Hold the token carry buffer in a std::unique_ptr

clang-tidy rejected the raw new[]/delete[] of token_carry_buffer
(cppcoreguidelines-owning-memory) and the capacity computation
(readability-use-std-min-max). The storage is now owned by a
std::unique_ptr<char[]>, as in json_view's edit storage, and the new
capacity is a std::max.

istream parse instructions (Apple clang, twitter, citm, canada, floats)
are unchanged within noise.

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

docs/mkdocs/docs/home/architecture.md

@@ -339,11 +339,6 @@ The `serializer` (used by [`dump`](../api/basic_json/dump.md) and [`operator<<`]
 - `output_stream_adapter` writes to a `std::ostream`.
 - `output_string_adapter` appends to a string.
 
-The `binary_writer` does not call an adapter for every byte. The `to_*` functions that return a `std::vector` write
-into the vector through a sink (`output_vector_sink`) that is not virtual. The functions that take an output adapter
-write through a sink (`output_adapter_sink`) that collects the output in a buffer of one kibibyte and passes it to the
-adapter in blocks, so that the adapter is called (and a stream locked) once per block instead of once per value.
-
 ## Value conversion
 
 Values are converted from and to other types with the `JSONSerializer` template parameter. The default,

include/nlohmann/detail/input/input_adapters.hpp

@@ -8,17 +8,18 @@
 
 #pragma once
 
-#include <algorithm> // count, find, min
+#include <algorithm> // count, find, max, min
 #include <array> // array
 #include <cstddef> // size_t
 #include <cstdint> // uint32_t
 #include <cstring> // strlen
 #include <iterator> // begin, end, iterator_traits, random_access_iterator_tag, distance, next, reverse_iterator
 #include <limits> // numeric_limits
+#include <memory> // unique_ptr
 #include <streambuf> // streambuf
 #include <string> // string, char_traits
 #include <type_traits> // enable_if, is_base_of, is_pointer, is_integral, remove_pointer
-#include <utility> // pair, declval
+#include <utility> // declval, move, pair
 #include <vector> // vector
 
 #ifndef JSON_NO_IO
@@ -72,6 +73,81 @@ enum class input_format_t { json, cbor, msgpack, ubjson, bson, bjdata, bon8 };
 
 #ifndef JSON_NO_IO
 /*!
+A growable array of characters for the part of a token that an input adapter
+copied out of its window: unlike std::vector<char>::push_back(), appending a
+character takes no reference to a local, and is a few instructions when there
+is room.
+*/
+class token_carry_buffer
+{
+  public:
+    token_carry_buffer() = default;
+    token_carry_buffer(const token_carry_buffer&) = delete;
+    token_carry_buffer& operator=(const token_carry_buffer&) = delete;
+    token_carry_buffer(token_carry_buffer&& rhs) noexcept
+        : m_data(std::move(rhs.m_data)), m_end(rhs.m_end), m_capacity_end(rhs.m_capacity_end)
+    {
+        rhs.m_end = rhs.m_capacity_end = nullptr;
+    }
+    token_carry_buffer& operator=(token_carry_buffer&&) = delete;
+    ~token_carry_buffer() = default;
+
+    void clear() noexcept
+    {
+        m_end = m_data.get();
+    }
+
+    void push_back(char c)
+    {
+        if (JSON_HEDLEY_UNLIKELY(m_end == m_capacity_end))
+        {
+            grow(1);
+        }
+        *m_end++ = c;
+    }
+
+    void append(const char* first, const char* last)
+    {
+        const auto n = static_cast<std::size_t>(last - first);
+        if (n > static_cast<std::size_t>(m_capacity_end - m_end))
+        {
+            grow(n);
+        }
+        if (n != 0)
+        {
+            std::memcpy(m_end, first, n);
+        }
+        m_end += n;
+    }
+
+    /// replace the contents of @a out
+    void copy_to(std::vector<char>& out) const
+    {
+        out.assign(m_data.get(), m_end);
+    }
+
+  private:
+    /// make room for @a extra more characters
+    JSON_HEDLEY_NEVER_INLINE void grow(std::size_t extra)
+    {
+        const auto size = static_cast<std::size_t>(m_end - m_data.get());
+        const auto capacity = static_cast<std::size_t>(m_capacity_end - m_data.get());
+        const std::size_t new_capacity = (std::max)(capacity < 32 ? static_cast<std::size_t>(32) : 2 * capacity, size + extra);
+        std::unique_ptr<char[]> data(new char[new_capacity]); // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
+        if (size != 0)
+        {
+            std::memcpy(data.get(), m_data.get(), size);
+        }
+        m_data = std::move(data);
+        m_end = m_data.get() + size;
+        m_capacity_end = m_data.get() + new_capacity;
+    }
+
+    std::unique_ptr<char[]> m_data{}; // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays,readability-redundant-member-init)
+    char* m_end = nullptr;
+    char* m_capacity_end = nullptr;
+};
+/*!
 Input adapter for stdio file access. This adapter read only 1 byte and do not use any
  buffer. This adapter is a very low level adapter.
 */
@@ -209,6 +285,7 @@ class input_stream_adapter
         , token_segment(rhs.token_segment)
         , current_in_get_area(rhs.current_in_get_area)
         , tracking_token(rhs.tracking_token)
+        , no_get_area(rhs.no_get_area)
 #endif
     {
         rhs.is = nullptr;
@@ -295,37 +372,20 @@ class input_stream_adapter
     std::char_traits<char>::int_type get_character()
     {
 #if !JSON_DISABLE_STREAM_BULK_SCAN
-        // sbumpc() refills the get area if it is exhausted
+        // the character is in the get area: step over it, as sbumpc() does
-        const bool refill = streambuf_access::get_ptr(sb) == streambuf_access::get_end(sb);
+        const char* const next = streambuf_access::get_ptr(sb);
-        if (JSON_HEDLEY_UNLIKELY(refill))
+        if (JSON_HEDLEY_LIKELY(next != streambuf_access::get_end(sb)))
-        {
-            save_token_segment();
-        }
-#endif
-
-        auto res = sb->sbumpc();
-        // set eof manually, as we don't use the istream interface.
-        if (JSON_HEDLEY_UNLIKELY(res == std::char_traits<char>::eof()))
-        {
-#if !JSON_DISABLE_STREAM_BULK_SCAN
-            current_in_get_area = false;
-#endif
-            is->clear(is->rdstate() | std::ios::eofbit);
-        }
-#if !JSON_DISABLE_STREAM_BULK_SCAN
-        else if (JSON_HEDLEY_UNLIKELY(refill))
-        {
-            // the consumed character is at gptr() - 1, unless the streambuf
-            // has no get area and returned it from uflow()
-            const char* const next = streambuf_access::get_ptr(sb);
-            after_refill(res, next != nullptr && next != streambuf_access::get_begin(sb));
-        }
-        else
         {
             current_in_get_area = true;
+            streambuf_access::bump(sb, 1);
+            return std::char_traits<char>::to_int_type(*next);
+        }
+        if (no_get_area)
+        {
+            return get_character_no_get_area();
         }
 #endif
-        return res;
+        return get_character_slow();
     }
 #endif
 
