FFmpeg结构体之AVCodec

Posted 2020-10-19 wangyaoguo

AVCodec字段

AVCodec是存储编解码器信息的结构体，主要字段注释如下：

• const char *name; //编解码器名字
• const char *long_name; //编解码器全名
• enum AVMediaType type; //编解码器类型
• enum AVCodecID id; //编解码器ID
• const AVRational *supported_framerates; //支持帧率数组（视频）
• const enum AVPixelFormat *pix_fmts; //支持像素格式数组(视频）
• const int *supported_samplerates; //支持音频采样率数组(音频）
• const enum AVSampleFormat *sample_fmts; //支持采样格式数组(音频)
• const uint64_t *channel_layouts; //支持声道数（音频）
• const AVClass *priv_class; //私有数据

AVCodec内容

以mpeg2video编码器为例，说明结构体的内容：

AVCodec遍历

编解码器以链表形式存储，av_codec_next()函数可以获得指向下一个解码器的指针，具体参考遍历AVCodec代码

常见错误

mpeg2video支持的格式有AV_PIX_FMT_YUV420P，AV_PIX_FMT_YUV422P，如果设置为AV_PIX_FMT_NV12

    AVCodec *codec  = avcodec_find_encoder(AV_CODEC_ID_MPEG2VIDEO);
    codecCtx->pix_fmt = AV_PIX_FMT_NV12;

Error：Specified pixel format nv12 is invalid or not supported

AVCodec定义

typedef struct AVCodec {
    /**
     * Name of the codec implementation.
     * The name is globally unique among encoders and among decoders (but an
     * encoder and a decoder can share the same name).
     * This is the primary way to find a codec from the user perspective.
     */
    const char *name;   
    /**
     * Descriptive name for the codec, meant to be more human readable than name.
     * You should use the NULL_IF_CONFIG_SMALL() macro to define it.
     */
    const char *long_name;  
    enum AVMediaType type; 
    enum AVCodecID id;       
    /**
     * Codec capabilities.
     * see AV_CODEC_CAP_*
     */
    int capabilities;
    const AVRational *supported_framerates; ///< array of supported framerates, or NULL if any, array is terminated by {0,0} 
    const enum AVPixelFormat *pix_fmts;     ///< array of supported pixel formats, or NULL if unknown, array is terminated by -1
    const int *supported_samplerates;       ///< array of supported audio samplerates, or NULL if unknown, array is terminated by 0
    const enum AVSampleFormat *sample_fmts; ///< array of supported sample formats, or NULL if unknown, array is terminated by -1
    const uint64_t *channel_layouts;         ///< array of support channel layouts, or NULL if unknown. array is terminated by 0
    uint8_t max_lowres;                     ///< maximum value for lowres supported by the decoder
    const AVClass *priv_class;              ///< AVClass for the private context
    const AVProfile *profiles;              ///< array of recognized profiles, or NULL if unknown, array is terminated by {FF_PROFILE_UNKNOWN}

    /*****************************************************************
     * No fields below this line are part of the public API. They
     * may not be used outside of libavcodec and can be changed and
     * removed at will.
     * New public fields should be added right above.
     *****************************************************************
     */
    int priv_data_size;
    struct AVCodec *next;
    /**
     * @name Frame-level threading support functions
     * @{
     */
    /**
     * If defined, called on thread contexts when they are created.
     * If the codec allocates writable tables in init(), re-allocate them here.
     * priv_data will be set to a copy of the original.
     */
    int (*init_thread_copy)(AVCodecContext *);
    /**
     * Copy necessary context variables from a previous thread context to the current one.
     * If not defined, the next thread will start automatically; otherwise, the codec
     * must call ff_thread_finish_setup().
     *
     * dst and src will (rarely) point to the same context, in which case memcpy should be skipped.
     */
    int (*update_thread_context)(AVCodecContext *dst, const AVCodecContext *src);
    /** @} */

    /**
     * Private codec-specific defaults.
     */
    const AVCodecDefault *defaults;

