Format the numbered test keys of json_view's index with a stream

The keys were made with snprintf() and a format from a list, which
Flawfinder reports as an error (CWE-134, a format string that is not a
literal). A stream now formats them; the 30000 keys of the test are the
same as before.

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

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

@@ -80,7 +80,8 @@ 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).
+   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.
 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

@@ -28,7 +28,8 @@ 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.
+index. Constant for an array none of whose elements is an array or object, since the elements are then adjacent
+in the index.
 
 ## Notes
 

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

@@ -86,7 +86,8 @@ 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).
+   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.
 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/view/builder.hpp

@@ -275,11 +275,41 @@ 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();
-        arena_run(s, static_cast<std::size_t>(p - s));
+        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;
+        }
         for (;;)
         {
-            if (p == m_end)
+            if (p == end)
             {
                 return failed(error_code::string_missing_quote, p);
             }
@@ -287,6 +317,7 @@ class builder
             if (c == '"')
             {
                 ++p;
+                m_arena_write = w;
                 return decoded{p, start, arena_used() - start};
             }
             if (c != '\\')
@@ -297,7 +328,7 @@ class builder
                 return failed(c < 0x20 ? error_code::string_control_character : error_code::string_utf8, p);
             }
             ++p;
-            if (p == m_end)
+            if (p == end)
             {
                 return failed(error_code::string_missing_quote, p);
             }
@@ -315,7 +346,7 @@ class builder
                     {
                         return failed(error_code::string_surrogate_low, p);
                     }
-                    if (m_end - p < 2 || p[0] != '\\' || p[1] != 'u')
+                    if (end - p < 2 || p[0] != '\\' || p[1] != 'u')
                     {
                         return failed(error_code::string_surrogate_high, p);
                     }
@@ -331,27 +362,108 @@ class builder
                     }
                     cp = 0x10000 + ((cp - 0xD800) << 10) + (lo - 0xDC00);
                 }
-                arena_ensure(4);
+                NLOHMANN_VIEW_ENSURE(4)
-                m_arena_write = put_utf8(m_arena_write, cp);
+                w = put_utf8(w, cp);
             }
             else if (NLOHMANN_VIEW_LIKELY(d < 128 && simple_escape[d] != 0))
             {
-                arena_ensure(1);
+                NLOHMANN_VIEW_ENSURE(1)
-                *m_arena_write++ = simple_escape[d];
+                *w++ = simple_escape[d];
             }
             else
             {
                 --p;
                 return failed(error_code::string_escape, p);
             }
-            if (p != m_end && *p == '\\')
+#if NLOHMANN_VIEW_NEON
+            if (p != 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, m_end);
+            p = scan_string_run(p, end);
-            arena_run(r, static_cast<std::size_t>(p - r));
+            const auto n = static_cast<std::size_t>(p - r);
+            NLOHMANN_VIEW_ENSURE(n)
+            std::memcpy(w, r, n);
+            w += n;
+#endif
         }
+#undef NLOHMANN_VIEW_ENSURE
     }
 
     /// does the float token [s, p) overflow FloatType? (parse() rejects it)
@@ -397,14 +509,6 @@ class builder
         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();
@@ -413,25 +517,6 @@ class builder
         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.)
@@ -954,11 +1039,11 @@ indent_done:
                 ++p;
             }
             const unsigned char* const int_start = p;
-            if (p != e && *p == '0')
+            if (cur() == '0')
             {
                 ++p;
             }
-            else if (NLOHMANN_VIEW_LIKELY(p != e && *p >= '1' && *p <= '9'))
+            else if (NLOHMANN_VIEW_LIKELY(cur() >= '1' && cur() <= '9'))
             {
                 p = skip_digits(p + 1, e);
             }
@@ -969,7 +1054,7 @@ 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 (p != e && *p == '.')
+            if (cur() == '.')
             {
                 ++p;
                 const unsigned char* const f0 = p;
@@ -982,20 +1067,20 @@ indent_done:
                 is_float = true;
             }
             std::int64_t exponent = 0;
-            if (p != e && (*p | 0x20) == 'e')
+            if ((cur() | 0x20) == 'e')
             {
                 ++p;
                 bool exp_negative = false;
-                if (p != e && (*p == '+' || *p == '-'))
+                if (cur() == '+' || cur() == '-')
                 {
                     exp_negative = *p == '-';
                     ++p;
                 }
-                if (NLOHMANN_VIEW_UNLIKELY(p == e || !is_digit(*p)))
+                if (NLOHMANN_VIEW_UNLIKELY(!is_digit(cur())))
                 {
                     return fail(error_code::number_after_exponent);
                 }
-                while (p != e && is_digit(*p))
+                while (is_digit(cur()))
                 {
                     if (exponent < 100000)
                     {
@@ -1057,7 +1142,7 @@ indent_done:
             ++p; // opening quote
             const unsigned char* const s = p;
             p = scan_string_run<Value>(p, e);
-            if (NLOHMANN_VIEW_LIKELY(p != e && *p == '"'))
+            if (NLOHMANN_VIEW_LIKELY(cur() == '"'))
             {
                 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

@@ -10,6 +10,9 @@
 
 #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
@@ -154,6 +157,37 @@ 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

@@ -147,20 +147,21 @@ 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
+    /// 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)
     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());
     }
 
@@ -183,7 +184,8 @@ class view_item
 
   private:
     iterator m_it;
-    std::string m_index{}; // NOLINT(readability-redundant-member-init)
+    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)
 };
 
