Compare commits

..
Author SHA1 Message Date
Niels Lohmann e59b455616 Update doc example outputs for new object-conversion iteration order
Reserving capacity in from_json()'s object-conversion path before
inserting elements changes libstdc++'s std::unordered_map bucket
layout, which changes the iteration order used by
get__ValueType_const.cpp, get_to.cpp and operator__ValueType.cpp to
print the elements of a converted std::unordered_map<std::string,
json>. Verified against a clean develop checkout (built with the
same GCC/libstdc++ used in CI) that the old order was produced
without this PR's change and the new order is produced with it, and
that the three affected examples now match their updated expected
output byte-for-byte.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-09-06 11:34:53 +02:00
Niels Lohmann e29ac4f043 Reserve capacity in from_json() object conversion when supported
The object-to-container from_json() overload filled the target
container one element at a time without reserving capacity, even
when the target type supports reserve() (e.g. std::unordered_map)
and the number of elements is already known. This caused unnecessary
rehashing while parsing large objects into such containers.

Add a reserve-detecting overload (from_json_object_impl), mirroring
the priority_tag-based SFINAE technique already used by the array
conversion path (from_json_array_impl), so that reserve(size()) is
called up front when available and the loop falls back unchanged
otherwise (e.g. for std::map).

Fixes #5406

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-09-05 20:43:23 +02:00
10 changed files with 108 additions and 249 deletions
@@ -4,8 +4,8 @@
Hello, world! Hello, world!
1 2 3 4 5 1 2 3 4 5
string: "Hello, world!"
number: {"floating-point":17.23,"integer":42} number: {"floating-point":17.23,"integer":42}
null: null null: null
string: "Hello, world!"
boolean: true boolean: true
array: [1,2,3,4,5] array: [1,2,3,4,5]
+1 -1
View File
@@ -4,8 +4,8 @@
Hello, world! Hello, world!
1 2 3 4 5 1 2 3 4 5
string: "Hello, world!"
number: {"floating-point":17.23,"integer":42} number: {"floating-point":17.23,"integer":42}
null: null null: null
string: "Hello, world!"
boolean: true boolean: true
array: [1,2,3,4,5] array: [1,2,3,4,5]
@@ -4,9 +4,9 @@
Hello, world! Hello, world!
1 2 3 4 5 1 2 3 4 5
string: "Hello, world!"
number: {"floating-point":17.23,"integer":42} number: {"floating-point":17.23,"integer":42}
null: null null: null
string: "Hello, world!"
boolean: true boolean: true
array: [1,2,3,4,5] array: [1,2,3,4,5]
[json.exception.type_error.302] type must be boolean, but is string [json.exception.type_error.302] type must be boolean, but is string
@@ -398,6 +398,34 @@ inline void from_json(const BasicJsonType& j, CompatibleArrayType& bin)
} }
} }
template<typename BasicJsonType, typename ConstructibleObjectType>
auto from_json_object_impl(const BasicJsonType& j, ConstructibleObjectType& obj, priority_tag<1> /*unused*/)
-> decltype(
obj.reserve(std::declval<typename ConstructibleObjectType::size_type>()),
void())
{
ConstructibleObjectType ret;
const auto* inner_object = j.template get_ptr<const typename BasicJsonType::object_t*>();
ret.reserve(inner_object->size());
for (const auto& p : *inner_object)
{
ret.emplace(p.first, p.second.template get<typename ConstructibleObjectType::mapped_type>());
}
obj = std::move(ret);
}
template<typename BasicJsonType, typename ConstructibleObjectType>
inline void from_json_object_impl(const BasicJsonType& j, ConstructibleObjectType& obj, priority_tag<0> /*unused*/)
{
ConstructibleObjectType ret;
const auto* inner_object = j.template get_ptr<const typename BasicJsonType::object_t*>();
for (const auto& p : *inner_object)
{
ret.emplace(p.first, p.second.template get<typename ConstructibleObjectType::mapped_type>());
}
obj = std::move(ret);
}
template<typename BasicJsonType, typename ConstructibleObjectType, template<typename BasicJsonType, typename ConstructibleObjectType,
