ffmpeg 结构体分析
Posted 狗蛋儿l
tags:
篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了ffmpeg 结构体分析相关的知识，希望对你有一定的参考价值。
AVFrame
AVFrame结构体一般用于存储原始数据（即非压缩数据，例如对视频来说是YUV，RGB，对音频来说是PCM），此外还包含了一些相关的信息。比如说，解码的时候存储了宏块类型表，QP表，运动矢量表等数据。编码的时候也存储了相关的数据。因此在使用FFMPEG进行码流分析的时候，AVFrame是一个很重要的结构体。
/*
*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()
*/
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()
*/
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()
*/
uint8_t **extended_data;
/**宽高
* width and height of the video frame
* - encoding: unused
* - decoding: Read by user.
*/
int width, height;
/**
* number of audio samples (per channel) described by this frame
* - encoding: Set by user
* - decoding: Set by libavcodec
*/
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.
*/
int format;
/**是否是关键帧
* 1 -> keyframe, 0-> not
* - encoding: Set by libavcodec.
* - decoding: Set by libavcodec.
*/
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.
*/
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.
*/
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.
*/
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;
下面看几个主要变量的作用（在这里考虑解码的情况）：
uint8_t *data[AV_NUM_DATA_POINTERS]：解码后原始数据（对视频来说是YUV，RGB，对音频来说是PCM）
int linesize[AV_NUM_DATA_POINTERS]：data中“一行”数据的大小。注意：未必等于图像的宽，一般大于图像的宽。
int width, height：视频帧宽和高（1920x1080,1280x720...）
int nb_samples：音频的一个AVFrame中可能包含多个音频帧，在此标记包含了几个
int format：解码后原始数据类型（YUV420，YUV422，RGB24...）
int key_frame：是否是关键帧
enum AVPictureType pict_type：帧类型（I,B,P...）
AVRational sample_aspect_ratio：宽高比（16:9，4:3...）
int64_t pts：显示时间戳
int coded_picture_number：编码帧序号
int display_picture_number：显示帧序号
int8_t *qscale_table：QP表
uint8_t *mbskip_table：跳过宏块表
int16_t (*motion_val[2])[2]：运动矢量表
uint32_t *mb_type：宏块类型表
short *dct_coeff：DCT系数，这个没有提取过
int8_t *ref_index[2]：运动估计参考帧列表（貌似H.264这种比较新的标准才会涉及到多参考帧）
int interlaced_frame：是否是隔行扫描
uint8_t motion_subsample_log2：一个宏块中的运动矢量采样个数，取log的
1.data[]
对于packed格式的数据（例如RGB24），会存到data[0]里面。
对于planar格式的数据（例如YUV420P），则会分开成data[0]，data[1]，data[2]…（YUV420P中data[0]存Y，data[1]存U，data[2]存V）
具体参见：FFMPEG 实现 YUV，RGB各种图像原始数据之间的转换（swscale）
2.pict_type
包含以下类型：
enum AVPictureType {
AV_PICTURE_TYPE_NONE = 0, ///< Undefined
AV_PICTURE_TYPE_I, ///< Intra
AV_PICTURE_TYPE_P, ///< Predicted
AV_PICTURE_TYPE_B, ///< Bi-dir predicted
AV_PICTURE_TYPE_S, ///< S(GMC)-VOP MPEG4
AV_PICTURE_TYPE_SI, ///< Switching Intra
AV_PICTURE_TYPE_SP, ///< Switching Predicted
AV_PICTURE_TYPE_BI, ///< BI type
};
3.sample_aspect_ratio
宽高比是一个分数，FFMPEG中用AVRational表达分数：
/**
* rational number numerator/denominator
*/
typedef struct AVRational{
int num; ///< numerator
int den; ///< denominator
} AVRational;
4.qscale_table
QP表指向一块内存，里面存储的是每个宏块的QP值。宏块的标号是从左往右，一行一行的来的。每个宏块对应1个QP。
qscale_table[0]就是第1行第1列宏块的QP值；qscale_table[1]就是第1行第2列宏块的QP值；qscale_table[2]就是第1行第3列宏块的QP值。以此类推…
宏块的个数用下式计算：
注：宏块大小是16x16的。
每行宏块数：
int mb_stride = pCodecCtx->width/16+1
宏块的总数：
int mb_sum = ((pCodecCtx->height+15)>>4)*(pCodecCtx->width/16+1)
5.motion_subsample_log2
1个运动矢量所能代表的画面大小（用宽或者高表示，单位是像素），注意，这里取了log2。
代码注释中给出以下数据：