 /// the range returned by basic_json_view::items()

include/nlohmann/detail/view/lookup.hpp

@@ -166,6 +166,10 @@ 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);
@@ -181,6 +185,10 @@ 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 <algorithm> // max
+#include <array> // array
 #include <cstddef> // size_t
 #include <cstdint> // int64_t, uint8_t
 #include <string> // string
@@ -44,8 +44,9 @@ 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; sized once from the
+    // their end, and whether they are objects; for the first 16 levels on the
-    // document's deepest nesting (for a subtree an upper bound)
+    // stack, else sized once from the document's deepest nesting (for a
+    // subtree an upper bound)
     struct frame
     {
         const node* pos;
@@ -53,10 +54,43 @@ 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{};
-    std::vector<frame> open((std::max)(d.max_depth, std::size_t{1}));
+    // (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::size_t depth = 0;
     for (;;)
     {
@@ -76,9 +110,13 @@ BasicJsonType materialize(const document_data& d, const node* n)
                 {
                     sax.start_array(n->len);
                 }
-                if (NLOHMANN_VIEW_UNLIKELY(depth == open.size()))
+                if (NLOHMANN_VIEW_UNLIKELY(depth == capacity))
                 {
-                    open.resize(depth * 2); // (deeper than the recorded nesting, e.g. after edits)
+                    // (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[depth++] = frame{nav::first(d, n), nav::end(d, n), object};
                 break;

include/nlohmann/detail/view/object_index.hpp

@@ -47,27 +47,96 @@ 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
+/// 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)
 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;
-    for (std::size_t i = 0; i < n; ++i)
+    if (n >= 8)
     {
-        w |= static_cast<std::uint64_t>(p[i]) << (8u * 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);
     }
-    h = (h ^ w) * 0x94D049BB133111EBu;
+    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;
     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)
 {
@@ -132,6 +201,27 @@ 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/serializer.hpp

@@ -23,7 +23,6 @@
 #include <nlohmann/detail/view/macro_scope.hpp>
 #include <nlohmann/detail/view/node.hpp>
 #include <nlohmann/detail/view/number.hpp>
-#include <nlohmann/detail/view/simd.hpp>
 
 NLOHMANN_JSON_NAMESPACE_BEGIN
 namespace detail
@@ -81,6 +80,13 @@ class output_buffer
         put(s, N - 1);
     }
 
+    void put_repeated(char c, std::size_t n)
+    {
+        reserve(n);
+        std::memset(m_pos, c, n);
+        m_pos += n;
+    }
+
     /// the write position and the end of the writable space, for a writer
     /// that keeps the position in a local variable (set_cursor() hands it back)
     char* cursor() const noexcept
@@ -137,25 +143,9 @@ class output_buffer
 /// image_check::bounds can have others, which are then written unchanged).
 inline std::size_t plain_output_run(const unsigned char* s, std::size_t n) noexcept
 {
-    std::size_t i = 0;
-#if NLOHMANN_VIEW_SSE2
-    // (16 bytes per step; with NEON, the mask of a step costs more than it saves on the
-    // short runs that are typical here)
-    for (; i + 16 <= n; i += 16)
-    {
-        const __m128i in = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(s + i))); // NOLINT(bugprone-casting-through-void)
-        // (a byte is below 0x20 if it is its own minimum with 0x1F)
-        const __m128i special = _mm_or_si128(_mm_or_si128(_mm_cmpeq_epi8(in, _mm_set1_epi8('"')), _mm_cmpeq_epi8(in, _mm_set1_epi8('\\'))),
-                                             _mm_cmpeq_epi8(_mm_min_epu8(in, _mm_set1_epi8(0x1F)), in));
-        const auto mask = static_cast<std::uint64_t>(static_cast<unsigned>(_mm_movemask_epi8(special)));
-        if (mask != 0)
-        {
-            return i + static_cast<std::size_t>(count_trailing_zeros(mask));
-        }
-    }
-#endif
     constexpr std::uint64_t ones = 0x0101010101010101ull;
     constexpr std::uint64_t high = 0x8080808080808080ull;
+    std::size_t i = 0;
     for (; i + 8 <= n; i += 8)
     {
         const std::uint64_t v = read_eight_bytes(s + i);
@@ -206,70 +196,6 @@ inline bool is_ascii_without_delete(const char* s, std::size_t n) noexcept
     return true;
 }
 
