Copy the tokens of json_pointer::to_string() with std::copy

clang-tidy (bugprone-not-null-terminated-result) took the memcpy into
the result string for a C string missing its terminator. std::copy is
the same memmove; to_string() instructions are unchanged (Apple clang).

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

include/nlohmann/detail/input/input_adapters.hpp

@@ -8,18 +8,17 @@
 
 #pragma once
 
-#include <algorithm> // count, find, max, min
+#include <algorithm> // count, find, 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> // declval, move, pair
+#include <utility> // pair, declval
 #include <vector> // vector
 
 #ifndef JSON_NO_IO
@@ -73,81 +72,6 @@ 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.
 */
@@ -285,7 +209,6 @@ 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;
@@ -372,20 +295,37 @@ class input_stream_adapter
     std::char_traits<char>::int_type get_character()
     {
 #if !JSON_DISABLE_STREAM_BULK_SCAN
-        // the character is in the get area: step over it, as sbumpc() does
+        // sbumpc() refills the get area if it is exhausted
-        const char* const next = streambuf_access::get_ptr(sb);
+        const bool refill = streambuf_access::get_ptr(sb) == streambuf_access::get_end(sb);
-        if (JSON_HEDLEY_LIKELY(next != streambuf_access::get_end(sb)))
+        if (JSON_HEDLEY_UNLIKELY(refill))
         {
-            current_in_get_area = true;
+            save_token_segment();
-            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 get_character_slow();
+
+        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
 
@@ -394,18 +334,6 @@ 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)))
@@ -493,7 +421,7 @@ class input_stream_adapter
     // last one if @a drop_last.
     void copy_token(std::vector<char>& out, bool drop_last) const
     {
-        token_carry.copy_to(out);
+        out = token_carry;
         if (token_segment != nullptr)
         {
             out.insert(out.end(), token_segment, current_end());
@@ -506,47 +434,6 @@ 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
@@ -570,11 +457,6 @@ 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
@@ -595,53 +477,16 @@ class input_stream_adapter
     {
         if (token_segment != nullptr)
         {
-            token_carry.append(token_segment, streambuf_access::get_end(sb));
+            token_carry.insert(token_carry.end(), 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;
@@ -680,16 +525,13 @@ class input_stream_adapter
 #endif
 #if !JSON_DISABLE_STREAM_BULK_SCAN
     /// the part of the current token that was in earlier get areas
-    token_carry_buffer token_carry{}; // NOLINT(readability-redundant-member-init)
+    std::vector<char> 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

@@ -8,7 +8,7 @@
 
 #pragma once
 
-#include <algorithm> // all_of
+#include <algorithm> // all_of, copy
 #include <array> // array
 #include <cctype> // isdigit
 #include <cerrno> // errno, ERANGE
@@ -82,12 +82,34 @@ class json_pointer
     {
         // one buffer: every token adds its escaped form (at least its length) and a slash
         std::size_t length = 0;
+        bool plain = true;
         for (const auto& reference_token : reference_tokens)
         {
             length += reference_token.size() + 1;
+            const char* const data = reference_token.data();
+            for (std::size_t i = 0, size = reference_token.size(); plain && i < size; ++i)
+            {
+                plain = data[i] != '~' && data[i] != '/';
+            }
         }
 
         string_t result;
+        if (JSON_HEDLEY_LIKELY(plain))
+        {
+            // nothing to escape: the tokens are copied into the string
+            result.resize(length);
+            if (length != 0)
+            {
+                char* out = &result[0];
+                for (const auto& reference_token : reference_tokens)
+                {
+                    *out++ = '/';
+                    out = std::copy(reference_token.data(), reference_token.data() + reference_token.size(), out);
+                }
+            }
+            return result;
+        }
+
         result.reserve(length);
         for (const auto& reference_token : reference_tokens)
         {
@@ -1198,33 +1220,32 @@ class json_pointer
         }
         result.reserve(token_count);
 
-        // extract the reference tokens:
+        // extract the reference tokens: every one runs from after a slash to
-        // - slash: position of the last read slash (or end of string)
+        // the next slash or the end of the string; a token without a '~' (the
-        // - start: position after the previous slash
+        // common case) is stored as it is, others are checked and unescaped
-        for (
+        const char* const data = reference_string.data();
-            // search for the first slash after the first character
+        const char* const end = data + size;
-            std::size_t slash = reference_string.find_first_of('/', 1),
+        for (const char* start = data + 1;; ++start)
-            // set the beginning of the first reference token
-            start = 1;
-            // we can stop if start == 0 (if slash == string_t::npos)
-            start != 0;
-            // set the beginning of the next reference token
-            // (will eventually be 0 if slash == string_t::npos)
-            start = (slash == string_t::npos) ? 0 : slash + 1,
-            // find next slash
-            slash = reference_string.find_first_of('/', start))
         {
-            // use the text between the beginning of the reference token
+            const char* slash = start;
-            // (start) and the last slash (slash).
+            bool escaped = false;
-            const auto count = (slash == string_t::npos ? reference_string.size() : slash) - start;
+            while (slash != end && *slash != '/')
-            auto reference_token = string_t(reference_string.data() + start, count);
+            {
+                escaped = escaped || *slash == '~';
+                ++slash;
+            }
 