4->16x16, 3->8x8, 2-> 4x4, 1-> 2x2
即1个运动矢量代表16x16的画面的时候，该值取4；1个运动矢量代表8x8的画面的时候，该值取3…以此类推
6.motion_val
运动矢量表存储了一帧视频中的所有运动矢量。
该值的存储方式比较特别：
int16_t (*motion_val[2])[2];
为了弄清楚该值究竟是怎么存的，花了我好一阵子功夫…
注释中给了一段代码：
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];
大概知道了该数据的结构：
1.首先分为两个列表L0和L1
2.每个列表（L0或L1）存储了一系列的MV（每个MV对应一个画面，大小由motion_subsample_log2决定）
3.每个MV分为横坐标和纵坐标（x,y）
注意，在FFMPEG中MV和MB在存储的结构上是没有什么关联的，第1个MV是屏幕上左上角画面的MV（画面的大小取决于motion_subsample_log2），第2个MV是屏幕上第1行第2列的画面的MV，以此类推。因此在一个宏块（16x16）的运动矢量很有可能如下图所示（line代表一行运动矢量的个数）：
//例如8x8划分的运动矢量与宏块的关系：
//-------------------------
//| | |
//|mv[x] |mv[x+1] |
//-------------------------
//| | |
//|mv[x+line]|mv[x+line+1]|
//-------------------------
7.mb_type
宏块类型表存储了一帧视频中的所有宏块的类型。其存储方式和QP表差不多。只不过其是uint32类型的，而QP表是uint8类型的。每个宏块对应一个宏块类型变量。
宏块类型如下定义所示：
//The following defines may change, don't expect compatibility if you use them.
#define MB_TYPE_INTRA4x4 0x0001
#define MB_TYPE_INTRA16x16 0x0002 //FIXME H.264-specific
#define MB_TYPE_INTRA_PCM 0x0004 //FIXME H.264-specific
#define MB_TYPE_16x16 0x0008
#define MB_TYPE_16x8 0x0010
#define MB_TYPE_8x16 0x0020
#define MB_TYPE_8x8 0x0040
#define MB_TYPE_INTERLACED 0x0080
#define MB_TYPE_DIRECT2 0x0100 //FIXME
#define MB_TYPE_ACPRED 0x0200
#define MB_TYPE_GMC 0x0400
#define MB_TYPE_SKIP 0x0800
#define MB_TYPE_P0L0 0x1000
#define MB_TYPE_P1L0 0x2000
#define MB_TYPE_P0L1 0x4000
#define MB_TYPE_P1L1 0x8000
#define MB_TYPE_L0 (MB_TYPE_P0L0 | MB_TYPE_P1L0)
#define MB_TYPE_L1 (MB_TYPE_P0L1 | MB_TYPE_P1L1)
#define MB_TYPE_L0L1 (MB_TYPE_L0 | MB_TYPE_L1)
#define MB_TYPE_QUANT 0x00010000
#define MB_TYPE_CBP 0x00020000
//Note bits 24-31 are reserved for codec specific use (h264 ref0, mpeg1 0mv, ...)
一个宏块如果包含上述定义中的一种或两种类型，则其对应的宏块变量的对应位会被置1。
注：一个宏块可以包含好几种类型，但是有些类型是不能重复包含的，比如说一个宏块不可能既是16x16又是8x8。
AVFormatContext
/* 雷霄骅
* 中国传媒大学/数字电视技术
* leixiaohua1020@126.com
*
*/
/**
* Format I/O context.
* New fields can be added to the end with minor version bumps.
* Removal, reordering and changes to existing fields require a major
* version bump.
* sizeof(AVFormatContext) must not be used outside libav*, use
* avformat_alloc_context() to create an AVFormatContext.
*/
typedef struct AVFormatContext {
/**
* A class for logging and AVOptions. Set by avformat_alloc_context().
* Exports (de)muxer private options if they exist.
*/
const AVClass *av_class;
/**
* Can only be iformat or oformat, not both at the same time.
*
* decoding: set by avformat_open_input().
* encoding: set by the user.
*/
struct AVInputFormat *iformat;
struct AVOutputFormat *oformat;
/**
* Format private data. This is an AVOptions-enabled struct
* if and only if iformat/oformat.priv_class is not NULL.
*/
void *priv_data;
/*
* I/O context.
*
* decoding: either set by the user before avformat_open_input() (then
* the user must close it manually) or set by avformat_open_input().
* encoding: set by the user.
*
* Do NOT set this field if AVFMT_NOFILE flag is set in
* iformat/oformat.flags. In such a case, the (de)muxer will handle
* I/O in some other way and this field will be NULL.
