目录
FFMPEG中结构体很多。最关键的结构体可以分成以下几类:
a) 解协议(http,rtsp,rtmp,mms)
AVIOContext,URLProtocol,URLContext主要存储视音频使用的协议的类型以及状态。URLProtocol存储输入视音频使用的封装格式。每种协议都对应一个URLProtocol结构。(注意:FFMPEG中文件也被当做一种协议“file”)
b) 解封装(flv,avi,rmvb,mp4)
AVFormatContext主要存储视音频封装格式中包含的信息;AVInputFormat存储输入视音频使用的封装格式。每种视音频封装格式都对应一个AVInputFormat 结构。
c) 解码(h264,mpeg2,aac,mp3)
每个AVStream存储一个视频/音频流的相关数据;每个AVStream对应一个AVCodecContext,存储该视频/音频流使用解码方式的相关数据;每个AVCodecContext中对应一个AVCodec,包含该视频/音频对应的解码器。每种解码器都对应一个AVCodec结构。
d) 存数据
视频的话,每个结构一般是存一帧;音频可能有好几帧
解码前数据:AVPacket
解码后数据:AVFrame
AVFrame:保存数据解码后的数据
/*
*雷霄骅
*leixiaohua1020@126.com
*中国传媒大学/数字电视技术
*/
/**
* Audio Video Frame.
* New fields can be added to the end of AVFRAME with minor version
* bumps. Similarly fields that are marked as to be only accessed by
* av_opt_ptr() can be reordered. This allows 2 forks to add fields
* without breaking compatibility with each other.
* Removal, reordering and changes in the remaining cases require
* a major version bump.
* sizeof(AVFrame) must not be used outside libavcodec.
*/
typedef struct AVFrame {
#define AV_NUM_DATA_POINTERS 8
/**图像数据
* pointer to the picture/channel planes.
* This might be different from the first allocated byte
* - encoding: Set by user
* - decoding: set by AVCodecContext.get_buffer()
*/
//解码后原始数据,针对视频可能是(YUV,RGB),音频的数据为(PCM)
uint8_t *data[AV_NUM_DATA_POINTERS];
/**
* Size, in bytes, of the data for each picture/channel plane.
*
* For audio, only linesize[0] may be set. For planar audio, each channel
* plane must be the same size.
*
* - encoding: Set by user
* - decoding: set by AVCodecContext.get_buffer()
*/
// data中每行数据的大小
int linesize[AV_NUM_DATA_POINTERS];
/**
* pointers to the data planes/channels.
*
* For video, this should simply point to data[].
*
* For planar audio, each channel has a separate data pointer, and
* linesize[0] contains the size of each channel buffer.
* For packed audio, there is just one data pointer, and linesize[0]
* contains the total size of the buffer for all channels.
*
* Note: Both data and extended_data will always be set by get_buffer(),
* but for planar audio with more channels that can fit in data,
* extended_data must be used by the decoder in order to access all
* channels.
*
* encoding: unused
* decoding: set by AVCodecContext.get_buffer()
*/
//扩展数据,指向数据平面/通道指针,对于音频的舒缓每个通道一个但对于的数据指针
//对于视频数据应该指向data[]
uint8_t **extended_data;
/**宽高
* width and height of the video frame
* - encoding: unused
* - decoding: Read by user.
*/
//视频数据的宽度和高度
int width, height;
/**
* number of audio samples (per channel) described by this frame
* - encoding: Set by user
* - decoding: Set by libavcodec
*/
//音频的一个AVframe中的包含多个视频帧
int nb_samples;
/**
* format of the frame, -1 if unknown or unset
* Values correspond to enum AVPixelFormat for video frames,
* enum AVSampleFormat for audio)
* - encoding: unused
* - decoding: Read by user.
*/
// 解码后原始数据的类型(YUV420,yuv422,RBG24)
int format;
/**
* 1 -> keyframe, 0-> not
* - encoding: Set by libavcodec.
* - decoding: Set by libavcodec.
*/
//是否是关键帧
int key_frame;
/**帧类型(I,B,P)
* Picture type of the frame, see ?_TYPE below.
* - encoding: Set by libavcodec. for coded_picture (and set by user for input).
* - decoding: Set by libavcodec.
*/
// 视频数据帧的类型
enum AVPictureType pict_type;
/**
* pointer to the first allocated byte of the picture. Can be used in get_buffer/release_buffer.
* This isn't used by libavcodec unless the default get/release_buffer() is used.
* - encoding:
* - decoding:
*/
uint8_t *base[AV_NUM_DATA_POINTERS];
/**
* sample aspect ratio for the video frame, 0/1 if unknown/unspecified
* - encoding: unused
* - decoding: Read by user.
*/
//视频数据宽高的比率
AVRational sample_aspect_ratio;
/**
* presentation timestamp in time_base units (time when frame should be shown to user)
* If AV_NOPTS_VALUE then frame_rate = 1/time_base will be assumed.
* - encoding: MUST be set by user.
* - decoding: Set by libavcodec.
*/
// 显示事件戳
int64_t pts;
/**
* reordered pts from the last AVPacket that has been input into the decoder
* - encoding: unused
* - decoding: Read by user.
*/
//
int64_t pkt_pts;
/**
* dts from the last AVPacket that has been input into the decoder
* - encoding: unused
* - decoding: Read by user.
*/
int64_t pkt_dts;
/**
* picture number in bitstream order
* - encoding: set by
* - decoding: Set by libavcodec.
*/
int coded_picture_number;
/**
* picture number in display order
* - encoding: set by
* - decoding: Set by libavcodec.
*/
int display_picture_number;
/**
* quality (between 1 (good) and FF_LAMBDA_MAX (bad))
* - encoding: Set by libavcodec. for coded_picture (and set by user for input).
* - decoding: Set by libavcodec.
*/
int quality;
/**
* is this picture used as reference
* The values for this are the same as the MpegEncContext.picture_structure
* variable, that is 1->top field, 2->bottom field, 3->frame/both fields.
* Set to 4 for delayed, non-reference frames.
* - encoding: unused
* - decoding: Set by libavcodec. (before get_buffer() call)).
*/
int reference;
/**QP表
* QP table
* - encoding: unused
* - decoding: Set by libavcodec.
*/
int8_t *qscale_table;
/**
* QP store stride
* - encoding: unused
* - decoding: Set by libavcodec.
*/
int qstride;
/**
*
*/
int qscale_type;
/**跳过宏块表
* mbskip_table[mb]>=1 if MB didn't change
* stride= mb_width = (width+15)>>4
* - encoding: unused
* - decoding: Set by libavcodec.
*/
uint8_t *mbskip_table;
/**运动矢量表
* motion vector table
* @code
* example:
* int mv_sample_log2= 4 - motion_subsample_log2;
* int mb_width= (width+15)>>4;
* int mv_stride= (mb_width << mv_sample_log2) + 1;
* motion_val[direction][x + y*mv_stride][0->mv_x, 1->mv_y];
* @endcode
* - encoding: Set by user.
* - decoding: Set by libavcodec.
*/
int16_t (*motion_val[2])[2];
/**宏块类型表
* macroblock type table
* mb_type_base + mb_width + 2
* - encoding: Set by user.
* - decoding: Set by libavcodec.
*/
uint32_t *mb_type;
/**DCT系数
* DCT coefficients
* - encoding: unused
* - decoding: Set by libavcodec.
*/
short *dct_coeff;
/**参考帧列表
* motion reference frame index
* the order in which these are stored can depend on the codec.
* - encoding: Set by user.
* - decoding: Set by libavcodec.
*/
int8_t *ref_index[2];
/**
* for some private data of the user
* - encoding: unused
* - decoding: Set by user.
*/
void *opaque;
/**
* error
* - encoding: Set by libavcodec. if flags&CODEC_FLAG_PSNR.
* - decoding: unused
*/
uint64_t error[AV_NUM_DATA_POINTERS];
/**
* type of the buffer (to keep track of who has to deallocate data[*])
* - encoding: Set by the one who allocates it.
* - decoding: Set by the one who allocates it.
* Note: User allocated (direct rendering) & internal buffers cannot coexist currently.
*/
int type;
/**
* When decoding, this signals how much the picture must be delayed.
* extra_delay = repeat_pict / (2*fps)
* - encoding: unused
* - decoding: Set by libavcodec.
*/
int repeat_pict;
/**
* The content of the picture is interlaced.
* - encoding: Set by user.
* - decoding: Set by libavcodec. (default 0)
*/
int interlaced_frame;
/**
* If the content is interlaced, is top field displayed first.
* - encoding: Set by user.
* - decoding: Set by libavcodec.
*/
int top_field_first;
/**
* Tell user application that palette has changed from previous frame.
* - encoding: ??? (no palette-enabled encoder yet)
* - decoding: Set by libavcodec. (default 0).
*/
int palette_has_changed;
/**
* codec suggestion on buffer type if != 0
* - encoding: unused
* - decoding: Set by libavcodec. (before get_buffer() call)).
*/
int buffer_hints;
/**
* Pan scan.
* - encoding: Set by user.
* - decoding: Set by libavcodec.
*/
AVPanScan *pan_scan;
/**
* reordered opaque 64bit (generally an integer or a double precision float
* PTS but can be anything).
