FFmpeg源代码：av_read_frame

ffmpeg中的av_read_frame()的作用是读取码流中的音频若干帧或者视频一帧。

例如，解码视频的时候，每解码一个视频帧，需要先调用 av_read_frame()获得一帧视频的压缩数据，然后才能对该数据进行解码（例如H.264中一帧压缩数据通常对应一个NAL）。

该函数声明位于libavformat\avformat.h中

/**
 * Return the next frame of a stream.
 * This function returns what is stored in the file, and does not validate
 * that what is there are valid frames for the decoder. It will split what is
 * stored in the file into frames and return one for each call. It will not
 * omit invalid data between valid frames so as to give the decoder the maximum
 * information possible for decoding.
 *
 * On success, the returned packet is reference-counted (pkt->buf is set) and
 * valid indefinitely. The packet must be freed with av_packet_unref() when
 * it is no longer needed. For video, the packet contains exactly one frame.
 * For audio, it contains an integer number of frames if each frame has
 * a known fixed size (e.g. PCM or ADPCM data). If the audio frames have
 * a variable size (e.g. MPEG audio), then it contains one frame.
 *
 * pkt->pts, pkt->dts and pkt->duration are always set to correct
 * values in AVStream.time_base units (and guessed if the format cannot
 * provide them). pkt->pts can be AV_NOPTS_VALUE if the video format
 * has B-frames, so it is better to rely on pkt->dts if you do not
 * decompress the payload.
 *
 * @return 0 if OK, < 0 on error or end of file. On error, pkt will be blank
 *         (as if it came from av_packet_alloc()).
 *
 * @note pkt will be initialized, so it may be uninitialized, but it must not
 *       contain data that needs to be freed.
 */
int av_read_frame(AVFormatContext *s, AVPacket *pkt);

该函数参数：

s: 输入流的AVFormatContext

pkt: 输出的AVPacket

 av_read_frame()的定义位于libavformat\utils.c，如下所示：

//获取一个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) {
        //一般情况下会调用read_frame_internal
        ret = s->internal->packet_buffer
              ? ff_packet_list_get(&s->internal->packet_buffer,
                                        &s->internal->packet_buffer_end, pkt)
              : read_frame_internal(s, pkt);
        if (ret < 0)
            return ret;
        goto return_packet;
    }
 
    for (;;) {
        AVPacketList *pktl = s->internal->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;
                av_assert2(wrap_bits <= 64);
                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, 2ULL << (wrap_bits - 1)) < 0) {
                        if (av_compare_mod(pktl->pkt.pts, pktl->pkt.dts, 2ULL << (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->internal->packet_buffer;
            }
 
            /* read packet from packet buffer, if there is data */
            st = s->streams[next_pkt->stream_index];
            if (!(next_pkt->pts == AV_NOPTS_VALUE && st->discard < AVDISCARD_ALL &&
                  next_pkt->dts != AV_NOPTS_VALUE && !eof)) {
                ret = ff_packet_list_get(&s->internal->packet_buffer,
                                               &s->internal->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;
        }
 
        ret = ff_packet_list_put(&s->internal->packet_buffer,
                                 &s->internal->packet_buffer_end,
                                 pkt, 0);
        if (ret < 0) {
            av_packet_unref(pkt);
            return ret;
        }
    }
 
return_packet:
 
    st = s->streams[pkt->stream_index];
    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;
}

 从接口定义中可以看出，av_read_frame()调用了read_frame_internal()

read_frame_internal()是一个内部函数

 
static int read_frame_internal(AVFormatContext *s, AVPacket *pkt)
{
    int ret, i, got_packet = 0;
    AVDictionary *metadata = NULL;
 
    while (!got_packet && !s->internal->parse_queue) {
        AVStream *st;
 
        /* read next packet */
        //Read a transport packet from a media file.
        // 很重要的一个函数
        ret = ff_read_packet(s, pkt);
        if (ret < 0) {
            if (ret == AVERROR(EAGAIN))
                return ret;
            /* flush the parsers */
            for (i = 0; i < s->nb_streams; i++) {
                st = s->streams[i];
                //解析pkt
                if (st->parser && st->need_parsing)
                    parse_packet(s, pkt, st->index, 1);
            }
            /* all remaining packets are now in parse_queue =>
             * really terminate parsing */
            break;
        }
        ret = 0;
        st  = s->streams[pkt->stream_index];
 
