Merge develop into fix/bjdata-count-size-max

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

include/nlohmann/detail/input/binary_reader.hpp

@@ -1856,14 +1856,18 @@ class binary_reader
 
     Only the start of an array is tried, which covers arrays of numbers
     (e.g. coordinates) but costs arrays of other values only one call, not one
-    per element.
+    per element. An array of one element is not tried at all: that element is
+    mostly an object or an array (`[[...]]`, the single ring of a GeoJSON
+    polygon), for which the call would find no scalar, while a single scalar,
+    which the run would read faster, is rare. The benchmarks
+    `FromBinaryShape/nested` and `FromBinaryShape/singles` show both sides.
 
     @param[in] len  the number of elements
     @return whether the SAX parser accepted the array and the values read
     */
     bool enter_cbor_array(const std::size_t len)
     {
-        return enter_array(len) && (len == 0 || parse_cbor_scalar_run(std::integral_constant<bool, bulk_scan> {}));
+        return enter_array(len) && (len <= 1 || parse_cbor_scalar_run(std::integral_constant<bool, bulk_scan> {}));
     }
 
     /// input that is not contiguous: every value is read by parse_cbor_value
@@ -2766,12 +2770,16 @@ class binary_reader
     /*!
     @brief open a MessagePack array and read the scalars it begins with (see
            @ref parse_msgpack_scalar_run)
+
+    An array of one element is not tried, for the reason given at
+    @ref enter_cbor_array.
+
     @param[in] len  the number of elements
     @return whether the SAX parser accepted the array and the values read
     */
     bool enter_msgpack_array(const std::size_t len)
     {
-        return enter_array(len) && (len == 0 || parse_msgpack_scalar_run(std::integral_constant<bool, bulk_scan> {}));
+        return enter_array(len) && (len <= 1 || parse_msgpack_scalar_run(std::integral_constant<bool, bulk_scan> {}));
     }
 
     /// input that is not contiguous: every value is read by parse_msgpack_value

include/nlohmann/detail/input/input_adapters.hpp

@@ -545,12 +545,9 @@ class input_stream_adapter
     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();
-        }
+        // the get area is exhausted (get_character() handles the other case),
+        // so sbumpc() refills it
+        save_token_segment();
 #endif
 
         auto res = sb->sbumpc();
@@ -563,17 +560,13 @@ class input_stream_adapter
             is->clear(is->rdstate() | std::ios::eofbit);
         }
 #if !JSON_DISABLE_STREAM_BULK_SCAN
-        else if (JSON_HEDLEY_UNLIKELY(refill))
+        else
         {
             // 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;
     }

include/nlohmann/detail/input/json_sax.hpp

@@ -999,7 +999,7 @@ class json_sax_dom_parser : public json_sax_dom_error_state
         ordered_data.members[f.ordered.dest_member].second = std::move(value);
     }
 
-    static void place_member(const frame& /*f*/, BasicJsonType&& /*value*/, std::false_type /*indexed*/) noexcept {}
+    static void place_member(const frame& /*f*/, BasicJsonType&& /*value*/, std::false_type /*indexed*/) noexcept {} // LCOV_EXCL_LINE
 
     /// store the members of a new object directly in it
     bool start_stored_object(std::size_t len)
@@ -1303,7 +1303,7 @@ class json_sax_dom_parser : public json_sax_dom_error_state
         {
             // a new member is null and holds nothing: construct the value
             // over it instead of destroying and swapping
-            ::new (static_cast<void*>(&member)) BasicJsonType(std::forward<Value>(v));
+            construct_member(member, std::forward<Value>(v), std::is_nothrow_constructible<BasicJsonType, Value> {});
         }
         else
         {
@@ -1312,6 +1312,26 @@ class json_sax_dom_parser : public json_sax_dom_error_state
         }
     }
 
+    /// constructing the value cannot throw (for example a number or a boolean): construct it in place
+    template<typename Value>
+    JSON_HEDLEY_ALWAYS_INLINE
+    static void construct_member(BasicJsonType& member, Value&& v, std::true_type /*nothrow*/)
+    {
+        ::new (static_cast<void*>(&member)) BasicJsonType(std::forward<Value>(v));
+    }
+
+    /// constructing the value can throw (for example a container or a string), and a
+    /// constructor that was interrupted must not have touched the member (#5985):
+    /// create the value first, then move it over the member (the move constructor is
+    /// noexcept)
+    template<typename Value>
+    JSON_HEDLEY_ALWAYS_INLINE
+    static void construct_member(BasicJsonType& member, Value&& v, std::false_type /*may throw*/)
+    {
+        BasicJsonType value(std::forward<Value>(v));
+        ::new (static_cast<void*>(&member)) BasicJsonType(std::move(value));
+    }
+
     /// a custom base class may care about the lifetime of the value
     template<typename Value>
     static void set_member(BasicJsonType& member, Value&& v, std::false_type /*custom base*/)
@@ -1737,7 +1757,7 @@ class json_sax_dom_callback_parser : public json_sax_dom_error_state
         key_stack.push_back(val);
 
         // add discarded value at the given key and store the reference for later
-        if (keep && ref_stack.back())
+        if (keep)
         {
             auto& obj = *ref_stack.back()->m_data.m_value.object;
             // a single lookup: insert the placeholder, or find the existing member
@@ -1794,7 +1814,7 @@ class json_sax_dom_callback_parser : public json_sax_dom_error_state
 
         const string_t object_key = pop_container();
 