* The user sets AVCodecContext.reordered_opaque to represent the input at
* that time,
* the decoder reorders values as needed and sets AVFrame.reordered_opaque
* to exactly one of the values provided by the user through AVCodecContext.reordered_opaque
* @deprecated in favor of pkt_pts
* - encoding: unused
* - decoding: Read by user.
*/
int64_t reordered_opaque;
/**
* hardware accelerator private data (FFmpeg-allocated)
* - encoding: unused
* - decoding: Set by libavcodec
*/
void *hwaccel_picture_private;
/**
* the AVCodecContext which ff_thread_get_buffer() was last called on
* - encoding: Set by libavcodec.
* - decoding: Set by libavcodec.
*/
struct AVCodecContext *owner;
/**
* used by multithreading to store frame-specific info
* - encoding: Set by libavcodec.
* - decoding: Set by libavcodec.
*/
void *thread_opaque;
/**
* log2 of the size of the block which a single vector in motion_val represents:
* (4->16x16, 3->8x8, 2-> 4x4, 1-> 2x2)
* - encoding: unused
* - decoding: Set by libavcodec.
*/
uint8_t motion_subsample_log2;
/**(音频)采样率
* Sample rate of the audio data.
*
* - encoding: unused
* - decoding: read by user
*/
int sample_rate;
/**
* Channel layout of the audio data.
*
* - encoding: unused
* - decoding: read by user.
*/
uint64_t channel_layout;
/**
* frame timestamp estimated using various heuristics, in stream time base
* Code outside libavcodec should access this field using:
* av_frame_get_best_effort_timestamp(frame)
* - encoding: unused
* - decoding: set by libavcodec, read by user.
*/
int64_t best_effort_timestamp;
/**
* reordered pos from the last AVPacket that has been input into the decoder
* Code outside libavcodec should access this field using:
* av_frame_get_pkt_pos(frame)
* - encoding: unused
* - decoding: Read by user.
*/
int64_t pkt_pos;
/**
* duration of the corresponding packet, expressed in
* AVStream->time_base units, 0 if unknown.
* Code outside libavcodec should access this field using:
* av_frame_get_pkt_duration(frame)
* - encoding: unused
* - decoding: Read by user.
*/
int64_t pkt_duration;
/**
* metadata.
* Code outside libavcodec should access this field using:
* av_frame_get_metadata(frame)
* - encoding: Set by user.
* - decoding: Set by libavcodec.
*/
AVDictionary *metadata;
/**
* decode error flags of the frame, set to a combination of
* FF_DECODE_ERROR_xxx flags if the decoder produced a frame, but there
* were errors during the decoding.
* Code outside libavcodec should access this field using:
* av_frame_get_decode_error_flags(frame)
* - encoding: unused
* - decoding: set by libavcodec, read by user.
*/
int decode_error_flags;
#define FF_DECODE_ERROR_INVALID_BITSTREAM 1
#define FF_DECODE_ERROR_MISSING_REFERENCE 2
/**
* number of audio channels, only used for audio.
* Code outside libavcodec should access this field using:
* av_frame_get_channels(frame)
* - encoding: unused
* - decoding: Read by user.
*/
int64_t channels;
} AVFrame;
AVPacket存储未解码的数据
typedef struct AVPacket {
//对数据包数据所在数缓冲区的引用
AVBufferRef *buf;
/**
* Presentation timestamp in AVStream->time_base units; the time at which
* the decompressed packet will be presented to the user.
* Can be AV_NOPTS_VALUE if it is not stored in the file.
* pts MUST be larger or equal to dts as presentation cannot happen before
* decompression, unless one wants to view hex dumps. Some formats misuse
* the terms dts and pts/cts to mean something different. Such timestamps
* must be converted to true pts/dts before they are stored in AVPacket.
*/
// 显示时间戳
int64_t pts;
/**
* Decompression timestamp in AVStream->time_base units; the time at which
* the packet is decompressed.
* Can be AV_NOPTS_VALUE if it is not stored in the file.
*/
// 解码事件戳
int64_t dts;
//保存压缩数据的指针
uint8_t *data;
//压缩收据的大小
int size;
// 包存在数据的的数据流的ID
int stream_index;
/**
* A combination of AV_PKT_FLAG values
*/
// 数据为最低为1表示该数据为的关键帧率
int flags;
/**
* Additional packet data that can be provided by the container.
* Packet can contain several types of side information.
*/
AVPacketSideData *side_data;
int side_data_elems;
//单位数据包的持续时间
int64_t duration;
//在数据流中的具体位置
int64_t pos; ///< byte position in stream, -1 if unknown
//保存用户的私有数据
void *opaque;
/**
* AVBufferRef for free use by the API user. FFmpeg will never check the
* contents of the buffer ref. FFmpeg calls av_buffer_unref() on it when
* the packet is unreferenced. av_packet_copy_props() calls create a new
* reference with av_buffer_ref() for the target packet's opaque_ref field.
*
* This is unrelated to the opaque field, although it serves a similar
* purpose.
*/
AVBufferRef *opaque_ref;
/**
* Time base of the packet's timestamps.
* In the future, this field may be set on packets output by encoders or
* demuxers, but its value will be by default ignored on input to decoders
* or muxers.
*/
// 数据包的时间基
AVRational time_base;
} AVPacket;
typedef struct AVBufferRef {
AVBuffer *buffer;
/**
* The data buffer. It is considered writable if and only if
* this is the only reference to the buffer, in which case
* av_buffer_is_writable() returns 1.
*/
uint8_t *data;
/**
* Size of data in bytes.
*/
size_t size;
} AVBufferRef;
AVBuffer:数据缓冲区
struct AVBuffer {
//指向一段长度为size的neicun
uint8_t *data; /**< data described by this buffer */
size_t size; /**< size of data in bytes */
// 引用计数,表示有多山个AVBufferRef对象引用了自己
atomic_uint refcount;
/**
* a callback for freeing the data
*/
void (*free)(void *opaque, uint8_t *data);
//一个指针,指向一个用户自定义类型的对象,也可为空,FFmpeg 不关心。
void *opaque;
//一些辅助自身状态的标志变量
int flags;
int flags_internal;
};
AVFormatcontext
此结构包含了一个视频流的格式内容。其中AVInputFormat或者AVOutputFormat,但是同一时间AVFormatContext内只能存在其中一个),AVStream,AVPacket这几个重要的结构以及一些其他信息,比如title,author,copyright等,后还有一些可能在编解码中会用到的信息,比如 duration、file_size、 bit_rate等。
typedef struct AVFormatContext
{
/**
* A class for logging and @ref avoptions. Set by avformat_alloc_context().
* Exports (de)muxer private options if they exist.
*/
const AVClass *av_class;
// 输入容器的格式
// avformat_open_input() 设置
ff_const59 struct AVInputFormat *iformat;
// 输出容器的个数
// avformat_write_header()设置
ff_const59 struct AVOutputFormat *oformat;
// * - muxing: set by avformat_write_header()
// * - demuxing: set by avformat_open_input()
// 格式私有数据
void *priv_data;
// I/O context. 在解复用时候,在avformat_open_input()调用之前设置
AVIOContext *pb;
// 流信息
int ctx_flags;
// 流的数量
unsigned int nb_streams;
// 文件流的链表
AVStream **streams;
#if FF_API_FORMAT_FILENAME
// 流所属的文件名
char filename[1024];
#endif
// 流的url地址
char *url;
// 开始帧的位置,只有在解复用的时候用到
int64_t start_time;
// 流的时长
int64_t duration;
// 整个流的比特率
int64_t bit_rate;
// 整个packet的大小
unsigned int packet_size;
// 最大的延迟
int max_delay;
// 解码器的状态
int flags;
#define AVFMT_FLAG_GENPTS 0x0001 ///< Generate missing pts even if it requires parsing future frames.
#define AVFMT_FLAG_IGNIDX 0x0002 ///< Ignore index.
#define AVFMT_FLAG_NONBLOCK 0x0004 ///< Do not block when reading packets from input.
#define AVFMT_FLAG_IGNDTS 0x0008 ///< Ignore DTS on frames that contain both DTS & PTS
#define AVFMT_FLAG_NOFILLIN 0x0010 ///< Do not infer any values from other values, just return what is stored in the container
#define AVFMT_FLAG_NOPARSE 0x0020 ///< Do not use AVParsers, you also must set AVFMT_FLAG_NOFILLIN as the fillin code works on frames and no parsing -> no frames. Also seeking to frames can not work if parsing to find frame boundaries has been disabled
#define AVFMT_FLAG_NOBUFFER 0x0040 ///< Do not buffer frames when possible
#define AVFMT_FLAG_CUSTOM_IO 0x0080 ///< The caller has supplied a custom AVIOContext, don't avio_close() it.
#define AVFMT_FLAG_DISCARD_CORRUPT 0x0100 ///< Discard frames marked corrupted
#define AVFMT_FLAG_FLUSH_PACKETS 0x0200 ///< Flush the AVIOContext every packet.
/**
* When muxing, try to avoid writing any random/volatile data to the output.
* This includes any random IDs, real-time timestamps/dates, muxer version, etc.
*
* This flag is mainly intended for testing.
*/
#define AVFMT_FLAG_BITEXACT 0x0400
#if FF_API_LAVF_MP4A_LATM
#define AVFMT_FLAG_MP4A_LATM 0x8000 ///< Deprecated, does nothing.