@@ -334,6 +394,18 @@ class input_stream_adapter
     {
 #if JSON_PRECISE_STREAM_POSITION
         commit_lookahead();
+#endif
+#if !JSON_DISABLE_STREAM_BULK_SCAN
+        // the elements are in the get area: copy them, as sgetn() does, but
+        // without the virtual call
+        const char* const first = streambuf_access::get_ptr(sb);
+        const auto available = static_cast<std::size_t>(streambuf_access::get_end(sb) - first);
+        if (JSON_HEDLEY_LIKELY(count * sizeof(T) <= available && count * sizeof(T) <= static_cast<std::size_t>((std::numeric_limits<int>::max)())))
+        {
+            std::memcpy(dest, first, count * sizeof(T));
+            streambuf_access::bump(sb, static_cast<int>(count * sizeof(T)));
+            return count * sizeof(T);
+        }
 #endif
         auto res = static_cast<std::size_t>(sb->sgetn(reinterpret_cast<char*>(dest), static_cast<std::streamsize>(count * sizeof(T))));
         if (JSON_HEDLEY_UNLIKELY(res < count * sizeof(T)))
@@ -421,7 +493,7 @@ class input_stream_adapter
     // last one if @a drop_last.
     void copy_token(std::vector<char>& out, bool drop_last) const
     {
-        out = token_carry;
+        token_carry.copy_to(out);
         if (token_segment != nullptr)
         {
             out.insert(out.end(), token_segment, current_end());
@@ -434,6 +506,47 @@ class input_stream_adapter
 #endif
 
   private:
+#if !JSON_PRECISE_STREAM_POSITION
+    // the get area is exhausted, or there is none
+#if !JSON_DISABLE_STREAM_BULK_SCAN
+    JSON_HEDLEY_NEVER_INLINE
+#endif
+    std::char_traits<char>::int_type get_character_slow()
+    {
+#if !JSON_DISABLE_STREAM_BULK_SCAN
+        // sbumpc() refills the get area if it is exhausted
+        const bool refill = streambuf_access::get_ptr(sb) == streambuf_access::get_end(sb);
+        if (JSON_HEDLEY_UNLIKELY(refill))
+        {
+            save_token_segment();
+        }
+#endif
+
+        auto res = sb->sbumpc();
+        // set eof manually, as we don't use the istream interface.
+        if (JSON_HEDLEY_UNLIKELY(res == std::char_traits<char>::eof()))
+        {
+#if !JSON_DISABLE_STREAM_BULK_SCAN
+            current_in_get_area = false;
+#endif
+            is->clear(is->rdstate() | std::ios::eofbit);
+        }
+#if !JSON_DISABLE_STREAM_BULK_SCAN
+        else if (JSON_HEDLEY_UNLIKELY(refill))
+        {
+            // the consumed character is at gptr() - 1, unless the streambuf
+            // has no get area and returned it from uflow()
+            const char* const next = streambuf_access::get_ptr(sb);
+            after_refill(res, next != nullptr && next != streambuf_access::get_begin(sb));
+        }
+        else
+        {
+            current_in_get_area = true;
+        }
+#endif
+        return res;
+    }
+#endif
 #if !JSON_DISABLE_STREAM_BULK_SCAN
     // Reads the protected get-area pointers of any std::streambuf. Naming the
     // members through a derived class makes forming the member pointers
@@ -457,6 +570,11 @@ class input_stream_adapter
         {
             (s->*(&streambuf_access::gbump))(n);
         }
+        // sbumpc() for an exhausted get area
+        static std::streambuf::int_type next_character(std::streambuf* s)
+        {
+            return (s->*(&streambuf_access::uflow))();
+        }
     };
 
     // one past the character last returned by get_character(), if that is in
@@ -477,16 +595,53 @@ class input_stream_adapter
     {
         if (token_segment != nullptr)
         {
-            token_carry.insert(token_carry.end(), token_segment, streambuf_access::get_end(sb));
+            token_carry.append(token_segment, streambuf_access::get_end(sb));
             token_segment = nullptr;
         }
     }
 
+#if !JSON_PRECISE_STREAM_POSITION
+    // The streambuf has no get area (e.g., std::cin synchronized with stdio):
+    // every character comes from uflow(), and the token is kept by value.
+    JSON_HEDLEY_NEVER_INLINE std::char_traits<char>::int_type get_character_no_get_area()
+    {
+        // the get area is exhausted, so this is what sbumpc() does
+        const auto res = streambuf_access::next_character(sb);
+        if (JSON_HEDLEY_UNLIKELY(res == std::char_traits<char>::eof() || streambuf_access::get_end(sb) != nullptr))
+        {
+            return get_character_no_get_area_other(res);
+        }
+        // current_in_get_area is false: only the first character of a get
+        // area, or the end of the input, is read here
+        if (tracking_token)
+        {
+            token_carry.push_back(std::char_traits<char>::to_char_type(res));
+        }
+        return res;
+    }
+
+    // @a res came from uflow() of a streambuf without a get area: it is the
+    // end of the input, or the streambuf has a get area now
+    JSON_HEDLEY_NEVER_INLINE std::char_traits<char>::int_type get_character_no_get_area_other(std::char_traits<char>::int_type res)
+    {
+        if (res == std::char_traits<char>::eof())
+        {
+            current_in_get_area = false;
+            is->clear(is->rdstate() | std::ios::eofbit);
+            return res;
+        }
+        // the consumed character is at gptr() - 1
+        after_refill(res, streambuf_access::get_ptr(sb) != streambuf_access::get_begin(sb));
+        return res;
+    }
+#endif
+
     // character @a c was just read into a new get area (@a in_get_area) or
     // returned without one
     void after_refill(std::char_traits<char>::int_type c, bool in_get_area)
     {
         current_in_get_area = in_get_area;
+        no_get_area = !in_get_area;
         if (!tracking_token)
         {
             return;
@@ -525,13 +680,16 @@ class input_stream_adapter
 #endif
 #if !JSON_DISABLE_STREAM_BULK_SCAN
     /// the part of the current token that was in earlier get areas
-    std::vector<char> token_carry{}; // NOLINT(readability-redundant-member-init)
+    token_carry_buffer token_carry{}; // NOLINT(readability-redundant-member-init)
     /// start of the current token's part in the get area, or nullptr
     const char* token_segment = nullptr;
     /// whether the character last returned by get_character() is in the get area
     bool current_in_get_area = false;
     /// whether a token is tracked at all; the binary readers never start one
     bool tracking_token = false;
+    /// whether the streambuf had no get area when it was last asked for a
+    /// character
+    bool no_get_area = false;
 #endif
 };
 #endif  // JSON_NO_IO

include/nlohmann/detail/output/output_adapters.hpp

@@ -55,66 +55,6 @@ using output_adapter_t = std::shared_ptr<output_adapter_protocol<CharType>>;
 /// output_vector_sink also appends writes of at least this size with insert()
 constexpr std::size_t max_reserve_size = 256;
 
