Fix 32-bit overflow in huge_string_t BSON length-overflow tests

huge_string_t doubles as basic_json's StringType, so it is used not only
for the JSON string value under test but also for object keys (e.g. "s",
"nested"). Making size() unconditionally lie about being huge therefore
inflated the keys' reported sizes as well, pushing the running totals
computed while walking the BSON document (calc_bson_object_size and
friends in binary_writer.hpp) past what a 32-bit std::size_t can hold.

On 64-bit platforms this happens to still produce a working (if
needlessly large) result, but on 32-bit platforms (e.g. the mingw x86 CI
job) the size_t arithmetic silently wraps around: for the "document" test
this merely surfaces the wrong number in the exception message, but for
the "string" test the wrapped total happens to fall back under
INT32_MAX, so the intended out_of_range.412 guard is skipped entirely and
the code goes on to actually write ~2 GiB worth of characters from the
key's real, tiny buffer - which is what raised the reported
"vector::_M_range_insert" exception instead of a controlled 412.

Make the fake-huge size opt-in via huge_string_t::as_huge() and only
apply it to the string value under test, leaving keys at their real
(small) size. This keeps every intermediate size well within 32-bit
size_t range on any platform, matching how huge_binary_t already avoids
the same trap (it is only ever used as the BSON value type, never as a
key). Expected out_of_range.412 messages are updated accordingly.

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

include/nlohmann/detail/input/binary_reader.hpp

@@ -996,21 +996,23 @@ class binary_reader
     }
 
     /*!
-    @brief reads a definite-length CBOR string
+    @brief reads a CBOR string
 
-    Reads everything @ref get_cbor_string accepts except the indefinite-length
-    form, which that function handles itself. The bytes are appended to @a
-    result, so consecutive chunks of an indefinite-length string can be read
-    into the same string.
+    This function first reads starting bytes to determine the expected
+    string length and then copies this number of bytes into a string.
+    Additionally, CBOR's strings with indefinite lengths are supported.
 
-    @param[out] result  string the bytes are appended to
+    @param[out] result  created string
 
     @return whether string creation completed
-
-    @pre @a current is not EOF
     */
-    bool get_cbor_string_chunk(string_t& result)
+    bool get_cbor_string(string_t& result)
     {
+        if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "string")))
+        {
+            return false;
+        }
+
         switch (current)
         {
             // UTF-8 string (0x00..0x17 bytes follow)
@@ -1066,6 +1068,20 @@ class binary_reader
                 return get_number(input_format_t::cbor, len) && get_string(input_format_t::cbor, len, result);
             }
 
+            case 0x7F: // UTF-8 string (indefinite length)
+            {
+                while (get() != 0xFF)
+                {
+                    string_t chunk;
+                    if (!get_cbor_string(chunk))
+                    {
+                        return false;
+                    }
+                    result.append(chunk);
+                }
+                return true;
+            }
+
             default:
             {
                 auto last_token = get_token_string();
@@ -1076,82 +1092,23 @@ class binary_reader
     }
 
     /*!
-    @brief reads a CBOR string
+    @brief reads a CBOR byte array
 
     This function first reads starting bytes to determine the expected
-    string length and then copies this number of bytes into a string.
-    Additionally, CBOR's strings with indefinite lengths are supported.
+    byte array length and then copies this number of bytes into the byte array.
+    Additionally, CBOR's byte arrays with indefinite lengths are supported.
 
-    @param[out] result  created string
-
-    @return whether string creation completed
-    */
-    bool get_cbor_string(string_t& result)
-    {
-        // number of indefinite-length strings that have been opened and not
-        // closed yet. RFC 8949, Section 3.2.3 does not permit nesting them,
-        // but this reader has always accepted it, so the open levels are
-        // counted instead of recursed through, which overflowed the stack for
-        // an input of repeated 0x7F bytes (see #5104). Every chunk is appended
-        // to the same result, so no per-level state is needed.
-        std::size_t open = 0;
-
-        while (true)
-        {
-            if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "string")))
-            {
-                return false;
-            }
-
-            if (current == 0x7F) // UTF-8 string (indefinite length)
-            {
-                ++open;
-                get();
-                continue;
-            }
-
-            // a break marker closes the innermost indefinite-length string;
-            // outside of one it is not a string and falls through to the error
-            if (open != 0 && current == 0xFF)
-            {
-                if (--open == 0)
-                {
-                    return true;
-                }
-                get();
-                continue;
-            }
-
-            if (JSON_HEDLEY_UNLIKELY(!get_cbor_string_chunk(result)))
-            {
-                return false;
-            }
-
-            if (open == 0)
-            {
-                return true;
-            }
-
-            get();
-        }
-    }
-
-    /*!
-    @brief reads a definite-length CBOR byte array
-
-    Reads everything @ref get_cbor_binary accepts except the indefinite-length
-    form, which that function handles itself. The bytes are appended to @a
-    result, so consecutive chunks of an indefinite-length byte array can be
-    read into the same byte array.
-
-    @param[out] result  byte array the bytes are appended to
+    @param[out] result  created byte array
 