#endif
#define AVFMT_FLAG_SORT_DTS 0x10000 ///< try to interleave outputted packets by dts (using this flag can slow demuxing down)
#if FF_API_LAVF_PRIV_OPT
#define AVFMT_FLAG_PRIV_OPT 0x20000 ///< Enable use of private options by delaying codec open (deprecated, will do nothing once av_demuxer_open() is removed)
#endif
#if FF_API_LAVF_KEEPSIDE_FLAG
#define AVFMT_FLAG_KEEP_SIDE_DATA 0x40000 ///< Deprecated, does nothing.
#endif
#define AVFMT_FLAG_FAST_SEEK 0x80000 ///< Enable fast, but inaccurate seeks for some formats
#define AVFMT_FLAG_SHORTEST 0x100000 ///< Stop muxing when the shortest stream stops.
#define AVFMT_FLAG_AUTO_BSF 0x200000 ///< Add bitstream filters as requested by the muxer
// 从输入中读取最大字节数用来确定流的属性
int64_t probesize;
// 读取数据的最大持续时间
int64_t max_analyze_duration;
const uint8_t *key;
int keylen;
unsigned int nb_programs;
AVProgram **programs;
// 视屏编码数据编码器类型 Id
enum AVCodecID video_codec_id;
// 音频编码器的类型 Id
enum AVCodecID audio_codec_id;
// 字幕类型编码器的 ID
enum AVCodecID subtitle_codec_id;
// 每条流中最大内存字节数
unsigned int max_index_size;
// Buffering frames的最大内存字节数
unsigned int max_picture_buffer;
// AVChapters array的chapters的数量
unsigned int nb_chapters;
AVChapter **chapters;
/**
* Metadata that applies to the whole file.
*
* - demuxing: set by libavformat in avformat_open_input()
* - muxing: may be set by the caller before avformat_write_header()
*
* Freed by libavformat in avformat_free_context().
*/
// 元数据,应用整个数据过程
AVDictionary *metadata;
// 起始时间,从PTS=0开始
int64_t start_time_realtime;
// 帧率
int fps_probe_size;
// 错误检测
int error_recognition;
/**
* Custom interrupt callbacks for the I/O layer.
*
* demuxing: set by the user before avformat_open_input().
* muxing: set by the user before avformat_write_header()
* (mainly useful for AVFMT_NOFILE formats). The callback
* should also be passed to avio_open2() if it's used to
* open the file.
*/
AVIOInterruptCB interrupt_callback;
/**
* Flags to enable debugging.
*/
int debug;
#define FF_FDEBUG_TS 0x0001
/**
* Maximum buffering duration for interleaving.
*
* To ensure all the streams are interleaved correctly,
* av_interleaved_write_frame() will wait until it has at least one packet
* for each stream before actually writing any packets to the output file.
* When some streams are "sparse" (i.e. there are large gaps between
* successive packets), this can result in excessive buffering.
*
* This field specifies the maximum difference between the timestamps of the
* first and the last packet in the muxing queue, above which libavformat
* will output a packet regardless of whether it has queued a packet for all
* the streams.
*
* Muxing only, set by the caller before avformat_write_header().
*/
int64_t max_interleave_delta;
/**
* Allow non-standard and experimental extension
* @see AVCodecContext.strict_std_compliance
*/
int strict_std_compliance;
/**
* Flags indicating events happening on the file, a combination of
* AVFMT_EVENT_FLAG_*.
*
* - demuxing: may be set by the demuxer in avformat_open_input(),
* avformat_find_stream_info() and av_read_frame(). Flags must be cleared
* by the user once the event has been handled.
* - muxing: may be set by the user after avformat_write_header() to
* indicate a user-triggered event. The muxer will clear the flags for
* events it has handled in av_[interleaved]_write_frame().
*/
int event_flags;
/**
* - demuxing: the demuxer read new metadata from the file and updated
* AVFormatContext.metadata accordingly
* - muxing: the user updated AVFormatContext.metadata and wishes the muxer to
* write it into the file
*/
#define AVFMT_EVENT_FLAG_METADATA_UPDATED 0x0001
/**
* Maximum number of packets to read while waiting for the first timestamp.
* Decoding only.
*/
int max_ts_probe;
/**
* Avoid negative timestamps during muxing.
* Any value of the AVFMT_AVOID_NEG_TS_* constants.
* Note, this only works when using av_interleaved_write_frame. (interleave_packet_per_dts is in use)
* - muxing: Set by user
* - demuxing: unused
*/
int avoid_negative_ts;
#define AVFMT_AVOID_NEG_TS_AUTO -1 ///< Enabled when required by target format
#define AVFMT_AVOID_NEG_TS_MAKE_NON_NEGATIVE 1 ///< Shift timestamps so they are non negative
#define AVFMT_AVOID_NEG_TS_MAKE_ZERO 2 ///< Shift timestamps so that they start at 0
// 数据传输过程中的流ID
int ts_id;
// 音视频提前加载,不是所有格式都支持
int audio_preload;
// 最大chunk时长,不是所有格式都支持
int max_chunk_duration;
// 最大chunk以字节为单位
int max_chunk_size;
// 强制使用wallclock时间戳作为数据包的pts/dts
int use_wallclock_as_timestamps;
/**
* avio flags, used to force AVIO_FLAG_DIRECT.
* - encoding: unused
* - decoding: Set by user
*/
int avio_flags;
// 可以通过不同的方式估计持续时间字段
enum AVDurationEstimationMethod duration_estimation_method;
// 当字节流打开流的时候,跳过初始化字节
int64_t skip_initial_bytes;
// 纠正单个时间戳的溢出
unsigned int correct_ts_overflow;
// 强制seek到任意一帧
int seek2any;
// 在每个packet之后
int flush_packets;
// 格式探测评分
int probe_score;
// 读取最大的字节数来确定格式
int format_probesize;
// 由','分隔的所有可用的decoder(解码器)
char *codec_whitelist;
// 由‘,’分隔的所有可用的demuxers(解复用器)
char *format_whitelist;
// libavformat内部私有成员
AVFormatInternal *internal;
// I/O 更改的标志
int io_repositioned;
// 特殊解码器或者相同codec_id的视频Codec
AVCodec *video_codec;
// 特殊解码器或者相同codec_id的音频Codec
AVCodec *audio_codec;
// 特殊解码器或者相同codec_id的字幕Codec
AVCodec *subtitle_codec;
// 特殊解码器或者相同codec_id的数据Codec
AVCodec *data_codec;
/**
* Number of bytes to be written as padding in a metadata header.
* Demuxing: Unused.
* Muxing: Set by user via av_format_set_metadata_header_padding.
*/
int metadata_header_padding;
// 用户私有数据
void *opaque;
/**
* Callback used by devices to communicate with application.
*/
av_format_control_message control_message_cb;
/**
* Output timestamp offset, in microseconds.
* Muxing: set by user
*/
int64_t output_ts_offset;
/**
* dump format separator.
* can be ", " or "\n " or anything else
* - muxing: Set by user.
* - demuxing: Set by user.
*/
uint8_t *dump_separator;
/**
* Forced Data codec_id.
* Demuxing: Set by user.
*/
enum AVCodecID data_codec_id;
#if FF_API_OLD_OPEN_CALLBACKS
/**
* Called to open further IO contexts when needed for demuxing.
*
* This can be set by the user application to perform security checks on
* the URLs before opening them.
* The function should behave like avio_open2(), AVFormatContext is provided
* as contextual information and to reach AVFormatContext.opaque.
*
* If NULL then some simple checks are used together with avio_open2().
*
* Must not be accessed directly from outside avformat.
* @See av_format_set_open_cb()
*
* Demuxing: Set by user.
*
* @deprecated Use io_open and io_close.
*/
attribute_deprecated int (*open_cb)(struct AVFormatContext *s, AVIOContext **p, const char *url, int flags, const AVIOInterruptCB *int_cb, AVDictionary **options);
#endif
/**
* ',' separated list of allowed protocols.
* - encoding: unused
* - decoding: set by user
*/
// 协议白名单
char *protocol_whitelist;
/**
* A callback for opening new IO streams.
*
* Whenever a muxer or a demuxer needs to open an IO stream (typically from
* avformat_open_input() for demuxers, but for certain formats can happen at
* other times as well), it will call this callback to obtain an IO context.
*
* @param s the format context
* @param pb on success, the newly opened IO context should be returned here
* @param url the url to open
* @param flags a combination of AVIO_FLAG_*
* @param options a dictionary of additional options, with the same
* semantics as in avio_open2()
* @return 0 on success, a negative AVERROR code on failure
*
* @note Certain muxers and demuxers do nesting, i.e. they open one or more
* additional internal format contexts. Thus the AVFormatContext pointer
* passed to this callback may be different from the one facing the caller.
* It will, however, have the same 'opaque' field.
*/
int (*io_open)(struct AVFormatContext *s, AVIOContext **pb, const char *url,
int flags, AVDictionary **options);
/**
* A callback for closing the streams opened with AVFormatContext.io_open().
*/
void (*io_close)(struct AVFormatContext *s, AVIOContext *pb);
// 协议的黑名单
char *protocol_blacklist;
// 流的最大数量
int max_streams;
/**
* Skip duration calcuation in estimate_timings_from_pts.
