tool_metalink.c: Filtered resource URLs by type

In Metalink v3, the type attribute of url element indicates the
type of the resource the URL points to. It can include URL to the
meta data, such as BitTorrent metainfo file.  In Curl, we are not
interested in these meta data URLs. Instead, we are only
interested in the HTTP and FTP URLs. This change filters out
non-HTTP and FTP URLs. If we don't filter out them, it will be
downloaded by curl and hash check will fail if hash is provided
and next URL will be tried. This change will cut this useless
network transfer.

diff --git a/src/tool_metalink.c b/src/tool_metalink.c
index 3163927814e12f9e06b95bd4d2d64c6641d9efae..103c88649d9fd14fffa9a34d4686950fa15447c1 100644 (file)
--- a/src/tool_metalink.c
+++ b/src/tool_metalink.c
@@ -573,9 +573,24 @@ static metalinkfile *new_metalinkfile(metalink_file_t *fileinfo)
     tail = &root;
     for(p = fileinfo->resources; *p; ++p) {
       metalink_resource *res;
-      res = new_metalink_resource((*p)->url);
-      tail->next = res;
-      tail = res;
+      /* Filter by type if it is non-NULL. In Metalink v3, type
+         includes the type of the resource. In curl, we are only
+         interested in HTTP, HTTPS and FTP. In addition to them,
+         Metalink v3 file may contain bittorrent type URL, which
+         points to the BitTorrent metainfo file. We ignore it here.
+         In Metalink v4, type was deprecated and all
+         fileinfo->resources point to the target file. BitTorrent
+         metainfo file URL may be appeared in fileinfo->metaurls.
+      */
+      if((*p)->type == NULL ||
+         Curl_raw_equal((*p)->type, "http") ||
+         Curl_raw_equal((*p)->type, "https") ||
+         Curl_raw_equal((*p)->type, "ftp") ||
+         Curl_raw_equal((*p)->type, "ftps")) {
+        res = new_metalink_resource((*p)->url);
+        tail->next = res;
+        tail = res;
+      }
     }
     f->resource = root.next;
   }