diff mbox series

[FFmpeg-devel,19/20] avformat/matroskaenc: Redo handling of FlagDefault

Message ID 20200405155928.9323-20-andreas.rheinhardt@gmail.com
State Accepted
Commit e3c54b549abf2798422245582c0ed775c894ddeb
Headers show
Series Matroska muxer patches | expand

Checks

Context Check Description
andriy/ffmpeg-patchwork success Make fate finished

Commit Message

Andreas Rheinhardt April 5, 2020, 3:59 p.m. UTC
Up until now, the Matroska muxer would mark a track as default if it had
the disposition AV_DISPOSITION_DEFAULT or if there was no track with
AV_DISPOSITION_DEFAULT set; in the latter case even more than one track
of a kind (audio, video, subtitles) was marked as default which is not
sensible.

This commit changes the logic used to mark tracks as default. There are
now three modes for this:
a) In the "infer" mode the first track of every type (audio, video,
subtitles) with default disposition set will be marked as default; if
there is no such track (for a given type), then the first track of this
type (if existing) will be marked as default. This behaviour is inspired
by mkvmerge. It ensures that the default flags will be set in a sensible
way even if the input comes from containers that lack the concept of
default flags. This mode is the default mode.
b) The "infer_no_subs" mode is similar to the "infer" mode; the
difference is that if no subtitle track with default disposition exists,
no subtitle track will be marked as default at all.
c) The "passthrough" mode: Here the track will be marked as default if
and only the corresponding input stream had disposition default.

This fixes ticket #8173 (the passthrough mode is ideal for this) as
well as ticket #8416 (the "infer_no_subs" mode leads to the desired
output).

Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@gmail.com>
---
I did not apply this with the last round of patches as I am still hoping
that someone would come up with better names.

Furthermore, AVFormatContext.nb_streams is actually an unsigned, yet I
am using an int to run through it (this is no problem now and probably
won't be one ever, because the nb_streams is always in the range of int);
I could rewrite this to only use unsigned. Should I do it?

 doc/muxers.texi                               | 19 +++++++
 libavformat/matroskaenc.c                     | 56 ++++++++++++++++---
 tests/ref/fate/matroska-flac-extradata-update |  4 +-
 3 files changed, 69 insertions(+), 10 deletions(-)
diff mbox series

Patch

diff --git a/doc/muxers.texi b/doc/muxers.texi
index 3be1c89416..4083e24205 100644
--- a/doc/muxers.texi
+++ b/doc/muxers.texi
@@ -1358,6 +1358,25 @@  A safe size for most use cases should be about 50kB per hour of video.
 
 Note that cues are only written if the output is seekable and this option will
 have no effect if it is not.
+@item default_mode
+This option controls how the FlagDefault of the output tracks will be set.
+It influences which tracks players should play by default. The default mode
+is @samp{infer}.
+@table @samp
+@item infer
+In this mode, for each type of track (audio, video or subtitle), if there is
+a track with disposition default of this type, then the first such track
+(i.e. the one with the lowest index) will be marked as default; if no such
+track exists, the first track of this type will be marked as default instead
+(if existing). This ensures that the default flag is set in a sensible way even
+if the input originated from containers that lack the concept of default tracks.
+@item infer_no_subs
+This mode is the same as infer except that if no subtitle track with
+disposition default exists, no subtitle track will be marked as default.
+@item passthrough
+In this mode the FlagDefault is set if and only if the AV_DISPOSITION_DEFAULT
+flag is set in the disposition of the corresponding stream.
+@end table
 @end table
 
 @anchor{md5}
diff --git a/libavformat/matroskaenc.c b/libavformat/matroskaenc.c
index 3cbaaf9574..084e7ca416 100644
--- a/libavformat/matroskaenc.c
+++ b/libavformat/matroskaenc.c
@@ -60,6 +60,12 @@ 
  * Info, Tracks, Chapters, Attachments, Tags and Cues */
 #define MAX_SEEKHEAD_ENTRIES 6
 
+enum {
+    DEFAULT_MODE_INFER,
+    DEFAULT_MODE_INFER_NO_SUBS,
+    DEFAULT_MODE_PASSTHROUGH,
+};
+
 typedef struct ebml_master {
     int64_t         pos;                ///< absolute offset in the containing AVIOContext where the master's elements start
     int             sizebytes;          ///< how many bytes were reserved for the size
@@ -149,6 +155,7 @@  typedef struct MatroskaMuxContext {
     int wrote_chapters;
 
     int allow_raw_vfw;
+    int default_mode;
 
     uint32_t segment_uid[4];
 } MatroskaMuxContext;
@@ -1088,7 +1095,7 @@  static int mkv_write_stereo_mode(AVFormatContext *s, AVIOContext *pb,
 
 static int mkv_write_track(AVFormatContext *s, MatroskaMuxContext *mkv,
                            AVStream *st, mkv_track *track, AVIOContext *pb,
-                           int default_stream_exists)
+                           int is_default)
 {
     AVCodecParameters *par = st->codecpar;
     ebml_master subinfo, track_master;
@@ -1126,8 +1133,8 @@  static int mkv_write_track(AVFormatContext *s, MatroskaMuxContext *mkv,
 