*/
AVIOContext *pb;
/* stream info */
int ctx_flags; /**< Format-specific flags, see AVFMTCTX_xx */
/**
* A list of all streams in the file. New streams are created with
* avformat_new_stream().
*
* decoding: streams are created by libavformat in avformat_open_input().
* If AVFMTCTX_NOHEADER is set in ctx_flags, then new streams may also
* appear in av_read_frame().
* encoding: streams are created by the user before avformat_write_header().
*/
unsigned int nb_streams;
AVStream **streams;
char filename[1024]; /**< input or output filename */
/**
* Decoding: position of the first frame of the component, in
* AV_TIME_BASE fractional seconds. NEVER set this value directly:
* It is deduced from the AVStream values.
*/
int64_t start_time;
/**
* Decoding: duration of the stream, in AV_TIME_BASE fractional
* seconds. Only set this value if you know none of the individual stream
* durations and also do not set any of them. This is deduced from the
* AVStream values if not set.
*/
int64_t duration;
/**
* Decoding: total stream bitrate in bit/s, 0 if not
* available. Never set it directly if the file_size and the
* duration are known as FFmpeg can compute it automatically.
*/
int bit_rate;
unsigned int packet_size;
int max_delay;
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_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_MP4A_LATM 0x8000 ///< Enable RTP MP4A-LATM payload
#define AVFMT_FLAG_SORT_DTS 0x10000 ///< try to interleave outputted packets by dts (using this flag can slow demuxing down)
#define AVFMT_FLAG_PRIV_OPT 0x20000 ///< Enable use of private options by delaying codec open (this could be made default once all code is converted)
#define AVFMT_FLAG_KEEP_SIDE_DATA 0x40000 ///< Dont merge side data but keep it separate.
/**
* decoding: size of data to probe; encoding: unused.
*/
unsigned int probesize;
/**
* decoding: maximum time (in AV_TIME_BASE units) during which the input should
* be analyzed in avformat_find_stream_info().
*/
int max_analyze_duration;
const uint8_t *key;
int keylen;
unsigned int nb_programs;
AVProgram **programs;
/**
* Forced video codec_id.
* Demuxing: Set by user.
*/
enum CodecID video_codec_id;
/**
* Forced audio codec_id.
* Demuxing: Set by user.
*/
enum CodecID audio_codec_id;
/**
* Forced subtitle codec_id.
* Demuxing: Set by user.
*/
enum CodecID subtitle_codec_id;
/**
* Maximum amount of memory in bytes to use for the index of each stream.
* If the index exceeds this size, entries will be discarded as
* needed to maintain a smaller size. This can lead to slower or less
* accurate seeking (depends on demuxer).
* Demuxers for which a full in-memory index is mandatory will ignore
* this.
* muxing : unused
* demuxing: set by user
*/
unsigned int max_index_size;
/**
* Maximum amount of memory in bytes to use for buffering frames
* obtained from realtime capture devices.
*/
unsigned int max_picture_buffer;
unsigned int nb_chapters;
AVChapter **chapters;
AVDictionary *metadata;
/**
* Start time of the stream in real world time, in microseconds
* since the unix epoch (00:00 1st January 1970). That is, pts=0
* in the stream was captured at this real world time.
* - encoding: Set by user.
* - decoding: Unused.
*/
int64_t start_time_realtime;
/**
* decoding: number of frames used to probe fps
*/
int fps_probe_size;
/**
* Error recognition; higher values will detect more errors but may
* misdetect some more or less valid parts as errors.
* - encoding: unused
* - decoding: Set by user.
*/
int error_recognition;
/**
* Custom interrupt callbacks for the I/O layer.
*
* decoding: set by the user before avformat_open_input().
* encoding: 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
/**
* Transport stream id.
* This will be moved into demuxer private options. Thus no API/ABI compatibility
*/
int ts_id;
/**
* Audio preload in microseconds.
* Note, not all formats support this and unpredictable things may happen if it is used when not supported.
* - encoding: Set by user via AVOptions (NO direct access)
* - decoding: unused
*/
int audio_preload;
/**
* Max chunk time in microseconds.
* Note, not all formats support this and unpredictable things may happen if it is used when not supported.
* - encoding: Set by user via AVOptions (NO direct access)
* - decoding: unused
*/
int max_chunk_duration;
/**
* Max chunk size in bytes
* Note, not all formats support this and unpredictable things may happen if it is used when not supported.
* - encoding: Set by user via AVOptions (NO direct access)
* - decoding: unused
*/
int max_chunk_size;
/*****************************************************************
* 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.
