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>

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);
-        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));
+        if (JSON_HEDLEY_LIKELY(next != streambuf_access::get_end(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/json_pointer.hpp

@@ -15,7 +15,7 @@
 #include <cstddef> // size_t
 #include <cstdint> // uint64_t
 #include <cstdlib> // strtoull
-#include <cstring> // memchr, memcmp, memcpy
+#include <cstring> // memcmp, memcpy
 #ifndef JSON_NO_IO
     #include <iosfwd> // ostream
 #endif  // JSON_NO_IO
@@ -303,12 +303,6 @@ class json_pointer
         exceeds_size_type  ///< @a s converts to an integer that exceeds size_type
     };
 
-    /// whether a reference token is "-" (a plain comparison with a string literal is not always inlined)
-    static bool is_dash(const string_t& s) noexcept
-    {
-        return s.size() == 1 && s[0] == '-';
-    }
-
     /*!
     @param[in] s    reference token to be converted into an array index
     @param[out] idx the integer representation of @a s if @ref array_index_status::ok
@@ -334,7 +328,7 @@ class json_pointer
         // error condition (cf. RFC 6901, Sect. 4); this also covers single-
         // character tokens, so "/x" and "/xy" fail alike; "-" and the empty
         // token are left to the conversion below and are reported as unresolved
-        if (JSON_HEDLEY_UNLIKELY(!s.empty() && !is_dash(s) && !(s[0] >= '0' && s[0] <= '9')))
+        if (JSON_HEDLEY_UNLIKELY(!s.empty() && s != "-" && !(s[0] >= '0' && s[0] <= '9')))
         {
             return array_index_status::not_a_number;
         }
@@ -481,40 +475,9 @@ class json_pointer
         return pos == size;
     }
 
-    /// reserve room for @a n elements of an array type that has reserve()
-    template<typename ArrayType>
-    static auto reserve_elements(ArrayType& array, const std::size_t n, detail::priority_tag<1> /*unused*/)
-    -> decltype(array.reserve(n), void())
-    {
-        array.reserve(n);
-    }
-
-    template<typename ArrayType>
-    static void reserve_elements(ArrayType& /*array*/, const std::size_t /*n*/, detail::priority_tag<0> /*unused*/)
-    {}
-
     /// @brief object member access with a key that is only copied if it is inserted
-    ///
-    /// Objects that can find the position of a key and insert there
-    /// (std::map) search once, others look the key up and add it if it is missing.
     template<typename BasicJsonType>
-    static auto object_member_impl(BasicJsonType& object, const string_t& key, detail::priority_tag<1> /*unused*/)
+    static BasicJsonType& object_member(BasicJsonType& object, const string_t& key)
-    -> decltype(object.m_data.m_value.object->emplace_hint(object.m_data.m_value.object->lower_bound(key), key, nullptr), std::declval<BasicJsonType&>())
-    {
-        auto& members = *object.m_data.m_value.object;
-        auto it = members.lower_bound(key);
-        if (it != members.end() && !members.key_comp()(key, it->first))
-        {
-            return it->second;
-        }
-
-        const auto old_capacity = object.container_capacity();
-        it = members.emplace_hint(it, key, nullptr);
-        return object.set_parent_after_insert(it->second, old_capacity);
-    }
-
-    template<typename BasicJsonType>
-    static BasicJsonType& object_member_impl(BasicJsonType& object, const string_t& key, detail::priority_tag<0> /*unused*/)
     {
         auto& members = *object.m_data.m_value.object;
         const auto it = members.find(key);
@@ -525,12 +488,6 @@ class json_pointer
         return object.operator[](key);
     }
 
-    template<typename BasicJsonType>
-    static BasicJsonType& object_member(BasicJsonType& object, const string_t& key)
-    {
-        return object_member_impl(object, key, detail::priority_tag<1> {});
-    }
-
   JSON_PRIVATE_UNLESS_TESTED:
     json_pointer top() const
     {
@@ -763,103 +720,48 @@ class json_pointer
         }
     }
 
