        std::memcpy(&x0, a, 4);
-        std::memcpy(&x1, a + n - 4, 4);
-        std::memcpy(&y0, b, 4);
-        std::memcpy(&y1, b + n - 4, 4);
-        return x0 == y0 && x1 == y1;
-    }
-    if (n >= 2)
-    {
-        std::uint16_t x0 = 0;
-        std::uint16_t x1 = 0;
-        std::uint16_t y0 = 0;
-        std::uint16_t y1 = 0;
-        std::memcpy(&x0, a, 2);
-        std::memcpy(&x1, a + n - 2, 2);
-        std::memcpy(&y0, b, 2);
-        std::memcpy(&y1, b + n - 2, 2);
-        return x0 == y0 && x1 == y1;
-    }
-    return n == 0 || *a == *b;
-}
-
 /// build the table of a large object
 inline void build_object_index(document_data& d, node* obj)
 {
@@ -201,27 +132,6 @@ inline const node* find_indexed(const document_data& d, const node* obj, const c
     const document_data::object_index& ix = d.indexes[obj->extra - 1u];
     const std::uint32_t* const table = d.index_slots.data() + ix.start;
     std::size_t slot = conditional_static_cast<std::size_t>(key_hash(key, n)) & ix.mask;
-    const auto* const k_bytes = reinterpret_cast<const unsigned char*>(key); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-    // (the loop for longer keys comes first, as the code is laid out; it is not the more common case)
-    if (NLOHMANN_VIEW_UNLIKELY(n <= 16))
-    {
-        // (up to 16 bytes, the bytes are compared as two words, without a call)
-        for (std::size_t distance = 0; distance <= index_max_displacement; ++distance)
-        {
-            const std::uint32_t s = table[slot];
-            if (s == 0)
-            {
-                return nullptr;
-            }
-            const node* const k = obj + s;
-            if (k->len == n && same_short_bytes(reinterpret_cast<const unsigned char*>(d.str(*k)), k_bytes, n)) // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-            {
-                return k;
-            }
-            slot = (slot + 1) & ix.mask;
-        }
-        return nullptr;
-    }
     for (std::size_t distance = 0; distance <= index_max_displacement; ++distance)
     {
         const std::uint32_t s = table[slot];

include/nlohmann/detail/view/simd.hpp

@@ -116,34 +116,6 @@ NLOHMANN_VIEW_ALWAYS_INLINE const unsigned char* vector_plain_run(const unsigned
     }
     return p;
 }
-
-/*!
-@brief copy 16 bytes from p to w, and find the first quote, backslash,
-control character, or non-ASCII byte among them
-
-The bytes are copied whether or not they are all plain (the caller has room
-for 16 bytes and keeps only the plain ones).
-
-@return the offset of that byte, or 16 if there is none
-*/
-NLOHMANN_VIEW_ALWAYS_INLINE unsigned copy_plain_run16(const unsigned char* p, char* w) noexcept
-{
-#if NLOHMANN_VIEW_NEON
-    const uint8x16_t in = vld1q_u8(p);
-    vst1q_u8(reinterpret_cast<std::uint8_t*>(w), in); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-    const uint8x16_t special = vorrq_u8(vorrq_u8(vceqq_u8(in, vdupq_n_u8('"')), vceqq_u8(in, vdupq_n_u8('\\'))),
-                                        vcltq_s8(vreinterpretq_s8_u8(in), vdupq_n_s8(0x20)));
-    const std::uint64_t bits = vget_lane_u64(vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(special), 4)), 0);
-    return bits != 0 ? static_cast<unsigned>(count_trailing_zeros(bits) >> 2u) : 16u;
-#else
-    const __m128i in = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(p))); // NOLINT(bugprone-casting-through-void)
-    _mm_storeu_si128(static_cast<__m128i*>(static_cast<void*>(w)), in); // NOLINT(bugprone-casting-through-void)
-    const __m128i special = _mm_or_si128(_mm_or_si128(_mm_cmpeq_epi8(in, _mm_set1_epi8('"')), _mm_cmpeq_epi8(in, _mm_set1_epi8('\\'))),
-                                         _mm_cmplt_epi8(in, _mm_set1_epi8(0x20)));
-    const auto bits = static_cast<std::uint64_t>(static_cast<unsigned>(_mm_movemask_epi8(special)));
-    return bits != 0 ? static_cast<unsigned>(count_trailing_zeros(bits)) : 16u;
-#endif
-}
 #endif
 
 #if NLOHMANN_VIEW_SSSE3_DISPATCH

include/nlohmann/json_view.hpp

@@ -295,7 +295,7 @@ class basic_json_view
             }
             detail::view::throw_type_error(305, "cannot use operator[] with a numeric argument with ", type_name());
         }
-        return idx < m_node->len ? element(idx) : basic_json_view();
+        return idx < m_node->len ? basic_json_view(m_doc, navigation::value(detail::view::element_at<Editable>(*m_doc, m_node, idx))) : basic_json_view();
     }
 
     /// any other integer type (int, unsigned, long, std::int64_t, ...; a
@@ -358,7 +358,7 @@ class basic_json_view
         {
             detail::view::throw_out_of_range(401, detail::concat("array index ", std::to_string(idx), " is out of range"));
         }
-        return element(idx);
+        return basic_json_view(m_doc, navigation::value(detail::view::element_at<Editable>(*m_doc, m_node, idx)));
     }
 
     /// any other integer type, see operator[]; negative values are out of
@@ -392,13 +392,7 @@ class basic_json_view
 
     string_t value(string_view_t key, const char* default_value) const
     {
-        if (NLOHMANN_VIEW_UNLIKELY(!is_object()))
-        {
-            detail::view::throw_type_error(306, "cannot use value() with ", type_name());
-        }
-        // (the default is made only if there is no such member)
-        const basic_json_view r = lookup(key);
-        return r.is_discarded() ? string_t(default_value) : r.template get<string_t>();
+        return value(key, string_t(default_value));
     }
 
     /// the value a JSON pointer refers to converted to T, or the default
@@ -417,12 +411,7 @@ class basic_json_view
 
     string_t value(const json_pointer& ptr, const char* default_value) const
     {
-        if (NLOHMANN_VIEW_UNLIKELY(!is_structured()))
-        {
-            detail::view::throw_type_error(306, "cannot use value() with ", type_name());
-        }
-        const basic_json_view r = detail::view::resolve_pointer(*this, detail::json_pointer_access::reference_tokens(ptr), detail::view::pointer_mode::value);
-        return r.is_discarded() ? string_t(default_value) : r.template get<string_t>();
+        return value(ptr, string_t(default_value));
     }
 
     /// the first element or member value; a primitive value itself. Throws
@@ -444,8 +433,7 @@ class basic_json_view
     {
         if (is_structured() && m_node->len != 0)
         {
-            return unedited() ? basic_json_view(m_doc, detail::view::last_child<false>(*m_doc, m_node) + (is_object() ? 1 : 0))
-                   : basic_json_view(m_doc, navigation::value(detail::view::last_child<Editable>(*m_doc, m_node) + (is_object() ? 1 : 0)));
+            return basic_json_view(m_doc, navigation::value(detail::view::last_child<Editable>(*m_doc, m_node) + (is_object() ? 1 : 0)));
         }
         return front();
     }
@@ -462,8 +450,7 @@ class basic_json_view
         {
             return end();
         }
-        const node* const k = unedited() ? detail::view::find_member<false>(*m_doc, m_node, key.data(), key.size())
-                              : detail::view::find_member<Editable>(*m_doc, m_node, key.data(), key.size());
+        const node* const k = detail::view::find_member<Editable>(*m_doc, m_node, key.data(), key.size());
         return k != nullptr ? iterator(m_doc, k, true) : end();
     }
 
@@ -480,8 +467,7 @@ class basic_json_view
     /// whether this is an object with a member with this key
     bool contains(string_view_t key) const
     {
-        return is_object() && (unedited() ? detail::view::find_member<false>(*m_doc, m_node, key.data(), key.size()) != nullptr
-                               : detail::view::find_member<Editable>(*m_doc, m_node, key.data(), key.size()) != nullptr);
+        return is_object() && detail::view::find_member<Editable>(*m_doc, m_node, key.data(), key.size()) != nullptr;
     }
 
     bool contains(const char* key) const
@@ -641,14 +627,7 @@ class basic_json_view
         // the compact writer keeps 64 bytes of slack, so that it does not grow
         // the buffer just before the end
         const std::size_t estimate = source_extent() + (style.pretty ? source_extent() / 2 : 0) + 160;
-        if (unedited())
-        {
-            detail::view::view_serializer<BasicJsonType, false>(*m_doc, out, estimate, style).dump(m_node);
-        }
-        else
-        {
-            detail::view::view_serializer<BasicJsonType, Editable>(*m_doc, out, estimate, style).dump(m_node);
-        }
+        detail::view::view_serializer<BasicJsonType, Editable>(*m_doc, out, estimate, style).dump(m_node);
         return out;
     }
 
@@ -728,7 +707,7 @@ class basic_json_view
         {
             return BasicJsonType(value_t::discarded);
         }
-        return unedited() ? detail::view::materialize<BasicJsonType, false>(*m_doc, m_node) : detail::view::materialize<BasicJsonType, Editable>(*m_doc, m_node);
+        return detail::view::materialize<BasicJsonType, Editable>(*m_doc, m_node);
     }
 
     /// byte offset of this value in the source text (for strings: of the
@@ -806,32 +785,10 @@ class basic_json_view
     /// (object required)
     NLOHMANN_VIEW_ALWAYS_INLINE basic_json_view lookup(string_view_t key) const noexcept
     {
-        if (unedited())
-        {
-            const node* const k = detail::view::find_member<false>(*m_doc, m_node, key.data(), key.size());
-            return k != nullptr ? basic_json_view(m_doc, k + 1) : basic_json_view();
-        }
         const node* const k = detail::view::find_member<Editable>(*m_doc, m_node, key.data(), key.size());
         return k != nullptr ? basic_json_view(m_doc, navigation::value(k + 1)) : basic_json_view();
     }
 
-    /// whether the document has not been edited yet: until the first edit, its index is walked like that of a
-    /// read-only document (nothing is moved or linked), which is cheaper
-    NLOHMANN_VIEW_ALWAYS_INLINE bool unedited() const noexcept
-    {
-        return !navigation::editable() || m_doc->edits == nullptr;
-    }
-
-    /// the element of an array at an index below its size
-    NLOHMANN_VIEW_ALWAYS_INLINE basic_json_view element(size_type idx) const
-    {
-        if (unedited())
-        {
-            return basic_json_view(m_doc, detail::view::element_at<false>(*m_doc, m_node, idx));
-        }
-        return basic_json_view(m_doc, navigation::value(detail::view::element_at<Editable>(*m_doc, m_node, idx)));
-    }
-
     // --- get() dispatch ---
 
     bool get_impl(detail::view::value_tag<bool> /*unused*/, detail::priority_tag<2> /*unused*/) const
@@ -1571,8 +1528,7 @@ class basic_json_document
         // NOLINTBEGIN(readability-avoid-nested-conditional-operator): a constant expression of C++11
         append_input_impl(buf, std::forward<T>(input), std::integral_constant < int, detail::is_contiguous_byte_container<D>::value ? 0
                           : std::is_base_of<std::istream, D>::value ? 1
-                          : detail::view::is_adapter_input<D>::value ? 2
-                          : detail::view::is_c_stream<D>::value ? 4 : 3 > {});
+                          : detail::view::is_adapter_input<D>::value ? 2 : 3 > {});
         // NOLINTEND(readability-avoid-nested-conditional-operator)
     }
 
@@ -1594,19 +1550,6 @@ class basic_json_document
         detail::view::append_adapter(buf, std::move(input.ia));
     }
 
-#ifndef JSON_NO_IO
-    static void append_input_impl(std::string& buf, std::FILE* file, std::integral_constant<int, 4> /*C stream*/)
-    {
-        if (file == nullptr)
-        {
-            // (as before: the library's adapter decides what a null stream yields)
-            detail::view::append_adapter(buf, detail::input_adapter(file));
-            return;
-        }
-        detail::view::append_file(buf, file);
-    }
-#endif
-
     template<typename T>
     static void append_input_impl(std::string& buf, T&& input, std::integral_constant<int, 3> /*other*/)
     {

single_include/nlohmann/json.hpp

@@ -30178,6 +30178,14 @@ NLOHMANN_JSON_NAMESPACE_END
 // #include <nlohmann/detail/value_t.hpp>
 
 
+// the short-string fast path of the serializer assembles words from little-endian
+// loads, see serializer::put_short_quoted()
+#if defined(_MSC_VER) || defined(__x86_64__) || defined(__i386__) || (defined(__BYTE_ORDER__) && defined(__ORDER_LITTLE_ENDIAN__) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__)
+    #define JSON_DUMP_SHORT_STRINGS 1
+#else
+    #define JSON_DUMP_SHORT_STRINGS 0
+#endif
+
 NLOHMANN_JSON_NAMESPACE_BEGIN
 namespace detail
 {
@@ -30224,11 +30232,14 @@ class serializer
                const std::size_t indent_step_ = 0,
                error_handler_t error_handler_ = error_handler_t::strict)
         : o(&s)
+        , number_buffer() // NOLINT(readability-redundant-member-init)
+        , string_buffer() // NOLINT(readability-redundant-member-init)
         , indent_char(ichar)
         , pretty_print(pretty_print_)
         , ensure_ascii(ensure_ascii_)
         , indent_step(indent_step_)
         , error_handler(error_handler_)
+        , write_buffer() // NOLINT(readability-redundant-member-init)
     {}
 
