llvm-project/libcxx/include/charconv

640 lines
20 KiB
Plaintext
Raw Normal View History

// -*- C++ -*-
//===----------------------------------------------------------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
#ifndef _LIBCPP_CHARCONV
#define _LIBCPP_CHARCONV
/*
charconv synopsis
namespace std {
// floating-point format for primitive numerical conversion
enum class chars_format {
scientific = unspecified,
fixed = unspecified,
hex = unspecified,
general = fixed | scientific
};
// 23.20.2, primitive numerical output conversion
struct to_chars_result {
char* ptr;
errc ec;
friend bool operator==(const to_chars_result&, const to_chars_result&) = default; // since C++20
};
to_chars_result to_chars(char* first, char* last, see below value,
int base = 10);
to_chars_result to_chars(char* first, char* last, bool value,
int base = 10) = delete;
to_chars_result to_chars(char* first, char* last, float value);
to_chars_result to_chars(char* first, char* last, double value);
to_chars_result to_chars(char* first, char* last, long double value);
to_chars_result to_chars(char* first, char* last, float value,
chars_format fmt);
to_chars_result to_chars(char* first, char* last, double value,
chars_format fmt);
to_chars_result to_chars(char* first, char* last, long double value,
chars_format fmt);
to_chars_result to_chars(char* first, char* last, float value,
chars_format fmt, int precision);
to_chars_result to_chars(char* first, char* last, double value,
chars_format fmt, int precision);
to_chars_result to_chars(char* first, char* last, long double value,
chars_format fmt, int precision);
// 23.20.3, primitive numerical input conversion
struct from_chars_result {
const char* ptr;
errc ec;
friend bool operator==(const from_chars_result&, const from_chars_result&) = default; // since C++20
};
from_chars_result from_chars(const char* first, const char* last,
see below& value, int base = 10);
from_chars_result from_chars(const char* first, const char* last,
float& value,
chars_format fmt = chars_format::general);
from_chars_result from_chars(const char* first, const char* last,
double& value,
chars_format fmt = chars_format::general);
from_chars_result from_chars(const char* first, const char* last,
long double& value,
chars_format fmt = chars_format::general);
} // namespace std
*/
#include <__availability>
#include <__bits>
#include <__charconv/chars_format.h>
#include <__charconv/from_chars_result.h>
#include <__charconv/to_chars_result.h>
#include <__config>
#include <__errc>
#include <cmath> // for log2f
#include <cstdint>
#include <cstdlib> // for _LIBCPP_UNREACHABLE
#include <cstring>
#include <limits>
#include <type_traits>
#include <__debug>
#if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
#pragma GCC system_header
#endif
_LIBCPP_PUSH_MACROS
#include <__undef_macros>
_LIBCPP_BEGIN_NAMESPACE_STD
namespace __itoa {
_LIBCPP_AVAILABILITY_TO_CHARS _LIBCPP_FUNC_VIS char* __u64toa(uint64_t __value, char* __buffer) _NOEXCEPT;
_LIBCPP_AVAILABILITY_TO_CHARS _LIBCPP_FUNC_VIS char* __u32toa(uint32_t __value, char* __buffer) _NOEXCEPT;
} // namespace __itoa