-    /*!
-    @brief the values along the pointer last resolved by @ref resolve_plain
-
-    A patch from @ref basic_json::diff lists its operations in document order,
-    so consecutive pointers share most of their reference tokens; the values
-    along the previous pointer are kept to resume from the common prefix.
-    `steps[k]` is the value after the first `k` reference tokens together with
-    the length of the prefix of `*path` that holds them. A value stays valid as
-    long as no operation changes its container: callers keep only values up to
-    the parent of the pointer they modify, or call `reset()`.
-    */
-    template<typename BasicJsonType>
-    struct plain_steps
-    {
-        const string_t* path = nullptr;
-        std::vector<std::pair<std::size_t, BasicJsonType*>> steps{};
-
-        void reset() noexcept
-        {
-            path = nullptr;
-            steps.clear();
-        }
-    };
-
     /*!
     @brief resolve a plain JSON pointer without building its reference tokens
 
-    @param[in] root    the value the pointer starts at
+    @param[in] ptr     the value the pointer starts at
     @param[in] path    a JSON pointer string
     @param[in] length  the number of leading bytes of @a path to resolve; 0 or
                        the position of a slash
     @param[in,out] token  a string to hold the reference tokens, to reuse its storage
-    @param[in,out] cache  the values along the previously resolved pointer;
-                          @a path must outlive the next call
 
     @return the pointed to value, or `nullptr` if the pointer does not denote
-            an existing value, or does so in a way that is not plain: an array
+            an existing value, or does so in a way that is not plain: a
-            index that is malformed or out of range, or a "-", or a reference
+            reference token with an escape, an array index that is malformed or
-            token with an escape. No exception is
+            out of range, or a "-". No exception is thrown for these; callers
-            thrown for these; callers use @ref json_pointer instead, which
+            use @ref json_pointer instead, which handles them.
-            handles them.
     */
     template<typename BasicJsonType>
-    static BasicJsonType* resolve_plain(BasicJsonType* root, const string_t& path, const std::size_t length, string_t& token, plain_steps<BasicJsonType>& cache)
+    static BasicJsonType* resolve_plain(BasicJsonType* ptr, const string_t& path, const std::size_t length, string_t& token)
     {
-        auto& steps = cache.steps;
+        for (std::size_t pos = 0; pos < length;)
-
-        // resume from the deepest step that is also a prefix of this path
-        std::size_t depth = 1;
-        if (cache.path != nullptr && !steps.empty() && steps[0].second == root)
-        {
-            const string_t& previous = *cache.path;
-            for (depth = steps.size(); depth > 1; --depth)
-            {
-                // a step ends at a token boundary of the previous path
-                const std::size_t prefix = steps[depth - 1].first;
-                if (prefix <= length && (prefix == length || path[prefix] == '/') && std::memcmp(path.data(), previous.data(), prefix) == 0)
-                {
-                    break;
-                }
-            }
-            steps.resize(depth);
-        }
-        else
-        {
-            steps.assign(1, std::make_pair(std::size_t{0}, root));
-        }
-        cache.path = &path;
-
-        BasicJsonType* ptr = steps[depth - 1].second;
-        for (std::size_t pos = steps[depth - 1].first; pos < length;)
         {
             if (JSON_HEDLEY_UNLIKELY(path[pos] != '/'))
             {
                 return nullptr;
             }
 
-            // the reference token between the slash at pos and the next one,
+            // the reference token between the slash at pos and the next one
-            // which must not have an escape
+            std::size_t end = path.find_first_of('/', pos + 1);
-            const char* const begin = path.data() + pos + 1;
+            if (end == string_t::npos || end > length)
-            const char* const limit = path.data() + length;
-            const char* end = begin;
-            while (end < limit && *end != '/')
             {
-                if (JSON_HEDLEY_UNLIKELY(*end == '~'))
+                end = length;
+            }
+            token.clear();
+            token.append(path.data() + pos + 1, end - pos - 1);
+            if (JSON_HEDLEY_UNLIKELY(token.find_first_of('~') != string_t::npos))
             {
                 return nullptr;
             }
-                ++end;
-            }
 