-#if NLOHMANN_VIEW_VECTOR
-/// the bytes of the 16 at p that ensure_ascii cannot copy (a quote, a
-/// backslash, a control character, DEL, or not ASCII; a signed compare with
-/// 0x20 finds control characters and non-ASCII bytes at once), one bit per
-/// byte (x86) or one nibble per byte (NEON)
-NLOHMANN_VIEW_ALWAYS_INLINE std::uint64_t ascii_stop_mask(const unsigned char* p) noexcept
-{
-#if NLOHMANN_VIEW_NEON
-    const uint8x16_t in = vld1q_u8(p);
-    const uint8x16_t special = vorrq_u8(vorrq_u8(vceqq_u8(in, vdupq_n_u8('"')), vceqq_u8(in, vdupq_n_u8('\\'))),
-                                        vorrq_u8(vceqq_u8(in, vdupq_n_u8(0x7F)), vcltq_s8(vreinterpretq_s8_u8(in), vdupq_n_s8(0x20))));
-    return vget_lane_u64(vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(special), 4)), 0);
-#else
-    const __m128i in = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(p))); // 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_or_si128(_mm_cmpeq_epi8(in, _mm_set1_epi8(0x7F)), _mm_cmplt_epi8(in, _mm_set1_epi8(0x20))));
-    return static_cast<std::uint64_t>(static_cast<unsigned>(_mm_movemask_epi8(special)));
-#endif
-}
-
-/// the width in bits of a byte in the mask of ascii_stop_mask()
-constexpr unsigned ascii_stop_bits() noexcept
-{
-    return NLOHMANN_VIEW_NEON ? 4u : 1u;
-}
-#endif
-
-/// As find_ascii_copyable_run(), 16 bytes per step. end is the end of the
-/// buffer that holds the n bytes at p (a short run is read as 16 bytes if
-/// they are in the buffer).
-inline std::size_t ascii_copyable_run(const unsigned char* p, std::size_t n, const unsigned char* end) noexcept
-{
-#if NLOHMANN_VIEW_VECTOR
-    if (n >= 16)
-    {
-        std::size_t i = 0;
-        for (; i + 16 <= n; i += 16)
-        {
-            const std::uint64_t mask = ascii_stop_mask(p + i);
-            if (mask != 0)
-            {
-                return i + (static_cast<std::size_t>(count_trailing_zeros(mask)) / ascii_stop_bits());
-            }
-        }
-        if (i == n)
-        {
-            return n;
-        }
-        // the last 16 bytes: those before i are known to be copyable
-        const std::uint64_t mask = ascii_stop_mask(p + n - 16);
-        return mask != 0 ? n - 16 + (static_cast<std::size_t>(count_trailing_zeros(mask)) / ascii_stop_bits()) : n;
-    }
-    if (end - p >= 16)
-    {
-        // (the bytes after the run are masked out)
-        const std::uint64_t mask = ascii_stop_mask(p) & ((std::uint64_t{1} << (n * ascii_stop_bits())) - 1u);
-        return mask != 0 ? static_cast<std::size_t>(count_trailing_zeros(mask)) / ascii_stop_bits() : n;
-    }
-#else
-    static_cast<void>(end);
-#endif
-    return find_ascii_copyable_run(p, n);
-}
-
 /// A stack that starts in a buffer of the caller (a local array) and moves to
 /// the heap (a vector of the caller) only when that is full, so that dumps of
 /// shallow documents need no allocation. The top is a pointer, as in
@@ -349,39 +275,6 @@ NLOHMANN_VIEW_ALWAYS_INLINE char* put_literal(char* w, const char (&s)[N]) noexc
     return w + N - 1;
 }
 
-/// the depth of the innermost open container, counted only for indented output
-template<bool Counted>
-struct depth_counter
-{
-    std::size_t value = 0;
-    void enter() noexcept
-    {
-        ++value;
-    }
-    std::size_t leave() noexcept
-    {
-        return --value;
-    }
-    std::size_t get() const noexcept
-    {
-        return value;
-    }
-};
-
-template<>
-struct depth_counter<false>
-{
-    void enter() noexcept {}
-    std::size_t leave() noexcept
-    {
-        return 0;
-    }
-    std::size_t get() const noexcept
-    {
-        return 0;
-    }
-};
-
 /// how the view's dump() writes a value
 struct dump_style
 {
@@ -418,95 +311,139 @@ class view_serializer
 
     void dump(const node* root)
     {
-        if (m_style.ensure_ascii)
+        if (!m_style.pretty)
         {
-            dump_ascii(root);
+            if (m_style.ensure_ascii)
+            {
+                dump_compact_ascii(root);
+            }
+            else if (m_style.source_numbers)
+            {
+                dump_compact<true, false>(root);
+            }
+            else
+            {
+                dump_compact<false, false>(root);
+            }
+            return;
         }
-        else if (m_style.pretty)
+        struct frame
         {
-            dump_pretty(root);
+            const node* pos; ///< next element, or key of the next member
-        }
+            const node* end;
-        else if (m_style.source_numbers)
+            bool object;
+            bool first;  ///< nothing written yet
+        };
+        std::array<frame, 32> buffer; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
+        std::vector<frame> heap;
+        small_stack<frame> stack(buffer.data(), buffer.size(), heap);
+        const node* n = root;
+        for (;;)
         {
-            dump_text<true, false, false>(root);
+            // write the value at n
-        }
+            if (is_container(*n))
-        else
+            {
-        {
+                const bool object = n->kind == static_cast<std::uint8_t>(value_t::object);
-            dump_text<false, false, false>(root);
+                if (n->len == 0)
+                {
+                    m_out.put(object ? "{}" : "[]", 2);
+                }
+                else
+                {
+                    m_out.put(object ? '{' : '[');
+                    stack.push_back(frame{nav::first(m_doc, n), nav::end(m_doc, n), object, true});
+                }
+            }
+            else
+            {
+                write_scalar(*n);
+            }
+
+            // go to the next value: close finished containers, then separate
+            for (;;)
+            {
+                if (stack.empty())
+                {
+                    m_out.finish();
+                    return;
+                }
+                if (stack.back().pos == stack.back().end)
+                {
+                    const bool object = stack.back().object;
+                    stack.pop_back();
+                    newline(stack.size());
+                    m_out.put(object ? '}' : ']');
+                    continue;
+                }
+                frame& f = stack.back();
+                if (!f.first)
+                {
+                    m_out.put(',');
+                }
+                f.first = false;
+                newline(stack.size());
+                if (f.object)
+                {
+                    write_string(*f.pos);
+                    if (m_style.pretty)
+                    {
+                        m_out.put(": ");
+                    }
+                    else
+                    {
+                        m_out.put(':');
+                    }
+                    n = nav::value(f.pos + 1);
+                    f.pos = document_data::after(f.pos + 1);
+                }
+                else
+                {
+                    n = nav::value(f.pos);
+                    f.pos = document_data::after(f.pos);
+                }
+                break;
+            }
         }
     }
 
