Compare commits

..
Author SHA1 Message Date
Niels Lohmann 03270c6085 Avoid temporary-string concatenation flagged by clang-tidy in the differential test
Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-09-08 13:12:44 +02:00
Niels Lohmann 49291818de Document why the digit-count fast path is safe regardless of number_unsigned_t/number_integer_t width
Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-09-08 13:12:44 +02:00
Niels Lohmann 786419dca5 Skip integer conversion in accept()/SAX validation when the value is unused
lexer::scan_number() always converted every numeric token with
strtoull()/strtoll() before returning, even though accept() (and any
consumer using json_sax_acceptor) immediately discards the converted
value. For value_unsigned/value_integer tokens whose digit count
already guarantees the value fits into 64 bits, the conversion cannot
change the accept/reject decision (such tokens are always finite and
unconditionally accepted), so scan_number() can skip strtoull()/
strtoll() entirely in that case when the caller signals it does not
need the value. Numbers with more digits keep using the exact,
unmodified conversion path, so overflow reclassification to
value_float (and the finiteness check on it) is unaffected.

parse() and value_float handling are completely unchanged.

Fixes #5411

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-09-08 13:12:44 +02:00
7 changed files with 386 additions and 478 deletions
+49 -135
View File
@@ -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 This function first reads starting bytes to determine the expected
form, which that function handles itself. The bytes are appended to @a string length and then copies this number of bytes into a string.
result, so consecutive chunks of an indefinite-length string can be read Additionally, CBOR's strings with indefinite lengths are supported.
into the same string.
@param[out] result string the bytes are appended to @param[out] result created string
@return whether string creation completed @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) switch (current)
{ {
// UTF-8 string (0x00..0x17 bytes follow) // 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); 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: default:
{ {
auto last_token = get_token_string(); 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 This function first reads starting bytes to determine the expected
string length and then copies this number of bytes into a string. byte array length and then copies this number of bytes into the byte array.
Additionally, CBOR's strings with indefinite lengths are supported. Additionally, CBOR's byte arrays with indefinite lengths are supported.
@param[out] result created string @param[out] result created byte array
@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
@return whether byte array creation completed @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) switch (current)
{ {
// Binary data (0x00..0x17 bytes follow) // Binary data (0x00..0x17 bytes follow)
@@ -1211,6 +1168,20 @@ class binary_reader
get_binary(input_format_t::cbor, len, result); 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: default:
{ {
auto last_token = get_token_string(); 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 @brief narrow a definite CBOR array/map length to std::size_t
+61 -1
View File
@@ -149,10 +149,11 @@ class lexer : public lexer_base<BasicJsonType>
public: public:
using token_type = typename lexer_base<BasicJsonType>::token_type; using token_type = typename lexer_base<BasicJsonType>::token_type;
explicit lexer(InputAdapterType&& adapter, bool ignore_comments_ = false) noexcept explicit lexer(InputAdapterType&& adapter, bool ignore_comments_ = false, bool discard_number_values_ = false) noexcept
: ia(std::move(adapter)) : ia(std::move(adapter))
, ignore_comments(ignore_comments_) , ignore_comments(ignore_comments_)
, decimal_point_char(static_cast<char_int_type>(get_decimal_point())) , decimal_point_char(static_cast<char_int_type>(get_decimal_point()))
, discard_number_values(discard_number_values_)
{} {}
// deleted because of pointer members // deleted because of pointer members
@@ -1279,6 +1280,58 @@ scan_number_done:
// we are done scanning a number) // we are done scanning a number)
unget(); unget();
// If the caller does not need the converted value (only whether the
// input is syntactically valid; see json_sax_acceptor/accept()), an
// unsigned/integer token can be reported without calling
// strtoull()/strtoll() at all, *provided* we can already tell from
// the digit count alone that the conversion cannot overflow 64 bits.
// Such tokens are always finite and are accepted unconditionally by
// the parser regardless of their actual value (parser::sax_parse_internal()
// never checks finiteness for value_unsigned/value_integer), so the
// classification below is all that is needed.
