amorfo77/json
1
0
Fork 0
mirror of https://github.com/nlohmann/json.git synced 2026-09-06 08:17:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

Skip integer conversion in accept()/SAX validation when the value is unused

Browse Source 
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>
This commit is contained in:
Niels Lohmann
2026-09-05 20:59:51 +02:00
parent 09b6b6b5ba
commit 7b648c7dc4
5 changed files with 188 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files
single_include/nlohmann/json.hpp
+50 -8
View File
@@ -7932,10 +7932,11 @@ class lexer : public lexer_base<BasicJsonType>
public:
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))
, ignore_comments(ignore_comments_)
, decimal_point_char(static_cast<char_int_type>(get_decimal_point()))
, discard_number_values(discard_number_values_)
{}
// deleted because of pointer members
@@ -9062,6 +9063,38 @@ scan_number_done:
// we are done scanning a number)
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.
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)
errno = 0;
@@ -9537,6 +9570,13 @@ scan_number_done:
const char_int_type decimal_point_char = '.';
/// the position of the decimal point in the input
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
@@ -14043,9 +14083,10 @@ class parser
parser_callback_t<BasicJsonType> cb = nullptr,
const bool allow_exceptions_ = true,
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))
, m_lexer(std::move(adapter), ignore_comments)
, m_lexer(std::move(adapter), ignore_comments, discard_number_values_)
, allow_exceptions(allow_exceptions_)
, ignore_trailing_commas(ignore_trailing_commas_)
{
@@ -21592,11 +21633,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
detail::parser_callback_t<basic_json>cb = nullptr,
const bool allow_exceptions = true,
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),
std::move(cb), allow_exceptions, ignore_comments, ignore_trailing_commas);
std::move(cb), allow_exceptions, ignore_comments, ignore_trailing_commas, discard_number_values);
}
private:
@@ -25561,7 +25603,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
const bool ignore_comments = 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)
@@ -25572,7 +25614,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
const bool ignore_comments = 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
@@ -25581,7 +25623,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
const bool ignore_comments = 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