wget 原代码分析 十二

<-------------______________
返回到all_tests()
{
. . . . . /*The last one is coming*/
mu_run_test(test_is_robots_txt_url); /*和那spider有关1、_____________------------->src/res.c*/
. . . . . .
}
1、____________-------------->
618 test_is_robots_txt_url()
619 {
620   int i;
621   struct {
622     char *url;
623     bool expected_result;
624   } test_array[] = {
625     { "", true },  /*因为此文件在服务器根目录所以只有它是正确的*/
626     { "", false },
627     { "robots.txt", false },
628   };
629   
630   for (i = 0; i < sizeof(test_array)/sizeof(test_array[0]); ++i)
631     {
632       mu_assert ("test_is_robots_txt_url: wrong result",
633                  is_robots_txt_url (test_array[i].url) == test_array[i].expected_result);
                         /*2、_________------------>/src/res.c*/
634     }
635
636   return NULL;
637 }
2、_____________--------------->
586 bool
587 is_robots_txt_url (const char *url)
588 {
589   char *robots_url = uri_merge (url, RES_SPECS_LOCATION); /*3、________------------>/src/url.c*/
590   bool ret = are_urls_equal (url, robots_url);
591
592   xfree (robots_url);
593
594   return ret;
595 }
3、____________----------------->
#define RES_SPECS_LOCATION "/robots.txt"
1743 uri_merge (const char *base, const char *link)
1744 {
1745   int linklength;
1746   const char *end;
1747   char *merge;
1748
1749   if (url_has_scheme (link))4、_________---------->src/url.c*/
1750     return xstrdup (link); 5、__________----------->/xmalloc.c*/
1751      
1752   /* We may not examine BASE past END. */
1753   end = path_end (base);
1754   linklength = strlen (link);
1755
1756   if (!*link)
1757     {
1758       /* Empty LINK points back to BASE, query string and all. */
1759       return xstrdup (base);
1760     }
1761   else if (*link == '?')
1762     {
1763       /* LINK points to the same location, but changes the query
1764          string.  Examples: */
1765       /* uri_merge("path",         "?new") -> "path?new"     */
1766       /* uri_merge("path?foo",     "?new") -> "path?new"     */
1767       /* uri_merge("path?foo#bar", "?new") -> "path?new"     */
1768       /* uri_merge("path#foo",     "?new") -> "path?new"     */
1769       int baselength = end - base;
1770       merge = xmalloc (baselength + linklength + 1);
1771       memcpy (merge, base, baselength);
1772       memcpy (merge + baselength, link, linklength);
1773       merge[baselength + linklength] = '\0';
1774     }
1775   else if (*link == '#')
. . .
4、_____________________------------->
url_has_scheme (const char *url)  意思是如果以scheme格式，开始的话就返回1，如果不要就返回0.
/*这个函数解释了url格式中的skeme,我查资料没有查到*/
5、__________________-------------------->
120 char *
121 xstrdup (char const *string)
122 {      
123   return xmemdup (string, strlen (string) + 1);
124 }   
113 xmemdup (void const *p, size_t s)
114 {
115   return memcpy (xmalloc (s), p, s);
116 }   
/*这是复制一份该字符串的值*/