c - 是否有无法编译它的 C 编译器？

Question

我在我的分析器中闲逛了一段时间，试图弄清楚如何加速一个在日期解析方面存在瓶颈的常见日志解析器，我尝试了各种算法来加快速度。

我尝试过的对我来说最快的东西也是迄今为止最可读的，但可能是非标准的 C。

这在 GCC 中运作良好, icc ，以及我非常老旧且挑剔的 SGI 编译器。由于这是一个非常可读的优化，它在哪里没有按照我的要求进行？

static int parseMonth(const char *input) {
    int rv=-1;
    int inputInt=0;
    int i=0;

    for(i=0; i<4 && input[i]; i++) {
        inputInt = (inputInt << 8) | input[i];
    }

    switch(inputInt) {
        case 'Jan/': rv=0; break;
        case 'Feb/': rv=1; break;
        case 'Mar/': rv=2; break;
        case 'Apr/': rv=3; break;
        case 'May/': rv=4; break;
        case 'Jun/': rv=5; break;
        case 'Jul/': rv=6; break;
        case 'Aug/': rv=7; break;
        case 'Sep/': rv=8; break;
        case 'Oct/': rv=9; break;
        case 'Nov/': rv=10; break;
        case 'Dec/': rv=11; break;
    }
    return rv;
}

Answer 1

Solaris 10 - SPARC - SUN 编译器。

测试代码:

#include <stdio.h>

static int parseMonth(const char *input) {
    int rv=-1;
    int inputInt=0;
    int i=0;

    for(i=0; i<4 && input[i]; i++) {
        inputInt = (inputInt << 8) | input[i];
    }

    switch(inputInt) {
        case 'Jan/': rv=0; break;
        case 'Feb/': rv=1; break;
        case 'Mar/': rv=2; break;
        case 'Apr/': rv=3; break;
        case 'May/': rv=4; break;
        case 'Jun/': rv=5; break;
        case 'Jul/': rv=6; break;
        case 'Aug/': rv=7; break;
        case 'Sep/': rv=8; break;
        case 'Oct/': rv=9; break;
        case 'Nov/': rv=10; break;
        case 'Dec/': rv=11; break;
    }

    return rv;
}

static const struct
{
    char *data;
    int   result;
} test_case[] =
{
    { "Jan/", 0 },
    { "Feb/", 1 },
    { "Mar/", 2 },
    { "Apr/", 3 },
    { "May/", 4 },
    { "Jun/", 5 },
    { "Jul/", 6 },
    { "Aug/", 7 },
    { "Sep/", 8 },
    { "Oct/", 9 },
    { "Nov/", 10 },
    { "Dec/", 11 },
    { "aJ/n", -1 },
};

#define DIM(x) (sizeof(x)/sizeof(*(x)))

int main(void)
{
    size_t i;
    int    result;

    for (i = 0; i < DIM(test_case); i++)
    {
        result = parseMonth(test_case[i].data);
        if (result != test_case[i].result)
            printf("!! FAIL !! %s (got %d, wanted %d)\n",
                   test_case[i].data, result, test_case[i].result);
    }
    return(0);
}

结果(GCC 3.4.2 和 Sun):

$ gcc -O xx.c -o xx
xx.c:14:14: warning: multi-character character constant
xx.c:15:14: warning: multi-character character constant
xx.c:16:14: warning: multi-character character constant
xx.c:17:14: warning: multi-character character constant
xx.c:18:14: warning: multi-character character constant
xx.c:19:14: warning: multi-character character constant
xx.c:20:14: warning: multi-character character constant
xx.c:21:14: warning: multi-character character constant
xx.c:22:14: warning: multi-character character constant
xx.c:23:14: warning: multi-character character constant
xx.c:24:14: warning: multi-character character constant
xx.c:25:14: warning: multi-character character constant
$ ./xx
$ cc -o xx xx.c
$ ./xx
!! FAIL !! Jan/ (got -1, wanted 0)
!! FAIL !! Feb/ (got -1, wanted 1)
!! FAIL !! Mar/ (got -1, wanted 2)
!! FAIL !! Apr/ (got -1, wanted 3)
!! FAIL !! May/ (got -1, wanted 4)
!! FAIL !! Jun/ (got -1, wanted 5)
!! FAIL !! Jul/ (got -1, wanted 6)
!! FAIL !! Aug/ (got -1, wanted 7)
!! FAIL !! Sep/ (got -1, wanted 8)
!! FAIL !! Oct/ (got -1, wanted 9)
!! FAIL !! Nov/ (got -1, wanted 10)
!! FAIL !! Dec/ (got -1, wanted 11)
$

