C - 浮點數的序列化（浮點數，雙精度數）

Question

如何將浮點數轉換為字節序列，以便它可以保存在文件中？ 這種算法必須快速且高度便攜。 它必須允許相反的操作，反序列化。 如果每個值（持久空間）只需要非常微小的多余位，那就太好了。

Answer 1

假設您正在使用主流編譯器，C和C ++中的浮點值遵循IEEE標准，並且當以二進制形式寫入文件時，可以在任何其他平台中恢復，前提是您使用相同的字節endianess進行寫入和讀取。 所以我的建議是：選擇一個選擇的結尾，在寫作之前或閱讀之后，檢查該結尾是否與當前平台相同; 如果沒有，只需交換字節。

Answer 2

您始終可以按固定的字節順序（小端或大端）轉換為IEEE-754格式。 對於大多數機器來說，根本不需要任何東西，或者需要簡單的字節交換來序列化和反序列化。 一台本機不支持IEEE-754的機器需要編寫一個轉換器，但使用ldexp和frexp（標准C庫函數）和位混洗這樣做並不是太難。

Answer 3

這可能會給你一個良好的開端 - 它將一個浮點值打包到一個int和long long對中，然后你可以按照通常的方式進行序列化。

#define FRAC_MAX 9223372036854775807LL /* 2**63 - 1 */

struct dbl_packed
{
    int exp;
    long long frac;
};

void pack(double x, struct dbl_packed *r)
{
    double xf = fabs(frexp(x, &r->exp)) - 0.5;

    if (xf < 0.0)
    {
        r->frac = 0;
        return;
    }

    r->frac = 1 + (long long)(xf * 2.0 * (FRAC_MAX - 1));

    if (x < 0.0)
        r->frac = -r->frac;
}

double unpack(const struct dbl_packed *p)
{
    double xf, x;

    if (p->frac == 0)
        return 0.0;

    xf = ((double)(llabs(p->frac) - 1) / (FRAC_MAX - 1)) / 2.0;

    x = ldexp(xf + 0.5, p->exp);

    if (p->frac < 0)
        x = -x;

    return x;
}

Answer 4

你是什​​么意思，“便攜式”？

為了便於攜帶，請記住將數字保持在標准中定義的限制范圍內：使用超出這些限制的單個數字，並將所有可移植性排除在外。

double planck_time = 5.39124E-44; /* second */

---

5.2.4.2.2浮點類型的特征<float.h>

[...]
10   The values given in the following list shall be replaced by constant
     expressions with implementation-defined values [...]
11   The values given in the following list shall be replaced by constant
     expressions with implementation-defined values [...]
12   The values given in the following list shall be replaced by constant
     expressions with implementation-defined (positive) values [...]
[...]

請注意所有這些子句中定義的實現 。

Answer 5

轉換為ascii表示將是最簡單的，但如果你需要處理大量的浮點數，那么你當然應該使用二進制數。 但如果您關心可移植性，這可能是一個棘手的問題。 浮點數在不同的機器中表示不同。

如果您不想使用固定庫，那么您的浮點二進制序列化器/解串器將只需要在每個位落地及其代表的位置上簽訂“合同”。

這是一個有趣的網站，以幫助： 鏈接 。

Answer 6

sprintf，fprintf？ 你沒有比那更便攜了。

Answer 7

您需要什么級別的便攜性？ 如果要在與生成的操作系統相同的計算機上讀取文件，則使用二進制文件並保存和恢復位模式應該可以正常工作。 否則正如boytheo所說，ASCII是你的朋友。

Answer 8

此版本每個浮點值僅超過一個字節以指示字節序。 但我認為，它仍然不是很便攜。

#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <ctype.h>

#define LITEND      'L'
#define BIGEND      'B'

typedef short               INT16;
typedef int                 INT32;
typedef double              vec1_t;

 typedef struct {
    FILE            *fp;
} WFILE, RFILE;

#define w_byte(c, p)    putc((c), (p)->fp)
#define r_byte(p)       getc((p)->fp)

static void w_vec1(vec1_t v1_Val, WFILE *p)
{
    INT32   i;
    char    *pc_Val;

    pc_Val = (char *)&v1_Val;

    w_byte(LITEND, p);
    for (i = 0; i<sizeof(vec1_t); i++)
    {
        w_byte(pc_Val[i], p);
    }
}


static vec1_t r_vec1(RFILE *p)
{
    INT32   i;
    vec1_t  v1_Val;
    char    c_Type,
            *pc_Val;

    pc_Val = (char *)&v1_Val;

    c_Type = r_byte(p);
    if (c_Type==LITEND)
    {
        for (i = 0; i<sizeof(vec1_t); i++)
        {
            pc_Val[i] = r_byte(p);
        }
    }
    return v1_Val;
}

int main(void)
{
    WFILE   x_FileW,
            *px_FileW = &x_FileW;
    RFILE   x_FileR,
            *px_FileR = &x_FileR;

    vec1_t  v1_Val;
    INT32   l_Val;
    char    *pc_Val = (char *)&v1_Val;
    INT32   i;

    px_FileW->fp = fopen("test.bin", "w");
    v1_Val = 1234567890.0987654321;
    printf("v1_Val before write = %.20f \n", v1_Val);
    w_vec1(v1_Val, px_FileW);
    fclose(px_FileW->fp);

    px_FileR->fp = fopen("test.bin", "r");
    v1_Val = r_vec1(px_FileR);
    printf("v1_Val after read = %.20f \n", v1_Val);
    fclose(px_FileR->fp);
    return 0;
}