     // deleted because of pointer members
@@ -30303,34 +30314,27 @@ class serializer
 
                 if (pretty_print)
                 {
-                    put_literal("{\n");
-
                     // variable to hold indentation for recursive calls
                     const auto new_indent = next_indent(current_indent, indent_step);
 
+                    put_literal_indent("{\n", new_indent);
+
                     // first n-1 elements
                     auto i = val.m_data.m_value.object->cbegin();
                     for (std::size_t cnt = 0; cnt < val.m_data.m_value.object->size() - 1; ++cnt, ++i)
                     {
-                        put_indent(new_indent);
-                        put_char('"');
-                        dump_escaped(i->first);
-                        put_literal("\": ");
-                        dump_internal(i->second, new_indent, depth + 1);
-                        put_literal(",\n");
+                        put_quoted(i->first, "\": ");
+                        dump_element(i->second, new_indent, depth + 1);
+                        put_literal_indent(",\n", new_indent);
                     }
 
                     // last element
                     JSON_ASSERT(i != val.m_data.m_value.object->cend());
                     JSON_ASSERT(std::next(i) == val.m_data.m_value.object->cend());
-                    put_indent(new_indent);
-                    put_char('"');
-                    dump_escaped(i->first);
-                    put_literal("\": ");
-                    dump_internal(i->second, new_indent, depth + 1);
+                    put_quoted(i->first, "\": ");
+                    dump_element(i->second, new_indent, depth + 1);
 
-                    put_char('\n');
-                    put_indent(current_indent);
+                    put_literal_indent("\n", current_indent);
                     put_char('}');
                 }
                 else
@@ -30341,20 +30345,16 @@ class serializer
                     auto i = val.m_data.m_value.object->cbegin();
                     for (std::size_t cnt = 0; cnt < val.m_data.m_value.object->size() - 1; ++cnt, ++i)
                     {
-                        put_char('"');
-                        dump_escaped(i->first);
-                        put_literal("\":");
-                        dump_internal(i->second, current_indent, depth + 1);
+                        put_quoted(i->first, "\":");
+                        dump_element(i->second, current_indent, depth + 1);
                         put_char(',');
                     }
 
                     // last element
                     JSON_ASSERT(i != val.m_data.m_value.object->cend());
                     JSON_ASSERT(std::next(i) == val.m_data.m_value.object->cend());
-                    put_char('"');
-                    dump_escaped(i->first);
-                    put_literal("\":");
-                    dump_internal(i->second, current_indent, depth + 1);
+                    put_quoted(i->first, "\":");
+                    dump_element(i->second, current_indent, depth + 1);
 
                     put_char('}');
                 }
@@ -30378,27 +30378,24 @@ class serializer
 
                 if (pretty_print)
                 {
-                    put_literal("[\n");
-
                     // variable to hold indentation for recursive calls
                     const auto new_indent = next_indent(current_indent, indent_step);
 
+                    put_literal_indent("[\n", new_indent);
+
                     // first n-1 elements
                     for (auto i = val.m_data.m_value.array->cbegin();
                             i != val.m_data.m_value.array->cend() - 1; ++i)
                     {
-                        put_indent(new_indent);
-                        dump_internal(*i, new_indent, depth + 1);
-                        put_literal(",\n");
+                        dump_element(*i, new_indent, depth + 1);
+                        put_literal_indent(",\n", new_indent);
                     }
 
                     // last element
                     JSON_ASSERT(!val.m_data.m_value.array->empty());
-                    put_indent(new_indent);
-                    dump_internal(val.m_data.m_value.array->back(), new_indent, depth + 1);
+                    dump_element(val.m_data.m_value.array->back(), new_indent, depth + 1);
 
-                    put_char('\n');
-                    put_indent(current_indent);
+                    put_literal_indent("\n", current_indent);
                     put_char(']');
                 }
                 else
@@ -30409,13 +30406,13 @@ class serializer
                     for (auto i = val.m_data.m_value.array->cbegin();
                             i != val.m_data.m_value.array->cend() - 1; ++i)
                     {
-                        dump_internal(*i, current_indent, depth + 1);
+                        dump_element(*i, current_indent, depth + 1);
                         put_char(',');
                     }
 
                     // last element
                     JSON_ASSERT(!val.m_data.m_value.array->empty());
-                    dump_internal(val.m_data.m_value.array->back(), current_indent, depth + 1);
+                    dump_element(val.m_data.m_value.array->back(), current_indent, depth + 1);
 
                     put_char(']');
                 }
@@ -30438,6 +30435,27 @@ class serializer
     }
 
   private:
+    /*!
+    @brief serialize an element of a container
+
+    Most elements are scalars, which need none of the state dump_internal() keeps
+    for a container; writing them from here spares each the entry and exit of
+    that function.
+    */
+    JSON_HEDLEY_ALWAYS_INLINE void dump_element(const BasicJsonType& val,
+            const std::size_t current_indent,
+            const std::size_t depth)
+    {
+        if (val.m_data.m_type == value_t::object || val.m_data.m_type == value_t::array)
+        {
+            dump_internal(val, current_indent, depth);
+        }
+        else
+        {
+            dump_scalar(val, current_indent);
+        }
+    }
+
     /*!
     @brief write out @a val and everything below it without the call stack
 
@@ -30497,16 +30515,13 @@ class serializer
                     put_indent(frame.child_indent);
                 }
 
-                put_char('"');
-                dump_escaped(frame.object_it->first);
-
                 if (pretty_print)
                 {
-                    put_literal("\": ");
+                    put_quoted(frame.object_it->first, "\": ");
                 }
                 else
                 {
-                    put_literal("\":");
+                    put_quoted(frame.object_it->first, "\":");
                 }
 
                 const BasicJsonType& element = frame.object_it->second;
@@ -30681,78 +30696,13 @@ class serializer
         {
             case value_t::string:
             {
-                put_char('"');
-                dump_escaped(*val.m_data.m_value.string);
-                put_char('"');
+                dump_string_value(*val.m_data.m_value.string);
                 return;
             }
 
             case value_t::binary:
             {
-                if (pretty_print)
-                {
-                    put_literal("{\n");
-
-                    // variable to hold indentation for the bytes
-                    const auto new_indent = next_indent(current_indent, indent_step);
-
-                    put_indent(new_indent);
-
-                    put_literal("\"bytes\": [");
-
-                    if (!val.m_data.m_value.binary->empty())
-                    {
-                        for (auto i = val.m_data.m_value.binary->cbegin();
-                                i != val.m_data.m_value.binary->cend() - 1; ++i)
-                        {
-                            dump_byte(*i);
-                            put_literal(", ");
-                        }
-                        dump_byte(val.m_data.m_value.binary->back());
-                    }
-
-                    put_literal("],\n");
-                    put_indent(new_indent);
-
-                    put_literal("\"subtype\": ");
-                    if (val.m_data.m_value.binary->has_subtype())
-                    {
-                        dump_integer(val.m_data.m_value.binary->subtype());
-                    }
-                    else
-                    {
-                        put_literal("null");
-                    }
-                    put_char('\n');
-                    put_indent(current_indent);
-                    put_char('}');
-                }
-                else
-                {
-                    put_literal("{\"bytes\":[");
-
-                    if (!val.m_data.m_value.binary->empty())
-                    {
-                        for (auto i = val.m_data.m_value.binary->cbegin();
-                                i != val.m_data.m_value.binary->cend() - 1; ++i)
-                        {
-                            dump_byte(*i);
-                            put_char(',');
-                        }
-                        dump_byte(val.m_data.m_value.binary->back());
-                    }
-
-                    put_literal("],\"subtype\":");
-                    if (val.m_data.m_value.binary->has_subtype())
-                    {
-                        dump_integer(val.m_data.m_value.binary->subtype());
-                        put_char('}');
-                    }
-                    else
-                    {
-                        put_literal("null}");
-                    }
-                }
+                dump_binary_value(current_indent, *val.m_data.m_value.binary);
                 return;
             }
 
@@ -30771,19 +30721,19 @@ class serializer
 
             case value_t::number_integer:
             {
-                dump_integer(val.m_data.m_value.number_integer);
+                dump_signed_value(val.m_data.m_value.number_integer);
                 return;
             }
 
             case value_t::number_unsigned:
             {
-                dump_integer(val.m_data.m_value.number_unsigned);
+                dump_unsigned_value(val.m_data.m_value.number_unsigned);
                 return;
             }
 
             case value_t::number_float:
             {
-                dump_float(val.m_data.m_value.number_float);
+                dump_float_value(val.m_data.m_value.number_float);
                 return;
             }
 
@@ -30806,6 +30756,107 @@ class serializer
         }
     }
 
+    /// @brief write the string @a s in quotes; kept out of line, so that the
+    /// other scalars do not pay for its register needs (and the other way round)
+    JSON_HEDLEY_NEVER_INLINE void dump_string_value(const string_t& s)
+    {
+#if JSON_DUMP_SHORT_STRINGS
+        if (s.size() <= short_string_max && put_short_quoted(s, "\""))
+        {
+            return;
+        }
+#endif
+        put_char('"');
+        dump_escaped(s);
+        put_char('"');
+    }
+
+    // The numbers, and the rest of what dump_scalar() writes, are left to
+    // functions of their own as well: a single function holding all of them
+    // saves and restores every register any of them needs, on every call. Now
+    // dump_scalar() only dispatches, and each writer pays for what it uses.
+    JSON_HEDLEY_NEVER_INLINE void dump_signed_value(const number_integer_t x)
+    {
+        dump_integer(x);
+    }
+
+    JSON_HEDLEY_NEVER_INLINE void dump_unsigned_value(const number_unsigned_t x)
+    {
+        dump_integer(x);
+    }
+
+    JSON_HEDLEY_NEVER_INLINE void dump_float_value(const number_float_t x)
+    {
+        dump_float(x);
+    }
+
+    JSON_HEDLEY_NEVER_INLINE void dump_binary_value(const std::size_t current_indent, const typename BasicJsonType::binary_t& binary)
+    {
+        if (pretty_print)
+        {
+            put_literal("{\n");
+
+            // variable to hold indentation for the bytes
+            const auto new_indent = next_indent(current_indent, indent_step);
+
+            put_indent(new_indent);
+
+            put_literal("\"bytes\": [");
+
+            if (!binary.empty())
+            {
+                for (auto i = binary.cbegin();
+                        i != binary.cend() - 1; ++i)
+                {
+                    dump_byte(*i);
+                    put_literal(", ");
+                }
+                dump_byte(binary.back());
+            }
+
+            put_literal("],\n");
+            put_indent(new_indent);
+
+            put_literal("\"subtype\": ");
+            if (binary.has_subtype())
+            {
+                dump_integer(binary.subtype());
+            }
+            else
+            {
+                put_literal("null");
+            }
+            put_char('\n');
+            put_indent(current_indent);
+            put_char('}');
+        }
+        else
+        {
+            put_literal("{\"bytes\":[");
+
+            if (!binary.empty())
+            {
+                for (auto i = binary.cbegin();
+                        i != binary.cend() - 1; ++i)
+                {
+                    dump_byte(*i);
+                    put_char(',');
+                }
+                dump_byte(binary.back());
+            }
+
+            put_literal("],\"subtype\":");
+            if (binary.has_subtype())
+            {
+                dump_integer(binary.subtype());
+                put_char('}');
+            }
+            else
+            {
+                put_literal("null}");
+            }
+        }
+    }
 
     /*!
     @brief the indentation level to use for the children of the current value
@@ -30822,6 +30873,217 @@ class serializer
         return new_indent;
     }
 
