mirror of
https://github.com/nlohmann/json.git
synced 2026-09-06 08:17:59 +00:00
Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
ef97a360c8 | ||
|
|
7b648c7dc4 |
@@ -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
|
||||||
|
|||||||
@@ -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_)
|
||||||
{
|
{
|
||||||
|
|||||||
@@ -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
|
||||||
|
|||||||
@@ -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
|
||||||
@@ -14043,9 +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_)
|
||||||
{
|
{
|
||||||
@@ -21592,11 +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:
|
||||||
@@ -25561,7 +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)
|
||||||
@@ -25572,7 +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
|
||||||
@@ -25581,7 +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
|
||||||
|
|||||||
+3
-114
@@ -38,26 +38,6 @@ class huge_binary_t : public std::vector<std::uint8_t>
|
|||||||
using huge_binary_json = nlohmann::basic_json <
|
using huge_binary_json = nlohmann::basic_json <
|
||||||
std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t,
|
std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t,
|
||||||
double, std::allocator, nlohmann::adl_serializer, huge_binary_t, void >;
|
double, std::allocator, nlohmann::adl_serializer, huge_binary_t, void >;
|
||||||
|
|
||||||
// a string type that reports 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
|
|
||||||
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)
|
|
||||||
|
|
||||||
size_type size() const noexcept // NOLINT(readability-convert-member-functions-to-static)
|
|
||||||
{
|
|
||||||
// one byte more than the BSON length field can represent
|
|
||||||
return static_cast<size_type>((std::numeric_limits<std::int32_t>::max)()) + 1;
|
|
||||||
}
|
|
||||||
};
|
|
||||||
|
|
||||||
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
|
} // namespace
|
||||||
|
|
||||||
TEST_CASE("BSON")
|
TEST_CASE("BSON")
|
||||||
@@ -125,36 +105,10 @@ TEST_CASE("BSON")
|
|||||||
|
|
||||||
SECTION("lengths exceeding INT32_MAX cannot be serialized to BSON")
|
SECTION("lengths exceeding INT32_MAX cannot be serialized to BSON")
|
||||||
{
|
{
|
||||||
// out_of_range.412 is thrown from a single shared helper
|
huge_binary_json j;
|
||||||
// (to_bson_length) that guards the BSON length fields of binary
|
j["b"] = huge_binary_json::binary(huge_binary_t{});
|
||||||
// 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_json::string_t("value");
|
|
||||||
|
|
||||||
CHECK_THROWS_WITH_AS(huge_string_json::to_bson(j), "[json.exception.out_of_range.412] BSON length 4294967308 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_json::string_t("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 6442450963 exceeds maximum of 2147483647", huge_string_json::out_of_range&);
|
|
||||||
}
|
|
||||||
}
|
}
|
||||||
|
|
||||||
SECTION("string length must be at least 1")
|
SECTION("string length must be at least 1")
|
||||||
@@ -239,23 +193,6 @@ TEST_CASE("BSON")
|
|||||||
CHECK(json::from_bson(result, true, false) == j);
|
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")
|
SECTION("non-empty object with double")
|
||||||
{
|
{
|
||||||
json const j =
|
json const j =
|
||||||
@@ -562,29 +499,6 @@ TEST_CASE("BSON")
|
|||||||
CHECK(json::from_bson(result, true, false) == j);
|
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")
|
SECTION("non-empty object with binary member")
|
||||||
{
|
{
|
||||||
const size_t N = 10;
|
const size_t N = 10;
|
||||||
@@ -680,31 +594,6 @@ TEST_CASE("BSON")
|
|||||||
CHECK(json::from_bson(result, true, false) == j);
|
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")
|
SECTION("Some more complex document")
|
||||||
{
|
{
|
||||||
json const j =
|
json const j =
|
||||||
|
|||||||
@@ -930,6 +930,94 @@ 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
|
||||||
|
const std::string wrapped = "[" + number + "," + number + "]";
|
||||||
|
CHECK(json::accept(wrapped) == expected);
|
||||||
|
}
|
||||||
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user