-            // check reference tokens are properly escaped; a token without
+            const auto count = static_cast<std::size_t>(slash - start);
-            // a '~' (the common case) needs neither check nor unescaping
+            if (JSON_HEDLEY_LIKELY(!escaped))
-            std::size_t pos = reference_token.find_first_of('~');
-            if (pos != string_t::npos)
             {
-                for (; pos != string_t::npos; pos = reference_token.find_first_of('~', pos + 1))
+                result.emplace_back(start, count);
+            }
+            else
+            {
+                auto reference_token = string_t(start, count);
+
+                // check reference tokens are properly escaped
+                for (std::size_t pos = reference_token.find_first_of('~'); pos != string_t::npos; pos = reference_token.find_first_of('~', pos + 1))
                 {
                     JSON_ASSERT(reference_token[pos] == '~');
 
@@ -1238,10 +1259,14 @@ class json_pointer
                 }
 
                 detail::unescape(reference_token);
+                result.push_back(std::move(reference_token));
             }
 
-            // finally, store the reference token
+            if (slash == end)
-            result.push_back(std::move(reference_token));
+            {
+                break;
+            }
+            start = slash;
         }
 
         return result;

single_include/nlohmann/json.hpp

@@ -8468,18 +8468,17 @@ NLOHMANN_JSON_NAMESPACE_END
 
 
 
-#include <algorithm> // count, find, max, min
+#include <algorithm> // count, find, 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> // declval, move, pair
+#include <utility> // pair, declval
 #include <vector> // vector
 
 #ifndef JSON_NO_IO
@@ -8538,81 +8537,6 @@ 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.
 */
@@ -8750,7 +8674,6 @@ 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;
@@ -8837,20 +8760,37 @@ class input_stream_adapter
     std::char_traits<char>::int_type get_character()
     {
 #if !JSON_DISABLE_STREAM_BULK_SCAN
-        // the character is in the get area: step over it, as sbumpc() does
+        // sbumpc() refills the get area if it is exhausted
-        const char* const next = streambuf_access::get_ptr(sb);
+        const bool refill = streambuf_access::get_ptr(sb) == streambuf_access::get_end(sb);
-        if (JSON_HEDLEY_LIKELY(next != streambuf_access::get_end(sb)))
+        if (JSON_HEDLEY_UNLIKELY(refill))
         {
-            current_in_get_area = true;
+            save_token_segment();
-            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 get_character_slow();
+
+        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
 
@@ -8859,18 +8799,6 @@ 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)))
@@ -8958,7 +8886,7 @@ class input_stream_adapter
     // last one if @a drop_last.
     void copy_token(std::vector<char>& out, bool drop_last) const
     {
-        token_carry.copy_to(out);
+        out = token_carry;
         if (token_segment != nullptr)
         {
             out.insert(out.end(), token_segment, current_end());
@@ -8971,47 +8899,6 @@ 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
@@ -9035,11 +8922,6 @@ 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
@@ -9060,53 +8942,16 @@ class input_stream_adapter
     {
         if (token_segment != nullptr)
         {
-            token_carry.append(token_segment, streambuf_access::get_end(sb));
+            token_carry.insert(token_carry.end(), 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;
@@ -9145,16 +8990,13 @@ class input_stream_adapter
 #endif
 #if !JSON_DISABLE_STREAM_BULK_SCAN
     /// the part of the current token that was in earlier get areas
-    token_carry_buffer token_carry{}; // NOLINT(readability-redundant-member-init)
+    std::vector<char> 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
@@ -22508,7 +22350,7 @@ NLOHMANN_JSON_NAMESPACE_END
 
 
 