        /* update context if required */
        if (st->internal->need_context_update) {
            if (avcodec_is_open(st->internal->avctx)) {
                av_log(s, AV_LOG_DEBUG, "Demuxer context update while decoder is open, closing and trying to re-open\n");
                avcodec_close(st->internal->avctx);
                st->info->found_decoder = 0;
            }
 
            /* close parser, because it depends on the codec */
            if (st->parser && st->internal->avctx->codec_id != st->codecpar->codec_id) {
                av_parser_close(st->parser);
                st->parser = NULL;
            }
 
            ret = avcodec_parameters_to_context(st->internal->avctx, st->codecpar);
            if (ret < 0) {
                av_packet_unref(pkt);
                return ret;
            }
 
#if FF_API_LAVF_AVCTX
FF_DISABLE_DEPRECATION_WARNINGS
            /* update deprecated public codec context */
            ret = avcodec_parameters_to_context(st->codec, st->codecpar);
            if (ret < 0) {
                av_packet_unref(pkt);
                return ret;
            }
FF_ENABLE_DEPRECATION_WARNINGS
#endif
 
            st->internal->need_context_update = 0;
        }
 
        if (pkt->pts != AV_NOPTS_VALUE &&
            pkt->dts != AV_NOPTS_VALUE &&
            pkt->pts < pkt->dts) {
            av_log(s, AV_LOG_WARNING,
                   "Invalid timestamps stream=%d, pts=%s, dts=%s, size=%d\n",
                   pkt->stream_index,
                   av_ts2str(pkt->pts),
                   av_ts2str(pkt->dts),
                   pkt->size);
        }
        if (s->debug & FF_FDEBUG_TS)
            av_log(s, AV_LOG_DEBUG,
                   "ff_read_packet stream=%d, pts=%s, dts=%s, size=%d, duration=%"PRId64", flags=%d\n",
                   pkt->stream_index,
                   av_ts2str(pkt->pts),
                   av_ts2str(pkt->dts),
                   pkt->size, pkt->duration, pkt->flags);
 
        if (st->need_parsing && !st->parser && !(s->flags & AVFMT_FLAG_NOPARSE)) {
            st->parser = av_parser_init(st->codecpar->codec_id);
            if (!st->parser) {
                av_log(s, AV_LOG_VERBOSE, "parser not found for codec "
                       "%s, packets or times may be invalid.\n",
                       avcodec_get_name(st->codecpar->codec_id));
                /* no parser available: just output the raw packets */
                st->need_parsing = AVSTREAM_PARSE_NONE;
            } else if (st->need_parsing == AVSTREAM_PARSE_HEADERS)
                st->parser->flags |= PARSER_FLAG_COMPLETE_FRAMES;
            else if (st->need_parsing == AVSTREAM_PARSE_FULL_ONCE)
                st->parser->flags |= PARSER_FLAG_ONCE;
            else if (st->need_parsing == AVSTREAM_PARSE_FULL_RAW)
                st->parser->flags |= PARSER_FLAG_USE_CODEC_TS;
        }
 
        if (!st->need_parsing || !st->parser) {
            /* no parsing needed: we just output the packet as is */
            compute_pkt_fields(s, st, NULL, pkt, AV_NOPTS_VALUE, AV_NOPTS_VALUE);
            if ((s->iformat->flags & AVFMT_GENERIC_INDEX) &&
                (pkt->flags & AV_PKT_FLAG_KEY) && pkt->dts != AV_NOPTS_VALUE) {
                ff_reduce_index(s, st->index);
                av_add_index_entry(st, pkt->pos, pkt->dts,
                                   0, 0, AVINDEX_KEYFRAME);
            }
            got_packet = 1;
        } else if (st->discard < AVDISCARD_ALL) {
            if ((ret = parse_packet(s, pkt, pkt->stream_index, 0)) < 0)
                return ret;
            st->codecpar->sample_rate = st->internal->avctx->sample_rate;
            st->codecpar->bit_rate = st->internal->avctx->bit_rate;
            st->codecpar->channels = st->internal->avctx->channels;
            st->codecpar->channel_layout = st->internal->avctx->channel_layout;
            st->codecpar->codec_id = st->internal->avctx->codec_id;
        } else {
            /* free packet */
            av_packet_unref(pkt);
        }
        if (pkt->flags & AV_PKT_FLAG_KEY)
            st->skip_to_keyframe = 0;
        if (st->skip_to_keyframe) {
            av_packet_unref(pkt);
            got_packet = 0;
        }
    }
 
