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
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 */
其他回答
摘自Rob Pike的《字节顺序谬误》:
假设数据流有一个小端编码的32位整数。下面是如何提取它(假设无符号字节):
i = (data[0]<<0) | (data[1]<<8) | (data[2]<<16) | ((unsigned)data[3]<<24);
如果它是big-endian,下面是如何提取它:
i = (data[3]<<0) | (data[2]<<8) | (data[1]<<16) | ((unsigned)data[0]<<24);
TL;DR:不要担心你的平台原生顺序,重要的是你从中读取的流的字节顺序,你最好希望它是定义良好的。
注1:这里int和unsigned int是32位,否则类型可能需要调整。
注2:最后一个字节必须在移位前显式转换为unsigned,因为默认情况下它被提升为int,移位24位意味着操作符号位,这是未定义行为。
我喜欢这个,只是为了风格:-)
long swap(long i) {
char *c = (char *) &i;
return * (long *) (char[]) {c[3], c[2], c[1], c[0] };
}
下面介绍如何读取以IEEE 754 64位格式存储的double,即使您的主机使用不同的系统。
/*
* read a double from a stream in ieee754 format regardless of host
* encoding.
* fp - the stream
* bigendian - set to if big bytes first, clear for little bytes
* first
*
*/
double freadieee754(FILE *fp, int bigendian)
{
unsigned char buff[8];
int i;
double fnorm = 0.0;
unsigned char temp;
int sign;
int exponent;
double bitval;
int maski, mask;
int expbits = 11;
int significandbits = 52;
int shift;
double answer;
/* read the data */
for (i = 0; i < 8; i++)
buff[i] = fgetc(fp);
/* just reverse if not big-endian*/
if (!bigendian)
{
for (i = 0; i < 4; i++)
{
temp = buff[i];
buff[i] = buff[8 - i - 1];
buff[8 - i - 1] = temp;
}
}
sign = buff[0] & 0x80 ? -1 : 1;
/* exponet in raw format*/
exponent = ((buff[0] & 0x7F) << 4) | ((buff[1] & 0xF0) >> 4);
/* read inthe mantissa. Top bit is 0.5, the successive bits half*/
bitval = 0.5;
maski = 1;
mask = 0x08;
for (i = 0; i < significandbits; i++)
{
if (buff[maski] & mask)
fnorm += bitval;
bitval /= 2.0;
mask >>= 1;
if (mask == 0)
{
mask = 0x80;
maski++;
}
}
/* handle zero specially */
if (exponent == 0 && fnorm == 0)
return 0.0;
shift = exponent - ((1 << (expbits - 1)) - 1); /* exponent = shift + bias */
/* nans have exp 1024 and non-zero mantissa */
if (shift == 1024 && fnorm != 0)
return sqrt(-1.0);
/*infinity*/
if (shift == 1024 && fnorm == 0)
{
#ifdef INFINITY
return sign == 1 ? INFINITY : -INFINITY;
#endif
return (sign * 1.0) / 0.0;
}
if (shift > -1023)
{
answer = ldexp(fnorm + 1.0, shift);
return answer * sign;
}
else
{
/* denormalised numbers */
if (fnorm == 0.0)
return 0.0;
shift = -1022;
while (fnorm < 1.0)
{
fnorm *= 2;
shift--;
}
answer = ldexp(fnorm, shift);
return answer * sign;
}
}
对于这套函数的其余部分,包括写和整数例程,请参阅我的github项目
https://github.com/MalcolmMcLean/ieee754
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 */
c++20无分支版本,现在std::endian已经存在,但在c++23之前增加了std::byteswap
#include <bit>
#include <type_traits>
#include <concepts>
#include <array>
#include <cstring>
#include <iostream>
#include <bitset>
template <int LEN, int OFF=LEN/2>
class do_swap
{
// FOR 8 bytes:
// LEN=8 (LEN/2==4) <H><G><F><E><D><C><B><A>
// OFF=4: FROM=0, TO=7 => [A]<G><F><E><D><C><B>[H]
// OFF=3: FROM=1, TO=6 => [A][B]<F><E><D><C>[G][H]
// OFF=2: FROM=2, TO=5 => [A][B][C]<E><D>[F][G][H]
// OFF=1: FROM=3, TO=4 => [A][B][C][D][E][F][G][H]
// OFF=0: FROM=4, TO=3 => DONE
public:
enum consts {FROM=LEN/2-OFF, TO=(LEN-1)-FROM};
using NXT=do_swap<LEN, OFF-1>;
// flip the first and last for the current iteration's range
static void flip(std::array<std::byte, LEN>& b)
{
std::byte tmp=b[FROM];
b[FROM]=b[TO];
b[TO]=tmp;
NXT::flip(b);
}
};
template <int LEN>
class do_swap<LEN, 0> // STOP the template recursion
{
public:
static void flip(std::array<std::byte, LEN>&)
{
}
};
template<std::integral T, std::endian TO, std::endian FROM=std::endian::native>
requires ((TO==std::endian::big) || (TO==std::endian::little))
&& ((FROM==std::endian::big) || (FROM==std::endian::little))
class endian_swap
{
public:
enum consts {BYTE_COUNT=sizeof(T)};
static T cvt(const T integral)
{
// if FROM and TO are the same -- nothing to do
if (TO==FROM)
{
return integral;
}
// endian::big --> endian::little is the same as endian::little --> endian::big
// the bytes have to be reversed
// memcpy seems to be the most supported way to do byte swaps in a defined way
std::array<std::byte, BYTE_COUNT> bytes;
std::memcpy(&bytes, &integral, BYTE_COUNT);
do_swap<BYTE_COUNT>::flip(bytes);
T ret;
std::memcpy(&ret, &bytes, BYTE_COUNT);
return ret;
}
};
std::endian big()
{
return std::endian::big;
}
std::endian little()
{
return std::endian::little;
}
std::endian native()
{
return std::endian::native;
}
long long swap_to_big(long long x)
{
return endian_swap<long long, std::endian::big>::cvt(x);
}
long long swap_to_little(long long x)
{
return endian_swap<long long, std::endian::little>::cvt(x);
}
void show(std::string label, long long x)
{
std::cout << label << "\t: " << std::bitset<64>(x) << " (" << x << ")" << std::endl;
}
int main(int argv, char ** argc)
{
long long init=0xF8FCFEFF7F3F1F0;
long long to_big=swap_to_big(init);
long long to_little=swap_to_little(init);
show("Init", init);
show(">big", to_big);
show(">little", to_little);
}