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
如果你正在使用Visual c++,请执行以下操作:包含intrin.h并调用以下函数:
对于16位数字:
unsigned short _byteswap_ushort(unsigned short value);
对于32位数字:
unsigned long _byteswap_ulong(unsigned long value);
对于64位数字:
unsigned __int64 _byteswap_uint64(unsigned __int64 value);
8位数字(字符)不需要转换。
此外,这些仅定义为无符号值,它们也适用于有符号整数。
对于浮点数和双精度数,要比普通整数困难得多,因为它们可能在主机的字节顺序中。你可以在大端机器上得到小端浮点数,反之亦然。
其他编译器也有类似的特性。
例如,在GCC中,你可以直接调用一些内置程序,如下所示:
uint32_t __builtin_bswap32 (uint32_t x)
uint64_t __builtin_bswap64 (uint64_t x)
(不需要包含任何东西)。Afaik bits.h也以非gcc为中心的方式声明了相同的函数。
16位交换就是位旋转。
顺便说一句,调用这些内在函数而不是调用自己的内在函数可以获得最好的性能和代码密度。
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 */
查找位移位,因为这基本上是所有你需要做的交换从小->大端dian。然后根据位的大小,改变位移位的方式。
认真……我不明白为什么所有的解决方案都那么复杂!最简单、最通用的模板函数如何?它可以在任何操作系统的任何情况下交换任何大小的任何类型????
template <typename T>
void SwapEnd(T& var)
{
static_assert(std::is_pod<T>::value, "Type must be POD type for safety");
std::array<char, sizeof(T)> varArray;
std::memcpy(varArray.data(), &var, sizeof(T));
for(int i = 0; i < static_cast<int>(sizeof(var)/2); i++)
std::swap(varArray[sizeof(var) - 1 - i],varArray[i]);
std::memcpy(&var, varArray.data(), sizeof(T));
}
这是C和c++结合的神奇力量!只需逐个字符交换原始变量。
要点1:没有操作符:请记住,我没有使用简单的赋值操作符“=”,因为当反转字节序时,一些对象将被打乱,复制构造函数(或赋值操作符)将不起作用。因此,一个字符一个字符地复制它们更加可靠。
Point 2: Be aware of alignment issues: Notice that we're copying to and from an array, which is the right thing to do because the C++ compiler doesn't guarantee that we can access unaligned memory (this answer was updated from its original form for this). For example, if you allocate uint64_t, your compiler cannot guarantee that you can access the 3rd byte of that as a uint8_t. Therefore, the right thing to do is to copy this to a char array, swap it, then copy it back (so no reinterpret_cast). Notice that compilers are mostly smart enough to convert what you did back to a reinterpret_cast if they're capable of accessing individual bytes regardless of alignment.
使用此函数:
double x = 5;
SwapEnd(x);
现在x的字节序不同了。
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。