-/// @brief copy @a length characters, at most 32, without a call of memcpy()
-///
-/// Short strings are the typical payload of a binary value, and a call of
-/// memcpy() costs more than copying them. A copy of 16 to 32 characters is two
-/// possibly overlapping 16-byte copies, one of 8 to 15 two 8-byte copies, and
-/// so on down to a single character; each is a fixed-size load and store.
-/// Nothing outside of [src, src + length) is read or written.
-template<typename CharType>
-inline void copy_short(CharType* dst, const CharType* src, const std::size_t length, std::true_type /*is_byte*/) noexcept
-{
-    JSON_ASSERT(length <= 32);
-    if (length >= 16)
-    {
-        std::array<char, 16> first; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
-        std::array<char, 16> last; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
-        std::memcpy(first.data(), src, 16);
-        std::memcpy(last.data(), src + (length - 16), 16);
-        std::memcpy(dst, first.data(), 16);
-        std::memcpy(dst + (length - 16), last.data(), 16);
-    }
-    else if (length >= 8)
-    {
-        std::array<char, 8> first; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
-        std::array<char, 8> last; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
-        std::memcpy(first.data(), src, 8);
-        std::memcpy(last.data(), src + (length - 8), 8);
-        std::memcpy(dst, first.data(), 8);
-        std::memcpy(dst + (length - 8), last.data(), 8);
-    }
-    else if (length >= 4)
-    {
-        std::array<char, 4> first; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
-        std::array<char, 4> last; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
-        std::memcpy(first.data(), src, 4);
-        std::memcpy(last.data(), src + (length - 4), 4);
-        std::memcpy(dst, first.data(), 4);
-        std::memcpy(dst + (length - 4), last.data(), 4);
-    }
-    else if (length != 0)
-    {
-        // 1 to 3: the first, the middle, and the last character
-        const CharType a = src[0];
-        const CharType b = src[length >> 1];
-        const CharType c = src[length - 1];
-        dst[0] = a;
-        dst[length >> 1] = b;
-        dst[length - 1] = c;
-    }
-}
-
-/// @brief copy @a length characters, of a character type wider than a byte
-template<typename CharType>
-inline void copy_short(CharType* dst, const CharType* src, const std::size_t length, std::false_type /*is_byte*/) noexcept
-{
-    std::memcpy(dst, src, length * sizeof(CharType));
-}
-
-/// the number of characters an empty vector is grown to by output_vector_sink
-constexpr std::size_t min_vector_sink_capacity = 64;
-
 /// @brief non-virtual output sink writing into a std::vector
 ///
 /// This sink is not part of the virtual output_adapter_protocol hierarchy: it is
@@ -138,7 +78,7 @@ class output_vector_sink
 {
   public:
     explicit output_vector_sink(std::vector<CharType, AllocatorType>& vec) noexcept
-        : v(&vec), cursor(vec.data() + vec.size()), limit(cursor)
+        : v(&vec), position(vec.size())
     {}
 
     output_vector_sink(const output_vector_sink&) = delete;
@@ -146,7 +86,7 @@ class output_vector_sink
     output_vector_sink& operator=(output_vector_sink&&) = delete;
 
     output_vector_sink(output_vector_sink&& other) noexcept
-        : v(other.v), cursor(other.cursor), limit(other.limit)
+        : v(other.v), position(other.position)
     {
         other.v = nullptr;
     }
@@ -155,7 +95,7 @@ class output_vector_sink
     {
         if (v != nullptr)
         {
-            v->resize(position());
+            v->resize(position);
         }
     }
 
@@ -164,11 +104,11 @@ class output_vector_sink
     JSON_HEDLEY_ALWAYS_INLINE
     void write_character(CharType c)
     {
-        if (JSON_HEDLEY_UNLIKELY(cursor == limit))
+        if (JSON_HEDLEY_UNLIKELY(position == v->size()))
         {
             grow(1);
         }
-        *cursor++ = c;
+        (*v)[position++] = c;
     }
 
     // no JSON_HEDLEY_NON_NULL here: binary_writer legitimately passes a null
@@ -177,7 +117,7 @@ class output_vector_sink
     JSON_HEDLEY_ALWAYS_INLINE
     void write_characters(const CharType* s, std::size_t length)
     {
-        if (JSON_HEDLEY_UNLIKELY(space() < length))
+        if (JSON_HEDLEY_UNLIKELY(v->size() - position < length))
         {
             if (length >= max_reserve_size)
             {
@@ -186,15 +126,10 @@ class output_vector_sink
             }
             grow(length);
         }
-        if (length <= 32)
+        if (length != 0)
         {
-            copy_short(cursor, s, length, std::integral_constant<bool, sizeof(CharType) == 1>());
+            std::memcpy(v->data() + position, s, length * sizeof(CharType));
-            cursor += length;
+            position += length;
-        }
-        else
-        {
-            std::memcpy(cursor, s, length * sizeof(CharType));
-            cursor += length;
         }
     }
 
@@ -209,37 +144,21 @@ class output_vector_sink
     CharType* reserve(const std::size_t length)
     {
         JSON_ASSERT(length <= max_reserve_size);
-        if (JSON_HEDLEY_UNLIKELY(space() < length))
+        if (JSON_HEDLEY_UNLIKELY(v->size() - position < length))
         {
             grow(length);
         }
-        return cursor;
+        return v->data() + position;
     }
 
     /// keep the first @a length characters written to the space from reserve()
     JSON_HEDLEY_ALWAYS_INLINE
     void commit(const std::size_t length) noexcept
     {
-        cursor += length;
+        position += length;
     }
 
-    /// nothing to pass on: the characters are in the vector (see output_adapter_sink)
-    void flush() noexcept
-    {}
-
   private:
-    /// number of characters of *v written so far
-    std::size_t position() const noexcept
-    {
-        return static_cast<std::size_t>(cursor - v->data());
-    }
-
-    /// number of characters that fit the vector behind the write position
-    std::size_t space() const noexcept
-    {
-        return static_cast<std::size_t>(limit - cursor);
-    }
-
     /// make room for at least @a length more characters after the position;
     /// kept out of line so that the write functions stay small enough for
     /// GCC to inline them into the writer
@@ -247,15 +166,12 @@ class output_vector_sink
     void grow(const std::size_t length)
     {
         // use the capacity the vector already has, else at least double it;
-        // never less than min_vector_sink_capacity, so that a small value does not
+        // never less than 64 characters, so that a small value does not
         // reallocate for every few bytes
-        const std::size_t written = position();
+        const std::size_t needed = position + length;
-        const std::size_t needed = written + length;
+        v->resize((std::max)(std::size_t{64}, needed <= v->capacity()
-        v->resize((std::max)(min_vector_sink_capacity, needed <= v->capacity()
                              ? v->capacity()
                              : (std::max)(needed, v->capacity() * 2)));
-        cursor = v->data() + written;
-        limit = v->data() + v->size();
     }
 
