FFMPeg代码分析：AVPacket结构体和av_read_frame函数

AVPacket结构用于保存压缩编码过的数据。在解码时，该结构的实例通常作为解复用器（demuxer）的输出并输入到解码器中；在编码时，通常是编码器的输出，并输入到复用器（muxer）中。该结构体的定义如下：

typedef struct AVPacket {
    /**
     * A reference to the reference-counted buffer where the packet data is
     * stored.
     * May be NULL, then the packet data is not reference-counted.
     */
    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.
     */
    int64_t pts;//显示时间戳
    /**
     * 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.
     */
    int64_t dts;//解码时间戳
    uint8_t *data;//实例所包含的压缩数据，直接获取该指针指向缓存的数据可以得到压缩过的码流；
    int   size;//原始压缩数据的大小
    int   stream_index;//标识当前AVPacket所从属的码流
    /**
     * A combination of AV_PKT_FLAG values
     */
    int   flags;
    /**
     * Additional packet data that can be provided by the container.
     * Packet can contain several types of side information.
     */
    struct {
        uint8_t *data;
        int      size;
        enum AVPacketSideDataType type;
    } *side_data;
    int side_data_elems;

    /**
     * Duration of this packet in AVStream->time_base units, 0 if unknown.
     * Equals next_pts - this_pts in presentation order.
     */
    int   duration;
#if FF_API_DESTRUCT_PACKET
    attribute_deprecated
    void  (*destruct)(struct AVPacket *);
    attribute_deprecated
    void  *priv;
#endif
    int64_t pos;                            ///< byte position in stream, -1 if unknown

    /**
     * Time difference in AVStream->time_base units from the pts of this
     * packet to the point at which the output from the decoder has converged
     * independent from the availability of previous frames. That is, the
     * frames are virtually identical no matter if decoding started from
     * the very first frame or from this keyframe.
     * Is AV_NOPTS_VALUE if unknown.
     * This field is not the display duration of the current packet.
     * This field has no meaning if the packet does not have AV_PKT_FLAG_KEY
     * set.
     *
     * The purpose of this field is to allow seeking in streams that have no
     * keyframes in the conventional sense. It corresponds to the
     * recovery point SEI in H.264 and match_time_delta in NUT. It is also
     * essential for some types of subtitle streams to ensure that all
     * subtitles are correctly displayed after seeking.
     */
    int64_t convergence_duration;
} AVPacket;

int av_read_frame(AVFormatContext *s, AVPacket *pkt)
{
    const int genpts = s->flags & AVFMT_FLAG_GENPTS;
    int          eof = 0;
    int ret;
    AVStream *st;

    if (!genpts) {
        ret = s->packet_buffer ?
            read_from_packet_buffer(&s->packet_buffer, &s->packet_buffer_end, pkt) :
            read_frame_internal(s, pkt);
        if (ret < 0)
            return ret;
        goto return_packet;
    }

    for (;;) {
        AVPacketList *pktl = s->packet_buffer;

        if (pktl) {
            AVPacket *next_pkt = &pktl->pkt;

            if (next_pkt->dts != AV_NOPTS_VALUE) {
                int wrap_bits = s->streams[next_pkt->stream_index]->pts_wrap_bits;
                // last dts seen for this stream. if any of packets following
                // current one had no dts, we will set this to AV_NOPTS_VALUE.
                int64_t last_dts = next_pkt->dts;
                while (pktl && next_pkt->pts == AV_NOPTS_VALUE) {
                    if (pktl->pkt.stream_index == next_pkt->stream_index &&
                        (av_compare_mod(next_pkt->dts, pktl->pkt.dts, 2LL << (wrap_bits - 1)) < 0)) {
                        if (av_compare_mod(pktl->pkt.pts, pktl->pkt.dts, 2LL << (wrap_bits - 1))) { //not b frame
                            next_pkt->pts = pktl->pkt.dts;
                        }
                        if (last_dts != AV_NOPTS_VALUE) {
                            // Once last dts was set to AV_NOPTS_VALUE, we don't change it.
                            last_dts = pktl->pkt.dts;
                        }
                    }
                    pktl = pktl->next;
                }
                if (eof && next_pkt->pts == AV_NOPTS_VALUE && last_dts != AV_NOPTS_VALUE) {
                    // Fixing the last reference frame had none pts issue (For MXF etc).
                    // We only do this when
                    // 1. eof.
                    // 2. we are not able to resolve a pts value for current packet.
                    // 3. the packets for this stream at the end of the files had valid dts.
                    next_pkt->pts = last_dts + next_pkt->duration;
                }
                pktl = s->packet_buffer;
            }

            /* read packet from packet buffer, if there is data */
            if (!(next_pkt->pts == AV_NOPTS_VALUE &&
                  next_pkt->dts != AV_NOPTS_VALUE && !eof)) {
                ret = read_from_packet_buffer(&s->packet_buffer,
                                               &s->packet_buffer_end, pkt);
                goto return_packet;
            }
        }

        ret = read_frame_internal(s, pkt);
        if (ret < 0) {
            if (pktl && ret != AVERROR(EAGAIN)) {
                eof = 1;
                continue;
            } else
                return ret;
        }

        if (av_dup_packet(add_to_pktbuf(&s->packet_buffer, pkt,
                          &s->packet_buffer_end)) < 0)
            return AVERROR(ENOMEM);
    }

return_packet:

    st = s->streams[pkt->stream_index];
    if (st->skip_samples) {
        uint8_t *p = av_packet_new_side_data(pkt, AV_PKT_DATA_SKIP_SAMPLES, 10);
        if (p) {
            AV_WL32(p, st->skip_samples);
            av_log(s, AV_LOG_DEBUG, "demuxer injecting skip %d\n", st->skip_samples);
        }
        st->skip_samples = 0;
    }

    if ((s->iformat->flags & AVFMT_GENERIC_INDEX) && pkt->flags & AV_PKT_FLAG_KEY) {
        ff_reduce_index(s, st->index);
        av_add_index_entry(st, pkt->pos, pkt->dts, 0, 0, AVINDEX_KEYFRAME);
    }

    if (is_relative(pkt->dts))
        pkt->dts -= RELATIVE_TS_BASE;
    if (is_relative(pkt->pts))
        pkt->pts -= RELATIVE_TS_BASE;

    return ret;
}