   private:
     /// a string that is not a plain string of the source (decoded, or written
     /// by an edit), without ensure_ascii: runs without characters to escape
-    /// are copied. If validate is set, the string must be valid UTF-8: the
+    /// are copied
-    /// runs are found by the lexer's scan, which validates the sequences, and
+    NLOHMANN_VIEW_NOINLINE void write_decoded(const node& n)
-    /// invalid UTF-8 throws what basic_json::dump() throws. (The compact output
-    /// writes the bytes of a damaged image unchanged, and scans without
-    /// validating them.)
-    NLOHMANN_VIEW_NOINLINE void write_decoded(const node& n, bool validate)
     {
         const auto* const s = reinterpret_cast<const unsigned char*>(m_doc.str(n)); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
         m_out.put('"');
         for (std::size_t i = 0; i < n.len;)
         {
-            const std::size_t run = validate ? string_bulk_run(s + i, n.len - i) : plain_output_run(s + i, n.len - i);
+            const std::size_t run = plain_output_run(s + i, n.len - i);
             if (run != 0)
             {
                 m_out.put(reinterpret_cast<const char*>(s + i), run); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
                 i += run;
                 continue;
             }
-            if (validate && s[i] >= 0x80)
-            {
-                invalid_utf8(s, n.len); // (the scan stopped at ill-formed UTF-8)
-            }
             write_codepoint<false>(s[i], s + i, 1); // a quote, a backslash, or a control character
             ++i;
         }
         m_out.put('"');
     }
 
-    /// dump_text() with indentation, out of line: the compact walk is faster
+    /// dump_compact() with ensure_ascii, out of line: the walk without it is
-    /// when it is not merged with the indented ones into dump()
+    /// faster when it is not merged with this one into dump()
-    NLOHMANN_VIEW_NOINLINE void dump_pretty(const node* root)
+    NLOHMANN_VIEW_NOINLINE void dump_compact_ascii(const node* root)
     {
         if (m_style.source_numbers)
         {
-            dump_text<true, true, false>(root);
+            dump_compact<true, true>(root);
         }
         else
         {
-            dump_text<false, true, false>(root);
+            dump_compact<false, true>(root);
         }
     }
 
-    /// dump_text() with ensure_ascii, out of line: the walk without it is
+    /// whether dump_compact() copies a string or key from the source: one of
-    /// faster when it is not merged with this one into dump()
-    NLOHMANN_VIEW_NOINLINE void dump_ascii(const node* root)
-    {
-        if (m_style.pretty)
-        {
-            if (m_style.source_numbers)
-            {
-                dump_text<true, true, true>(root);
-            }
-            else
-            {
-                dump_text<false, true, true>(root);
-            }
-        }
-        else if (m_style.source_numbers)
-        {
-            dump_text<true, false, true>(root);
-        }
-        else
-        {
-            dump_text<false, false, true>(root);
-        }
-    }
-
-    /// whether dump_text() copies a string or key from the source: one of
     /// the source, and with ensure_ascii one without bytes >= 0x7F (an overload
     /// each, so that the walk without ensure_ascii is compiled exactly as
     /// before: with GCC, a condition that only folds away later changed its
@@ -521,154 +458,13 @@ class view_serializer
         return (n.flags & node_flags::storage) == 0 && is_ascii_without_delete(src + n.off, n.len);
     }
 