    /**
     * Initialize codec static data, called from avcodec_register().
     */
    void (*init_static_data)(struct AVCodec *codec);

    int (*init)(AVCodecContext *);
    int (*encode_sub)(AVCodecContext *, uint8_t *buf, int buf_size,
                      const struct AVSubtitle *sub);
    /**
     * Encode data to an AVPacket.
     *
     * @param      avctx          codec context
     * @param      avpkt          output AVPacket (may contain a user-provided buffer)
     * @param[in]  frame          AVFrame containing the raw data to be encoded
     * @param[out] got_packet_ptr encoder sets to 0 or 1 to indicate that a
     *                            non-empty packet was returned in avpkt.
     * @return 0 on success, negative error code on failure
     */
    int (*encode2)(AVCodecContext *avctx, AVPacket *avpkt, const AVFrame *frame,
                   int *got_packet_ptr);
    int (*decode)(AVCodecContext *, void *outdata, int *outdata_size, AVPacket *avpkt);
    int (*close)(AVCodecContext *);
    /**
     * Encode API with decoupled packet/frame dataflow. The API is the
     * same as the avcodec_ prefixed APIs (avcodec_send_frame() etc.), except
     * that:
     * - never called if the codec is closed or the wrong type,
     * - if AV_CODEC_CAP_DELAY is not set, drain frames are never sent,
     * - only one drain frame is ever passed down,
     */
    int (*send_frame)(AVCodecContext *avctx, const AVFrame *frame);
    int (*receive_packet)(AVCodecContext *avctx, AVPacket *avpkt);

    /**
     * Decode API with decoupled packet/frame dataflow. This function is called
     * to get one output frame. It should call ff_decode_get_packet() to obtain
     * input data.
     */
    int (*receive_frame)(AVCodecContext *avctx, AVFrame *frame);
    /**
     * Flush buffers.
     * Will be called when seeking
     */
    void (*flush)(AVCodecContext *);
    /**
     * Internal codec capabilities.
     * See FF_CODEC_CAP_* in internal.h
     */
    int caps_internal;

    /**
     * Decoding only, a comma-separated list of bitstream filters to apply to
     * packets before decoding.
     */
    const char *bsfs;
} AVCodec;

关联类型

enum AVMediaType {
    AVMEDIA_TYPE_UNKNOWN = -1,  ///< Usually treated as AVMEDIA_TYPE_DATA
    AVMEDIA_TYPE_VIDEO,
    AVMEDIA_TYPE_AUDIO,
    AVMEDIA_TYPE_DATA,          ///< Opaque data information usually continuous
    AVMEDIA_TYPE_SUBTITLE,
    AVMEDIA_TYPE_ATTACHMENT,    ///< Opaque data information usually sparse
    AVMEDIA_TYPE_NB
};

enum AVCodecID {
    AV_CODEC_ID_NONE,

    /* video codecs */
    AV_CODEC_ID_MPEG1VIDEO,
    AV_CODEC_ID_MPEG2VIDEO, ///< preferred ID for MPEG-1/2 video decoding
#if FF_API_XVMC
    AV_CODEC_ID_MPEG2VIDEO_XVMC,
#endif /* FF_API_XVMC */
    AV_CODEC_ID_H261,
    AV_CODEC_ID_H263,
    AV_CODEC_ID_RV10,
    AV_CODEC_ID_RV20,
    AV_CODEC_ID_MJPEG,
    AV_CODEC_ID_MJPEGB,
    AV_CODEC_ID_LJPEG,
    AV_CODEC_ID_SP5X,
    AV_CODEC_ID_JPEGLS,
    AV_CODEC_ID_MPEG4,
    AV_CODEC_ID_RAWVIDEO,
    AV_CODEC_ID_MSMPEG4V1,
    AV_CODEC_ID_MSMPEG4V2,
    .......
}

/**
 * Rational number (pair of numerator and denominator).
 */
typedef struct AVRational{
    int num; ///< Numerator
    int den; ///< Denominator
} AVRational;

