mirror of
https://github.com/nlohmann/json.git
synced 2026-07-21 19:23:03 +04:00
Compare commits
5 Commits
41c4589c0a
...
41833047cc
| Author | SHA1 | Date | |
|---|---|---|---|
| 41833047cc | |||
| 0d5b70a95a | |||
| 0c91bbc4ba | |||
| 2aa570f8f3 | |||
| 4b9fc0ad76 |
@@ -658,7 +658,7 @@ typename container_input_adapter_factory_impl::container_input_adapter_factory<C
|
||||
// iterators it replaces did.
|
||||
template < typename ContainerType,
|
||||
enable_if_t < is_contiguous_byte_container<ContainerType>::value, int > = 0 >
|
||||
auto input_adapter(ContainerType && container)
|
||||
auto input_adapter(const ContainerType& container)
|
||||
-> decltype(input_adapter(container.data(), container.data() + container.size()))
|
||||
{
|
||||
return input_adapter(container.data(), container.data() + container.size());
|
||||
|
||||
@@ -1382,8 +1382,14 @@ scan_number_done:
|
||||
}
|
||||
|
||||
// this code is reached if we parse a floating-point number or if an
|
||||
// integer conversion above overflowed. Try the exact fast path (double
|
||||
// only) before falling back to the locale-independent strtof/strtod.
|
||||
// integer conversion above overflowed. Prefer std::from_chars
|
||||
// (Eisel-Lemire, locale-independent, correctly rounded) when available;
|
||||
// otherwise the exact Clinger fast path (double only); otherwise the
|
||||
// locale-aware strtof/strtod.
|
||||
if (parse_float_from_chars(num_begin, num_end, value_float))
|
||||
{
|
||||
return token_type::value_float;
|
||||
}
|
||||
if (parse_float_fast(num_begin, num_end, decimal_point_char, value_float))
|
||||
{
|
||||
return token_type::value_float;
|
||||
|
||||
@@ -9,12 +9,24 @@
|
||||
#pragma once
|
||||
|
||||
#include <array> // array
|
||||
#include <cfloat> // FLT_EVAL_METHOD
|
||||
#include <cstddef> // size_t
|
||||
#include <cstdint> // int64_t, uint64_t
|
||||
#include <limits> // numeric_limits
|
||||
|
||||
#include <nlohmann/detail/macro_scope.hpp>
|
||||
|
||||
// std::from_chars lives in <charconv>, but being in C++17 mode does not
|
||||
// guarantee the header exists: GCC 7 sets __cplusplus to C++17 yet ships no
|
||||
// <charconv> (added in GCC 8; floating-point support in GCC 11). Guard the
|
||||
// include with __has_include so such toolchains fall back to the scalar path.
|
||||
#if defined(JSON_HAS_CPP_17) && defined(__has_include)
|
||||
#if __has_include(<charconv>)
|
||||
#include <charconv> // from_chars (only used when __cpp_lib_to_chars is defined)
|
||||
#include <system_error> // errc
|
||||
#endif
|
||||
#endif
|
||||
|
||||
// This file contains the value-conversion helpers used by the lexer to turn an
|
||||
// already-validated number token into a value, without the locale/errno
|
||||
// overhead of std::strtoull/std::strtod. They are free functions so the lexer
|
||||
@@ -54,7 +66,7 @@ bool parse_integer_unsigned(const char* first, const char* last, NumberUnsignedT
|
||||
{
|
||||
return false;
|
||||
}
|
||||
x = x * 10u + digit;
|
||||
x = (x * 10u) + digit;
|
||||
}
|
||||
value = static_cast<NumberUnsignedType>(x);
|
||||
// reject values that do not round-trip into a narrower NumberUnsignedType
|
||||
@@ -84,7 +96,7 @@ bool parse_integer_signed(const char* first, const char* last, NumberIntegerType
|
||||
{
|
||||
return false;
|
||||
}
|
||||
magnitude = magnitude * 10u + digit;
|
||||
magnitude = (magnitude * 10u) + digit;
|
||||
}
|
||||
const std::int64_t x = (magnitude == limit)
|
||||
? (std::numeric_limits<std::int64_t>::min)()
|
||||
@@ -115,6 +127,19 @@ below).
