AVCodec是存储编解码器信息的结构体。本文将会详细分析一下该结构体里每个变量的含义和作用。
首先看一下结构体的定义(位于libavcodec\avcodec.h文件中):
/**
* AVCodec.
*/
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}
/**
* Group name of the codec implementation.
* This is a short symbolic name of the wrapper backing this codec. A
* wrapper uses some kind of external implementation for the codec, such
* as an external library, or a codec implementation provided by the OS or
* the hardware.
* If this field is NULL, this is a builtin, libavcodec native codec.
* If non-NULL, this will be the suffix in AVCodec.name in most cases
* (usually AVCodec.name will be of the form "<codec_name>_<wrapper_name>").
*/
const char *wrapper_name;
/*****************************************************************
* 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().
*
* This is not intended for time consuming operations as it is
* run for every codec regardless of that codec being used.
*/
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;
/**
* Array of pointers to hardware configurations supported by the codec,
* or NULL if no hardware supported. The array is terminated by a NULL
* pointer.
*
* The user can only access this field via avcodec_get_hw_config().
*/
const struct AVCodecHWConfigInternal **hw_configs;
} AVCodec;
下面说一下最主要的几个变量:
@ const char *name:编解码器的名字,比较短
@ const char *long_name:编解码器的名字,全称,比较长
@ enum AVMediaType type:指明了类型,是视频,音频,还是字幕
@ enum AVCodecID id:ID,不重复
@ const AVRational *supported_framerates:支持的帧率(仅视频)
@ const enum AVPixelFormat *pix_fmts:支持的像素格式(仅视频)
@ const int *supported_samplerates:支持的采样率(仅音频)
@ const enum AVSampleFormat *sample_fmts:支持的采样格式(仅音频)
@ const uint64_t *channel_layouts:支持的声道数(仅音频)
@ int priv_data_size:私有数据的大小
详细介绍几个变量:
1.enum AVMediaType type
AVMediaType定义如下:
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
};
2.enum AVCodecID id
AVCodecID定义如下:
enum AVCodecID {
AV_CODEC_ID_NONE,
/* video codecs */
AV_CODEC_ID_MPEG1VIDEO,
.....
AV_CODEC_ID_WMV1,
AV_CODEC_ID_WMV2,
AV_CODEC_ID_H263P,
AV_CODEC_ID_H263I,
AV_CODEC_ID_FLV1,
AV_CODEC_ID_SVQ1,
AV_CODEC_ID_SVQ3,
AV_CODEC_ID_DVVIDEO,
AV_CODEC_ID_HUFFYUV,
AV_CODEC_ID_CYUV,
AV_CODEC_ID_H264,
...(代码太长,略)
}
3.const enum AVPixelFormat *pix_fmts
AVPixelFormat定义如下:
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 bit with PIX_FMT_RGB32 palette
AV_PIX_FMT_YUVJ420P, ///< planar YUV 4:2:0, 12bpp, full scale (JPEG), deprecated in favor of PIX_FMT_YUV420P and setting color_range
AV_PIX_FMT_YUVJ422P, ///< planar YUV 4:2:2, 16bpp, full scale (JPEG), deprecated in favor of PIX_FMT_YUV422P and setting color_range
AV_PIX_FMT_YUVJ444P, ///< planar YUV 4:4:4, 24bpp, full scale (JPEG), deprecated in favor of PIX_FMT_YUV444P and setting color_range
AV_PIX_FMT_XVMC_MPEG2_MC,///< XVideo Motion Acceleration via common packet passing
AV_PIX_FMT_XVMC_MPEG2_IDCT,
...(代码太长,略)
}
4.const enum AVSampleFormat *sample_fmts
AVSampleFormat定义如下:
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_NB ///< Number of sample formats. DO NOT USE if linking dynamically
};
每一个编解码器对应一个该结构体,查看一下ffmpeg的源代码,我们可以看一下H.264解码器的结构体如下所示(libavcodec\h264dec.c):
AVCodec ff_h264_decoder = {
.name = "h264",
.long_name = NULL_IF_CONFIG_SMALL("H.264 / AVC / MPEG-4 AVC / MPEG-4 part 10"),
.type = AVMEDIA_TYPE_VIDEO,
.id = AV_CODEC_ID_H264,
.priv_data_size = sizeof(H264Context),
.init = h264_decode_init,
.close = h264_decode_end,
.decode = h264_decode_frame,
.capabilities = /*AV_CODEC_CAP_DRAW_HORIZ_BAND |*/ AV_CODEC_CAP_DR1 |
AV_CODEC_CAP_DELAY | AV_CODEC_CAP_SLICE_THREADS |
AV_CODEC_CAP_FRAME_THREADS,
.hw_configs = (const AVCodecHWConfigInternal*[]) {
#if CONFIG_H264_DXVA2_HWACCEL
HWACCEL_DXVA2(h264),
#endif
#if CONFIG_H264_D3D11VA_HWACCEL
HWACCEL_D3D11VA(h264),
#endif
#if CONFIG_H264_D3D11VA2_HWACCEL
HWACCEL_D3D11VA2(h264),
#endif
#if CONFIG_H264_NVDEC_HWACCEL
HWACCEL_NVDEC(h264),
#endif
#if CONFIG_H264_VAAPI_HWACCEL
HWACCEL_VAAPI(h264),
#endif
#if CONFIG_H264_VDPAU_HWACCEL
HWACCEL_VDPAU(h264),
#endif
#if CONFIG_H264_VIDEOTOOLBOX_HWACCEL
HWACCEL_VIDEOTOOLBOX(h264),
#endif
NULL
},
.caps_internal = FF_CODEC_CAP_INIT_THREADSAFE | FF_CODEC_CAP_EXPORTS_CROPPING,
.flush = flush_dpb,
.init_thread_copy = ONLY_IF_THREADS_ENABLED(decode_init_thread_copy),
.update_thread_context = ONLY_IF_THREADS_ENABLED(ff_h264_update_thread_context),
.profiles = NULL_IF_CONFIG_SMALL(ff_h264_profiles),
.priv_class = &h264_class,
};
参考文献:
https://www.jianshu.com/p/0f7320e6e647
https://blog.csdn.net/leixiaohua1020/article/details/14215833