#ifndef _LIBCPP_CXX03_LANG
to_chars_result to_chars(char*, char*, bool, int = 10) = delete;
from_chars_result from_chars(const char*, const char*, bool, int = 10) = delete;
namespace __itoa
{
static _LIBCPP_CONSTEXPR uint64_t __pow10_64[] = {
UINT64_C(0),
UINT64_C(10),
UINT64_C(100),
UINT64_C(1000),
UINT64_C(10000),
UINT64_C(100000),
UINT64_C(1000000),
UINT64_C(10000000),
UINT64_C(100000000),
UINT64_C(1000000000),
UINT64_C(10000000000),
UINT64_C(100000000000),
UINT64_C(1000000000000),
UINT64_C(10000000000000),
UINT64_C(100000000000000),
UINT64_C(1000000000000000),
UINT64_C(10000000000000000),
UINT64_C(100000000000000000),
UINT64_C(1000000000000000000),
UINT64_C(10000000000000000000),
};
static _LIBCPP_CONSTEXPR uint32_t __pow10_32[] = {
UINT32_C(0), UINT32_C(10), UINT32_C(100),
UINT32_C(1000), UINT32_C(10000), UINT32_C(100000),
UINT32_C(1000000), UINT32_C(10000000), UINT32_C(100000000),
UINT32_C(1000000000),
};
template <typename _Tp, typename = void>
struct _LIBCPP_HIDDEN __traits_base
{
using type = uint64_t;
static _LIBCPP_INLINE_VISIBILITY int __width(_Tp __v)
{
auto __t = (64 - _VSTD::__libcpp_clz(static_cast<type>(__v | 1))) * 1233 >> 12;
return __t - (__v < __pow10_64[__t]) + 1;
}
_LIBCPP_AVAILABILITY_TO_CHARS
static _LIBCPP_INLINE_VISIBILITY char* __convert(_Tp __v, char* __p)
{
return __u64toa(__v, __p);
}
static _LIBCPP_INLINE_VISIBILITY decltype(__pow10_64)& __pow() { return __pow10_64; }
};
template <typename _Tp>
struct _LIBCPP_HIDDEN
__traits_base<_Tp, decltype(void(uint32_t{declval<_Tp>()}))>
{
using type = uint32_t;
static _LIBCPP_INLINE_VISIBILITY int __width(_Tp __v)
{
auto __t = (32 - _VSTD::__libcpp_clz(static_cast<type>(__v | 1))) * 1233 >> 12;
return __t - (__v < __pow10_32[__t]) + 1;
}
_LIBCPP_AVAILABILITY_TO_CHARS
static _LIBCPP_INLINE_VISIBILITY char* __convert(_Tp __v, char* __p)
{
return __u32toa(__v, __p);
}
static _LIBCPP_INLINE_VISIBILITY decltype(__pow10_32)& __pow() { return __pow10_32; }
};
template <typename _Tp>
inline _LIBCPP_INLINE_VISIBILITY bool
__mul_overflowed(unsigned char __a, _Tp __b, unsigned char& __r)
{
auto __c = __a * __b;
__r = __c;
return __c > numeric_limits<unsigned char>::max();
}
template <typename _Tp>
inline _LIBCPP_INLINE_VISIBILITY bool
__mul_overflowed(unsigned short __a, _Tp __b, unsigned short& __r)
{
auto __c = __a * __b;
__r = __c;
return __c > numeric_limits<unsigned short>::max();
}
template <typename _Tp>
inline _LIBCPP_INLINE_VISIBILITY bool
__mul_overflowed(_Tp __a, _Tp __b, _Tp& __r)
{
static_assert(is_unsigned<_Tp>::value, "");
#if !defined(_LIBCPP_COMPILER_MSVC)
return __builtin_mul_overflow(__a, __b, &__r);
#else
bool __did = __b && (numeric_limits<_Tp>::max() / __b) < __a;
__r = __a * __b;
return __did;
#endif
}
template <typename _Tp, typename _Up>
inline _LIBCPP_INLINE_VISIBILITY bool
__mul_overflowed(_Tp __a, _Up __b, _Tp& __r)
{
return __mul_overflowed(__a, static_cast<_Tp>(__b), __r);
}
template <typename _Tp>
struct _LIBCPP_HIDDEN __traits : __traits_base<_Tp>
{
static _LIBCPP_CONSTEXPR int digits = numeric_limits<_Tp>::digits10 + 1;
using __traits_base<_Tp>::__pow;