|
||||
template<typename DecimalPointType>
|
||||
bool parse_float_fast(const char* first, const char* last, DecimalPointType decimal_point, double& out) noexcept
|
||||
{
|
||||
#if defined(FLT_EVAL_METHOD) && FLT_EVAL_METHOD != 0
|
||||
// Clinger's fast path is only exact when double operations are evaluated in
|
||||
// true double precision. On platforms that keep intermediates in extended
|
||||
// precision (e.g. the x87 FPU on 32-bit x86, where FLT_EVAL_METHOD == 2) the
|
||||
// single significand * 10^scale step is double-rounded and can be 1 ULP off,
|
||||
// so decline and let the caller fall back to the correctly-rounded
|
||||
// std::from_chars / std::strtod path.
|
||||
static_cast<void>(first);
|
||||
static_cast<void>(last);
|
||||
static_cast<void>(decimal_point);
|
||||
static_cast<void>(out);
|
||||
return false;
|
||||
#else
|
||||
static const std::array<double, 23> powers_of_ten =
|
||||
{
|
||||
{
|
||||
@@ -146,7 +171,7 @@ bool parse_float_fast(const char* first, const char* last, DecimalPointType deci
|
||||
{
|
||||
return false; // significand may not fit into uint64_t
|
||||
}
|
||||
significand = significand * 10u + static_cast<std::uint64_t>(c - '0');
|
||||
significand = (significand * 10u) + static_cast<std::uint64_t>(c - '0');
|
||||
++num_digits;
|
||||
fractional_digits += static_cast<int>(seen_dot);
|
||||
}
|
||||
@@ -189,7 +214,7 @@ bool parse_float_fast(const char* first, const char* last, DecimalPointType deci
|
||||
{
|
||||
return false;
|
||||
}
|
||||
exponent = exponent * 10 + (*p - '0');
|
||||
exponent = (exponent * 10) + (*p - '0');
|
||||
any_exp_digit = true;
|
||||
if (JSON_HEDLEY_UNLIKELY(exponent > 9999))
|
||||
{
|
||||
@@ -231,6 +256,7 @@ bool parse_float_fast(const char* first, const char* last, DecimalPointType deci
|
||||
}
|
||||
out = negative ? -result : result;
|
||||
return true;
|
||||
#endif
|
||||
}
|
||||
|
||||
/// fast float path is only exact for `double`; decline for float/long double
|
||||
@@ -240,5 +266,37 @@ bool parse_float_fast(const char* /*first*/, const char* /*last*/, DecimalPointT
|
||||
return false;
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief parse a float with std::from_chars (Eisel-Lemire) when available
|
||||
|
||||
std::from_chars is locale-independent, correctly rounded, and - via the
|
||||
Eisel-Lemire algorithm in modern standard libraries - much faster than strtod
|
||||
over the whole value range (not just the Clinger subset). It is used only when
|
||||
__cpp_lib_to_chars indicates full floating-point support and only when it
|
||||
consumes the entire token ([first, last)); a partial parse means the buffer
|
||||
uses a non-'.' locale decimal point, in which case the caller falls back to the
|
||||
locale-aware path. An under-/overflow (result_out_of_range) also declines, so
|
||||
the caller's strtod fallback supplies the well-defined ±inf/0 result the parser
|
||||
expects (side-stepping the P4168 divergence between implementations).
|
||||
|
||||
@return true if the value was parsed exactly and fully; false to fall back
|
||||
*/
|
||||
template<typename FloatType>
|
||||
bool parse_float_from_chars(const char* first, const char* last, FloatType& out) noexcept
|
||||
{
|
||||
// JSON_HAS_CPP_17 must gate the use as well as the <charconv> include above:
|
||||
// some standard libraries (e.g. libstdc++ 15) define __cpp_lib_to_chars even
|
||||
// in C++14 mode, where <charconv> is not included.
|
||||
#if defined(JSON_HAS_CPP_17) && defined(__cpp_lib_to_chars)
|
||||
const auto result = std::from_chars(first, last, out);
|
||||
return result.ec == std::errc() && result.ptr == last;
|
||||
#else
|
||||
static_cast<void>(first);
|
||||
static_cast<void>(last);
|
||||
static_cast<void>(out);
|
||||
return false;
|
||||
#endif
|
||||
}
|
||||
|
||||
} // namespace detail
|
||||
NLOHMANN_JSON_NAMESPACE_END
|
||||
|
||||
@@ -7645,7 +7645,7 @@ typename container_input_adapter_factory_impl::container_input_adapter_factory<C
|
||||
// iterators it replaces did.
