FFMPEG版本3.2release,文件位于libavformat/utils.c
函数read_frame_internal()主要功能分为三部分
static int read_frame_internal(AVFormatContext *s, AVPacket *pkt)
{
int ret = 0, i, got_packet = 0;
AVDictionary *metadata = NULL;
av_init_packet(pkt);
while (!got_packet && !s->internal->parse_queue) {
AVStream *st;
AVPacket cur_pkt;
/* read next packet */
ret = ff_read_packet(s, &cur_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];
if (st->parser && st->need_parsing)
parse_packet(s, NULL, st->index);
}
/* all remaining packets are now in parse_queue =>
* really terminate parsing */
break;
}
ret = 0;
st = s->streams[cur_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;
}
ret = avcodec_parameters_to_context(st->internal->avctx, st->codecpar);
if (ret < 0)
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)
return ret;
FF_ENABLE_DEPRECATION_WARNINGS
#endif
st->internal->need_context_update = 0;
}
if (cur_pkt.pts != AV_NOPTS_VALUE &&
cur_pkt.dts != AV_NOPTS_VALUE &&
cur_pkt.pts < cur_pkt.dts) {
av_log(s, AV_LOG_WARNING,
"Invalid timestamps stream=%d, pts=%s, dts=%s, size=%d\n",
cur_pkt.stream_index,
av_ts2str(cur_pkt.pts),
av_ts2str(cur_pkt.dts),
cur_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",
cur_pkt.stream_index,
av_ts2str(cur_pkt.pts),
av_ts2str(cur_pkt.dts),
cur_pkt.size, cur_pkt.duration, cur_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 */
*pkt = cur_pkt;
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, &cur_pkt, cur_pkt.stream_index)) < 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(&cur_pkt);
}
if (pkt->flags & AV_PKT_FLAG_KEY)
st->skip_to_keyframe = 0;
if (st->skip_to_keyframe) {
av_packet_unref(&cur_pkt);
if (got_packet) {
*pkt = cur_pkt;
}
got_packet = 0;
}
}
if (!got_packet && s->internal->parse_queue)
ret = read_from_packet_buffer(&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;
}
if (!(s->flags & AVFMT_FLAG_KEEP_SIDE_DATA))
av_packet_merge_side_data(pkt);
}
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);
return ret;
}
函数ff_read_packet(AVFormatContext *s, AVPacket *pkt)
从指针AVFormatContext *pb读取音频或者视频数据,保存到pkt->data,同时得到音视频的编解码格式。
int ff_read_packet(AVFormatContext *s, AVPacket *pkt)
{
int ret, i, err;
AVStream *st;
for (;;) {
AVPacketList *pktl = s->internal->raw_packet_buffer;
if (pktl) {
*pkt = pktl->pkt;
st = s->streams[pkt->stream_index];
if (s->internal->raw_packet_buffer_remaining_size <= 0)
if ((err = probe_codec(s, st, NULL)) < 0)
return err;
if (st->request_probe <= 0) {
s->internal->raw_packet_buffer = pktl->next;
s->internal->raw_packet_buffer_remaining_size += pkt->size;
av_free(pktl);
return 0;
}
}
pkt->data = NULL;
pkt->size = 0;
av_init_packet(pkt);
ret = s->iformat->read_packet(s, pkt);
if (ret < 0) {
/* Some demuxers return FFERROR_REDO when they consume
data and discard it (ignored streams, junk, extradata).
We must re-call the demuxer to get the real packet. */
if (ret == FFERROR_REDO)
continue;
if (!pktl || ret == AVERROR(EAGAIN))
return ret;
for (i = 0; i < s->nb_streams; i++) {
st = s->streams[i];
if (st->probe_packets || st->request_probe > 0)
if ((err = probe_codec(s, st, NULL)) < 0)
return err;
av_assert0(st->request_probe <= 0);
}
continue;
}
if (!pkt->buf) {
AVPacket tmp = { 0 };
ret = av_packet_ref(&tmp, pkt);
if (ret < 0)
return ret;
*pkt = tmp;
}
if ((s->flags & AVFMT_FLAG_DISCARD_CORRUPT) &&
(pkt->flags & AV_PKT_FLAG_CORRUPT)) {
av_log(s, AV_LOG_WARNING,
"Dropped corrupted packet (stream = %d)\n",
pkt->stream_index);
av_packet_unref(pkt);
continue;
}
if (pkt->stream_index >= (unsigned)s->nb_streams) {