//
// A decimal number with up to 18 digits is always representable in
// both std::uint64_t and std::int64_t (18 nines is ~1e18, well below
// both UINT64_MAX ~1.8e19 and INT64_MAX ~9.2e18), so strtoull()/strtoll()
// could not have set errno to ERANGE for it. Numbers with more digits
// (rare in practice) fall through to the exact code below, unchanged,
// so their handling -- including reclassification to value_float when
// the value overflows 64 bits, and rejection when it is not even
// finite as a double -- is bit-for-bit identical to before this
// optimization.
//
// Note this reasons about std::uint64_t/std::int64_t, not about
// number_unsigned_t/number_integer_t (BasicJsonType's own, possibly
// narrower, template parameters -- e.g. std::uint32_t). That is fine
// *only* because discard_number_values is exclusively set by
// accept() (see json.hpp), and accept() always parses through the
// library's own json_sax_acceptor -- never a user-supplied SAX
// consumer -- whose number_unsigned()/number_integer()/number_float()
// callbacks unconditionally discard their argument and return true.
// So for every caller that can reach this branch, neither the token
// classification below nor the eventual (possibly narrowed, and on
// this fast path left stale/unset) value_unsigned/value_integer is
// ever consulted -- an unsigned/integer token is accepted outright,
// and even a >18-digit token that this fast path deliberately falls
// through for is, once reclassified to value_float, still finite
// (and thus accepted) for any digit count that fits in number_unsigned_t
// or number_integer_t regardless of that type's width. If this
// function is ever taught to run with discard_number_values true for
// a caller that *does* read the converted value, this reasoning (and
// the fast path below) would need to be revisited.
if (discard_number_values)
{
constexpr std::size_t safe_digit_count = 18;
if (number_type == token_type::value_unsigned && token_buffer.size() <= safe_digit_count)
{
return token_type::value_unsigned;
}
if (number_type == token_type::value_integer && token_buffer.size() - 1 <= safe_digit_count)
{
return token_type::value_integer;
}
}
char* endptr = nullptr; // NOLINT(misc-const-correctness,cppcoreguidelines-pro-type-vararg,hicpp-vararg) char* endptr = nullptr; // NOLINT(misc-const-correctness,cppcoreguidelines-pro-type-vararg,hicpp-vararg)
errno = 0; errno = 0;
@@ -1754,6 +1807,13 @@ scan_number_done:
const char_int_type decimal_point_char = '.'; const char_int_type decimal_point_char = '.';
/// the position of the decimal point in the input /// the position of the decimal point in the input
std::size_t decimal_point_position = std::string::npos; std::size_t decimal_point_position = std::string::npos;
/// whether the caller (e.g. accept()/json_sax_acceptor) only needs the
/// token classification and never looks at the converted numeric value;
/// when set, scan_number() may skip strtoull()/strtoll() for
/// value_unsigned/value_integer tokens whose digit count guarantees they
/// fit into 64 bits (see scan_number())
const bool discard_number_values = false;
}; };
} // namespace detail } // namespace detail
+3 -2
View File
@@ -72,9 +72,10 @@ class parser
parser_callback_t<BasicJsonType> cb = nullptr, parser_callback_t<BasicJsonType> cb = nullptr,
const bool allow_exceptions_ = true, const bool allow_exceptions_ = true,
const bool ignore_comments = false, const bool ignore_comments = false,
const bool ignore_trailing_commas_ = false) const bool ignore_trailing_commas_ = false,
const bool discard_number_values_ = false)
: callback(std::move(cb)) : callback(std::move(cb))
, m_lexer(std::move(adapter), ignore_comments) , m_lexer(std::move(adapter), ignore_comments, discard_number_values_)
, allow_exceptions(allow_exceptions_) , allow_exceptions(allow_exceptions_)
, ignore_trailing_commas(ignore_trailing_commas_) , ignore_trailing_commas(ignore_trailing_commas_)
{ {
+34 -75
View File
@@ -164,11 +164,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
detail::parser_callback_t<basic_json>cb = nullptr, detail::parser_callback_t<basic_json>cb = nullptr,
const bool allow_exceptions = true, const bool allow_exceptions = true,
const bool ignore_comments = false, const bool ignore_comments = false,
const bool ignore_trailing_commas = false const bool ignore_trailing_commas = false,
const bool discard_number_values = false
) )
{ {
return ::nlohmann::detail::parser<basic_json, InputAdapterType>(std::move(adapter), return ::nlohmann::detail::parser<basic_json, InputAdapterType>(std::move(adapter),
std::move(cb), allow_exceptions, ignore_comments, ignore_trailing_commas); std::move(cb), allow_exceptions, ignore_comments, ignore_trailing_commas, discard_number_values);
} }
private: private:
@@ -4133,7 +4134,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
const bool ignore_comments = false, const bool ignore_comments = false,
const bool ignore_trailing_commas = false) const bool ignore_trailing_commas = false)
{ {
return parser(detail::input_adapter(std::forward<InputType>(i)), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true); return parser(detail::input_adapter(std::forward<InputType>(i)), nullptr, false, ignore_comments, ignore_trailing_commas, true).accept(true);
} }
/// @brief check if the input is valid JSON (iterator pair, or iterator+sentinel pair for C++20 ranges support) /// @brief check if the input is valid JSON (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4144,7 +4145,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
