[svn] Remove K&R support.

[wget] / src / html-url.c

diff --git a/src/html-url.c b/src/html-url.c
index 3dc072592e37fcee912e4506dc76f3f2af202a94..b5071151ef34084492b4fddcef817f547cfd7c4b 100644 (file)
--- a/src/html-url.c
+++ b/src/html-url.c
@@ -30,11 +30,7 @@ so, delete this exception statement from your version.  */
 #include <config.h>
 
 #include <stdio.h>
-#ifdef HAVE_STRING_H
-# include <string.h>
-#else
-# include <strings.h>
-#endif
+#include <string.h>
 #include <stdlib.h>
 #include <errno.h>
 #include <assert.h>
@@ -45,18 +41,14 @@ so, delete this exception statement from your version.  */
 #include "utils.h"
 #include "hash.h"
 #include "convert.h"
-
-#ifndef errno
-extern int errno;
-#endif
+#include "recur.h"             /* declaration of get_urls_html */
 
 struct map_context;
 
-typedef void (*tag_handler_t) PARAMS ((int, struct taginfo *,
-                                      struct map_context *));
+typedef void (*tag_handler_t) (int, struct taginfo *, struct map_context *);
 
-#define DECLARE_TAG_HANDLER(fun)                                       \
-  static void fun PARAMS ((int, struct taginfo *, struct map_context *))
+#define DECLARE_TAG_HANDLER(fun)                               \
+  static void fun (int, struct taginfo *, struct map_context *)
 
 DECLARE_TAG_HANDLER (tag_find_urls);
 DECLARE_TAG_HANDLER (tag_handle_base);
@@ -81,6 +73,7 @@ enum {
   TAG_LAYER,
   TAG_LINK,
   TAG_META,
+  TAG_OBJECT,
   TAG_OVERLAY,
   TAG_SCRIPT,
   TAG_TABLE,
@@ -111,6 +104,7 @@ static struct known_tag {
   { TAG_LAYER,  "layer",       tag_find_urls },
   { TAG_LINK,   "link",        tag_handle_link },
   { TAG_META,   "meta",        tag_handle_meta },
+  { TAG_OBJECT,  "object",     tag_find_urls },
   { TAG_OVERLAY, "overlay",    tag_find_urls },
   { TAG_SCRIPT,         "script",      tag_find_urls },
   { TAG_TABLE,  "table",       tag_find_urls },
@@ -157,6 +151,7 @@ static struct {
   { TAG_IMG,           "src",          ATTR_INLINE },
   { TAG_INPUT,         "src",          ATTR_INLINE },
   { TAG_LAYER,         "src",          ATTR_INLINE | ATTR_HTML },
+  { TAG_OBJECT,                "data",         ATTR_INLINE },
   { TAG_OVERLAY,       "src",          ATTR_INLINE | ATTR_HTML },
   { TAG_SCRIPT,                "src",          ATTR_INLINE },
   { TAG_TABLE,         "background",   ATTR_INLINE },
@@ -477,6 +472,10 @@ tag_handle_link (int tagid, struct taginfo *tag, struct map_context *ctx)
              && (0 == strcasecmp (rel, "stylesheet")
                  || 0 == strcasecmp (rel, "shortcut icon")))
            up->link_inline_p = 1;
+         else
+           /* The external ones usually point to HTML pages, such as
+              <link rel="next" href="..."> */
+           up->link_expect_html = 1;
        }
     }
 }
@@ -596,7 +595,7 @@ get_urls_html (const char *file, const char *url, int *meta_disallow_follow)
       logprintf (LOG_NOTQUIET, "%s: %s\n", file, strerror (errno));
       return NULL;
     }
-  DEBUGP (("Loaded %s (size %ld).\n", file, fm->length));
+  DEBUGP (("Loaded %s (size %s).\n", file, number_to_static_string (fm->length)));
 
   ctx.text = fm->content;
   ctx.head = ctx.tail = NULL;
@@ -609,9 +608,12 @@ get_urls_html (const char *file, const char *url, int *meta_disallow_follow)
     init_interesting ();
 
   /* Specify MHT_TRIM_VALUES because of buggy HTML generators that
-     generate <a href=" foo"> instead of <a href="foo"> (Netscape
-     ignores spaces as well.)  If you really mean space, use &32; or
-     %20.  */
+     generate <a href=" foo"> instead of <a href="foo"> (browsers
+     ignore spaces as well.)  If you really mean space, use &32; or
+     %20.  MHT_TRIM_VALUES also causes squashing of embedded newlines,
+     e.g. in <img src="foo.[newline]html">.  Such newlines are also
+     ignored by IE and Mozilla and are presumably introduced by
+     writing HTML with editors that force word wrap.  */
   flags = MHT_TRIM_VALUES;
   if (opt.strict_comments)
     flags |= MHT_STRICT_COMMENTS;
@@ -645,7 +647,7 @@ get_urls_file (const char *file)
       logprintf (LOG_NOTQUIET, "%s: %s\n", file, strerror (errno));
       return NULL;
     }
-  DEBUGP (("Loaded %s (size %ld).\n", file, fm->length));
+  DEBUGP (("Loaded %s (size %s).\n", file, number_to_static_string (fm->length)));
 
   head = tail = NULL;
   text = fm->content;
@@ -691,7 +693,7 @@ get_urls_file (const char *file)
       url = url_parse (url_text, &up_error_code);
       if (!url)
        {
-         logprintf (LOG_NOTQUIET, "%s: Invalid URL %s: %s\n",
+         logprintf (LOG_NOTQUIET, _("%s: Invalid URL %s: %s\n"),
                     file, url_text, url_error (up_error_code));
          xfree (url_text);
          continue;