php内核函数手册,php内核函数natsort浅析

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，官方手册(http://us.php.net/manual/en/function.natsort.php)bool natsort ( array &$array )

This function implements a sort algorithm that orders alphanumeric strings in the way a human being would while maintaining key/value associations. This is described as a "natural ordering". An example of the difference between this algorithm and the regular computer string sorting algorithms (used in sort()) can be seen in the example below.

据官方手册还可以得到这样的结果：

img1.png img2.png img10.png img12.png

显然这很适合对类似文件名的排序。从结果看这种自然算法应该是去掉头和尾的非数字部分，然后对留下来的数字部分进行排序，究竟是不是，还是看一下php源码吧。//从ext/standard/array.c抽取的相关代码如下

static int php_array_natural_general_compare(const void *a, const void *b, int fold_case) /* {{{ */

{

Bucket *f, *s;

zval *fval, *sval;

zval first, second;

int result;

f = *((Bucket **) a);

s = *((Bucket **) b);

fval = *((zval **) f->pData);

sval = *((zval **) s->pData);

first = *fval;

second = *sval;

if (Z_TYPE_P(fval) != IS_STRING) {

zval_copy_ctor(&first);

convert_to_string(&first);

}

if (Z_TYPE_P(sval) != IS_STRING) {

zval_copy_ctor(&second);

convert_to_string(&second);

}

result = strnatcmp_ex(Z_STRVAL(first), Z_STRLEN(first), Z_STRVAL(second), Z_STRLEN(second), fold_case);

if (Z_TYPE_P(fval) != IS_STRING) {

zval_dtor(&first);

}

if (Z_TYPE_P(sval) != IS_STRING) {

zval_dtor(&second);

}

return result;

}

/* }}} */

static int php_array_natural_compare(const void *a, const void *b TSRMLS_DC) /* {{{ */

{

return php_array_natural_general_compare(a, b, 0);

}

/* }}} */

static void php_natsort(INTERNAL_FUNCTION_PARAMETERS, int fold_case) /* {{{ */

{

zval *array;

if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "a", &array) == FAILURE) {

return;

}

if (fold_case) {

if (zend_hash_sort(Z_ARRVAL_P(array), zend_qsort, php_array_natural_case_compare, 0 TSRMLS_CC) == FAILURE) {

return;

}

} else {

if (zend_hash_sort(Z_ARRVAL_P(array), zend_qsort, php_array_natural_compare, 0 TSRMLS_CC) == FAILURE) {

return;

}

}

RETURN_TRUE;

}

/* }}} */

/* {{{ proto void natsort(array &array_arg)

Sort an array using natural sort */

PHP_FUNCTION(natsort)

{

php_natsort(INTERNAL_FUNCTION_PARAM_PASSTHRU, 0);

}

/* }}} */

然是第一次查看php的内核代码，不过凭借多年看代码的经验，还是很容易找到这个自然排序算法的核心就是函数：strnatcmp_ex(位于ext/standard/strnatcmp.c文件中)。/* {{{ 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：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：

Bucket: http://www.phpchina.cn/bbs/viewthread.php?tid=88505

zval: http://www.laruence.com/2008/08/22/412.html

本文原创发布php中文网，转载请注明出处，感谢您的尊重！