av_log(s, AV_LOG_ERROR, "Invalid stream index %d\n", pkt->stream_index);
continue;
}
st = s->streams[pkt->stream_index];
if (update_wrap_reference(s, st, pkt->stream_index, pkt) && st->pts_wrap_behavior == AV_PTS_WRAP_SUB_OFFSET) {
// correct first time stamps to negative values
if (!is_relative(st->first_dts))
st->first_dts = wrap_timestamp(st, st->first_dts);
if (!is_relative(st->start_time))
st->start_time = wrap_timestamp(st, st->start_time);
if (!is_relative(st->cur_dts))
st->cur_dts = wrap_timestamp(st, st->cur_dts);
}
pkt->dts = wrap_timestamp(st, pkt->dts);
pkt->pts = wrap_timestamp(st, pkt->pts);
force_codec_ids(s, st);
/* TODO: audio: time filter; video: frame reordering (pts != dts) */
if (s->use_wallclock_as_timestamps)
pkt->dts = pkt->pts = av_rescale_q(av_gettime(), AV_TIME_BASE_Q, st->time_base);
if (!pktl && st->request_probe <= 0)
return ret;
err = add_to_pktbuf(&s->internal->raw_packet_buffer, pkt,
&s->internal->raw_packet_buffer_end, 0);
if (err)
return err;
s->internal->raw_packet_buffer_remaining_size -= pkt->size;
if ((err = probe_codec(s, st, pkt)) < 0)
return err;
}
}
函数 parse_packet(AVFormatContext *s, AVPacket *pkt, int stream_index)
如果需要解析包数据的话,分析pkt包的数据,并将pkt添加到AVFormatContext *s->internal->parse_queue。
选择哪个分析器哪? 通过调用函数av_parser_init(int codec_id),根据codec_id选择分析器。以h264为例,codec_id为AV_CODEC_ID_H264,所以分析器为ff_h264_parser。
#define REGISTER_PARSER(X, x) \
{ \
extern AVCodecParser ff_##x##_parser; \
if (CONFIG_##X##_PARSER) \
av_register_codec_parser(&ff_##x##_parser); \
}
void avcodec_register_all(void)
{
... ...
/* parsers */
REGISTER_PARSER(AAC, aac);
REGISTER_PARSER(AAC_LATM, aac_latm);
REGISTER_PARSER(AC3, ac3);
REGISTER_PARSER(ADX, adx);
REGISTER_PARSER(BMP, bmp);
REGISTER_PARSER(CAVSVIDEO, cavsvideo);
REGISTER_PARSER(COOK, cook);
REGISTER_PARSER(DCA, dca);
REGISTER_PARSER(DIRAC, dirac);
REGISTER_PARSER(DNXHD, dnxhd);
REGISTER_PARSER(DPX, dpx);
REGISTER_PARSER(DVAUDIO, dvaudio);
REGISTER_PARSER(DVBSUB, dvbsub);
REGISTER_PARSER(DVDSUB, dvdsub);
REGISTER_PARSER(DVD_NAV, dvd_nav);
REGISTER_PARSER(FLAC, flac);
REGISTER_PARSER(G729, g729);
REGISTER_PARSER(GSM, gsm);
REGISTER_PARSER(H261, h261);
REGISTER_PARSER(H263, h263);
REGISTER_PARSER(H264, h264);
REGISTER_PARSER(HEVC, hevc);
REGISTER_PARSER(MJPEG, mjpeg);
REGISTER_PARSER(MLP, mlp);
REGISTER_PARSER(MPEG4VIDEO, mpeg4video);
REGISTER_PARSER(MPEGAUDIO, mpegaudio);
REGISTER_PARSER(MPEGVIDEO, mpegvideo);
REGISTER_PARSER(OPUS, opus);
REGISTER_PARSER(PNG, png);
REGISTER_PARSER(PNM, pnm);
REGISTER_PARSER(RV30, rv30);
REGISTER_PARSER(RV40, rv40);
REGISTER_PARSER(TAK, tak);
REGISTER_PARSER(VC1, vc1);
REGISTER_PARSER(VORBIS, vorbis);
REGISTER_PARSER(VP3, vp3);
REGISTER_PARSER(VP8, vp8);
REGISTER_PARSER(VP9, vp9);
}
read_frame_internal(AVFormatContext *s, AVPacket *pkt)函数pkt数据获取
AVFormatContext *s->streams[index]->need_parsing 或者s->streams[index]->parser为空时,函数ff_read_packet(AVFormatContext *s, AVPacket *pkt)获取到pkt内容。
或者通过函数 parse_packet(AVFormatContext *s, AVPacket *pkt, int stream_index),pkt指针指向的数据存储到AVFormatContext *s->internal->parse_queue。然后调用函数
read_from_packet_buffer(&s->internal->parse_queue, &s->internal->parse_queue_end, pkt);
static int read_from_packet_buffer(AVPacketList **pkt_buffer,
AVPacketList **pkt_buffer_end,
AVPacket *pkt)
{
AVPacketList *pktl;
av_assert0(*pkt_buffer);
pktl = *pkt_buffer;
*pkt = pktl->pkt;
*pkt_buffer = pktl->next;
if (!pktl->next)
*pkt_buffer_end = NULL;
av_freep(&pktl);
return 0;
}
总结:
函数read_frame_internal()主要作用为:
从指针AVFormatContext *pb读取音频或者视频数据,保存到pkt->data,同时得到音视频的编解码格式。