php natsort内核函数浅析

 更新时间:2009年08月10日 10:32:08   作者:  
今天发现了php有个自然排序的函数----natsort,第一次听说了原来还有一种叫做“自然排序”的算法,很好奇

复制代码 代码如下:

/* {{{ compare_right
*/
static int
compare_right(char const **a, char const *aend, char const **b, char const *bend)
{
    int bias = 0;
    /* The longest run of digits wins. That aside, the greatest
     value wins, but we can't know that it will until we've scanned
     both numbers to know that they have the same magnitude, so we
     remember it in BIAS. */
    for(;; (*a)++, (*b)++) {
        if ((*a == aend || !isdigit((int)(unsigned char)**a)) &&
            (*b == bend || !isdigit((int)(unsigned char)**b)))
            return bias;
        else if (*a == aend || !isdigit((int)(unsigned char)**a))
            return -1;
        else if (*b == bend || !isdigit((int)(unsigned char)**b))
            return +1;
        else if (**a < **b) {
            if (!bias)
                bias = -1;
        } else if (**a > **b) {
            if (!bias)
                bias = +1;
        }
}
return 0;
}
/* }}} */
/* {{{ compare_left
*/
static int
compare_left(char const **a, char const *aend, char const **b, char const *bend)
{
/* Compare two left-aligned numbers: the first to have a
different value wins. */
    for(;; (*a)++, (*b)++) {
        if ((*a == aend || !isdigit((int)(unsigned char)**a)) &&
            (*b == bend || !isdigit((int)(unsigned char)**b)))
            return 0;
        else if (*a == aend || !isdigit((int)(unsigned char)**a))
            return -1;
        else if (*b == bend || !isdigit((int)(unsigned char)**b))
            return +1;
         else if (**a < **b)
             return -1;
         else if (**a > **b)
             return +1;
}

return 0;
}
/* }}} */
/* {{{ strnatcmp_ex
* call in array.c: strnatcmp_ex(Z_STRVAL(first), Z_STRLEN(first), Z_STRVAL(second), Z_STRLEN(second), fold_case);
*/
PHPAPI int strnatcmp_ex(char const *a, size_t a_len, char const *b, size_t b_len, int fold_case)
{
    char ca, cb;
    char const *ap, *bp;
    char const *aend = a + a_len,
             *bend = b + b_len;
    int fractional, result;
    if (a_len == 0 || b_len == 0)
        return a_len - b_len;
    ap = a;
    bp = b;
    while (1) {
        ca = *ap; cb = *bp;
        /* skip over leading spaces or zeros */
        while (isspace((int)(unsigned char)ca) || (ca == '0' && (ap+1 < aend) && (*(ap+1)!='.')))
            ca = *++ap;
        while (isspace((int)(unsigned char)cb) || (cb == '0' && (bp+1 < bend) && (*(bp+1)!='.')))
            cb = *++bp;
        /* process run of digits */
        if (isdigit((int)(unsigned char)ca) && isdigit((int)(unsigned char)cb)) {
            fractional = (ca == '0' || cb == '0');
            if (fractional)
                result = compare_left(&ap, aend, &bp, bend);
            else
                result = compare_right(&ap, aend, &bp, bend);
            if (result != 0)
                return result;
            else if (ap == aend && bp == bend)
                /* End of the strings. Let caller sort them out. */
                return 0;
            else {
                /* Keep on comparing from the current point. */
                ca = *ap; cb = *bp;
            }
        }
        if (fold_case) {
            ca = toupper((int)(unsigned char)ca);
            cb = toupper((int)(unsigned char)cb);
        }
        if (ca < cb)
            return -1;
        else if (ca > cb)
            return +1;
        ++ap; ++bp;
        if (ap >= aend && bp >= bend)
            /* The strings compare the same. Perhaps the caller
             will want to call strcmp to break the tie. */
            return 0;
        else if (ap >= aend)
            return -1;
        else if (bp >= bend)
            return 1;
    }
}
/* }}} */

从strnatcmp_ex函数中的:
复制代码 代码如下:

while (isspace((int)(unsigned char)ca) || (ca == '0' && (ap+1 < aend) && (*(ap+1)!='.')))
    ca = *++ap;
while (isspace((int)(unsigned char)cb) || (cb == '0' && (bp+1 < bend) && (*(bp+1)!='.')))
    cb = *++bp;

所以,我觉得应该字符串(当前位置开始)中前面的空字符和数字前面的‘0'不会参与比较,比较的结果应该和

http://us.php.net/manual/en/function.natsort.php

http://sourcefrog.net/projects/natsort/example-out.txt

所说的一样,但是在我的php5.2.9中对于“0”的处理结果却不一样(例如“img002.png”与“img1.png”,我的理解应该是前者大于后者,不过在我的5.2.9中却是前者小于后者),原因还没想清楚,可能是5.2.9的一个bug,也可能是自己还没有理解清楚源码的意思。下次配置好环境再好好测试,好好消化~~

在array.c中有两个重要的数据结构很值得我们关注

相关文章

最新评论