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
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);
其他回答
如果您采用反转单词中位序的常见模式，并剔除每个字节中反转位的部分，那么您将只剩下反转单词中的字节的部分。对于64位:
x = ((x & 0x00000000ffffffff) << 32) ^ ((x >> 32) & 0x00000000ffffffff);
x = ((x & 0x0000ffff0000ffff) << 16) ^ ((x >> 16) & 0x0000ffff0000ffff);
x = ((x & 0x00ff00ff00ff00ff) << 8) ^ ((x >> 8) & 0x00ff00ff00ff00ff);
编译器应该清除多余的位屏蔽操作(我把它们留在了突出显示模式)，但如果它没有，你可以这样重写第一行:
x = ( x << 32) ^ (x >> 32);
在大多数架构上，这通常应该简化为一条旋转指令(忽略整个操作可能是一条指令)。
在RISC处理器上，大而复杂的常量可能会导致编译困难。不过，您可以简单地计算前一个的每个常数。像这样:
uint64_t k = 0x00000000ffffffff; /* compiler should know a trick for this */
x = ((x & k) << 32) ^ ((x >> 32) & k);
k ^= k << 16;
x = ((x & k) << 16) ^ ((x >> 16) & k);
k ^= k << 8;
x = ((x & k) << 8) ^ ((x >> 8) & k);
如果你愿意，你可以把它写成一个循环。这样做效率不高，只是为了好玩:
int i = sizeof(x) * CHAR_BIT / 2;
uintmax_t k = (1 << i) - 1;
while (i >= 8)
{
x = ((x & k) << i) ^ ((x >> i) & k);
i >>= 1;
k ^= k << i;
}
为了完整起见，这里是第一种形式的简化32位版本:
x = ( x << 16) ^ (x >> 16);
x = ((x & 0x00ff00ff) << 8) ^ ((x >> 8) & 0x00ff00ff);
如果你有c++ 17，那么添加这个头文件
#include <algorithm>
使用这个模板函数交换字节:
template <typename T>
void swapEndian(T& buffer)
{
static_assert(std::is_pod<T>::value, "swapEndian support POD type only");
char* startIndex = static_cast<char*>((void*)buffer.data());
char* endIndex = startIndex + sizeof(buffer);
std::reverse(startIndex, endIndex);
}
这样称呼它:
swapEndian (stlContainer);
这里有一个基本的函数来交换大小端序。它是基本的，但不需要补充库。
void endianness_swap(uint32_t& val) {
uint8_t a, b, c;
a = (val & 0xFF000000) >> 24;
b = (val & 0x00FF0000) >> 16;
c = (val & 0x0000FF00) >> 8;
val=(val & 0x000000FF) << 24;
val = val + (c << 16) + (b << 8) + (a);
}
有一个叫做BSWAP的汇编指令可以帮你做交换，非常快。 你可以在这里阅读。
Visual Studio，或者更准确地说是Visual c++运行时库，为此提供了平台intrinsic，称为_byteswap_ushort()、_byteswap_ulong()和_byteswap_int64()。其他平台应该也有类似的情况，但我不知道它们会被称为什么。
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);
