movenc: Fix conversion of the first frame for extradata-less H264/HEVC

Move the copying of the frame to vos_data further up in the function,
so that when writing the actual frame data for the first frame, it's
clear that the stream really is in annex b format, for the cases where
we create extradata from the first frame.

Alternatively - we could invert the checks for bitstream format. If
extradata is missing, we can't pretend that the bitstream is in
mp4 form, because we can't even know the NAL unit length prefix size
in that case.

Also avoid creating extradata for AVC intra. If the track tag is
an AVC intra tag, don't copy the frame into vos_data - this matches
other existing cases of how vos_data and TAG_IS_AVCI interact in
other places.

Signed-off-by: Martin Storsjö <martin@martin.st>

1 files changed, 19 insertions, 16 deletions

diff --git a/libavformat/movenc.c b/libavformat/movenc.c
index e6b3ea7ef1..f9fc4d5c07 100644
--- a/libavformat/movenc.c
+++ b/libavformat/movenc.c
@@ -5504,6 +5504,25 @@ int ff_mov_write_packet(AVFormatContext *s, AVPacket *pkt)
         memset(trk->vos_data + trk->vos_len, 0, AV_INPUT_BUFFER_PADDING_SIZE);
     }
 
+    if ((par->codec_id == AV_CODEC_ID_DNXHD ||
+         par->codec_id == AV_CODEC_ID_H264 ||
+         par->codec_id == AV_CODEC_ID_HEVC ||
+         par->codec_id == AV_CODEC_ID_TRUEHD ||
+         par->codec_id == AV_CODEC_ID_AC3 ||
+         par->codec_id == AV_CODEC_ID_H264 ||
+         par->codec_id == AV_CODEC_ID_HEVC) && !trk->vos_len &&
+         !TAG_IS_AVCI(trk->tag)) {
+        /* copy frame to create needed atoms */
+        trk->vos_len  = size;
+        trk->vos_data = av_malloc(size + AV_INPUT_BUFFER_PADDING_SIZE);
+        if (!trk->vos_data) {
+            ret = AVERROR(ENOMEM);
+            goto err;
+        }
+        memcpy(trk->vos_data, pkt->data, size);
+        memset(trk->vos_data + size, 0, AV_INPUT_BUFFER_PADDING_SIZE);
+    }
+
     if (par->codec_id == AV_CODEC_ID_AAC && pkt->size > 2 &&
         (AV_RB16(pkt->data) & 0xfff0) == 0xfff0) {
         if (!s->streams[pkt->stream_index]->nb_frames) {
@@ -5582,22 +5601,6 @@ int ff_mov_write_packet(AVFormatContext *s, AVPacket *pkt)
         }
     }
 
-    if ((par->codec_id == AV_CODEC_ID_DNXHD ||
-         par->codec_id == AV_CODEC_ID_H264 ||
-         par->codec_id == AV_CODEC_ID_HEVC ||
-         par->codec_id == AV_CODEC_ID_TRUEHD ||
-         par->codec_id == AV_CODEC_ID_AC3) && !trk->vos_len) {
-        /* copy frame to create needed atoms */
-        trk->vos_len  = size;
-        trk->vos_data = av_malloc(size + AV_INPUT_BUFFER_PADDING_SIZE);
-        if (!trk->vos_data) {
-            ret = AVERROR(ENOMEM);
-            goto err;
-        }
-        memcpy(trk->vos_data, pkt->data, size);
-        memset(trk->vos_data + size, 0, AV_INPUT_BUFFER_PADDING_SIZE);
-    }
-
     if (trk->entry >= trk->cluster_capacity) {
         unsigned new_capacity = trk->entry + MOV_INDEX_CLUSTER_SIZE;
         if (av_reallocp_array(&trk->cluster, new_capacity,