             switch (ptr->type())
             {
                 case detail::value_t::object:
                 {
-                    token.clear();
-                    token.append(begin, static_cast<std::size_t>(end - begin));
                     const auto it = ptr->m_data.m_value.object->find(token);
                     if (JSON_HEDLEY_UNLIKELY(it == ptr->m_data.m_value.object->end()))
                     {
@@ -871,24 +773,8 @@ class json_pointer
 
                 case detail::value_t::array:
                 {
-                    // an index of up to 18 digits without a leading zero fits into size_type
+                    typename BasicJsonType::size_type idx{};
-                    // (9 digits for a 32-bit size_type); everything else is left to json_pointer
+                    if (JSON_HEDLEY_UNLIKELY(parse_array_index<BasicJsonType>(token, idx) != array_index_status::ok || idx >= ptr->m_data.m_value.array->size()))
-                    constexpr std::size_t max_digits = sizeof(typename BasicJsonType::size_type) >= 8 ? 18 : 9;
-                    const std::size_t digits = static_cast<std::size_t>(end - begin);
-                    if (JSON_HEDLEY_UNLIKELY(digits == 0 || digits > max_digits || (digits > 1 && *begin == '0')))
-                    {
-                        return nullptr;
-                    }
-                    typename BasicJsonType::size_type idx = 0;
-                    for (const char* c = begin; c != end; ++c)
-                    {
-                        if (JSON_HEDLEY_UNLIKELY(*c < '0' || *c > '9'))
-                        {
-                            return nullptr;
-                        }
-                        idx = static_cast<typename BasicJsonType::size_type>((idx * 10) + static_cast<typename BasicJsonType::size_type>(*c - '0'));
-                    }
-                    if (JSON_HEDLEY_UNLIKELY(idx >= ptr->m_data.m_value.array->size()))
                     {
                         return nullptr;
                     }
@@ -907,8 +793,7 @@ class json_pointer
                 default:
                     return nullptr;
             }
-            pos = static_cast<std::size_t>(end - path.data());
+            pos = end;
-            steps.emplace_back(pos, ptr);
         }
 
         return ptr;
@@ -1022,7 +907,7 @@ class json_pointer
 
                 case detail::value_t::array:
                 {
-                    if (JSON_HEDLEY_UNLIKELY(is_dash(reference_token)))
+                    if (JSON_HEDLEY_UNLIKELY(reference_token == "-"))
                     {
                         // "-" always fails the range check
                         JSON_THROW(detail::out_of_range::create(detail::exception_id::pointer_past_the_end_index, detail::concat(
@@ -1093,7 +978,7 @@ class json_pointer
 
                 case detail::value_t::array:
                 {
-                    if (JSON_HEDLEY_UNLIKELY(is_dash(reference_token)))
+                    if (JSON_HEDLEY_UNLIKELY(reference_token == "-"))
                     {
                         // "-" cannot be used for const access
                         JSON_THROW(detail::out_of_range::create(detail::exception_id::pointer_past_the_end_index, detail::concat("array index '-' (", std::to_string(ptr->m_data.m_value.array->size()), ") is out of range"), ptr));
@@ -1155,7 +1040,7 @@ class json_pointer
 
                 case detail::value_t::array:
                 {
-                    if (JSON_HEDLEY_UNLIKELY(is_dash(reference_token)))
+                    if (JSON_HEDLEY_UNLIKELY(reference_token == "-"))
                     {
                         // "-" always fails the range check
                         return nullptr;
@@ -1232,7 +1117,7 @@ class json_pointer
 
                 case detail::value_t::array:
                 {
-                    if (JSON_HEDLEY_UNLIKELY(is_dash(reference_token)))
+                    if (JSON_HEDLEY_UNLIKELY(reference_token == "-"))
                     {
                         // "-" always fails the range check
                         return false;
@@ -1391,52 +1276,6 @@ class json_pointer
         obj[key] = std::forward<ValueType>(v);
     }
 
