Skip to content

Commit

Permalink
change bjdata ndarray flag to detect negative size, as part of #3475 (#…
Browse files Browse the repository at this point in the history 
…3479)

* change bjdata ndarray flag to detect negative size, fix #3475

* fix CI error

* fix CI on 32bit windows

* remove platform specific out_of_range error messages

* Incorporate suggestions from @nlohmann and @falbrechtskirchinger

* fix CI errors

* add coverage

* fix sax event order

* fix coverage
  • Loading branch information
@fangq
fangq authored May 10, 2022
1 parent d6efe67 commit a8a547d
Show file tree
Hide file tree
Showing 3 changed files with 144 additions and 42 deletions.
55 changes: 40 additions & 15 deletions include/nlohmann/detail/input/binary_reader.hpp
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1938,6 +1938,7 @@ class binary_reader
{
std::pair<std::size_t, char_int_type> size_and_type;
size_t dimlen = 0;
bool is_ndarray = false;

if (JSON_HEDLEY_UNLIKELY(!get_ubjson_size_type(size_and_type)))
{
Expand All @@ -1952,7 +1953,7 @@ class binary_reader
{
for (std::size_t i = 0; i < size_and_type.first; ++i)
{
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_size_value(dimlen, size_and_type.second)))
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_size_value(dimlen, is_ndarray, size_and_type.second)))
{
return false;
}
Expand All @@ -1964,7 +1965,7 @@ class binary_reader
{
for (std::size_t i = 0; i < size_and_type.first; ++i)
{
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_size_value(dimlen)))
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_size_value(dimlen, is_ndarray)))
{
return false;
}
Expand All @@ -1976,7 +1977,7 @@ class binary_reader
{
while (current != ']')
{
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_size_value(dimlen, current)))
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_size_value(dimlen, is_ndarray, current)))
{
return false;
}
Expand All @@ -1991,8 +1992,9 @@ class binary_reader
@param[out] result determined size
@return whether size determination completed
*/
bool get_ubjson_size_value(std::size_t& result, char_int_type prefix = 0)
bool get_ubjson_size_value(std::size_t& result, bool& is_ndarray, char_int_type prefix = 0)
{
is_ndarray = false;
if (prefix == 0)
{
prefix = get_ignore_noop();
Expand Down Expand Up @@ -2132,7 +2134,7 @@ class binary_reader
return false;
}
}
result |= (1ull << (sizeof(result) * 8 - 1)); // low 63 bit of result stores the total element count, sign-bit indicates ndarray
is_ndarray = true;
return sax->end_array();
}
result = 0;
Expand Down Expand Up @@ -2168,6 +2170,7 @@ class binary_reader
*/
bool get_ubjson_size_type(std::pair<std::size_t, char_int_type>& result)
{
bool is_ndarray = false;
result.first = string_t::npos; // size
result.second = 0; // type

Expand All @@ -2185,7 +2188,7 @@ class binary_reader
exception_message(input_format, concat("marker 0x", last_token, " is not a permitted optimized array type"), "type"), nullptr));
}

if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format, "type") || (input_format == input_format_t::bjdata && std::find(bjdx.begin(), bjdx.end(), result.second) != bjdx.end() )))
if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format, "type")))
{
return false;
}
Expand All @@ -2202,12 +2205,22 @@ class binary_reader
exception_message(input_format, concat("expected '#' after type information; last byte: 0x", last_token), "size"), nullptr));
}

return get_ubjson_size_value(result.first);
bool is_error = get_ubjson_size_value(result.first, is_ndarray);
if (input_format == input_format_t::bjdata && is_ndarray)
{
result.second |= (1 << 8); // use bit 8 to indicate ndarray, all UBJSON and BJData markers should be ASCII letters
}
return is_error;
}

if (current == '#')
{
return get_ubjson_size_value(result.first);
bool is_error = get_ubjson_size_value(result.first, is_ndarray);
if (input_format == input_format_t::bjdata && is_ndarray)
{
result.second |= (1 << 8); // use bit 8 to indicate ndarray, all UBJSON and BJData markers should be ASCII letters
}
return is_error;
}

return true;
Expand Down Expand Up @@ -2408,17 +2421,26 @@ class binary_reader
return false;
}