|
||||
template < typename ContainerType,
|
||||
enable_if_t < is_contiguous_byte_container<ContainerType>::value, int > = 0 >
|
||||
auto input_adapter(ContainerType && container)
|
||||
auto input_adapter(const ContainerType& container)
|
||||
-> decltype(input_adapter(container.data(), container.data() + container.size()))
|
||||
{
|
||||
return input_adapter(container.data(), container.data() + container.size());
|
||||
@@ -7791,6 +7791,7 @@ NLOHMANN_JSON_NAMESPACE_END
|
||||
|
||||
|
||||
#include <array> // array
|
||||
#include <cfloat> // FLT_EVAL_METHOD
|
||||
#include <cstddef> // size_t
|
||||
#include <cstdint> // int64_t, uint64_t
|
||||
#include <limits> // numeric_limits
|
||||
@@ -7798,6 +7799,17 @@ NLOHMANN_JSON_NAMESPACE_END
|
||||
// #include <nlohmann/detail/macro_scope.hpp>
|
||||
|
||||
|
||||
// std::from_chars lives in <charconv>, but being in C++17 mode does not
|
||||
// guarantee the header exists: GCC 7 sets __cplusplus to C++17 yet ships no
|
||||
// <charconv> (added in GCC 8; floating-point support in GCC 11). Guard the
|
||||
// include with __has_include so such toolchains fall back to the scalar path.
|
||||
#if defined(JSON_HAS_CPP_17) && defined(__has_include)
|
||||
#if __has_include(<charconv>)
|
||||
#include <charconv> // from_chars (only used when __cpp_lib_to_chars is defined)
|
||||
#include <system_error> // errc
|
||||
#endif
|
||||
#endif
|
||||
|
||||
// This file contains the value-conversion helpers used by the lexer to turn an
|
||||
// already-validated number token into a value, without the locale/errno
|
||||
// overhead of std::strtoull/std::strtod. They are free functions so the lexer
|
||||
@@ -7837,7 +7849,7 @@ bool parse_integer_unsigned(const char* first, const char* last, NumberUnsignedT
|
||||
{
|
||||
return false;
|
||||
}
|
||||
x = x * 10u + digit;
|
||||
x = (x * 10u) + digit;
|
||||
}
|
||||
value = static_cast<NumberUnsignedType>(x);
|
||||
// reject values that do not round-trip into a narrower NumberUnsignedType
|
||||
@@ -7867,7 +7879,7 @@ bool parse_integer_signed(const char* first, const char* last, NumberIntegerType
|
||||
{
|
||||
return false;
|
||||
}
|
||||
magnitude = magnitude * 10u + digit;
|
||||
magnitude = (magnitude * 10u) + digit;
|
||||
}
|
||||
const std::int64_t x = (magnitude == limit)
|
||||
? (std::numeric_limits<std::int64_t>::min)()
|
||||
@@ -7898,6 +7910,19 @@ below).
|
||||
template<typename DecimalPointType>
|
||||
bool parse_float_fast(const char* first, const char* last, DecimalPointType decimal_point, double& out) noexcept
|
||||
{
|
||||
#if defined(FLT_EVAL_METHOD) && FLT_EVAL_METHOD != 0
|
||||
// Clinger's fast path is only exact when double operations are evaluated in
|
||||
// true double precision. On platforms that keep intermediates in extended
|
||||
// precision (e.g. the x87 FPU on 32-bit x86, where FLT_EVAL_METHOD == 2) the
|
||||
// single significand * 10^scale step is double-rounded and can be 1 ULP off,
|
||||
// so decline and let the caller fall back to the correctly-rounded
|
||||
// std::from_chars / std::strtod path.
