在看雷神博客的时候发现现在版本的ffmpeg的AVStream和雷神博客的已经不一样了,如果雷神没走的话估计已经更新了,雷神真的宝藏。我就自己记录下AVStream
贴上雷神的AVStream: FFMPEG结构体分析:AVStream
我们知道在AVFormatContext里就有AVStream,下面是AVFormatContext中AVStream部分代码
/**
* 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;
AVStream就是存储视频和音频的结构体,他是在libavformat/avformat.h下声明的,代码有点长,声明如下:
/**
* Stream 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.
* sizeof(AVStream) must not be used outside libav*.
*/
typedef struct AVStream {
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
*/
int id;
#if FF_API_LAVF_AVCTX
/**
* @deprecated use the codecpar struct instead
*/
attribute_deprecated
AVCodecContext *codec;
#endif
void *priv_data;
#if FF_API_LAVF_FRAC
/**
* @deprecated this field is unused
*/
attribute_deprecated
struct AVFrac pts;
#endif
/**
* This is the fundamental unit of time (in seconds) in terms
* of which frame timestamps are represented.
*
* decoding: set by libavformat
* encoding: May be set by the caller before avformat_write_header() to
* provide a hint to the muxer about the desired timebase. In
* avformat_write_header(), the muxer will overwrite this field
* with the timebase that will actually be used for the timestamps
* written into the file (which may or may not be related to the
* user-provided one, depending on the format).
*/
AVRational time_base;
/**
* Decoding: pts of the first frame of the stream in presentation order, in stream time base.
* Only set this if you are absolutely 100% sure that the value you set
* it to really is the pts of the first frame.
* This may be undefined (AV_NOPTS_VALUE).
* @note The ASF header does NOT contain a correct start_time the ASF
* demuxer must NOT set this.
*/
int64_t start_time;
/**
* Decoding: duration of the stream, in stream time base.
* If a source file does not specify a duration, but does specify
* a bitrate, this value will be estimated from bitrate and file size.
*
* Encoding: May be set by the caller before avformat_write_header() to
* provide a hint to the muxer about the estimated duration.
*/
int64_t duration;
int64_t nb_frames; ///< number of frames in this stream if known or 0
int disposition; /**< AV_DISPOSITION_* bit field */
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.
*/
AVRational sample_aspect_ratio;
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 for the user to detect events happening on the stream. Flags must
* be cleared by the user once the event has been handled.
* A combination of AVSTREAM_EVENT_FLAG_*.
*/
int event_flags;
#define AVSTREAM_EVENT_FLAG_METADATA_UPDATED 0x0001 ///< The call resulted in updated metadata.
/*****************************************************************
* 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.
*****************************************************************
*/
/**
* Stream information used internally by avformat_find_stream_info()
*/
#define MAX_STD_TIMEBASES (30*12+30+3+6)
struct {
int64_t last_dts;
int64_t duration_gcd;
int duration_count;
int64_t rfps_duration_sum;
double (*duration_error)[2][MAX_STD_TIMEBASES];
int64_t codec_info_duration;
int64_t codec_info_duration_fields;
/**
* 0 -> decoder has not been searched for yet.
* >0 -> decoder found
* <0 -> decoder with codec_id == -found_decoder has not been found
*/
int found_decoder;
int64_t last_duration;
/**
* Those are used for average framerate estimation.
*/
int64_t fps_first_dts;
int fps_first_dts_idx;
int64_t fps_last_dts;
int fps_last_dts_idx;
} *info;
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;
/**
* last packet in packet_buffer for this stream when muxing.
*/
struct AVPacketList *last_in_packet_buffer;
AVProbeData probe_data;
#define MAX_REORDER_DELAY 16
int64_t pts_buffer[MAX_REORDER_DELAY+1];
AVIndexEntry *index_entries; /**< Only used if the format does not
support seeking natively. */
int nb_index_entries;
unsigned int index_entries_allocated_size;
/**
* 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.