+  private:
+    /*!
+    @brief append the string @a s in quotes, followed by @a tail
+
+    The quote, the string and @a tail (the closing quote, possibly with the
+    colon of an object key) are the bulk of what most documents consist of, and
+    most keys and many values are short and plain. Those are handled in one go
+    by put_short_quoted(); everything else takes the general path.
+    */
+    template<std::size_t N>
+    void put_quoted(const string_t& s, const char (&tail)[N]) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
+    {
+#if JSON_DUMP_SHORT_STRINGS
+        if (put_short_quoted(s, tail))
+        {
+            return;
+        }
+#endif
+        put_char('"');
+        dump_escaped(s);
+        put_literal(tail);
+    }
+
+#if JSON_DUMP_SHORT_STRINGS
+    /// the longest string put_short_quoted() takes
+    static constexpr std::size_t short_string_max = JSON_SCAN_VECTOR ? 32 : 16;
+
+    /// the high bit of every byte of @a v that is not printable ASCII or is a
+    /// quote, a backslash, or DEL (zero if the bytes can be copied as they are)
+    static std::uint64_t swar_not_plain(const std::uint64_t v) noexcept
+    {
+        constexpr std::uint64_t ones = 0x0101010101010101ull;
+        const std::uint64_t q = v ^ 0x2222222222222222ull; // '"'
+        const std::uint64_t b = v ^ 0x5C5C5C5C5C5C5C5Cull; // '\\'
+        return (((q - ones) & ~q) | ((b - ones) & ~b)         // == '"', == '\\'
+                | ((v - 0x2020202020202020ull) & ~v)          // < 0x20
+                | v | (v + ones))                             // >= 0x7F
+               & 0x8080808080808080ull;
+    }
+
+    template<typename WordType>
+    static WordType load_word(const char* p) noexcept
+    {
+        WordType w;
+        std::memcpy(&w, p, sizeof(w));
+        return w;
+    }
+
+    template<typename WordType>
+    static void store_word(char* p, const WordType w) noexcept
+    {
+        std::memcpy(p, &w, sizeof(w));
+    }
+
+    /*!
+    @brief write `"`, @a s and @a tail if @a s is short and needs no escaping
+
+    A string of up to 16 (32 with vector instructions) printable ASCII
+    characters (no quote, backslash, or DEL) is read with two overlapping loads
+    and written with two overlapping stores, instead of scanning it and calling
+    memcpy with a length that is only known at run time. Returns false, having
+    changed nothing, if @a s does not qualify or the write buffer lacks the
+    room.
+    */
+    template<std::size_t N>
+    bool put_short_quoted(const string_t& s, const char (&tail)[N]) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
+    {
+        const std::size_t n = s.size();
+        if (n > short_string_max || write_buffer_pos + n + N > write_buffer.size())
+        {
+            return false;
+        }
+
+        char* d = write_buffer.data() + write_buffer_pos + 1;
+        const char* const p = s.data();
+
+        if (n >= 8)
+        {
+#if JSON_SCAN_VECTOR
+            if (!(n >= 16 ? copy_plain_vectors(d, p, n) : copy_plain_halves(d, p, n)))
+            {
+                return false;
+            }
+#else
+            const auto a = load_word<std::uint64_t>(p);
+            const auto b = load_word<std::uint64_t>(p + n - 8);
+            if ((swar_not_plain(a) | swar_not_plain(b)) != 0)
+            {
+                return false;
+            }
+            store_word(d, a);
+            store_word(d + n - 8, b);
+#endif
+        }
+        else if (n >= 4)
+        {
+            const auto a = load_word<std::uint32_t>(p);
+            const auto b = load_word<std::uint32_t>(p + n - 4);
+            // the bytes above the string are filled with a plain character
+            const std::uint64_t w = a | (static_cast<std::uint64_t>(b) << (8 * (n - 4)))
+                                    | (0x4141414141414141ull << (8 * n));
+            if (swar_not_plain(w) != 0)
+            {
+                return false;
+            }
+            store_word(d, a);
+            store_word(d + n - 4, b);
+        }
+        else if (n >= 2)
+        {
+            const auto a = load_word<std::uint16_t>(p);
+            const auto b = load_word<std::uint16_t>(p + n - 2);
+            const std::uint64_t w = a | (static_cast<std::uint64_t>(b) << (8 * (n - 2)))
+                                    | (0x4141414141414141ull << (8 * n));
+            if (swar_not_plain(w) != 0)
+            {
+                return false;
+            }
+            store_word(d, a);
+            store_word(d + n - 2, b);
+        }
+        else if (n == 1)
+        {
+            const std::uint64_t w = static_cast<std::uint64_t>(static_cast<unsigned char>(p[0])) | (0x4141414141414141ull << 8u);
+            if (swar_not_plain(w) != 0)
+            {
+                return false;
+            }
+            *d = p[0];
+        }
+
+        d[-1] = '"';
+        std::memcpy(d + n, tail, N - 1);
+        write_buffer_pos += n + N;
+        return true;
+    }
+
+#if JSON_SCAN_VECTOR
+    /// copy the 8 to 15 bytes [@a p, @a p + @a n) to @a d with two overlapping
+    /// words, tested together as one vector, see copy_plain_vectors()
+    static bool copy_plain_halves(char* d, const char* p, const std::size_t n) noexcept
+    {
+#if JSON_SCAN_NEON
+        const uint8x8_t lo = vld1_u8(reinterpret_cast<const std::uint8_t*>(p));
+        const uint8x8_t hi = vld1_u8(reinterpret_cast<const std::uint8_t*>(p + n - 8));
+        const uint8x16_t in = vcombine_u8(lo, hi);
+        const uint8x16_t special = vorrq_u8(vorrq_u8(vceqq_u8(in, vdupq_n_u8('"')), vceqq_u8(in, vdupq_n_u8('\\'))),
+                                            vorrq_u8(vcltq_s8(vreinterpretq_s8_u8(in), vdupq_n_s8(0x20)), vceqq_u8(in, vdupq_n_u8(0x7F))));
+        if (vmaxvq_u8(special) != 0)
+        {
+            return false;
+        }
+        vst1_u8(reinterpret_cast<std::uint8_t*>(d), lo);
+        vst1_u8(reinterpret_cast<std::uint8_t*>(d + n - 8), hi);
+#else
+        const __m128i lo = _mm_loadl_epi64(static_cast<const __m128i*>(static_cast<const void*>(p))); // NOLINT(bugprone-casting-through-void)
+        const __m128i hi = _mm_loadl_epi64(static_cast<const __m128i*>(static_cast<const void*>(p + n - 8))); // NOLINT(bugprone-casting-through-void)
+        const __m128i in = _mm_unpacklo_epi64(lo, hi);
+        const __m128i special = _mm_or_si128(_mm_or_si128(_mm_cmpeq_epi8(in, _mm_set1_epi8('"')), _mm_cmpeq_epi8(in, _mm_set1_epi8('\\'))),
+                                             _mm_or_si128(_mm_cmplt_epi8(in, _mm_set1_epi8(0x20)), _mm_cmpeq_epi8(in, _mm_set1_epi8(0x7F))));
+        if (_mm_movemask_epi8(special) != 0)
+        {
+            return false;
+        }
+        _mm_storel_epi64(static_cast<__m128i*>(static_cast<void*>(d)), lo); // NOLINT(bugprone-casting-through-void)
+        _mm_storel_epi64(static_cast<__m128i*>(static_cast<void*>(d + n - 8)), hi); // NOLINT(bugprone-casting-through-void)
+#endif
+        return true;
+    }
+
+    /// copy the 16 to 32 bytes [@a p, @a p + @a n) to @a d with two overlapping
+    /// vectors, unless one of them is a quote, a backslash, a control
+    /// character, DEL or not ASCII
+    static bool copy_plain_vectors(char* d, const char* p, const std::size_t n) noexcept
+    {
+#if JSON_SCAN_NEON
+        const uint8x16_t a = vld1q_u8(reinterpret_cast<const std::uint8_t*>(p));
+        const uint8x16_t b = vld1q_u8(reinterpret_cast<const std::uint8_t*>(p + n - 16));
+        const uint8x16_t special = vorrq_u8(vorrq_u8(vorrq_u8(vceqq_u8(a, vdupq_n_u8('"')), vceqq_u8(a, vdupq_n_u8('\\'))),
+                                            vorrq_u8(vceqq_u8(b, vdupq_n_u8('"')), vceqq_u8(b, vdupq_n_u8('\\')))),
+                                            vorrq_u8(vorrq_u8(vcltq_s8(vreinterpretq_s8_u8(a), vdupq_n_s8(0x20)), vcltq_s8(vreinterpretq_s8_u8(b), vdupq_n_s8(0x20))),
+                                                vorrq_u8(vceqq_u8(a, vdupq_n_u8(0x7F)), vceqq_u8(b, vdupq_n_u8(0x7F)))));
+        if (vmaxvq_u8(special) != 0)
+        {
+            return false;
+        }
+        vst1q_u8(reinterpret_cast<std::uint8_t*>(d), a);
+        vst1q_u8(reinterpret_cast<std::uint8_t*>(d + n - 16), b);
+#else
+        const __m128i a = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(p))); // NOLINT(bugprone-casting-through-void)
+        const __m128i b = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(p + n - 16))); // NOLINT(bugprone-casting-through-void)
+        const __m128i quote = _mm_set1_epi8('"');
+        const __m128i backslash = _mm_set1_epi8('\\');
+        const __m128i space = _mm_set1_epi8(0x20);
+        const __m128i del = _mm_set1_epi8(0x7F);
+        const __m128i special = _mm_or_si128(_mm_or_si128(_mm_or_si128(_mm_cmpeq_epi8(a, quote), _mm_cmpeq_epi8(a, backslash)),
+                                             _mm_or_si128(_mm_cmpeq_epi8(b, quote), _mm_cmpeq_epi8(b, backslash))),
+                                             _mm_or_si128(_mm_or_si128(_mm_cmplt_epi8(a, space), _mm_cmplt_epi8(b, space)),
+                                                 _mm_or_si128(_mm_cmpeq_epi8(a, del), _mm_cmpeq_epi8(b, del))));
+        if (_mm_movemask_epi8(special) != 0)
+        {
+            return false;
+        }
+        _mm_storeu_si128(static_cast<__m128i*>(static_cast<void*>(d)), a); // NOLINT(bugprone-casting-through-void)
+        _mm_storeu_si128(static_cast<__m128i*>(static_cast<void*>(d + n - 16)), b); // NOLINT(bugprone-casting-through-void)
+#endif
+        return true;
+    }
+#endif
+#endif
+
   JSON_PRIVATE_UNLESS_TESTED:
     /*!
     @brief dump escaped string
@@ -30834,14 +31096,23 @@ class serializer
     @param[in] s  the string to escape
 
     Complexity: Linear in the length of string @a s.
+
+    @note kept out of line: with the short-string attempts in front of it gone
+          from here, compilers would otherwise inline it into @ref put_quoted
+          and then no longer into the loops that call that
     */
-    void dump_escaped(const string_t& s)
+    JSON_HEDLEY_NEVER_INLINE void dump_escaped(const string_t& s)
     {
         // Short strings of printable ASCII - most object keys and many values -
         // are checked byte by byte against a table and then copied in one go.
         // For them, this is cheaper than starting the vector scanner below,
         // whose setup costs more than such a string takes to scan. The same
         // check serves both values of ensure_ascii.
+        //
+        // Where put_short_quoted() exists and takes strings of up to 32 bytes,
+        // the callers have tried it already, and repeating the attempt only
+        // costs time for strings that need escaping or are not ASCII.
+#if !(JSON_DUMP_SHORT_STRINGS && JSON_SCAN_VECTOR)
         if (s.size() <= 32)
         {
             const auto& copyable = ascii_copyable();
@@ -30863,6 +31134,7 @@ class serializer
                 return;
             }
         }
+#endif
 
         // dispatch once here rather than test the flag inside the loop: it does
         // not change while a string is written, and folding it lets each of the
@@ -30940,7 +31212,7 @@ class serializer
                         put_buffer(string_buffer, bytes);
                         bytes = 0;
                     }
-                    put_string(s, i, i + run);
+                    put_run(s, i, run);
                     bytes_after_last_accept = 0;
                     undumped_chars = 0;
                     i += run;
@@ -30980,6 +31252,27 @@ class serializer
 
             const auto byte = static_cast<std::uint8_t>(s[i]);
 
+            if (EnsureAscii && state == UTF8_ACCEPT && byte >= 0x80)
+            {
+                // a run of well-formed multi-byte characters is escaped
+                // straight into the write buffer; an ill-formed sequence
+                // ends the run and is left to the byte-at-a-time path
+                if (bytes != 0)
+                {
+                    put_buffer(string_buffer, bytes);
+                    bytes = 0;
+                    bytes_after_last_accept = 0;
+                }
+                const std::size_t escaped = write_u_escapes(reinterpret_cast<const unsigned char*>(s.data()) + i, s.size() - i);
+                if (escaped != 0)
+                {
+                    bytes_after_last_accept = 0;
+                    undumped_chars = 0;
+                    i += escaped - 1;
+                    continue;
+                }
+            }
+
             switch (decode(state, codepoint, byte))
             {
                 case UTF8_ACCEPT:  // decode found a new code point
@@ -31257,6 +31550,21 @@ class serializer
             return;
         }
 
+        // the usual indentation: four words of the indentation character are
+        // stored unconditionally and only the part wanted is claimed, which
+        // spares the call of memset
+        if (JSON_HEDLEY_LIKELY(indent <= 32 && write_buffer_pos + 32 <= write_buffer.size()))
+        {
+            const std::uint64_t word = 0x0101010101010101ull * static_cast<unsigned char>(indent_char);
+            char* const d = write_buffer.data() + write_buffer_pos;
+            std::memcpy(d, &word, sizeof(word));
+            std::memcpy(d + 8, &word, sizeof(word));
+            std::memcpy(d + 16, &word, sizeof(word));
+            std::memcpy(d + 24, &word, sizeof(word));
+            write_buffer_pos += indent;
+            return;
+        }
+
         const std::size_t capacity = write_buffer.size();
 
         // fill whatever room is left in the buffer; this is the whole job
@@ -31290,6 +31598,32 @@ class serializer
         write_buffer_pos = indent;
     }
 
+    /*!
+    @brief append a string literal and then @a indent indentation characters
+
+    The usual line break and indentation go into the buffer with one check of
+    its room and four stores of the indentation, see @ref put_indent.
+    */
+    template<std::size_t N>
+    JSON_HEDLEY_ALWAYS_INLINE void put_literal_indent(const char (&s)[N], const std::size_t indent) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
+    {
+        constexpr std::size_t length = N - 1;
+        if (JSON_HEDLEY_LIKELY(indent <= 32 && write_buffer_pos + length + 32 <= write_buffer.size()))
+        {
+            const std::uint64_t word = 0x0101010101010101ull * static_cast<unsigned char>(indent_char);
+            char* const d = write_buffer.data() + write_buffer_pos;
+            std::memcpy(d, s, length);
+            std::memcpy(d + length, &word, sizeof(word));
+            std::memcpy(d + length + 8, &word, sizeof(word));
+            std::memcpy(d + length + 16, &word, sizeof(word));
+            std::memcpy(d + length + 24, &word, sizeof(word));
+            write_buffer_pos += length + indent;
+            return;
+        }
+        put_literal(s);
+        put_indent(indent);
+    }
+
     /*!
     @brief append a string literal to the write buffer
 