-    /// the number of entries that flattening @a value adds: its primitive
-    /// values and empty containers
-    template<typename BasicJsonType>
-    static std::size_t count_flattened(const BasicJsonType& value)
-    {
-        std::size_t count = 0;
-        std::vector<const BasicJsonType*> pending(1, &value);
-        while (!pending.empty())
-        {
-            const BasicJsonType* const v = pending.back();
-            pending.pop_back();
-            if (v->is_array() && !v->m_data.m_value.array->empty())
-            {
-                for (const auto& element : *v->m_data.m_value.array)
-                {
-                    pending.push_back(&element);
-                }
-            }
-            else if (v->is_object() && !v->m_data.m_value.object->empty())
-            {
-                for (const auto& member : *v->m_data.m_value.object)
-                {
-                    pending.push_back(&member.second);
-                }
-            }
-            else
-            {
-                ++count;
-            }
-        }
-        return count;
-    }
-
-    // Reserve the storage for @a value of objects that have a reserve(), so
-    // that it does not have to be moved while it grows
-    template<typename ObjectType, typename BasicJsonType>
-    static auto reserve_flattened(ObjectType& obj, const BasicJsonType& value, detail::priority_tag<1> /*unused*/)
-    -> decltype(obj.reserve(std::size_t {}), void())
-    {
-        obj.reserve(count_flattened(value));
-    }
-
-    template<typename ObjectType, typename BasicJsonType>
-    static void reserve_flattened(ObjectType& /*obj*/, const BasicJsonType& /*value*/, detail::priority_tag<0> /*unused*/)
-    {}
-
     /// append the decimal representation of @a i to @a out
     static void append_index(string_t& out, std::size_t i)
     {
@@ -1546,7 +1385,6 @@ class json_pointer
             }
         };
 
-        reserve_flattened(object, value, detail::priority_tag<1> {});
         enter(value);
         while (!stack.empty())
         {
@@ -1554,9 +1392,8 @@ class json_pointer
             // frame, which would invalidate a reference to it
             const BasicJsonType* const container = stack.back().container;
 
-            // the path of the previous child is replaced by the path of the
+            // drop the path of the previous child
-            // next one; for an array element in one resize
+            path.resize(stack.back().path_length);
-            const std::size_t path_length = stack.back().path_length;
 
             if (container->is_array())
             {
@@ -1570,20 +1407,8 @@ class json_pointer
 
                 // iterate array and use index as a reference string
                 ++stack.back().index;
-                std::array<char, 24> digits{};
+                path.push_back('/');
-                std::size_t pos = digits.size();
+                append_index(path, i);
-                std::size_t rest = i;
-                do
-                {
-                    digits[--pos] = static_cast<char>('0' + rest % 10);
-                    rest /= 10;
-                }
-                while (rest != 0);
-                const std::size_t count = digits.size() - pos;
-                path.resize(path_length + 1 + count);
-                char* const out = &path[path_length];
-                out[0] = '/';
-                std::memcpy(out + 1, digits.data() + pos, count);
                 enter(array[i]);
             }
             else
@@ -1597,7 +1422,6 @@ class json_pointer
 
                 // iterate object and use keys as reference string
                 ++stack.back().member;
-                path.resize(path_length);
                 path.push_back('/');
                 detail::escape_into(path, it->first);
                 enter(it->second);
@@ -1693,28 +1517,8 @@ class json_pointer
                 {
                     end = key.size();
                 }
-                const std::size_t token_size = end - pos - 1;
-
-                // a token that is a plain index of up to 9 digits, which is
-                // the case for almost all array elements, is not copied
-                std::size_t index = 0;
-                bool plain_index = current->type() == detail::value_t::array && token_size != 0 && token_size <= 9 && (token_size == 1 || data[pos + 1] != '0');
-                for (std::size_t k = pos + 1; plain_index && k < end; ++k)
-                {
-                    plain_index = data[k] >= '0' && data[k] <= '9';
-                    index = (index * 10) + static_cast<std::size_t>(data[k] - '0');
-                }
-                if (plain_index)
-                {
-                    current = &current->operator[](static_cast<typename BasicJsonType::size_type>(index));
-                    values.push_back(current);
-                    ends.push_back(end);
-                    pos = end;
-                    continue;
-                }
-
                 token.clear();
-                token.append(data + pos + 1, token_size);
+                token.append(data + pos + 1, end - pos - 1);
                 if (token.find_first_of('~') != string_t::npos)
                 {
                     detail::unescape(token);
@@ -1724,13 +1528,10 @@ class json_pointer
                 {
                     case detail::value_t::null:
                     {
-                        // a first child 0 makes the value an array without a look-up
+                        if (arrays.contains(data, pos))
-                        if ((token_size == 1 && data[pos + 1] == '0') || arrays.contains(data, pos))
                         {
                             // some reference token below this position is 0, so the
                             // value is an array
-                            *current = BasicJsonType(detail::value_t::array);
-                            reserve_elements(*current->m_data.m_value.array, 2, detail::priority_tag<1> {});
                             current = &current->operator[](array_index<BasicJsonType>(token));
                         }
                         else