* New public fields should be added right above.
*****************************************************************
*/
/**
* This buffer is only needed when packets were already buffered but
* not decoded, for example to get the codec parameters in MPEG
* streams.
*/
struct AVPacketList *packet_buffer;
struct AVPacketList *packet_buffer_end;
/* av_seek_frame() support */
int64_t data_offset; /**< offset of the first packet */
/**
* Raw packets from the demuxer, prior to parsing and decoding.
* This buffer is used for buffering packets until the codec can
* be identified, as parsing cannot be done without knowing the
* codec.
*/
struct AVPacketList *raw_packet_buffer;
struct AVPacketList *raw_packet_buffer_end;
/**
* Packets split by the parser get queued here.
*/
struct AVPacketList *parse_queue;
struct AVPacketList *parse_queue_end;
/**
* Remaining size available for raw_packet_buffer, in bytes.
*/
#define RAW_PACKET_BUFFER_SIZE 2500000
int raw_packet_buffer_remaining_size;
} AVFormatContext;
在使用FFMPEG进行开发的时候，AVFormatContext是一个贯穿始终的数据结构，很多函数都要用到它作为参数。它是FFMPEG解封装（flv，mp4，rmvb，avi）功能的结构体。下面看几个主要变量的作用（在这里考虑解码的情况）：
struct AVInputFormat *iformat：输入数据的封装格式
AVIOContext *pb：输入数据的缓存
unsigned int nb_streams：视音频流的个数
AVStream **streams：视音频流
char filename[1024]：文件名
int64_t duration：时长（单位：微秒us，转换为秒需要除以1000000）
int bit_rate：比特率（单位bps，转换为kbps需要除以1000）
AVDictionary *metadata：元数据
视频的时长可以转换成HH:MM:SS的形式，示例代码如下：
AVFormatContext *pFormatCtx;
CString timelong;
...
//duration是以微秒为单位
//转换成hh:mm:ss形式
int tns, thh, tmm, tss;
tns = (pFormatCtx->duration)/1000000;
thh = tns / 3600;
tmm = (tns % 3600) / 60;
tss = (tns % 60);
timelong.Format("%02d:%02d:%02d",thh,tmm,tss);
视频的原数据（metadata）信息可以通过AVDictionary获取。元数据存储在AVDictionaryEntry结构体中，如下所示
typedef struct AVDictionaryEntry {
char *key;
char *value;
} AVDictionaryEntry;
每一条元数据分为key和value两个属性。
在ffmpeg中通过av_dict_get()函数获得视频的原数据。
下列代码显示了获取元数据并存入meta字符串变量的过程，注意每一条key和value之间有一个"\\t:"，value之后有一个"\\r\\n"
//MetaData------------------------------------------------------------
//从AVDictionary获得
//需要用到AVDictionaryEntry对象
//CString author,copyright,description;
CString meta=NULL,key,value;
AVDictionaryEntry *m = NULL;
//不用一个一个找出来
/* m=av_dict_get(pFormatCtx->metadata,"author",m,0);
author.Format("作者：%s",m->value);
m=av_dict_get(pFormatCtx->metadata,"copyright",m,0);
copyright.Format("版权：%s",m->value);
m=av_dict_get(pFormatCtx->metadata,"description",m,0);
description.Format("描述：%s",m->value);
*/
//使用循环读出
//(需要读取的数据，字段名称，前一条字段（循环时使用），参数)
while(m=av_dict_get(pFormatCtx->metadata,"",m,AV_DICT_IGNORE_SUFFIX)){
key.Format(m->key);
value.Format(m->value);
meta+=key+"\\t:"+value+"\\r\\n" ;
}
AVCodecContext
/*
*雷霄骅
*leixiaohua1020@126.com
*中国传媒大学/数字电视技术
*/
/**
* main external API structure.
* New fields can be added to the end with minor version bumps.
* Removal, reordering and changes to existing fields require a major
* version bump.
* Please use AVOptions (av_opt* / av_set/get*()) to access these fields from user
* applications.
* sizeof(AVCodecContext) must not be used outside libav*.
*/
typedef struct AVCodecContext {
/**
* information on struct for av_log
* - set by avcodec_alloc_context3
*/
const AVClass *av_class;
int log_level_offset;
enum AVMediaType codec_type; /* see AVMEDIA_TYPE_xxx */
const struct AVCodec *codec;
char codec_name[32];
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;
/**
* fourcc from the AVI stream header (LSB first, so "ABCD" -> ('D'<<24) + ('C'<<16) + ('B'<<8) + 'A').