     @return whether byte array creation completed
-
-    @pre @a current is not EOF
     */
-    bool get_cbor_binary_chunk(binary_t& result)
+    bool get_cbor_binary(binary_t& result)
     {
+        if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "binary")))
+        {
+            return false;
+        }
+
         switch (current)
         {
             // Binary data (0x00..0x17 bytes follow)
@@ -1211,6 +1168,20 @@ class binary_reader
                        get_binary(input_format_t::cbor, len, result);
             }
 
+            case 0x5F: // Binary data (indefinite length)
+            {
+                while (get() != 0xFF)
+                {
+                    binary_t chunk;
+                    if (!get_cbor_binary(chunk))
+                    {
+                        return false;
+                    }
+                    result.insert(result.end(), chunk.begin(), chunk.end());
+                }
+                return true;
+            }
+
             default:
             {
                 auto last_token = get_token_string();
@@ -1220,63 +1191,6 @@ class binary_reader
         }
     }
 
-    /*!
-    @brief reads a CBOR byte array
-
-    This function first reads starting bytes to determine the expected
-    byte array length and then copies this number of bytes into the byte array.
-    Additionally, CBOR's byte arrays with indefinite lengths are supported.
-
-    @param[out] result  created byte array
-
-    @return whether byte array creation completed
-    */
-    bool get_cbor_binary(binary_t& result)
-    {
-        // the open indefinite-length byte arrays are counted rather than
-        // recursed through, for the reason given in @ref get_cbor_string
-        std::size_t open = 0;
-
-        while (true)
-        {
-            if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "binary")))
-            {
-                return false;
-            }
-
-            if (current == 0x5F) // Binary data (indefinite length)
-            {
-                ++open;
-                get();
-                continue;
-            }
-
-            // a break marker closes the innermost indefinite-length byte
-            // array; outside of one it falls through to the error below
-            if (open != 0 && current == 0xFF)
-            {
-                if (--open == 0)
-                {
-                    return true;
-                }
-                get();
-                continue;
-            }
-
-            if (JSON_HEDLEY_UNLIKELY(!get_cbor_binary_chunk(result)))
-            {
-                return false;
-            }
-
-            if (open == 0)
-            {
-                return true;
-            }
-
-            get();
-        }
-    }
-
     /*!
     @brief narrow a definite CBOR array/map length to std::size_t
 
@@ -2477,12 +2391,7 @@ class binary_reader
     {
         result.first = npos; // size
         result.second = 0; // type
-        // seed the flag with the caller's context: inside an ndarray dimension
-        // vector another ndarray is not allowed, and get_ubjson_size_value()
-        // rejects it up front instead of reading it and reporting afterwards.
-        // Seeding it with `false` made every '#' of a "[#[#[..." chain descend
-        // another level, which overflowed the stack (see #5104).
-        bool is_ndarray = inside_ndarray;
+        bool is_ndarray = false;
 
         get_ignore_noop();
 