@@ -31314,6 +31648,28 @@ class serializer
         write_buffer_pos += length;
     }
 
+    /*!
+    @brief append the characters of @a str in [@a start, @a start + @a length)
+
+    A run of up to 16 characters with 16 or more in the string from @a start on
+    and in the write buffer from its end on is copied as a whole block of 16,
+    which spares the call of memcpy with a length known only at run time; the
+    surplus characters in the buffer are overwritten by what follows.
+    */
+    template<typename StringType>
+    void put_run(const StringType& str, const std::size_t start, const std::size_t length)
+    {
+        // a short run is the exception in text without escapes (CJK, accented
+        // Latin), for which this keeps the long path the fast one
+        if (JSON_HEDLEY_UNLIKELY(length <= 16 && start + 16 <= str.size() && write_buffer_pos + 16 <= write_buffer.size()))
+        {
+            std::memcpy(write_buffer.data() + write_buffer_pos, str.data() + start, 16);
+            write_buffer_pos += length;
+            return;
+        }
+        put_string(str, start, start + length);
+    }
+
     /*!
     @brief append the characters of @a str in [@a start, @a end)
 
@@ -31556,6 +31912,75 @@ class serializer
         return escapes;
     }
 
+    /*!
+    @brief escape the well-formed multi-byte characters at the start of @a data
+
+    Writes the "\\uXXXX" escape of each character (two of them for a character
+    above U+FFFF) straight into the write buffer, which is why the caller must
+    have written out what is pending in @ref string_buffer. Stops at the first
+    byte that is below 0x80 or starts an ill-formed or truncated sequence, which
+    the caller handles.
+
+    @return the number of bytes of @a data that have been escaped
+    */
+    JSON_HEDLEY_NEVER_INLINE std::size_t write_u_escapes(const unsigned char* data, std::size_t n)
+    {
+        constexpr const char* nibble_to_hex = "0123456789abcdef";
+        std::size_t i = 0;
+        while (i < n && data[i] >= 0x80)
+        {
+            const std::size_t length = validate_one_utf8(data + i, n - i);
+            if (length == 0)
+            {
+                break;
+            }
+
+            const auto b0 = static_cast<std::uint32_t>(data[i]);
+            const auto b1 = static_cast<std::uint32_t>(data[i + 1]);
+            std::uint32_t codepoint = 0;
+            switch (length)
+            {
+                case 2:
+                    codepoint = ((b0 & 0x1Fu) << 6u) | (b1 & 0x3Fu);
+                    break;
+                case 3:
+                    codepoint = ((b0 & 0x0Fu) << 12u) | ((b1 & 0x3Fu) << 6u) | (static_cast<std::uint32_t>(data[i + 2]) & 0x3Fu);
+                    break;
+                default:
+                    codepoint = ((b0 & 0x07u) << 18u) | ((b1 & 0x3Fu) << 12u) | ((static_cast<std::uint32_t>(data[i + 2]) & 0x3Fu) << 6u) | (static_cast<std::uint32_t>(data[i + 3]) & 0x3Fu);
+                    break;
+            }
+
+            // at most two escapes of six bytes each
+            if (JSON_HEDLEY_UNLIKELY(write_buffer.size() - write_buffer_pos < 12))
+            {
+                flush();
+            }
+            char* d = write_buffer.data() + write_buffer_pos;
+            if (codepoint > 0xFFFFu)
+            {
+                d = put_u_escape(d, static_cast<std::uint16_t>(0xD7C0u + (codepoint >> 10u)), nibble_to_hex);
+                codepoint = 0xDC00u + (codepoint & 0x3FFu);
+            }
+            d = put_u_escape(d, static_cast<std::uint16_t>(codepoint), nibble_to_hex);
+            write_buffer_pos = static_cast<std::size_t>(d - write_buffer.data());
+            i += length;
+        }
+        return i;
+    }
+
+    static char* put_u_escape(char* d, const std::uint16_t codeunit, const char* nibble_to_hex) noexcept
+    {
+        const auto unit = static_cast<std::uint32_t>(codeunit);
+        d[0] = '\\';
+        d[1] = 'u';
+        d[2] = nibble_to_hex[(unit >> 12u) & 0x0Fu];
+        d[3] = nibble_to_hex[(unit >> 8u) & 0x0Fu];
+        d[4] = nibble_to_hex[(unit >> 4u) & 0x0Fu];
+        d[5] = nibble_to_hex[unit & 0x0Fu];
+        return d + 6;
+    }
+
     /*!
      * @brief write a lowercase "\\uXXXX" escape sequence into @a string_buffer
      *
@@ -31913,11 +32338,22 @@ class serializer
     /// the output of the serializer (non-owning; the adapter lives at the call site)
     output_adapter_protocol<char>* o = nullptr;
 
+    /// a character buffer left uninitialized: the buffers below are written
+    /// before they are read (only the part written is ever read), and zeroing
+    /// 1.6 KiB took more than half of what dumping a small value costs (the
+    /// user-provided constructor keeps the member initialization, which
+    /// -Weffc++ asks for, from zeroing them)
+    template<std::size_t N>
+    struct uninitialized_buffer : std::array<char, N>
+    {
+        uninitialized_buffer() noexcept {} // NOLINT(modernize-use-equals-default,hicpp-use-equals-default,cppcoreguidelines-pro-type-member-init,hicpp-member-init): see above
+    };
+
     /// a (hopefully) large enough character buffer
-    std::array<char, 64> number_buffer{{}};
+    uninitialized_buffer<64> number_buffer;
 
     /// string buffer
-    std::array<char, 512> string_buffer{{}};
+    uninitialized_buffer<512> string_buffer;
 
     /// the indentation character
     const char indent_char;
@@ -31937,7 +32373,7 @@ class serializer
     /// buffer collecting output before it is flushed to the output adapter, so
     /// that the many small structural writes become few bulk writes
     static constexpr std::size_t write_buffer_size = 1024;
-    std::array<char, write_buffer_size> write_buffer{{}};
+    uninitialized_buffer<write_buffer_size> write_buffer;
     /// number of valid bytes currently held in @ref write_buffer
     std::size_t write_buffer_pos = 0;
 };
@@ -40701,6 +41137,7 @@ struct formatter<nlohmann::NLOHMANN_BASIC_JSON_TPL, char> // NOLINT(cert-dcl58-c
 #undef JSON_SCAN_SSSE3_TARGET
 #undef JSON_SCAN_VECTOR
 #undef JSON_SCAN_VECTOR_UTF8
+#undef JSON_DUMP_SHORT_STRINGS
 
 #ifndef JSON_TEST_KEEP_MACROS
     #undef JSON_CATCH

single_include/nlohmann/json_view.hpp

@@ -756,34 +756,6 @@ NLOHMANN_VIEW_ALWAYS_INLINE const unsigned char* vector_plain_run(const unsigned
     }
     return p;
 }
-
-/*!
-@brief copy 16 bytes from p to w, and find the first quote, backslash,
-control character, or non-ASCII byte among them
-
-The bytes are copied whether or not they are all plain (the caller has room
-for 16 bytes and keeps only the plain ones).
-
-@return the offset of that byte, or 16 if there is none
-*/
-NLOHMANN_VIEW_ALWAYS_INLINE unsigned copy_plain_run16(const unsigned char* p, char* w) noexcept
-{
-#if NLOHMANN_VIEW_NEON
-    const uint8x16_t in = vld1q_u8(p);
-    vst1q_u8(reinterpret_cast<std::uint8_t*>(w), in); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-    const uint8x16_t special = vorrq_u8(vorrq_u8(vceqq_u8(in, vdupq_n_u8('"')), vceqq_u8(in, vdupq_n_u8('\\'))),
-                                        vcltq_s8(vreinterpretq_s8_u8(in), vdupq_n_s8(0x20)));
-    const std::uint64_t bits = vget_lane_u64(vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(special), 4)), 0);
-    return bits != 0 ? static_cast<unsigned>(count_trailing_zeros(bits) >> 2u) : 16u;
-#else
-    const __m128i in = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(p))); // NOLINT(bugprone-casting-through-void)
-    _mm_storeu_si128(static_cast<__m128i*>(static_cast<void*>(w)), in); // NOLINT(bugprone-casting-through-void)
-    const __m128i special = _mm_or_si128(_mm_or_si128(_mm_cmpeq_epi8(in, _mm_set1_epi8('"')), _mm_cmpeq_epi8(in, _mm_set1_epi8('\\'))),
-                                         _mm_cmplt_epi8(in, _mm_set1_epi8(0x20)));
-    const auto bits = static_cast<std::uint64_t>(static_cast<unsigned>(_mm_movemask_epi8(special)));
-    return bits != 0 ? static_cast<unsigned>(count_trailing_zeros(bits)) : 16u;
-#endif
-}
 #endif
 
 #if NLOHMANN_VIEW_SSSE3_DISPATCH
@@ -1465,41 +1437,11 @@ class builder
                 0, 0, '\b', 0, 0, 0, '\f', 0, 0, 0, 0, 0, 0, 0, '\n', 0, 0, 0, '\r', 0, '\t', 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
             }
         };
-        // The write position is kept in locals: the stores of characters into
-        // the arena may alias the members of the builder, which would then be
-        // reloaded after every one. It is stored back where the arena grows
-        // and at the end.
-        const unsigned char* const end = m_end;
         const std::size_t start = arena_used();
-        char* w = m_arena_write;
-        const char* w_end = m_arena_end;
-#define NLOHMANN_VIEW_ENSURE(n)                                                       \
-    if (NLOHMANN_VIEW_UNLIKELY(static_cast<std::size_t>(w_end - w) < (n)))            \
-    {                                                                                 \
-        m_arena_write = w;                                                            \
-        arena_grow(n);                                                                \
-        w = m_arena_write;                                                            \
-        w_end = m_arena_end;                                                          \
-    }
-        {
-            const auto n = static_cast<std::size_t>(p - s);
-            if (n <= 16 && end - s >= 16)
-            {
-                NLOHMANN_VIEW_ENSURE(16)
-                std::memcpy(w, s, 16);
-            }
-            else if (n != 0)
-            {
-                // (an empty run leaves an empty arena unallocated, and memcpy()
-                // must not be passed its null pointer even for zero bytes)
-                NLOHMANN_VIEW_ENSURE(n)
-                std::memcpy(w, s, n);
-            }
-            w += n;
-        }
+        arena_run(s, static_cast<std::size_t>(p - s));
         for (;;)
         {
-            if (p == end)
+            if (p == m_end)
             {
                 return failed(error_code::string_missing_quote, p);
             }
@@ -1507,7 +1449,6 @@ class builder
             if (c == '"')
             {
                 ++p;
-                m_arena_write = w;
                 return decoded{p, start, arena_used() - start};
             }
             if (c != '\\')
@@ -1518,7 +1459,7 @@ class builder
                 return failed(c < 0x20 ? error_code::string_control_character : error_code::string_utf8, p);
             }
             ++p;
-            if (p == end)
+            if (p == m_end)
             {
                 return failed(error_code::string_missing_quote, p);
             }
@@ -1536,7 +1477,7 @@ class builder
                     {
                         return failed(error_code::string_surrogate_low, p);
                     }
-                    if (end - p < 2 || p[0] != '\\' || p[1] != 'u')
+                    if (m_end - p < 2 || p[0] != '\\' || p[1] != 'u')
                     {
                         return failed(error_code::string_surrogate_high, p);
                     }
@@ -1552,108 +1493,27 @@ class builder
                     }
                     cp = 0x10000 + ((cp - 0xD800) << 10) + (lo - 0xDC00);
                 }
-                NLOHMANN_VIEW_ENSURE(4)
-                w = put_utf8(w, cp);
+                arena_ensure(4);
+                m_arena_write = put_utf8(m_arena_write, cp);
             }
             else if (NLOHMANN_VIEW_LIKELY(d < 128 && simple_escape[d] != 0))
             {
-                NLOHMANN_VIEW_ENSURE(1)
-                *w++ = simple_escape[d];
+                arena_ensure(1);
+                *m_arena_write++ = simple_escape[d];
             }
             else
             {
                 --p;
                 return failed(error_code::string_escape, p);
             }
-#if NLOHMANN_VIEW_NEON
-            if (p != end && *p == '\\')
+            if (p != m_end && *p == '\\')
             {
                 continue; // consecutive escapes ("\u00e4\u00f6"): no run in between
             }
-            // The first 16 bytes of the run are checked one by one, in predicted branches, and copied
-            // as one block: where the runs between escapes are short, the vector step below would put
-            // its longer dependency chain (load, compare, mask, count, add) on p for each of them,
-            // and be slower than these steps (the scanner of the keys works the same way)
-            {
-                if (end - p >= 16)
-                {
-                    const std::uint8_t* const plain = string_plain();
-                    std::size_t steps = 16;
-#define NLOHMANN_VIEW_STEP(i) if (NLOHMANN_VIEW_LIKELY(plain[p[i]] != 0)) {} else { steps = (i); goto run_found; }
-                    NLOHMANN_VIEW_REPEAT16(NLOHMANN_VIEW_STEP)
-#undef NLOHMANN_VIEW_STEP
-run_found:
-                    NLOHMANN_VIEW_ENSURE(16)
-                    std::memcpy(w, p, 16); // (only the first `steps` bytes are kept)
-                    w += steps;
-                    p += steps;
-                    if (steps < 16)
-                    {
-                        if (*p >= 0x80)
-                        {
-                            // non-ASCII: the UTF-8 check, and the rest of the run
-                            const unsigned char* const r = p;
-                            p = scan_string_run(p, end);
-                            const auto n = static_cast<std::size_t>(p - r);
-                            NLOHMANN_VIEW_ENSURE(n)
-                            std::memcpy(w, r, n);
-                            w += n;
-                        }
-                        continue;
-                    }
-                }
-            }
-#else
-            if (p != end && (*p == '\\' || *p == '"'))
-            {
-                continue; // consecutive escapes ("\u00e4\u00f6"), or the end of the string: no run in between
-            }
-#endif
-#if NLOHMANN_VIEW_VECTOR
-            // the plain bytes up to the next quote, backslash, or control
-            // character are copied as they are scanned, 16 bytes at a time
-            for (;;)
-            {
-                if (NLOHMANN_VIEW_UNLIKELY(end - p < 16))
-                {
-                    const unsigned char* const r = p;
-                    p = scan_string_run(p, end);
-                    const auto n = static_cast<std::size_t>(p - r);
-                    NLOHMANN_VIEW_ENSURE(n)
-                    std::memcpy(w, r, n);
-                    w += n;
-                    break;
-                }
-                NLOHMANN_VIEW_ENSURE(16)
-                const unsigned k = copy_plain_run16(p, w);
-                w += k;
-                p += k;
-                if (k == 16)
-                {
-                    continue;
-                }
-                if (NLOHMANN_VIEW_UNLIKELY(*p >= 0x80))
-                {
-                    // non-ASCII: the UTF-8 check, and the rest of the run
-                    const unsigned char* const r = p;
-                    p = scan_string_run(p, end);
-                    const auto n = static_cast<std::size_t>(p - r);
-                    NLOHMANN_VIEW_ENSURE(n)
-                    std::memcpy(w, r, n);
-                    w += n;
-                }
-                break;
-            }
-#else
             const unsigned char* const r = p;
-            p = scan_string_run(p, end);
-            const auto n = static_cast<std::size_t>(p - r);
-            NLOHMANN_VIEW_ENSURE(n)
-            std::memcpy(w, r, n);
-            w += n;
-#endif
+            p = scan_string_run(p, m_end);
+            arena_run(r, static_cast<std::size_t>(p - r));
         }
-#undef NLOHMANN_VIEW_ENSURE
     }
 