enable_if_t<is_constructible_object_type<BasicJsonType, ConstructibleObjectType>::value, int> = 0> enable_if_t<is_constructible_object_type<BasicJsonType, ConstructibleObjectType>::value, int> = 0>
inline void from_json(const BasicJsonType& j, ConstructibleObjectType& obj) inline void from_json(const BasicJsonType& j, ConstructibleObjectType& obj)
@@ -407,13 +435,7 @@ inline void from_json(const BasicJsonType& j, ConstructibleObjectType& obj)
JSON_THROW(type_error::create(302, concat("type must be object, but is ", j.type_name()), &j)); JSON_THROW(type_error::create(302, concat("type must be object, but is ", j.type_name()), &j));
} }
ConstructibleObjectType ret; from_json_object_impl(j, obj, priority_tag<1> {});
const auto* inner_object = j.template get_ptr<const typename BasicJsonType::object_t*>();
for (const auto& p : *inner_object)
{
ret.emplace(p.first, p.second.template get<typename ConstructibleObjectType::mapped_type>());
}
obj = std::move(ret);
} }
// overload for arithmetic types, not chosen for basic_json template arguments // overload for arithmetic types, not chosen for basic_json template arguments
+1 -61
View File
@@ -149,11 +149,10 @@ 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, bool discard_number_values_ = false) noexcept explicit lexer(InputAdapterType&& adapter, bool ignore_comments_ = 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
@@ -1280,58 +1279,6 @@ 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;
@@ -1807,13 +1754,6 @@ 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
+2 -3
View File
@@ -72,10 +72,9 @@ 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, discard_number_values_) , m_lexer(std::move(adapter), ignore_comments)
, allow_exceptions(allow_exceptions_) , allow_exceptions(allow_exceptions_)
, ignore_trailing_commas(ignore_trailing_commas_) , ignore_trailing_commas(ignore_trailing_commas_)
{ {
+5 -6
View File
@@ -164,12 +164,11 @@ 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, discard_number_values); std::move(cb), allow_exceptions, ignore_comments, ignore_trailing_commas);
} }
private: private:
@@ -4134,7 +4133,7 @@ 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, true).accept(true); return parser(detail::input_adapter(std::forward<InputType>(i)), nullptr, false, ignore_comments, ignore_trailing_commas).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)
@@ -4145,7 +4144,7 @@ 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, true).accept(true); return parser(detail::input_adapter(std::move(first), std::move(last)), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true);
} }
JSON_HEDLEY_WARN_UNUSED_RESULT JSON_HEDLEY_WARN_UNUSED_RESULT
@@ -4154,7 +4153,7 @@ 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, true).accept(true); return parser(i.get(), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true);
} }
/// @brief generate SAX events /// @brief generate SAX events
+37 -77
View File
@@ -5693,6 +5693,34 @@ inline void from_json(const BasicJsonType& j, CompatibleArrayType& bin)
} }
} }
template<typename BasicJsonType, typename ConstructibleObjectType>
auto from_json_object_impl(const BasicJsonType& j, ConstructibleObjectType& obj, priority_tag<1> /*unused*/)
-> decltype(
obj.reserve(std::declval<typename ConstructibleObjectType::size_type>()),
void())
{
ConstructibleObjectType ret;
const auto* inner_object = j.template get_ptr<const typename BasicJsonType::object_t*>();
ret.reserve(inner_object->size());
for (const auto& p : *inner_object)
{
ret.emplace(p.first, p.second.template get<typename ConstructibleObjectType::mapped_type>());
}
obj = std::move(ret);
}
template<typename BasicJsonType, typename ConstructibleObjectType>
inline void from_json_object_impl(const BasicJsonType& j, ConstructibleObjectType& obj, priority_tag<0> /*unused*/)
{
ConstructibleObjectType ret;
const auto* inner_object = j.template get_ptr<const typename BasicJsonType::object_t*>();
for (const auto& p : *inner_object)
{
ret.emplace(p.first, p.second.template get<typename ConstructibleObjectType::mapped_type>());
}
obj = std::move(ret);
}