|
||||
static_cast<void>(first);
|
||||
static_cast<void>(last);
|
||||
static_cast<void>(decimal_point);
|
||||
static_cast<void>(out);
|
||||
return false;
|
||||
#else
|
||||
static const std::array<double, 23> powers_of_ten =
|
||||
{
|
||||
{
|
||||
@@ -7929,7 +7954,7 @@ bool parse_float_fast(const char* first, const char* last, DecimalPointType deci
|
||||
{
|
||||
return false; // significand may not fit into uint64_t
|
||||
}
|
||||
significand = significand * 10u + static_cast<std::uint64_t>(c - '0');
|
||||
significand = (significand * 10u) + static_cast<std::uint64_t>(c - '0');
|
||||
++num_digits;
|
||||
fractional_digits += static_cast<int>(seen_dot);
|
||||
}
|
||||
@@ -7972,7 +7997,7 @@ bool parse_float_fast(const char* first, const char* last, DecimalPointType deci
|
||||
{
|
||||
return false;
|
||||
}
|
||||
exponent = exponent * 10 + (*p - '0');
|
||||
exponent = (exponent * 10) + (*p - '0');
|
||||
any_exp_digit = true;
|
||||
if (JSON_HEDLEY_UNLIKELY(exponent > 9999))
|
||||
{
|
||||
@@ -8014,6 +8039,7 @@ bool parse_float_fast(const char* first, const char* last, DecimalPointType deci
|
||||
}
|
||||
out = negative ? -result : result;
|
||||
return true;
|
||||
#endif
|
||||
}
|
||||
|
||||
/// fast float path is only exact for `double`; decline for float/long double
|
||||
@@ -8023,6 +8049,38 @@ bool parse_float_fast(const char* /*first*/, const char* /*last*/, DecimalPointT
|
||||
return false;
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief parse a float with std::from_chars (Eisel-Lemire) when available
|
||||
|
||||
std::from_chars is locale-independent, correctly rounded, and - via the
|
||||
Eisel-Lemire algorithm in modern standard libraries - much faster than strtod
|
||||
over the whole value range (not just the Clinger subset). It is used only when
|
||||
__cpp_lib_to_chars indicates full floating-point support and only when it
|
||||
consumes the entire token ([first, last)); a partial parse means the buffer
|
||||
uses a non-'.' locale decimal point, in which case the caller falls back to the
|
||||
locale-aware path. An under-/overflow (result_out_of_range) also declines, so
|
||||
the caller's strtod fallback supplies the well-defined ±inf/0 result the parser
|
||||
expects (side-stepping the P4168 divergence between implementations).
|
||||
|
||||
@return true if the value was parsed exactly and fully; false to fall back
|
||||
*/
|
||||
template<typename FloatType>
|
||||
bool parse_float_from_chars(const char* first, const char* last, FloatType& out) noexcept
|
||||
{
|
||||
// JSON_HAS_CPP_17 must gate the use as well as the <charconv> include above:
|
||||
// some standard libraries (e.g. libstdc++ 15) define __cpp_lib_to_chars even
|
||||
// in C++14 mode, where <charconv> is not included.
|
||||
#if defined(JSON_HAS_CPP_17) && defined(__cpp_lib_to_chars)
|
||||
const auto result = std::from_chars(first, last, out);
|
||||
return result.ec == std::errc() && result.ptr == last;
|
||||
#else
|
||||
static_cast<void>(first);
|
||||
static_cast<void>(last);
|
||||
static_cast<void>(out);
|
||||
return false;
|
||||
#endif
|
||||
}
|
||||
|
||||
} // namespace detail
|
||||
NLOHMANN_JSON_NAMESPACE_END
|
||||
|
||||
@@ -9630,8 +9688,14 @@ scan_number_done:
|
||||
}
|
||||
|
||||
// this code is reached if we parse a floating-point number or if an
|
||||
// integer conversion above overflowed. Try the exact fast path (double
|
||||
// only) before falling back to the locale-independent strtof/strtod.
|
||||
// integer conversion above overflowed. Prefer std::from_chars
|
||||
// (Eisel-Lemire, locale-independent, correctly rounded) when available;
|
||||
// otherwise the exact Clinger fast path (double only); otherwise the
|
||||
// locale-aware strtof/strtod.
|
||||
if (parse_float_from_chars(num_begin, num_end, value_float))
|
||||
{
|
||||
return token_type::value_float;
|
||||
}
|
||||
if (parse_float_fast(num_begin, num_end, decimal_point_char, value_float))
|
||||
{
|
||||
return token_type::value_float;
|
||||
|
||||
@@ -249,7 +249,11 @@ TEST_CASE("lexer number fast path")
|
||||
"-9223372036854775808", // INT64_MIN -> integer
|
||||
"-9223372036854775809", // INT64_MIN - 1 -> float
|
||||
"123456789012345678901234567890", // huge -> float
|
||||
"0.30000000000000004", "2.2250738585072014e-308", "1e308"
|
||||
"0.30000000000000004", "2.2250738585072014e-308", "1e308",
|
||||
// high-precision / wide-exponent values that exercise the
|
||||
// std::from_chars (Eisel-Lemire) path beyond the Clinger subset
|
||||
"1.7976931348623157e308", "1.2345678901234567e-250",
|
||||
"9007199254740993", "5e-324", "1e-320"
|
||||
};
|
||||
|
||||
for (const auto& n : numbers)
|
||||
|
||||
Reference in New Issue
Block a user