[FFmpeg-devel] [PATCH] avformat/mxfenc: support XAVC long gop

Michael Niedermayer michael at niedermayer.cc
Thu Mar 28 20:08:34 EET 2019


On Thu, Mar 28, 2019 at 08:50:36AM -0700, Baptiste Coudurier wrote:
> ---
>  libavformat/mxf.h    |   1 +
>  libavformat/mxfenc.c | 194 ++++++++++++++++++++++++++++++++-----------
>  2 files changed, 145 insertions(+), 50 deletions(-)
> 
> diff --git a/libavformat/mxf.h b/libavformat/mxf.h
> index 4394450dea..f32124f772 100644
> --- a/libavformat/mxf.h
> +++ b/libavformat/mxf.h
> @@ -48,6 +48,7 @@ enum MXFMetadataSetType {
>      EssenceGroup,
>      TaggedValue,
>      TapeDescriptor,
> +    AVCSubDescriptor,
>  };
>  
>  enum MXFFrameLayout {
> diff --git a/libavformat/mxfenc.c b/libavformat/mxfenc.c
> index 8c6db94865..b2e818a8a5 100644
> --- a/libavformat/mxfenc.c
> +++ b/libavformat/mxfenc.c
> @@ -49,7 +49,10 @@
>  #include "libavcodec/bytestream.h"
>  #include "libavcodec/dnxhddata.h"
>  #include "libavcodec/dv_profile.h"
> -#include "libavcodec/h264.h"
> +#include "libavcodec/golomb.h"
> +#include "libavcodec/h264data.h"
> +#include "libavcodec/h264_ps.h"
> +#include "libavcodec/h2645_parse.h"
>  #include "libavcodec/internal.h"
>  #include "audiointerleave.h"
>  #include "avformat.h"
> @@ -99,6 +102,7 @@ typedef struct MXFStreamContext {
>      int max_gop;             ///< maximum gop size, used by mpeg-2 descriptor
>      int b_picture_count;     ///< maximum number of consecutive b pictures, used in mpeg-2 descriptor
>      int low_delay;           ///< low delay, used in mpeg-2 descriptor
> +    int avc_intra;
>  } MXFStreamContext;
>  
>  typedef struct MXFContainerEssenceEntry {
> @@ -167,6 +171,7 @@ static const struct {
>  static void mxf_write_wav_desc(AVFormatContext *s, AVStream *st);
>  static void mxf_write_aes3_desc(AVFormatContext *s, AVStream *st);
>  static void mxf_write_mpegvideo_desc(AVFormatContext *s, AVStream *st);
> +static void mxf_write_h264_desc(AVFormatContext *s, AVStream *st);
>  static void mxf_write_cdci_desc(AVFormatContext *s, AVStream *st);
>  static void mxf_write_generic_sound_desc(AVFormatContext *s, AVStream *st);
>  static void mxf_write_s436m_anc_desc(AVFormatContext *s, AVStream *st);
> @@ -310,7 +315,7 @@ static const MXFContainerEssenceEntry mxf_essence_container_uls[] = {
>      { { 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x0D,0x01,0x03,0x01,0x02,0x10,0x60,0x01 },
>        { 0x06,0x0E,0x2B,0x34,0x01,0x02,0x01,0x01,0x0D,0x01,0x03,0x01,0x15,0x01,0x05,0x00 },
>        { 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x00,0x00,0x00 },
> -      mxf_write_mpegvideo_desc },
> +      mxf_write_h264_desc },
>      // S436M ANC
>      { { 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x0D,0x01,0x03,0x01,0x02,0x0e,0x00,0x00 },
>        { 0x06,0x0E,0x2B,0x34,0x01,0x02,0x01,0x01,0x0D,0x01,0x03,0x01,0x17,0x01,0x02,0x00 },
> @@ -498,6 +503,12 @@ static const MXFLocalTagPair mxf_local_tag_batch[] = {
>      { 0x8006, {0x06,0x0E,0x2B,0x34,0x01,0x01,0x01,0x05,0x04,0x01,0x06,0x02,0x01,0x08,0x00,0x00}}, /* MaxGOP */
>      { 0x8007, {0x06,0x0E,0x2B,0x34,0x01,0x01,0x01,0x05,0x04,0x01,0x06,0x02,0x01,0x0A,0x00,0x00}}, /* ProfileAndLevel */
>      { 0x8008, {0x06,0x0E,0x2B,0x34,0x01,0x01,0x01,0x05,0x04,0x01,0x06,0x02,0x01,0x09,0x00,0x00}}, /* BPictureCount */
> +    // Generic Descriptor
> +    { 0x8100, {0x06,0x0E,0x2B,0x34,0x01,0x01,0x01,0x09,0x06,0x01,0x01,0x04,0x06,0x10,0x00,0x00}}, /* SubDescriptors */
> +    // AVC SubDescriptor
> +    { 0x8200, {0x06,0x0E,0x2B,0x34,0x01,0x01,0x01,0x0E,0x04,0x01,0x06,0x06,0x01,0x0E,0x00,0x00}}, /* AVC Decoding Delay */
> +    { 0x8201, {0x06,0x0E,0x2B,0x34,0x01,0x01,0x01,0x0E,0x04,0x01,0x06,0x06,0x01,0x0A,0x00,0x00}}, /* AVC Profile */
> +    { 0x8202, {0x06,0x0E,0x2B,0x34,0x01,0x01,0x01,0x0E,0x04,0x01,0x06,0x06,0x01,0x0D,0x00,0x00}}, /* AVC Level */
>      // Wave Audio Essence Descriptor
>      { 0x3D09, {0x06,0x0E,0x2B,0x34,0x01,0x01,0x01,0x05,0x04,0x02,0x03,0x03,0x05,0x00,0x00,0x00}}, /* Average Bytes Per Second */
>      { 0x3D0A, {0x06,0x0E,0x2B,0x34,0x01,0x01,0x01,0x05,0x04,0x02,0x03,0x02,0x01,0x00,0x00,0x00}}, /* Block Align */
> @@ -1126,6 +1137,8 @@ static const UID mxf_aes3_descriptor_key      = { 0x06,0x0E,0x2B,0x34,0x02,0x53,
>  static const UID mxf_cdci_descriptor_key      = { 0x06,0x0E,0x2B,0x34,0x02,0x53,0x01,0x01,0x0D,0x01,0x01,0x01,0x01,0x01,0x28,0x00 };
>  static const UID mxf_generic_sound_descriptor_key = { 0x06,0x0E,0x2B,0x34,0x02,0x53,0x01,0x01,0x0D,0x01,0x01,0x01,0x01,0x01,0x42,0x00 };