const bool ignore_comments = false, const bool ignore_comments = false,
const bool ignore_trailing_commas = false) const bool ignore_trailing_commas = false)
{ {
return parser(detail::input_adapter(std::move(first), std::move(last)), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true); return parser(detail::input_adapter(std::move(first), std::move(last)), nullptr, false, ignore_comments, ignore_trailing_commas, true).accept(true);
} }
JSON_HEDLEY_WARN_UNUSED_RESULT JSON_HEDLEY_WARN_UNUSED_RESULT
@@ -4153,7 +4154,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
const bool ignore_comments = false, const bool ignore_comments = false,
const bool ignore_trailing_commas = false) const bool ignore_trailing_commas = false)
{ {
return parser(i.get(), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true); return parser(i.get(), nullptr, false, ignore_comments, ignore_trailing_commas, true).accept(true);
} }
/// @brief generate SAX events /// @brief generate SAX events
@@ -4473,11 +4474,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
basic_json result; basic_json result;
auto ia = detail::input_adapter(std::forward<InputType>(i)); auto ia = detail::input_adapter(std::forward<InputType>(i));
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions); 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] 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);
result = value_t::discarded;
}
return result;
} }
/// @brief create a JSON value from an input in CBOR format (iterator pair, or iterator+sentinel pair for C++20 ranges support) /// @brief create a JSON value from an input in CBOR format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4493,11 +4491,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
basic_json result; basic_json result;
auto ia = detail::input_adapter(std::move(first), std::move(last)); auto ia = detail::input_adapter(std::move(first), std::move(last));
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions); 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] 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);
result = value_t::discarded;
}
return result;
} }
template<typename T> template<typename T>
@@ -4522,11 +4517,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
auto ia = i.get(); auto ia = i.get();
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions); detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
// NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg) // 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] 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);
result = value_t::discarded;
}
return result;
} }
/// @brief create a JSON value from an input in MessagePack format /// @brief create a JSON value from an input in MessagePack format
@@ -4540,11 +4532,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
basic_json result; basic_json result;
auto ia = detail::input_adapter(std::forward<InputType>(i)); auto ia = detail::input_adapter(std::forward<InputType>(i));
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions); 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] 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);
result = value_t::discarded;
}
return result;
} }
/// @brief create a JSON value from an input in MessagePack format (iterator pair, or iterator+sentinel pair for C++20 ranges support) /// @brief create a JSON value from an input in MessagePack format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4559,11 +4548,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
basic_json result; basic_json result;
auto ia = detail::input_adapter(std::move(first), std::move(last)); auto ia = detail::input_adapter(std::move(first), std::move(last));
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions); 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] 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);
result = value_t::discarded;
}
return result;
} }
template<typename T> template<typename T>
@@ -4586,11 +4572,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
auto ia = i.get(); auto ia = i.get();
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions); detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
// NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg) // 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] 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);
result = value_t::discarded;
}
return result;
} }
/// @brief create a JSON value from an input in UBJSON format /// @brief create a JSON value from an input in UBJSON format
@@ -4604,11 +4587,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
basic_json result; basic_json result;
auto ia = detail::input_adapter(std::forward<InputType>(i)); auto ia = detail::input_adapter(std::forward<InputType>(i));
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions); 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] 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);
result = value_t::discarded;
}
return result;
} }
/// @brief create a JSON value from an input in UBJSON format (iterator pair, or iterator+sentinel pair for C++20 ranges support) /// @brief create a JSON value from an input in UBJSON format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4623,11 +4603,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
basic_json result; basic_json result;