     /// append @a length (at least max_reserve_size) characters that do not fit
@@ -265,24 +181,20 @@ class output_vector_sink
     JSON_HEDLEY_NEVER_INLINE
     void append(const CharType* s, const std::size_t length)
     {
-        const std::size_t written = position();
+        v->resize(position);
-        v->resize(written);
+        if (v->capacity() - position < length)
-        if (v->capacity() - written < length)
         {
             // grow geometrically, with room for the writes that follow, so
             // that the next grow() need not reallocate right away
-            v->reserve((std::max)(v->capacity() * 2, written + length + max_reserve_size));
+            v->reserve((std::max)(v->capacity() * 2, position + length + max_reserve_size));
         }
         v->insert(v->end(), s, s + length);
-        cursor = v->data() + v->size();
+        position = v->size();
-        limit = cursor;
     }
 
     std::vector<CharType, AllocatorType>* v;
-    /// the write position: in *v, at the number of characters written so far
+    /// number of characters of *v written so far
-    CharType* cursor;
+    std::size_t position;
-    /// the end of *v
-    CharType* limit;
 };
 
 /// output adapter for byte vectors
@@ -365,17 +277,9 @@ class output_string_adapter : public output_adapter_protocol<CharType>
 ///
 /// Wraps the polymorphic output_adapter_t so the same binary_writer template can
 /// also target arbitrary adapters (output streams, strings, user-provided
-/// adapters) via the `output_adapter`-based overloads.
+/// adapters) via the `output_adapter`-based overloads. Each write still goes
-///
+/// through one virtual call, exactly as before; only the concrete sinks above
-/// A write through the adapter is a virtual call, and for a stream a call with
+/// avoid it.
-/// a sentry on top, which costs more than encoding the few bytes of most values.
-/// The sink therefore collects what is written in a buffer and passes it on in
-/// one piece when it is full, a write is too large for it, or @ref flush is
-/// called. Everything written reaches the adapter in the same order and with
-/// the same bytes; the destructor passes on what is left, so that a write that
-/// throws leaves the adapter with exactly the bytes written before it. Only
-/// @ref flush can report an error of the adapter (the destructor must not
-/// throw), so it has to be called once the value is written.
 template<typename CharType>
 class output_adapter_sink
 {
@@ -386,121 +290,36 @@ class output_adapter_sink
         JSON_ASSERT(oa);
     }
 
-    output_adapter_sink(const output_adapter_sink&) = delete;
-    output_adapter_sink& operator=(const output_adapter_sink&) = delete;
-    output_adapter_sink& operator=(output_adapter_sink&&) = delete;
-
-    output_adapter_sink(output_adapter_sink&& other) noexcept
-        : oa(std::move(other.oa)), used(other.used)
-    {
-        std::memcpy(buffer.data(), other.buffer.data(), other.used * sizeof(CharType));
-        other.used = 0;
-    }
-
-    ~output_adapter_sink()
-    {
-        // a normal return has flushed already, so this is for a write that threw
-        if (used != 0)
-        {
-            JSON_TRY
-            {
-                flush();
-            }
-            JSON_CATCH(...)
-            {
-                // nothing can be done about an adapter that throws here
-            }
-        }
-    }
-
-    JSON_HEDLEY_ALWAYS_INLINE
     void write_character(CharType c)
     {
-        if (JSON_HEDLEY_UNLIKELY(used == buffer_size))
+        oa->write_character(c);
-        {
-            flush();
-        }
-        buffer[used++] = c;
     }
 
     // no JSON_HEDLEY_NON_NULL: forwards (null, 0) for empty payloads, exactly as
     // the type-erased path already did before this sink existed
-    JSON_HEDLEY_ALWAYS_INLINE
     void write_characters(const CharType* s, std::size_t length)
     {
-        if (JSON_HEDLEY_UNLIKELY(buffer_size - used < length))
+        oa->write_characters(s, length);
-        {
-            write_large(s, length);
-            return;
-        }
-        if (length <= 32)
-        {
-            copy_short(buffer.data() + used, s, length, std::integral_constant<bool, sizeof(CharType) == 1>());
-            used += length;
-        }
-        else
-        {
-            std::memcpy(buffer.data() + used, s, length * sizeof(CharType));
-            used += length;
-        }
     }
 
     /// space for writing up to @a length characters (see
     /// output_vector_sink::reserve)
-    JSON_HEDLEY_ALWAYS_INLINE
+    CharType* reserve(const std::size_t length) noexcept
-    CharType* reserve(const std::size_t length)
     {
         JSON_ASSERT(length <= max_reserve_size);
-        if (JSON_HEDLEY_UNLIKELY(buffer_size - used < length))
+        static_cast<void>(length);
-        {
+        return reserved.data();
-            flush();
-        }
-        return buffer.data() + used;
     }
 
-    /// keep the first @a length characters written to the space from reserve()
+    /// write the first @a length characters written to the space from reserve()
-    JSON_HEDLEY_ALWAYS_INLINE
+    void commit(const std::size_t length)
-    void commit(const std::size_t length) noexcept
     {
-        used += length;
+        oa->write_characters(reserved.data(), length);
-    }
-
-    /// pass everything written so far on to the adapter
-    void flush()
-    {
-        if (used != 0)
-        {
-            // reset first: the characters count as written even if the adapter throws
-            const std::size_t length = used;
-            used = 0;
-            oa->write_characters(buffer.data(), length);
-        }
     }
 
   private:
-    /// a write that does not fit the space left in the buffer
-    JSON_HEDLEY_NEVER_INLINE
-    void write_large(const CharType* s, const std::size_t length)
-    {
-        flush();
-        if (length >= buffer_size)
-        {
-            oa->write_characters(s, length);
-        }
-        else
-        {
-            std::memcpy(buffer.data(), s, length * sizeof(CharType));
-            used = length;
-        }
-    }
-
-    /// large enough for reserve() at any time
-    static constexpr std::size_t buffer_size = 4 * max_reserve_size;
-
     output_adapter_t<CharType> oa;
-    /// number of characters of @ref buffer not yet passed on
+    std::array<CharType, max_reserve_size> reserved{};
-    std::size_t used = 0;
-    std::array<CharType, buffer_size> buffer{};
 };
 