@@ -2515,11 +2424,13 @@ class binary_reader
             }
 
             const bool is_error = get_ubjson_size_value(result.first, is_ndarray);
-            // an ndarray was read here only if the flag flipped; when it was
-            // seeded true, get_ubjson_size_value() already rejected the nested
-            // dimension vector
-            if (input_format == input_format_t::bjdata && is_ndarray && !inside_ndarray)
+            if (input_format == input_format_t::bjdata && is_ndarray)
             {
+                if (inside_ndarray)
+                {
+                    return sax->parse_error(chars_read, get_token_string(), parse_error::create(112, chars_read,
+                                            exception_message(input_format, "ndarray can not be recursive", "size"), nullptr));
+                }
                 result.second |= (1 << 8); // use bit 8 to indicate ndarray, all UBJSON and BJData markers should be ASCII letters
             }
             return is_error;
@@ -2528,7 +2439,7 @@ class binary_reader
         if (current == '#')
         {
             const bool is_error = get_ubjson_size_value(result.first, is_ndarray);
-            if (input_format == input_format_t::bjdata && is_ndarray && !inside_ndarray)
+            if (input_format == input_format_t::bjdata && is_ndarray)
             {
                 return sax->parse_error(chars_read, get_token_string(), parse_error::create(112, chars_read,
                                         exception_message(input_format, "ndarray requires both type and size", "size"), nullptr));

include/nlohmann/json.hpp

@@ -4473,11 +4473,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in CBOR format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4493,11 +4490,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     template<typename T>
@@ -4522,11 +4516,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = i.get();
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in MessagePack format
@@ -4540,11 +4531,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in MessagePack format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4559,11 +4547,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     template<typename T>
@@ -4586,11 +4571,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = i.get();
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in UBJSON format
@@ -4604,11 +4586,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in UBJSON format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4623,11 +4602,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     template<typename T>
@@ -4650,11 +4626,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = i.get();
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in BJData format
@@ -4668,11 +4641,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in BJData format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4687,11 +4657,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in BSON format
@@ -4705,11 +4672,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in BSON format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4724,11 +4688,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     template<typename T>
@@ -4751,11 +4712,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = i.get();
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
     /// @}
 

single_include/nlohmann/json.hpp

@@ -11683,21 +11683,23 @@ class binary_reader
     }
 
     /*!
-    @brief reads a definite-length CBOR string
+    @brief reads a CBOR string
 
-    Reads everything @ref get_cbor_string accepts except the indefinite-length
-    form, which that function handles itself. The bytes are appended to @a
-    result, so consecutive chunks of an indefinite-length string can be read
-    into the same string.
+    This function first reads starting bytes to determine the expected
+    string length and then copies this number of bytes into a string.
+    Additionally, CBOR's strings with indefinite lengths are supported.
 
-    @param[out] result  string the bytes are appended to
+    @param[out] result  created string
 
     @return whether string creation completed
-
-    @pre @a current is not EOF
     */
-    bool get_cbor_string_chunk(string_t& result)
+    bool get_cbor_string(string_t& result)
     {
+        if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "string")))
+        {
+            return false;
+        }
+
         switch (current)
         {
             // UTF-8 string (0x00..0x17 bytes follow)
@@ -11753,6 +11755,20 @@ class binary_reader
                 return get_number(input_format_t::cbor, len) && get_string(input_format_t::cbor, len, result);
             }
 
+            case 0x7F: // UTF-8 string (indefinite length)
+            {
+                while (get() != 0xFF)
+                {
+                    string_t chunk;
+                    if (!get_cbor_string(chunk))
+                    {
+                        return false;
+                    }
+                    result.append(chunk);
+                }
+                return true;
+            }
+
             default:
             {
                 auto last_token = get_token_string();
@@ -11763,82 +11779,23 @@ class binary_reader
     }
 
     /*!
-    @brief reads a CBOR string
+    @brief reads a CBOR byte array
 
     This function first reads starting bytes to determine the expected
-    string length and then copies this number of bytes into a string.
-    Additionally, CBOR's strings with indefinite lengths are supported.
+    byte array length and then copies this number of bytes into the byte array.
+    Additionally, CBOR's byte arrays with indefinite lengths are supported.
 