auto ia = detail::input_adapter(std::move(first), std::move(last)); auto ia = detail::input_adapter(std::move(first), std::move(last));
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions); 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] 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);
result = value_t::discarded;
}
return result;
} }
template<typename T> template<typename T>
@@ -4650,11 +4627,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
auto ia = i.get(); auto ia = i.get();
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions); detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
// NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg) // 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] 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);
result = value_t::discarded;
}
return result;
} }
/// @brief create a JSON value from an input in BJData format /// @brief create a JSON value from an input in BJData format
@@ -4668,11 +4642,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
basic_json result; basic_json result;
auto ia = detail::input_adapter(std::forward<InputType>(i)); auto ia = detail::input_adapter(std::forward<InputType>(i));
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions); 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] 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);
result = value_t::discarded;
}
return result;
} }
/// @brief create a JSON value from an input in BJData format (iterator pair, or iterator+sentinel pair for C++20 ranges support) /// @brief create a JSON value from an input in BJData format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4687,11 +4658,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
basic_json result; basic_json result;
auto ia = detail::input_adapter(std::move(first), std::move(last)); auto ia = detail::input_adapter(std::move(first), std::move(last));
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions); 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] 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);
result = value_t::discarded;
}
return result;
} }
/// @brief create a JSON value from an input in BSON format /// @brief create a JSON value from an input in BSON format
@@ -4705,11 +4673,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
basic_json result; basic_json result;
auto ia = detail::input_adapter(std::forward<InputType>(i)); auto ia = detail::input_adapter(std::forward<InputType>(i));
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions); 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] 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);
result = value_t::discarded;
}
return result;
} }
/// @brief create a JSON value from an input in BSON format (iterator pair, or iterator+sentinel pair for C++20 ranges support) /// @brief create a JSON value from an input in BSON format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4724,11 +4689,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
basic_json result; basic_json result;
auto ia = detail::input_adapter(std::move(first), std::move(last)); auto ia = detail::input_adapter(std::move(first), std::move(last));
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions); 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] 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);
result = value_t::discarded;
}
return result;
} }
template<typename T> template<typename T>
@@ -4751,11 +4713,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
auto ia = i.get(); auto ia = i.get();
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions); detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
// NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg) // 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] 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);
result = value_t::discarded;
}
return result;
} }
/// @} /// @}
+147 -213
View File
@@ -7932,10 +7932,11 @@ class lexer : public lexer_base<BasicJsonType>
public: public:
using token_type = typename lexer_base<BasicJsonType>::token_type; using token_type = typename lexer_base<BasicJsonType>::token_type;
explicit lexer(InputAdapterType&& adapter, bool ignore_comments_ = false) noexcept explicit lexer(InputAdapterType&& adapter, bool ignore_comments_ = false, bool discard_number_values_ = false) noexcept
: ia(std::move(adapter)) : ia(std::move(adapter))
, ignore_comments(ignore_comments_) , ignore_comments(ignore_comments_)
, decimal_point_char(static_cast<char_int_type>(get_decimal_point())) , decimal_point_char(static_cast<char_int_type>(get_decimal_point()))
, discard_number_values(discard_number_values_)
{} {}
// deleted because of pointer members // deleted because of pointer members
@@ -9062,6 +9063,58 @@ scan_number_done:
// we are done scanning a number) // we are done scanning a number)
unget(); unget();
// If the caller does not need the converted value (only whether the
// input is syntactically valid; see json_sax_acceptor/accept()), an
// unsigned/integer token can be reported without calling
// strtoull()/strtoll() at all, *provided* we can already tell from
// the digit count alone that the conversion cannot overflow 64 bits.
// Such tokens are always finite and are accepted unconditionally by
// the parser regardless of their actual value (parser::sax_parse_internal()
// never checks finiteness for value_unsigned/value_integer), so the
// classification below is all that is needed.