     /// does the float token [s, p) overflow FloatType? (parse() rejects it)
@@ -1699,6 +1559,14 @@ run_found:
         return m_arena_write != nullptr ? static_cast<std::size_t>(m_arena_write - m_doc.arena.data()) : 0;
     }
 
+    NLOHMANN_VIEW_ALWAYS_INLINE void arena_ensure(std::size_t n)
+    {
+        if (NLOHMANN_VIEW_UNLIKELY(static_cast<std::size_t>(m_arena_end - m_arena_write) < n))
+        {
+            arena_grow(n);
+        }
+    }
+
     NLOHMANN_VIEW_NOINLINE void arena_grow(std::size_t n)
     {
         const std::size_t used = arena_used();
@@ -1707,6 +1575,25 @@ run_found:
         m_arena_end = m_doc.arena.data() + m_doc.arena.size();
     }
 
+    /// append the run [r, r + n) to the arena; short runs as one fixed-size
+    /// 16-byte move when both sides have the room (no library call)
+    NLOHMANN_VIEW_ALWAYS_INLINE void arena_run(const unsigned char* r, std::size_t n)
+    {
+        if (n <= 16 && m_end - r >= 16)
+        {
+            arena_ensure(16);
+            std::memcpy(m_arena_write, r, 16);
+        }
+        else if (n != 0)
+        {
+            // (an empty run leaves an empty arena unallocated, and memcpy()
+            // must not be passed its null pointer even for zero bytes)
+            arena_ensure(n);
+            std::memcpy(m_arena_write, r, n);
+        }
+        m_arena_write += n;
+    }
+
     /// UTF-8 encoding of cp at w (room for 4 bytes); returns the position after
     /// it. (A returned pointer stays in a register; writing through a
     /// reference to m_arena_write would store and reload it around every byte.)
@@ -2229,11 +2116,11 @@ indent_done:
                 ++p;
             }
             const unsigned char* const int_start = p;
-            if (cur() == '0')
+            if (p != e && *p == '0')
             {
                 ++p;
             }
-            else if (NLOHMANN_VIEW_LIKELY(cur() >= '1' && cur() <= '9'))
+            else if (NLOHMANN_VIEW_LIKELY(p != e && *p >= '1' && *p <= '9'))
             {
                 p = skip_digits(p + 1, e);
             }
@@ -2244,7 +2131,7 @@ indent_done:
             const auto int_digits = static_cast<std::size_t>(p - int_start);
             std::size_t frac_digits = 0;
             bool is_float = false;
-            if (cur() == '.')
+            if (p != e && *p == '.')
             {
                 ++p;
                 const unsigned char* const f0 = p;
@@ -2257,20 +2144,20 @@ indent_done:
                 is_float = true;
             }
             std::int64_t exponent = 0;
-            if ((cur() | 0x20) == 'e')
+            if (p != e && (*p | 0x20) == 'e')
             {
                 ++p;
                 bool exp_negative = false;
-                if (cur() == '+' || cur() == '-')
+                if (p != e && (*p == '+' || *p == '-'))
                 {
                     exp_negative = *p == '-';
                     ++p;
                 }
-                if (NLOHMANN_VIEW_UNLIKELY(!is_digit(cur())))
+                if (NLOHMANN_VIEW_UNLIKELY(p == e || !is_digit(*p)))
                 {
                     return fail(error_code::number_after_exponent);
                 }
-                while (is_digit(cur()))
+                while (p != e && is_digit(*p))
                 {
                     if (exponent < 100000)
                     {
@@ -2332,7 +2219,7 @@ indent_done:
             ++p; // opening quote
             const unsigned char* const s = p;
             p = scan_string_run<Value>(p, e);
-            if (NLOHMANN_VIEW_LIKELY(cur() == '"'))
+            if (NLOHMANN_VIEW_LIKELY(p != e && *p == '"'))
             {
                 push_node(value_t::string, 0, 0, static_cast<std::size_t>(s - b), static_cast<std::uint64_t>(p - s));
                 ++p;
@@ -3281,96 +3168,27 @@ constexpr std::size_t index_max_displacement = 64;
 static_assert(document_data::index_min_members >= 2 * index_max_displacement,
               "a table must be much larger than the probe window of a lookup");
 
-/// hash of a key: its bytes, eight at a time (in a fixed byte order), where the
-/// last word may overlap the one before (so that no loop over single bytes is
-/// needed); a key of fewer than eight bytes is read as two overlapping words of
-/// four or two bytes (in the native byte order: the hash is not stored, and the
-/// same on both sides of a lookup)
+/// hash of a key: its bytes, eight at a time, in a fixed byte order
 inline std::uint64_t key_hash(const char* s, std::size_t n) noexcept
 {
     std::uint64_t h = 0x9E3779B97F4A7C15u * (n + 1);
     const auto* p = reinterpret_cast<const unsigned char*>(s); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
+    while (n >= 8)
+    {
+        h = (h ^ read_eight_bytes(p)) * 0xBF58476D1CE4E5B9u;
+        h ^= h >> 29u;
+        p += 8;
+        n -= 8;
+    }
     std::uint64_t w = 0;
-    if (n >= 8)
+    for (std::size_t i = 0; i < n; ++i)
     {
-        const unsigned char* const last = p + n - 8;
-        while (p < last)
-        {
-            h = (h ^ read_eight_bytes(p)) * 0xBF58476D1CE4E5B9u;
-            h ^= h >> 29u;
-            p += 8;
-        }
-        w = read_eight_bytes(last);
+        w |= static_cast<std::uint64_t>(p[i]) << (8u * i);
     }
-    else if (n >= 4)
-    {
-        std::uint32_t head = 0;
-        std::uint32_t tail = 0;
-        std::memcpy(&head, p, 4);
-        std::memcpy(&tail, p + n - 4, 4);
-        w = static_cast<std::uint64_t>(head) | (static_cast<std::uint64_t>(tail) << 32u);
-    }
-    else if (n >= 2)
-    {
-        std::uint16_t head = 0;
-        std::uint16_t tail = 0;
-        std::memcpy(&head, p, 2);
-        std::memcpy(&tail, p + n - 2, 2);
-        w = static_cast<std::uint64_t>(head) | (static_cast<std::uint64_t>(tail) << 16u);
-    }
-    else if (n == 1)
-    {
-        w = p[0];
-    }
-    // (a product only carries bits upwards, and the slot is taken from the low
-    // bits: the high bits of the last word are folded down before the multiplication)
-    h = (h ^ w ^ (w >> 29u)) * 0x94D049BB133111EBu;
+    h = (h ^ w) * 0x94D049BB133111EBu;
     return h ^ (h >> 31u);
 }
 
-/// whether the n <= 16 bytes at a and b are equal, as two overlapping words
-/// (the first and the last 8, 4, or 2 bytes) and without a call
-NLOHMANN_VIEW_ALWAYS_INLINE bool same_short_bytes(const unsigned char* a, const unsigned char* b, std::size_t n) noexcept
-{
-    if (n >= 8)
-    {
-        std::uint64_t x0 = 0;
-        std::uint64_t x1 = 0;
-        std::uint64_t y0 = 0;
-        std::uint64_t y1 = 0;
-        std::memcpy(&x0, a, 8);
-        std::memcpy(&x1, a + n - 8, 8);
-        std::memcpy(&y0, b, 8);
-        std::memcpy(&y1, b + n - 8, 8);
-        return x0 == y0 && x1 == y1;
-    }
-    if (n >= 4)
-    {
-        std::uint32_t x0 = 0;
-        std::uint32_t x1 = 0;
-        std::uint32_t y0 = 0;
-        std::uint32_t y1 = 0;
-        std::memcpy(&x0, a, 4);
-        std::memcpy(&x1, a + n - 4, 4);
-        std::memcpy(&y0, b, 4);
-        std::memcpy(&y1, b + n - 4, 4);
-        return x0 == y0 && x1 == y1;
-    }
-    if (n >= 2)
-    {
-        std::uint16_t x0 = 0;
-        std::uint16_t x1 = 0;
-        std::uint16_t y0 = 0;
-        std::uint16_t y1 = 0;
-        std::memcpy(&x0, a, 2);
-        std::memcpy(&x1, a + n - 2, 2);
-        std::memcpy(&y0, b, 2);
-        std::memcpy(&y1, b + n - 2, 2);
-        return x0 == y0 && x1 == y1;
-    }
-    return n == 0 || *a == *b;
-}
-
 /// build the table of a large object
 inline void build_object_index(document_data& d, node* obj)
 {
@@ -3435,27 +3253,6 @@ inline const node* find_indexed(const document_data& d, const node* obj, const c
     const document_data::object_index& ix = d.indexes[obj->extra - 1u];
     const std::uint32_t* const table = d.index_slots.data() + ix.start;
     std::size_t slot = conditional_static_cast<std::size_t>(key_hash(key, n)) & ix.mask;
-    const auto* const k_bytes = reinterpret_cast<const unsigned char*>(key); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-    // (the loop for longer keys comes first, as the code is laid out; it is not the more common case)
-    if (NLOHMANN_VIEW_UNLIKELY(n <= 16))
-    {
-        // (up to 16 bytes, the bytes are compared as two words, without a call)
-        for (std::size_t distance = 0; distance <= index_max_displacement; ++distance)
-        {
-            const std::uint32_t s = table[slot];
-            if (s == 0)
-            {
-                return nullptr;
-            }
-            const node* const k = obj + s;
-            if (k->len == n && same_short_bytes(reinterpret_cast<const unsigned char*>(d.str(*k)), k_bytes, n)) // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-            {
-                return k;
-            }
-            slot = (slot + 1) & ix.mask;
-        }
-        return nullptr;
-    }
     for (std::size_t distance = 0; distance <= index_max_displacement; ++distance)
     {
         const std::uint32_t s = table[slot];
@@ -3624,10 +3421,6 @@ const node* element_at(const document_data& d, const node* array, std::size_t id
     {
         return e + idx; // a growable block: one link per element
     }
-    if (array->next == array->len + 1u && (!nav::editable() || (array->flags & node_flags::moved) == 0))
-    {
-        return e + idx; // no element has a subtree: the elements are the nodes after the array
-    }
     for (std::size_t i = 0; i < idx; ++i)
     {
         e = document_data::after(e);
@@ -3643,10 +3436,6 @@ const node* last_child(const document_data& d, const node* container) noexcept
     const std::size_t value_offset = container->kind == static_cast<std::uint8_t>(value_t::object) ? 1 : 0;
     const node* const end = navigation<Editable>::end(d, container);
     const node* last = navigation<Editable>::first(d, container);
-    if (value_offset == 0 && container->next == container->len + 1u && (!navigation<Editable>::editable() || (container->flags & node_flags::moved) == 0))
-    {
-        return last + (container->len - 1u); // an array without subtrees: the elements are the nodes after it
-    }
     for (const node* c = document_data::after(last + value_offset); c != end; c = document_data::after(c + value_offset))
     {
         last = c;
@@ -5512,9 +5301,6 @@ NLOHMANN_JSON_NAMESPACE_END
 