include/nlohmann/json.hpp

@@ -6878,72 +6878,6 @@ public:
     /// @name JSON Patch functions
     /// @{
 
-  private:
-    /// the members of an operation of a JSON patch that are of interest
-    struct patch_members
-    {
-        basic_json* op = nullptr;
-        basic_json* path = nullptr;
-        basic_json* value = nullptr;
-        basic_json* from = nullptr;
-    };
-
-    /// @brief find the members "op", "path", "value", and "from" of the object @a val in one pass
-    static patch_members find_patch_members(const basic_json& val, std::true_type /*key_type is string_t*/)
-    {
-        patch_members members;
-        for (auto& member : *val.m_data.m_value.object)
-        {
-            const string_t& key = member.first;
-            switch (key.size())
-            {
-                case 2:
-                    if (key == "op")
-                    {
-                        members.op = &member.second;
-                    }
-                    break;
-                case 4:
-                    if (key == "path")
-                    {
-                        members.path = &member.second;
-                    }
-                    else if (key == "from")
-                    {
-                        members.from = &member.second;
-                    }
-                    break;
-                case 5:
-                    if (key == "value")
-                    {
-                        members.value = &member.second;
-                    }
-                    break;
-                default:
-                    break;
-            }
-        }
-        return members;
-    }
-
-    /// @brief find the members by lookup for key types other than string_t
-    static patch_members find_patch_members(const basic_json& val, std::false_type /*key_type is not string_t*/)
-    {
-        const auto find_member = [&val](const char* name) -> basic_json *
-        {
-            const auto it = val.m_data.m_value.object->find(string_t(name));
-            return it != val.m_data.m_value.object->end() ? &it->second : nullptr;
-        };
-
-        patch_members members;
-        members.op = find_member("op");
-        members.path = find_member("path");
-        members.value = find_member("value");
-        members.from = find_member("from");
-        return members;
-    }
-
-  public:
     /// @brief applies a JSON patch in-place without copying the object
     /// @sa https://json.nlohmann.me/api/basic_json/patch/
     void patch_inplace(const basic_json& json_patch)
@@ -7117,18 +7051,18 @@ public:
         // a diff creates them: apply the operation and return true; return
         // false, with nothing changed, for all others
         string_t token;
-        typename json_pointer::template plain_steps<basic_json> steps;
+        const string_t value_key = "value";
-        const auto try_plain = [&result, &token, &steps](patch_operations operation, const string_t& path, const patch_members & members, const basic_json & val)
+        const auto try_plain = [&result, &token, &value_key](patch_operations operation, const string_t& path, const basic_json & val)
         {
-            if (path.empty())
+            if (path.empty() || path.find_first_of('~') != string_t::npos)
             {
                 return false;
             }
 
             // a missing "value" is reported below
-            const basic_json* const value_ptr = members.value;
+            const auto value_it = val.m_data.m_value.object->find(value_key);
-            const basic_json& value = value_ptr != nullptr ? *value_ptr : val;
+            const basic_json& value = value_it != val.m_data.m_value.object->end() ? value_it->second : val;
-            if (operation != patch_operations::remove && value_ptr == nullptr)
+            if (operation != patch_operations::remove && value_it == val.m_data.m_value.object->end())
             {
                 return false;
             }
@@ -7137,7 +7071,7 @@ public:
             {
                 case patch_operations::replace:
                 {
-                    basic_json* const target = json_pointer::resolve_plain(&result, path, path.size(), token, steps);
+                    basic_json* const target = json_pointer::resolve_plain(&result, path, path.size(), token);
                     if (target == nullptr)
                     {
                         return false;
@@ -7148,7 +7082,7 @@ public:
 
                 case patch_operations::test:
                 {
-                    const basic_json* const target = json_pointer::resolve_plain(&result, path, path.size(), token, steps);
+                    const basic_json* const target = json_pointer::resolve_plain(&result, path, path.size(), token);
                     // a failing test is reported below
                     return target != nullptr && *target == value;
                 }
@@ -7168,17 +7102,13 @@ public:
                     }
                     --slash;
 