//
// A decimal number with up to 18 digits is always representable in
// both std::uint64_t and std::int64_t (18 nines is ~1e18, well below
// both UINT64_MAX ~1.8e19 and INT64_MAX ~9.2e18), so strtoull()/strtoll()
// could not have set errno to ERANGE for it. Numbers with more digits
// (rare in practice) fall through to the exact code below, unchanged,
// so their handling -- including reclassification to value_float when
// the value overflows 64 bits, and rejection when it is not even
// finite as a double -- is bit-for-bit identical to before this
// optimization.
//
// Note this reasons about std::uint64_t/std::int64_t, not about
// number_unsigned_t/number_integer_t (BasicJsonType's own, possibly
// narrower, template parameters -- e.g. std::uint32_t). That is fine
// *only* because discard_number_values is exclusively set by
// accept() (see json.hpp), and accept() always parses through the
// library's own json_sax_acceptor -- never a user-supplied SAX
// consumer -- whose number_unsigned()/number_integer()/number_float()
// callbacks unconditionally discard their argument and return true.
// So for every caller that can reach this branch, neither the token
// classification below nor the eventual (possibly narrowed, and on
// this fast path left stale/unset) value_unsigned/value_integer is
// ever consulted -- an unsigned/integer token is accepted outright,
// and even a >18-digit token that this fast path deliberately falls
// through for is, once reclassified to value_float, still finite
// (and thus accepted) for any digit count that fits in number_unsigned_t
// or number_integer_t regardless of that type's width. If this
// function is ever taught to run with discard_number_values true for
// a caller that *does* read the converted value, this reasoning (and
// the fast path below) would need to be revisited.
if (discard_number_values)
{
constexpr std::size_t safe_digit_count = 18;
if (number_type == token_type::value_unsigned && token_buffer.size() <= safe_digit_count)
{
return token_type::value_unsigned;
}
if (number_type == token_type::value_integer && token_buffer.size() - 1 <= safe_digit_count)
{
return token_type::value_integer;
}
}
char* endptr = nullptr; // NOLINT(misc-const-correctness,cppcoreguidelines-pro-type-vararg,hicpp-vararg) char* endptr = nullptr; // NOLINT(misc-const-correctness,cppcoreguidelines-pro-type-vararg,hicpp-vararg)
errno = 0; errno = 0;
@@ -9537,6 +9590,13 @@ scan_number_done:
const char_int_type decimal_point_char = '.'; const char_int_type decimal_point_char = '.';
/// the position of the decimal point in the input /// the position of the decimal point in the input
std::size_t decimal_point_position = std::string::npos; std::size_t decimal_point_position = std::string::npos;
/// whether the caller (e.g. accept()/json_sax_acceptor) only needs the
/// token classification and never looks at the converted numeric value;
/// when set, scan_number() may skip strtoull()/strtoll() for
/// value_unsigned/value_integer tokens whose digit count guarantees they
/// fit into 64 bits (see scan_number())
const bool discard_number_values = false;
}; };
} // namespace detail } // namespace detail
@@ -11683,21 +11743,23 @@ 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 This function first reads starting bytes to determine the expected
form, which that function handles itself. The bytes are appended to @a string length and then copies this number of bytes into a string.
result, so consecutive chunks of an indefinite-length string can be read Additionally, CBOR's strings with indefinite lengths are supported.
into the same string.
@param[out] result string the bytes are appended to @param[out] result created string
@return whether string creation completed @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) switch (current)
{ {
// UTF-8 string (0x00..0x17 bytes follow) // UTF-8 string (0x00..0x17 bytes follow)
@@ -11753,6 +11815,20 @@ class binary_reader
return get_number(input_format_t::cbor, len) && get_string(input_format_t::cbor, len, result); 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: default:
{ {
auto last_token = get_token_string(); auto last_token = get_token_string();
@@ -11763,82 +11839,23 @@ class binary_reader
} }
/*! /*!
@brief reads a CBOR string @brief reads a CBOR byte array
This function first reads starting bytes to determine the expected This function first reads starting bytes to determine the expected
string length and then copies this number of bytes into a string. byte array length and then copies this number of bytes into the byte array.
