[FFmpeg-devel] [PATCH 2/2] avformat/flvdec: support enhanced flv PacketTypeMetadata

James Almer jamrial at gmail.com
Mon Dec 4 23:32:51 EET 2023


On 11/15/2023 11:40 AM, zhupengfei via ffmpeg-devel wrote:
> From: Zhu Pengfei <411294962 at qq.com>
> 
> Signed-off-by: Zhu Pengfei <411294962 at qq.com>
> ---
>   libavformat/flvdec.c | 171 ++++++++++++++++++++++++++++++++++++++++++-
>   1 file changed, 170 insertions(+), 1 deletion(-)
> 
> diff --git a/libavformat/flvdec.c b/libavformat/flvdec.c
> index e25b5bd163..46bb0825ca 100644
> --- a/libavformat/flvdec.c
> +++ b/libavformat/flvdec.c
> @@ -34,6 +34,7 @@
>   #include "libavutil/intfloat.h"
>   #include "libavutil/intreadwrite.h"
>   #include "libavutil/mathematics.h"
> +#include "libavutil/mastering_display_metadata.h"
>   #include "avformat.h"
>   #include "demux.h"
>   #include "internal.h"
> @@ -45,6 +46,28 @@
>   
>   #define MAX_DEPTH 16      ///< arbitrary limit to prevent unbounded recursion
>   
> +typedef struct FLVMasteringMeta {
> +    double r_x;
> +    double r_y;
> +    double g_x;
> +    double g_y;
> +    double b_x;
> +    double b_y;
> +    double white_x;
> +    double white_y;
> +    double max_luminance;
> +    double min_luminance;
> +} FLVMasteringMeta;
> +
> +typedef struct FLVMetaVideoColor {
> +    uint64_t matrix_coefficients;
> +    uint64_t transfer_characteristics;
> +    uint64_t primaries;
> +    uint64_t max_cll;
> +    uint64_t max_fall;
> +    FLVMasteringMeta mastering_meta;
> +} FLVMetaVideoColor;
> +
>   typedef struct FLVContext {
>       const AVClass *class; ///< Class for private options.
>       int trust_metadata;   ///< configure streams according onMetaData
> @@ -80,6 +103,8 @@ typedef struct FLVContext {
>       int64_t time_offset;
>       int64_t time_pos;
>   
> +    FLVMetaVideoColor *metaVideoColor;
> +    int meta_color_info_flag;
>   } FLVContext;
>   
>   /* AMF date type */
> @@ -524,6 +549,7 @@ static int amf_parse_object(AVFormatContext *s, AVStream *astream,
>       FLVContext *flv = s->priv_data;
>       AVIOContext *ioc;
>       AMFDataType amf_type;
> +    FLVMetaVideoColor *meta_video_color = flv->metaVideoColor;
>       char str_val[1024];
>       double num_val;
>       amf_date date;
> @@ -655,6 +681,36 @@ static int amf_parse_object(AVFormatContext *s, AVStream *astream,
>                       } else if (!strcmp(key, "height") && vpar) {
>                           vpar->height = num_val;
>                       }
> +                } else if (!strcmp(key, "colorPrimaries") && meta_video_color) {

You should put this inside an "else if (meta_video_color)" block, 
instead of checking for meta_video_color with every single string.

See how it's done for flv->trust_metadata above.