-    /*!
+    /// a string with ensure_ascii (dump_compact()), out of line
-    @brief a string with ensure_ascii: the characters that are not printable ASCII as \\uXXXX
+    NLOHMANN_VIEW_NOINLINE void write_ascii_string(const node& n)
-    (a character beyond U+FFFF as a surrogate pair); strings of a document
-    are valid UTF-8, except in a damaged image loaded with image_check::bounds,
-    for which this throws what basic_json::dump() throws for the string
-    */
-    NLOHMANN_VIEW_NOINLINE void write_ascii(const node& n)
     {
-        const auto* const s = reinterpret_cast<const unsigned char*>(m_doc.str(n)); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
+        write_string(n);
-        const std::size_t size = n.len;
-        char* w = m_out.cursor();
-        char* lim = m_out.limit();
-        // room for k bytes
-        const auto room = [&](std::size_t k)
-        {
-            if (NLOHMANN_VIEW_UNLIKELY(static_cast<std::size_t>(lim - w) < k))
-            {
-                m_out.set_cursor(w);
-                m_out.reserve(k);
-                w = m_out.cursor();
-                lim = m_out.limit();
-            }
-        };
-        static constexpr const char* hex = "0123456789abcdef";
-        // \\uXXXX
-        const auto u_escape = [&](std::uint32_t u)
-        {
-            w[0] = '\\';
-            w[1] = 'u';
-            w[2] = hex[(u >> 12u) & 0xFu];
-            w[3] = hex[(u >> 8u) & 0xFu];
-            w[4] = hex[(u >> 4u) & 0xFu];
-            w[5] = hex[u & 0xFu];
-            w += 6;
-        };
-        room(1);
-        *w++ = '"';
-        std::size_t i = 0;
-        // (a string of the source starts with a run that has nothing to escape, 16 bytes per step)
-        const std::size_t prefix = (n.flags & node_flags::storage) == 0 ? ascii_copyable_run(s, size, reinterpret_cast<const unsigned char*>(m_doc.src + m_doc.size)) : 0; // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-        if (prefix != 0)
-        {
-            room(prefix);
-            std::memcpy(w, s, prefix);
-            w += prefix;
-            i = prefix;
-        }
-        while (i < size)
-        {
-            // (a character that needs an escape sequence is not worth a call)
-            const std::size_t run = is_ascii_copyable(s[i]) ? find_ascii_copyable_run(s + i, size - i) : 0;
-            if (run != 0)
-            {
-                room(run);
-                std::memcpy(w, s + i, run);
-                w += run;
-                i += run;
-                continue;
-            }
-            room(12);
-            if (s[i] >= 0x80)
-            {
-                const unsigned char lead = s[i];
-                // (the two-byte sequences of Latin text and the three-byte sequences of most other
-                // text, with continuation bytes of any value: the ranges that are restricted (E0,
-                // ED, and the sequences of four bytes) go through validate_one_utf8())
-                if (lead >= 0xE1 && lead <= 0xEF && lead != 0xED && size - i >= 3 && (s[i + 1] & 0xC0u) == 0x80 && (s[i + 2] & 0xC0u) == 0x80)
-                {
-                    u_escape(((lead & 0x0Fu) << 12u) | ((s[i + 1] & 0x3Fu) << 6u) | (s[i + 2] & 0x3Fu));
-                    i += 3;
-                    continue;
-                }
-                if (lead >= 0xC2 && lead <= 0xDF && size - i >= 2 && (s[i + 1] & 0xC0u) == 0x80)
-                {
-                    u_escape(((lead & 0x1Fu) << 6u) | (s[i + 1] & 0x3Fu));
-                    i += 2;
-                    continue;
-                }
-                const std::size_t len = validate_one_utf8(s + i, size - i);
-                if (NLOHMANN_VIEW_UNLIKELY(len == 0))
-                {
-                    m_out.set_cursor(w);
-                    invalid_utf8(s, size);
-                    return; // LCOV_EXCL_LINE (invalid_utf8 throws)
-                }
-                std::uint32_t codepoint = s[i] & (0xFFu >> (len + 1));
-                for (std::size_t k = 1; k < len; ++k)
-                {
-                    codepoint = (codepoint << 6u) | (s[i + k] & 0x3Fu);
-                }
-                i += len;
-                if (codepoint <= 0xFFFF)
-                {
-                    u_escape(codepoint);
-                }
-                else
-                {
-                    u_escape(0xD7C0u + (codepoint >> 10u));
-                    u_escape(0xDC00u + (codepoint & 0x3FFu));
-                }
-                continue;
-            }
-            // a quote, a backslash, or a control character (or DEL)
-            const unsigned char c = s[i++];
-            char escape = 0;
-            switch (c)
-            {
-                case 0x08:
-                    escape = 'b';
-                    break;
-                case 0x09:
-                    escape = 't';
-                    break;
-                case 0x0A:
-                    escape = 'n';
-                    break;
-                case 0x0C:
-                    escape = 'f';
-                    break;
-                case 0x0D:
-                    escape = 'r';
-                    break;
-                case 0x22:
-                    escape = '"';
-                    break;
-                case 0x5C:
-                    escape = '\\';
-                    break;
-                default:
-                    break;
-            }
-            if (escape != 0)
-            {
-                w[0] = '\\';
-                w[1] = escape;
-                w += 2;
-            }
-            else
-            {
-                u_escape(c);
-            }
-        }
-        room(1);
-        *w++ = '"';
-        m_out.set_cursor(w);
     }
 
-    /// the copies of dump_text() that are not fixed-size moves (long
+    /// the copies of dump_compact() that are not fixed-size moves (long
     /// strings, or near the end of the source); out of line, so that the
     /// compiler does not merge the fixed-size moves into this call
     NLOHMANN_VIEW_NOINLINE static void copy_long(char* to, const char* from, std::size_t n) noexcept
@@ -685,7 +481,7 @@ class view_serializer
     }
 
     /*!
-    @brief the output, compact (the default dump()) or indented, with or without ensure_ascii
+    @brief the compact output (the default dump(), or with ensure_ascii)
 