Additionally, CBOR's strings with indefinite lengths are supported. Additionally, CBOR's byte arrays with indefinite lengths are supported.
@param[out] result created string @param[out] result created byte array
@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
@return whether byte array creation completed @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) switch (current)
{ {
// Binary data (0x00..0x17 bytes follow) // Binary data (0x00..0x17 bytes follow)
@@ -11898,6 +11915,20 @@ class binary_reader
get_binary(input_format_t::cbor, len, result); 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: default:
{ {
auto last_token = get_token_string(); auto last_token = get_token_string();
@@ -11907,63 +11938,6 @@ 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 @brief narrow a definite CBOR array/map length to std::size_t
@@ -14129,9 +14103,10 @@ class parser
parser_callback_t<BasicJsonType> cb = nullptr, parser_callback_t<BasicJsonType> cb = nullptr,
const bool allow_exceptions_ = true, const bool allow_exceptions_ = true,
const bool ignore_comments = false, const bool ignore_comments = false,
const bool ignore_trailing_commas_ = false) const bool ignore_trailing_commas_ = false,
const bool discard_number_values_ = false)
: callback(std::move(cb)) : callback(std::move(cb))
, m_lexer(std::move(adapter), ignore_comments) , m_lexer(std::move(adapter), ignore_comments, discard_number_values_)
, allow_exceptions(allow_exceptions_) , allow_exceptions(allow_exceptions_)
, ignore_trailing_commas(ignore_trailing_commas_) , ignore_trailing_commas(ignore_trailing_commas_)
{ {
@@ -21678,11 +21653,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
detail::parser_callback_t<basic_json>cb = nullptr, detail::parser_callback_t<basic_json>cb = nullptr,
const bool allow_exceptions = true, const bool allow_exceptions = true,
const bool ignore_comments = false, const bool ignore_comments = false,
const bool ignore_trailing_commas = false const bool ignore_trailing_commas = false,
const bool discard_number_values = false
) )
{ {
return ::nlohmann::detail::parser<basic_json, InputAdapterType>(std::move(adapter), return ::nlohmann::detail::parser<basic_json, InputAdapterType>(std::move(adapter),
std::move(cb), allow_exceptions, ignore_comments, ignore_trailing_commas); std::move(cb), allow_exceptions, ignore_comments, ignore_trailing_commas, discard_number_values);
} }
private: private:
@@ -25647,7 +25623,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
const bool ignore_comments = false, const bool ignore_comments = false,
const bool ignore_trailing_commas = false) const bool ignore_trailing_commas = false)
{ {
return parser(detail::input_adapter(std::forward<InputType>(i)), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true); return parser(detail::input_adapter(std::forward<InputType>(i)), nullptr, false, ignore_comments, ignore_trailing_commas, true).accept(true);
} }
/// @brief check if the input is valid JSON (iterator pair, or iterator+sentinel pair for C++20 ranges support) /// @brief check if the input is valid JSON (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -25658,7 +25634,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
const bool ignore_comments = false, const bool ignore_comments = false,
const bool ignore_trailing_commas = false) const bool ignore_trailing_commas = false)
{ {
return parser(detail::input_adapter(std::move(first), std::move(last)), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true); return parser(detail::input_adapter(std::move(first), std::move(last)), nullptr, false, ignore_comments, ignore_trailing_commas, true).accept(true);
} }
JSON_HEDLEY_WARN_UNUSED_RESULT JSON_HEDLEY_WARN_UNUSED_RESULT
@@ -25667,7 +25643,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
const bool ignore_comments = false, const bool ignore_comments = false,
const bool ignore_trailing_commas = false) const bool ignore_trailing_commas = false)
{ {
return parser(i.get(), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true); return parser(i.get(), nullptr, false, ignore_comments, ignore_trailing_commas, true).accept(true);
} }
/// @brief generate SAX events /// @brief generate SAX events
@@ -25987,11 +25963,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
basic_json result; basic_json result;
auto ia = detail::input_adapter(std::forward<InputType>(i)); auto ia = detail::input_adapter(std::forward<InputType>(i));
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions); 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] 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);
result = value_t::discarded;
}
return result;
} }
/// @brief create a JSON value from an input in CBOR format (iterator pair, or iterator+sentinel pair for C++20 ranges support) /// @brief create a JSON value from an input in CBOR format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -26007,11 +25980,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
basic_json result; basic_json result;
auto ia = detail::input_adapter(std::move(first), std::move(last)); auto ia = detail::input_adapter(std::move(first), std::move(last));
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions); 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] 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);
result = value_t::discarded;
}
return result;
} }
template<typename T> template<typename T>
@@ -26036,11 +26006,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
auto ia = i.get(); auto ia = i.get();
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions); detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
// NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg) // 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] 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);
result = value_t::discarded;
}
return result;
} }
/// @brief create a JSON value from an input in MessagePack format /// @brief create a JSON value from an input in MessagePack format
@@ -26054,11 +26021,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
basic_json result; basic_json result;
auto ia = detail::input_adapter(std::forward<InputType>(i)); auto ia = detail::input_adapter(std::forward<InputType>(i));
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions); 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] 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);
result = value_t::discarded;
}
return result;
} }