 #include <algorithm> // max
 #include <cstddef> // size_t
-#ifndef JSON_NO_IO
-    #include <cstdio> // FILE, fread
-#endif
 #include <istream> // istream, streambuf
 #include <string> // basic_string, char_traits, string
 #include <type_traits> // decay, integral_constant, is_array, is_const, is_integral, is_lvalue_reference, is_pointer, is_same, remove_cv, remove_extent, remove_pointer, remove_reference
@@ -5660,37 +5446,6 @@ inline void append_stream(std::string& buf, std::istream& is)
     is.clear(is.rdstate() | std::ios::eofbit);
 }
 
-/// a pointer to a C stream (never with JSON_NO_IO, which leaves out <cstdio>)
-template<typename T>
-struct is_c_stream
-#ifndef JSON_NO_IO
-    : std::is_same<T, std::FILE*>
-#else
-    : std::false_type
-#endif
-{};
-
-#ifndef JSON_NO_IO
-/// append the rest of a C stream: in blocks with fread, not character by
-/// character (the library's file adapter reads with fgetc);
-/// f is not null
-inline void append_file(std::string& buf, std::FILE* f)
-{
-    for (;;)
-    {
-        const std::size_t used = buf.size();
-        const std::size_t room = (std::max)(buf.capacity() - used, std::size_t{4096});
-        buf.resize(used + room);
-        const std::size_t got = std::fread(&buf[used], 1, room, f);
-        buf.resize(used + got);
-        if (got < room)
-        {
-            break; // end of file, or an error (as fgetc, which returns EOF for both)
-        }
-    }
-}
-#endif
-
 }  // namespace view
 }  // namespace detail
 NLOHMANN_JSON_NAMESPACE_END
@@ -5849,21 +5604,20 @@ class view_item
 
     view_item(const iterator& it, std::size_t index)
         : m_it(it)
-        , m_position(index)
-    {}
+    {
+        if (!it.is_object_iterator())
+        {
+            m_index = std::to_string(index);
+        }
+    }
 
-    /// the member key, or the element index for arrays (as text made on the
-    /// first call, so that iterating over the values pays nothing for it)
+    /// the member key, or the element index for arrays
     string_view_t key() const
     {
         if (m_it.is_object_iterator())
         {
             return m_it.key();
         }
-        if (m_index.empty())
-        {
-            m_index = std::to_string(m_position);
-        }
         return string_view_t(m_index.data(), m_index.size());
     }
 
@@ -5886,8 +5640,7 @@ class view_item
 
   private:
     iterator m_it;
-    std::size_t m_position; ///< the index of an array element
-    mutable std::string m_index{}; ///< the text of m_position, once key() was called // NOLINT(readability-redundant-member-init)
+    std::string m_index{}; // NOLINT(readability-redundant-member-init)
 };
 
 /// the range returned by basic_json_view::items()
@@ -5981,7 +5734,7 @@ NLOHMANN_JSON_NAMESPACE_END
 
 
 
-#include <array> // array
+#include <algorithm> // max
 #include <cstddef> // size_t
 #include <cstdint> // int64_t, uint8_t
 #include <string> // string
@@ -6021,9 +5774,8 @@ BasicJsonType materialize(const document_data& d, const node* n)
     using nav = navigation<Editable>;
 
     // the open containers: their next element (or key of the next member),
-    // their end, and whether they are objects; for the first 16 levels on the
-    // stack, else sized once from the document's deepest nesting (for a
-    // subtree an upper bound)
+    // their end, and whether they are objects; sized once from the
+    // document's deepest nesting (for a subtree an upper bound)
     struct frame
     {
         const node* pos;
@@ -6031,43 +5783,10 @@ BasicJsonType materialize(const document_data& d, const node* n)
         bool object;
     };
 
-    // a scalar needs neither the handler nor the stack of open containers
-    switch (static_cast<value_t>(n->kind))
-    {
-        case value_t::string:
-            return BasicJsonType(string_t(d.str(*n), n->len));
-        case value_t::number_integer:
-            return BasicJsonType(static_cast<typename BasicJsonType::number_integer_t>(static_cast<std::int64_t>(integer_bits(*n))));
-        case value_t::number_unsigned:
-            return BasicJsonType(static_cast<typename BasicJsonType::number_unsigned_t>(integer_bits(*n)));
-        case value_t::number_float:
-            return BasicJsonType(float_value<typename BasicJsonType::number_float_t>(d, *n));
-        case value_t::boolean:
-            return BasicJsonType((n->flags & node_flags::is_true) != 0);
-        case value_t::null:
-            return BasicJsonType(nullptr);
-        case value_t::object:
-        case value_t::array:
-        case value_t::binary:
-        case value_t::discarded:
-        default:
-            break;
-    }
-
     BasicJsonType result;
     sax_t sax(result, true);
     const string_t no_token{};
-    // (shallow subtrees on the stack: a call for a small value then allocates only for the value)
-    std::array<frame, 16> shallow; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): filled as containers open
-    std::vector<frame> deep{};
-    frame* open = shallow.data();
-    std::size_t capacity = shallow.size();
-    if (d.max_depth > capacity)
-    {
-        deep.resize(d.max_depth);
-        open = deep.data();
-        capacity = deep.size();
-    }
+    std::vector<frame> open((std::max)(d.max_depth, std::size_t{1}));
     std::size_t depth = 0;
     for (;;)
     {
@@ -6087,13 +5806,9 @@ BasicJsonType materialize(const document_data& d, const node* n)
                 {
                     sax.start_array(n->len);
                 }
-                if (NLOHMANN_VIEW_UNLIKELY(depth == capacity))
+                if (NLOHMANN_VIEW_UNLIKELY(depth == open.size()))
                 {
-                    // (deeper than the recorded nesting, e.g. after edits)
-                    deep.assign(open, open + depth);
-                    deep.resize(depth * 2);
-                    open = deep.data();
-                    capacity = deep.size();
+                    open.resize(depth * 2); // (deeper than the recorded nesting, e.g. after edits)
                 }
                 open[depth++] = frame{nav::first(d, n), nav::end(d, n), object};
                 break;
@@ -7875,7 +7590,7 @@ class basic_json_view
             }
             detail::view::throw_type_error(305, "cannot use operator[] with a numeric argument with ", type_name());
         }
-        return idx < m_node->len ? element(idx) : basic_json_view();
+        return idx < m_node->len ? basic_json_view(m_doc, navigation::value(detail::view::element_at<Editable>(*m_doc, m_node, idx))) : basic_json_view();
     }
 
     /// any other integer type (int, unsigned, long, std::int64_t, ...; a
@@ -7938,7 +7653,7 @@ class basic_json_view
         {
             detail::view::throw_out_of_range(401, detail::concat("array index ", std::to_string(idx), " is out of range"));
         }
-        return element(idx);
+        return basic_json_view(m_doc, navigation::value(detail::view::element_at<Editable>(*m_doc, m_node, idx)));
     }
 
     /// any other integer type, see operator[]; negative values are out of
@@ -7972,13 +7687,7 @@ class basic_json_view
 
     string_t value(string_view_t key, const char* default_value) const
     {
-        if (NLOHMANN_VIEW_UNLIKELY(!is_object()))
-        {
-            detail::view::throw_type_error(306, "cannot use value() with ", type_name());
-        }
-        // (the default is made only if there is no such member)
-        const basic_json_view r = lookup(key);
-        return r.is_discarded() ? string_t(default_value) : r.template get<string_t>();
+        return value(key, string_t(default_value));
     }
 
     /// the value a JSON pointer refers to converted to T, or the default
@@ -7997,12 +7706,7 @@ class basic_json_view
 
     string_t value(const json_pointer& ptr, const char* default_value) const
     {
-        if (NLOHMANN_VIEW_UNLIKELY(!is_structured()))
-        {
-            detail::view::throw_type_error(306, "cannot use value() with ", type_name());
-        }
-        const basic_json_view r = detail::view::resolve_pointer(*this, detail::json_pointer_access::reference_tokens(ptr), detail::view::pointer_mode::value);
-        return r.is_discarded() ? string_t(default_value) : r.template get<string_t>();
+        return value(ptr, string_t(default_value));
     }
 
     /// the first element or member value; a primitive value itself. Throws
@@ -8024,8 +7728,7 @@ class basic_json_view
     {
         if (is_structured() && m_node->len != 0)
         {
-            return unedited() ? basic_json_view(m_doc, detail::view::last_child<false>(*m_doc, m_node) + (is_object() ? 1 : 0))
-                   : basic_json_view(m_doc, navigation::value(detail::view::last_child<Editable>(*m_doc, m_node) + (is_object() ? 1 : 0)));
+            return basic_json_view(m_doc, navigation::value(detail::view::last_child<Editable>(*m_doc, m_node) + (is_object() ? 1 : 0)));
         }
         return front();
     }
@@ -8042,8 +7745,7 @@ class basic_json_view
         {
             return end();
         }
-        const node* const k = unedited() ? detail::view::find_member<false>(*m_doc, m_node, key.data(), key.size())
-                              : detail::view::find_member<Editable>(*m_doc, m_node, key.data(), key.size());
+        const node* const k = detail::view::find_member<Editable>(*m_doc, m_node, key.data(), key.size());
         return k != nullptr ? iterator(m_doc, k, true) : end();
     }
 
@@ -8060,8 +7762,7 @@ class basic_json_view
     /// whether this is an object with a member with this key
     bool contains(string_view_t key) const
     {
-        return is_object() && (unedited() ? detail::view::find_member<false>(*m_doc, m_node, key.data(), key.size()) != nullptr
-                               : detail::view::find_member<Editable>(*m_doc, m_node, key.data(), key.size()) != nullptr);
+        return is_object() && detail::view::find_member<Editable>(*m_doc, m_node, key.data(), key.size()) != nullptr;
     }
 
     bool contains(const char* key) const
@@ -8221,14 +7922,7 @@ class basic_json_view
         // the compact writer keeps 64 bytes of slack, so that it does not grow
         // the buffer just before the end
         const std::size_t estimate = source_extent() + (style.pretty ? source_extent() / 2 : 0) + 160;
-        if (unedited())
-        {
-            detail::view::view_serializer<BasicJsonType, false>(*m_doc, out, estimate, style).dump(m_node);
-        }
-        else
-        {
-            detail::view::view_serializer<BasicJsonType, Editable>(*m_doc, out, estimate, style).dump(m_node);
-        }
+        detail::view::view_serializer<BasicJsonType, Editable>(*m_doc, out, estimate, style).dump(m_node);
         return out;
     }
 
@@ -8308,7 +8002,7 @@ class basic_json_view
         {
             return BasicJsonType(value_t::discarded);
         }
-        return unedited() ? detail::view::materialize<BasicJsonType, false>(*m_doc, m_node) : detail::view::materialize<BasicJsonType, Editable>(*m_doc, m_node);
+        return detail::view::materialize<BasicJsonType, Editable>(*m_doc, m_node);
     }
 
     /// byte offset of this value in the source text (for strings: of the
@@ -8386,32 +8080,10 @@ class basic_json_view
     /// (object required)
     NLOHMANN_VIEW_ALWAYS_INLINE basic_json_view lookup(string_view_t key) const noexcept
     {
-        if (unedited())
-        {
-            const node* const k = detail::view::find_member<false>(*m_doc, m_node, key.data(), key.size());
-            return k != nullptr ? basic_json_view(m_doc, k + 1) : basic_json_view();
-        }
         const node* const k = detail::view::find_member<Editable>(*m_doc, m_node, key.data(), key.size());
         return k != nullptr ? basic_json_view(m_doc, navigation::value(k + 1)) : basic_json_view();
     }
 
-    /// whether the document has not been edited yet: until the first edit, its index is walked like that of a
-    /// read-only document (nothing is moved or linked), which is cheaper
-    NLOHMANN_VIEW_ALWAYS_INLINE bool unedited() const noexcept
-    {
-        return !navigation::editable() || m_doc->edits == nullptr;
-    }
-
-    /// the element of an array at an index below its size
-    NLOHMANN_VIEW_ALWAYS_INLINE basic_json_view element(size_type idx) const
-    {
-        if (unedited())
-        {
-            return basic_json_view(m_doc, detail::view::element_at<false>(*m_doc, m_node, idx));
-        }
-        return basic_json_view(m_doc, navigation::value(detail::view::element_at<Editable>(*m_doc, m_node, idx)));
-    }
-
     // --- get() dispatch ---
 
     bool get_impl(detail::view::value_tag<bool> /*unused*/, detail::priority_tag<2> /*unused*/) const
@@ -9151,8 +8823,7 @@ class basic_json_document
         // NOLINTBEGIN(readability-avoid-nested-conditional-operator): a constant expression of C++11
         append_input_impl(buf, std::forward<T>(input), std::integral_constant < int, detail::is_contiguous_byte_container<D>::value ? 0
                           : std::is_base_of<std::istream, D>::value ? 1
-                          : detail::view::is_adapter_input<D>::value ? 2
-                          : detail::view::is_c_stream<D>::value ? 4 : 3 > {});
+                          : detail::view::is_adapter_input<D>::value ? 2 : 3 > {});
         // NOLINTEND(readability-avoid-nested-conditional-operator)
     }
 