>  
> +static const UID mxf_avc_subdescriptor_key = { 0x06,0x0E,0x2B,0x34,0x02,0x53,0x01,0x01,0x0d,0x01,0x01,0x01,0x01,0x01,0x6E,0x00 };
> +
>  static int get_trc(UID ul, enum AVColorTransferCharacteristic trc)
>  {
>      switch (trc){
> @@ -1317,6 +1330,13 @@ static int64_t mxf_write_cdci_common(AVFormatContext *s, AVStream *st, const UID
>          avio_w8(pb, sc->field_dominance);
>      }
>  
> +    if (st->codecpar->codec_id == AV_CODEC_ID_H264 && !sc->avc_intra) {
> +        // write avc sub descriptor ref
> +        mxf_write_local_tag(pb, 8 + 16, 0x8100);
> +        mxf_write_refs_count(pb, 1);
> +        mxf_write_uuid(pb, AVCSubDescriptor, 0);
> +    }
> +
>      return pos;
>  }
>  
> @@ -1329,10 +1349,50 @@ static void mxf_update_klv_size(AVIOContext *pb, int64_t pos)
>      avio_seek(pb, cur_pos, SEEK_SET);
>  }
>  
> +static void mxf_write_avc_subdesc(AVFormatContext *s, AVStream *st)
> +{
> +    AVIOContext *pb = s->pb;
> +    int64_t pos;
> +
> +    avio_write(pb, mxf_avc_subdescriptor_key, 16);
> +    klv_encode_ber4_length(pb, 0);
> +    pos = avio_tell(pb);
> +
> +    mxf_write_local_tag(pb, 16, 0x3C0A);
> +    mxf_write_uuid(pb, AVCSubDescriptor, 0);
> +
> +    mxf_write_local_tag(pb, 1, 0x8200);
> +    avio_w8(pb, 0xFF); // AVC Decoding Delay, unknown
> +
> +    mxf_write_local_tag(pb, 1, 0x8201);
> +    avio_w8(pb, st->codecpar->profile); // AVC Profile
> +
> +    mxf_write_local_tag(pb, 1, 0x8202);
> +    avio_w8(pb, st->codecpar->level); // AVC Level
> +
> +    mxf_update_klv_size(s->pb, pos);
> +}
> +
>  static void mxf_write_cdci_desc(AVFormatContext *s, AVStream *st)
>  {
>      int64_t pos = mxf_write_cdci_common(s, st, mxf_cdci_descriptor_key);
>      mxf_update_klv_size(s->pb, pos);
> +
> +    if (st->codecpar->codec_id == AV_CODEC_ID_H264) {
> +        mxf_write_avc_subdesc(s, st);
> +    }
> +}
> +
> +static void mxf_write_h264_desc(AVFormatContext *s, AVStream *st)
> +{
> +    MXFStreamContext *sc = st->priv_data;
> +    if (sc->avc_intra) {
> +        mxf_write_mpegvideo_desc(s, st);
> +    } else {
> +        int64_t pos = mxf_write_cdci_common(s, st, mxf_cdci_descriptor_key);
> +        mxf_update_klv_size(s->pb, pos);
> +        mxf_write_avc_subdesc(s, st);
> +    }
>  }
>  
>  static void mxf_write_s436m_anc_desc(AVFormatContext *s, AVStream *st)
> @@ -2136,30 +2196,30 @@ static const struct {
>      int frame_size;
>      int profile;
>      uint8_t interlaced;
> -    int long_gop; // 1 or 0 when there are separate UIDs for Long GOP and Intra, -1 when Intra/LGOP detection can be ignored
> +    int intra_only; // 1 or 0 when there are separate UIDs for Long GOP and Intra, -1 when Intra/LGOP detection can be ignored
>  } mxf_h264_codec_uls[] = {
> -    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x31,0x11,0x01 },      0,  66, 0, -1 }, // AVC Baseline, Unconstrained Coding
> +    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x31,0x11,0x01 },      0,  66, 0, -1 }, // AVC Baseline
>      {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x31,0x20,0x01 },      0,  77, 0, -1 }, // AVC Main
>      {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x31,0x30,0x01 },      0,  88, 0, -1 }, // AVC Extended
>      {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x31,0x40,0x01 },      0, 100, 0, -1 }, // AVC High
> -    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x31,0x50,0x01 },      0, 110, 0,  1 }, // AVC High 10
> -    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x31,0x60,0x01 },      0, 122, 0,  1 }, // AVC High 422
> -    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x31,0x70,0x01 },      0, 244, 0,  1 }, // AVC High 444
> +    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x31,0x50,0x01 },      0, 110, 0,  0 }, // AVC High 10
> +    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x31,0x60,0x01 },      0, 122, 0,  0 }, // AVC High 422
> +    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x31,0x70,0x01 },      0, 244, 0,  0 }, // AVC High 444
>      {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x20,0x01 },      0, 110, 0,  0 }, // AVC High 10 Intra
> -    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x21,0x01 }, 232960,   0, 1,  0 }, // AVC Intra 50 1080i60
> -    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x21,0x02 }, 281088,   0, 1,  0 }, // AVC Intra 50 1080i50
> -    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x21,0x03 }, 232960,   0, 0,  0 }, // AVC Intra 50 1080p30