/// @brief create a JSON value from an input in MessagePack format (iterator pair, or iterator+sentinel pair for C++20 ranges support) /// @brief create a JSON value from an input in MessagePack format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -26073,11 +26037,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
basic_json result; basic_json result;
auto ia = detail::input_adapter(std::move(first), std::move(last)); auto ia = detail::input_adapter(std::move(first), std::move(last));
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions); 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] 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);
result = value_t::discarded;
}
return result;
} }
template<typename T> template<typename T>
@@ -26100,11 +26061,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
auto ia = i.get(); auto ia = i.get();
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions); detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
// NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg) // 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] 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);
result = value_t::discarded;
}
return result;
} }
/// @brief create a JSON value from an input in UBJSON format /// @brief create a JSON value from an input in UBJSON format
@@ -26118,11 +26076,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
basic_json result; basic_json result;
auto ia = detail::input_adapter(std::forward<InputType>(i)); auto ia = detail::input_adapter(std::forward<InputType>(i));
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions); 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] 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);
result = value_t::discarded;
}
return result;
} }
/// @brief create a JSON value from an input in UBJSON format (iterator pair, or iterator+sentinel pair for C++20 ranges support) /// @brief create a JSON value from an input in UBJSON format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -26137,11 +26092,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
basic_json result; basic_json result;
auto ia = detail::input_adapter(std::move(first), std::move(last)); auto ia = detail::input_adapter(std::move(first), std::move(last));
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions); 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] 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);
result = value_t::discarded;
}
return result;
} }
template<typename T> template<typename T>
@@ -26164,11 +26116,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
auto ia = i.get(); auto ia = i.get();
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions); detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
// NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg) // 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] 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);
result = value_t::discarded;
}
return result;
} }
/// @brief create a JSON value from an input in BJData format /// @brief create a JSON value from an input in BJData format
@@ -26182,11 +26131,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
basic_json result; basic_json result;
auto ia = detail::input_adapter(std::forward<InputType>(i)); auto ia = detail::input_adapter(std::forward<InputType>(i));
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions); 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] 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);
result = value_t::discarded;
}
return result;
} }
/// @brief create a JSON value from an input in BJData format (iterator pair, or iterator+sentinel pair for C++20 ranges support) /// @brief create a JSON value from an input in BJData format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -26201,11 +26147,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
basic_json result; basic_json result;
auto ia = detail::input_adapter(std::move(first), std::move(last)); auto ia = detail::input_adapter(std::move(first), std::move(last));
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions); 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] 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);
result = value_t::discarded;
}
return result;
} }
/// @brief create a JSON value from an input in BSON format /// @brief create a JSON value from an input in BSON format
@@ -26219,11 +26162,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
basic_json result; basic_json result;
auto ia = detail::input_adapter(std::forward<InputType>(i)); auto ia = detail::input_adapter(std::forward<InputType>(i));
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions); 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] 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);
result = value_t::discarded;
}
return result;
} }
/// @brief create a JSON value from an input in BSON format (iterator pair, or iterator+sentinel pair for C++20 ranges support) /// @brief create a JSON value from an input in BSON format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -26238,11 +26178,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
basic_json result; basic_json result;
auto ia = detail::input_adapter(std::move(first), std::move(last)); auto ia = detail::input_adapter(std::move(first), std::move(last));
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions); 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] 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);
result = value_t::discarded;
}
return result;
} }
template<typename T> template<typename T>
@@ -26265,11 +26202,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
auto ia = i.get(); auto ia = i.get();
detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions); detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
// NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg) // 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] 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);
result = value_t::discarded;
}
return result;
} }
/// @} /// @}
-52
View File
@@ -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()) TEST_CASE("CBOR roundtrips" * doctest::skip())
{ {
SECTION("input from flynn") SECTION("input from flynn")
+92
View File
@@ -930,6 +930,98 @@ TEST_CASE("parser class")
CHECK(accept_helper("+1") == false); CHECK(accept_helper("+1") == false);
CHECK(accept_helper("+0") == false); CHECK(accept_helper("+0") == false);
} }
SECTION("issue #5411 - skip conversion when accept() does not need the numeric value")
{
// lexer::scan_number() may skip strtoull()/strtoll() for
// value_unsigned/value_integer tokens when the caller (e.g.
