[FFmpeg-devel] [PATCH] avformat/mov: Fix decoding fragmented MP4 with multiple sample entries and empty stsc

[Dimitry Andric]

On 19 Apr 2025, at 16:27, Dimitry Andric <dimitry at unified-streaming.com> wrote:
> 
> On 10 Apr 2025, at 11:03, Dimitry Andric <dimitry at unified-streaming.com> wrote:
>> 
>> On 3 Apr 2025, at 22:02, Dimitry Andric <dimitry at unified-streaming.com> wrote:
>>> 
>>> When decoding fragmented MP4 files that have an empty stsc box, and
>>> instead contain sample description indexes in their tfhd boxes, the mov
>>> demuxer does not notify the decoder whenever the current sample
>>> description index changes. If the SPS or PPS changed sufficiently, this
>>> can lead to unexpected decoding errors.
>>> 
>>> To fix this, in mov_finalize_packet(), when stsc_data is not available,
>>> use get_frag_stream_info_from_pkt() to get at the current fragment
>>> stream info, and retrieve the current sample description index from
>>> there. Then use that index in a similar manner as the stsc case.
>>> 
>>> Signed-off-by: Dimitry Andric <dimitry at unified-streaming.com>
>>> ---
>>> libavformat/mov.c | 50 ++++++++++++++++++++++++++++-------------------
>>> 1 file changed, 30 insertions(+), 20 deletions(-)
>>> 
>>> diff --git a/libavformat/mov.c b/libavformat/mov.c
>>> index 452690090c..ead89192f4 100644
>>> --- a/libavformat/mov.c
>>> +++ b/libavformat/mov.c
>>> @@ -10756,25 +10756,29 @@ static int mov_switch_root(AVFormatContext *s, int64_t target, int index)
>>>   return 1;
>>> }
>>> 
>>> -static int mov_change_extradata(AVStream *st, AVPacket *pkt)
>>> +static int mov_change_extradata(AVStream *st, AVPacket *pkt, int stsd_id)
>>> {
>>>   MOVStreamContext *sc = st->priv_data;
>>>   uint8_t *side, *extradata;
>>>   int extradata_size;
>>> 
>>> -    /* Save the current index. */
>>> -    sc->last_stsd_index = sc->stsc_data[sc->stsc_index].id - 1;
>>> +    if (stsd_id > 0 &&
>>> +        stsd_id - 1 < sc->stsd_count &&
>>> +        stsd_id - 1 != sc->last_stsd_index) {
>>> +        /* Save the current index. */
>>> +        sc->last_stsd_index = stsd_id - 1;
>>> 
>>> -    /* Notify the decoder that extradata changed. */
>>> -    extradata_size = sc->extradata_size[sc->last_stsd_index];
>>> -    extradata = sc->extradata[sc->last_stsd_index];
>>> -    if (st->discard != AVDISCARD_ALL && extradata_size > 0 && extradata) {
>>> -        side = av_packet_new_side_data(pkt,
>>> -                                       AV_PKT_DATA_NEW_EXTRADATA,
>>> -                                       extradata_size);
>>> -        if (!side)
>>> -            return AVERROR(ENOMEM);
>>> -        memcpy(side, extradata, extradata_size);
>>> +        /* Notify the decoder that extradata changed. */
>>> +        extradata_size = sc->extradata_size[sc->last_stsd_index];
>>> +        extradata = sc->extradata[sc->last_stsd_index];
>>> +        if (st->discard != AVDISCARD_ALL && extradata_size > 0 && extradata) {
>>> +            side = av_packet_new_side_data(pkt,
>>> +                                           AV_PKT_DATA_NEW_EXTRADATA,
>>> +                                           extradata_size);
>>> +            if (!side)
>>> +                return AVERROR(ENOMEM);
>>> +            memcpy(side, extradata, extradata_size);
>>> +        }
>>>   }
>>> 
>>>   return 0;
>>> @@ -10893,13 +10897,10 @@ static int mov_finalize_packet(AVFormatContext *s, AVStream *st, AVIndexEntry *s
>>> 
>>>   /* Multiple stsd handling. */
>>>   if (sc->stsc_data) {
>>> -        if (sc->stsc_data[sc->stsc_index].id > 0 &&
>>> -            sc->stsc_data[sc->stsc_index].id - 1 < sc->stsd_count &&
>>> -            sc->stsc_data[sc->stsc_index].id - 1 != sc->last_stsd_index) {
>>> -            int ret = mov_change_extradata(st, pkt);
>>> -            if (ret < 0)
>>> -                return ret;
>>> -        }
>>> +        int stsd_id = sc->stsc_data[sc->stsc_index].id;
>>> +        int ret = mov_change_extradata(st, pkt, stsd_id);
>>> +        if (ret < 0)
>>> +            return ret;
>>> 
>>>       /* Update the stsc index for the next sample */
>>>       sc->stsc_sample++;
>>> @@ -10908,6 +10909,15 @@ static int mov_finalize_packet(AVFormatContext *s, AVStream *st, AVIndexEntry *s
>>>           sc->stsc_index++;
>>>           sc->stsc_sample = 0;
>>>       }
>>> +    } else {
>>> +        MOVContext *mov = s->priv_data;
>>> +        MOVFragmentStreamInfo *frag_stream_info = get_frag_stream_info_from_pkt(&mov->frag_index, pkt, sc->id);
>>> +        if (frag_stream_info) {
>>> +            int stsd_id = frag_stream_info->stsd_id;
>>> +            int ret = mov_change_extradata(st, pkt, stsd_id);
>>> +            if (ret < 0)
>>> +                return ret;
>>> +        }
>>>   }
>>> 
>>>   return 0;
>>> -- 
>>> 2.43.0
>>> 
>> 
>> Any comments on this patch?
> 
> Ping :)

Is there any particular group of persons that "own" the mov muxer?

-Dimitry