> -    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x21,0x04 }, 281088,   0, 0,  0 }, // AVC Intra 50 1080p25
> -    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x21,0x08 }, 116736,   0, 0,  0 }, // AVC Intra 50 720p60
> -    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x21,0x09 }, 140800,   0, 0,  0 }, // AVC Intra 50 720p50
> -    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x30,0x01 },      0, 122, 0,  0 }, // AVC High 422 Intra
> -    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x31,0x01 }, 472576,   0, 1,  0 }, // AVC Intra 100 1080i60
> -    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x31,0x02 }, 568832,   0, 1,  0 }, // AVC Intra 100 1080i50
> -    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x31,0x03 }, 472576,   0, 0,  0 }, // AVC Intra 100 1080p30
> -    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x31,0x04 }, 568832,   0, 0,  0 }, // AVC Intra 100 1080p25
> -    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x31,0x08 }, 236544,   0, 0,  0 }, // AVC Intra 100 720p60
> -    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x31,0x09 }, 284672,   0, 0,  0 }, // AVC Intra 100 720p50
> -    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0d,0x04,0x01,0x02,0x02,0x01,0x32,0x40,0x01 },      0, 244, 0,  0 }, // AVC High 444 Intra
> +    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x21,0x01 }, 232960, 110, 1,  1 }, // AVC High 10 Intra RP2027 Class 50 1080/59.94i
> +    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x21,0x02 }, 281088, 110, 1,  1 }, // AVC High 10 Intra RP2027 Class 50 1080/50i
> +    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x21,0x03 }, 232960, 110, 0,  1 }, // AVC High 10 Intra RP2027 Class 50 1080/29.97p
> +    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x21,0x04 }, 281088, 110, 0,  1 }, // AVC High 10 Intra RP2027 Class 50 1080/25p
> +    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x21,0x08 }, 116736, 110, 0,  1 }, // AVC High 10 Intra RP2027 Class 50 720/59.94p
> +    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x21,0x09 }, 140800, 110, 0,  1 }, // AVC High 10 Intra RP2027 Class 50 720/50p
> +    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x30,0x01 },      0, 122, 0,  1 }, // AVC High 422 Intra
> +    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x31,0x01 }, 472576, 122, 1,  1 }, // AVC High 422 Intra RP2027 Class 100 1080/59.94i
> +    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x31,0x02 }, 568832, 122, 1,  1 }, // AVC High 422 Intra RP2027 Class 100 1080/50i
> +    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x31,0x03 }, 472576, 122, 0,  1 }, // AVC High 422 Intra RP2027 Class 100 1080/29.97p
> +    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x31,0x04 }, 568832, 122, 0,  1 }, // AVC High 422 Intra RP2027 Class 100 1080/25p
> +    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x31,0x08 }, 236544, 122, 0,  1 }, // AVC High 422 Intra RP2027 Class 100 720/59.94p
> +    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x31,0x09 }, 284672, 122, 0,  1 }, // AVC High 422 Intra RP2027 Class 100 720/50p
> +    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0d,0x04,0x01,0x02,0x02,0x01,0x32,0x40,0x01 },      0, 244, 0,  1 }, // AVC High 444 Intra
>      {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0d,0x04,0x01,0x02,0x02,0x01,0x32,0x50,0x01 },      0,  44, 0, -1 }, // AVC CAVLC 444
>  };
>  
> @@ -2168,37 +2228,66 @@ static int mxf_parse_h264_frame(AVFormatContext *s, AVStream *st,
>  {
>      MXFContext *mxf = s->priv_data;
>      MXFStreamContext *sc = st->priv_data;
> -    AVCodecParameters *par = st->codecpar;
> -    static const int mxf_h264_num_codec_uls = sizeof(mxf_h264_codec_uls) / sizeof(mxf_h264_codec_uls[0]);
> -    const uint8_t *buf = pkt->data;
> -    const uint8_t *buf_end = pkt->data + pkt->size;
> -    uint32_t state = -1;
> -    int long_gop = 0; // assume intra when there is no SPS header
> +    int i, j, frame_size, ret, slice_type, intra_only = 0;
> +    H2645Packet hpkt = { 0 };
> +    H264ParamSets ps = { { 0 } };
>      int extra_size = 512; // support AVC Intra files without SPS/PPS header
> -    int i, frame_size;
> -    uint8_t uid_found;
>  
> -    if (pkt->size > extra_size)
> -        buf_end -= pkt->size - extra_size; // no need to parse beyond SPS/PPS header
> +    ret = ff_h2645_packet_split(&hpkt, pkt->data, pkt->size, (AVCodecContext*)s, 0, 2, AV_CODEC_ID_H264, 1);

