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);

似乎安全的方法是在每个单词上使用“顿音”。所以，如果你有。

std::vector<uint16_t> storage(n);  // where n is the number to be converted

// the following would do the trick
std::transform(word_storage.cbegin(), word_storage.cend()
  , word_storage.begin(), [](const uint16_t input)->uint16_t {
  return htons(input); });

如果您是在一个大端系统上，那么上面的代码将是一个无操作，因此我将查找您的平台使用的任何编译时条件，以确定htons是否是一个无操作。毕竟是O(n)在Mac上，它会是这样的……

#if (__DARWIN_BYTE_ORDER != __DARWIN_BIG_ENDIAN)
std::transform(word_storage.cbegin(), word_storage.cend()
  , word_storage.begin(), [](const uint16_t input)->uint16_t {
  return htons(input); });
#endif

实现优化器友好的未对齐非就地末端访问器的可移植技术。它们处理每个编译器、每个边界对齐和每个字节排序。这些未对齐的例程被补充或讨论，取决于本机的端序和对齐方式。部分列出，但你懂的。BO*是基于本机字节排序的常数值。

uint32_t sw_get_uint32_1234(pu32)
uint32_1234 *pu32;
{
  union {
    uint32_1234 u32_1234;
    uint32_t u32;
  } bou32;
  bou32.u32_1234[0] = (*pu32)[BO32_0];
  bou32.u32_1234[1] = (*pu32)[BO32_1];
  bou32.u32_1234[2] = (*pu32)[BO32_2];
  bou32.u32_1234[3] = (*pu32)[BO32_3];
  return(bou32.u32);
}

void sw_set_uint32_1234(pu32, u32)
uint32_1234 *pu32;
uint32_t u32;
{
  union {
    uint32_1234 u32_1234;
    uint32_t u32;
  } bou32;
  bou32.u32 = u32;
  (*pu32)[BO32_0] = bou32.u32_1234[0];
  (*pu32)[BO32_1] = bou32.u32_1234[1];
  (*pu32)[BO32_2] = bou32.u32_1234[2];
  (*pu32)[BO32_3] = bou32.u32_1234[3];
}

#if HAS_SW_INT64
int64 sw_get_int64_12345678(pi64)
int64_12345678 *pi64;
{
  union {
    int64_12345678 i64_12345678;
    int64 i64;
  } boi64;
  boi64.i64_12345678[0] = (*pi64)[BO64_0];
  boi64.i64_12345678[1] = (*pi64)[BO64_1];
  boi64.i64_12345678[2] = (*pi64)[BO64_2];
  boi64.i64_12345678[3] = (*pi64)[BO64_3];
  boi64.i64_12345678[4] = (*pi64)[BO64_4];
  boi64.i64_12345678[5] = (*pi64)[BO64_5];
  boi64.i64_12345678[6] = (*pi64)[BO64_6];
  boi64.i64_12345678[7] = (*pi64)[BO64_7];
  return(boi64.i64);
}
#endif

int32_t sw_get_int32_3412(pi32)
int32_3412 *pi32;
{
  union {
    int32_3412 i32_3412;
    int32_t i32;
  } boi32;
  boi32.i32_3412[2] = (*pi32)[BO32_0];
  boi32.i32_3412[3] = (*pi32)[BO32_1];
  boi32.i32_3412[0] = (*pi32)[BO32_2];
  boi32.i32_3412[1] = (*pi32)[BO32_3];
  return(boi32.i32);
}

void sw_set_int32_3412(pi32, i32)
int32_3412 *pi32;
int32_t i32;
{
  union {
    int32_3412 i32_3412;
    int32_t i32;
  } boi32;
  boi32.i32 = i32;
  (*pi32)[BO32_0] = boi32.i32_3412[2];
  (*pi32)[BO32_1] = boi32.i32_3412[3];
  (*pi32)[BO32_2] = boi32.i32_3412[0];
  (*pi32)[BO32_3] = boi32.i32_3412[1];
}

uint32_t sw_get_uint32_3412(pu32)
uint32_3412 *pu32;
{
  union {
    uint32_3412 u32_3412;
    uint32_t u32;
  } bou32;
  bou32.u32_3412[2] = (*pu32)[BO32_0];
  bou32.u32_3412[3] = (*pu32)[BO32_1];
  bou32.u32_3412[0] = (*pu32)[BO32_2];
  bou32.u32_3412[1] = (*pu32)[BO32_3];
  return(bou32.u32);
}

void sw_set_uint32_3412(pu32, u32)
uint32_3412 *pu32;
uint32_t u32;
{
  union {
    uint32_3412 u32_3412;
    uint32_t u32;
  } bou32;
  bou32.u32 = u32;
  (*pu32)[BO32_0] = bou32.u32_3412[2];
  (*pu32)[BO32_1] = bou32.u32_3412[3];
  (*pu32)[BO32_2] = bou32.u32_3412[0];
  (*pu32)[BO32_3] = bou32.u32_3412[1];
}

float sw_get_float_1234(pf)
float_1234 *pf;
{
  union {
    float_1234 f_1234;
    float f;
  } bof;
  bof.f_1234[0] = (*pf)[BO32_0];
  bof.f_1234[1] = (*pf)[BO32_1];
  bof.f_1234[2] = (*pf)[BO32_2];
  bof.f_1234[3] = (*pf)[BO32_3];
  return(bof.f);
}