-                    basic_json* const parent = json_pointer::resolve_plain(&result, path, slash, token, steps);
+                    basic_json* const parent = json_pointer::resolve_plain(&result, path, slash, token);
                     if (parent == nullptr)
                     {
                         return false;
                     }
                     token.clear();
                     token.append(path.data() + slash + 1, path.size() - slash - 1);
-                    if (token.find_first_of('~') != string_t::npos)
-                    {
-                        return false;
-                    }
 
                     if (operation == patch_operations::add)
                     {
@@ -7234,32 +7164,31 @@ public:
             }
         };
 
-        // the name of the first member to check
-        const string_t op_member = "op";
-
         // iterate and apply the operations
         for (const auto& val : json_patch)
         {
             // wrapper to get a value for an operation
-            const auto get_value = [&val](basic_json * found,
+            const auto get_value = [&val](const string_t& op,
-                                          const string_t& op,
+                                          const string_t& member,
-                                          const char* member,
                                           bool string_type) -> basic_json &
             {
+                // find value
+                auto it = val.m_data.m_value.object->find(member);
+
                 // check if the desired value is present
-                if (JSON_HEDLEY_UNLIKELY(found == nullptr))
+                if (JSON_HEDLEY_UNLIKELY(it == val.m_data.m_value.object->end()))
                 {
-                    detail::throw_patch_missing_member(op, string_t(member), false, val);
+                    detail::throw_patch_missing_member(op, member, false, val);
                 }
 
                 // check if the result is of type string
-                if (JSON_HEDLEY_UNLIKELY(string_type && !found->is_string()))
+                if (JSON_HEDLEY_UNLIKELY(string_type && !it->second.is_string()))
                 {
-                    detail::throw_patch_missing_member(op, string_t(member), true, val);
+                    detail::throw_patch_missing_member(op, member, true, val);
                 }
 
                 // no error: return value
-                return *found;
+                return it->second;
             };
 
             // type check: every element of the array must be an object
@@ -7268,30 +7197,26 @@ public:
                 detail::throw_patch_not_an_array(val);
             }
 
-            const patch_members members = find_patch_members(val, std::is_same<typename object_t::key_type, string_t> {});
-
             // collect mandatory members
-            const string_t& op = *get_value(members.op, op_member, "op", true).m_data.m_value.string;
+            const string_t& op = *get_value("op", "op", true).m_data.m_value.string;
-            const string_t& path = *get_value(members.path, op, "path", true).m_data.m_value.string;
+            const string_t& path = *get_value(op, "path", true).m_data.m_value.string;
             const patch_operations operation = get_op(op);
 
             // the usual operations on a plain pointer are applied without
             // building the pointer's reference tokens; anything else (and
             // every error) is handled below
-            if (try_plain(operation, path, members, val))
+            if (try_plain(operation, path, val))
             {
                 continue;
             }
 
-            // the general operations may change any container
-            steps.reset();
             json_pointer ptr(path);
 
             switch (operation)
             {
                 case patch_operations::add:
                 {
-                    operation_add(ptr, get_value(members.value, "add", "value", false));
+                    operation_add(ptr, get_value("add", "value", false));
                     break;
                 }
 