     // The default value for TRACKFLAGDEFAULT is 1, so add element
     // if we need to clear it.
-    if (default_stream_exists && !(st->disposition & AV_DISPOSITION_DEFAULT))
-        put_ebml_uint(pb, MATROSKA_ID_TRACKFLAGDEFAULT, !!(st->disposition & AV_DISPOSITION_DEFAULT));
+    if (!is_default)
+        put_ebml_uint(pb, MATROSKA_ID_TRACKFLAGDEFAULT, 0);
 
     if (st->disposition & AV_DISPOSITION_FORCED)
         put_ebml_uint(pb, MATROSKA_ID_TRACKFLAGFORCED, 1);
@@ -1357,7 +1364,7 @@  static int mkv_write_tracks(AVFormatContext *s)
 {
     MatroskaMuxContext *mkv = s->priv_data;
     AVIOContext *pb = s->pb;
-    int i, ret, default_stream_exists = 0;
+    int i, ret, video_default_idx, audio_default_idx, subtitle_default_idx;
 
     if (mkv->nb_attachments == s->nb_streams)
         return 0;
@@ -1368,14 +1375,43 @@  static int mkv_write_tracks(AVFormatContext *s)
     if (ret < 0)
         return ret;
 
-    for (i = 0; i < s->nb_streams; i++) {
-        AVStream *st = s->streams[i];
-        default_stream_exists |= st->disposition & AV_DISPOSITION_DEFAULT;
+    if (mkv->default_mode != DEFAULT_MODE_PASSTHROUGH) {
+        int video_idx, audio_idx, subtitle_idx;
+
+        video_idx    = video_default_idx    =
+        audio_idx    = audio_default_idx    =
+        subtitle_idx = subtitle_default_idx = -1;
+
+        for (i = s->nb_streams - 1; i >= 0; i--) {
+            AVStream *st = s->streams[i];
+
+            switch (st->codecpar->codec_type) {
+#define CASE(type, variable)                                  \
+            case AVMEDIA_TYPE_ ## type:                       \
+                variable ## _idx = i;                         \
+                if (st->disposition & AV_DISPOSITION_DEFAULT) \
+                    variable ## _default_idx = i;             \
+                break;
+            CASE(VIDEO,    video)
+            CASE(AUDIO,    audio)
+            CASE(SUBTITLE, subtitle)
+#undef CASE
+            }
+        }
+
+        video_default_idx = FFMAX(video_default_idx, video_idx);
+        audio_default_idx = FFMAX(audio_default_idx, audio_idx);
+        if (mkv->default_mode != DEFAULT_MODE_INFER_NO_SUBS)
+            subtitle_default_idx = FFMAX(subtitle_default_idx, subtitle_idx);
     }
     for (i = 0; i < s->nb_streams; i++) {
         AVStream *st = s->streams[i];
+        int is_default = mkv->default_mode == DEFAULT_MODE_PASSTHROUGH ?
+                             st->disposition & AV_DISPOSITION_DEFAULT  :
+                             i == video_default_idx || i == audio_default_idx ||
+                             i == subtitle_default_idx;
         ret = mkv_write_track(s, mkv, st, &mkv->tracks[i],
-                              mkv->tracks_bc, default_stream_exists);
+                              mkv->tracks_bc, is_default);
         if (ret < 0)
             return ret;
     }
@@ -2724,6 +2760,10 @@  static const AVOption options[] = {
     { "live", "Write files assuming it is a live stream.", OFFSET(is_live), AV_OPT_TYPE_BOOL, { .i64 = 0 }, 0, 1, FLAGS },
     { "allow_raw_vfw", "allow RAW VFW mode", OFFSET(allow_raw_vfw), AV_OPT_TYPE_BOOL, { .i64 = 0 }, 0, 1, FLAGS },
     { "write_crc32", "write a CRC32 element inside every Level 1 element", OFFSET(write_crc), AV_OPT_TYPE_BOOL, { .i64 = 1 }, 0, 1, FLAGS },
+    { "default_mode", "Controls how a track's FlagDefault is inferred", OFFSET(default_mode), AV_OPT_TYPE_INT, { .i64 = DEFAULT_MODE_INFER }, DEFAULT_MODE_INFER, DEFAULT_MODE_PASSTHROUGH, FLAGS, "default_mode" },
+    { "infer", "For each track type, mark the first track of disposition default as default; if none exists, mark the first track as default.", 0, AV_OPT_TYPE_CONST, { .i64 = DEFAULT_MODE_INFER }, 0, 0, FLAGS, "default_mode" },
+    { "infer_no_subs", "For each track type, mark the first track of disposition default as default; for audio and video: if none exists, mark the first track as default.", 0, AV_OPT_TYPE_CONST, { .i64 = DEFAULT_MODE_INFER_NO_SUBS }, 0, 0, FLAGS, "default_mode" },
+    { "passthrough", "Use the disposition flag as-is", 0, AV_OPT_TYPE_CONST, { .i64 = DEFAULT_MODE_PASSTHROUGH }, 0, 0, FLAGS, "default_mode" },
     { NULL },
 };
 
diff --git a/tests/ref/fate/matroska-flac-extradata-update b/tests/ref/fate/matroska-flac-extradata-update
index 890bf1ac52..8b575903e6 100644
--- a/tests/ref/fate/matroska-flac-extradata-update
+++ b/tests/ref/fate/matroska-flac-extradata-update
@@ -1,5 +1,5 @@ 
-2b82ee67ace359edb464e289486b3ebd *tests/data/fate/matroska-flac-extradata-update.matroska
-2008 tests/data/fate/matroska-flac-extradata-update.matroska
+332bf4d9c92d24478d2a218e81223433 *tests/data/fate/matroska-flac-extradata-update.matroska
+2011 tests/data/fate/matroska-flac-extradata-update.matroska
 #extradata 0:       34, 0x7acb09e7
 #extradata 1:       34, 0x7acb09e7
 #extradata 2:       34, 0x443402dd