-        if (!ref_stack.empty() && ref_stack.back() && ref_stack.back()->is_structured())
+        if (!ref_stack.empty() && ref_stack.back())
         {
             // remove discarded value
             remove_discarded_value(*ref_stack.back(), object_key);
@@ -1960,8 +1980,7 @@ class json_sax_dom_callback_parser : public json_sax_dom_error_state
     */
     string_t current_key() const
     {
-        if (!ref_stack.empty() && ref_stack.back() && ref_stack.back()->is_object()
-                && !key_stack.empty())
+        if (!ref_stack.empty() && ref_stack.back() && ref_stack.back()->is_object())
         {
             return key_stack.back();
         }

include/nlohmann/detail/input/lexer.hpp

@@ -300,14 +300,16 @@ class lexer : public lexer_base<BasicJsonType>
     /// calls would (including the position and token bookkeeping of a
     /// streaming adapter, see bulk_consume) and leaves @a current holding the last of
     /// the 4 digits, just as the last such get() would; the codepoint is
-    /// written to @a out. Makes no state change and returns false for a
-    /// pending unget, fewer than 4 remaining bytes, or any of the 4 bytes not
-    /// being a hex digit, so the caller falls back unchanged to the
-    /// per-character loop, which then reports the same diagnostic (stopping
-    /// at the first invalid digit) as before this optimization.
+    /// written to @a out. Makes no state change and returns false for fewer
+    /// than 4 remaining bytes or any of the 4 bytes not being a hex digit, so
+    /// the caller falls back unchanged to the per-character loop, which then
+    /// reports the same diagnostic (stopping at the first invalid digit) as
+    /// before this optimization.
     bool get_codepoint_bulk(std::true_type /*bulk*/, int& out)
     {
-        if (next_unget || ia.bulk_remaining() < 4)
+        // no unget is pending inside a string (see get_after_string_run())
+        JSON_ASSERT(!next_unget);
+        if (ia.bulk_remaining() < 4)
         {
             return false;
         }
@@ -437,11 +439,10 @@ class lexer : public lexer_base<BasicJsonType>
     template<bool Keep>
     char_int_type get_after_string_run(std::true_type /*bulk*/, std::integral_constant<bool, Keep> keep)
     {
-        // a pending unget must be consumed through the normal path first
-        if (next_unget)
-        {
-            return get();
-        }
+        // scan_string() is entered from scan_after_whitespace(), whose current
+        // was read by skip_whitespace() (its first get() clears a pending
+        // unget), and nothing in scan_string() calls unget()
+        JSON_ASSERT(!next_unget);
         const std::size_t remaining = ia.bulk_remaining();
         if (remaining == 0)
         {
@@ -1410,7 +1411,7 @@ scan_number_done:
                 return token_type::value_unsigned;
             }
         }
-        else if (number_type == token_type::value_integer)
+        else // value_integer (the callers handle value_float themselves)
         {
             if (parse_integer_signed(first, last, value_integer))
             {
@@ -1516,11 +1517,9 @@ scan_number_done:
     */
     token_type scan_number_bulk_contiguous()
     {
-        // a pending unget offsets the buffer position from current; fall back
-        if (next_unget)
-        {
-            return token_type::uninitialized;
-        }
+        // called right after scan_after_whitespace() read current (see
+        // get_after_string_run()), so no unget is pending
+        JSON_ASSERT(!next_unget);
         const std::size_t rem = ia.bulk_remaining();
         if (rem == 0)
         {
@@ -1541,11 +1540,7 @@ scan_number_done:
         if (data[0] == '-')
         {
             number_type = token_type::value_integer;
-            i = 1;
-            if (i >= avail)
-            {
-                return token_type::uninitialized;
-            }
+            i = 1; // avail >= 2: rem == 0 returned above
         }
         const std::size_t integer_begin = i;
         if (data[i] == '0')
@@ -1787,7 +1782,10 @@ scan_number_done:
     /// the error at the right character
     JSON_HEDLEY_ALWAYS_INLINE bool scan_literal_bulk(const char* rest, const std::size_t length, std::true_type /*bulk*/)
     {
-        if (next_unget || ia.bulk_remaining() < length
+        // called right after scan_after_whitespace() read current (see
+        // get_after_string_run()), so no unget is pending
+        JSON_ASSERT(!next_unget);
+        if (ia.bulk_remaining() < length
                 || std::memcmp(ia.bulk_data(), rest, length) != 0)
         {
             return false;

include/nlohmann/detail/input/parser.hpp

@@ -573,14 +573,7 @@ class parser
 
     std::string exception_message(const token_type expected, const std::string& context)
     {
-        std::string error_msg = "syntax error ";
-
-        if (!context.empty())
-        {
-            error_msg += concat("while parsing ", context, ' ');
-        }
-
-        error_msg += "- ";
+        std::string error_msg = concat("syntax error while parsing ", context, " - ");
 
         if (last_token == token_type::parse_error)
         {
@@ -598,7 +591,7 @@ class parser
         }
 
         return error_msg;
-    }
+    } // LCOV_EXCL_LINE (exception cleanup only)
 
   private:
     /// callback function