-    @param[out] result  created string
-
-    @return whether string creation completed
-    */
-    bool get_cbor_string(string_t& result)
-    {
-        // number of indefinite-length strings that have been opened and not
-        // closed yet. RFC 8949, Section 3.2.3 does not permit nesting them,
-        // but this reader has always accepted it, so the open levels are
-        // counted instead of recursed through, which overflowed the stack for
-        // an input of repeated 0x7F bytes (see #5104). Every chunk is appended
-        // to the same result, so no per-level state is needed.
-        std::size_t open = 0;
-
-        while (true)
-        {
-            if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "string")))
-            {
-                return false;
-            }
-
-            if (current == 0x7F) // UTF-8 string (indefinite length)
-            {
-                ++open;
-                get();
-                continue;
-            }
-
-            // a break marker closes the innermost indefinite-length string;
-            // outside of one it is not a string and falls through to the error
-            if (open != 0 && current == 0xFF)
-            {
-                if (--open == 0)
-                {
-                    return true;
-                }
-                get();
-                continue;
-            }
-
-            if (JSON_HEDLEY_UNLIKELY(!get_cbor_string_chunk(result)))
-            {
-                return false;
-            }
-
-            if (open == 0)
-            {
-                return true;
-            }
-
-            get();
-        }
-    }
-
-    /*!
-    @brief reads a definite-length CBOR byte array
-
-    Reads everything @ref get_cbor_binary accepts except the indefinite-length
-    form, which that function handles itself. The bytes are appended to @a
-    result, so consecutive chunks of an indefinite-length byte array can be
-    read into the same byte array.
-
-    @param[out] result  byte array the bytes are appended to
+    @param[out] result  created byte array
 
     @return whether byte array creation completed
-
-    @pre @a current is not EOF
     */
-    bool get_cbor_binary_chunk(binary_t& result)
+    bool get_cbor_binary(binary_t& result)
     {
+        if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "binary")))
+        {
+            return false;
+        }
+
         switch (current)
         {
             // Binary data (0x00..0x17 bytes follow)
@@ -11898,6 +11855,20 @@ class binary_reader
                        get_binary(input_format_t::cbor, len, result);
             }
 
+            case 0x5F: // Binary data (indefinite length)
+            {
+                while (get() != 0xFF)
+                {
+                    binary_t chunk;
+                    if (!get_cbor_binary(chunk))
+                    {
+                        return false;
+                    }
+                    result.insert(result.end(), chunk.begin(), chunk.end());
+                }
+                return true;
+            }
+
             default:
             {
                 auto last_token = get_token_string();
@@ -11907,63 +11878,6 @@ class binary_reader
         }
     }
 
-    /*!
-    @brief reads a CBOR byte array
-
-    This function first reads starting bytes to determine the expected
-    byte array length and then copies this number of bytes into the byte array.
-    Additionally, CBOR's byte arrays with indefinite lengths are supported.
-
-    @param[out] result  created byte array
-
-    @return whether byte array creation completed
-    */
-    bool get_cbor_binary(binary_t& result)
-    {
-        // the open indefinite-length byte arrays are counted rather than
-        // recursed through, for the reason given in @ref get_cbor_string
-        std::size_t open = 0;
-
-        while (true)
-        {
-            if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "binary")))
-            {
-                return false;
-            }
-
-            if (current == 0x5F) // Binary data (indefinite length)
-            {
-                ++open;
-                get();
-                continue;
-            }
-
-            // a break marker closes the innermost indefinite-length byte
-            // array; outside of one it falls through to the error below
-            if (open != 0 && current == 0xFF)
-            {
-                if (--open == 0)
-                {
-                    return true;
-                }
-                get();
-                continue;
-            }
-
-            if (JSON_HEDLEY_UNLIKELY(!get_cbor_binary_chunk(result)))
-            {
-                return false;
-            }
-
-            if (open == 0)
-            {
-                return true;
-            }
-
-            get();
-        }
-    }
-
     /*!
     @brief narrow a definite CBOR array/map length to std::size_t
 
@@ -13164,12 +13078,7 @@ class binary_reader
     {
         result.first = npos; // size
         result.second = 0; // type
-        // seed the flag with the caller's context: inside an ndarray dimension
-        // vector another ndarray is not allowed, and get_ubjson_size_value()
-        // rejects it up front instead of reading it and reporting afterwards.
-        // Seeding it with `false` made every '#' of a "[#[#[..." chain descend
-        // another level, which overflowed the stack (see #5104).
-        bool is_ndarray = inside_ndarray;
+        bool is_ndarray = false;
 
         get_ignore_noop();
 
