FFmpeg 提取多音轨视频文件

版权声明:本文为博主原创文章,遵循 CC 4.0 by-sa 版权协议,转载请附上原文出处链接和本声明。
本文链接:https://blog.csdn.net/Zhang__Yue/article/details/53133043

在FFMpeg中,轨道信息保存在AVFormatContext中:

在AVFormatContext结构体中,有一个变量:nb_streams.

nb_streams描述如下:

/**
     * Number of elements in AVFormatContext.streams.
     *
     * Set by avformat_new_stream(), must not be modified by any other code.
     */
    unsigned int nb_streams;

nb_streams由编码用户所决定。nb_streams的数量代表着流的种类个数

例如:

对于一个音频文件,一般来说nb_streams的值为0。代表着只有0这一个轨道

对于视频文件来说,视频轨道一般为一个,音轨就不好说了。可能有 中英,国粤,国粤英,而且 字幕一般会占一个轨道。对于一些要求严格的movie,LTC也会占一个轨道。

一般情况下。视频轨道为0,音轨依次增加(1.2.3)。但字幕(4)和LTC(5)一般在最后面,但也不绝对。

AVFormatContext结构体的代码如下:

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;

    /**
     * The input container format.
     *
     * Demuxing only, set by avformat_open_input().
     */
    struct AVInputFormat *iformat;

    /**
     * The output container format.
     *
     * Muxing only, must be set by the caller before avformat_write_header().
     */
    struct AVOutputFormat *oformat;

    /**
     * Format private data. This is an AVOptions-enabled struct
     * if and only if iformat/oformat.priv_class is not NULL.
     *
     * - muxing: set by avformat_write_header()
     * - demuxing: set by avformat_open_input()
     */
    void *priv_data;

    /**
     * I/O context.
     *
     * - demuxing: either set by the user before avformat_open_input() (then
     *             the user must close it manually) or set by avformat_open_input().
     * - muxing: set by the user before avformat_write_header(). The caller must
     *           take care of closing / freeing the IO context.
     *
     * 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 */

    /**
     * Number of elements in AVFormatContext.streams.
     *
     * Set by avformat_new_stream(), must not be modified by any other code.
     */
    unsigned int nb_streams;
    /**
     * A list of all streams in the file. New streams are created with
     * avformat_new_stream().
     *
     * - demuxing: 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().
     * - muxing: streams are created by the user before avformat_write_header().
     *
     * Freed by libavformat in avformat_free_context().
     */
    AVStream **streams;

    /**
     * input or output filename
     *
     * - demuxing: set by avformat_open_input()
     * - muxing: may be set by the caller before avformat_write_header()
     */
    char filename[1024];

    /**
     * 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.
     *
     * Demuxing only, set by libavformat.
     */
    int64_t start_time;

    /**
     * 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.
     *
     * Demuxing only, set by libavformat.
     */
    int64_t duration;

    /**
     * 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_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.
#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 ///< Don't merge side data but keep it separate.

    /**
     * Maximum size of the data read from input for determining
     * the input container format.
     * Demuxing only, set by the caller before avformat_open_input().
     */
    unsigned int probesize;

    /**
     * Maximum duration (in AV_TIME_BASE units) of the data read
     * from input in avformat_find_stream_info().
     * Demuxing only, set by the caller before 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 AVCodecID video_codec_id;

    /**
     * Forced audio codec_id.
     * Demuxing: Set by user.
     */
    enum AVCodecID audio_codec_id;

    /**
     * Forced subtitle codec_id.
     * Demuxing: Set by user.
     */
    enum AVCodecID 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;

    /**
     * Number of chapters in AVChapter array.
     * When muxing, chapters are normally written in the file header,
     * so nb_chapters should normally be initialized before write_header
     * is called. Some muxers (e.g. mov and mkv) can also write chapters
     * in the trailer.  To write chapters in the trailer, nb_chapters
     * must be zero when write_header is called and non-zero when
     * write_trailer is called.
     * - muxing: set by user
     * - demuxing: set by libavformat
     */
    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().
     */
    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.
     * - muxing: Set by the caller before avformat_write_header(). If set to
     *           either 0 or AV_NOPTS_VALUE, then the current wall-time will
     *           be used.
     * - demuxing: Set by libavformat. AV_NOPTS_VALUE if unknown. Note that
     *             the value may become known after some number of frames
     *             have been received.
     */
    int64_t start_time_realtime;

