Check the declared BSON document size before reading its content

The BSON reader compared a document's declared size with the number of bytes
read only when it reached the terminator. The declared size never bounded
the reads, so a SAX handler saw the keys and values of a document whose size
was too small before parse error 112 was reported.

The container frame now stores the position where the document ends
according to its declared size. open_bson_document rejects a size below 5
(size prefix plus terminator) and an embedded document that does not end
before the terminator of its enclosing document; the element loop rejects an
element whose type byte leaves no room for the name terminator and the
document terminator. The terminator check stays and still catches a declared
size that is too large. No input that was accepted before is rejected now;
documents with a wrong size are reported earlier, with fewer SAX events, a
different byte position and, in three cases, a different message. The error
id (parse_error.112) is unchanged and strict=false still does not skip the
check.

The tests that asserted the old messages and positions are updated, with the
outer sizes of two inputs corrected so that they still exercise the embedded
document. New tests cover the SAX events, a size below 5, and an embedded
document that fits exactly.

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

include/nlohmann/detail/input/binary_reader.hpp

@@ -235,6 +235,9 @@ class binary_reader
         /// UBJSON/BJData: the type marker of an optimized container, so that
         /// its elements are read without one of their own; 0 otherwise
         char_int_type type_marker;
+        /// BSON: the position right after this document, according to the
+        /// size it declares
+        std::size_t end_position = 0;
         /// BSON: the size this document declares, in bytes
         std::int32_t declared_size = 0;
         /// whether to close this container with end_object() or end_array()
@@ -371,6 +374,23 @@ class binary_reader
             return false;
         }
 
+        // the smallest document is the size prefix and the terminator
+        if (JSON_HEDLEY_UNLIKELY(document_size < 5))
+        {
+            return bson_document_size_error("document size ", document_size, " is less than 5");
+        }
+
+        // the declared size bounds where the document ends: an embedded
+        // document must end before the terminator of the document that contains it
+        const std::size_t unsigned_size = static_cast<std::size_t>(document_size);
+        const std::size_t document_end = unsigned_size > (std::numeric_limits<std::size_t>::max)() - document_start
+                                         ? (std::numeric_limits<std::size_t>::max)()
+                                         : document_start + unsigned_size;
+        if (JSON_HEDLEY_UNLIKELY(!container_stack.empty() && document_end >= container_stack.back().end_position))
+        {
+            return bson_document_size_error("document size ", document_size, " exceeds the size of the enclosing document");
+        }
+
         if (JSON_HEDLEY_UNLIKELY(!enter_container(is_object, detail::unknown_size())))
         {
             return false;
@@ -378,6 +398,7 @@ class binary_reader
 
         container_frame& frame = container_stack.back();
         frame.start_position = document_start;
+        frame.end_position = document_end;
         frame.declared_size = document_size;
         return true;
     }
@@ -436,6 +457,13 @@ class binary_reader
                 return false;
             }
 
+            // an element needs at least its name's terminator, and the
+            // document its own terminator, within the declared size
+            if (JSON_HEDLEY_UNLIKELY(chars_read + 2 > container_stack.back().end_position))
+            {
+                return bson_document_size_error("document size ", container_stack.back().declared_size, " is too small for its content");
+            }
+
             const std::size_t element_type_parse_position = chars_read;
             key.clear();
             if (JSON_HEDLEY_UNLIKELY(!get_bson_cstr(key)))
@@ -4436,6 +4464,12 @@ class binary_reader
         return last_byte_error(exception_id::unexpected_byte, concat("document size ", std::to_string(document_size), " does not match the number of bytes read (", std::to_string(bytes_read), ")"), "document");
     }
 
+    JSON_HEDLEY_NEVER_INLINE
+    bool bson_document_size_error(const char* prefix, const std::int32_t document_size, const char* suffix) const
+    {
+        return last_byte_error(exception_id::unexpected_byte, concat(prefix, std::to_string(document_size), suffix), "document");
+    }
+
     JSON_HEDLEY_NEVER_INLINE
     bool bson_unsupported_type_error(const std::size_t position, const char_int_type element_type) const
     {