using typename __traits_base<_Tp>::type;
// precondition: at least one non-zero character available
static _LIBCPP_INLINE_VISIBILITY char const*
__read(char const* __p, char const* __ep, type& __a, type& __b)
{
type __cprod[digits];
int __j = digits - 1;
int __i = digits;
do
{
if (!('0' <= *__p && *__p <= '9'))
break;
__cprod[--__i] = *__p++ - '0';
} while (__p != __ep && __i != 0);
__a = __inner_product(__cprod + __i + 1, __cprod + __j, __pow() + 1,
__cprod[__i]);
if (__mul_overflowed(__cprod[__j], __pow()[__j - __i], __b))
--__p;
return __p;
}
template <typename _It1, typename _It2, class _Up>
static _LIBCPP_INLINE_VISIBILITY _Up
__inner_product(_It1 __first1, _It1 __last1, _It2 __first2, _Up __init)
{
for (; __first1 < __last1; ++__first1, ++__first2)
__init = __init + *__first1 * *__first2;
return __init;
}
};
} // namespace __itoa
template <typename _Tp>
inline _LIBCPP_INLINE_VISIBILITY _Tp
__complement(_Tp __x)
{
static_assert(is_unsigned<_Tp>::value, "cast to unsigned first");
return _Tp(~__x + 1);
}
template <typename _Tp>
_LIBCPP_AVAILABILITY_TO_CHARS
inline _LIBCPP_INLINE_VISIBILITY to_chars_result
__to_chars_itoa(char* __first, char* __last, _Tp __value, true_type)
{
auto __x = __to_unsigned_like(__value);
if (__value < 0 && __first != __last)
{
*__first++ = '-';
__x = __complement(__x);
}
return __to_chars_itoa(__first, __last, __x, false_type());
}
template <typename _Tp>
_LIBCPP_AVAILABILITY_TO_CHARS
inline _LIBCPP_INLINE_VISIBILITY to_chars_result
__to_chars_itoa(char* __first, char* __last, _Tp __value, false_type)
{
using __tx = __itoa::__traits<_Tp>;
auto __diff = __last - __first;
if (__tx::digits <= __diff || __tx::__width(__value) <= __diff)
return {__tx::__convert(__value, __first), errc(0)};
else
return {__last, errc::value_too_large};
}
template <typename _Tp>
_LIBCPP_AVAILABILITY_TO_CHARS
inline _LIBCPP_INLINE_VISIBILITY to_chars_result
__to_chars_integral(char* __first, char* __last, _Tp __value, int __base,
true_type)
{
auto __x = __to_unsigned_like(__value);
if (__value < 0 && __first != __last)
{
*__first++ = '-';
__x = __complement(__x);
}
return __to_chars_integral(__first, __last, __x, __base, false_type());
}
template <typename _Tp>
_LIBCPP_AVAILABILITY_TO_CHARS _LIBCPP_INLINE_VISIBILITY int __to_chars_integral_width(_Tp __value, unsigned __base) {
_LIBCPP_ASSERT(__value >= 0, "The function requires a non-negative value.");
unsigned __base_2 = __base * __base;
unsigned __base_3 = __base_2 * __base;
unsigned __base_4 = __base_2 * __base_2;
int __r = 0;
while (true) {
if (__value < __base)
return __r + 1;
if (__value < __base_2)
return __r + 2;
if (__value < __base_3)
return __r + 3;
if (__value < __base_4)
return __r + 4;
__value /= __base_4;
__r += 4;
}
_LIBCPP_UNREACHABLE();
}
template <typename _Tp>
_LIBCPP_AVAILABILITY_TO_CHARS
inline _LIBCPP_INLINE_VISIBILITY to_chars_result
__to_chars_integral(char* __first, char* __last, _Tp __value, int __base,
false_type)
{
if (__base == 10)
return __to_chars_itoa(__first, __last, __value, false_type());
ptrdiff_t __cap = __last - __first;
int __n = __to_chars_integral_width(__value, __base);