    /**
     * The number of frames used for determining the framerate in
     * avformat_find_stream_info().
     * Demuxing only, set by the caller before avformat_find_stream_info().
     */
    int fps_probe_size;

    /**
     * Error recognition; higher values will detect more errors but may
     * misdetect some more or less valid parts as errors.
     * Demuxing only, set by the caller before avformat_open_input().
     */
    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;

    /**
     * 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;

    /**
     * forces the use of wallclock timestamps as pts/dts of packets
     * This has undefined results in the presence of B frames.
     * - encoding: unused
     * - decoding: Set by user via AVOptions (NO direct access)
     */
    int use_wallclock_as_timestamps;

    /**
     * Avoid negative timestamps during muxing.
     *  0 -> allow negative timestamps
     *  1 -> avoid negative timestamps
     * -1 -> choose automatically (default)
     * Note, this only works when interleave_packet_per_dts is in use.
     * - encoding: Set by user via AVOptions (NO direct access)
     * - decoding: unused
     */
    int avoid_negative_ts;

    /**
     * avio flags, used to force AVIO_FLAG_DIRECT.
     * - encoding: unused
     * - decoding: Set by user via AVOptions (NO direct access)
     */
    int avio_flags;

    /**
     * The duration field can be estimated through various ways, and this field can be used
     * to know how the duration was estimated.
     * - encoding: unused
     * - decoding: Read by user via AVOptions (NO direct access)
     */
    enum AVDurationEstimationMethod duration_estimation_method;

    /**
     * Skip initial bytes when opening stream
     * - encoding: unused
     * - decoding: Set by user via AVOptions (NO direct access)
     */
    unsigned int skip_initial_bytes;

    /**
     * Correct single timestamp overflows
     * - encoding: unused
     * - decoding: Set by user via AVOptions (NO direct access)
     */
    unsigned int correct_ts_overflow;

    /**
     * Force seeking to any (also non key) frames.
     * - encoding: unused
     * - decoding: Set by user via AVOptions (NO direct access)
     */
    int seek2any;

    /**
     * Flush the I/O context after each packet.
     * - encoding: Set by user via AVOptions (NO direct access)
     * - decoding: unused
     */
    int flush_packets;

    /**
     * format probing score.
     * The maximal score is AVPROBE_SCORE_MAX, its set when the demuxer probes
     * the format.
     * - encoding: unused
     * - decoding: set by avformat, read by user via av_format_get_probe_score() (NO direct access)
     */
    int probe_score;

    /*****************************************************************
     * 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;

    /**
     * Offset to remap timestamps to be non-negative.
     * Expressed in timebase units.
     * @see AVStream.mux_ts_offset
     */
    int64_t offset;

    /**
     * Timebase for the timestamp offset.
     */
    AVRational offset_timebase;

    /**
     * An opaque field for libavformat internal usage.
     * Must not be accessed in any way by callers.
     */
    AVFormatInternal *internal;

    /**
     * IO repositioned flag.
     * This is set by avformat when the underlaying IO context read pointer
     * is repositioned, for example when doing byte based seeking.
     * Demuxers can use the flag to detect such changes.
     */
    int io_repositioned;

    /**
     * Forced video codec.
     * This allows forcing a specific decoder, even when there are multiple with
     * the same codec_id.
     * Demuxing: Set by user via av_format_set_video_codec (NO direct access).
     */
    AVCodec *video_codec;

    /**
     * Forced audio codec.
     * This allows forcing a specific decoder, even when there are multiple with
     * the same codec_id.
     * Demuxing: Set by user via av_format_set_audio_codec (NO direct access).
     */
    AVCodec *audio_codec;

    /**
     * Forced subtitle codec.
     * This allows forcing a specific decoder, even when there are multiple with
     * the same codec_id.
     * Demuxing: Set by user via av_format_set_subtitle_codec (NO direct access).
     */
    AVCodec *subtitle_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;

    /**
     * User data.
     * This is a place for some private data of the user.
     * Mostly usable with control_message_cb or any future callbacks in device's context.
     */
    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 via AVOptions (NO direct access)
     */
    int64_t output_ts_offset;
} AVFormatContext;


展开阅读全文

没有更多推荐了,返回首页