typefind: fix reading file extension from URI

Currently reading extension relies on the fact that everything after the
last"." character is a file extension. Whereas that works fine for most
of the cases, it breaks when the URI contains a query part.

E.g.: `http://url.com/file.mp4?param=value` returns `mp4?param=value`
instead of `mp4`.

In this commit we use URI parser to read the path of the URI (in the example
above, that is `/file.mp4`) and read extension from that path.

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/1305>

diff --git a/subprojects/gstreamer/plugins/elements/gsttypefindelement.c b/subprojects/gstreamer/plugins/elements/gsttypefindelement.c
index fb14df6..84e60a9 100644 (file)
--- a/subprojects/gstreamer/plugins/elements/gsttypefindelement.c
+++ b/subprojects/gstreamer/plugins/elements/gsttypefindelement.c
@@ -800,9 +800,8 @@ static gchar *
 gst_type_find_get_extension (GstTypeFindElement * typefind, GstPad * pad)
 {
   GstQuery *query;
-  gchar *uri, *result;
-  size_t len;
-  gint find;
+  gchar *uri, *result, *path, *base_path, *find;
+  GstUri *gst_uri;
 
   query = gst_query_new_uri ();
 
@@ -816,22 +815,30 @@ gst_type_find_get_extension (GstTypeFindElement * typefind, GstPad * pad)
 
   GST_DEBUG_OBJECT (typefind, "finding extension of %s", uri);
 
-  /* find the extension on the uri, this is everything after a '.' */
-  len = strlen (uri);
-  find = len - 1;
+  gst_uri = gst_uri_from_string (uri);
+  if (gst_uri == NULL)
+    goto invalid_uri;
 
-  while (find >= 0) {
-    if (uri[find] == '.')
-      break;
-    find--;
-  }
-  if (find < 0)
+  path = gst_uri_get_path (gst_uri);
+  gst_uri_unref (gst_uri);
+
+  if (path == NULL)
+    goto invalid_uri;
+
+  base_path = g_path_get_basename (path);
+  g_free (path);
+
+  /* find the extension on the path, this is everything after a '.' */
+  find = strrchr (base_path, '.');
+
+  if (find == NULL)
     goto no_extension;
 
-  result = g_strdup (&uri[find + 1]);
+  result = g_strdup (find + 1);
 
   GST_DEBUG_OBJECT (typefind, "found extension %s", result);
   gst_query_unref (query);
+  g_free (base_path);
   g_free (uri);
 
   return result;
@@ -849,11 +856,19 @@ no_uri:
     gst_query_unref (query);
     return NULL;
   }
+invalid_uri:
+  {
+    GST_INFO_OBJECT (typefind, "failed to extract path from uri %s", uri);
+    g_free (uri);
+    gst_query_unref (query);
+    return NULL;
+  }
 no_extension:
   {
     GST_INFO_OBJECT (typefind, "could not find uri extension in %s", uri);
-    gst_query_unref (query);
+    g_free (base_path);
     g_free (uri);
+    gst_query_unref (query);
     return NULL;
   }
 }