@@ -13202,11 +13111,13 @@ class binary_reader
             }
 
             const bool is_error = get_ubjson_size_value(result.first, is_ndarray);
-            // an ndarray was read here only if the flag flipped; when it was
-            // seeded true, get_ubjson_size_value() already rejected the nested
-            // dimension vector
-            if (input_format == input_format_t::bjdata && is_ndarray && !inside_ndarray)
+            if (input_format == input_format_t::bjdata && is_ndarray)
             {
+                if (inside_ndarray)
+                {
+                    return sax->parse_error(chars_read, get_token_string(), parse_error::create(112, chars_read,
+                                            exception_message(input_format, "ndarray can not be recursive", "size"), nullptr));
+                }
                 result.second |= (1 << 8); // use bit 8 to indicate ndarray, all UBJSON and BJData markers should be ASCII letters
             }
             return is_error;
@@ -13215,7 +13126,7 @@ class binary_reader
         if (current == '#')
         {
             const bool is_error = get_ubjson_size_value(result.first, is_ndarray);
-            if (input_format == input_format_t::bjdata && is_ndarray && !inside_ndarray)
+            if (input_format == input_format_t::bjdata && is_ndarray)
             {
                 return sax->parse_error(chars_read, get_token_string(), parse_error::create(112, chars_read,
                                         exception_message(input_format, "ndarray requires both type and size", "size"), nullptr));
@@ -25990,11 +25901,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in CBOR format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -26010,11 +25918,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     template<typename T>
@@ -26039,11 +25944,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = i.get();
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in MessagePack format
@@ -26057,11 +25959,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in MessagePack format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -26076,11 +25975,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     template<typename T>
@@ -26103,11 +25999,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = i.get();
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in UBJSON format
@@ -26121,11 +26014,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in UBJSON format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -26140,11 +26030,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     template<typename T>
@@ -26167,11 +26054,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = i.get();
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in BJData format
@@ -26185,11 +26069,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in BJData format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -26204,11 +26085,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in BSON format
@@ -26222,11 +26100,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     /// @brief create a JSON value from an input in BSON format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -26241,11 +26116,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
 
     template<typename T>
@@ -26268,11 +26140,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = i.get();
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        {
-            result = value_t::discarded;
-        }
-        return result;
+        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        return res ? result : basic_json(value_t::discarded);
     }
     /// @}
 

tests/src/unit-bjdata.cpp

@@ -3288,10 +3288,8 @@ TEST_CASE("BJData")
             CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vR1), "[json.exception.parse_error.113] parse error at byte 6: syntax error while parsing BJData size: ndarray dimensional vector is not allowed", json::parse_error&);
             CHECK(json::from_bjdata(vR1, true, false).is_discarded());
 
-            // a dimension vector that opens another one is rejected where the
-            // nested '[' is read, rather than after it has been descended into
             std::vector<uint8_t> const vR2 = {'[', '$', 'i', '#', '[', '#', '[', 'i', 1, ']', ']', 1};
-            CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vR2), "[json.exception.parse_error.113] parse error at byte 7: syntax error while parsing BJData size: ndarray dimensional vector is not allowed", json::parse_error&);
+            CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vR2), "[json.exception.parse_error.113] parse error at byte 11: syntax error while parsing BJData size: expected length type specification (U, i, u, I, m, l, M, L) after '#'; last byte: 0x5D", json::parse_error&);
             CHECK(json::from_bjdata(vR2, true, false).is_discarded());
 
             std::vector<uint8_t> const vR3 = {'[', '#', '[', 'i', '2', 'i', 2, ']'};
@@ -3299,7 +3297,7 @@ TEST_CASE("BJData")
             CHECK(json::from_bjdata(vR3, true, false).is_discarded());
 
             std::vector<uint8_t> const vR4 = {'[', '$', 'i', '#', '[', '$', 'i', '#', '[', 'i', 1, ']', 1};
-            CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vR4), "[json.exception.parse_error.113] parse error at byte 9: syntax error while parsing BJData size: ndarray dimensional vector is not allowed", json::parse_error&);
+            CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vR4), "[json.exception.parse_error.110] parse error at byte 14: syntax error while parsing BJData number: unexpected end of input", json::parse_error&);
             CHECK(json::from_bjdata(vR4, true, false).is_discarded());
 
             std::vector<uint8_t> const vR5 = {'[', '$', 'i', '#', '[', '[', '[', ']', ']', ']'};
@@ -3307,25 +3305,12 @@ TEST_CASE("BJData")
             CHECK(json::from_bjdata(vR5, true, false).is_discarded());
 
