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
在模板函数中围绕枢轴使用老式的3-step-xor技巧进行字节交换，提供了一个灵活、快速的O(ln2)解决方案，不需要库，这里的风格也拒绝1字节类型:
template<typename T>void swap(T &t){
for(uint8_t pivot = 0; pivot < sizeof(t)/2; pivot ++){
*((uint8_t *)&t + pivot) ^= *((uint8_t *)&t+sizeof(t)-1- pivot);
*((uint8_t *)&t+sizeof(t)-1- pivot) ^= *((uint8_t *)&t + pivot);
*((uint8_t *)&t + pivot) ^= *((uint8_t *)&t+sizeof(t)-1- pivot);
}
}
其他回答
简单地说:
#include <climits>
template <typename T>
T swap_endian(T u)
{
static_assert (CHAR_BIT == 8, "CHAR_BIT != 8");
union
{
T u;
unsigned char u8[sizeof(T)];
} source, dest;
source.u = u;
for (size_t k = 0; k < sizeof(T); k++)
dest.u8[k] = source.u8[sizeof(T) - k - 1];
return dest.u;
}
用法:swap_endian < uint32_t >(42)。
从大端序到小端序的过程与从小端序到大端序的过程是一样的。
下面是一些示例代码:
void swapByteOrder(unsigned short& us)
{
us = (us >> 8) |
(us << 8);
}
void swapByteOrder(unsigned int& ui)
{
ui = (ui >> 24) |
((ui<<8) & 0x00FF0000) |
((ui>>8) & 0x0000FF00) |
(ui << 24);
}
void swapByteOrder(unsigned long long& ull)
{
ull = (ull >> 56) |
((ull<<40) & 0x00FF000000000000) |
((ull<<24) & 0x0000FF0000000000) |
((ull<<8) & 0x000000FF00000000) |
((ull>>8) & 0x00000000FF000000) |
((ull>>24) & 0x0000000000FF0000) |
((ull>>40) & 0x000000000000FF00) |
(ull << 56);
}
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);
}
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。)
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 */
