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
我有这个代码，允许我从HOST_ENDIAN_ORDER(无论它是什么)转换为LITTLE_ENDIAN_ORDER或BIG_ENDIAN_ORDER。我使用一个模板，所以如果我试图从HOST_ENDIAN_ORDER转换为LITTLE_ENDIAN_ORDER，他们恰好是相同的机器为我编译，不会生成任何代码。
下面是带有注释的代码:
// We define some constant for little, big and host endianess. Here I use
// BOOST_LITTLE_ENDIAN/BOOST_BIG_ENDIAN to check the host indianess. If you
// don't want to use boost you will have to modify this part a bit.
enum EEndian
{
LITTLE_ENDIAN_ORDER,
BIG_ENDIAN_ORDER,
#if defined(BOOST_LITTLE_ENDIAN)
HOST_ENDIAN_ORDER = LITTLE_ENDIAN_ORDER
#elif defined(BOOST_BIG_ENDIAN)
HOST_ENDIAN_ORDER = BIG_ENDIAN_ORDER
#else
#error "Impossible de determiner l'indianness du systeme cible."
#endif
};
// this function swap the bytes of values given it's size as a template
// parameter (could sizeof be used?).
template <class T, unsigned int size>
inline T SwapBytes(T value)
{
union
{
T value;
char bytes[size];
} in, out;
in.value = value;
for (unsigned int i = 0; i < size / 2; ++i)
{
out.bytes[i] = in.bytes[size - 1 - i];
out.bytes[size - 1 - i] = in.bytes[i];
}
return out.value;
}
// Here is the function you will use. Again there is two compile-time assertion
// that use the boost librarie. You could probably comment them out, but if you
// do be cautious not to use this function for anything else than integers
// types. This function need to be calles like this :
//
// int x = someValue;
// int i = EndianSwapBytes<HOST_ENDIAN_ORDER, BIG_ENDIAN_ORDER>(x);
//
template<EEndian from, EEndian to, class T>
inline T EndianSwapBytes(T value)
{
// A : La donnée à swapper à une taille de 2, 4 ou 8 octets
BOOST_STATIC_ASSERT(sizeof(T) == 2 || sizeof(T) == 4 || sizeof(T) == 8);
// A : La donnée à swapper est d'un type arithmetic
BOOST_STATIC_ASSERT(boost::is_arithmetic<T>::value);
// Si from et to sont du même type on ne swap pas.
if (from == to)
return value;
return SwapBytes<T, sizeof(T)>(value);
}
其他回答
我有这个代码，允许我从HOST_ENDIAN_ORDER(无论它是什么)转换为LITTLE_ENDIAN_ORDER或BIG_ENDIAN_ORDER。我使用一个模板，所以如果我试图从HOST_ENDIAN_ORDER转换为LITTLE_ENDIAN_ORDER，他们恰好是相同的机器为我编译，不会生成任何代码。
下面是带有注释的代码:
// We define some constant for little, big and host endianess. Here I use
// BOOST_LITTLE_ENDIAN/BOOST_BIG_ENDIAN to check the host indianess. If you
// don't want to use boost you will have to modify this part a bit.
enum EEndian
{
LITTLE_ENDIAN_ORDER,
BIG_ENDIAN_ORDER,
#if defined(BOOST_LITTLE_ENDIAN)
HOST_ENDIAN_ORDER = LITTLE_ENDIAN_ORDER
#elif defined(BOOST_BIG_ENDIAN)
HOST_ENDIAN_ORDER = BIG_ENDIAN_ORDER
#else
#error "Impossible de determiner l'indianness du systeme cible."
#endif
};
// this function swap the bytes of values given it's size as a template
// parameter (could sizeof be used?).
template <class T, unsigned int size>
inline T SwapBytes(T value)
{
union
{
T value;
char bytes[size];
} in, out;
in.value = value;
for (unsigned int i = 0; i < size / 2; ++i)
{
out.bytes[i] = in.bytes[size - 1 - i];
out.bytes[size - 1 - i] = in.bytes[i];
}
return out.value;
}
// Here is the function you will use. Again there is two compile-time assertion
// that use the boost librarie. You could probably comment them out, but if you
// do be cautious not to use this function for anything else than integers
// types. This function need to be calles like this :
//
// int x = someValue;
// int i = EndianSwapBytes<HOST_ENDIAN_ORDER, BIG_ENDIAN_ORDER>(x);
//
template<EEndian from, EEndian to, class T>
inline T EndianSwapBytes(T value)
{
// A : La donnée à swapper à une taille de 2, 4 ou 8 octets
BOOST_STATIC_ASSERT(sizeof(T) == 2 || sizeof(T) == 4 || sizeof(T) == 8);
// A : La donnée à swapper est d'un type arithmetic
BOOST_STATIC_ASSERT(boost::is_arithmetic<T>::value);
// Si from et to sont du même type on ne swap pas.
if (from == to)
return value;
return SwapBytes<T, sizeof(T)>(value);
}
在大多数POSIX系统中(虽然不是在POSIX标准中)有end .h，它可以用来确定系统使用的编码。然后是这样的:
unsigned int change_endian(unsigned int x)
{
unsigned char *ptr = (unsigned char *)&x;
return (ptr[0] << 24) | (ptr[1] << 16) | (ptr[2] << 8) | ptr[3];
}
这将交换顺序(从大端序到小端序):
如果你有数字0xDEADBEEF(在一个小端序系统中存储为0xEFBEADDE)， ptr[0]将是0xEF, ptr[1]是0xBE，等等。
但是如果你想将它用于网络，那么htons, htonl和htonll(以及它们的逆ntohs, ntohl和ntohll)将有助于从主机顺序转换到网络顺序。
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);
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 */
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))
推荐文章
- 为什么我的程序不能在Windows 7下用法语编译?
- 如何获取变量的类型?
- 什么是奇怪的重复模板模式(CRTP)?
- 连接两个向量的最佳方法是什么?
- 在c++中，是通过值传递更好，还是通过引用到const传递更好?
- 在STL中deque到底是什么?
- Windows上最好的免费c++分析器是什么?
- 如何自动转换强类型枚举为int?
- 在一个类中使用具有成员函数的泛型std::function对象
- 'for'循环中的后增量和前增量产生相同的输出
- 虚函数和纯虚函数的区别
- c++中的_tmain()和main()有什么区别?
- 内存泄漏是否正常?
- 当启用c++ 11时，std::vector性能回归
- 什么时候使用哪种指针?
