注:写了一系列的结构体的分析的文章,在这里列一个列表:
FFMPEG结构体分析:AVFormatContext
FFMPEG结构体分析:AVFrame
FFMPEG结构体分析:AVCodecContext
FFMPEG结构体分析:AVIOContext
FFMPEG结构体分析:AVCodec
FFMPEG结构体分析:AVStream
FFMPEG结构体分析:AVPacket
首先看一下结构体的定义(位于avformat.h):
FFMPEG有几个最重要的结构体,包含了解协议,解封装,解码操作,此前已经进行过分析:
FFMPEG中最关键的结构体之间的关系
在此不再详述,其中AVFormatContext是包含码流参数较多的结构体。本文将会详细分析一下该结构体里每个变量的含义和作用。
/* 雷霄骅 * 中国传媒大学/数字电视技术 * [email protected] * */ /** * 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ms,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" ; }