this needs to be updated due to

992532ee3122d7938a7581988eea401b57de8189

otherwise it fails to build

CC	libavformat/mxfenc.o
libavformat/mxfenc.c: In function ‘mxf_parse_h264_frame’:
libavformat/mxfenc.c:2236:5: error: too few arguments to function ‘ff_h2645_packet_split’
     ret = ff_h2645_packet_split(&hpkt, pkt->data, pkt->size, (AVCodecContext*)s, 0, 2, AV_CODEC_ID_H264, 1);
     ^
In file included from ./libavcodec/h264dec.h:40:0,
                 from ./libavcodec/h264data.h:24,
                 from libavformat/mxfenc.c:53:
./libavcodec/h2645_parse.h:103:5: note: declared here
 int ff_h2645_packet_split(H2645Packet *pkt, const uint8_t *buf, int length,
     ^
make: *** [libavformat/mxfenc.o] Error 1
make: Target `all' not remade because of errors.

[...]
-- 
Michael     GnuPG fingerprint: 9FF2128B147EF6730BADF133611EC787040B0FAB

Good people do not need laws to tell them to act responsibly, while bad
people will find a way around the laws. -- Plato
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 181 bytes
Desc: not available
URL: <http://ffmpeg.org/pipermail/ffmpeg-devel/attachments/20190328/2e5985f2/attachment.sig>


More information about the ffmpeg-devel mailing list