> +                    meta_video_color->primaries = num_val;
> +                } else if (!strcmp(key, "transferCharacteristics") && meta_video_color) {
> +                    meta_video_color->transfer_characteristics = num_val;
> +                } else if (!strcmp(key, "matrixCoefficients") && meta_video_color) {
> +                    meta_video_color->matrix_coefficients = num_val;
> +                } else if (!strcmp(key, "maxFall") && meta_video_color) {
> +                    meta_video_color->max_fall = num_val;
> +                } else if (!strcmp(key, "maxCLL") && meta_video_color) {
> +                    meta_video_color->max_cll = num_val;
> +                } else if (!strcmp(key, "redX") && meta_video_color) {
> +                    meta_video_color->mastering_meta.r_x = num_val;
> +                } else if (!strcmp(key, "redY") && meta_video_color) {
> +                    meta_video_color->mastering_meta.r_y = num_val;
> +                } else if (!strcmp(key, "greenX") && meta_video_color) {
> +                    meta_video_color->mastering_meta.g_x = num_val;
> +                } else if (!strcmp(key, "greenY") && meta_video_color) {
> +                    meta_video_color->mastering_meta.g_y = num_val;
> +                } else if (!strcmp(key, "blueX") && meta_video_color) {
> +                    meta_video_color->mastering_meta.b_x = num_val;
> +                } else if (!strcmp(key, "blueY") && meta_video_color) {
> +                    meta_video_color->mastering_meta.b_y = num_val;
> +                } else if (!strcmp(key, "whitePointX") && meta_video_color) {
> +                    meta_video_color->mastering_meta.white_x = num_val;
> +                } else if (!strcmp(key, "whitePointY") && meta_video_color) {
> +                    meta_video_color->mastering_meta.white_y = num_val;
> +                } else if (!strcmp(key, "maxLuminance") && meta_video_color) {
> +                    meta_video_color->mastering_meta.max_luminance = num_val;
> +                } else if (!strcmp(key, "minLuminance") && meta_video_color) {
> +                    meta_video_color->mastering_meta.min_luminance = num_val;
>                   }
>               }
>               if (amf_type == AMF_DATA_TYPE_STRING) {
> @@ -824,6 +880,7 @@ static int flv_read_close(AVFormatContext *s)
>           av_freep(&flv->new_extradata[i]);
>       av_freep(&flv->keyframe_times);
>       av_freep(&flv->keyframe_filepositions);
> +    av_freep(&flv->metaVideoColor);
>       return 0;
>   }
>   
> @@ -1028,6 +1085,104 @@ static int resync(AVFormatContext *s)
>       return AVERROR_EOF;
>   }
>   
> +static int flv_parse_video_color_info(AVFormatContext *s, AVStream *st, int64_t next_pos)
> +{
> +    FLVContext *flv = s->priv_data;
> +    AMFDataType type;
> +    AVIOContext *ioc;
> +    char buffer[32];
> +    ioc     = s->pb;
> +
> +    // first object needs to be "colorInfo" string
> +    type = avio_r8(ioc);
> +    if (type != AMF_DATA_TYPE_STRING ||
> +        amf_get_string(ioc, buffer, sizeof(buffer)) < 0)
> +        return TYPE_UNKNOWN;
> +
> +    if (strcmp(buffer, "colorInfo")) {
> +        av_log(s, AV_LOG_DEBUG, "Unknown type %s\n", buffer);
> +        return TYPE_UNKNOWN;
> +    }
> +
> +    flv->metaVideoColor = av_mallocz(sizeof(FLVMetaVideoColor));
> +    if (!flv->metaVideoColor) {
> +        return AVERROR(ENOMEM);
> +    }
> +    flv->meta_color_info_flag = 1;
> +    amf_parse_object(s, NULL, NULL, buffer, next_pos, 0); // parse metadata
> +    return 0;
> +}
> +
> +static int flv_update_video_color_info(AVFormatContext *s, AVStream *st)
> +{
> +    FLVContext *flv = s->priv_data;
> +    const FLVMetaVideoColor* meta_video_color = flv->metaVideoColor;
> +    const FLVMasteringMeta *mastering_meta = &meta_video_color->mastering_meta;
> +
> +    int has_mastering_primaries, has_mastering_luminance;
> +    // Mastering primaries are CIE 1931 coords, and must be > 0.
> +    has_mastering_primaries =
> +        mastering_meta->r_x > 0 && mastering_meta->r_y > 0 &&
> +        mastering_meta->g_x > 0 && mastering_meta->g_y > 0 &&
> +        mastering_meta->b_x > 0 && mastering_meta->b_y > 0 &&
> +        mastering_meta->white_x > 0 && mastering_meta->white_y > 0;
> +    has_mastering_luminance = mastering_meta->max_luminance >= 0 && mastering_meta->min_luminance >= 0;
> +
> +    if (meta_video_color->matrix_coefficients != AVCOL_SPC_RESERVED)
> +        st->codecpar->color_space = meta_video_color->matrix_coefficients;
> +    if (meta_video_color->primaries != AVCOL_PRI_RESERVED &&
> +        meta_video_color->primaries != AVCOL_PRI_RESERVED0)