template<typename BasicJsonType, typename ConstructibleObjectType, template<typename BasicJsonType, typename ConstructibleObjectType,
enable_if_t<is_constructible_object_type<BasicJsonType, ConstructibleObjectType>::value, int> = 0> enable_if_t<is_constructible_object_type<BasicJsonType, ConstructibleObjectType>::value, int> = 0>
inline void from_json(const BasicJsonType& j, ConstructibleObjectType& obj) inline void from_json(const BasicJsonType& j, ConstructibleObjectType& obj)
@@ -5702,13 +5730,7 @@ inline void from_json(const BasicJsonType& j, ConstructibleObjectType& obj)
JSON_THROW(type_error::create(302, concat("type must be object, but is ", j.type_name()), &j)); JSON_THROW(type_error::create(302, concat("type must be object, but is ", j.type_name()), &j));
} }
ConstructibleObjectType ret; from_json_object_impl(j, obj, priority_tag<1> {});
const auto* inner_object = j.template get_ptr<const typename BasicJsonType::object_t*>();
for (const auto& p : *inner_object)
{
ret.emplace(p.first, p.second.template get<typename ConstructibleObjectType::mapped_type>());
}
obj = std::move(ret);
} }
// overload for arithmetic types, not chosen for basic_json template arguments // overload for arithmetic types, not chosen for basic_json template arguments
@@ -7932,11 +7954,10 @@ 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, bool discard_number_values_ = false) noexcept explicit lexer(InputAdapterType&& adapter, bool ignore_comments_ = 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
@@ -9063,58 +9084,6 @@ 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;
@@ -9590,13 +9559,6 @@ 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
@@ -14103,10 +14065,9 @@ 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, discard_number_values_) , m_lexer(std::move(adapter), ignore_comments)
, allow_exceptions(allow_exceptions_) , allow_exceptions(allow_exceptions_)
, ignore_trailing_commas(ignore_trailing_commas_) , ignore_trailing_commas(ignore_trailing_commas_)
{ {
@@ -21653,12 +21614,11 @@ 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, discard_number_values); std::move(cb), allow_exceptions, ignore_comments, ignore_trailing_commas);
} }
private: private:
@@ -25623,7 +25583,7 @@ 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, true).accept(true); return parser(detail::input_adapter(std::forward<InputType>(i)), nullptr, false, ignore_comments, ignore_trailing_commas).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)
@@ -25634,7 +25594,7 @@ 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, true).accept(true); return parser(detail::input_adapter(std::move(first), std::move(last)), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true);
} }
JSON_HEDLEY_WARN_UNUSED_RESULT JSON_HEDLEY_WARN_UNUSED_RESULT
@@ -25643,7 +25603,7 @@ 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, true).accept(true); return parser(i.get(), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true);
} }
/// @brief generate SAX events /// @brief generate SAX events
-92
View File
@@ -930,98 +930,6 @@ 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);
}
}
} }
} }
+31
View File
@@ -1389,6 +1389,37 @@ TEST_CASE("value conversion")
// CHECK(m5["one"] == "eins"); // CHECK(m5["one"] == "eins");
} }
SECTION("reserve is called on containers that support it (#5406)")
{
// build a larger object so that a missing/incorrect reserve()
// call would be more likely to corrupt or drop elements
json j_large;
for (int i = 0; i < 100; ++i)
{
j_large[std::to_string(i)] = i;
}
SECTION("std::unordered_map (supports reserve)")
{
const auto m = j_large.get<std::unordered_map<std::string, int>>();
CHECK(m.size() == 100);
for (int i = 0; i < 100; ++i)
{
CHECK(m.at(std::to_string(i)) == i);
}
}
SECTION("std::map (no reserve, fallback path)")
{
const auto m = j_large.get<std::map<std::string, int>>();
CHECK(m.size() == 100);
for (int i = 0; i < 100; ++i)
{
CHECK(m.at(std::to_string(i)) == i);
}
}
}
SECTION("std::multimap") SECTION("std::multimap")
{ {
j1.get<std::multimap<std::string, int>>(); j1.get<std::multimap<std::string, int>>();