@@ -9174,19 +8845,6 @@ class basic_json_document
         detail::view::append_adapter(buf, std::move(input.ia));
     }
 
-#ifndef JSON_NO_IO
-    static void append_input_impl(std::string& buf, std::FILE* file, std::integral_constant<int, 4> /*C stream*/)
-    {
-        if (file == nullptr)
-        {
-            // (as before: the library's adapter decides what a null stream yields)
-            detail::view::append_adapter(buf, detail::input_adapter(file));
-            return;
-        }
-        detail::view::append_file(buf, file);
-    }
-#endif
-
     template<typename T>
     static void append_input_impl(std::string& buf, T&& input, std::integral_constant<int, 3> /*other*/)
     {

tests/src/unit-json_view.cpp

@@ -185,29 +185,6 @@ TEST_CASE("json_view")
         // duplicate keys: the last value, at the position of the first key
         CHECK(materialized<json_document>(R"({"a":1,"b":2,"a":3})") == json::parse(R"({"a":1,"b":2,"a":3})"));
         CHECK(materialized<ordered_json_document>(R"({"a":1,"b":2,"a":3})").dump() == R"({"a":3,"b":2})");
-        // scalars (made without the handler), and nesting around the depth up to which the stack of open containers is local
-        for (const char* scalar :
-                {"null", "true", "false", "0", "-7", "18446744073709551615", "1.5e300", "-0.0", "\"\"", "\"short\"", "\"a string that is longer than fifteen bytes\"", "\"\\u00e4\\n\""
-                })
-        {
-            CAPTURE(scalar)
-            CHECK(materialized<json_document>(scalar) == json::parse(scalar));
-            const std::string in_array = std::string("[1,") + scalar + "]";
-            const json_document d = json_document::parse(in_array);
-            CHECK(d.root()[1].materialize() == json::parse(scalar));
-            CHECK(d.root()[1].get<json>() == json::parse(scalar));
-        }
-        for (const std::size_t levels :
-                {
-                    std::size_t{1}, std::size_t{15}, std::size_t{16}, std::size_t{17}, std::size_t{32}, std::size_t{33}
-                })
-        {
-            CAPTURE(levels)
-            const std::string nested = std::string(levels, '[') + "{\"k\":[1,{\"j\":2}]}" + std::string(levels, ']');
-            CHECK(materialized<json_document>(nested) == json::parse(nested));
-            const std::string wide = "{\"a\":" + nested + ",\"b\":" + nested + "}";
-            CHECK(materialized<json_document>(wide) == json::parse(wide));
-        }
         // very deep nesting (iterative, as parse())
         const std::string deep = std::string(100000, '[') + std::string(100000, ']');
         // (one check per step, so that a failure shows which step it is)
@@ -433,31 +410,6 @@ TEST_CASE("json_view")
         std::istringstream rvalue_source("[1]");
         CHECK(json_document::parse_copy(std::move(rvalue_source)).owns_source());
 
-        // a C stream is read in blocks as well (more than one block, and a
-        // text whose length is a multiple of the block size)
-        for (const std::size_t extra :
-                {
-                    std::size_t{0}, std::size_t{1}
-                })
-        {
-            std::FILE* long_file = std::tmpfile(); // NOLINT(cppcoreguidelines-owning-memory)
-            if (long_file != nullptr)
-            {
-                std::string padded = text;
-                padded.append((4096 - (padded.size() % 4096)) % 4096 + extra, ' ');
-                CHECK(std::fwrite(padded.data(), 1, padded.size(), long_file) == padded.size());
-                CHECK(std::fseek(long_file, 0, SEEK_SET) == 0);
-                const json_document from_long_file = json_document::parse(long_file);
-                CHECK(from_long_file.source() == padded);
-                CHECK(from_long_file.root().materialize() == json::parse(text));
-                CHECK(std::fclose(long_file) == 0); // NOLINT(cppcoreguidelines-owning-memory)
-            }
-        }
-        {
-            json_document from_null;
-            CHECK_THROWS_AS(from_null = json_document::parse(static_cast<std::FILE*>(nullptr)), json::parse_error&);
-        }
-
         // a stream without a buffer is an empty input
         std::istream no_buffer(nullptr);
         CHECK(json_document::parse(no_buffer, false).is_discarded());
@@ -1054,49 +1006,6 @@ TEST_CASE("json_view element access and iteration")
 #endif
     }
 
-    SECTION("arrays whose elements have no subtrees: index and back()")
-    {
-        // (the elements are adjacent in the index; an array, an object, or an
-        // empty container anywhere makes the lookup skip element by element)
-        const std::vector<std::string> texts =
-        {
-            "[]", "[1]", "[1,2,3]", "[1,\"two\",3.5,true,null,-7,18446744073709551615]", "[[]]", "[{}]", "[1,[2],3]",
-            "[1,2,{\"a\":3}]", "[[1,2],3,4]", "[1,2,3,[4,5,6,7,8],9,10,11,12]", "[{\"a\":[1]},2]", "[\"a\\u00e4\",\"b\"]"
-        };
-        for (const std::string& text : texts)
-        {
-            CAPTURE(text)
-            const json_document d = json_document::parse(text);
-            const json_view v = d.root();
-            const json expected = json::parse(text);
-            for (std::size_t i = 0; i < expected.size(); ++i)
-            {
-                CHECK(v[i].materialize() == expected[i]);
-                CHECK(v.at(i).materialize() == expected[i]);
-            }
-            CHECK(v[expected.size()].is_discarded());
-            if (!expected.empty())
-            {
-                CHECK(v.back().materialize() == expected.back());
-            }
-        }
-        // a long array (the direct lookup is not limited to short ones), also with a container at its end
-        std::string text = "[0";
-        for (int i = 1; i < 1000; ++i)
-        {
-            text += "," + std::to_string(i);
-        }
-        const json_document scalars = json_document::parse(text + "]");
-        CHECK(scalars.root()[999].get<int>() == 999);
-        CHECK(scalars.root()[500].get<int>() == 500);
-        CHECK(scalars.root().at(1).get<int>() == 1);
-        CHECK(scalars.root().back().get<int>() == 999);
-        const json_document container_last = json_document::parse(text + ",[1000]]");
-        CHECK(container_last.root()[999].get<int>() == 999);
-        CHECK(container_last.root()[1000][0].get<int>() == 1000);
-        CHECK(container_last.root().back()[0].get<int>() == 1000);
-    }
-
     SECTION("iterators")
     {
         const json_document d = json_document::parse(R"({"x":[1,{"y":2}],"z":null})");
@@ -1136,28 +1045,6 @@ TEST_CASE("json_view element access and iteration")
         CHECK((*first++).key() == "0");
         CHECK((*first).key() == "1");
         CHECK(++first == items.end());
-
-        // the keys of array elements are their indexes, whether or not they are asked for
-        std::string numbers = "[0";
-        for (int i = 1; i < 1234; ++i)
-        {
-            numbers += "," + std::to_string(i);
-        }
-        const json_document array = json_document::parse(numbers + "]");
-        std::size_t position = 0;
-        for (const auto& item : array.root().items())
-        {
-            CHECK(item.value().get<std::size_t>() == position);
-            if (position % 3 != 0) // (not for every item: values alone do not make the key)
-            {
-                CHECK(item.key() == std::to_string(position));
-                CHECK(item.key().data() == item.key().data()); // (the same text every time)
-                const json_view::item copy = item;
-                CHECK(copy.key() == std::to_string(position));
-            }
-            ++position;
-        }
-        CHECK(position == 1234);
 #ifdef JSON_HAS_CPP_17
         std::string pairs;
         for (const auto [key, value] : d.root().items())
@@ -1496,17 +1383,7 @@ TEST_CASE("json_view values")
         CHECK(exception_of([&] { static_cast<void>(v.value("s", 0)); }) == without_path(exception_of([&] { static_cast<void>(j.value("s", 0)); })));
         CHECK(exception_of([&] { static_cast<void>(v["n"].value("x", 0)); }) == without_path(exception_of([&] { static_cast<void>(j["n"].value("x", 0)); })));
         CHECK(exception_of([&] { static_cast<void>(v["n"].value(json::json_pointer("/x"), 0)); }) == without_path(exception_of([&] { static_cast<void>(j["n"].value(json::json_pointer("/x"), 0)); })));
-        // string defaults: the member is not a string, or the value is neither an object nor an array
-        CHECK(exception_of([&] { static_cast<void>(v.value("n", "default")); }) == without_path(exception_of([&] { static_cast<void>(j.value("n", "default")); })));
-        CHECK(exception_of([&] { static_cast<void>(v["n"].value("x", "default")); }) == without_path(exception_of([&] { static_cast<void>(j["n"].value("x", "default")); })));
-        CHECK(exception_of([&] { static_cast<void>(v.value(json::json_pointer("/n"), "default")); }) == without_path(exception_of([&] { static_cast<void>(j.value(json::json_pointer("/n"), "default")); })));
-        CHECK(exception_of([&] { static_cast<void>(v["s"].value(json::json_pointer("/x"), "default")); }) == without_path(exception_of([&] { static_cast<void>(j["s"].value(json::json_pointer("/x"), "default")); })));
 #endif
-        // (defaults and members longer than the short string optimization)
-        CHECK(v.value("s", "a default longer than fifteen characters") == "text");
-        CHECK(v.value("missing", "a default longer than fifteen characters") == "a default longer than fifteen characters");
-        CHECK(v.value(json::json_pointer("/s"), "a default longer than fifteen characters") == "text");
-        CHECK(v.value(json::json_pointer("/zz"), "a default longer than fifteen characters") == "a default longer than fifteen characters");
     }
 }
 

tests/src/unit-json_view_builder.cpp

@@ -523,58 +523,6 @@ TEST_CASE("json_view builder: strings across vector blocks")
     }
 }
 
-TEST_CASE("json_view builder: escapes between runs of text")
-{
-    // The text between escapes is copied 16 bytes at a time where there are
-    // that many bytes left, and with the UTF-8 check where there is
-    // non-ASCII text. Runs of every length from 0 to 40 between valid and
-    // invalid escapes, UTF-8 sequences, and control characters, in strings
-    // that are cut at all places 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*, 9> invalid = {{"\\x", "\\ud800", "\\udc00", "\\u12G4", "\\u12", "\\ud83dx", "\\ud83d\\u0041", "\\", "\x01"}};
-    const std::array<const char*, 6> utf8 = {{"\xc3\xa4", "\xe2\x82\xac", "\xf0\x9f\x98\x80", "\xc3", "\xff", "\x80"}};
-    std::mt19937 rng(2026); // 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 < 60; ++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;
-                }
-            }
-            check_string(content);
-            check_string(content.substr(0, content.size() - (rng() % 4)));
-        }
-    }
-    // the text before the first escape, and runs and escapes at the end of the text
-    for (std::size_t before = 0; before <= 40; ++before)
-    {
-        for (const char* escape : valid)
-        {
-            check_string(std::string(before, 'a') + escape);
-            check_string(std::string(before, 'a') + escape + std::string(before % 19, 'z'));
-            check_string(std::string(before, 'a') + escape + escape + std::string(before % 19, 'z'));
-        }
-    }
-}
-
 TEST_CASE("json_view node integer bits")
 {
     using nlohmann::detail::view::integer_bits;

tests/src/unit-json_view_dump.cpp

@@ -21,7 +21,6 @@ using nlohmann::ordered_json_view;
 using json_view_test::generator;
 using json_view_test::has_duplicate_keys;
 
-#include <algorithm>
 #include <array>
 #include <cmath>
 #include <cstddef>
@@ -30,7 +29,6 @@ using json_view_test::has_duplicate_keys;
 #include <iomanip>
 #include <map>
 #include <random>
-#include <set>
 #include <sstream>
 #include <string>
 #include <vector>
@@ -600,142 +598,6 @@ TEST_CASE("json_view large objects")
         CHECK(without_collisions.memory_usage() >= with_collisions.memory_usage() + (table_size * sizeof(std::uint32_t)));
     }
 