void sw_set_float_1234(pf, f)
float_1234 *pf;
float f;
{
  union {
    float_1234 f_1234;
    float f;
  } bof;
  bof.f = (float)f;
  (*pf)[BO32_0] = bof.f_1234[0];
  (*pf)[BO32_1] = bof.f_1234[1];
  (*pf)[BO32_2] = bof.f_1234[2];
  (*pf)[BO32_3] = bof.f_1234[3];
}

double sw_get_double_12345678(pd)
double_12345678 *pd;
{
  union {
    double_12345678 d_12345678;
    double d;
  } bod;
  bod.d_12345678[0] = (*pd)[BO64_0];
  bod.d_12345678[1] = (*pd)[BO64_1];
  bod.d_12345678[2] = (*pd)[BO64_2];
  bod.d_12345678[3] = (*pd)[BO64_3];
  bod.d_12345678[4] = (*pd)[BO64_4];
  bod.d_12345678[5] = (*pd)[BO64_5];
  bod.d_12345678[6] = (*pd)[BO64_6];
  bod.d_12345678[7] = (*pd)[BO64_7];
  return(bod.d);
}

void sw_set_double_12345678(pd, d)
double_12345678 *pd;
double d;
{
  union {
    double_12345678 d_12345678;
    double d;
  } bod;
  bod.d = d;
  (*pd)[BO64_0] = bod.d_12345678[0];
  (*pd)[BO64_1] = bod.d_12345678[1];
  (*pd)[BO64_2] = bod.d_12345678[2];
  (*pd)[BO64_3] = bod.d_12345678[3];
  (*pd)[BO64_4] = bod.d_12345678[4];
  (*pd)[BO64_5] = bod.d_12345678[5];
  (*pd)[BO64_6] = bod.d_12345678[6];
  (*pd)[BO64_7] = bod.d_12345678[7];
}

如果不与访问器一起使用，这些类型def的好处是会引发编译器错误，从而减少被遗忘的访问器错误。

typedef char int8_1[1], uint8_1[1];

typedef char int16_12[2], uint16_12[2]; /* little endian */
typedef char int16_21[2], uint16_21[2]; /* big endian */

typedef char int24_321[3], uint24_321[3]; /* Alpha Micro, PDP-11 */

typedef char int32_1234[4], uint32_1234[4]; /* little endian */
typedef char int32_3412[4], uint32_3412[4]; /* Alpha Micro, PDP-11 */
typedef char int32_4321[4], uint32_4321[4]; /* big endian */

typedef char int64_12345678[8], uint64_12345678[8]; /* little endian */
typedef char int64_34128756[8], uint64_34128756[8]; /* Alpha Micro, PDP-11 */
typedef char int64_87654321[8], uint64_87654321[8]; /* big endian */

typedef char float_1234[4]; /* little endian */
typedef char float_3412[4]; /* Alpha Micro, PDP-11 */
typedef char float_4321[4]; /* big endian */

typedef char double_12345678[8]; /* little endian */
typedef char double_78563412[8]; /* Alpha Micro? */
typedef char double_87654321[8]; /* big endian */

和在C中一样:

short big = 0xdead;
short little = (((big & 0xff)<<8) | ((big & 0xff00)>>8));

您还可以声明一个无符号字符的向量，将输入值memcpy放入其中，将字节反向转换为另一个向量，然后将字节memcpy取出，但这将花费比旋转位长几个数量级的时间，特别是对于64位值。

哇，我简直不敢相信我在这里读到的一些答案。实际上汇编中有一条指令比其他任何程序都快。bswap。你可以简单地写一个这样的函数…

__declspec(naked) uint32_t EndianSwap(uint32 value)
{
    __asm
    {
        mov eax, dword ptr[esp + 4]
        bswap eax
        ret
    }
}

它比之前提到的内在函数要快得多。我把它们拆开看了看。上面的函数没有序言/尾声，因此实际上没有任何开销。

unsigned long _byteswap_ulong(unsigned long value);

做16位同样容易，除了你会使用xchg al，啊。Bswap仅适用于32位寄存器。

64位有点棘手，但也不过分。比上面所有带有循环和模板的例子都要好得多。

这里有一些注意事项……首先，bswap只能在80x486以上的CPU上使用。有人打算在386上运行吗?!?如果是这样，你仍然可以用…替换bswap。

mov ebx, eax
shr ebx, 16
xchg al, ah
xchg bl, bh
shl eax, 16
or eax, ebx

内联汇编也只能在Visual Studio的x86代码中使用。裸函数不能内衬，而且在x64版本中也不可用。对于那个实例，你必须使用编译器的内在函数。

我们已经用模板做到了这一点。你可以这样做:

// Specialization for 2-byte types.
template<>
inline void endian_byte_swapper< 2 >(char* dest, char const* src)
{
    // Use bit manipulations instead of accessing individual bytes from memory, much faster.
    ushort* p_dest = reinterpret_cast< ushort* >(dest);
    ushort const* const p_src = reinterpret_cast< ushort const* >(src);
    *p_dest = (*p_src >> 8) | (*p_src << 8);
}

// Specialization for 4-byte types.
template<>
inline void endian_byte_swapper< 4 >(char* dest, char const* src)
{
    // Use bit manipulations instead of accessing individual bytes from memory, much faster.
    uint* p_dest = reinterpret_cast< uint* >(dest);
    uint const* const p_src = reinterpret_cast< uint const* >(src);
    *p_dest = (*p_src >> 24) | ((*p_src & 0x00ff0000) >> 8) | ((*p_src & 0x0000ff00) << 8) | (*p_src << 24);
}