Re: [FFmpeg-devel] [PATCH] avformat/mov: Add support for demuxing still HEIC images

[Leo Izen <leo.izen@gmail.com>]

On 9/26/23 13:37, Vignesh Venkatasubramanian via ffmpeg-devel wrote:
> They are similar to AVIF images (both use the HEIF container).
> The only additional work needed is to parse the hvcC box and put
> it in the extradata.
> 
> With this patch applied, ffmpeg (when built with an HEVC decoder)
> is able to decode the files in
> https://github.com/nokiatech/heif/tree/gh-pages/content/images
> 
> Partially fixes trac ticket #6521.
> 
> Signed-off-by: Vignesh Venkatasubramanian <vigneshv@google.com>
> ---
>   libavformat/isom.h |  2 ++
>   libavformat/mov.c  | 38 +++++++++++++++++++++++++++++++++++++-
>   2 files changed, 39 insertions(+), 1 deletion(-)
> 
> diff --git a/libavformat/isom.h b/libavformat/isom.h
> index 3d375d7a46..b30b9da65e 100644
> --- a/libavformat/isom.h
> +++ b/libavformat/isom.h
> @@ -327,6 +327,8 @@ typedef struct MOVContext {
>           int64_t extent_offset;
>       } *avif_info;
>       int avif_info_size;
> +    int64_t hvcC_offset;
> +    int hvcC_size;
>       int interleaved_read;
>   } MOVContext;
>   
> diff --git a/libavformat/mov.c b/libavformat/mov.c
> index 1996e0028c..cec9cb5fe1 100644
> --- a/libavformat/mov.c
> +++ b/libavformat/mov.c
> @@ -1218,7 +1218,8 @@ static int mov_read_ftyp(MOVContext *c, AVIOContext *pb, MOVAtom atom)
>           c->isom = 1;
>       av_log(c->fc, AV_LOG_DEBUG, "ISO: File Type Major Brand: %.4s\n",(char *)&type);
>       av_dict_set(&c->fc->metadata, "major_brand", type, 0);
> -    c->is_still_picture_avif = !strncmp(type, "avif", 4);
> +    c->is_still_picture_avif = !strncmp(type, "avif", 4) ||
> +                               !strncmp(type, "mif1", 4);

This appears to be an unrelated change. Is it?

>       minor_ver = avio_rb32(pb); /* minor version */
>       av_dict_set_int(&c->fc->metadata, "minor_version", minor_ver, 0);
>   
> @@ -4911,6 +4912,16 @@ static int avif_add_stream(MOVContext *c, int item_id)
>       st->priv_data = sc;
>       st->codecpar->codec_type = AVMEDIA_TYPE_VIDEO;
>       st->codecpar->codec_id = AV_CODEC_ID_AV1;
> +    if (c->hvcC_offset >= 0) {
> +        int ret;
> +        int64_t pos = avio_tell(c->fc->pb);
> +        st->codecpar->codec_id = AV_CODEC_ID_HEVC;
> +        avio_seek(c->fc->pb, c->hvcC_offset, SEEK_SET);
> +        ret = ff_get_extradata(c->fc, st->codecpar, c->fc->pb, c->hvcC_size);
> +        if (ret < 0)
> +            return ret;
> +        avio_seek(c->fc->pb, pos, SEEK_SET);
> +    }

Will this fail on non-seekable input? If it does, do we care?

>       sc->ffindex = st->index;
>       c->trak_index = st->index;
>       st->avg_frame_rate.num = st->avg_frame_rate.den = 1;
> @@ -4953,6 +4964,8 @@ static int avif_add_stream(MOVContext *c, int item_id)
>   
>   static int mov_read_meta(MOVContext *c, AVIOContext *pb, MOVAtom atom)
>   {
> +    c->hvcC_offset = -1;
> +    c->hvcC_size = 0;
>       while (atom.size > 8) {
>           uint32_t tag;
>           if (avio_feof(pb))
> @@ -7826,6 +7839,28 @@ static int mov_read_iloc(MOVContext *c, AVIOContext *pb, MOVAtom atom)
>       return atom.size;
>   }
>   
> +static int mov_read_iprp(MOVContext *c, AVIOContext *pb, MOVAtom atom)
> +{
> +    int size = avio_rb32(pb);
> +    if (avio_rl32(pb) != MKTAG('i','p','c','o'))
> +        return AVERROR_INVALIDDATA;

Is there a reason you use ipco here instead of iprp? I'm not saying this 
is wrong, but I am confused while you're doing it this way.

> +    size -= 8;
> +    while (size > 0) {
> +        int sub_size, sub_type;
> +        sub_size = avio_rb32(pb);
> +        sub_type = avio_rl32(pb);
> +        sub_size -= 8;
> +        size -= sub_size + 8;
> +        if (sub_type == MKTAG('h','v','c','C')) {
> +            c->hvcC_offset = avio_tell(pb);
> +            c->hvcC_size = sub_size;
> +            break;
> +        }

Are these permitted to use extended-size tags? i.e. size = 1, followed 
by a big-endian 64-bit size, then followed by the tag?

> +        avio_skip(pb, sub_size);
> +    }
> +    return atom.size;
> +}
> +
>   static const MOVParseTableEntry mov_default_parse_table[] = {
>   { MKTAG('A','C','L','R'), mov_read_aclr },
>   { MKTAG('A','P','R','G'), mov_read_avid },
> @@ -7933,6 +7968,7 @@ static const MOVParseTableEntry mov_default_parse_table[] = {
>   { MKTAG('p','c','m','C'), mov_read_pcmc }, /* PCM configuration box */
>   { MKTAG('p','i','t','m'), mov_read_pitm },
>   { MKTAG('e','v','c','C'), mov_read_glbl },
> +{ MKTAG('i','p','r','p'), mov_read_iprp },
>   { 0, NULL }
>   };
>   

- Leo Izen
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel

To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".