*
* Code outside avformat should access this field using:
* av_stream_get/set_r_frame_rate(stream)
*/
AVRational r_frame_rate;
/**
* Stream Identifier
* This is the MPEG-TS stream identifier +1
* 0 means unknown
*/
int stream_identifier;
int64_t interleaver_chunk_size;
int64_t interleaver_chunk_duration;
/**
* stream probing state
* -1 -> probing finished
* 0 -> no probing requested
* rest -> perform probing with request_probe being the minimum score to accept.
* NOT PART OF PUBLIC API
*/
int request_probe;
/**
* Indicates that everything up to the next keyframe
* should be discarded.
*/
int skip_to_keyframe;
/**
* Number of samples to skip at the start of the frame decoded from the next packet.
*/
int skip_samples;
/**
* If not 0, the number of samples that should be skipped from the start of
* the stream (the samples are removed from packets with pts==0, which also
* assumes negative timestamps do not happen).
* Intended for use with formats such as mp3 with ad-hoc gapless audio
* support.
*/
int64_t start_skip_samples;
/**
* If not 0, the first audio sample that should be discarded from the stream.
* This is broken by design (needs global sample count), but can't be
* avoided for broken by design formats such as mp3 with ad-hoc gapless
* audio support.
*/
int64_t first_discard_sample;
/**
* The sample after last sample that is intended to be discarded after
* first_discard_sample. Works on frame boundaries only. Used to prevent
* early EOF if the gapless info is broken (considered concatenated mp3s).
*/
int64_t last_discard_sample;
/**
* Number of internally decoded frames, used internally in libavformat, do not access
* its lifetime differs from info which is why it is not in that structure.
*/
int nb_decoded_frames;
/**
* Timestamp offset added to timestamps before muxing
* NOT PART OF PUBLIC API
*/
int64_t mux_ts_offset;
/**
* Internal data to check for wrapping of the time stamp
*/
int64_t pts_wrap_reference;
/**
* Options for behavior, when a wrap is detected.
*
* Defined by AV_PTS_WRAP_ values.
*
* If correction is enabled, there are two possibilities:
* If the first time stamp is near the wrap point, the wrap offset
* will be subtracted, which will create negative time stamps.
* Otherwise the offset will be added.
*/
int pts_wrap_behavior;
/**
* Internal data to prevent doing update_initial_durations() twice
*/
int update_initial_durations_done;
/**
* Internal data to generate dts from pts
*/
int64_t pts_reorder_error[MAX_REORDER_DELAY+1];
uint8_t pts_reorder_error_count[MAX_REORDER_DELAY+1];
/**
* Internal data to analyze DTS and detect faulty mpeg streams
*/
int64_t last_dts_for_order_check;
uint8_t dts_ordered;
uint8_t dts_misordered;
/**
* Internal data to inject global side data
*/
int inject_global_side_data;
/*****************************************************************
* All fields above this line are not part of the public API.
* Fields below are part of the public API and ABI again.
*****************************************************************
*/
/**
* String containing paris of key and values describing recommended encoder configuration.
* Paris are separated by ','.
* Keys are separated from values by '='.
*/
char *recommended_encoder_configuration;
/**
* display aspect ratio (0 if unknown)
* - encoding: unused
* - decoding: Set by libavformat to calculate sample_aspect_ratio internally
*/
AVRational display_aspect_ratio;
struct FFFrac *priv_pts;
/**
* An opaque field for libavformat internal usage.
* Must not be accessed in any way by callers.
*/
AVStreamInternal *internal;
/*
* 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;
} AVStream;
在声明中,有几个比较重要的如下:
int index:用来标识是视频还是音频 一般0是视频,1是音频
AVCodecContext *codec;这个现在不怎么多用,这个是指向视频或者音频的AVCodecContext
AVRational time_base;
这里我们需要看下AVRational的结构体
/**
* Rational number (pair of numerator and denominator).