             std::vector<uint8_t> const vR6 = {'[', '$', 'i', '#', '[', '$', 'i', '#', '[', 'i', '2', 'i', 2, ']'};
-            CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vR6), "[json.exception.parse_error.113] parse error at byte 9: syntax error while parsing BJData size: ndarray dimensional vector is not allowed", json::parse_error&);
+            CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vR6), "[json.exception.parse_error.112] parse error at byte 14: syntax error while parsing BJData size: ndarray can not be recursive", json::parse_error&);
             CHECK(json::from_bjdata(vR6, true, false).is_discarded());
 
             std::vector<uint8_t> const vH = {'[', 'H', '[', '#', '[', '$', 'i', '#', '[', 'i', '2', 'i', 2, ']'};
             CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vH), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing BJData size: ndarray dimensional vector is not allowed", json::parse_error&);
             CHECK(json::from_bjdata(vH, true, false).is_discarded());
-
-            // Every "#[" of this chain used to open another dimension vector
-            // and cost several stack frames before anything was rejected, so a
-            // long enough chain crashed the process (see #5104). The nested
-            // vector is refused where it is read, so the length is irrelevant.
-            std::vector<uint8_t> vRdeep = {'['};
-            for (std::size_t i = 0; i < 100000; ++i)
-            {
-                vRdeep.push_back('#');
-                vRdeep.push_back('[');
-            }
-            CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vRdeep), "[json.exception.parse_error.113] parse error at byte 5: syntax error while parsing BJData size: ndarray dimensional vector is not allowed", json::parse_error&);
-            CHECK(json::from_bjdata(vRdeep, true, false).is_discarded());
         }
 
         SECTION("objects")

tests/src/unit-bson.cpp

@@ -38,6 +38,54 @@ class huge_binary_t : public std::vector<std::uint8_t>
 using huge_binary_json = nlohmann::basic_json <
                          std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t,
                          double, std::allocator, nlohmann::adl_serializer, huge_binary_t, void >;
+
+// a string type that can be made to report a size beyond INT32_MAX without
+// allocating that much memory, so BSON length overflow can be tested for
+// strings and (embedded) documents as well, following the same idea as
+// huge_binary_t.
+//
+// Unlike huge_binary_t (which is only ever used as the BSON *value* type),
+// this type doubles as basic_json's StringType and is therefore also used
+// for *object keys* (e.g. "s" or "nested" below). Only the designated test
+// value is meant to lie about its size - if every huge_string_t (including
+// keys) reported a huge size, the running totals computed while walking the
+// BSON document (see calc_bson_object_size & friends in binary_writer.hpp)
+// would need more than 32 bits, and on platforms where std::size_t is only
+// 32 bits wide that arithmetic would silently wrap around, producing wrong
+// (or even unguarded) lengths. The fake size is therefore opt-in via
+// as_huge(), and plain strings - in particular object keys - keep reporting
+// their real, small size.
+class huge_string_t : public std::string
+{
+  public:
+    using std::string::string;
+    huge_string_t(const std::string& s) : std::string(s) {} // NOLINT(google-explicit-constructor,hicpp-explicit-conversions)
+
+    // returns a copy of @a s whose size() pretends to be huge
+    static huge_string_t as_huge(const std::string& s)
+    {
+        huge_string_t result(s);
+        result.pretend_huge = true;
+        return result;
+    }
+
+    size_type size() const noexcept
+    {
+        if (pretend_huge)
+        {
+            // one byte more than the BSON length field can represent
+            return static_cast<size_type>((std::numeric_limits<std::int32_t>::max)()) + 1;
+        }
+        return std::string::size();
+    }
+
+  private:
+    bool pretend_huge = false;
+};
+
+using huge_string_json = nlohmann::basic_json <
+                         std::map, std::vector, huge_string_t, bool, std::int64_t, std::uint64_t,
+                         double, std::allocator, nlohmann::adl_serializer, std::vector<std::uint8_t>, void >;
 } // namespace
 
 TEST_CASE("BSON")
@@ -105,10 +153,36 @@ TEST_CASE("BSON")
 
     SECTION("lengths exceeding INT32_MAX cannot be serialized to BSON")
     {
-        huge_binary_json j;
-        j["b"] = huge_binary_json::binary(huge_binary_t{});
+        // out_of_range.412 is thrown from a single shared helper
+        // (to_bson_length) that guards the BSON length fields of binary
+        // values, strings, and (embedded) documents alike
+        SECTION("binary")
+        {
+            huge_binary_json j;
+            j["b"] = huge_binary_json::binary(huge_binary_t{});
 