     The same walk as dump(), with the write position in a local variable
     (stores through char pointers would otherwise force a reload of the
@@ -693,11 +489,11 @@ class view_serializer
     the source copied by fixed-size moves of 32 bytes where the source has
     that many bytes left, instead of a library call per token. The buffer
     keeps 64 bytes of slack for the overshoot. With ensure_ascii (Ascii), a
-    string of the source is copied only if it has nothing to escape (see
+    string of the source is copied only if it has no byte >= 0x7F (see
-    copied()); any other string is written by write_ascii().
+    is_ascii_without_delete()); any other string is written by write_string().
     */
-    template<bool SourceNumbers, bool Pretty, bool Ascii>
+    template<bool SourceNumbers, bool Ascii>
-    void dump_text(const node* root)
+    void dump_compact(const node* root)
     {
         struct frame
         {
@@ -712,16 +508,6 @@ class view_serializer
         const char* const src_end = src + m_doc.size;
         char* w = m_out.cursor();
         char* lim = m_out.limit();
-        // (indented output) a line break and 63 indentation characters, from
-        // which the line break of a level of up to 63 characters is a copy
-        std::array<char, 64> ruler; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): filled below if used
-        if (Pretty)
-        {
-            ruler.fill(m_style.indent_char);
-            ruler[0] = '\n';
-        }
-        const std::size_t indent = m_style.indent;
-        depth_counter<Pretty> level; // depth of the innermost open container (indented output)
         // room for n bytes and the slack
         const auto room = [&](std::size_t n)
         {
@@ -753,22 +539,6 @@ class view_serializer
             }
             w += n;
         };
-        // (indented output) the line break and the indentation of a level
-        const auto newline = [&](std::size_t depth)
-        {
-            const std::size_t count = 1 + (depth * indent);
-            room(count);
-            if (count <= ruler.size())
-            {
-                std::memcpy(w, ruler.data(), ruler.size());
-            }
-            else
-            {
-                *w = '\n';
-                std::memset(w + 1, m_style.indent_char, count - 1);
-            }
-            w += count;
-        };
         // a string that is not a plain string of the source (out of line, so
         // that the cursor stays in a register here)
         const auto escaped = [&](const node & n)
@@ -776,11 +546,11 @@ class view_serializer
             m_out.set_cursor(w);
             if (enabled(Ascii))
             {
-                write_ascii(n);
+                write_ascii_string(n);
             }
             else
             {
-                write_decoded(n, Pretty);
+                write_decoded(n);
             }
             w = m_out.cursor();
             lim = m_out.limit();
@@ -881,7 +651,6 @@ class view_serializer
                     {
                         *w++ = object ? '{' : '[';
                         stack.push_back(cur);
-                        level.enter();
                         if (Editable)
                         {
                             cur = frame{nav::first(m_doc, n), nav::end(m_doc, n), object};
@@ -924,10 +693,6 @@ class view_serializer
                     {
                         break;
                     }
-                    if (Pretty)
-                    {
-                        newline(level.leave());
-                    }
                     room(1);
                     *w++ = cur.object ? '}' : ']';
                     cur = stack.back();
@@ -936,17 +701,13 @@ class view_serializer
                 room(1);
                 *w++ = ',';
             }
-            if (Pretty)
-            {
-                newline(level.get());
-            }
             const node* const at = Editable ? cur.pos : n;
             if (cur.object)
             {
                 const node& key = *at;
                 if (copied(key, src, std::integral_constant<bool, Ascii>()))
                 {
-                    room(key.len + (Pretty ? 4 : 3));
+                    room(key.len + 3);
                     *w++ = '"';
                     copy(src + key.off, key.len);
                     w[0] = '"';
@@ -956,13 +717,9 @@ class view_serializer
                 else
                 {
                     escaped(key);
-                    room(Pretty ? 2 : 1);
+                    room(1);
                     *w++ = ':';
                 }
-                if (Pretty)
-                {
-                    *w++ = ' ';
-                }
                 if (Editable)
                 {
                     n = nav::value(at + 1);
@@ -981,6 +738,69 @@ class view_serializer
         }
     }
 
+    void newline(std::size_t level)
+    {
+        if (m_style.pretty)
+        {
+            m_out.put('\n');
+            m_out.put_repeated(m_style.indent_char, level * m_style.indent);
+        }
+    }
+
+    void write_scalar(const node& n)
+    {
+        switch (static_cast<value_t>(n.kind))
+        {
+            case value_t::null:
+                m_out.put("null");
+                break;
+            case value_t::boolean:
+                if ((n.flags & node_flags::is_true) != 0)
+                {
+                    m_out.put("true");
+                }
+                else
+                {
+                    m_out.put("false");
+                }
+                break;
+            case value_t::string:
+                write_string(n);
+                break;
+            case value_t::number_integer:
+            case value_t::number_unsigned:
+            {
+                const char* const token = m_doc.str(n);
+                const std::uint32_t len = number_length(n);
+                if (!m_style.source_numbers && len == 2 && token[0] == '-' && token[1] == '0')
+                {
+                    m_out.put('0'); // parse() reads -0 as the integer 0
+                }
+                else
+                {
+                    m_out.put(token, len);
+                }
+                break;
+            }
+            case value_t::number_float:
+                if (m_style.source_numbers && (n.flags & node_flags::storage) != node_flags::edited)
+                {
+                    m_out.put(m_doc.str(n), n.len); // (a float set by an edit is written as with shortest)
+                }
+                else
+                {
+                    write_float_node(n);
+                }
+                break;
+            case value_t::object:    // LCOV_EXCL_LINE (containers are written by dump())
+            case value_t::array:     // LCOV_EXCL_LINE
+            case value_t::binary:    // LCOV_EXCL_LINE (not in a document)
+            case value_t::discarded: // LCOV_EXCL_LINE
+            default:                 // LCOV_EXCL_LINE
+                break;               // LCOV_EXCL_LINE
+        }
+    }
+
     /// a float node as dump() writes it
     void write_float_node(const node& n)
     {
@@ -1091,6 +911,72 @@ class view_serializer
         m_out.put(s.data(), s.size());
     }
 