// detect and encode bjdata ndarray as an object in JData annotated array format (https://github.com/NeuroJSON/jdata):
// if bit-8 of size_and_type.second is set to 1, encode bjdata ndarray as an object in JData annotated array format (https://github.com/NeuroJSON/jdata):
// {"_ArrayType_" : "typeid", "_ArraySize_" : [n1, n2, ...], "_ArrayData_" : [v1, v2, ...]}

if (input_format == input_format_t::bjdata && size_and_type.first != string_t::npos && size_and_type.first >= (1ull << (sizeof(std::size_t) * 8 - 1)))
if (input_format == input_format_t::bjdata && size_and_type.first != string_t::npos && (size_and_type.second & (1 << 8)) != 0)
{
std::map<char_int_type, string_t> bjdtype = {{'U', "uint8"}, {'i', "int8"}, {'u', "uint16"}, {'I', "int16"},
{'m', "uint32"}, {'l', "int32"}, {'M', "uint64"}, {'L', "int64"}, {'d', "single"}, {'D', "double"}, {'C', "char"}
};

size_and_type.second &= ~(static_cast<char_int_type>(1) << 8); // use bit 8 to indicate ndarray, here we remove the bit to restore the type marker

string_t key = "_ArrayType_";
if (JSON_HEDLEY_UNLIKELY(bjdtype.count(size_and_type.second) == 0 || !sax->key(key) || !sax->string(bjdtype[size_and_type.second]) ))
if (JSON_HEDLEY_UNLIKELY(bjdtype.count(size_and_type.second) == 0))
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(input_format, "invalid byte: 0x" + last_token, "type"), nullptr));
}

if (JSON_HEDLEY_UNLIKELY(!sax->key(key) || !sax->string(bjdtype[size_and_type.second]) ))
{
return false;
}
Expand All @@ -2428,7 +2450,6 @@ class binary_reader
size_and_type.second = 'U';
}

size_and_type.first &= ~(1ull << (sizeof(std::size_t) * 8 - 1));
key = "_ArrayData_";
if (JSON_HEDLEY_UNLIKELY(!sax->key(key) || !sax->start_array(size_and_type.first) ))
{
Expand Down Expand Up @@ -2508,9 +2529,12 @@ class binary_reader
return false;
}

if (input_format == input_format_t::bjdata && size_and_type.first != string_t::npos && size_and_type.first >= (1ull << (sizeof(std::size_t) * 8 - 1)))
// do not accept ND-array size in objects in BJData
if (input_format == input_format_t::bjdata && size_and_type.first != string_t::npos && (size_and_type.second & (1 << 8)) != 0)
{
return false;
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(input_format, "BJData object does not support ND-array size in optimized format", "object"), nullptr));
}

string_t key;
Expand Down Expand Up @@ -2584,7 +2608,8 @@ class binary_reader
{
// get size of following number string
std::size_t size{};
auto res = get_ubjson_size_value(size);
bool is_ndarray = false;
auto res = get_ubjson_size_value(size, is_ndarray);
if (JSON_HEDLEY_UNLIKELY(!res))
{
return res;
Expand Down
55 changes: 40 additions & 15 deletions single_include/nlohmann/json.hpp
View file
Original file line number Diff line number Diff line change
Expand Up @@ -10412,6 +10412,7 @@ class binary_reader
{
std::pair<std::size_t, char_int_type> size_and_type;
size_t dimlen = 0;
bool is_ndarray = false;

if (JSON_HEDLEY_UNLIKELY(!get_ubjson_size_type(size_and_type)))
{
Expand All @@ -10426,7 +10427,7 @@ class binary_reader
{
for (std::size_t i = 0; i < size_and_type.first; ++i)
{
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_size_value(dimlen, size_and_type.second)))
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_size_value(dimlen, is_ndarray, size_and_type.second)))
{
return false;
}
Expand All @@ -10438,7 +10439,7 @@ class binary_reader
{
for (std::size_t i = 0; i < size_and_type.first; ++i)
{
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_size_value(dimlen)))
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_size_value(dimlen, is_ndarray)))
{
return false;
}
Expand All @@ -10450,7 +10451,7 @@ class binary_reader
{
while (current != ']')
{
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_size_value(dimlen, current)))
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_size_value(dimlen, is_ndarray, current)))
{
return false;
}
Expand All @@ -10465,8 +10466,9 @@ class binary_reader
@param[out] result determined size
@return whether size determination completed
*/
bool get_ubjson_size_value(std::size_t& result, char_int_type prefix = 0)
bool get_ubjson_size_value(std::size_t& result, bool& is_ndarray, char_int_type prefix = 0)
{
is_ndarray = false;
if (prefix == 0)
{
prefix = get_ignore_noop();
Expand Down Expand Up @@ -10606,7 +10608,7 @@ class binary_reader
return false;
}
}
result |= (1ull << (sizeof(result) * 8 - 1)); // low 63 bit of result stores the total element count, sign-bit indicates ndarray
is_ndarray = true;
return sax->end_array();
}
result = 0;
Expand Down Expand Up @@ -10642,6 +10644,7 @@ class binary_reader
*/
bool get_ubjson_size_type(std::pair<std::size_t, char_int_type>& result)
{
bool is_ndarray = false;
result.first = string_t::npos; // size
result.second = 0; // type

