[svn] Remove K&R support.

[wget] / src / recur.c

diff --git a/src/recur.c b/src/recur.c
index bf367074d9a0f2c4a6846f7b473e0cc32a834e45..a00b47aa5db00574ba5157718422a41ee4195a2f 100644 (file)
--- a/src/recur.c
+++ b/src/recur.c
@@ -31,17 +31,12 @@ so, delete this exception statement from your version.  */
 
 #include <stdio.h>
 #include <stdlib.h>
-#ifdef HAVE_STRING_H
-# include <string.h>
-#else
-# include <strings.h>
-#endif /* HAVE_STRING_H */
+#include <string.h>
 #ifdef HAVE_UNISTD_H
 # include <unistd.h>
 #endif /* HAVE_UNISTD_H */
 #include <errno.h>
 #include <assert.h>
-#include <sys/types.h>
 
 #include "wget.h"
 #include "url.h"
@@ -54,11 +49,8 @@ so, delete this exception statement from your version.  */
 #include "res.h"
 #include "convert.h"
 
-#ifndef errno
-extern int errno;
-#endif
-
 extern char *version_string;
+extern LARGE_INT total_downloaded_bytes;
 
 extern struct hash_table *dl_url_file_map;
 extern struct hash_table *downloaded_html_set;
@@ -86,8 +78,7 @@ struct url_queue {
 static struct url_queue *
 url_queue_new (void)
 {
-  struct url_queue *queue = xmalloc (sizeof (*queue));
-  memset (queue, '\0', sizeof (*queue));
+  struct url_queue *queue = xnew0 (struct url_queue);
   return queue;
 }
 
@@ -107,7 +98,7 @@ static void
 url_enqueue (struct url_queue *queue,
             const char *url, const char *referer, int depth, int html_allowed)
 {
-  struct queue_element *qel = xmalloc (sizeof (*qel));
+  struct queue_element *qel = xnew (struct queue_element);
   qel->url = url;
   qel->referer = referer;
   qel->depth = depth;
@@ -160,10 +151,10 @@ url_dequeue (struct url_queue *queue,
   return 1;
 }
 \f
-static int download_child_p PARAMS ((const struct urlpos *, struct url *, int,
-                                    struct url *, struct hash_table *));
-static int descend_redirect_p PARAMS ((const char *, const char *, int,
-                                      struct url *, struct hash_table *));
+static int download_child_p (const struct urlpos *, struct url *, int,
+                            struct url *, struct hash_table *);
+static int descend_redirect_p (const char *, const char *, int,
+                              struct url *, struct hash_table *);
 
 
 /* Retrieve a part of the web beginning with START_URL.  This used to
@@ -222,9 +213,9 @@ retrieve_tree (const char *start_url)
       int descend = 0;
       char *url, *referer, *file = NULL;
       int depth, html_allowed;
-      boolean dash_p_leaf_HTML = FALSE;
+      int dash_p_leaf_HTML = 0;
 
-      if (downloaded_exceeds_quota ())
+      if (opt.quota && total_downloaded_bytes > opt.quota)
        break;
       if (status == FWRITEERR)
        break;
@@ -304,7 +295,7 @@ retrieve_tree (const char *start_url)
                 one, but we allow one more level so that the leaf
                 pages that contain frames can be loaded
                 correctly.  */
-             dash_p_leaf_HTML = TRUE;
+             dash_p_leaf_HTML = 1;
            }
          else
            {
@@ -382,8 +373,8 @@ retrieve_tree (const char *start_url)
        }
 
       xfree (url);
-      FREE_MAYBE (referer);
-      FREE_MAYBE (file);
+      xfree_null (referer);
+      xfree_null (file);
     }
 
   /* If anything is left of the queue due to a premature exit, free it
@@ -395,7 +386,7 @@ retrieve_tree (const char *start_url)
                        (const char **)&d1, (const char **)&d2, &d3, &d4))
       {
        xfree (d1);
-       FREE_MAYBE (d2);
+       xfree_null (d2);
       }
   }
   url_queue_delete (queue);
@@ -404,7 +395,7 @@ retrieve_tree (const char *start_url)
     url_free (start_url_parsed);
   string_set_free (blacklist);
 
-  if (downloaded_exceeds_quota ())
+  if (opt.quota && total_downloaded_bytes > opt.quota)
     return QUOTEXC;
   else if (status == FWRITEERR)
     return FWRITEERR;
@@ -516,13 +507,21 @@ download_child_p (const struct urlpos *upos, struct url *parent, int depth,
     }
 
   /* 6. Check for acceptance/rejection rules.  We ignore these rules
-     for directories (no file name to match) and for HTML documents,
-     which might lead to other files that do need to be downloaded.
-     That is, unless we've exhausted the recursion depth anyway.  */
+     for directories (no file name to match) and for non-leaf HTMLs,
+     which can lead to other files that do need to be downloaded.  (-p
+     automatically implies non-leaf because with -p we can, if
+     necesary, overstep the maximum depth to get the page requisites.)  */
   if (u->file[0] != '\0'
       && !(has_html_suffix_p (u->file)
-          && depth != INFINITE_RECURSION
-          && depth < opt.reclevel - 1))
+          /* The exception only applies to non-leaf HTMLs (but -p
+             always implies non-leaf because we can overstep the
+             maximum depth to get the requisites): */
+          && (/* non-leaf */
+              opt.reclevel == INFINITE_RECURSION
+              /* also non-leaf */
+              || depth < opt.reclevel - 1
+              /* -p, which implies non-leaf (see above) */
+              || opt.page_requisites)))
     {
       if (!acceptable (u->file))
        {
@@ -604,8 +603,7 @@ descend_redirect_p (const char *redirected, const char *original, int depth,
   new_parsed = url_parse (redirected, NULL);
   assert (new_parsed != NULL);
 
-  upos = xmalloc (sizeof (struct urlpos));
-  memset (upos, 0, sizeof (*upos));
+  upos = xnew0 (struct urlpos);
   upos->url = new_parsed;
 
   success = download_child_p (upos, orig_parsed, depth,