if (__n > __cap)
return {__last, errc::value_too_large};
__last = __first + __n;
char* __p = __last;
do {
unsigned __c = __value % __base;
__value /= __base;
*--__p = "0123456789abcdefghijklmnopqrstuvwxyz"[__c];
} while (__value != 0);
return {__last, errc(0)};
}
template <typename _Tp, typename enable_if<is_integral<_Tp>::value, int>::type = 0>
_LIBCPP_AVAILABILITY_TO_CHARS
inline _LIBCPP_INLINE_VISIBILITY to_chars_result
to_chars(char* __first, char* __last, _Tp __value)
{
return __to_chars_itoa(__first, __last, __value, is_signed<_Tp>());
}
template <typename _Tp, typename enable_if<is_integral<_Tp>::value, int>::type = 0>
_LIBCPP_AVAILABILITY_TO_CHARS
inline _LIBCPP_INLINE_VISIBILITY to_chars_result
to_chars(char* __first, char* __last, _Tp __value, int __base)
{
_LIBCPP_ASSERT(2 <= __base && __base <= 36, "base not in [2, 36]");
return __to_chars_integral(__first, __last, __value, __base,
is_signed<_Tp>());
}
template <typename _It, typename _Tp, typename _Fn, typename... _Ts>
inline _LIBCPP_INLINE_VISIBILITY from_chars_result
__sign_combinator(_It __first, _It __last, _Tp& __value, _Fn __f, _Ts... __args)
{
using __tl = numeric_limits<_Tp>;
decltype(__to_unsigned_like(__value)) __x;
bool __neg = (__first != __last && *__first == '-');
auto __r = __f(__neg ? __first + 1 : __first, __last, __x, __args...);
switch (__r.ec)
{
case errc::invalid_argument:
return {__first, __r.ec};
case errc::result_out_of_range:
return __r;
default:
break;
}
if (__neg)
{
if (__x <= __complement(__to_unsigned_like(__tl::min())))
{
__x = __complement(__x);
_VSTD::memcpy(&__value, &__x, sizeof(__x));
return __r;
}
}
else
{
if (__x <= __tl::max())
{
__value = __x;
return __r;
}
}
return {__r.ptr, errc::result_out_of_range};
}
template <typename _Tp>
inline _LIBCPP_INLINE_VISIBILITY bool
__in_pattern(_Tp __c)
{
return '0' <= __c && __c <= '9';
}
struct _LIBCPP_HIDDEN __in_pattern_result
{
bool __ok;
int __val;
explicit _LIBCPP_INLINE_VISIBILITY operator bool() const { return __ok; }
};
template <typename _Tp>
inline _LIBCPP_INLINE_VISIBILITY __in_pattern_result
__in_pattern(_Tp __c, int __base)
{
if (__base <= 10)
return {'0' <= __c && __c < '0' + __base, __c - '0'};
else if (__in_pattern(__c))
return {true, __c - '0'};
else if ('a' <= __c && __c < 'a' + __base - 10)
return {true, __c - 'a' + 10};
else
return {'A' <= __c && __c < 'A' + __base - 10, __c - 'A' + 10};
}
template <typename _It, typename _Tp, typename _Fn, typename... _Ts>
inline _LIBCPP_INLINE_VISIBILITY from_chars_result
__subject_seq_combinator(_It __first, _It __last, _Tp& __value, _Fn __f,
_Ts... __args)
{
auto __find_non_zero = [](_It __first, _It __last) {
for (; __first != __last; ++__first)
if (*__first != '0')
break;
return __first;
};
auto __p = __find_non_zero(__first, __last);
if (__p == __last || !__in_pattern(*__p, __args...))
{
if (__p == __first)
return {__first, errc::invalid_argument};
else
{
__value = 0;
return {__p, {}};
}
}
auto __r = __f(__p, __last, __value, __args...);
if (__r.ec == errc::result_out_of_range)
{
for (; __r.ptr != __last; ++__r.ptr)
{
if (!__in_pattern(*__r.ptr, __args...))