-    SECTION("keys that differ in their last bytes are spread over the table")
-    {
-        // The hash must spread the usual families of keys (numbered names, hex
-        // strings, dates, short names): a key farther than index_max_displacement
-        // from its home slot would leave the object without a table. The keys
-        // are placed with linear probing, as the table does.
-        const auto max_displacement = [](const std::vector<std::string>& keys)
-        {
-            std::size_t slots = 16;
-            while (slots < 2 * keys.size())
-            {
-                slots *= 2;
-            }
-            std::vector<bool> used(slots, false);
-            std::size_t farthest = 0;
-            for (const std::string& key : keys)
-            {
-                std::size_t i = static_cast<std::size_t>(nlohmann::detail::view::key_hash(key.data(), key.size())) & (slots - 1);
-                std::size_t distance = 0;
-                while (used[i])
-                {
-                    i = (i + 1) & (slots - 1);
-                    ++distance;
-                }
-                used[i] = true;
-                farthest = (std::max)(farthest, distance);
-            }
-            return farthest;
-        };
-        // the keys of a printf-like pattern with one %d, %0Nd or %0Nx, formatted with a stream
-        // (a format string that is not a literal is a Flawfinder error)
-        const auto numbered = [](const char* format, int count, int step)
-        {
-            const std::string pattern(format);
-            const std::size_t percent = pattern.find('%');
-            std::size_t conversion = percent + 1;
-            std::size_t width = 0;
-            while (pattern[conversion] >= '0' && pattern[conversion] <= '9')
-            {
-                width = width * 10 + static_cast<std::size_t>(pattern[conversion] - '0');
-                ++conversion;
-            }
-            const bool hex = pattern[conversion] == 'x';
-            std::vector<std::string> keys;
-            for (int i = 0; i < count; ++i)
-            {
-                std::ostringstream key;
-                key << pattern.substr(0, percent) << std::setfill('0') << std::setw(static_cast<int>(width))
-                    << (hex ? std::hex : std::dec) << i * step << pattern.substr(conversion + 1);
-                keys.push_back(key.str());
-            }
-            return keys;
-        };
-        for (const char* format :
-                {"key%d", "%d", "item_%04d", "a%05d", "%03dxyz", "id%d", "user_%d", "%d_suffix", "0x%04x", "A%07d", "12345678%d", "1234567%d", "123456789%d",
-                 "configuration_parameter_value_%04d_extra", "2026-01-%02dT00:00:00Z"
-                })
-        {
-            CAPTURE(format)
-            CHECK(max_displacement(numbered(format, std::string(format).find("%02d") != std::string::npos ? 60 : 1000, 1)) < nlohmann::detail::view::index_max_displacement);
-            CHECK(max_displacement(numbered(format, 600, 7)) < nlohmann::detail::view::index_max_displacement);
-        }
-        std::mt19937_64 rng(7);
-        for (const std::size_t length :
-                {
-                    std::size_t{1}, std::size_t{2}, std::size_t{3}, std::size_t{5}, std::size_t{7}, std::size_t{8}, std::size_t{9}, std::size_t{12}, std::size_t{16}, std::size_t{17}, std::size_t{33}
-                })
-        {
-            CAPTURE(length)
-            std::set<std::string> distinct;
-            while (distinct.size() < (length == 1 ? 26 : (length == 2 ? 500 : 700))) // (there are 26 and 676 keys of one and two letters)
-            {
-                std::string key(length, 'a');
-                for (char& c : key)
-                {
-                    c = static_cast<char>('a' + (rng() % 26));
-                }
-                distinct.insert(key);
-            }
-            CHECK(max_displacement(std::vector<std::string>(distinct.begin(), distinct.end())) < nlohmann::detail::view::index_max_displacement);
-        }
-    }
-
-    SECTION("keys of every length that differ in one byte")
-    {
-        // In a large object, a key is found by comparing its bytes with those of the member the
-        // table points to: up to 16 bytes as two overlapping words, longer ones with memcmp.
-        // Keys of every length from 0 to 40, and keys that differ from them in one byte.
-        std::mt19937_64 rng(2026);
-        std::vector<std::string> keys;
-        std::set<std::string> distinct;
-        for (std::size_t length = 0; length <= 40; ++length)
-        {
-            for (int copy = 0; copy < 5; ++copy)
-            {
-                std::string key(length, 'a');
-                for (char& c : key)
-                {
-                    c = static_cast<char>('a' + (rng() % 26));
-                }
-                if (distinct.insert(key).second)
-                {
-                    keys.push_back(key);
-                }
-            }
-        }
-        std::string text = "{";
-        for (std::size_t i = 0; i < keys.size(); ++i)
-        {
-            text += (i != 0 ? ",\"" : "\"") + keys[i] + "\":" + std::to_string(i);
-        }
-        text += "}";
-        REQUIRE(keys.size() >= 128); // (a table is built for 128 members)
-        const json_document d = json_document::parse(text);
-        const json_view v = d.root();
-        for (std::size_t i = 0; i < keys.size(); ++i)
-        {
-            CAPTURE(keys[i])
-            CHECK(v[keys[i]].get<std::size_t>() == i);
-            CHECK(v.at(keys[i]).get<std::size_t>() == i);
-            CHECK(v.contains(keys[i]));
-            for (std::size_t at = 0; at < keys[i].size(); ++at)
-            {
-                std::string other = keys[i];
-                other[at] = other[at] == 'z' ? 'y' : 'z';
-                CAPTURE(other)
-                CHECK(v.contains(other) == (distinct.count(other) != 0));
-            }
-            CHECK(v.contains(keys[i] + "a") == (distinct.count(keys[i] + "a") != 0));
-            if (!keys[i].empty())
-            {
-                CHECK(v.contains(keys[i].substr(1)) == (distinct.count(keys[i].substr(1)) != 0));
-            }
-        }
-    }
-
     SECTION("shrink_to_fit releases the tables' spare capacity")
     {
         const auto make_text = [](int objects, int members)

tests/src/unit-json_view_edit.cpp

@@ -661,115 +661,6 @@ TEST_CASE("json_view edits: replacing arrays and objects by scalars")
     CHECK(d.root().materialize() == expected);
 }
 
-TEST_CASE("json_view edits: arrays whose elements have no subtrees")
-{
-    // such an array is indexed directly while it is in its parsed layout; edits
-    // that replace elements by scalars keep it, others move it
-    json_editable_document d = json_editable_document::parse("[10,20,30,40]");
-    json expected = json::array({10, 20, 30, 40});
-    const auto check = [&]
-    {
-        CHECK(d.root().size() == expected.size());
-        for (std::size_t i = 0; i < expected.size(); ++i)
-        {
-            CHECK(d.root()[i].materialize() == expected[i]);
-            CHECK(d.root().at(i).materialize() == expected[i]);
-        }
-        CHECK(d.root()[expected.size()].is_discarded());
-        CHECK(d.root().back().materialize() == expected.back());
-        CHECK(d.root().dump() == expected.dump());
-    };
-    check();
-    d.set(d.root()[1], "x");
-    expected[1] = "x";
-    check();
-    d.set(d.root()[3], 2.5);
-    expected[3] = 2.5;
-    check();
-    d.set(d.root()[2], json::array({1, 2}));
-    expected[2] = json::array({1, 2});
-    check();
-    d.push_back(d.root(), 50);
-    expected.push_back(50);
-    check();
-    d.insert(d.root(), 0, true);
-    expected.insert(expected.begin(), true);
-    check();
-    d.erase(d.root(), 1);
-    expected.erase(expected.begin() + 1);
-    check();
-    d.set(d.root()[2], nullptr);
-    expected[2] = nullptr;
-    check();
-}
-
-TEST_CASE("json_view edits: materializing values nested deeper than the document was parsed")
-{
-    // the stack of open containers of materialize() is sized from the nesting of the parsed text;
-    // a value added by an edit can be deeper than that (and than the stack that is local to the call)
-    json_editable_document d = json_editable_document::parse("[1,[2]]");
-    json expected = json::array({1, json::array({2})});
-    json nested = 3;
-    for (int level = 0; level < 40; ++level)
-    {
-        nested = json::array({nested, json{{"k", level}}});
-    }
-    d.push_back(d.root(), nested);
-    expected.push_back(nested);
-    CHECK(d.root().materialize() == expected);
-    CHECK(d.root()[2].materialize() == nested);
-    d.set(d.root()[1][0], nested);
-    expected[1][0] = nested;
-    CHECK(d.root().materialize() == expected);
-    CHECK(d.root().get<json>() == expected);
-}
-
-TEST_CASE("json_view edits: an editable document before and after its first edit")
-{
-    // until the first edit, an editable document is read like a read-only one; views made before the edit
-    // keep working after it
-    const std::string text = R"({"a":[1,2,{"x":"y"},4],"b":{"c":true,"d":null},"e":"text","f":[]})";
-    const json_document read_only = json_document::parse(text);
-    json_editable_document d = json_editable_document::parse(text);
-    const auto root = d.root();
-    const auto same_as_read_only = [&]
-    {
-        CHECK(root.dump() == read_only.root().dump());
-        CHECK(root.dump(2) == read_only.root().dump(2));
-        CHECK(root.materialize() == read_only.root().materialize());
-        CHECK(root["a"][2]["x"].get_string() == "y");
-        CHECK(root["a"].at(3).get<int>() == 4);
-        CHECK(root["a"].back().get<int>() == 4);
-        CHECK(root.contains("b"));
-        CHECK(!root.contains("zz"));
-        CHECK(root.find("e")->get_string() == "text");
-        CHECK(root.find("zz") == root.end());
-        CHECK(root["b"]["c"].get<bool>());
-        CHECK(root.value("e", "none") == "text");
-        std::size_t count = 0;
-        for (const auto m : root["a"])
-        {
-            CHECK(m.materialize() == read_only.root()["a"][count].materialize());
-            ++count;
-        }
-        CHECK(count == 4);
-    };
-    same_as_read_only();
-    // an edit that changes a scalar in place, then one that moves an array
-    d.set(root["e"], "other");
-    CHECK(root["e"].get_string() == "other");
-    CHECK(root["a"][2]["x"].get_string() == "y");
-    CHECK(root["a"].back().get<int>() == 4);
-    d.push_back(root["f"], 7);
-    CHECK(root["f"][0].get<int>() == 7);
-    CHECK(root["f"].back().get<int>() == 7);
-    CHECK(root.dump() == R"({"a":[1,2,{"x":"y"},4],"b":{"c":true,"d":null},"e":"other","f":[7]})");
-    d.set(root["a"], 2, json::array({1, 2}));
-    CHECK(root["a"][2][1].get<int>() == 2);
-    CHECK(root["a"].dump() == "[1,2,[1,2],4]");
-    CHECK(root.materialize() == json::parse(R"({"a":[1,2,[1,2],4],"b":{"c":true,"d":null},"e":"other","f":[7]})"));
-}
-
 namespace
 {
 // reads of "a" in an object that repeats it: the first member wins, however the

tests/src/unit-serialization.cpp

@@ -1580,3 +1580,94 @@ TEST_CASE("invalid UTF-8 at every position is handled like the reference")
         }
     }
 }
+
+TEST_CASE("short strings are written like the reference, as values and as keys")
+{
+    // strings of up to 16 characters (32 with vector instructions) that need no
+    // escaping are written as a whole (together with the quotes and, for a key,
+    // the colon); everything else, including a string that is merely short,
+    // takes the general path.
+    // Every length around the edges of the size classes of the fast path is
+    // combined with each kind of byte that must send a string to the general
+    // path, at each position, and compared with the reference for values and,
+    // via the value, for keys.
+    const std::vector<std::string> specials =
+    {
+        "\"", "\\", "\n", "\x1f", "\x7f", "\xc3\xa9", "\xe2\x82\xac", "\xf0\x9f\x98\x80", "\xff", "\x80", "\xc3"
+    };
+
+    for (std::size_t length = 0; length <= 36; ++length)
+    {
+        const std::string plain(length, 'k');
+        check_dump_against_reference(plain, false);
+
+        for (const auto& special : specials)
+        {
+            for (std::size_t pos = 0; pos <= length; ++pos)
+            {
+                std::string s = plain;
+                s.insert(pos, special);
+                check_dump_against_reference(s, false);
+
+                for (const bool ensure_ascii :
+                        {
+                            false, true
+                        })
+                {
+                    // a key and a value are written alike, in compact and
+                    // in pretty-printed form
+                    const json value = s;
+                    const json object = json::object({{s, 1}});
+                    for (const auto error_handler :
+                            {
+                                json::error_handler_t::replace, json::error_handler_t::keep
+                            })
+                    {
+                        const std::string quoted = value.dump(-1, ' ', ensure_ascii, error_handler);
+                        CHECK(object.dump(-1, ' ', ensure_ascii, error_handler) == "{" + quoted + ":1}");
+                        CHECK(object.dump(2, ' ', ensure_ascii, error_handler) == "{\n  " + quoted + ": 1\n}");
+                    }
+                }
+            }
+        }
+    }
+}
+
+TEST_CASE("runs of multi-byte characters are escaped like the reference under ensure_ascii")
+{
+    // a run of well-formed multi-byte characters is escaped straight into the
+    // write buffer; it has to flush that mid-run, stop at an ASCII character or
+    // an ill-formed sequence and leave those to the general path, and pick up
+    // behind what the general path has pending
+    const std::vector<std::string> characters =
+    {
+        "\xc2\x80", "\xdf\xbf", "\xe0\xa0\x80", "\xe2\x82\xac", "\xed\x9f\xbf", "\xef\xbf\xbf",
+        "\xf0\x90\x80\x80", "\xf0\x9f\x98\x80", "\xf4\x8f\xbf\xbf"
+    };
+    const std::vector<std::string> interruptions =
+    {
+        "", "a", "\n", "\"", "\x7f", "\xff", "\x80", "\xc3", "\xe2\x82", "\xf0\x9f\x98", "\xed\xa0\x80"
+    };
+
+    for (std::size_t shift = 0; shift <= 13; ++shift)
+    {
+        for (const auto& interruption : interruptions)
+        {
+            for (const std::size_t count :
+                    {
+                        std::size_t{1}, std::size_t{2}, std::size_t{85}, std::size_t{200}
+                    })
+            {
+                std::string s(shift, 'x');
+                for (std::size_t i = 0; i < count; ++i)
+                {
+                    s += characters[(i + shift) % characters.size()];
+                }
+                s += interruption;
+                s += characters[shift % characters.size()];
+                s += characters[(shift + 3) % characters.size()];
+                check_dump_against_reference(s, shift < 2);
+            }
+        }
+    }
+}