    if (!got_packet && s->internal->parse_queue)
        ret = ff_packet_list_get(&s->internal->parse_queue, &s->internal->parse_queue_end, pkt);
 
    if (ret >= 0) {
        AVStream *st = s->streams[pkt->stream_index];
        int discard_padding = 0;
        if (st->first_discard_sample && pkt->pts != AV_NOPTS_VALUE) {
            int64_t pts = pkt->pts - (is_relative(pkt->pts) ? RELATIVE_TS_BASE : 0);
            int64_t sample = ts_to_samples(st, pts);
            int duration = ts_to_samples(st, pkt->duration);
            int64_t end_sample = sample + duration;
            if (duration > 0 && end_sample >= st->first_discard_sample &&
                sample < st->last_discard_sample)
                discard_padding = FFMIN(end_sample - st->first_discard_sample, duration);
        }
        if (st->start_skip_samples && (pkt->pts == 0 || pkt->pts == RELATIVE_TS_BASE))
            st->skip_samples = st->start_skip_samples;
        if (st->skip_samples || discard_padding) {
            uint8_t *p = av_packet_new_side_data(pkt, AV_PKT_DATA_SKIP_SAMPLES, 10);
            if (p) {
                AV_WL32(p, st->skip_samples);
                AV_WL32(p + 4, discard_padding);
                av_log(s, AV_LOG_DEBUG, "demuxer injecting skip %d / discard %d\n", st->skip_samples, discard_padding);
            }
            st->skip_samples = 0;
        }
 
        if (st->inject_global_side_data) {
            for (i = 0; i < st->nb_side_data; i++) {
                AVPacketSideData *src_sd = &st->side_data[i];
                uint8_t *dst_data;
 
                if (av_packet_get_side_data(pkt, src_sd->type, NULL))
                    continue;
 
                dst_data = av_packet_new_side_data(pkt, src_sd->type, src_sd->size);
                if (!dst_data) {
                    av_log(s, AV_LOG_WARNING, "Could not inject global side data\n");
                    continue;
                }
 
                memcpy(dst_data, src_sd->data, src_sd->size);
            }
            st->inject_global_side_data = 0;
        }
    }
 
    av_opt_get_dict_val(s, "metadata", AV_OPT_SEARCH_CHILDREN, &metadata);
    if (metadata) {
        s->event_flags |= AVFMT_EVENT_FLAG_METADATA_UPDATED;
        av_dict_copy(&s->metadata, metadata, 0);
        av_dict_free(&metadata);
        av_opt_set_dict_val(s, "metadata", NULL, AV_OPT_SEARCH_CHILDREN);
    }
 
#if FF_API_LAVF_AVCTX
    update_stream_avctx(s);
#endif
 
    if (s->debug & FF_FDEBUG_TS)
        av_log(s, AV_LOG_DEBUG,
               "read_frame_internal stream=%d, pts=%s, dts=%s, "
               "size=%d, duration=%"PRId64", flags=%d\n",
               pkt->stream_index,
               av_ts2str(pkt->pts),
               av_ts2str(pkt->dts),
               pkt->size, pkt->duration, pkt->flags);
 
    /* A demuxer might have returned EOF because of an IO error, let's
     * propagate this back to the user. */
    if (ret == AVERROR_EOF && s->pb && s->pb->error < 0 && s->pb->error != AVERROR(EAGAIN))
        ret = s->pb->error;
 
    return ret;
}

read_frame_internal() 的功能主要由以下两个接口实现：

1. ff_read_packet()从相应的AVInputFormat读取AVPacket数据;

2. 如果媒体频流需要使用AVCodecParser，则调用parse_packet()解析相应的AVPacket