Merge branch 'develop' into claude/fix-issue-3989-db7e45

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

include/nlohmann/detail/input/binary_reader.hpp

@@ -108,7 +108,7 @@ inline bool is_cbor_item_head(const unsigned int byte) noexcept
         into a JSON value use false, because their SAX parsers never do, and
         then the code that recovers is not compiled.
 */
-template<typename BasicJsonType, typename InputAdapterType, typename SAX = json_sax_dom_parser<BasicJsonType, InputAdapterType>, bool AllowRecovery = false>
+template<typename BasicJsonType, typename InputAdapterType, typename SAX = json_sax_dom_binary_parser<BasicJsonType, InputAdapterType>, bool AllowRecovery = false>
 class binary_reader
 {
     using number_integer_t = typename BasicJsonType::number_integer_t;

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 +73,82 @@ 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);
+        const auto room = static_cast<std::size_t>(m_capacity_end - m_end);
+        if (n > room)
+        {
+            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 +286,7 @@ 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 +373,20 @@ 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
-        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
+        // the character is in the get area: step over it, as sbumpc() does
+        const char* const next = streambuf_access::get_ptr(sb);
+        if (JSON_HEDLEY_LIKELY(next != streambuf_access::get_end(sb)))
         {
             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 +395,18 @@ 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 +494,7 @@ 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 +507,47 @@ 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 +571,11 @@ 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 +596,53 @@ 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 +681,16 @@ 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/input/lexer.hpp

@@ -14,6 +14,7 @@
 #include <cstdio> // snprintf
 #include <cstring> // memcmp
 #include <initializer_list> // initializer_list
+#include <limits> // numeric_limits
 #include <string> // char_traits, string
 #include <utility> // move
 #include <vector> // vector
@@ -1881,6 +1882,15 @@ scan_number_done:
     /// significand (see scan_number_bulk_contiguous())
     bool convert_accumulated_float(const float_significand& s, std::true_type /*native*/) noexcept
     {
+        // accept() only needs to know that the value is finite (see the parser):
+        // w < 10^19, so a value below 10^max_exponent10 cannot overflow, and a
+        // value that underflows is a finite number as well. Only a token that
+        // may overflow has to be converted to find out.
+        if (JSON_HEDLEY_UNLIKELY(discard_number_values && s.exponent + 19 <= std::numeric_limits<number_float_t>::max_exponent10))
+        {
+            value_float = 0;
+            return true;
+        }
         value_float = decimal_to_float<number_float_t>(s);
         return true;
     }

include/nlohmann/detail/input/parser.hpp

@@ -56,8 +56,8 @@ using parser_callback_t =
 template<typename SAX>
 struct sax_ignores_number_text : std::false_type {};
 
-template<typename BasicJsonType, typename InputAdapterType>
-struct sax_ignores_number_text<json_sax_dom_parser<BasicJsonType, InputAdapterType>> : std::true_type {};
+template<typename BasicJsonType, typename InputAdapterType, bool Collect>
+struct sax_ignores_number_text<json_sax_dom_parser<BasicJsonType, InputAdapterType, Collect>> : std::true_type {};
 
 template<typename BasicJsonType, typename InputAdapterType>
 struct sax_ignores_number_text<json_sax_dom_callback_parser<BasicJsonType, InputAdapterType>> : std::true_type {};
@@ -131,7 +131,7 @@ class parser
         }
         else
         {
-            json_sax_dom_parser<BasicJsonType, InputAdapterType> sdp(result, allow_exceptions, &m_lexer);
+            json_sax_dom_parser<BasicJsonType, InputAdapterType, true> sdp(result, allow_exceptions, &m_lexer);
 
             // in case of an error, return a discarded value
             if (!parse_dom(sdp, strict))
@@ -286,13 +286,19 @@ class parser
     bool sax_parse_internal(SAX* sax)
     {
         const std::integral_constant<bool, AllowRecovery> allow_recovery{};
+        // value to avoid a goto (see comment where set to true)
+        bool skip_to_state_evaluation = false;
 
         // stack to remember the hierarchy of structured values we are parsing
         // true = array; false = object (bytes, not std::vector<bool>, whose
         // push_back() is a call with GCC)
         std::vector<std::uint8_t> states;
-        // value to avoid a goto (see comment where set to true)
-        bool skip_to_state_evaluation = false;
+        // a document that starts with a container pushes onto the stack at
+        // once: allocate it in one step instead of growing it from 1 byte
+        if (last_token == token_type::begin_object || last_token == token_type::begin_array)
+        {
+            states.reserve(32);
+        }
 
         while (true)
         {