enum AVPixelFormat {
    AV_PIX_FMT_NONE = -1,
    AV_PIX_FMT_YUV420P,   ///< planar YUV 4:2:0, 12bpp, (1 Cr & Cb sample per 2x2 Y samples)
    AV_PIX_FMT_YUYV422,   ///< packed YUV 4:2:2, 16bpp, Y0 Cb Y1 Cr
    AV_PIX_FMT_RGB24,     ///< packed RGB 8:8:8, 24bpp, RGBRGB...
    AV_PIX_FMT_BGR24,     ///< packed RGB 8:8:8, 24bpp, BGRBGR...
    AV_PIX_FMT_YUV422P,   ///< planar YUV 4:2:2, 16bpp, (1 Cr & Cb sample per 2x1 Y samples)
    AV_PIX_FMT_YUV444P,   ///< planar YUV 4:4:4, 24bpp, (1 Cr & Cb sample per 1x1 Y samples)
    AV_PIX_FMT_YUV410P,   ///< planar YUV 4:1:0,  9bpp, (1 Cr & Cb sample per 4x4 Y samples)
    AV_PIX_FMT_YUV411P,   ///< planar YUV 4:1:1, 12bpp, (1 Cr & Cb sample per 4x1 Y samples)
    AV_PIX_FMT_GRAY8,     ///<        Y        ,  8bpp
    AV_PIX_FMT_MONOWHITE, ///<        Y        ,  1bpp, 0 is white, 1 is black, in each byte pixels are ordered from the msb to the lsb
    AV_PIX_FMT_MONOBLACK, ///<        Y        ,  1bpp, 0 is black, 1 is white, in each byte pixels are ordered from the msb to the lsb
    AV_PIX_FMT_PAL8,      ///< 8 bits with AV_PIX_FMT_RGB32 palette
    AV_PIX_FMT_YUVJ420P,  ///< planar YUV 4:2:0, 12bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV420P and setting color_range
    AV_PIX_FMT_YUVJ422P,  ///< planar YUV 4:2:2, 16bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV422P and setting color_range
    AV_PIX_FMT_YUVJ444P,  ///< planar YUV 4:4:4, 24bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV444P and setting color_range
#if FF_API_XVMC
    AV_PIX_FMT_XVMC_MPEG2_MC,///< XVideo Motion Acceleration via common packet passing
    AV_PIX_FMT_XVMC_MPEG2_IDCT,
    AV_PIX_FMT_XVMC = AV_PIX_FMT_XVMC_MPEG2_IDCT,
#endif /* FF_API_XVMC */
    AV_PIX_FMT_UYVY422,   
    ......
}

enum AVSampleFormat {
    AV_SAMPLE_FMT_NONE = -1,
    AV_SAMPLE_FMT_U8,          ///< unsigned 8 bits
    AV_SAMPLE_FMT_S16,         ///< signed 16 bits
    AV_SAMPLE_FMT_S32,         ///< signed 32 bits
    AV_SAMPLE_FMT_FLT,         ///< float
    AV_SAMPLE_FMT_DBL,         ///< double

    AV_SAMPLE_FMT_U8P,         ///< unsigned 8 bits, planar
    AV_SAMPLE_FMT_S16P,        ///< signed 16 bits, planar
    AV_SAMPLE_FMT_S32P,        ///< signed 32 bits, planar
    AV_SAMPLE_FMT_FLTP,        ///< float, planar
    AV_SAMPLE_FMT_DBLP,        ///< double, planar
    AV_SAMPLE_FMT_S64,         ///< signed 64 bits
    AV_SAMPLE_FMT_S64P,        ///< signed 64 bits, planar

    AV_SAMPLE_FMT_NB           ///< Number of sample formats. DO NOT USE if linking dynamically
};

typedef struct AVClass {
    /**
     * The name of the class; usually it is the same name as the
     * context structure type to which the AVClass is associated.
     */
    const char* class_name;

    /**
     * A pointer to a function which returns the name of a context
     * instance ctx associated with the class.
     */
    const char* (*item_name)(void* ctx);

    /**
     * a pointer to the first option specified in the class if any or NULL
     *
     * @see av_set_default_options()
     */
    const struct AVOption *option;

    /**
     * LIBAVUTIL_VERSION with which this structure was created.
     * This is used to allow fields to be added without requiring major
     * version bumps everywhere.
     */

    int version;

    /**
     * Offset in the structure where log_level_offset is stored.
     * 0 means there is no such variable
     */
    int log_level_offset_offset;

    /**
     * Offset in the structure where a pointer to the parent context for
     * logging is stored. For example a decoder could pass its AVCodecContext
     * to eval as such a parent context, which an av_log() implementation
     * could then leverage to display the parent context.
     * The offset can be NULL.
     */
    int parent_log_context_offset;

    /**
     * Return next AVOptions-enabled child or NULL
     */
    void* (*child_next)(void *obj, void *prev);

    /**
     * Return an AVClass corresponding to the next potential
     * AVOptions-enabled child.
     *
     * The difference between child_next and this is that
     * child_next iterates over _already existing_ objects, while
     * child_class_next iterates over _all possible_ children.
     */
    const struct AVClass* (*child_class_next)(const struct AVClass *prev);

    /**
     * Category used for visualization (like color)
     * This is only set if the category is equal for all objects using this class.
     * available since version (51 << 16 | 56 << 8 | 100)
     */
    AVClassCategory category;

    /**
     * Callback to return the category.
     * available since version (51 << 16 | 59 << 8 | 100)
     */
    AVClassCategory (*get_category)(void* ctx);

    /**
     * Callback to return the supported/allowed ranges.
     * available since version (52.12)
     */
    int (*query_ranges)(struct AVOptionRanges **, void *obj, const char *key, int flags);
} AVClass;

typedef struct AVProfile {
    int profile;
    const char *name; ///< short name for the profile
} AVProfile;