movenc: Use packets in interleaving queues for the duration at the end of fragments

As long as caller only writes packets using av_interleaved_write_frame
with no manual flushing, this should allow us to always have accurate
durations at the end of fragments, since there should be at least
one queued packet in each stream (except for the stream where the
current packet is being written, but if the muxer itself does the
cutting of fragments, it also has info about the next packet for that
stream).
Signed-off-by: Martin Storsjö <martin@martin.st>

libavformat/avformat.h

@@ -1720,6 +1720,10 @@ int av_write_frame(AVFormatContext *s, AVPacket *pkt);
  * increasing dts. Callers doing their own interleaving should call
  * av_write_frame() instead of this function.
  *
+ * Using this function instead of av_write_frame() can give muxers advance
+ * knowledge of future packets, improving e.g. the behaviour of the mp4
+ * muxer for VFR content in fragmenting mode.
+ *
  * @param s media file handle
  * @param pkt The packet containing the data to be written.
  *            <br>

libavformat/internal.h

@@ -441,4 +441,14 @@ static inline int ff_rename(const char *oldpath, const char *newpath)
  */
 void ff_format_io_close(AVFormatContext *s, AVIOContext **pb);
 
+/**
+ * Find the next packet in the interleaving queue for the given stream.
+ * The packet is not removed from the interleaving queue, but only
+ * a pointer to it is returned.
+ *
+ * @return a pointer to the next packet, or NULL if no packet is queued
+ *         for this stream.
+ */
+const AVPacket *ff_interleaved_peek(AVFormatContext *s, int stream);
+
 #endif /* AVFORMAT_INTERNAL_H */

libavformat/movenc.c

@@ -3188,6 +3188,25 @@ static int mov_flush_fragment(AVFormatContext *s, int force)
     if (!(mov->flags & FF_MOV_FLAG_FRAGMENT))
         return 0;
 
+    // Try to fill in the duration of the last packet in each stream
+    // from queued packets in the interleave queues. If the flushing
+    // of fragments was triggered automatically by an AVPacket, we
+    // already have reliable info for the end of that track, but other
+    // tracks may need to be filled in.
+    for (i = 0; i < s->nb_streams; i++) {
+        MOVTrack *track = &mov->tracks[i];
+        if (!track->end_reliable) {
+            AVPacket *next = ff_interleaved_peek(s, i);
+            if (next) {
+                track->track_duration = next->dts - track->start_dts;
+                if (next->pts != AV_NOPTS_VALUE)
+                    track->end_pts = next->pts;
+                else
+                    track->end_pts = next->dts;
+            }
+        }
+    }
+
     for (i = 0; i < mov->nb_streams; i++) {
         MOVTrack *track = &mov->tracks[i];
         if (track->entry <= 1)
@@ -3267,6 +3286,7 @@ static int mov_flush_fragment(AVFormatContext *s, int force)
                                              mov->tracks[i].track_duration -
                                              mov->tracks[i].cluster[0].dts;
             mov->tracks[i].entry = 0;
+            mov->tracks[i].end_reliable = 0;
         }
         avio_flush(s->pb);
         return 0;
@@ -3346,6 +3366,7 @@ static int mov_flush_fragment(AVFormatContext *s, int force)
             track->frag_start += duration;
         track->entry = 0;
         track->entries_flushed = 0;
+        track->end_reliable = 0;
         if (!mov->frag_interleave) {
             if (!track->mdat_buf)
                 continue;
@@ -3650,6 +3671,7 @@ static int mov_write_packet(AVFormatContext *s, AVPacket *pkt)
                     trk->end_pts = pkt->pts;
                 else
                     trk->end_pts = pkt->dts;
+                trk->end_reliable = 1;
                 mov_auto_flush_fragment(s, 0);
             }
         }

libavformat/movenc.h

@@ -106,6 +106,7 @@ typedef struct MOVTrack {
     int64_t     start_dts;
     int64_t     start_cts;
     int64_t     end_pts;
+    int         end_reliable;
 
     int         hint_track;   ///< the track that hints this track, -1 if no hint track is set
     int         src_track;    ///< the track that this hint track describes

libavformat/mux.c

@@ -614,6 +614,17 @@ int ff_interleave_packet_per_dts(AVFormatContext *s, AVPacket *out,
     }
 }
 
+const AVPacket *ff_interleaved_peek(AVFormatContext *s, int stream)
+{
+    AVPacketList *pktl = s->internal->packet_buffer;
+    while (pktl) {
+        if (pktl->pkt.stream_index == stream)
+            return &pktl->pkt;
+        pktl = pktl->next;
+    }
+    return NULL;
+}
+
 /**
  * Interleave an AVPacket correctly so it can be muxed.
  * @param out the interleaved packet will be output here

libavformat/version.h

@@ -31,7 +31,7 @@
 
 #define LIBAVFORMAT_VERSION_MAJOR 57
 #define LIBAVFORMAT_VERSION_MINOR  7
-#define LIBAVFORMAT_VERSION_MICRO  0
+#define LIBAVFORMAT_VERSION_MICRO  1
 
 #define LIBAVFORMAT_VERSION_INT AV_VERSION_INT(LIBAVFORMAT_VERSION_MAJOR, \
                                                LIBAVFORMAT_VERSION_MINOR, \