> +        st->codecpar->color_primaries = meta_video_color->primaries;
> +    if (meta_video_color->transfer_characteristics != AVCOL_TRC_RESERVED &&
> +        meta_video_color->transfer_characteristics != AVCOL_TRC_RESERVED0)
> +        st->codecpar->color_trc = meta_video_color->transfer_characteristics;
> +
> +    if (meta_video_color->max_cll && meta_video_color->max_fall) {
> +        size_t size = 0;
> +        AVContentLightMetadata *metadata = av_content_light_metadata_alloc(&size);
> +        if (!metadata)
> +            return AVERROR(ENOMEM);
> +        if (!av_packet_side_data_add(&st->codecpar->coded_side_data, &st->codecpar->nb_coded_side_data,
> +                                        AV_PKT_DATA_CONTENT_LIGHT_LEVEL, metadata, size, 0)) {
> +            av_freep(&metadata);
> +            return AVERROR(ENOMEM);
> +        }
> +        metadata->MaxCLL  = meta_video_color->max_cll;
> +        metadata->MaxFALL = meta_video_color->max_fall;
> +    }
> +
> +    if (has_mastering_primaries || has_mastering_luminance) {
> +        AVMasteringDisplayMetadata *metadata;
> +        AVPacketSideData *sd = av_packet_side_data_new(&st->codecpar->coded_side_data,
> +                                                        &st->codecpar->nb_coded_side_data,
> +                                                        AV_PKT_DATA_MASTERING_DISPLAY_METADATA,
> +                                                        sizeof(AVMasteringDisplayMetadata), 0);
> +        if (!sd)
> +            return AVERROR(ENOMEM);
> +        metadata = (AVMasteringDisplayMetadata*)sd->data;
> +        memset(metadata, 0, sizeof(AVMasteringDisplayMetadata));
> +        // hdrCll
> +        if (has_mastering_luminance) {
> +            metadata->max_luminance = av_d2q(mastering_meta->max_luminance, INT_MAX);
> +            metadata->min_luminance = av_d2q(mastering_meta->min_luminance, INT_MAX);
> +            metadata->has_luminance = 1;
> +        }
> +        // hdrMdcv
> +        if (has_mastering_primaries) {
> +            metadata->display_primaries[0][0] = av_d2q(mastering_meta->r_x, INT_MAX);
> +            metadata->display_primaries[0][1] = av_d2q(mastering_meta->r_y, INT_MAX);
> +            metadata->display_primaries[1][0] = av_d2q(mastering_meta->g_x, INT_MAX);
> +            metadata->display_primaries[1][1] = av_d2q(mastering_meta->g_y, INT_MAX);
> +            metadata->display_primaries[2][0] = av_d2q(mastering_meta->b_x, INT_MAX);
> +            metadata->display_primaries[2][1] = av_d2q(mastering_meta->b_y, INT_MAX);
> +            metadata->white_point[0] = av_d2q(mastering_meta->white_x, INT_MAX);
> +            metadata->white_point[1] = av_d2q(mastering_meta->white_y, INT_MAX);
> +            metadata->has_primaries = 1;
> +        }
> +    }
> +    return 0;
> +}
> +
>   static int flv_read_packet(AVFormatContext *s, AVPacket *pkt)
>   {
>       FLVContext *flv = s->priv_data;
> @@ -1100,8 +1255,17 @@ retry:
>               video_codec_id = avio_rb32(s->pb);
>               size -= 4;
>           }
> -        if ((flags & FLV_VIDEO_FRAMETYPE_MASK) == FLV_FRAME_VIDEO_INFO_CMD)
> +
> +        if (enhanced_flv && stream_type == FLV_STREAM_TYPE_VIDEO && (flags & FLV_VIDEO_FRAMETYPE_MASK) == FLV_FRAME_VIDEO_INFO_CMD) {
> +            type = flags & 0x0F;
> +            if (type == PacketTypeMetadata) {
> +                int ret = flv_parse_video_color_info(s, st, next);
> +                av_log(s, AV_LOG_INFO, "enhanced flv parse metadata ret %d and skip\n", ret);
> +            }
> +            goto skip;
> +        } else if ((flags & FLV_VIDEO_FRAMETYPE_MASK) == FLV_FRAME_VIDEO_INFO_CMD) {
>               goto skip;
> +        }
>       } else if (type == FLV_TAG_TYPE_META) {
>           stream_type=FLV_STREAM_TYPE_SUBTITLE;
>           if (size > 13 + 1 + 4) { // Header-type metadata stuff
> @@ -1287,6 +1451,11 @@ retry_duration:
>               goto leave;
>           }
>   
> +        if (enhanced_flv && stream_type == FLV_STREAM_TYPE_VIDEO && flv->meta_color_info_flag) {
> +            flv_update_video_color_info(s, st); // update av packet side data
> +            flv->meta_color_info_flag = 0;
> +        }
> +
>           if (st->codecpar->codec_id == AV_CODEC_ID_H264 || st->codecpar->codec_id == AV_CODEC_ID_MPEG4 ||
>               (st->codecpar->codec_id == AV_CODEC_ID_HEVC && type == PacketTypeCodedFrames)) {
>               // sign extension

A test for this would be nice. Can be one that creates a file and then 
demuxes it.
See the fate-lavf-fate-* tests to remux an existing sample.


More information about the ffmpeg-devel mailing list