break;
}
}
return __r;
}
template <typename _Tp, typename enable_if<is_unsigned<_Tp>::value, int>::type = 0>
inline _LIBCPP_INLINE_VISIBILITY from_chars_result
__from_chars_atoi(const char* __first, const char* __last, _Tp& __value)
{
using __tx = __itoa::__traits<_Tp>;
using __output_type = typename __tx::type;
return __subject_seq_combinator(
__first, __last, __value,
[](const char* __first, const char* __last,
_Tp& __value) -> from_chars_result {
__output_type __a, __b;
auto __p = __tx::__read(__first, __last, __a, __b);
if (__p == __last || !__in_pattern(*__p))
{
__output_type __m = numeric_limits<_Tp>::max();
if (__m >= __a && __m - __a >= __b)
{
__value = __a + __b;
return {__p, {}};
}
}
return {__p, errc::result_out_of_range};
});
}
template <typename _Tp, typename enable_if<is_signed<_Tp>::value, int>::type = 0>
inline _LIBCPP_INLINE_VISIBILITY from_chars_result
__from_chars_atoi(const char* __first, const char* __last, _Tp& __value)
{
using __t = decltype(__to_unsigned_like(__value));
return __sign_combinator(__first, __last, __value, __from_chars_atoi<__t>);
}
template <typename _Tp, typename enable_if<is_unsigned<_Tp>::value, int>::type = 0>
inline _LIBCPP_INLINE_VISIBILITY from_chars_result
__from_chars_integral(const char* __first, const char* __last, _Tp& __value,
int __base)
{
if (__base == 10)
return __from_chars_atoi(__first, __last, __value);
return __subject_seq_combinator(
__first, __last, __value,
[](const char* __p, const char* __lastx, _Tp& __value,
int __base) -> from_chars_result {
using __tl = numeric_limits<_Tp>;
auto __digits = __tl::digits / log2f(float(__base));
_Tp __a = __in_pattern(*__p++, __base).__val, __b = 0;
for (int __i = 1; __p != __lastx; ++__i, ++__p)
{
if (auto __c = __in_pattern(*__p, __base))
{
if (__i < __digits - 1)
__a = __a * __base + __c.__val;
else
{
if (!__itoa::__mul_overflowed(__a, __base, __a))
++__p;
__b = __c.__val;
break;
}
}
else
break;
}
if (__p == __lastx || !__in_pattern(*__p, __base))
{
if (__tl::max() - __a >= __b)
{
__value = __a + __b;
return {__p, {}};
}
}
return {__p, errc::result_out_of_range};
},
__base);
}
template <typename _Tp, typename enable_if<is_signed<_Tp>::value, int>::type = 0>
inline _LIBCPP_INLINE_VISIBILITY from_chars_result
__from_chars_integral(const char* __first, const char* __last, _Tp& __value,
int __base)
{
using __t = decltype(__to_unsigned_like(__value));
return __sign_combinator(__first, __last, __value,
__from_chars_integral<__t>, __base);
}
template <typename _Tp, typename enable_if<is_integral<_Tp>::value, int>::type = 0>
inline _LIBCPP_INLINE_VISIBILITY from_chars_result
from_chars(const char* __first, const char* __last, _Tp& __value)
{
return __from_chars_atoi(__first, __last, __value);
}
template <typename _Tp, typename enable_if<is_integral<_Tp>::value, int>::type = 0>
inline _LIBCPP_INLINE_VISIBILITY from_chars_result
from_chars(const char* __first, const char* __last, _Tp& __value, int __base)
{
_LIBCPP_ASSERT(2 <= __base && __base <= 36, "base not in [2, 36]");
return __from_chars_integral(__first, __last, __value, __base);
}
Microsoft's floating-point to_chars powered by Ryu and Ryu Printf Microsoft would like to contribute its implementation of floating-point to_chars to libc++. This uses the impossibly fast Ryu and Ryu Printf algorithms invented by Ulf Adams at Google. Upstream repos: https://github.com/microsoft/STL and https://github.com/ulfjack/ryu . Licensing notes: MSVC's STL is available under the Apache License v2.0 with LLVM Exception, intentionally chosen to match libc++. We've used Ryu under the Boost Software License. This patch contains minor changes from Jorg Brown at Google, to adapt the code to libc++. He verified that it works in Google's Linux-based environment, but then I applied more changes on top of his, so any compiler errors are my fault. (I haven't tried to build and test libc++ yet.) Please tell me if we