本文所使用的是FFmpeg n4.4的源码,所有分析均来自博主瞎猜,如果有误,欢迎批评指正。
这个函数太难分析了,太复杂了,慢慢补全吧~
先看一下FFmpeg是怎么定义avformat_find_stream_info函数的
/**
* Read packets of a media file to get stream information. This
* is useful for file formats with no headers such as MPEG. This
* function also computes the real framerate in case of MPEG-2 repeat
* frame mode.
* The logical file position is not changed by this function;
* examined packets may be buffered for later processing.
*
* @param ic media file handle
* @param options If non-NULL, an ic.nb_streams long array of pointers to
* dictionaries, where i-th member contains options for
* codec corresponding to i-th stream.
* On return each dictionary will be filled with options that were not found.
* @return >=0 if OK, AVERROR_xxx on error
*
* @note this function isn't guaranteed to open all the codecs, so
* options being non-empty at return is a perfectly normal behavior.
*
* @todo Let the user decide somehow what information is needed so that
* we do not waste time getting stuff the user does not need.
*/
int avformat_find_stream_info(AVFormatContext *ic, AVDictionary **options);
通过从媒体文件中读取部分packet,来获取流的信息。有一些文件格式没有头,比如说MPEG格式的,这个时候,这个函数就很有用,因为它可以从读取到的包中获得到流的信息。可以获得MPEG-2 的repeat mode下的真实帧率。 (MPEG-2 支持对于大量静止的画面设置 repeat mode,重复的帧不用编码和存储,可以减少体积)。并且读取的这些包都会被缓存起来,等待下次使用。
在用avformat_open_input初始化AVFormatContext的时候,只是通过解析封装体结构实现的,比如MP4类型,avformat_open_input会解析所有的box,但是如果box缺失或者通过单纯解析box无法了解的信息,比如pix_fmt(像素格式)等,就需要读取甚至解码部分的AVPacket来完成。
总而言之,这个函数的作用就如函数名所讲avformat_find_stream_info,找到流相关的信息。
avformat_find_stream_info的源码比较长,有好几百行,下面分段来介绍这些功能。
int avformat_find_stream_info(AVFormatContext *ic, AVDictionary **options)
{
int i, count = 0, ret = 0, j;
int64_t read_size;
AVStream *st;
AVCodecContext *avctx;
AVPacket *pkt1 = ic->internal->pkt;
int64_t old_offset = avio_tell(ic->pb);
// new streams might appear, no options for those
int orig_nb_streams = ic->nb_streams;
int flush_codecs;
int64_t max_analyze_duration = ic->max_analyze_duration;
int64_t max_stream_analyze_duration;
int64_t max_subtitle_analyze_duration;
int64_t probesize = ic->probesize;
int eof_reached = 0;
int *missing_streams = av_opt_ptr(ic->iformat->priv_class, ic->priv_data, "missing_streams");
flush_codecs = probesize > 0;
av_opt_set(ic, "skip_clear", "1", AV_OPT_SEARCH_CHILDREN);
// 开始的一段,就是设置本次探测的最大时长
// 首帧秒开等需要立马显示的可以减少这里的时间限制。
max_stream_analyze_duration = max_analyze_duration;
max_subtitle_analyze_duration = max_analyze_duration;
if (!max_analyze_duration) {
max_stream_analyze_duration =
max_analyze_duration = 5*AV_TIME_BASE; //默认是5s
max_subtitle_analyze_duration = 30*AV_TIME_BASE;
if (!strcmp(ic->iformat->name, "flv")) // flv格式默认是90s
max_stream_analyze_duration = 90*AV_TIME_BASE;
if (!strcmp(ic->iformat->name, "mpeg") || !strcmp(ic->iformat->name, "mpegts"))
max_stream_analyze_duration = 7*AV_TIME_BASE;
}
if (ic->pb)
av_log(ic, AV_LOG_DEBUG, "Before avformat_find_stream_info() pos: %"PRId64" bytes read:%"PRId64" seeks:%d nb_streams:%d\n",
avio_tell(ic->pb), ic->pb->bytes_read, ic->pb->seek_count, ic->nb_streams);
这个一段最主要就是设置探测时长。
第一遍循环:
遍历一遍所有的AVStream,然后根据格式设置设置AVCodecContext,并打开对应的AVCodec
for (i = 0; i < ic->nb_streams; i++) {
const AVCodec *codec;
AVDictionary *thread_opt = NULL;
st = ic->streams[i];
avctx = st->internal->avctx;
if (st->codecpar->codec_type == AVMEDIA_TYPE_VIDEO ||
st->codecpar->codec_type == AVMEDIA_TYPE_SUBTITLE) {
/* if (!st->time_base.num)
st->time_base = */
//根据从容器中获得的timebase,先设置一下AVCodecContext的timbase
if (!avctx->time_base.num)
avctx->time_base = st->time_base;
}
/* check if the caller has overridden the codec id */
#if FF_API_LAVF_AVCTX
FF_DISABLE_DEPRECATION_WARNINGS
if (st->codec->codec_id != st->internal->orig_codec_id) {
st->codecpar->codec_id = st->codec->codec_id;
st->codecpar->codec_type = st->codec->codec_type;