+    void write_string(const node& n)
+    {
+        const char* const s = m_doc.str(n);
+        m_out.put('"');
+        if ((n.flags & node_flags::storage) == 0 && (!m_style.ensure_ascii || is_ascii_without_delete(s, n.len)))
+        {
+            // a string of the source without escape sequences has nothing to
+            // escape (with ensure_ascii, if it is printable ASCII)
+            m_out.put(s, n.len);
+        }
+        else if (m_style.ensure_ascii)
+        {
+            write_escaped<true>(reinterpret_cast<const unsigned char*>(s), n.len); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
+        }
+        else
+        {
+            write_escaped<false>(reinterpret_cast<const unsigned char*>(s), n.len); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
+        }
+        m_out.put('"');
+    }
+
+    /// as serializer::dump_escaped(); strings of a document are valid UTF-8,
+    /// except in a damaged image loaded with image_check::bounds, for which
+    /// this throws what basic_json::dump() throws for the string
+    template<bool EnsureAscii>
+    void write_escaped(const unsigned char* s, std::size_t n)
+    {
+        std::size_t i = 0;
+        while (i < n)
+        {
+            std::size_t run = 0;
+            if (!EnsureAscii)
+            {
+                run = string_bulk_run(s + i, n - i);
+            }
+            else if (is_ascii_copyable(s[i]))
+            {
+                run = find_ascii_copyable_run(s + i, n - i);
+            }
+            if (run != 0)
+            {
+                m_out.put(reinterpret_cast<const char*>(s + i), run); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
+                i += run;
+                continue;
+            }
+            std::uint32_t codepoint = s[i];
+            std::size_t len = 1;
+            if (codepoint >= 0x80)
+            {
+                len = validate_one_utf8(s + i, n - i);
+                if (NLOHMANN_VIEW_UNLIKELY(len == 0))
+                {
+                    invalid_utf8(s, n);
+                    return;
+                }
+                codepoint &= 0xFFu >> (len + 1);
+                for (std::size_t k = 1; k < len; ++k)
+                {
+                    codepoint = (codepoint << 6u) | (s[i + k] & 0x3Fu);
+                }
+            }
+            write_codepoint<EnsureAscii>(codepoint, s + i, len);
+            i += len;
+        }
+    }
+
     /// throw what basic_json::dump() throws for a string that is not valid UTF-8
     NLOHMANN_VIEW_NOINLINE static void invalid_utf8(const unsigned char* s, std::size_t n)
     {

include/nlohmann/detail/view/simd.hpp

@@ -116,6 +116,34 @@ 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 ? basic_json_view(m_doc, navigation::value(detail::view::element_at<Editable>(*m_doc, m_node, idx))) : basic_json_view();
+        return idx < m_node->len ? element(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 basic_json_view(m_doc, navigation::value(detail::view::element_at<Editable>(*m_doc, m_node, idx)));
+        return element(idx);
     }
 
     /// any other integer type, see operator[]; negative values are out of
@@ -392,7 +392,13 @@ class basic_json_view
 
     string_t value(string_view_t key, const char* default_value) const
     {
-        return value(key, string_t(default_value));
+        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>();
     }
 
     /// the value a JSON pointer refers to converted to T, or the default
@@ -411,7 +417,12 @@ class basic_json_view
 
     string_t value(const json_pointer& ptr, const char* default_value) const
     {
-        return value(ptr, string_t(default_value));
+        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>();
     }
 
     /// the first element or member value; a primitive value itself. Throws
@@ -433,7 +444,8 @@ class basic_json_view
     {
         if (is_structured() && m_node->len != 0)
         {
-            return basic_json_view(m_doc, navigation::value(detail::view::last_child<Editable>(*m_doc, m_node) + (is_object() ? 1 : 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 front();
     }
@@ -450,7 +462,8 @@ class basic_json_view
         {
             return end();
         }
-        const node* const k = detail::view::find_member<Editable>(*m_doc, m_node, key.data(), key.size());
+        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());
         return k != nullptr ? iterator(m_doc, k, true) : end();
     }
 
@@ -467,7 +480,8 @@ 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() && detail::view::find_member<Editable>(*m_doc, m_node, key.data(), key.size()) != nullptr;
+        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);
     }
 
     bool contains(const char* key) const
@@ -627,7 +641,14 @@ 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;
-        detail::view::view_serializer<BasicJsonType, Editable>(*m_doc, out, estimate, style).dump(m_node);
+        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);
+        }
         return out;
     }
 
@@ -707,7 +728,7 @@ class basic_json_view
         {
             return BasicJsonType(value_t::discarded);
         }
-        return detail::view::materialize<BasicJsonType, Editable>(*m_doc, m_node);
+        return unedited() ? detail::view::materialize<BasicJsonType, false>(*m_doc, m_node) : detail::view::materialize<BasicJsonType, Editable>(*m_doc, m_node);
     }
 
     /// byte offset of this value in the source text (for strings: of the
@@ -785,10 +806,32 @@ 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
@@ -1528,7 +1571,8 @@ 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 : 3 > {});
+                          : detail::view::is_adapter_input<D>::value ? 2
+                          : detail::view::is_c_stream<D>::value ? 4 : 3 > {});
         // NOLINTEND(readability-avoid-nested-conditional-operator)
     }
 
@@ -1550,6 +1594,19 @@ 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

@@ -185,6 +185,29 @@ 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)
@@ -410,6 +433,31 @@ 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());
@@ -1006,6 +1054,49 @@ 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})");
@@ -1045,6 +1136,28 @@ 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())
@@ -1383,7 +1496,17 @@ 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

@@ -523,6 +523,58 @@ 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

@@ -21,6 +21,7 @@ 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>
@@ -29,6 +30,7 @@ using json_view_test::has_duplicate_keys;
 #include <iomanip>
 #include <map>
 #include <random>
+#include <set>
 #include <sstream>
 #include <string>
 #include <vector>
@@ -186,131 +188,6 @@ TEST_CASE("json_view dump")
         CHECK(deep_document.root().dump() == deep);
     }
 