请注意，最后一个测试用例仍然通过 - 也就是说，它生成了 -1。

这里是 parseMonth() 的修订版 - 更详细 - 在 GCC 和 Sun C 编译器下工作相同:

#include <stdio.h>

/* MONTH_CODE("Jan/") does not reduce to an integer constant */
#define MONTH_CODE(x)   ((((((x[0]<<8)|x[1])<<8)|x[2])<<8)|x[3])

#define MONTH_JAN       (((((('J'<<8)|'a')<<8)|'n')<<8)|'/')
#define MONTH_FEB       (((((('F'<<8)|'e')<<8)|'b')<<8)|'/')
#define MONTH_MAR       (((((('M'<<8)|'a')<<8)|'r')<<8)|'/')
#define MONTH_APR       (((((('A'<<8)|'p')<<8)|'r')<<8)|'/')
#define MONTH_MAY       (((((('M'<<8)|'a')<<8)|'y')<<8)|'/')
#define MONTH_JUN       (((((('J'<<8)|'u')<<8)|'n')<<8)|'/')
#define MONTH_JUL       (((((('J'<<8)|'u')<<8)|'l')<<8)|'/')
#define MONTH_AUG       (((((('A'<<8)|'u')<<8)|'g')<<8)|'/')
#define MONTH_SEP       (((((('S'<<8)|'e')<<8)|'p')<<8)|'/')
#define MONTH_OCT       (((((('O'<<8)|'c')<<8)|'t')<<8)|'/')
#define MONTH_NOV       (((((('N'<<8)|'o')<<8)|'v')<<8)|'/')
#define MONTH_DEC       (((((('D'<<8)|'e')<<8)|'c')<<8)|'/')

static int parseMonth(const char *input) {
    int rv=-1;
    int inputInt=0;
    int i=0;

    for(i=0; i<4 && input[i]; i++) {
        inputInt = (inputInt << 8) | input[i];
    }

    switch(inputInt) {
        case MONTH_JAN: rv=0; break;
        case MONTH_FEB: rv=1; break;
        case MONTH_MAR: rv=2; break;
        case MONTH_APR: rv=3; break;
        case MONTH_MAY: rv=4; break;
        case MONTH_JUN: rv=5; break;
        case MONTH_JUL: rv=6; break;
        case MONTH_AUG: rv=7; break;
        case MONTH_SEP: rv=8; break;
        case MONTH_OCT: rv=9; break;
        case MONTH_NOV: rv=10; break;
        case MONTH_DEC: rv=11; break;
    }

    return rv;
}

static const struct
{
    char *data;
    int   result;
} test_case[] =
{
    { "Jan/", 0 },
    { "Feb/", 1 },
    { "Mar/", 2 },
    { "Apr/", 3 },
    { "May/", 4 },
    { "Jun/", 5 },
    { "Jul/", 6 },
    { "Aug/", 7 },
    { "Sep/", 8 },
    { "Oct/", 9 },
    { "Nov/", 10 },
    { "Dec/", 11 },
    { "aJ/n", -1 },
    { "/naJ", -1 },
};

#define DIM(x) (sizeof(x)/sizeof(*(x)))

int main(void)
{
    size_t i;
    int    result;

    for (i = 0; i < DIM(test_case); i++)
    {
        result = parseMonth(test_case[i].data);
        if (result != test_case[i].result)
            printf("!! FAIL !! %s (got %d, wanted %d)\n",
                   test_case[i].data, result, test_case[i].result);
    }
    return(0);
}

我想使用 MONTH_CODE() 但编译器不配合。