*/
typedef struct AVRational{
int num; ///< Numerator 分子
int den; ///< Denominator 分母
} AVRational;
可以把AVRational看成一个分数,time_base是一个时间基数,这里的time_base和ic里面define的是不一样的,用pts*time_base 可以得到真正的时间
int64_t duration; 视频或音频的长度
我们可以用duration和time_base做乘法得到秒或毫秒
duration * ( (double)time_base.num / (double)time_base.den ) * 1000
注意 这里的time_base.den可能为0,所以自己可以写这么一个函数来做容错
AVRational avg_frame_rate;从名字可以看出 这是帧率
AVCodecParameters *codecpar;(音视频参数) 这个参数是用来替代上面的codec的
下面是codecpar在AVFrame中的代码部分单独提出来
/*
* 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;
我们发现解封装的时候,是从avformat_find_stream_info()过来的,下面是AVCodecParameters的结构体,我觉得这个结构体可能可以单独开一篇文章
/**
* This struct describes the properties of an encoded stream.
*
* sizeof(AVCodecParameters) is not a part of the public ABI, this struct must
* be allocated with avcodec_parameters_alloc() and freed with
* avcodec_parameters_free().
*/
typedef struct AVCodecParameters {
/**
* General type of the encoded data.
*/
enum AVMediaType codec_type;
/**
* Specific type of the encoded data (the codec used).
*/
enum AVCodecID codec_id;
/**
* Additional information about the codec (corresponds to the AVI FOURCC).
*/
uint32_t codec_tag;
/**
* Extra binary data needed for initializing the decoder, codec-dependent.
*
* Must be allocated with av_malloc() and will be freed by
* avcodec_parameters_free(). The allocated size of extradata must be at
* least extradata_size + AV_INPUT_BUFFER_PADDING_SIZE, with the padding
* bytes zeroed.
*/
uint8_t *extradata;
/**
* Size of the extradata content in bytes.
*/
int extradata_size;
/**
* - video: the pixel format, the value corresponds to enum AVPixelFormat.
* - audio: the sample format, the value corresponds to enum AVSampleFormat.
*/
int format;
/**
* The average bitrate of the encoded data (in bits per second).
*/
int64_t bit_rate;
/**
* The number of bits per sample in the codedwords.
*
* This is basically the bitrate per sample. It is mandatory for a bunch of
* formats to actually decode them. It's the number of bits for one sample in
* the actual coded bitstream.
*
* This could be for example 4 for ADPCM
* For PCM formats this matches bits_per_raw_sample
* Can be 0
*/
int bits_per_coded_sample;
/**
* This is the number of valid bits in each output sample. If the
* sample format has more bits, the least significant bits are additional
* padding bits, which are always 0. Use right shifts to reduce the sample
* to its actual size. For example, audio formats with 24 bit samples will
* have bits_per_raw_sample set to 24, and format set to AV_SAMPLE_FMT_S32.
* To get the original sample use "(int32_t)sample >> 8"."
*
* For ADPCM this might be 12 or 16 or similar
* Can be 0
*/
int bits_per_raw_sample;
/**
* Codec-specific bitstream restrictions that the stream conforms to.
*/
int profile;
int level;
/**
* Video only. The dimensions of the video frame in pixels.
*/
int width;
int height;
/**
* Video only. The aspect ratio (width / height) which a single pixel
* should have when displayed.
*
* When the aspect ratio is unknown / undefined, the numerator should be
* set to 0 (the denominator may have any value).
*/
AVRational sample_aspect_ratio;
/**
* Video only. The order of the fields in interlaced video.
*/
enum AVFieldOrder field_order;
/**
* Video only. Additional colorspace characteristics.
*/
enum AVColorRange color_range;
enum AVColorPrimaries color_primaries;
enum AVColorTransferCharacteristic color_trc;
enum AVColorSpace color_space;
enum AVChromaLocation chroma_location;
/**
* Video only. Number of delayed frames.
*/
int video_delay;
/**
* Audio only. The channel layout bitmask. May be 0 if the channel layout is
* unknown or unspecified, otherwise the number of bits set must be equal to
* the channels field.
*/
uint64_t channel_layout;
/**
* Audio only. The number of audio channels.
*/
int channels;
/**
* Audio only. The number of audio samples per second.
*/
int sample_rate;
/**
* Audio only. The number of bytes per coded audio frame, required by some
* formats.