Expand All @@ -10659,7 +10662,7 @@ class binary_reader
exception_message(input_format, concat("marker 0x", last_token, " is not a permitted optimized array type"), "type"), nullptr));
}

if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format, "type") || (input_format == input_format_t::bjdata && std::find(bjdx.begin(), bjdx.end(), result.second) != bjdx.end() )))
if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format, "type")))
{
return false;
}
Expand All @@ -10676,12 +10679,22 @@ class binary_reader
exception_message(input_format, concat("expected '#' after type information; last byte: 0x", last_token), "size"), nullptr));
}

return get_ubjson_size_value(result.first);
bool is_error = get_ubjson_size_value(result.first, is_ndarray);
if (input_format == input_format_t::bjdata && is_ndarray)
{
result.second |= (1 << 8); // use bit 8 to indicate ndarray, all UBJSON and BJData markers should be ASCII letters
}
return is_error;
}

if (current == '#')
{
return get_ubjson_size_value(result.first);
bool is_error = get_ubjson_size_value(result.first, is_ndarray);
if (input_format == input_format_t::bjdata && is_ndarray)
{
result.second |= (1 << 8); // use bit 8 to indicate ndarray, all UBJSON and BJData markers should be ASCII letters
}
return is_error;
}

return true;
Expand Down Expand Up @@ -10882,17 +10895,26 @@ class binary_reader
return false;
}

// detect and encode bjdata ndarray as an object in JData annotated array format (https://github.com/NeuroJSON/jdata):
// if bit-8 of size_and_type.second is set to 1, encode bjdata ndarray as an object in JData annotated array format (https://github.com/NeuroJSON/jdata):
// {"_ArrayType_" : "typeid", "_ArraySize_" : [n1, n2, ...], "_ArrayData_" : [v1, v2, ...]}

if (input_format == input_format_t::bjdata && size_and_type.first != string_t::npos && size_and_type.first >= (1ull << (sizeof(std::size_t) * 8 - 1)))
if (input_format == input_format_t::bjdata && size_and_type.first != string_t::npos && (size_and_type.second & (1 << 8)) != 0)
{
std::map<char_int_type, string_t> bjdtype = {{'U', "uint8"}, {'i', "int8"}, {'u', "uint16"}, {'I', "int16"},
{'m', "uint32"}, {'l', "int32"}, {'M', "uint64"}, {'L', "int64"}, {'d', "single"}, {'D', "double"}, {'C', "char"}
};

size_and_type.second &= ~(static_cast<char_int_type>(1) << 8); // use bit 8 to indicate ndarray, here we remove the bit to restore the type marker

string_t key = "_ArrayType_";
if (JSON_HEDLEY_UNLIKELY(bjdtype.count(size_and_type.second) == 0 || !sax->key(key) || !sax->string(bjdtype[size_and_type.second]) ))
if (JSON_HEDLEY_UNLIKELY(bjdtype.count(size_and_type.second) == 0))
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(input_format, "invalid byte: 0x" + last_token, "type"), nullptr));
}

if (JSON_HEDLEY_UNLIKELY(!sax->key(key) || !sax->string(bjdtype[size_and_type.second]) ))
{
return false;
}
Expand All @@ -10902,7 +10924,6 @@ class binary_reader
size_and_type.second = 'U';
}

size_and_type.first &= ~(1ull << (sizeof(std::size_t) * 8 - 1));
key = "_ArrayData_";
if (JSON_HEDLEY_UNLIKELY(!sax->key(key) || !sax->start_array(size_and_type.first) ))
{
Expand Down Expand Up @@ -10982,9 +11003,12 @@ class binary_reader
return false;
}

if (input_format == input_format_t::bjdata && size_and_type.first != string_t::npos && size_and_type.first >= (1ull << (sizeof(std::size_t) * 8 - 1)))
// do not accept ND-array size in objects in BJData
if (input_format == input_format_t::bjdata && size_and_type.first != string_t::npos && (size_and_type.second & (1 << 8)) != 0)
{
return false;
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(input_format, "BJData object does not support ND-array size in optimized format", "object"), nullptr));
}

string_t key;
Expand Down Expand Up @@ -11058,7 +11082,8 @@ class binary_reader
{
// get size of following number string
std::size_t size{};
auto res = get_ubjson_size_value(size);
bool is_ndarray = false;
auto res = get_ubjson_size_value(size, is_ndarray);
if (JSON_HEDLEY_UNLIKELY(!res))
{
return res;
Expand Down
Loading

0 comments on commit a8a547d

Please sign in to comment.