@@ -7304,13 +7229,13 @@ public:
                 case patch_operations::replace:
                 {
                     // the "path" location must exist - use at()
-                    result.at(ptr) = get_value(members.value, "replace", "value", false);
+                    result.at(ptr) = get_value("replace", "value", false);
                     break;
                 }
 
                 case patch_operations::move:
                 {
-                    const string_t& from_path = *get_value(members.from, "move", "from", true).m_data.m_value.string;
+                    const string_t& from_path = *get_value("move", "from", true).m_data.m_value.string;
                     json_pointer from_ptr(from_path);
 
                     if (JSON_HEDLEY_UNLIKELY(is_proper_prefix(from_ptr, ptr)))
@@ -7333,7 +7258,7 @@ public:
 
                 case patch_operations::copy:
                 {
-                    const string_t& from_path = *get_value(members.from, "copy", "from", true).m_data.m_value.string;
+                    const string_t& from_path = *get_value("copy", "from", true).m_data.m_value.string;
                     const json_pointer from_ptr(from_path);
 
                     // The copy is functionally identical to an "add"
@@ -7351,7 +7276,7 @@ public:
                     {
                         // check if "value" matches the one at "path"
                         // the "path" location must exist - use at()
-                        success = (result.at(ptr) == get_value(members.value, "test", "value", false));
+                        success = (result.at(ptr) == get_value("test", "value", false));
                     }
                     JSON_INTERNAL_CATCH (out_of_range&)
                     {
@@ -7443,18 +7368,13 @@ public:
     /// @brief append an operation @a op for @a path to @a result, with @a value if it is not null
     static void diff_operation(basic_json& result, const char* op, const string_t& path, const basic_json* value)
     {
-        // the keys are distinct and in the order of std::map; the members are
-        // added without looking them up
         basic_json entry(value_t::object);
-        auto& members = *entry.m_data.m_value.object;
+        entry["op"] = op;
-        typename object_t::iterator hint = members.end();
+        entry["path"] = path;
-        json_pointer::add_flattened(members, hint, string_t("op"), string_t(op), detail::priority_tag<2> {});
-        json_pointer::add_flattened(members, hint, string_t("path"), path, detail::priority_tag<2> {});
         if (value != nullptr)
         {
-            json_pointer::add_flattened(members, hint, string_t("value"), *value, detail::priority_tag<2> {});
+            entry["value"] = *value;
         }
-        entry.set_parents();
         result.push_back(std::move(entry));
     }
 
@@ -7476,50 +7396,6 @@ public:
         diff_operation(result, "add", path, &value);
     }
 
-    /// @brief the values in the target of the members of a source object, for the
-    ///        objects of up to 16 members without allocating
-    ///
-    /// reserve() must be called with the number of values that are added.
-    class diff_target_values
-    {
-      public:
-        diff_target_values() = default;
-        diff_target_values(const diff_target_values&) = delete;
-        diff_target_values& operator=(const diff_target_values&) = delete;
-        ~diff_target_values() = default;
-
-        void reserve(const std::size_t n)
-        {
-            if (n > inline_size)
-            {
-                large.resize(n);
-                items = large.data();
-            }
-        }
-
-        void push_back(const basic_json* value)
-        {
-            items[count++] = value;
-        }
-
-        std::size_t size() const noexcept
-        {
-            return count;
-        }
-
-        const basic_json* operator[](const std::size_t i) const noexcept
-        {
-            return items[i];
-        }
-
-      private:
-        static constexpr std::size_t inline_size = 16;
-        std::size_t count = 0;
-        const basic_json** items = inline_items;
-        std::vector<const basic_json*> large{}; // NOLINT(readability-redundant-member-init)
-        const basic_json* inline_items[inline_size]; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init)
-    };
-
     /// @brief append "/" and the decimal representation of @a index to @a path
     static void diff_append_index(string_t& path, std::size_t index)
     {
@@ -7600,9 +7476,8 @@ public:
     operations that remove every member of @a source and add every member of
     @a target to @a result, and returns false.
     */
-    template<typename TargetValues>
     static bool diff_object_keys(basic_json& result, const basic_json& source, const basic_json& target,
-                                 const string_t& path, TargetValues& target_values,
+                                 const string_t& path, std::vector<const basic_json*>& target_values,
                                  std::vector<const_iterator>& added)
     {
         // first pass: one lookup per source key
@@ -7816,7 +7691,7 @@ public:
 
             case value_t::object:
             {
-                diff_target_values target_values;
+                std::vector<const basic_json*> target_values;
                 std::vector<const_iterator> added;
                 if (diff_object_keys(result, source, target, path, target_values, added))
                 {

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")