* - encoding: unused
* - decoding: set by user
*/
int skip_estimate_duration_from_pts;
// 多少个packet用于检测
int max_probe_packets;
} AVFormatContext;
AVFormatInput
VInputFormat
是解复用器(解封装)作用时读取媒体文件并将其拆分为数据块(数据包)。每个数据包,包含一个或者多个编码帧
typedef struct AVInputFormat
{
// 封装格式的短名
const char *name;
// 封装格式的长名字
const char *long_name;
/**
* Can use flags: AVFMT_NOFILE, AVFMT_NEEDNUMBER, AVFMT_SHOW_IDS,
* AVFMT_NOTIMESTAMPS, AVFMT_GENERIC_INDEX, AVFMT_TS_DISCONT, AVFMT_NOBINSEARCH,
* AVFMT_NOGENSEARCH, AVFMT_NO_BYTE_SEEK, AVFMT_SEEK_TO_PTS.
*/
int flags;
// 如果扩展被定义就不会进行类型格式的探查
const char *extensions;
// 编码器标签
const struct AVCodecTag *const *codec_tag;
// 私有数据
const AVClass *priv_class; ///< AVClass for the private context
// mime类型,比如video/avc,在probing(探测)时候需要检查
const char *mime_type;
/*****************************************************************
* No fields below this line are part of the public API. They
* may not be used outside of libavformat and can be changed and
* removed at will.
* New public fields should be added right above.
*****************************************************************
*/
#if FF_API_NEXT
ff_const59 struct AVInputFormat *next;
#endif
// 原始Demuxer存储的codec i
int raw_codec_id;
// 魔种格式文件的数据大小
int priv_data_size;
/**
* Tell if a given file has a chance of being parsed as this format.
* The buffer provided is guaranteed to be AVPROBE_PADDING_SIZE bytes
* big so you do not have to check for that unless you need more.
*/
int (*read_probe)(const AVProbeData *);
/**
* Read the format header and initialize the AVFormatContext
* structure. Return 0 if OK. 'avformat_new_stream' should be
* called to create new streams.
*/
int (*read_header)(struct AVFormatContext *);
/**
* Read one packet and put it in 'pkt'. pts and flags are also
* set. 'avformat_new_stream' can be called only if the flag
* AVFMTCTX_NOHEADER is used and only in the calling thread (not in a
* background thread).
* @return 0 on success, < 0 on error.
* Upon returning an error, pkt must be unreferenced by the caller.
*/
int (*read_packet)(struct AVFormatContext *, AVPacket *pkt);
/**
* Close the stream. The AVFormatContext and AVStreams are not
* freed by this function
*/
int (*read_close)(struct AVFormatContext *);
/**
* Seek to a given timestamp relative to the frames in
* stream component stream_index.
* @param stream_index Must not be -1.
* @param flags Selects which direction should be preferred if no exact
* match is available.
* @return >= 0 on success (but not necessarily the new offset)
*/
int (*read_seek)(struct AVFormatContext *,
int stream_index, int64_t timestamp, int flags);
/**
* Get the next timestamp in stream[stream_index].time_base units.
* @return the timestamp or AV_NOPTS_VALUE if an error occurred
*/
int64_t (*read_timestamp)(struct AVFormatContext *s, int stream_index,
int64_t *pos, int64_t pos_limit);
/**
* Start/resume playing - only meaningful if using a network-based format
* (RTSP).
*/
int (*read_play)(struct AVFormatContext *);
/**
* Pause playing - only meaningful if using a network-based format
* (RTSP).
*/
int (*read_pause)(struct AVFormatContext *);
/**
* Seek to timestamp ts.
* Seeking will be done so that the point from which all active streams
* can be presented successfully will be closest to ts and within min/max_ts.
* Active streams are all streams that have AVStream.discard < AVDISCARD_ALL.
*/
int (*read_seek2)(struct AVFormatContext *s, int stream_index, int64_t min_ts, int64_t ts, int64_t max_ts, int flags);
/**
* Returns device list with it properties.
* @see avdevice_list_devices() for more details.
*/
int (*get_device_list)(struct AVFormatContext *s, struct AVDeviceInfoList *device_list);
#if LIBAVFORMAT_VERSION_MAJOR < 59
/**
* Initialize device capabilities submodule.
* @see avdevice_capabilities_create() for more details.
*/
int (*create_device_capabilities)(struct AVFormatContext *s, struct AVDeviceCapabilitiesQuery *caps);
/**
* Free device capabilities submodule.
* @see avdevice_capabilities_free() for more details.
*/
int (*free_device_capabilities)(struct AVFormatContext *s, struct AVDeviceCapabilitiesQuery *caps);
#endif
} AVInputFormat;
AVOutputFormat
typedef struct AVOutputFormat
{
// 封装格式名称
const char *name;
// 封装格式的长名称
const char *long_name;
const char *mime_type;
const char *extensions; /**< comma-separated filename extensions */
/* output support */
enum AVCodecID audio_codec; /**< default audio codec */
enum AVCodecID video_codec; /**< default video codec */
enum AVCodecID subtitle_codec; /**< default subtitle codec */
/**
* can use flags: AVFMT_NOFILE, AVFMT_NEEDNUMBER,
* AVFMT_GLOBALHEADER, AVFMT_NOTIMESTAMPS, AVFMT_VARIABLE_FPS,
* AVFMT_NODIMENSIONS, AVFMT_NOSTREAMS, AVFMT_ALLOW_FLUSH,
* AVFMT_TS_NONSTRICT, AVFMT_TS_NEGATIVE
*/
int flags;
/**
* List of supported codec_id-codec_tag pairs, ordered by "better
* choice first". The arrays are all terminated by AV_CODEC_ID_NONE.
*/
const struct AVCodecTag *const *codec_tag;
const AVClass *priv_class; ///< AVClass for the private context
/*****************************************************************
* No fields below this line are part of the public API. They
* may not be used outside of libavformat and can be changed and
* removed at will.
* New public fields should be added right above.
*****************************************************************
*/
/**
* The ff_const59 define is not part of the public API and will
* be removed without further warning.
*/
#if FF_API_AVIOFORMAT
#define ff_const59
#else
#define ff_const59 const
#endif
#if FF_API_NEXT
ff_const59 struct AVOutputFormat *next;
#endif
/**
* size of private data so that it can be allocated in the wrapper
*/
int priv_data_size;
int (*write_header)(struct AVFormatContext *);
/**
* Write a packet. If AVFMT_ALLOW_FLUSH is set in flags,
* pkt can be NULL in order to flush data buffered in the muxer.
* When flushing, return 0 if there still is more data to flush,
* or 1 if everything was flushed and there is no more buffered
* data.
*/
int (*write_packet)(struct AVFormatContext *, AVPacket *pkt);
int (*write_trailer)(struct AVFormatContext *);
/**
* A format-specific function for interleavement.
* If unset, packets will be interleaved by dts.
*/
int (*interleave_packet)(struct AVFormatContext *, AVPacket *out,
AVPacket *in, int flush);
/**
* Test if the given codec can be stored in this container.
*
* @return 1 if the codec is supported, 0 if it is not.
* A negative number if unknown.
* MKTAG('A', 'P', 'I', 'C') if the codec is only supported as AV_DISPOSITION_ATTACHED_PIC
*/
int (*query_codec)(enum AVCodecID id, int std_compliance);
void (*get_output_timestamp)(struct AVFormatContext *s, int stream,
int64_t *dts, int64_t *wall);
/**
* Allows sending messages from application to device.
*/
int (*control_message)(struct AVFormatContext *s, int type,
void *data, size_t data_size);
/**
* Write an uncoded AVFrame.
*
* See av_write_uncoded_frame() for details.
*
* The library will free *frame afterwards, but the muxer can prevent it
* by setting the pointer to NULL.
*/
int (*write_uncoded_frame)(struct AVFormatContext *, int stream_index,
AVFrame **frame, unsigned flags);
/**
* Returns device list with it properties.
* @see avdevice_list_devices() for more details.
*/
int (*get_device_list)(struct AVFormatContext *s, struct AVDeviceInfoList *device_list);
#if LIBAVFORMAT_VERSION_MAJOR < 59
/**
* Initialize device capabilities submodule.
* @see avdevice_capabilities_create() for more details.
*/
int (*create_device_capabilities)(struct AVFormatContext *s, struct AVDeviceCapabilitiesQuery *caps);
/**
* Free device capabilities submodule.
* @see avdevice_capabilities_free() for more details.
*/
int (*free_device_capabilities)(struct AVFormatContext *s, struct AVDeviceCapabilitiesQuery *caps);
#endif
enum AVCodecID data_codec; /**< default data codec */
/**
* Initialize format. May allocate data here, and set any AVFormatContext or
* AVStream parameters that need to be set before packets are sent.
* This method must not write output.
*
* Return 0 if streams were fully configured, 1 if not, negative AVERROR on failure
*
* Any allocations made here must be freed in deinit().
*/
int (*init)(struct AVFormatContext *);
/**
* Deinitialize format. If present, this is called whenever the muxer is being
* destroyed, regardless of whether or not the header has been written.
*
* If a trailer is being written, this is called after write_trailer().
*
* This is called if init() fails as well.
*/
void (*deinit)(struct AVFormatContext *);
/**
* Set up any necessary bitstream filtering and extract any extra data needed
* for the global header.
