[svn] Squash embedded newlines in links.

[wget] / src / html-url.c

diff --git a/src/html-url.c b/src/html-url.c
index 54dbf382f0402845c87e863d5f2ee6ac9e4b1ba9..59d873b394e6443cbaacad970399fbf6b67596f3 100644 (file)
--- a/src/html-url.c
+++ b/src/html-url.c
@@ -81,6 +81,7 @@ enum {
   TAG_LAYER,
   TAG_LINK,
   TAG_META,
+  TAG_OBJECT,
   TAG_OVERLAY,
   TAG_SCRIPT,
   TAG_TABLE,
@@ -111,6 +112,7 @@ 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 +159,7 @@ 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 },
@@ -329,7 +332,6 @@ append_url (const char *link_uri,
   DEBUGP (("appending \"%s\" to urlpos.\n", url->url));
 
   newel = xnew0 (struct urlpos);
-  newel->next = NULL;
   newel->url = url;
   newel->pos = tag->attrs[attrind].value_raw_beginning - ctx->text;
   newel->size = tag->attrs[attrind].value_raw_size;
@@ -610,9 +612,12 @@ 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;