 /// @brief whether std::basic_string<CharType> has a non-deprecated std::char_traits

include/nlohmann/json.hpp

@@ -6321,7 +6321,7 @@ public:
             const error_handler_t error_handler = detail::binary_writer_default_error_handler())
     {
         std::vector<std::uint8_t> result;
-        result.reserve(detail::binary_initial_capacity(j));
+        result.reserve(detail::binary_reserve_hint(j));
         vector_writer(result, error_handler).write_cbor(j);
         return result;
     }
@@ -6331,9 +6331,7 @@ public:
     static void to_cbor(const basic_json& j, detail::output_adapter<std::uint8_t> o,
                         const error_handler_t error_handler = detail::binary_writer_default_error_handler())
     {
-        binary_writer<std::uint8_t> writer(o, error_handler);
+        binary_writer<std::uint8_t>(o, error_handler).write_cbor(j);
-        writer.write_cbor(j);
-        writer.flush();
     }
 
     /// @brief create a CBOR serialization of a given JSON value
@@ -6341,9 +6339,7 @@ public:
     static void to_cbor(const basic_json& j, detail::output_adapter<char> o,
                         const error_handler_t error_handler = detail::binary_writer_default_error_handler())
     {
-        binary_writer<char> writer(o, error_handler);
+        binary_writer<char>(o, error_handler).write_cbor(j);
-        writer.write_cbor(j);
-        writer.flush();
     }
 
     /// @brief create a MessagePack serialization of a given JSON value
@@ -6352,7 +6348,7 @@ public:
             const error_handler_t error_handler = error_handler_t::keep)
     {
         std::vector<std::uint8_t> result;
-        result.reserve(detail::binary_initial_capacity(j));
+        result.reserve(detail::binary_reserve_hint(j));
         vector_writer(result, error_handler).write_msgpack(j);
         return result;
     }
@@ -6362,9 +6358,7 @@ public:
     static void to_msgpack(const basic_json& j, detail::output_adapter<std::uint8_t> o,
                            const error_handler_t error_handler = error_handler_t::keep)
     {
-        binary_writer<std::uint8_t> writer(o, error_handler);
+        binary_writer<std::uint8_t>(o, error_handler).write_msgpack(j);
-        writer.write_msgpack(j);
-        writer.flush();
     }
 
     /// @brief create a MessagePack serialization of a given JSON value
@@ -6372,9 +6366,7 @@ public:
     static void to_msgpack(const basic_json& j, detail::output_adapter<char> o,
                            const error_handler_t error_handler = error_handler_t::keep)
     {
-        binary_writer<char> writer(o, error_handler);
+        binary_writer<char>(o, error_handler).write_msgpack(j);
-        writer.write_msgpack(j);
-        writer.flush();
     }
 
     /// @brief create a UBJSON serialization of a given JSON value
@@ -6385,7 +6377,7 @@ public:
             const error_handler_t error_handler = detail::binary_writer_default_error_handler())
     {
         std::vector<std::uint8_t> result;
-        result.reserve(detail::binary_initial_capacity(j));
+        result.reserve(detail::binary_reserve_hint(j));
         vector_writer(result, error_handler).write_ubjson(j, use_size, use_type);
         return result;
     }
@@ -6396,9 +6388,7 @@ public:
                           const bool use_size = false, const bool use_type = false,
                           const error_handler_t error_handler = detail::binary_writer_default_error_handler())
     {
-        binary_writer<std::uint8_t> writer(o, error_handler);
+        binary_writer<std::uint8_t>(o, error_handler).write_ubjson(j, use_size, use_type);
-        writer.write_ubjson(j, use_size, use_type);
-        writer.flush();
     }
 
     /// @brief create a UBJSON serialization of a given JSON value
@@ -6407,9 +6397,7 @@ public:
                           const bool use_size = false, const bool use_type = false,
                           const error_handler_t error_handler = detail::binary_writer_default_error_handler())
     {
-        binary_writer<char> writer(o, error_handler);
+        binary_writer<char>(o, error_handler).write_ubjson(j, use_size, use_type);
-        writer.write_ubjson(j, use_size, use_type);
-        writer.flush();
     }
 
     /// @brief create a BJData serialization of a given JSON value
@@ -6421,7 +6409,7 @@ public:
             const error_handler_t error_handler = detail::binary_writer_default_error_handler())
     {
         std::vector<std::uint8_t> result;
-        result.reserve(detail::binary_initial_capacity(j));
+        result.reserve(detail::binary_reserve_hint(j));
         vector_writer(result, error_handler).write_ubjson(j, use_size, use_type, true, true, version);
         return result;
     }
@@ -6433,9 +6421,7 @@ public:
                           const bjdata_version_t version = bjdata_version_t::draft2,
                           const error_handler_t error_handler = detail::binary_writer_default_error_handler())
     {
-        binary_writer<std::uint8_t> writer(o, error_handler);
+        binary_writer<std::uint8_t>(o, error_handler).write_ubjson(j, use_size, use_type, true, true, version);
-        writer.write_ubjson(j, use_size, use_type, true, true, version);
-        writer.flush();
     }
 
     /// @brief create a BJData serialization of a given JSON value
@@ -6445,9 +6431,7 @@ public:
                           const bjdata_version_t version = bjdata_version_t::draft2,
                           const error_handler_t error_handler = detail::binary_writer_default_error_handler())
     {
-        binary_writer<char> writer(o, error_handler);
+        binary_writer<char>(o, error_handler).write_ubjson(j, use_size, use_type, true, true, version);
-        writer.write_ubjson(j, use_size, use_type, true, true, version);
-        writer.flush();
     }
 
     /// @brief create a BSON serialization of a given JSON value
@@ -6456,7 +6440,7 @@ public:
             const error_handler_t error_handler = detail::binary_writer_default_error_handler())
     {
         std::vector<std::uint8_t> result;
-        result.reserve(detail::binary_initial_capacity(j));
+        result.reserve(detail::binary_reserve_hint(j));
         vector_writer(result, error_handler).write_bson(j);
         return result;
     }
@@ -6466,9 +6450,7 @@ public:
     static void to_bson(const basic_json& j, detail::output_adapter<std::uint8_t> o,
                         const error_handler_t error_handler = detail::binary_writer_default_error_handler())
     {
-        binary_writer<std::uint8_t> writer(o, error_handler);
+        binary_writer<std::uint8_t>(o, error_handler).write_bson(j);
-        writer.write_bson(j);
-        writer.flush();
     }
 
     /// @brief create a BSON serialization of a given JSON value
@@ -6476,9 +6458,7 @@ public:
     static void to_bson(const basic_json& j, detail::output_adapter<char> o,
                         const error_handler_t error_handler = detail::binary_writer_default_error_handler())
     {
-        binary_writer<char> writer(o, error_handler);
+        binary_writer<char>(o, error_handler).write_bson(j);
-        writer.write_bson(j);
-        writer.flush();
     }
 