-        CHECK_THROWS_WITH_AS(huge_binary_json::to_bson(j), "[json.exception.out_of_range.412] BSON length 2147483661 exceeds maximum of 2147483647", huge_binary_json::out_of_range&);
+            CHECK_THROWS_WITH_AS(huge_binary_json::to_bson(j), "[json.exception.out_of_range.412] BSON length 2147483661 exceeds maximum of 2147483647", huge_binary_json::out_of_range&);
+        }
+
+        SECTION("string")
+        {
+            huge_string_json j;
+            j["s"] = huge_string_t::as_huge("value");
+
+            CHECK_THROWS_WITH_AS(huge_string_json::to_bson(j), "[json.exception.out_of_range.412] BSON length 2147483661 exceeds maximum of 2147483647", huge_string_json::out_of_range&);
+        }
+
+        SECTION("document")
+        {
+            // an oversized string nested one level deep makes the
+            // *embedded* document's own length exceed INT32_MAX as well
+            huge_string_json nested;
+            nested["s"] = huge_string_t::as_huge("value");
+            huge_string_json j;
+            j["nested"] = nested;
+
+            CHECK_THROWS_WITH_AS(huge_string_json::to_bson(j), "[json.exception.out_of_range.412] BSON length 2147483674 exceeds maximum of 2147483647", huge_string_json::out_of_range&);
+        }
     }
 
     SECTION("string length must be at least 1")
@@ -193,6 +267,23 @@ TEST_CASE("BSON")
             CHECK(json::from_bson(result, true, false) == j);
         }
 
+        SECTION("non-empty object with bool from a non-0/1 byte (lenient parsing)")
+        {
+            // documented lenient behavior (see gh-5333): any non-zero byte
+            // is accepted as `true`, not just 0x01
+            std::vector<std::uint8_t> const input =
+            {
+                0x0D, 0x00, 0x00, 0x00, // size (little endian)
+                0x08,               // entry: boolean
+                'e', 'n', 't', 'r', 'y', '\x00',
+                0x02,           // value = 0x02 (neither 0x00 nor 0x01)
+                0x00                    // end marker
+            };
+
+            const json expected = { { "entry", true } };
+            CHECK(json::from_bson(input) == expected);
+        }
+
         SECTION("non-empty object with double")
         {
             json const j =
@@ -499,6 +590,29 @@ TEST_CASE("BSON")
             CHECK(json::from_bson(result, true, false) == j);
         }
 
+        SECTION("array elements with non-conforming keys (lenient parsing)")
+        {
+            // documented lenient behavior (see gh-5333): BSON array element
+            // keys are not checked against the required decimal sequence
+            // "0", "1", "2", ... - elements are taken in encoded order
+            std::vector<std::uint8_t> const input =
+            {
+                0x26, 0x00, 0x00, 0x00, // size (little endian)
+                0x04, 'e', 'n', 't', 'r', 'y', '\x00', // entry: embedded array
+
+                0x1A, 0x00, 0x00, 0x00, // size (little endian)
+                0x10, '5', 0x00, 0x0A, 0x00, 0x00, 0x00, // key "5" (bogus)      -> 10
+                0x10, 'x', 0x00, 0x14, 0x00, 0x00, 0x00, // key "x" (non-numeric) -> 20
+                0x10, '1', 0x00, 0x1E, 0x00, 0x00, 0x00, // key "1" (out of order) -> 30
+                0x00, // end marker (embedded array)
+
+                0x00 // end marker
+            };
+
+            const json expected = { { "entry", json::array({10, 20, 30}) } };
+            CHECK(json::from_bson(input) == expected);
+        }
+
         SECTION("non-empty object with binary member")
         {
             const size_t N = 10;
@@ -594,6 +708,31 @@ TEST_CASE("BSON")
             CHECK(json::from_bson(result, true, false) == j);
         }
 