*
* Corresponds to nBlockAlign in WAVEFORMATEX.
*/
int block_align;
/**
* Audio only. Audio frame size, if known. Required by some formats to be static.
*/
int frame_size;
/**
* Audio only. The amount of padding (in samples) inserted by the encoder at
* the beginning of the audio. I.e. this number of leading decoded samples
* must be discarded by the caller to get the original audio without leading
* padding.
*/
int initial_padding;
/**
* Audio only. The amount of padding (in samples) appended by the encoder to
* the end of the audio. I.e. this number of decoded samples must be
* discarded by the caller from the end of the stream to get the original
* audio without any trailing padding.
*/
int trailing_padding;
/**
* Audio only. Number of samples to skip after a discontinuity.
*/
int seek_preroll;
} AVCodecParameters;
在AVCodecParameters中,有几个比较重要的可以来看一下:
enum AVMediaType codec_type;
/**
* General type of the encoded data.
*/
enum AVMediaType codec_type; //表示编码的参数是音频还是视频
/*枚举类型如下:
/**
* @addtogroup lavu_media Media Type
* @brief Media Type
*/
enum AVMediaType {
AVMEDIA_TYPE_UNKNOWN = -1, ///< Usually treated as AVMEDIA_TYPE_DATA
AVMEDIA_TYPE_VIDEO,
AVMEDIA_TYPE_AUDIO,
AVMEDIA_TYPE_DATA, ///< Opaque data information usually continuous
AVMEDIA_TYPE_SUBTITLE,
AVMEDIA_TYPE_ATTACHMENT, ///< Opaque data information usually sparse
AVMEDIA_TYPE_NB
};
*/
enum AVCodecID codec_id;
/** 表示编码格式 到时候需要通过codec_id打开解封装器
* Specific type of the encoded data (the codec used).
*/
enum AVCodecID codec_id;
//这个枚举类型就有点长了 大家可以自己去看 在libavcodec/avcodec/h中
int format;int width;int height;
/** 对视频来说是像素格式,对音频来说是采样格式
* - video: the pixel format, the value corresponds to enum AVPixelFormat.
* - audio: the sample format, the value corresponds to enum AVSampleFormat.
*/
int format;
/** 视频里面才有宽和高
* Video only. The dimensions of the video frame in pixels.
*/
int width;
int height;
uint64_t channel_layout;
/** 声道音频才有,这里会有一个函数可以直接用
* Audio only. The channel layout bitmask. May be 0 if the channel layout is
* unknown or unspecified, otherwise the number of bits set must be equal to
* the channels field.
*/
uint64_t channel_layout;
int channels; int sample_rate;int frame_size;
/** 音频的声道数量
* Audio only. The number of audio channels.
*/
int channels;
/** 音频样本率
* Audio only. The number of audio samples per second.
*/
int sample_rate;
/** 一帧音频的大小
* Audio only. Audio frame size, if known. Required by some formats to be static.
*/
int frame_size;
所以,如果我们获得了一个AVStream,我们可以通过他里面的AVCodecParameters得到很多东西,下面就用代码示例来看下效果
//通过遍历获取音视频信息(ic->nb_streams)
for (int i = 0; i < ic->nb_streams; i++)
{
AVStream *as = ic->streams[i];
//音频 通过AVStream里的AVCodecParameters codecpar中的codectype来判断
if (as->codecpar->codec_type == AVMEDIA_TYPE_AUDIO)
{
cout << i << " audio " << endl;
cout << "sample_rate:" << as->codecpar->sample_rate << endl;
//AVSampleFormat 音频
cout << "format:" << as->codecpar->format << endl;
cout << "channels:" << as->codecpar->channels << endl;
cout << "codec_id:" << as->codecpar->codec_id << endl;
}
//视频
else if (as->codecpar->codec_type == AVMEDIA_TYPE_VIDEO)
{
cout << i << " video " << endl;
}
}
我们可以得到下图结果
这里的codec_id是86018,来看下
视频的就不写了。大家自己去分析吧,最后,雷神牛逼!