* Return 0 if more packets from this stream must be checked; 1 if not.
*/
int (*check_bitstream)(struct AVFormatContext *, const AVPacket *pkt);
} AVOutputFormat;
AVCodecContext
typedef struct AVCodecContext { // 一个用来记录和指向avoptions的类。由avformat_all_context()设置。如果(de)muxer存在私有option也会输出 const AVClass *av_class; int log_level_offset; // 解码器的类型(视频,音频...) enum AVMediaType codec_type; /* see AVMEDIA_TYPE_xxx */ // 采用编码器的AVcodec const struct AVCodec *codec; // 编码器的id enum AVCodecID codec_id; /* see AV_CODEC_ID_xxx */ /** * fourcc (LSB first, so "ABCD" -> ('D'<<24) + ('C'<<16) + ('B'<<8) + 'A'). * This is used to work around some encoder bugs. * A demuxer should set this to what is stored in the field used to identify the codec. * If there are multiple such fields in a container then the demuxer should choose the one * which maximizes the information about the used codec. * If the codec tag field in a container is larger than 32 bits then the demuxer should * remap the longer ID to 32 bits with a table or other structure. Alternatively a new * extra_codec_tag + size could be added but for this a clear advantage must be demonstrated * first. * - encoding: Set by user, if not then the default based on codec_id will be used. * - decoding: Set by user, will be converted to uppercase by libavcodec during init. */ unsigned int codec_tag; // 私有数据 void *priv_data; /** * Private context used for internal data. * * Unlike priv_data, this is not codec-specific. It is used in general * libavcodec functions. */ struct AVCodecInternal *internal; /** * Private data of the user, can be used to carry app specific stuff. * - encoding: Set by user. * - decoding: Set by user. */ void *opaque; // 平均比特率 int64_t bit_rate; // 比特流允许偏离参考的比特数 int bit_rate_tolerance; /** * Global quality for codecs which cannot change it per frame. * This should be proportional to MPEG-1/2/4 qscale. * - encoding: Set by user. * - decoding: unused */ int global_quality; /** * - encoding: Set by user. * - decoding: unused */ int compression_level; #define FF_COMPRESSION_DEFAULT -1 /** * AV_CODEC_FLAG_*. * - encoding: Set by user. * - decoding: Set by user. */ int flags; /** * AV_CODEC_FLAG2_* * - encoding: Set by user. * - decoding: Set by user. */ int flags2; /** * some codecs need / can use extradata like Huffman tables. * MJPEG: Huffman tables * rv10: additional flags * MPEG-4: global headers (they can be in the bitstream or here) * The allocated memory should be AV_INPUT_BUFFER_PADDING_SIZE bytes larger * than extradata_size to avoid problems if it is read with the bitstream reader. * The bytewise contents of extradata must not depend on the architecture or CPU endianness. * Must be allocated with the av_malloc() family of functions. * - encoding: Set/allocated/freed by libavcodec. * - decoding: Set/allocated/freed by user. */ uint8_t *extradata; int extradata_size; /** * This is the fundamental unit of time (in seconds) in terms * of which frame timestamps are represented. For fixed-fps content, * timebase should be 1/framerate and timestamp increments should be * identically 1. * This often, but not always is the inverse of the frame rate or field rate * for video. 1/time_base is not the average frame rate if the frame rate is not * constant. * * Like containers, elementary streams also can store timestamps, 1/time_base * is the unit in which these timestamps are specified. * As example of such codec time base see ISO/IEC 14496-2:2001(E) * vop_time_increment_resolution and fixed_vop_rate * (fixed_vop_rate == 0 implies that it is different from the framerate) * * - encoding: MUST be set by user. * - decoding: the use of this field for decoding is deprecated. * Use framerate instead. */ AVRational time_base; /** * For some codecs, the time base is closer to the field rate than the frame rate. * Most notably, H.264 and MPEG-2 specify time_base as half of frame duration * if no telecine is used ... * * Set to time_base ticks per frame. Default 1, e.g., H.264/MPEG-2 set it to 2. */ int ticks_per_frame; /** * Codec delay. * * Encoding: Number of frames delay there will be from the encoder input to * the decoder output. (we assume the decoder matches the spec) * Decoding: Number of frames delay in addition to what a standard decoder * as specified in the spec would produce. * * Video: * Number of frames the decoded output will be delayed relative to the * encoded input. * * Audio: * For encoding, this field is unused (see initial_padding). * * For decoding, this is the number of samples the decoder needs to * output before the decoder's output is valid. When seeking, you should * start decoding this many samples prior to your desired seek point. * * - encoding: Set by libavcodec. * - decoding: Set by libavcodec. */ int delay; // 视屏图像的尺寸 int width, height; //比特流的宽高,当解码帧裁剪之后输出,所以可能与width, height值不一样 int coded_width, coded_height; // 在一组gop中图像中的数量 int gop_size; // 图像的格式 enum AVPixelFormat pix_fmt; /** * If non NULL, 'draw_horiz_band' is called by the libavcodec * decoder to draw a horizontal band. It improves cache usage. Not * all codecs can do that. You must check the codec capabilities * beforehand. * When multithreading is used, it may be called from multiple threads * at the same time; threads might draw different parts of the same AVFrame, * or multiple AVFrames, and there is no guarantee that slices will be drawn * in order. * The function is also used by hardware acceleration APIs. * It is called at least once during frame decoding to pass * the data needed for hardware render. * In that mode instead of pixel data, AVFrame points to * a structure specific to the acceleration API. The application * reads the structure and can change some fields to indicate progress * or mark state. * - encoding: unused * - decoding: Set by user. * @param height the height of the slice * @param y the y position of the slice * @param type 1->top field, 2->bottom field, 3->frame * @param offset offset into the AVFrame.data from which the slice should be read */ void (*draw_horiz_band)(struct AVCodecContext *s, const AVFrame *src, int offset[AV_NUM_DATA_POINTERS], int y, int type, int height); /** * callback to negotiate the pixelFormat * @param fmt is the list of formats which are supported by the codec, * it is terminated by -1 as 0 is a valid format, the formats are ordered by quality. * The first is always the native one. * @note The callback may be called again immediately if initialization for * the selected (hardware-accelerated) pixel format failed. * @warning Behavior is undefined if the callback returns a value not * in the fmt list of formats. * @return the chosen format * - encoding: unused * - decoding: Set by user, if not set the native format will be chosen. */ enum AVPixelFormat (*get_format)(struct AVCodecContext *s, const enum AVPixelFormat *fmt); // 非 B 帧之间的最大 B 帧数 int max_b_frames; // IP 和 B 帧之间的 qscale 因子 如果 > 0,则将使用最后一个 P 帧量化器 float b_quant_factor; #if FF_API_PRIVATE_OPT /** @deprecated use encoder private options instead */ attribute_deprecated int b_frame_strategy; #endif // qscale offset between IP and B-frames float b_quant_offset; // 解码器中帧重新排序缓冲区的大小 int has_b_frames; #if FF_API_PRIVATE_OPT /** @deprecated use encoder private options instead */ attribute_deprecated int mpeg_quant; #endif /** * qscale factor between P- and I-frames * If > 0 then the last P-frame quantizer will be used (q = lastp_q * factor + offset). * If < 0 then normal ratecontrol will be done (q= -normal_q*factor+offset). * - encoding: Set by user. * - decoding: unused */ float i_quant_factor; /** * qscale offset between P and I-frames * - encoding: Set by user. * - decoding: unused */ float i_quant_offset; /** * luminance masking (0-> disabled) * - encoding: Set by user. * - decoding: unused */ float lumi_masking; /** * temporary complexity masking (0-> disabled) * - encoding: Set by user. * - decoding: unused */ float temporal_cplx_masking; /** * spatial complexity masking (0-> disabled) * - encoding: Set by user. * - decoding: unused */ float spatial_cplx_masking; /** * p block masking (0-> disabled) * - encoding: Set by user. * - decoding: unused */ float p_masking; /** * darkness masking (0-> disabled) * - encoding: Set by user. * - decoding: unused */ float dark_masking; /** * slice count * - encoding: Set by libavcodec. * - decoding: Set by user (or 0). */ int slice_count; #if FF_API_PRIVATE_OPT /** @deprecated use encoder private options instead */ attribute_deprecated int prediction_method; #define FF_PRED_LEFT 0 #define FF_PRED_PLANE 1 #define FF_PRED_MEDIAN 2 #endif /** * slice offsets in the frame in bytes * - encoding: Set/allocated by libavcodec. * - decoding: Set/allocated by user (or NULL). */ int *slice_offset; /** * sample aspect ratio (0 if unknown) * That is the width of a pixel divided by the height of the pixel. * Numerator and denominator must be relatively prime and smaller than 256 for some video standards. * - encoding: Set by user. * - decoding: Set by libavcodec. */ AVRational sample_aspect_ratio; /** * motion estimation comparison function * - encoding: Set by user. * - decoding: unused */ int me_cmp; /** * subpixel motion estimation comparison function * - encoding: Set by user. * - decoding: unused */ int me_sub_cmp; /** * macroblock comparison function (not supported yet) * - encoding: Set by user. * - decoding: unused */ int mb_cmp; /** * interlaced DCT comparison function * - encoding: Set by user. * - decoding: unused */ int ildct_cmp; #define FF_CMP_SAD 0 #define FF_CMP_SSE 1 #define FF_CMP_SATD 2 #define FF_CMP_DCT 3 #define FF_CMP_PSNR 4 #define FF_CMP_BIT 5 #define FF_CMP_RD 6 #define FF_CMP_ZERO 7 #define FF_CMP_VSAD 8 #define FF_CMP_VSSE 9 #define FF_CMP_NSSE 10 #define FF_CMP_W53 11 #define FF_CMP_W97 12 #define FF_CMP_DCTMAX 13 #define FF_CMP_DCT264 14 #define FF_CMP_MEDIAN_SAD 15 #define FF_CMP_CHROMA 256 /** * ME diamond size & shape * - encoding: Set by user. * - decoding: unused */ int dia_size; /** * amount of previous MV predictors (2a+1 x 2a+1 square) * - encoding: Set by user. * - decoding: unused */ int last_predictor_count; #if FF_API_PRIVATE_OPT /** @deprecated use encoder private options instead */ attribute_deprecated int pre_me; #endif /** * motion estimation prepass comparison function * - encoding: Set by user. * - decoding: unused */ int me_pre_cmp; /** * ME prepass diamond size & shape * - encoding: Set by user. * - decoding: unused */ int pre_dia_size; /** * subpel ME quality * - encoding: Set by user. * - decoding: unused */ int me_subpel_quality; /** * maximum motion estimation search range in subpel units * If 0 then no limit. * * - encoding: Set by user. * - decoding: unused */ int me_range; /** * slice flags * - encoding: unused * - decoding: Set by user. */ int slice_flags; #define SLICE_FLAG_CODED_ORDER 0x0001 ///< draw_horiz_band() is called in coded order instead of display #define SLICE_FLAG_ALLOW_FIELD 0x0002 ///< allow draw_horiz_band() with field slices (MPEG-2 field pics) #define SLICE_FLAG_ALLOW_PLANE 0x0004 ///< allow draw_horiz_band() with 1 component at a time (SVQ1) /** * macroblock decision mode * - encoding: Set by user. * - decoding: unused */ int mb_decision; #define FF_MB_DECISION_SIMPLE 0 ///< uses mb_cmp #define FF_MB_DECISION_BITS 1 ///< chooses the one which needs the fewest bits #define FF_MB_DECISION_RD 2 ///< rate distortion /** * custom intra quantization matrix * Must be allocated with the av_malloc() family of functions, and will be freed in * avcodec_free_context(). * - encoding: Set/allocated by user, freed by libavcodec. Can be NULL. * - decoding: Set/allocated/freed by libavcodec. */ uint16_t *intra_matrix; /** * custom inter quantization matrix * Must be allocated with the av_malloc() family of functions, and will be freed in * avcodec_free_context(). * - encoding: Set/allocated by user, freed by libavcodec. Can be NULL. * - decoding: Set/allocated/freed by libavcodec. */ uint16_t *inter_matrix; #if FF_API_PRIVATE_OPT /** @deprecated use encoder private options instead */ attribute_deprecated int scenechange_threshold; /** @deprecated use encoder private options instead */ attribute_deprecated int noise_reduction; #endif /** * precision of the intra DC coefficient - 8 * - encoding: Set by user. * - decoding: Set by libavcodec */ int intra_dc_precision; /** * Number of macroblock rows at the top which are skipped. * - encoding: unused * - decoding: Set by user. */ int skip_top; /** * Number of macroblock rows at the bottom which are skipped. * - encoding: unused * - decoding: Set by user. */ int skip_bottom; /** * minimum MB Lagrange multiplier * - encoding: Set by user. * - decoding: unused */ int mb_lmin; /** * maximum MB Lagrange multiplier * - encoding: Set by user. * - decoding: unused */ int mb_lmax; #if FF_API_PRIVATE_OPT /** * @deprecated use encoder private options instead */ attribute_deprecated int me_penalty_compensation; #endif /** * - encoding: Set by user. * - decoding: unused */ int bidir_refine; #if FF_API_PRIVATE_OPT /** @deprecated use encoder private options instead */ attribute_deprecated int brd_scale; #endif /** * minimum GOP size * - encoding: Set by user. * - decoding: unused */ int keyint_min; /** * number of reference frames * - encoding: Set by user. * - decoding: Set by lavc. */ int refs; #if FF_API_PRIVATE_OPT /** @deprecated use encoder private options instead */ attribute_deprecated int chromaoffset; #endif /** * Note: Value depends upon the compare function used for fullpel ME. * - encoding: Set by user. * - decoding: unused */ int mv0_threshold; #if FF_API_PRIVATE_OPT /** @deprecated use encoder private options instead */ attribute_deprecated int b_sensitivity; #endif /** * Chromaticity coordinates of the source primaries. * - encoding: Set by user * - decoding: Set by libavcodec */ enum AVColorPrimaries color_primaries; /** * Color Transfer Characteristic. * - encoding: Set by user * - decoding: Set by libavcodec */ enum AVColorTransferCharacteristic color_trc; /** * YUV colorspace type. * - encoding: Set by user * - decoding: Set by libavcodec */ enum AVColorSpace colorspace; /** * MPEG vs JPEG YUV range. * - encoding: Set by user * - decoding: Set by libavcodec */ enum AVColorRange color_range; /** * This defines the location of chroma samples. * - encoding: Set by user * - decoding: Set by libavcodec */ enum AVChromaLocation chroma_sample_location; /** * Number of slices. * Indicates number of picture subdivisions. Used for parallelized * decoding. * - encoding: Set by user * - decoding: unused */ int slices; /** Field order * - encoding: set by libavcodec * - decoding: Set by user. */ enum AVFieldOrder field_order; /* audio only */ int sample_rate; ///< samples per second int channels; ///< number of audio channels /** * audio sample format * - encoding: Set by user. * - decoding: Set by libavcodec. */ enum AVSampleFormat sample_fmt; ///< sample format /* The following data should not be initialized. */ /** * Number of samples per channel in an audio frame. * * - encoding: set by libavcodec in avcodec_open2(). Each submitted frame * except the last must contain exactly frame_size samples per channel. * May be 0 when the codec has AV_CODEC_CAP_VARIABLE_FRAME_SIZE set, then the * frame size is not restricted. * - decoding: may be set by some decoders to indicate constant frame size */ int frame_size; /** * Frame counter, set by libavcodec. * * - decoding: total number of frames returned from the decoder so far. * - encoding: total number of frames passed to the encoder so far. * * @note the counter is not incremented if encoding/decoding resulted in * an error. */ int frame_number; /** * number of bytes per packet if constant and known or 0 * Used by some WAV based audio codecs. */ int block_align; /** * Audio cutoff bandwidth (0 means "automatic") * - encoding: Set by user. * - decoding: unused */ int cutoff; /** * Audio channel layout. * - encoding: set by user. * - decoding: set by user, may be overwritten by libavcodec. */ uint64_t channel_layout; /** * Request decoder to use this channel layout if it can (0 for default) * - encoding: unused * - decoding: Set by user. */ uint64_t request_channel_layout; /** * Type of service that the audio stream conveys. * - encoding: Set by user. * - decoding: Set by libavcodec. */ enum AVAudioServiceType audio_service_type; /** * desired sample format * - encoding: Not used. * - decoding: Set by user. * Decoder will decode to this format if it can. */ enum AVSampleFormat request_sample_fmt; /** * This callback is called at the beginning of each frame to get data * buffer(s) for it. There may be one contiguous buffer for all the data or * there may be a buffer per each data plane or anything in between. What * this means is, you may set however many entries in buf[] you feel necessary. * Each buffer must be reference-counted using the AVBuffer API (see description * of buf[] below). * * The following fields will be set in the frame before this callback is * called: * - format * - width, height (video only) * - sample_rate, channel_layout, nb_samples (audio only) * Their values may differ from the corresponding values in * AVCodecContext. This callback must use the frame values, not the codec * context values, to calculate the required buffer size. * * This callback must fill the following fields in the frame: * - data[] * - linesize[] * - extended_data: * * if the data is planar audio with more than 8 channels, then this * callback must allocate and fill extended_data to contain all pointers * to all data planes. data[] must hold as many pointers as it can. * extended_data must be allocated with av_malloc() and will be freed in * av_frame_unref(). * * otherwise extended_data must point to data * - buf[] must contain one or more pointers to AVBufferRef structures. Each of * the frame's data and extended_data pointers must be contained in these. That * is, one AVBufferRef for each allocated chunk of memory, not necessarily one * AVBufferRef per data[] entry. See: av_buffer_create(), av_buffer_alloc(), * and av_buffer_ref(). * - extended_buf and nb_extended_buf must be allocated with av_malloc() by * this callback and filled with the extra buffers if there are more * buffers than buf[] can hold. extended_buf will be freed in * av_frame_unref(). * * If AV_CODEC_CAP_DR1 is not set then get_buffer2() must call * avcodec_default_get_buffer2() instead of providing buffers allocated by * some other means. * * Each data plane must be aligned to the maximum required by the target * CPU. * * @see avcodec_default_get_buffer2() * * Video: * * If AV_GET_BUFFER_FLAG_REF is set in flags then the frame may be reused * (read and/or written to if it is writable) later by libavcodec. * * avcodec_align_dimensions2() should be used to find the required width and * height, as they normally need to be rounded up to the next multiple of 16. * * Some decoders do not support linesizes changing between frames. * * If frame multithreading is used, this callback may be called from a * different thread, but not from more than one at once. Does not need to be * reentrant. * * @see avcodec_align_dimensions2() * * Audio: * * Decoders request a buffer of a particular size by setting * AVFrame.nb_samples prior to calling get_buffer2(). The decoder may, * however, utilize only part of the buffer by setting AVFrame.nb_samples * to a smaller value in the output frame. * * As a convenience, av_samples_get_buffer_size() and * av_samples_fill_arrays() in libavutil may be used by custom get_buffer2() * functions to find the required data size and to fill data pointers and * linesize. In AVFrame.linesize, only linesize[0] may be set for audio * since all planes must be the same size. * * @see av_samples_get_buffer_size(), av_samples_fill_arrays() * * - encoding: unused * - decoding: Set by libavcodec, user can override. */ int (*get_buffer2)(struct AVCodecContext *s, AVFrame *frame, int flags); #if FF_API_OLD_ENCDEC /** * If non-zero, the decoded audio and video frames returned from * avcodec_decode_video2() and avcodec_decode_audio4() are reference-counted * and are valid indefinitely. The caller must free them with * av_frame_unref() when they are not needed anymore. * Otherwise, the decoded frames must not be freed by the caller and are * only valid until the next decode call. * * This is always automatically enabled if avcodec_receive_frame() is used. * * - encoding: unused * - decoding: set by the caller before avcodec_open2(). */ attribute_deprecated int refcounted_frames; #endif /* - encoding parameters */ float qcompress; ///< amount of qscale change between easy & hard scenes (0.0-1.0) float qblur; ///< amount of qscale smoothing over time (0.0-1.0) /** * minimum quantizer * - encoding: Set by user. * - decoding: unused */ int qmin; /** * maximum quantizer * - encoding: Set by user. * - decoding: unused */ int qmax; /** * maximum quantizer difference between frames * - encoding: Set by user. * - decoding: unused */ int max_qdiff; /** * decoder bitstream buffer size * - encoding: Set by user. * - decoding: unused */ int rc_buffer_size; /** * ratecontrol override, see RcOverride * - encoding: Allocated/set/freed by user. * - decoding: unused */ int rc_override_count; RcOverride *rc_override; /** * maximum bitrate * - encoding: Set by user. * - decoding: Set by user, may be overwritten by libavcodec. */ int64_t rc_max_rate; /** * minimum bitrate * - encoding: Set by user. * - decoding: unused */ int64_t rc_min_rate; /** * Ratecontrol attempt to use, at maximum, <value> of what can be used without an underflow. * - encoding: Set by user. * - decoding: unused. */ float rc_max_available_vbv_use; /** * Ratecontrol attempt to use, at least, <value> times the amount needed to prevent a vbv overflow. * - encoding: Set by user. * - decoding: unused. */ float rc_min_vbv_overflow_use; /** * Number of bits which should be loaded into the rc buffer before decoding starts. * - encoding: Set by user. * - decoding: unused */ int rc_initial_buffer_occupancy; #if FF_API_CODER_TYPE #define FF_CODER_TYPE_VLC 0 #define FF_CODER_TYPE_AC 1 #define FF_CODER_TYPE_RAW 2 #define FF_CODER_TYPE_RLE 3 /** * @deprecated use encoder private options instead */ attribute_deprecated int coder_type; #endif /* FF_API_CODER_TYPE */ #if FF_API_PRIVATE_OPT /** @deprecated use encoder private options instead */ attribute_deprecated int context_model; #endif #if FF_API_PRIVATE_OPT /** @deprecated use encoder private options instead */ attribute_deprecated int frame_skip_threshold; /** @deprecated use encoder private options instead */ attribute_deprecated int frame_skip_factor; /** @deprecated use encoder private options instead */ attribute_deprecated int frame_skip_exp; /** @deprecated use encoder private options instead */ attribute_deprecated int frame_skip_cmp; #endif /* FF_API_PRIVATE_OPT */ /** * trellis RD quantization * - encoding: Set by user. * - decoding: unused */ int trellis; #if FF_API_PRIVATE_OPT /** @deprecated use encoder private options instead */ attribute_deprecated int min_prediction_order; /** @deprecated use encoder private options instead */ attribute_deprecated int max_prediction_order; /** @deprecated use encoder private options instead */ attribute_deprecated int64_t timecode_frame_start; #endif #if FF_API_RTP_CALLBACK /** * @deprecated unused */ /* The RTP callback: This function is called */ /* every time the encoder has a packet to send. */ /* It depends on the encoder if the data starts */ /* with a Start Code (it should). H.263 does. */ /* mb_nb contains the number of macroblocks */ /* encoded in the RTP payload. */ attribute_deprecated void (*rtp_callback)(struct AVCodecContext *avctx, void *data, int size, int mb_nb); #endif #if FF_API_PRIVATE_OPT /** @deprecated use encoder private options instead */ attribute_deprecated int rtp_payload_size; /* The size of the RTP payload: the coder will */ /* do its best to deliver a chunk with size */ /* below rtp_payload_size, the chunk will start */ /* with a start code on some codecs like H.263. */ /* This doesn't take account of any particular */ /* headers inside the transmitted RTP payload. */ #endif #if FF_API_STAT_BITS /* statistics, used for 2-pass encoding */ attribute_deprecated int mv_bits; attribute_deprecated int header_bits; attribute_deprecated int i_tex_bits; attribute_deprecated int p_tex_bits; attribute_deprecated int i_count; attribute_deprecated int p_count; attribute_deprecated int skip_count; attribute_deprecated int misc_bits; /** @deprecated this field is unused */ attribute_deprecated int frame_bits; #endif /** * pass1 encoding statistics output buffer * - encoding: Set by libavcodec. * - decoding: unused */ char *stats_out; /** * pass2 encoding statistics input buffer * Concatenated stuff from stats_out of pass1 should be placed here. * - encoding: Allocated/set/freed by user. * - decoding: unused */ char *stats_in; /** * Work around bugs in encoders which sometimes cannot be detected automatically. * - encoding: Set by user * - decoding: Set by user */ int workaround_bugs; #define FF_BUG_AUTODETECT 1 ///< autodetection #define FF_BUG_XVID_ILACE 4 #define FF_BUG_UMP4 8 #define FF_BUG_NO_PADDING 16 #define FF_BUG_AMV 32 #define FF_BUG_QPEL_CHROMA 64 #define FF_BUG_STD_QPEL 128 #define FF_BUG_QPEL_CHROMA2 256 #define FF_BUG_DIRECT_BLOCKSIZE 512 #define FF_BUG_EDGE 1024 #define FF_BUG_HPEL_CHROMA 2048 #define FF_BUG_DC_CLIP 4096 #define FF_BUG_MS 8192 ///< Work around various bugs in Microsoft's broken decoders. #define FF_BUG_TRUNCATED 16384 #define FF_BUG_IEDGE 32768 /** * strictly follow the standard (MPEG-4, ...). * - encoding: Set by user. * - decoding: Set by user. * Setting this to STRICT or higher means the encoder and decoder will * generally do stupid things, whereas setting it to unofficial or lower * will mean the encoder might produce output that is not supported by all * spec-compliant decoders. Decoders don't differentiate between normal, * unofficial and experimental (that is, they always try to decode things * when they can) unless they are explicitly asked to behave stupidly * (=strictly conform to the specs) */ int strict_std_compliance; #define FF_COMPLIANCE_VERY_STRICT 2 ///< Strictly conform to an older more strict version of the spec or reference software. #define FF_COMPLIANCE_STRICT 1 ///< Strictly conform to all the things in the spec no matter what consequences. #define FF_COMPLIANCE_NORMAL 0 #define FF_COMPLIANCE_UNOFFICIAL -1 ///< Allow unofficial extensions #define FF_COMPLIANCE_EXPERIMENTAL -2 ///< Allow nonstandardized experimental things. /** * error concealment flags * - encoding: unused * - decoding: Set by user. */ int error_concealment; #define FF_EC_GUESS_MVS 1 #define FF_EC_DEBLOCK 2 #define FF_EC_FAVOR_INTER 256 /** * debug * - encoding: Set by user. * - decoding: Set by user. */ int debug; #define FF_DEBUG_PICT_INFO 1 #define FF_DEBUG_RC 2 #define FF_DEBUG_BITSTREAM 4 #define FF_DEBUG_MB_TYPE 8 #define FF_DEBUG_QP 16 #define FF_DEBUG_DCT_COEFF 0x00000040 #define FF_DEBUG_SKIP 0x00000080 #define FF_DEBUG_STARTCODE 0x00000100 #define FF_DEBUG_ER 0x00000400 #define FF_DEBUG_MMCO 0x00000800 #define FF_DEBUG_BUGS 0x00001000 #define FF_DEBUG_BUFFERS 0x00008000 #define FF_DEBUG_THREADS 0x00010000 #define FF_DEBUG_GREEN_MD 0x00800000 #define