如何在c++中转换大端值和小端值?
为了清晰起见,我必须将二进制数据(双精度浮点值以及32位和64位整数)从一个CPU架构转换到另一个CPU架构。这并不涉及网络,因此ntoh()和类似的函数在这里不能工作。
注意:我接受的答案直接适用于我的目标编译器(这就是我选择它的原因)。然而,这里还有其他非常好的、更方便的答案。
如何在c++中转换大端值和小端值?
为了清晰起见,我必须将二进制数据(双精度浮点值以及32位和64位整数)从一个CPU架构转换到另一个CPU架构。这并不涉及网络,因此ntoh()和类似的函数在这里不能工作。
注意:我接受的答案直接适用于我的目标编译器(这就是我选择它的原因)。然而,这里还有其他非常好的、更方便的答案。
当前回答
虽然没有使用固有函数有效,但肯定是可移植的。我的回答:
#include <cstdint>
#include <type_traits>
/**
* Perform an endian swap of bytes against a templatized unsigned word.
*
* @tparam value_type The data type to perform the endian swap against.
* @param value The data value to swap.
*
* @return value_type The resulting swapped word.
*/
template <typename value_type>
constexpr inline auto endian_swap(value_type value) -> value_type
{
using half_type = typename std::conditional<
sizeof(value_type) == 8u,
uint32_t,
typename std::conditional<sizeof(value_type) == 4u, uint16_t, uint8_t>::
type>::type;
size_t const half_bits = sizeof(value_type) * 8u / 2u;
half_type const upper_half = static_cast<half_type>(value >> half_bits);
half_type const lower_half = static_cast<half_type>(value);
if (sizeof(value_type) == 2u)
{
return (static_cast<value_type>(lower_half) << half_bits) | upper_half;
}
return ((static_cast<value_type>(endian_swap(lower_half)) << half_bits) |
endian_swap(upper_half));
}
其他回答
下面介绍如何读取以IEEE 754 64位格式存储的double,即使您的主机使用不同的系统。
/*
* read a double from a stream in ieee754 format regardless of host
* encoding.
* fp - the stream
* bigendian - set to if big bytes first, clear for little bytes
* first
*
*/
double freadieee754(FILE *fp, int bigendian)
{
unsigned char buff[8];
int i;
double fnorm = 0.0;
unsigned char temp;
int sign;
int exponent;
double bitval;
int maski, mask;
int expbits = 11;
int significandbits = 52;
int shift;
double answer;
/* read the data */
for (i = 0; i < 8; i++)
buff[i] = fgetc(fp);
/* just reverse if not big-endian*/
if (!bigendian)
{
for (i = 0; i < 4; i++)
{
temp = buff[i];
buff[i] = buff[8 - i - 1];
buff[8 - i - 1] = temp;
}
}
sign = buff[0] & 0x80 ? -1 : 1;
/* exponet in raw format*/
exponent = ((buff[0] & 0x7F) << 4) | ((buff[1] & 0xF0) >> 4);
/* read inthe mantissa. Top bit is 0.5, the successive bits half*/
bitval = 0.5;
maski = 1;
mask = 0x08;
for (i = 0; i < significandbits; i++)
{
if (buff[maski] & mask)
fnorm += bitval;
bitval /= 2.0;
mask >>= 1;
if (mask == 0)
{
mask = 0x80;
maski++;
}
}
/* handle zero specially */
if (exponent == 0 && fnorm == 0)
return 0.0;
shift = exponent - ((1 << (expbits - 1)) - 1); /* exponent = shift + bias */
/* nans have exp 1024 and non-zero mantissa */
if (shift == 1024 && fnorm != 0)
return sqrt(-1.0);
/*infinity*/
if (shift == 1024 && fnorm == 0)
{
#ifdef INFINITY
return sign == 1 ? INFINITY : -INFINITY;
#endif
return (sign * 1.0) / 0.0;
}
if (shift > -1023)
{
answer = ldexp(fnorm + 1.0, shift);
return answer * sign;
}
else
{
/* denormalised numbers */
if (fnorm == 0.0)
return 0.0;
shift = -1022;
while (fnorm < 1.0)
{
fnorm *= 2;
shift--;
}
answer = ldexp(fnorm, shift);
return answer * sign;
}
}
对于这套函数的其余部分,包括写和整数例程,请参阅我的github项目
https://github.com/MalcolmMcLean/ieee754
我从这篇文章中得到了一些建议,并把它们放在一起形成了这个:
#include <boost/type_traits.hpp>
#include <boost/static_assert.hpp>
#include <boost/detail/endian.hpp>
#include <stdexcept>
#include <cstdint>
enum endianness
{
little_endian,
big_endian,
network_endian = big_endian,
#if defined(BOOST_LITTLE_ENDIAN)
host_endian = little_endian
#elif defined(BOOST_BIG_ENDIAN)
host_endian = big_endian
#else
#error "unable to determine system endianness"
#endif
};
namespace detail {
template<typename T, size_t sz>
struct swap_bytes
{
inline T operator()(T val)
{
throw std::out_of_range("data size");
}
};
template<typename T>
struct swap_bytes<T, 1>
{
inline T operator()(T val)
{
return val;
}
};
template<typename T>
struct swap_bytes<T, 2>
{
inline T operator()(T val)
{
return ((((val) >> 8) & 0xff) | (((val) & 0xff) << 8));
}
};
template<typename T>
struct swap_bytes<T, 4>
{
inline T operator()(T val)
{
return ((((val) & 0xff000000) >> 24) |
(((val) & 0x00ff0000) >> 8) |
(((val) & 0x0000ff00) << 8) |
(((val) & 0x000000ff) << 24));
}
};
template<>
struct swap_bytes<float, 4>
{
inline float operator()(float val)
{
uint32_t mem =swap_bytes<uint32_t, sizeof(uint32_t)>()(*(uint32_t*)&val);