     /// @brief create a BON8 serialization of a given JSON value
@@ -6486,7 +6466,7 @@ public:
     static std::vector<std::uint8_t> to_bon8(const basic_json& j)
     {
         std::vector<std::uint8_t> result;
-        result.reserve(detail::binary_initial_capacity(j));
+        result.reserve(detail::binary_reserve_hint(j));
         vector_writer(result).write_bon8(j);
         return result;
     }
@@ -6495,18 +6475,14 @@ public:
     /// @sa https://json.nlohmann.me/api/basic_json/to_bon8/
     static void to_bon8(const basic_json& j, detail::output_adapter<std::uint8_t> o)
     {
-        binary_writer<std::uint8_t> writer(o);
+        binary_writer<std::uint8_t>(o).write_bon8(j);
-        writer.write_bon8(j);
-        writer.flush();
     }
 
     /// @brief create a BON8 serialization of a given JSON value
     /// @sa https://json.nlohmann.me/api/basic_json/to_bon8/
     static void to_bon8(const basic_json& j, detail::output_adapter<char> o)
     {
-        binary_writer<char> writer(o);
+        binary_writer<char>(o).write_bon8(j);
-        writer.write_bon8(j);
-        writer.flush();
     }
 
     /// @brief create a JSON value from an input in CBOR format

tests/src/unit-binary_writer_sinks.cpp

@@ -492,275 +492,3 @@ TEST_CASE("binary_reserve_hint never over-reserves")
         CHECK(nlohmann::detail::binary_reserve_hint(json({{"a", 1}, {"b", 2}})) == 5);
     }
 }
-
-namespace
-{
-
-// numbers around every boundary of the integer encodings, and floats of each
-// kind (exact in float, needing double, special values)
-std::vector<json> boundary_numbers()
-{
-    std::vector<json> numbers;
-    for (int k = 0; k < 64; ++k)
-    {
-        const std::uint64_t p = std::uint64_t{1} << k;
-        for (const std::uint64_t d :
-                {
-                    p - 1, p, p + 1
-                })
-        {
-            numbers.emplace_back(d);
-            if (d <= static_cast<std::uint64_t>((std::numeric_limits<std::int64_t>::max)()))
-            {
-                numbers.emplace_back(static_cast<std::int64_t>(d));
-                numbers.emplace_back(-static_cast<std::int64_t>(d));
-                numbers.emplace_back(-static_cast<std::int64_t>(d) - 1);
-            }
-        }
-    }
-    numbers.emplace_back((std::numeric_limits<std::int64_t>::min)());
-    numbers.emplace_back((std::numeric_limits<std::uint64_t>::max)());
-    for (const double f :
-            {
-                0.0, -0.0, 1.0, -1.0, 0.5, 0.1, 3.25, 1e300, -1e-300, 3.4028234663852886e38, 1e39,
-                std::numeric_limits<double>::infinity(), -std::numeric_limits<double>::infinity(),
-                std::numeric_limits<double>::quiet_NaN()
-            })
-    {
-        numbers.emplace_back(f);
-    }
-    return numbers;
-}
-
-// the concatenation of the encodings of the elements of @a numbers[first, first + count)
-template<typename Single>
-std::vector<std::uint8_t> concat_singles(const std::vector<json>& numbers, const std::size_t first, const std::size_t count, Single single)
-{
-    std::vector<std::uint8_t> bytes;
-    for (std::size_t i = first; i < first + count; ++i)
-    {
-        const auto one = single(numbers[i]);
-        bytes.insert(bytes.end(), one.begin(), one.end());
-    }
-    return bytes;
-}
-
-} // namespace
-
-// Runs of numbers in arrays are encoded straight into space reserved from the
-// sink, by code that is separate from the encoding of a single value. Both have
-// to agree on every number: an array is its head and the encodings of its
-// elements, one after the other.
-TEST_CASE("runs of numbers in arrays are encoded as the numbers one by one")
-{
-    const std::vector<json> numbers = boundary_numbers();
-
-    // arrays of every length that a one-byte head covers, so that runs are as
-    // long as, and longer and shorter than, what fits one reservation
-    for (const std::size_t count :
-            {
-                1u, 2u, 3u, 5u, 14u, 15u, 23u
-            })
-    {
-        for (std::size_t first = 0; first + count <= numbers.size(); first += 7)
-        {
-            const json array(std::vector<json>(numbers.begin() + static_cast<std::ptrdiff_t>(first),
-                                               numbers.begin() + static_cast<std::ptrdiff_t>(first + count)));
-            CAPTURE(array.dump(-1, ' ', false, json::error_handler_t::replace))
-
-            std::vector<std::uint8_t> expected{static_cast<std::uint8_t>(0x80 + count)};
-            auto elements = concat_singles(numbers, first, count, [](const json & j)
-            {
-                return json::to_cbor(j);
-            });
-            expected.insert(expected.end(), elements.begin(), elements.end());
-            CHECK(json::to_cbor(array) == expected);
-
-            expected.assign(1, static_cast<std::uint8_t>(count <= 15 ? 0x90 + count : 0xDC));
-            if (count > 15)
-            {
-                expected.push_back(0);
-                expected.push_back(static_cast<std::uint8_t>(count));
-            }
-            elements = concat_singles(numbers, first, count, [](const json & j)
-            {
-                return json::to_msgpack(j);
-            });
-            expected.insert(expected.end(), elements.begin(), elements.end());
-            CHECK(json::to_msgpack(array) == expected);
-
-            for (const bool bjdata :
-                    {
-                        false, true
-                    })
-            {
-                expected.assign(1, static_cast<std::uint8_t>('['));
-                elements = concat_singles(numbers, first, count, [bjdata](const json & j)
-                {
-                    return bjdata ? json::to_bjdata(j) : json::to_ubjson(j);
-                });
-                expected.insert(expected.end(), elements.begin(), elements.end());
-                expected.push_back(static_cast<std::uint8_t>(']'));
-                CHECK((bjdata ? json::to_bjdata(array) : json::to_ubjson(array)) == expected);
-            }
-
-            // BON8 has no integers above the int64 range
-            bool representable = true;
-            for (std::size_t i = first; i < first + count; ++i)
-            {
-                representable = representable && bon8_representable(numbers[i]);
-            }
-            if (representable)
-            {
-                expected.assign(1, static_cast<std::uint8_t>(count <= 4 ? 0x80 + count : 0x85));