+        SECTION("binary member with subtype 0x02 (old binary) keeps its inner length prefix (lenient parsing)")
+        {
+            // documented lenient behavior (see gh-5333): the payload for
+            // binary subtype 0x02 ("old binary") is returned as-is,
+            // including its own inner 4-byte length prefix; it is not
+            // stripped or reinterpreted
+            std::vector<std::uint8_t> const input =
+            {
+                0x17, 0x00, 0x00, 0x00, // size (little endian)
+                0x05, 'e', 'n', 't', 'r', 'y', '\x00', // entry: binary
+
+                0x06, 0x00, 0x00, 0x00, // size of binary (little endian)
+                0x02, // "old binary" subtype
+                0x02, 0x00, 0x00, 0x00, // inner length prefix (part of the old-binary payload)
+                0x68, 0x69, // payload ('h', 'i')
+
+                0x00 // end marker
+            };
+
+            // the inner length prefix is part of the (unmodified) payload
+            const std::vector<std::uint8_t> expected_payload = {0x02, 0x00, 0x00, 0x00, 0x68, 0x69};
+            const json expected = { { "entry", json::binary(expected_payload, 0x02) } };
+            CHECK(json::from_bson(input) == expected);
+        }
+
         SECTION("Some more complex document")
         {
             json const j =

tests/src/unit-cbor.cpp

@@ -2035,58 +2035,6 @@ TEST_CASE("CBOR definite length equal to the indefinite-length sentinel")
     }
 }
 
-TEST_CASE("CBOR indefinite-length strings do not recurse per chunk")
-{
-    // Reading an indefinite-length string or byte array used to call itself
-    // once per chunk, so a payload of repeated 0x7F (or 0x5F) bytes exhausted
-    // the call stack before any of the input was rejected. The open levels are
-    // counted now, and the levels below prove the reader still reads the same
-    // values and reports the same errors at the same byte offsets.
-    json _;
-
-    SECTION("many open levels are reported, not crashed on")
-    {
-        const std::vector<uint8_t> input(200000, 0x7F);
-        CHECK_THROWS_WITH_AS(_ = json::from_cbor(input), "[json.exception.parse_error.110] parse error at byte 200001: syntax error while parsing CBOR string: unexpected end of input", json::parse_error&);
-        CHECK(json::from_cbor(input, true, false).is_discarded());
-    }
-
-    SECTION("many open levels are reported, not crashed on (binary)")
-    {
-        const std::vector<uint8_t> input(200000, 0x5F);
-        CHECK_THROWS_WITH_AS(_ = json::from_cbor(input), "[json.exception.parse_error.110] parse error at byte 200001: syntax error while parsing CBOR binary: unexpected end of input", json::parse_error&);
-        CHECK(json::from_cbor(input, true, false).is_discarded());
-    }
-
-    SECTION("chunks are still concatenated")
-    {
-        CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0xFF})) == json(""));
-        CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0x61, 0x61, 0xFF})) == json("a"));
-        // nested indefinite-length strings are concatenated across levels
-        CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0x7F, 0x61, 0x61, 0xFF, 0x61, 0x62, 0xFF})) == json("ab"));
-        CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0x7F, 0x7F, 0x61, 0x7A, 0xFF, 0xFF, 0xFF})) == json("z"));
-        CHECK(json::from_cbor(std::vector<uint8_t>({0xA1, 0x7F, 0x61, 0x61, 0xFF, 0x01})) == json({{"a", 1}}));
-    }
-
-    SECTION("chunks are still concatenated (binary)")
-    {
-        CHECK(json::from_cbor(std::vector<uint8_t>({0x5F, 0x41, 0x61, 0xFF})) == json::binary({0x61}));
-        CHECK(json::from_cbor(std::vector<uint8_t>({0x5F, 0x5F, 0x41, 0x61, 0xFF, 0x41, 0x62, 0xFF})) == json::binary({0x61, 0x62}));
-    }
-
-    SECTION("a chunk that is not a string is still rejected")
-    {
-        CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x7F, 0x7F, 0x00})), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing CBOR string: expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0x00", json::parse_error&);
-        CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x5F, 0x5F, 0x00})), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing CBOR binary: expected length specification (0x40-0x5B) or indefinite binary array type (0x5F); last byte: 0x00", json::parse_error&);
-    }
-
-    SECTION("a break marker outside an indefinite-length string is not a string")
-    {
-        // 0xFF only closes a string that was opened; on its own it is not one
-        CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xA1, 0xFF, 0x01})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR string: expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0xFF", json::parse_error&);
-    }
-}
-
 TEST_CASE("CBOR roundtrips" * doctest::skip())
 {
     SECTION("input from flynn")