need to do anything else in order to follow https://llvm.org/docs/DeveloperPolicy.html#attribution-of-changes . Notes: * libc++'s integer charconv is unchanged (except for a small refactoring). MSVC's integer charconv hasn't been tuned for performance yet, so you're not missing anything. * Floating-point from_chars isn't part of this patch because Jorg found that MSVC's implementation (derived from our CRT's strtod) was slower than Abseil's. If you're unable to use Abseil or another implementation due to licensing or technical considerations, Microsoft would be delighted if you used MSVC's from_chars (and you can just take it, or ask us to provide a patch like this). Ulf is also working on a novel algorithm for from_chars. * This assumes that float is IEEE 32-bit, double is IEEE 64-bit, and long double is also IEEE 64-bit. * I have added MSVC's charconv tests (the whole thing: integer/floating from_chars/to_chars), but haven't adapted them to libcxx's harness at all. (These tests will be available in the microsoft/STL repo soon.) * Jorg added int128 codepaths. These were originally present in upstream Ryu, and I removed them from microsoft/STL purely for performance reasons (MSVC doesn't support int128; Clang on Windows does, but I found that x64 intrinsics were slightly faster). * The implementation is split into 3 headers. In MSVC's STL, charconv contains only Microsoft-written code. xcharconv_ryu.h contains code derived from Ryu (with significant modifications and additions). xcharconv_ryu_tables.h contains Ryu's large lookup tables (they were sufficiently large to make editing inconvenient, hence the separate file). The xmeow.h convention is MSVC's for internal headers; you may wish to rename them. * You should consider separately compiling the lookup tables (see https://github.com/microsoft/STL/issues/172 ) for compiler throughput and reduced object file size. * See https://github.com/StephanTLavavej/llvm-project/commits/charconv for fine-grained history. (If necessary, I can perform some rebase surgery to show you what Jorg changed relative to the microsoft/STL repo; currently that's all fused into the first commit.) Differential Revision: https://reviews.llvm.org/D70631
2021-02-10 00:52:41 +08:00
// Floating-point implementation starts here.
// Unlike the other parts of charconv this is only available in C++17 and newer.
#if _LIBCPP_STD_VER > 14
_LIBCPP_AVAILABILITY_TO_CHARS_FLOATING_POINT _LIBCPP_FUNC_VIS
to_chars_result to_chars(char* __first, char* __last, float __value);
_LIBCPP_AVAILABILITY_TO_CHARS_FLOATING_POINT _LIBCPP_FUNC_VIS
to_chars_result to_chars(char* __first, char* __last, double __value);
_LIBCPP_AVAILABILITY_TO_CHARS_FLOATING_POINT _LIBCPP_FUNC_VIS
to_chars_result to_chars(char* __first, char* __last, long double __value);
_LIBCPP_AVAILABILITY_TO_CHARS_FLOATING_POINT _LIBCPP_FUNC_VIS
to_chars_result to_chars(char* __first, char* __last, float __value, chars_format __fmt);
_LIBCPP_AVAILABILITY_TO_CHARS_FLOATING_POINT _LIBCPP_FUNC_VIS
to_chars_result to_chars(char* __first, char* __last, double __value, chars_format __fmt);
_LIBCPP_AVAILABILITY_TO_CHARS_FLOATING_POINT _LIBCPP_FUNC_VIS
to_chars_result to_chars(char* __first, char* __last, long double __value, chars_format __fmt);
_LIBCPP_AVAILABILITY_TO_CHARS_FLOATING_POINT _LIBCPP_FUNC_VIS
to_chars_result to_chars(char* __first, char* __last, float __value, chars_format __fmt, int __precision);
_LIBCPP_AVAILABILITY_TO_CHARS_FLOATING_POINT _LIBCPP_FUNC_VIS
to_chars_result to_chars(char* __first, char* __last, double __value, chars_format __fmt, int __precision);
_LIBCPP_AVAILABILITY_TO_CHARS_FLOATING_POINT _LIBCPP_FUNC_VIS
to_chars_result to_chars(char* __first, char* __last, long double __value, chars_format __fmt, int __precision);
# endif // _LIBCPP_STD_VER > 14
#endif // _LIBCPP_CXX03_LANG
_LIBCPP_END_NAMESPACE_STD
_LIBCPP_POP_MACROS
#endif // _LIBCPP_CHARCONV