-                elements = concat_singles(numbers, first, count, [](const json & j)
-                {
-                    return json::to_bon8(j);
-                });
-                expected.insert(expected.end(), elements.begin(), elements.end());
-                if (count > 4)
-                {
-                    expected.push_back(0xFE);
-                }
-                CHECK(json::to_bon8(array) == expected);
-            }
-            else
-            {
-                CHECK_THROWS_AS(json::to_bon8(array), json::out_of_range&);
-            }
-        }
-    }
-}
-
-// An array that is written in more than one reservation (more numbers than fit
-// one), and arrays of an index with more digits, round trip for every format.
-TEST_CASE("large arrays and many digits of indices round trip")
-{
-    json array = json::array();
-    for (int i = 0; i < 12000; ++i)
-    {
-        switch (i % 4)
-        {
-            case 0:
-                array.push_back(i);
-                break;
-            case 1:
-                array.push_back(-i);
-                break;
-            case 2:
-                array.push_back(i * 0.25);
-                break;
-            default:
-                array.push_back(i % 8 == 3);
-                break;
-        }
-    }
-    json document = json::object();
-    document["numbers"] = array;
-    document["nested"] = json::array({array, "text", array});
-
-    CHECK(json::from_cbor(json::to_cbor(document)) == document);
-    CHECK(json::from_msgpack(json::to_msgpack(document)) == document);
-    CHECK(json::from_ubjson(json::to_ubjson(document)) == document);
-    CHECK(json::from_ubjson(json::to_ubjson(document, true, true)) == document);
-    CHECK(json::from_bjdata(json::to_bjdata(document)) == document);
-    CHECK(json::from_bson(json::to_bson(document)) == document);
-    CHECK(json::from_bon8(json::to_bon8(document)) == document);
-}
-
-// Strings and keys are written with their head in one reservation up to a
-// length; around that length, and with every kind of head, they must read back.
-TEST_CASE("strings of every head length round trip")
-{
-    json document = json::object();
-    json array = json::array();
-    for (const std::size_t length :
-            {
-                0u, 1u, 2u, 3u, 4u, 7u, 8u, 15u, 16u, 17u, 23u, 24u, 25u, 31u, 32u, 33u, 63u, 127u, 128u, 129u, 200u, 245u, 246u, 247u, 248u, 249u, 250u, 251u, 252u, 253u, 254u, 255u, 256u, 257u, 300u, 1000u, 65535u, 65536u, 70000u
-            })
-    {
-        const std::string text(length, 'x');
-        array.push_back(text);
-        document[std::string(length, 'k')] = text;
-    }
-    document["array"] = array;
-
-    CHECK(json::from_cbor(json::to_cbor(document)) == document);
-    CHECK(json::from_msgpack(json::to_msgpack(document)) == document);
-    CHECK(json::from_ubjson(json::to_ubjson(document)) == document);
-    CHECK(json::from_ubjson(json::to_ubjson(document, true, true)) == document);
-    CHECK(json::from_bjdata(json::to_bjdata(document)) == document);
-    CHECK(json::from_bson(json::to_bson(document)) == document);
-    CHECK(json::from_bon8(json::to_bon8(document)) == document);
-}
-
-// What a write that throws leaves behind in an output adapter is what was written
-// before it, whatever the adapter and however the adapter sink buffers.
-TEST_CASE("a write that throws leaves the same bytes in every kind of output")
-{
-    json array = json::array();
-    for (int i = 0; i < 700; ++i)
-    {
-        array.push_back(i * 1000);
-        array.push_back("text " + std::to_string(i));
-    }
-    array.push_back("bad \xFF byte");
-    json document = json::object();
-    document["first"] = array;
-    document["second"] = 1;
-
-    const auto strict = json::error_handler_t::strict;
-
-    SECTION("cbor")
-    {
-        std::vector<std::uint8_t> as_vector;
-        std::string as_string;
-        std::ostringstream as_stream;
-        CHECK_THROWS_AS(json::to_cbor(document, as_vector, strict), json::type_error&);
-        CHECK_THROWS_AS(json::to_cbor(document, as_string, strict), json::type_error&);
-        CHECK_THROWS_AS(json::to_cbor(document, as_stream, strict), json::type_error&);
-        CHECK(!as_vector.empty());
-        CHECK(std::string(as_vector.begin(), as_vector.end()) == as_string);
-        CHECK(as_stream.str() == as_string);
-    }
-
-    SECTION("msgpack")
-    {
-        std::vector<std::uint8_t> as_vector;
-        std::string as_string;
-        std::ostringstream as_stream;
-        CHECK_THROWS_AS(json::to_msgpack(document, as_vector, strict), json::type_error&);
-        CHECK_THROWS_AS(json::to_msgpack(document, as_string, strict), json::type_error&);
-        CHECK_THROWS_AS(json::to_msgpack(document, as_stream, strict), json::type_error&);
-        CHECK(!as_vector.empty());
-        CHECK(std::string(as_vector.begin(), as_vector.end()) == as_string);
-        CHECK(as_stream.str() == as_string);
-    }
-
-    SECTION("ubjson")
-    {
-        std::vector<std::uint8_t> as_vector;
-        std::string as_string;
-        std::ostringstream as_stream;
-        CHECK_THROWS_AS(json::to_ubjson(document, as_vector, false, false, strict), json::type_error&);
-        CHECK_THROWS_AS(json::to_ubjson(document, as_string, false, false, strict), json::type_error&);
-        CHECK_THROWS_AS(json::to_ubjson(document, as_stream, false, false, strict), json::type_error&);
-        CHECK(!as_vector.empty());
-        CHECK(std::string(as_vector.begin(), as_vector.end()) == as_string);
-        CHECK(as_stream.str() == as_string);
-    }
-
-    SECTION("bson")
-    {
-        // the size pass finds the string before anything is written
-        std::vector<std::uint8_t> as_vector;
-        std::string as_string;
-        std::ostringstream as_stream;
-        CHECK_THROWS_AS(json::to_bson(document, as_vector, strict), json::type_error&);
-        CHECK_THROWS_AS(json::to_bson(document, as_string, strict), json::type_error&);
-        CHECK_THROWS_AS(json::to_bson(document, as_stream, strict), json::type_error&);
-        CHECK(as_vector.empty());
-        CHECK(as_string.empty());
-        CHECK(as_stream.str().empty());
-    }
-}

tests/src/unit-custom-number-types.cpp

@@ -285,55 +285,6 @@ TEST_CASE("custom number types: integers beyond 64 bits")
         CHECK(wide_json::to_bjdata(wide_json::array({uint_big, uint_big}), true, true) == expected_bjdata_array);
     }
 