// json::accept()) does not need the converted value, as long
// as the digit count alone guarantees no 64-bit overflow (see
// the "safe_digit_count" fast path in scan_number()). This
// differential test checks that json::accept() (which enables
// the fast path) and json::parse() (which never does) always
// agree, over a corpus that exercises both the fast path
// (<=18 digits) and the untouched, exact fallback path (>=19
// digits) -- including reclassification of huge digit-only
// integers to a (possibly non-finite) floating-point value.
const std::vector<std::pair<std::string, bool>> cases =
{
// normal small/large integers, both signs
{"0", true}, {"1", true}, {"-1", true}, {"42", true}, {"-42", true},
{"123456789", true}, {"-123456789", true},
// digit-count boundary around the 18-digit safe cutoff (both signs)
{std::string(17, '9'), true},
{std::string(18, '9'), true},
{std::string(19, '9'), true},
{std::string(20, '9'), true},
{"-" + std::string(17, '9'), true},
{"-" + std::string(18, '9'), true},
{"-" + std::string(19, '9'), true},
{"-" + std::string(20, '9'), true},
// 64-bit boundaries
{"9223372036854775807", true}, // INT64_MAX
{"-9223372036854775808", true}, // INT64_MIN
{"18446744073709551615", true}, // UINT64_MAX
{"18446744073709551616", true}, // UINT64_MAX + 1 (overflows uint64_t, finite double)
// the 28-digit example from the issue: overflows uint64_t
// but is finite as a double, so the scanner reclassifies
// it to value_float and it is accepted
{"9999999999999999999999999999", true},
// huge digit-only integers that overflow even a double -> rejected
{std::string(309, '9'), false},
{std::string(400, '9'), false},
{"1" + std::string(400, '0'), false},
// 1e999 / 1e400 style overflow -> rejected
{"1e999", false},
{"1e400", false},
{"-1e999", false},
{"1E999", false},
// values straddling DBL_MAX
{"1.7976931348623157e308", true}, // <= DBL_MAX, finite
{"1.7976931348623159e308", false}, // > DBL_MAX, overflows to inf
// a mix of other valid/invalid numeric syntax
{"3.14159", true},
{"-0.0", true},
{"1.0e10", true},
{"01", false},
{"-", false},
{"1.", false},
{"1e", false},
{"+1", false},
};
for (const auto& c : cases)
{
const std::string& number = c.first;
const bool expected = c.second;
CAPTURE(number)
CAPTURE(expected)
// accept() takes the fast path (skips conversion when possible)
CHECK(json::accept(number) == expected);
// parse() always performs the full conversion; it must agree
json j;
CHECK_NOTHROW(json::parser(nlohmann::detail::input_adapter(number), nullptr, false).parse(true, j));
CHECK(!j.is_discarded() == expected);
// wrap in an array so get_token() is exercised beyond the
// very first (constructor-time) scan as well
std::string wrapped = "[";
wrapped += number;
wrapped += ",";
wrapped += number;
wrapped += "]";
CHECK(json::accept(wrapped) == expected);
}
}
} }
} }