return *(float*)&mem;
}
};
template<typename T>
struct swap_bytes<T, 8>
{
inline T operator()(T val)
{
return ((((val) & 0xff00000000000000ull) >> 56) |
(((val) & 0x00ff000000000000ull) >> 40) |
(((val) & 0x0000ff0000000000ull) >> 24) |
(((val) & 0x000000ff00000000ull) >> 8 ) |
(((val) & 0x00000000ff000000ull) << 8 ) |
(((val) & 0x0000000000ff0000ull) << 24) |
(((val) & 0x000000000000ff00ull) << 40) |
(((val) & 0x00000000000000ffull) << 56));
}
};
template<>
struct swap_bytes<double, 8>
{
inline double operator()(double val)
{
uint64_t mem =swap_bytes<uint64_t, sizeof(uint64_t)>()(*(uint64_t*)&val);
return *(double*)&mem;
}
};
template<endianness from, endianness to, class T>
struct do_byte_swap
{
inline T operator()(T value)
{
return swap_bytes<T, sizeof(T)>()(value);
}
};
// specialisations when attempting to swap to the same endianess
template<class T> struct do_byte_swap<little_endian, little_endian, T> { inline T operator()(T value) { return value; } };
template<class T> struct do_byte_swap<big_endian, big_endian, T> { inline T operator()(T value) { return value; } };
} // namespace detail
template<endianness from, endianness to, class T>
inline T byte_swap(T value)
{
// ensure the data is only 1, 2, 4 or 8 bytes
BOOST_STATIC_ASSERT(sizeof(T) == 1 || sizeof(T) == 2 || sizeof(T) == 4 || sizeof(T) == 8);
// ensure we're only swapping arithmetic types
BOOST_STATIC_ASSERT(boost::is_arithmetic<T>::value);
return detail::do_byte_swap<from, to, T>()(value);
}
然后你可以这样使用它:
// swaps val from host-byte-order to network-byte-order
auto swapped = byte_swap<host_endian, network_endian>(val);
反之亦然
// swap a value received from the network into host-byte-order
auto val = byte_swap<network_endian, host_endian>(val_from_network);
来这里寻找一个Boost解决方案,失望地离开,但最终在其他地方找到了它。你可以使用boost::endian::endian_reverse。它被模板化/重载了所有的基元类型:
#include <iostream>
#include <iomanip>
#include "boost/endian/conversion.hpp"
int main()
{
uint32_t word = 0x01;
std::cout << std::hex << std::setfill('0') << std::setw(8) << word << std::endl;
// outputs 00000001;
uint32_t word2 = boost::endian::endian_reverse(word);
// there's also a `void ::endian_reverse_inplace(...) function
// that reverses the value passed to it in place and returns nothing
std::cout << std::hex << std::setfill('0') << std::setw(8) << word2 << std::endl;
// outputs 01000000
return 0;
}
示范
虽然,看起来c++23最终用std::byteswap解决了这个问题。(我使用的是c++17,所以这不是一个选项。)
大多数平台都有一个系统头文件,提供了有效的byteswap函数。在Linux上是<end .h>。你可以用c++很好地包装它:
#include <iostream>
#include <endian.h>
template<size_t N> struct SizeT {};
#define BYTESWAPS(bits) \
template<class T> inline T htobe(T t, SizeT<bits / 8>) { return htobe ## bits(t); } \
template<class T> inline T htole(T t, SizeT<bits / 8>) { return htole ## bits(t); } \
template<class T> inline T betoh(T t, SizeT<bits / 8>) { return be ## bits ## toh(t); } \
template<class T> inline T letoh(T t, SizeT<bits / 8>) { return le ## bits ## toh(t); }
BYTESWAPS(16)
BYTESWAPS(32)
BYTESWAPS(64)
#undef BYTESWAPS
template<class T> inline T htobe(T t) { return htobe(t, SizeT<sizeof t>()); }
template<class T> inline T htole(T t) { return htole(t, SizeT<sizeof t>()); }
template<class T> inline T betoh(T t) { return betoh(t, SizeT<sizeof t>()); }
template<class T> inline T letoh(T t) { return letoh(t, SizeT<sizeof t>()); }
int main()
{
std::cout << std::hex;
std::cout << htobe(static_cast<unsigned short>(0xfeca)) << '\n';
std::cout << htobe(0xafbeadde) << '\n';
// Use ULL suffix to specify integer constant as unsigned long long
std::cout << htobe(0xfecaefbeafdeedfeULL) << '\n';
}
输出:
cafe
deadbeaf
feeddeafbeefcafe
如果一个大端位32位无符号整数看起来像0xAABBCCDD,它等于2864434397,那么同样的32位无符号整数在小端位处理器上看起来像0xDDCCBBAA,它也等于2864434397。
如果一个大端序16位无符号空头看起来像0xAABB,它等于43707,那么同一个16位无符号空头在小端序处理器上看起来像0xBBAA,它也等于43707。
这里有两个方便的#define函数,用于将字节从小端序转换为大端序,反之亦然——>
// can be used for short, unsigned short, word, unsigned word (2-byte types)
#define BYTESWAP16(n) (((n&0xFF00)>>8)|((n&0x00FF)<<8))
// can be used for int or unsigned int or float (4-byte types)
#define BYTESWAP32(n) ((BYTESWAP16((n&0xFFFF0000)>>16))|((BYTESWAP16(n&0x0000FFFF))<<16))
// can be used for unsigned long long or double (8-byte types)
#define BYTESWAP64(n) ((BYTESWAP32((n&0xFFFFFFFF00000000)>>32))|((BYTESWAP32(n&0x00000000FFFFFFFF))<<32))