-    SECTION("integers in arrays and objects")
-    {
-        // runs of numbers and scalar object members are encoded by loops of
-        // their own for the number types up to 64 bits; a wider number type
-        // takes the generic path, which checks the range of every integer
-        const wide_json run = wide_json::array({make_int(1), make_int(-3), make_uint(7), wide_json(1.5), int_big, make_int(5)});
-        const wide_json run_negative = wide_json::array({make_int(1), make_int(-3), int_big_negative});
-        const wide_json run_unsigned = wide_json::array({make_uint(1), make_uint(7), uint_big});
-        const wide_json members = wide_json::object({{"a", make_int(1)}, {"b", wide_json(1.5)}, {"c", int_big}});
-
-        const std::vector<wide_json> failing = {run, run_negative, run_unsigned, members, wrap(run), wrap(members)};
-        for (const auto& value : failing)
-        {
-            CHECK_THROWS_AS(_ = wide_json::to_cbor(value), out_of_range&);
-            CHECK_THROWS_AS(_ = wide_json::to_msgpack(value), out_of_range&);
-            CHECK_THROWS_AS(_ = wide_json::to_bson(wrap(value)), out_of_range&);
-            CHECK_THROWS_AS(_ = wide_json::to_bon8(value), out_of_range&);
-        }
-
-        // a failing write leaves no more than the elements before the failing one
-        std::vector<std::uint8_t> out;
-        CHECK_THROWS_AS(wide_json::to_cbor(run, out), out_of_range&);
-        // (the head of the array, 1, -3, 7, and 1.5 as a single-precision float)
-        CHECK(out == std::vector<std::uint8_t>({0x86, 0x01, 0x22, 0x07, 0xFA, 0x3F, 0xC0, 0x00, 0x00}));
-        out.clear();
-        CHECK_THROWS_AS(wide_json::to_bon8(run, out), out_of_range&);
-        CHECK(!out.empty());
-
-        // the same values that fit are written exactly as with 64-bit number types
-        const wide_json fits = wide_json::array({make_int(1), make_int(-3), make_uint(7), wide_json(1.5), make_int(min_int64), make_int(max_int64), make_int(200), make_int(-70000)});
-        const nlohmann::json fits64 = nlohmann::json::array({1, -3, 7, 1.5, (std::numeric_limits<std::int64_t>::min)(), (std::numeric_limits<std::int64_t>::max)(), 200, -70000});
-        CHECK(wide_json::to_cbor(fits) == nlohmann::json::to_cbor(fits64));
-        CHECK(wide_json::to_msgpack(fits) == nlohmann::json::to_msgpack(fits64));
-        CHECK(wide_json::to_ubjson(fits) == nlohmann::json::to_ubjson(fits64));
-        CHECK(wide_json::to_ubjson(fits, true, true) == nlohmann::json::to_ubjson(fits64, true, true));
-        CHECK(wide_json::to_bjdata(fits) == nlohmann::json::to_bjdata(fits64));
-        CHECK(wide_json::to_bjdata(fits, true, true) == nlohmann::json::to_bjdata(fits64, true, true));
-        CHECK(wide_json::to_bon8(fits) == nlohmann::json::to_bon8(fits64));
-        CHECK(wide_json::to_bson(wrap(fits)) == nlohmann::json::to_bson(nlohmann::json::object({{"v", fits64}})));
-
-        const wide_json fit_members = wide_json::object({{"a", make_int(1)}, {"b", make_int(-300)}, {"c", make_uint(max_uint64)}, {"d", wide_json(2.5)}});
-        const nlohmann::json fit_members64 = nlohmann::json::object({{"a", 1}, {"b", -300}, {"c", (std::numeric_limits<std::uint64_t>::max)()}, {"d", 2.5}});
-        CHECK(wide_json::to_cbor(fit_members) == nlohmann::json::to_cbor(fit_members64));
-        CHECK(wide_json::to_msgpack(fit_members) == nlohmann::json::to_msgpack(fit_members64));
-        CHECK(wide_json::to_ubjson(fit_members) == nlohmann::json::to_ubjson(fit_members64));
-        CHECK(wide_json::to_bjdata(fit_members) == nlohmann::json::to_bjdata(fit_members64));
-        CHECK(wide_json::to_bson(fit_members) == nlohmann::json::to_bson(fit_members64));
-    }
-
     SECTION("BJData ND-array")
     {
         // an ND-array element beyond 64 bits does not fit any dtype, so the

tests/src/unit-stream-bulk-scan.cpp

@@ -48,14 +48,16 @@ namespace
 class chunked_streambuf : public std::streambuf
 {
   public:
-    chunked_streambuf(std::string s, std::size_t chunk_size)
+    // The first @a unbuffered characters are served without a get area, the
-        : m_data(std::move(s)), m_chunk_size(chunk_size)
+    // rest in get areas of @a chunk_size.
+    chunked_streambuf(std::string s, std::size_t chunk_size, std::size_t unbuffered = 0)
+        : m_data(std::move(s)), m_chunk_size(chunk_size), m_unbuffered(unbuffered)
     {}
 
   protected:
     int_type underflow() override
     {
-        if (m_chunk_size == 0)
+        if (m_chunk_size == 0 || m_pos < m_unbuffered)
         {
             return m_pos < m_data.size() ? traits_type::to_int_type(m_data[m_pos]) : traits_type::eof();
         }
@@ -77,7 +79,7 @@ class chunked_streambuf : public std::streambuf
 
     int_type uflow() override
     {
-        if (m_chunk_size == 0)
+        if (m_chunk_size == 0 || m_pos < m_unbuffered)
         {
             return m_pos < m_data.size() ? traits_type::to_int_type(m_data[m_pos++]) : traits_type::eof();
         }
@@ -88,6 +90,7 @@ class chunked_streambuf : public std::streambuf
     std::string m_data;
     std::size_t m_pos = 0;
     std::size_t m_chunk_size;
+    std::size_t m_unbuffered;
 };
 
 // how a test reads from the stream
@@ -101,9 +104,9 @@ enum class read_mode
 // Read @a input from a chunked_streambuf and describe everything observable:
 // the values or the exception, the stream state after each value, and the
 // characters left in the stream.
-std::string observe(const std::string& input, std::size_t chunk_size, read_mode mode)
+std::string observe(const std::string& input, std::size_t chunk_size, read_mode mode, std::size_t unbuffered = 0)
 {
-    chunked_streambuf buf(input, chunk_size);
+    chunked_streambuf buf(input, chunk_size, unbuffered);
     std::istream is(&buf);
     std::string result;
     for (int i = 0; i < 4; ++i)
@@ -212,6 +215,31 @@ TEST_CASE("parsing from a std::istream scans the get area in bulk")
         }
     }
 
+    SECTION("results do not depend on a get area that appears late")
+    {
+        // the first characters come without a get area, then the streambuf
+        // starts to use one: the token that is read at that point is complete
+        for (const auto& input : corpus())
+        {
+            const std::string expected = observe(input, 0, read_mode::extract);
+            for (const std::size_t unbuffered :
+                    {
+                        1u, 2u, 3u, 5u, 8u, 13u, 21u
+                    })
+            {
+                for (const std::size_t chunk_size :
+                        {
+                            1u, 2u, 3u, 7u, 64u
+                        })
+                {
+                    CAPTURE(input)
+                    CAPTURE(unbuffered)
+                    CAPTURE(chunk_size)
+                    CHECK(observe(input, chunk_size, read_mode::extract, unbuffered) == expected);
+                }
+            }
+        }
+    }
 #endif // !defined(JSON_NOEXCEPTION)
 
     SECTION("values are the same as when parsing from a string")