FF_DEBUG_NOMC 0x01000000 /** * Error recognition; may misdetect some more or less valid parts as errors. * - encoding: Set by user. * - decoding: Set by user. */ int err_recognition; /** * Verify checksums embedded in the bitstream (could be of either encoded or * decoded data, depending on the codec) and print an error message on mismatch. * If AV_EF_EXPLODE is also set, a mismatching checksum will result in the * decoder returning an error. */ #define AV_EF_CRCCHECK (1 << 0) #define AV_EF_BITSTREAM (1 << 1) ///< detect bitstream specification deviations #define AV_EF_BUFFER (1 << 2) ///< detect improper bitstream length #define AV_EF_EXPLODE (1 << 3) ///< abort decoding on minor error detection #define AV_EF_IGNORE_ERR (1 << 15) ///< ignore errors and continue #define AV_EF_CAREFUL (1 << 16) ///< consider things that violate the spec, are fast to calculate and have not been seen in the wild as errors #define AV_EF_COMPLIANT (1 << 17) ///< consider all spec non compliances as errors #define AV_EF_AGGRESSIVE (1 << 18) ///< consider things that a sane encoder should not do as an error /** * opaque 64-bit number (generally a PTS) that will be reordered and * output in AVFrame.reordered_opaque * - encoding: Set by libavcodec to the reordered_opaque of the input * frame corresponding to the last returned packet. Only * supported by encoders with the * AV_CODEC_CAP_ENCODER_REORDERED_OPAQUE capability. * - decoding: Set by user. */ int64_t reordered_opaque; /** * Hardware accelerator in use * - encoding: unused. * - decoding: Set by libavcodec */ // 硬件加速的器正在使用的 const struct AVHWAccel *hwaccel; /** * Hardware accelerator context. * For some hardware accelerators, a global context needs to be * provided by the user. In that case, this holds display-dependent * data FFmpeg cannot instantiate itself. Please refer to the * FFmpeg HW accelerator documentation to know how to fill this * is. e.g. for VA API, this is a struct vaapi_context. * - encoding: unused * - decoding: Set by user */ // 加速器上下文 void *hwaccel_context; /** * error * - encoding: Set by libavcodec if flags & AV_CODEC_FLAG_PSNR. * - decoding: unused */ uint64_t error[AV_NUM_DATA_POINTERS]; /** * DCT algorithm, see FF_DCT_* below * - encoding: Set by user. * - decoding: unused */ int dct_algo; #define FF_DCT_AUTO 0 #define FF_DCT_FASTINT 1 #define FF_DCT_INT 2 #define FF_DCT_MMX 3 #define FF_DCT_ALTIVEC 5 #define FF_DCT_FAAN 6 /** * IDCT algorithm, see FF_IDCT_* below. * - encoding: Set by user. * - decoding: Set by user. */ int idct_algo; #define FF_IDCT_AUTO 0 #define FF_IDCT_INT 1 #define FF_IDCT_SIMPLE 2 #define FF_IDCT_SIMPLEMMX 3 #define FF_IDCT_ARM 7 #define FF_IDCT_ALTIVEC 8 #define FF_IDCT_SIMPLEARM 10 #define FF_IDCT_XVID
AVStream
其中AVStream是存储每一个视频/音频流信息的结构体
typedef struct AVStream
{
// 流的索引在
int index; /**< stream index in AVFormatContext */
/**
* Format-specific stream ID.
* decoding: set by libavformat
* encoding: set by the user, replaced by libavformat if left unset
*/
// 流的id
int id;
#if FF_API_LAVF_AVCTX
/**
* @deprecated use the codecpar struct instead
*/
attribute_deprecated
// 封装和解码器耦合在一起
AVCodecContext *codec;
#endif
// 私有数据
void *priv_data;
// 时间基
AVRational time_base;
// 第一帧的显示时间
int64_t start_time;
// 该视频或者音频的数据长度
int64_t duration;
// 数据帧的多长
int64_t nb_frames; ///< number of frames in this stream if known or 0
// 去除的数据帧的位置
int disposition; /**< AV_DISPOSITION_* bit field */
// 哪一个数据帧被抛弃
enum AVDiscard discard; ///< Selects which packets can be discarded at will and do not need to be demuxed.
/**
* sample aspect ratio (0 if unknown)
* - encoding: Set by user.
* - decoding: Set by libavformat.
*/
// 样本比特率
AVRational sample_aspect_ratio;
// 元数据
AVDictionary *metadata;
/**
* Average framerate
*
* - demuxing: May be set by libavformat when creating the stream or in
* avformat_find_stream_info().
* - muxing: May be set by the caller before avformat_write_header().
*/
AVRational avg_frame_rate;
/**
* For streams with AV_DISPOSITION_ATTACHED_PIC disposition, this packet
* will contain the attached picture.
*
* decoding: set by libavformat, must not be modified by the caller.
* encoding: unused
*/
AVPacket attached_pic;
/**
* An array of side data that applies to the whole stream (i.e. the
* container does not allow it to change between packets).
*
* There may be no overlap between the side data in this array and side data
* in the packets. I.e. a given side data is either exported by the muxer
* (demuxing) / set by the caller (muxing) in this array, then it never
* appears in the packets, or the side data is exported / sent through
* the packets (always in the first packet where the value becomes known or
* changes), then it does not appear in this array.
*
* - demuxing: Set by libavformat when the stream is created.
* - muxing: May be set by the caller before avformat_write_header().
*
* Freed by libavformat in avformat_free_context().
*
* @see av_format_inject_global_side_data()
*/
AVPacketSideData *side_data;
/**
* The number of elements in the AVStream.side_data array.
*/
int nb_side_data;
/**
* Flags indicating events happening on the stream, a combination of
* AVSTREAM_EVENT_FLAG_*.
*
* - demuxing: may be set by the demuxer in avformat_open_input(),
* avformat_find_stream_info() and av_read_frame(). Flags must be cleared
* by the user once the event has been handled.
* - muxing: may be set by the user after avformat_write_header(). to
* indicate a user-triggered event. The muxer will clear the flags for
* events it has handled in av_[interleaved]_write_frame().
*/
int event_flags;
/**
* - demuxing: the demuxer read new metadata from the file and updated
* AVStream.metadata accordingly
* - muxing: the user updated AVStream.metadata and wishes the muxer to write
* it into the file
*/
#define AVSTREAM_EVENT_FLAG_METADATA_UPDATED 0x0001
/**
* - demuxing: new packets for this stream were read from the file. This
* event is informational only and does not guarantee that new packets
* for this stream will necessarily be returned from av_read_frame().
*/
#define AVSTREAM_EVENT_FLAG_NEW_PACKETS (1 << 1)
/**
* Real base framerate of the stream.
* This is the lowest framerate with which all timestamps can be
* represented accurately (it is the least common multiple of all
* framerates in the stream). Note, this value is just a guess!
* For example, if the time base is 1/90000 and all frames have either
* approximately 3600 or 1800 timer ticks, then r_frame_rate will be 50/1.
*/
AVRational r_frame_rate;
#if FF_API_LAVF_FFSERVER
/**
* String containing pairs of key and values describing recommended encoder configuration.
* Pairs are separated by ','.
* Keys are separated from values by '='.
*
* @deprecated unused
*/
attribute_deprecated char *recommended_encoder_configuration;
#endif
/**
* Codec parameters associated with this stream. Allocated and freed by
* libavformat in avformat_new_stream() and avformat_free_context()
* respectively.
*
* - demuxing: filled by libavformat on stream creation or in
* avformat_find_stream_info()
* - muxing: filled by the caller before avformat_write_header()
*/
AVCodecParameters *codecpar;
/*****************************************************************
* All fields below this line are not part of the public API. They
* may not be used outside of libavformat and can be changed and
* removed at will.
* Internal note: be aware that physically removing these fields
* will break ABI. Replace removed fields with dummy fields, and
* add new fields to AVStreamInternal.
*****************************************************************
*/
#if LIBAVFORMAT_VERSION_MAJOR < 59
// kept for ABI compatibility only, do not access in any way
void *unused;
#endif
int pts_wrap_bits; /**< number of bits in pts (used for wrapping control) */
// Timestamp generation support:
/**
* Timestamp corresponding to the last dts sync point.
*
* Initialized when AVCodecParserContext.dts_sync_point >= 0 and
* a DTS is received from the underlying container. Otherwise set to
* AV_NOPTS_VALUE by default.
*/
int64_t first_dts;
int64_t cur_dts;
int64_t last_IP_pts;
int last_IP_duration;
/**
* Number of packets to buffer for codec probing
*/
int probe_packets;
/**
* Number of frames that have been demuxed during avformat_find_stream_info()
*/
int codec_info_nb_frames;
/* av_read_frame() support */
enum AVStreamParseType need_parsing;
struct AVCodecParserContext *parser;
#if LIBAVFORMAT_VERSION_MAJOR < 59
// kept for ABI compatibility only, do not access in any way
void *unused7;
AVProbeData unused6;
int64_t unused5[16 + 1];
#endif
AVIndexEntry *index_entries; /**< Only used if the format does not
support seeking natively. */
int nb_index_entries;
unsigned int index_entries_allocated_size;
/**
* Stream Identifier
* This is the MPEG-TS stream identifier +1
* 0 means unknown
*/
int stream_identifier;
#if LIBAVFORMAT_VERSION_MAJOR < 59
// kept for ABI compatibility only, do not access in any way
int unused8;
int unused9;
int unused10;
#endif
/**
* An opaque field for libavformat internal usage.
* Must not be accessed in any way by callers.
*/
AVStreamInternal *internal;
} AVStream;