[tracker-miners: 1/3] tracker-extract: ignore subtrack titles for videos

[Carlos Garnacho <carlosg src gnome org>]

commit 47b13910d6075bef7e23dc458399d5a1f493ab21
Author: Ignacy Kuchciński <ignacykuchcinski gmail com>
Date:   Tue Feb 22 10:13:45 2022 +0100

    tracker-extract: ignore subtrack titles for videos
    
    Currently, the resulting nie:title includes titles from the individual
    tracks due to both gstreamer not differentiating between
    global/container tags and track tags until introducing
    gst_discoverer_container_info_get_tags() as new API and tracker-extract
    gstreamer backend looping through available tracks and collecting all
    tags it could find.
    
    As a result, in cases where there is no title tag in the container, but
    there are some title tags in subtitle or audio tracks, they are included
    in the nie:title and prevent the file name based fallback title in grilo
    and cause the video to show up with nonsense titles in totem.
    
    To fix this, replace gst_discoverer_info_get_tags() with the new API,
    and ignore title tags from subtracks if the file is a video.
    
    Fixes https://gitlab.gnome.org/GNOME/tracker-miners/-/issues/202

 config-miners.h.meson.in                        |  3 +++
 meson.build                                     |  1 +
 src/tracker-extract/tracker-extract-gstreamer.c | 21 +++++++++++++++++++--
 3 files changed, 23 insertions(+), 2 deletions(-)
---
diff --git a/config-miners.h.meson.in b/config-miners.h.meson.in
index 863b50631..402d432b9 100644
--- a/config-miners.h.meson.in
+++ b/config-miners.h.meson.in
@@ -32,6 +32,9 @@
 /* Define if we have GStreamer */
 #mesondefine HAVE_GSTREAMER
 
+/* Define if we have Gstreamer version 1.20.0 or up */
+#mesondefine HAVE_GSTREAMER_1_20
+
 /* Define if we have HAL */
 #mesondefine HAVE_HAL
 
diff --git a/meson.build b/meson.build
index 9432f19db..1270e2512 100644
--- a/meson.build
+++ b/meson.build
@@ -368,6 +368,7 @@ conf.set('GIO_SUPPORTS_CREATION_TIME', glib.version().version_compare('>=2.70.0'
 conf.set('HAVE_ENCA', charset_library_name == 'enca')
 conf.set('HAVE_EXEMPI', exempi.found())
 conf.set('HAVE_GSTREAMER', generic_media_handler_name == 'gstreamer')
+conf.set('HAVE_GSTREAMER_1_20', gstreamer.version() >= '1.20.0')
 conf.set('GSTREAMER_BACKEND_DISCOVERER', gstreamer_backend_name == 'Discoverer')
 conf.set('GSTREAMER_BACKEND_GUPNP_DLNA', gstreamer_backend_name == 'GUPnP-DLNA')
 conf.set('HAVE_HAL', battery_detection_library_name == 'hal')
diff --git a/src/tracker-extract/tracker-extract-gstreamer.c b/src/tracker-extract/tracker-extract-gstreamer.c
index f5bd24d3e..f64413f72 100644
--- a/src/tracker-extract/tracker-extract-gstreamer.c
+++ b/src/tracker-extract/tracker-extract-gstreamer.c
@@ -1244,7 +1244,12 @@ discoverer_init_and_run (MetadataExtractor *extractor,
        extractor->duration = gst_discoverer_info_get_duration (info) / GST_SECOND;
 
        /* Retrieve global tags */
+#if defined(HAVE_GSTREAMER_1_20)
+       GstDiscovererStreamInfo *sinfo = gst_discoverer_info_get_stream_info (info);
+       discoverer_tags = gst_discoverer_container_info_get_tags ((GstDiscovererContainerInfo *)sinfo);
+#else
        discoverer_tags = gst_discoverer_info_get_tags (info);
+#endif
 
        if (discoverer_tags) {
                gst_tag_list_insert (extractor->tagcache,
@@ -1256,7 +1261,6 @@ discoverer_init_and_run (MetadataExtractor *extractor,
        extractor->streams = gst_discoverer_info_get_stream_list (info);
        for (l = extractor->streams; l; l = g_list_next (l)) {
                GstDiscovererStreamInfo *stream = l->data;
-               const GstTagList *stream_tags;
 
                if (G_TYPE_CHECK_INSTANCE_TYPE (stream, GST_TYPE_DISCOVERER_AUDIO_INFO)) {
                        GstDiscovererAudioInfo *audio = (GstDiscovererAudioInfo*)stream;
@@ -1285,17 +1289,30 @@ discoverer_init_and_run (MetadataExtractor *extractor,
                } else {
                        /* Unknown type - do nothing */
                }
+       }
 
-               stream_tags = gst_discoverer_stream_info_get_tags (stream);
+       for (l = extractor->streams; l; l = g_list_next (l)) {
+               GstDiscovererStreamInfo *stream = l->data;
+               GstTagList *stream_tags;
+
+               stream_tags = gst_tag_list_copy (gst_discoverer_stream_info_get_tags (stream));
+               if (extractor->has_video &&
+                   gst_tag_list_get_tag_size (extractor->tagcache, "title") > 0)
+                       gst_tag_list_remove_tag (stream_tags, "title");
 
                if (stream_tags) {
                        gst_tag_list_insert (extractor->tagcache,
                                             stream_tags,
                                             GST_TAG_MERGE_APPEND);
                }
+
+               gst_tag_list_unref (stream_tags);
        }
 
        gst_discoverer_info_unref (info);
+#if defined(HAVE_GSTREAMER_1_20)
+       gst_discoverer_stream_info_unref (sinfo);
+#endif
 
        return TRUE;
 }