Answer 9

開始了。

便攜式IEEE 754序列化/反序列化，無論機器的內部浮點表示如何，都應該工作。

https://github.com/MalcolmMcLean/ieee754

/*
* 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;
    }
}


/*
* write a double to a stream in ieee754 format regardless of host
*  encoding.
*  x - number to write
*  fp - the stream
*  bigendian - set to write big bytes first, elee write litle bytes
*              first
*  Returns: 0 or EOF on error
*  Notes: different NaN types and negative zero not preserved.
*         if the number is too big to represent it will become infinity
*         if it is too small to represent it will become zero.
*/
int fwriteieee754(double x, FILE *fp, int bigendian)
{
    int shift;
    unsigned long sign, exp, hibits, hilong, lowlong;
    double fnorm, significand;
    int expbits = 11;
    int significandbits = 52;

    /* zero (can't handle signed zero) */
    if (x == 0)
    {
        hilong = 0;
        lowlong = 0;
        goto writedata;
    }
    /* infinity */
    if (x > DBL_MAX)
    {
        hilong = 1024 + ((1 << (expbits - 1)) - 1);
        hilong <<= (31 - expbits);
        lowlong = 0;
        goto writedata;
    }
    /* -infinity */
    if (x < -DBL_MAX)
    {
        hilong = 1024 + ((1 << (expbits - 1)) - 1);
        hilong <<= (31 - expbits);
        hilong |= (1 << 31);
        lowlong = 0;
        goto writedata;
    }
    /* NaN - dodgy because many compilers optimise out this test, but
    *there is no portable isnan() */
    if (x != x)
    {
        hilong = 1024 + ((1 << (expbits - 1)) - 1);
        hilong <<= (31 - expbits);
        lowlong = 1234;
        goto writedata;
    }

    /* get the sign */
    if (x < 0) { sign = 1; fnorm = -x; }
    else { sign = 0; fnorm = x; }

    /* get the normalized form of f and track the exponent */
    shift = 0;
    while (fnorm >= 2.0) { fnorm /= 2.0; shift++; }
    while (fnorm < 1.0) { fnorm *= 2.0; shift--; }

    /* check for denormalized numbers */
    if (shift < -1022)
    {
        while (shift < -1022) { fnorm /= 2.0; shift++; }
        shift = -1023;
    }
    /* out of range. Set to infinity */
    else if (shift > 1023)
    {
        hilong = 1024 + ((1 << (expbits - 1)) - 1);
        hilong <<= (31 - expbits);
        hilong |= (sign << 31);
        lowlong = 0;
        goto writedata;
    }
    else
        fnorm = fnorm - 1.0; /* take the significant bit off mantissa */

    /* calculate the integer form of the significand */
    /* hold it in a  double for now */

    significand = fnorm * ((1LL << significandbits) + 0.5f);


    /* get the biased exponent */
    exp = shift + ((1 << (expbits - 1)) - 1); /* shift + bias */

    /* put the data into two longs (for convenience) */
    hibits = (long)(significand / 4294967296);
    hilong = (sign << 31) | (exp << (31 - expbits)) | hibits;
    x = significand - hibits * 4294967296;
    lowlong = (unsigned long)(significand - hibits * 4294967296);

writedata:
    /* write the bytes out to the stream */
    if (bigendian)
    {
        fputc((hilong >> 24) & 0xFF, fp);
        fputc((hilong >> 16) & 0xFF, fp);
        fputc((hilong >> 8) & 0xFF, fp);
        fputc(hilong & 0xFF, fp);

        fputc((lowlong >> 24) & 0xFF, fp);
        fputc((lowlong >> 16) & 0xFF, fp);
        fputc((lowlong >> 8) & 0xFF, fp);
        fputc(lowlong & 0xFF, fp);
    }
    else
    {
        fputc(lowlong & 0xFF, fp);
        fputc((lowlong >> 8) & 0xFF, fp);
        fputc((lowlong >> 16) & 0xFF, fp);
        fputc((lowlong >> 24) & 0xFF, fp);

        fputc(hilong & 0xFF, fp);
        fputc((hilong >> 8) & 0xFF, fp);
        fputc((hilong >> 16) & 0xFF, fp);
        fputc((hilong >> 24) & 0xFF, fp);
    }
    return ferror(fp);
}

Answer 10

fwrite（），fread（）？ 你可能會想要二進制文件，除非你想犧牲你在程序中執行的精度然后fwrite（）fread（），否則你不能將字節打包得更緊。 漂浮一個; 雙b; α=（浮點）B; 的fwrite（＆A，1，的sizeof（a）中，FP）;

如果您攜帶不同的浮點格式，它們可能無法以直接的二進制方式進行轉換，因此您可能必須分開這些位並執行數學計算，這需要加上此功能，等等.IEEE 754是一個可怕的標准使用但廣泛，所以它會盡量減少努力。