-    SECTION("ensure_ascii: a character that needs an escape at each position of a string")
-    {
-        // string lengths around the width of the vector steps, in a string value, a key, and a value near the end of the text
-        for (const char* const special :
-                {
-                    "\xC3\xA9", "\xE4\xB8\xAD", "\xF0\x9F\x98\x80", "\x7F", "\\n", "\\u0001", "\\\"", "\\\\"
-                })
-        {
-            for (std::size_t length = 0; length <= 40; ++length)
-            {
-                for (std::size_t position = 0; position <= length; ++position)
-                {
-                    std::string content(length, 'a');
-                    content.insert(position, special);
-                    const std::string texts[] =
-                    {
-                        "\"" + content + "\"",
-                        "[\"" + content + "\"]",
-                        "{\"" + content + "\":1}",
-                    };
-                    for (const std::string& text : texts)
-                    {
-                        CAPTURE(text)
-                        const ordered_json_document d = ordered_json_document::parse(text);
-                        const ordered_json j = ordered_json::parse(text);
-                        CHECK(d.root().dump(-1, ' ', true) == j.dump(-1, ' ', true));
-                        CHECK(d.root().dump(2, ' ', true) == j.dump(2, ' ', true));
-                        CHECK(d.root().dump() == j.dump());
-                    }
-                }
-            }
-        }
-    }
-
-    SECTION("ensure_ascii: every character of the Basic Multilingual Plane and some beyond")
-    {
-        // (the two- and three-byte sequences, including the ranges that need a check: E0, ED, EF BF BF)
-        std::string text = "[";
-        std::size_t in_chunk = 0;
-        const auto append = [&](std::uint32_t cp)
-        {
-            if (cp < 0x80)
-            {
-                if (cp < 0x20 || cp == '"' || cp == '\\')
-                {
-                    return;
-                }
-                text += static_cast<char>(cp);
-            }
-            else if (cp < 0x800)
-            {
-                text += static_cast<char>(0xC0 | (cp >> 6));
-                text += static_cast<char>(0x80 | (cp & 0x3F));
-            }
-            else if (cp < 0x10000)
-            {
-                text += static_cast<char>(0xE0 | (cp >> 12));
-                text += static_cast<char>(0x80 | ((cp >> 6) & 0x3F));
-                text += static_cast<char>(0x80 | (cp & 0x3F));
-            }
-            else
-            {
-                text += static_cast<char>(0xF0 | (cp >> 18));
-                text += static_cast<char>(0x80 | ((cp >> 12) & 0x3F));
-                text += static_cast<char>(0x80 | ((cp >> 6) & 0x3F));
-                text += static_cast<char>(0x80 | (cp & 0x3F));
-            }
-        };
-        for (std::uint32_t cp = 0x20; cp < 0x10400; ++cp)
-        {
-            if (cp >= 0xD800 && cp < 0xE000)
-            {
-                continue;
-            }
-            if (in_chunk == 0)
-            {
-                text += text.size() > 1 ? ",\"" : "\"";
-            }
-            append(cp);
-            if (++in_chunk == 37)
-            {
-                text += "\"";
-                in_chunk = 0;
-            }
-        }
-        text += in_chunk != 0 ? "\"]" : "]";
-        const ordered_json_document d = ordered_json_document::parse(text);
-        const ordered_json j = ordered_json::parse(text);
-        CHECK(d.root().dump(-1, ' ', true) == j.dump(-1, ' ', true));
-        CHECK(d.root().dump(2, ' ', true) == j.dump(2, ' ', true));
-        CHECK(d.root().dump() == j.dump());
-        CHECK(d.root().dump(2) == j.dump(2));
-    }
-
-    SECTION("deep nesting, indented")
-    {
-        // indentations of up to and beyond the width of the writer's fixed-size copy
-        for (const int depth :
-                {
-                    1, 5, 20, 70, 300
-                })
-        {
-            std::string text;
-            for (int i = 0; i < depth; ++i)
-            {
-                text += i % 2 == 0 ? "[1," : "{\"k\":2,\"\\u00e9\":";
-            }
-            text += "[]";
-            for (int i = depth - 1; i >= 0; --i)
-            {
-                text += i % 2 == 0 ? "]" : "}";
-            }
-            const ordered_json_document d = ordered_json_document::parse(text);
-            const ordered_json j = ordered_json::parse(text);
-            for (const int indent :
-                    {
-                        0, 1, 2, 3, 8
-                    })
-            {
-                CHECK(d.root().dump(indent) == j.dump(indent));
-                CHECK(d.root().dump(indent, '\t') == j.dump(indent, '\t'));
-            }
-        }
-    }
-
     SECTION("the output buffer of a small value is small")
     {
         // an escaped key after the value: its node lies in the arena, so the
@@ -723,6 +600,142 @@ 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

@@ -661,6 +661,115 @@ 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-json_view_image.cpp

@@ -682,26 +682,6 @@ TEST_CASE("json_view images: ownership")
 #if !defined(JSON_NOEXCEPTION)
 TEST_CASE("json_view images: errors")
 {
-    SECTION("invalid UTF-8 of a decoded string: the compact dump writes it, the others throw")
-    {
-        const json_document d = json_document::parse(R"({"k\n":"\u00e9x"})");
-        std::vector<std::uint8_t> image = d.save();
-        const std::size_t arena = text_at(image) + header_size_field(image, 16) + 1;
-        image[arena + 3] = 0x28; // the key is "k\n"; the value starts at 3: 0xC3 0x28 is invalid
-        const json_document loaded = json_document::load(image, image_check::bounds);
-        CHECK(loaded.root().dump().size() == 13);
-        for (const int indent :
-                {
-                    0, 2
-                })
-        {
-            CHECK_THROWS_AS(loaded.root().dump(indent), json::type_error);
-            CHECK_THROWS_AS(loaded.root().dump(indent, ' ', true), json::type_error);
-        }
-        CHECK_THROWS_AS(loaded.root().dump(-1, ' ', true), json::type_error);
-        CHECK_THROWS_WITH_AS(loaded.root().dump(2), "[json.exception.type_error.316] invalid UTF-8 byte at index 1: 0x28", json::type_error&);
-    }
-
     SECTION("a literal as the root: dump() after loading")
     {
         for (const char* text :