* This is used to work around some encoder bugs.
* - encoding: unused
* - decoding: Set by user, will be converted to uppercase by libavcodec during init.
*/
unsigned int stream_codec_tag;
#if FF_API_SUB_ID
/**
* @deprecated this field is unused
*/
attribute_deprecated int sub_id;
#endif
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;
/**
* the average bitrate
* - encoding: Set by user; unused for constant quantizer encoding.
* - decoding: Set by libavcodec. 0 or some bitrate if this info is available in the stream.
*/
int bit_rate;
/**
* number of bits the bitstream is allowed to diverge from the reference.
* the reference can be CBR (for CBR pass1) or VBR (for pass2)
* - encoding: Set by user; unused for constant quantizer encoding.
* - decoding: unused
*/
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
/**
* CODEC_FLAG_*.
* - encoding: Set by user.
* - decoding: Set by user.
*/
int flags;
/**
* 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
* mpeg4: global headers (they can be in the bitstream or here)
* The allocated memory should be FF_INPUT_BUFFER_PADDING_SIZE bytes larger
* than extradata_size to avoid prolems if it is read with the bitstream reader.
* The bytewise contents of extradata must not depend on the architecture or CPU endianness.
* - 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.
* - encoding: MUST be set by user.
* - decoding: Set by libavcodec.
*/
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;
/**
* 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 is the number of "priming" samples added to the
* beginning of the stream. The decoded output will be delayed by this
* many samples relative to the input to the encoder. Note that this
* field is purely informational and does not directly affect the pts
* output by the encoder, which should always be based on the actual
* presentation time, including any delay.
* 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;
/* video only */
/**
* picture width / height.
* - encoding: MUST be set by user.
* - decoding: Set by libavcodec.
* Note: For compatibility it is possible to set this instead of
* coded_width/height before decoding.
*/
int width, height;
/**
* Bitstream width / height, may be different from width/height if lowres enabled.
* - encoding: unused
* - decoding: Set by user before init if known. Codec should override / dynamically change if needed.
*/
int coded_width, coded_height;
#define FF_ASPECT_EXTENDED 15
/**
* the number of pictures in a group of pictures, or 0 for intra_only
* - encoding: Set by user.
* - decoding: unused
*/
int gop_size;
/**
* Pixel format, see AV_PIX_FMT_xxx.
* May be set by the demuxer if known from headers.
* May be overridden by the decoder if it knows better.
* - encoding: Set by user.
* - decoding: Set by user if known, overridden by libavcodec if known
*/
enum AVPixelFormat pix_fmt;
/**
* Motion estimation algorithm used for video coding.
* 1 (zero), 2 (full), 3 (log), 4 (phods), 5 (epzs), 6 (x1), 7 (hex),
* 8 (umh), 9 (iter), 10 (tesa) [7, 8, 10 are x264 specific, 9 is snow specific]
* - encoding: MUST be set by user.
* - decoding: unused
*/
int me_method;
/**
* 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.
* @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);
/**
* maximum number of B-frames between non-B-frames
* Note: The output will be delayed by max_b_frames+1 relative to the input.
* - encoding: Set by user.
* - decoding: unused
*/
int max_b_frames;
/**
* qscale factor between IP and B-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 b_quant_factor;
/** obsolete FIXME remove */
int rc_strategy;
#define FF_RC_STRATEGY_XVID 1
int b_frame_strategy;
#if FF_API_MPV_GLOBAL_OPTS
/**
* luma single coefficient elimination threshold
* - encoding: Set by user.
* - decoding: unused
*/
attribute_deprecated int luma_elim_threshold;
/**
* chroma single coeff elimination threshold
* - encoding: Set by user.
* - decoding: unused
*/
attribute_deprecated int chroma_elim_threshold;
#endif
/**
* qscale offset between IP and B-frames
* - encoding: Set by user.
* - decoding: unused
*/
float b_quant_offset;
/**
* Size of the frame reordering buffer in the decoder.
* For MPEG-2 it is 1 IPB or 0 low delay IP.
* - encoding: Set by libavcodec.
* - decoding: Set by libavcodec.
*/
int has_b_frames;
/**
* 0-> h263 quant 1-> mpeg quant
* - encoding: Set by user.
* - decoding: unused
*/
int mpeg_quant;
/**
* 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
*/以上是关于ffmpeg 结构体分析的主要内容，如果未能解决你的问题，请参考以下文章
FFmpeg源代码简单分析：常见结构体的初始化和销毁（AVFormatContext，AVFrame等）
FFmpeg源码简单分析：结构体成员管理系统-AVOption