-#include <algorithm> // all_of
+#include <algorithm> // all_of, copy
 #include <array> // array
 #include <cctype> // isdigit
 #include <cerrno> // errno, ERANGE
@@ -22590,12 +22432,34 @@ class json_pointer
     {
         // one buffer: every token adds its escaped form (at least its length) and a slash
         std::size_t length = 0;
+        bool plain = true;
         for (const auto& reference_token : reference_tokens)
         {
             length += reference_token.size() + 1;
+            const char* const data = reference_token.data();
+            for (std::size_t i = 0, size = reference_token.size(); plain && i < size; ++i)
+            {
+                plain = data[i] != '~' && data[i] != '/';
+            }
         }
 
         string_t result;
+        if (JSON_HEDLEY_LIKELY(plain))
+        {
+            // nothing to escape: the tokens are copied into the string
+            result.resize(length);
+            if (length != 0)
+            {
+                char* out = &result[0];
+                for (const auto& reference_token : reference_tokens)
+                {
+                    *out++ = '/';
+                    out = std::copy(reference_token.data(), reference_token.data() + reference_token.size(), out);
+                }
+            }
+            return result;
+        }
+
         result.reserve(length);
         for (const auto& reference_token : reference_tokens)
         {
@@ -23706,33 +23570,32 @@ class json_pointer
         }
         result.reserve(token_count);
 
-        // extract the reference tokens:
+        // extract the reference tokens: every one runs from after a slash to
-        // - slash: position of the last read slash (or end of string)
+        // the next slash or the end of the string; a token without a '~' (the
-        // - start: position after the previous slash
+        // common case) is stored as it is, others are checked and unescaped
-        for (
+        const char* const data = reference_string.data();
-            // search for the first slash after the first character
+        const char* const end = data + size;
-            std::size_t slash = reference_string.find_first_of('/', 1),
+        for (const char* start = data + 1;; ++start)
-            // set the beginning of the first reference token
-            start = 1;
-            // we can stop if start == 0 (if slash == string_t::npos)
-            start != 0;
-            // set the beginning of the next reference token
-            // (will eventually be 0 if slash == string_t::npos)
-            start = (slash == string_t::npos) ? 0 : slash + 1,
-            // find next slash
-            slash = reference_string.find_first_of('/', start))
         {
-            // use the text between the beginning of the reference token
+            const char* slash = start;
-            // (start) and the last slash (slash).
+            bool escaped = false;
-            const auto count = (slash == string_t::npos ? reference_string.size() : slash) - start;
+            while (slash != end && *slash != '/')
-            auto reference_token = string_t(reference_string.data() + start, count);
+            {
+                escaped = escaped || *slash == '~';
+                ++slash;
+            }
 
-            // check reference tokens are properly escaped; a token without
+            const auto count = static_cast<std::size_t>(slash - start);
-            // a '~' (the common case) needs neither check nor unescaping
+            if (JSON_HEDLEY_LIKELY(!escaped))
-            std::size_t pos = reference_token.find_first_of('~');
-            if (pos != string_t::npos)
             {
-                for (; pos != string_t::npos; pos = reference_token.find_first_of('~', pos + 1))
+                result.emplace_back(start, count);
+            }
+            else
+            {
+                auto reference_token = string_t(start, count);
+
+                // check reference tokens are properly escaped
+                for (std::size_t pos = reference_token.find_first_of('~'); pos != string_t::npos; pos = reference_token.find_first_of('~', pos + 1))
                 {
                     JSON_ASSERT(reference_token[pos] == '~');
 
@@ -23746,10 +23609,14 @@ class json_pointer
                 }
 
                 detail::unescape(reference_token);
+                result.push_back(std::move(reference_token));
             }
 
-            // finally, store the reference token
+            if (slash == end)
-            result.push_back(std::move(reference_token));
+            {
+                break;
+            }
+            start = slash;
         }
 
         return result;

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

@@ -48,16 +48,14 @@ namespace
 class chunked_streambuf : public std::streambuf
 {
   public:
-    // The first @a unbuffered characters are served without a get area, the
+    chunked_streambuf(std::string s, std::size_t chunk_size)
-    // rest in get areas of @a chunk_size.
+        : m_data(std::move(s)), m_chunk_size(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 || m_pos < m_unbuffered)
+        if (m_chunk_size == 0)
         {
             return m_pos < m_data.size() ? traits_type::to_int_type(m_data[m_pos]) : traits_type::eof();
         }
@@ -79,7 +77,7 @@ class chunked_streambuf : public std::streambuf
 
     int_type uflow() override
     {
-        if (m_chunk_size == 0 || m_pos < m_unbuffered)
+        if (m_chunk_size == 0)
         {
             return m_pos < m_data.size() ? traits_type::to_int_type(m_data[m_pos++]) : traits_type::eof();
         }
@@ -90,7 +88,6 @@ 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
@@ -104,9 +101,9 @@ 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::size_t unbuffered = 0)
+std::string observe(const std::string& input, std::size_t chunk_size, read_mode mode)
 {
-    chunked_streambuf buf(input, chunk_size, unbuffered);
+    chunked_streambuf buf(input, chunk_size);
     std::istream is(&buf);
     std::string result;
     for (int i = 0; i < 4; ++i)
@@ -215,31 +212,6 @@ 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")