st->internal->orig_codec_id = st->codec->codec_id;
}
FF_ENABLE_DEPRECATION_WARNINGS
#endif
// 初始化AVCodecParserContext, need_parsing参数是在read_header的时候设置的
// AVCodecParserContext是类似于AVCodecContext的存在,只不过AVCodecParserContext是专门来解析packet,然后把从packet中得到的info设置到AVCodecContext上,而AVCodecContext是利用存在的信息,解码packet
// AVCodecContext中编码相关的信息,基本都是从AVCodecParserContext得到的
// only for the split stuff
if (!st->parser && !(ic->flags & AVFMT_FLAG_NOPARSE) && st->internal->request_probe <= 0) {
//parse也是根据编码类型设置的,h264有自己专门的parse,类似解码器
st->parser = av_parser_init(st->codecpar->codec_id);
if (st->parser) {
if (st->need_parsing == AVSTREAM_PARSE_HEADERS) {
st->parser->flags |= PARSER_FLAG_COMPLETE_FRAMES;
} else if (st->need_parsing == AVSTREAM_PARSE_FULL_RAW) {
st->parser->flags |= PARSER_FLAG_USE_CODEC_TS;
}
} else if (st->need_parsing) {
av_log(ic, AV_LOG_VERBOSE, "parser not found for codec "
"%s, packets or times may be invalid.\n",
avcodec_get_name(st->codecpar->codec_id));
}
}
if (st->codecpar->codec_id != st->internal->orig_codec_id)
st->internal->orig_codec_id = st->codecpar->codec_id;
// 设置codec参数
ret = avcodec_parameters_to_context(avctx, st->codecpar);
if (ret < 0)
goto find_stream_info_err;
if (st->internal->request_probe <= 0)
st->internal->avctx_inited = 1;
// 根据容器中的记录的流格式,找到对应的解码器
codec = find_probe_decoder(ic, st, st->codecpar->codec_id);
/* Force thread count to 1 since the H.264 decoder will not extract
* SPS and PPS to extradata during multi-threaded decoding. */
av_dict_set(options ? &options[i] : &thread_opt, "threads", "1", 0);
/* Force lowres to 0. The decoder might reduce the video size by the
* lowres factor, and we don't want that propagated to the stream's
* codecpar */
av_dict_set(options ? &options[i] : &thread_opt, "lowres", "0", 0);
if (ic->codec_whitelist)
av_dict_set(options ? &options[i] : &thread_opt, "codec_whitelist", ic->codec_whitelist, 0);
/* Ensure that subtitle_header is properly set. */
if (st->codecpar->codec_type == AVMEDIA_TYPE_SUBTITLE
&& codec && !avctx->codec) {
if (avcodec_open2(avctx, codec, options ? &options[i] : &thread_opt) < 0)
av_log(ic, AV_LOG_WARNING,
"Failed to open codec in %s\n",__FUNCTION__);
}
// Try to just open decoders, in case this is enough to get parameters.
// 上面找到codec之后,这里就open 这个codec
if (!has_codec_parameters(st, NULL) && st->internal->request_probe <= 0) {
if (codec && !avctx->codec)
if (avcodec_open2(avctx, codec, options ? &options[i] : &thread_opt) < 0)
av_log(ic, AV_LOG_WARNING,
"Failed to open codec in %s\n",__FUNCTION__);
}
if (!options)
av_dict_free(&thread_opt);
}
这一段最主要就是根据read_header时获得的编码参数设置AVCodecContext,然后打开对应的解码器AVCodec 。
下面还是一段遍历, 这一段就简单多了,初始化这些值,这些会在接下来的计算中使用。
for (i = 0; i < ic->nb_streams; i++) {
#if FF_API_R_FRAME_RATE
ic->streams[i]->internal->info->last_dts = AV_NOPTS_VALUE;
#endif
ic->streams[i]->internal->info->fps_first_dts = AV_NOPTS_VALUE;
ic->streams[i]->internal->info->fps_last_dts = AV_NOPTS_VALUE;
}
第二遍循环:
经过上面的第一遍循环,已经打开的解码器,但是还没有从实际的媒体Packet中获取宽高 ,fps等信息,所以下来需要读取部分packet,根据需要解码,然后从读的packet和解码得到的frame中获取更多的参数信息,然后填充到AVCodecContext。
for (;;) {
const AVPacket *pkt;
int analyzed_all_streams;
if (ff_check_interrupt(&ic->interrupt_callback)) {
ret = AVERROR_EXIT;
av_log(ic, AV_LOG_DEBUG, "interrupted\n");
break;
}
/* check if one codec still needs to be handled */
for (i = 0; i < ic->nb_streams; i++) {
int fps_analyze_framecount = 20;
int count;
st = ic->streams[i];
if (!has_codec_parameters(st, NULL))
break;
/* If the timebase is coarse (like the usual millisecond precision
* of mkv), we need to analyze more frames to reliably arrive at
* the correct fps. */
if (av_q2d(st->time_base) > 0.0005)
fps_analyze_framecount *= 2;
if (!tb_unreliable(st->internal->avctx))
fps_analyze_framecount = 0;
if (ic->fps_probe_size >= 0)
fps_analyze_framecount = ic->fps_probe_size;
if (st->disposition & AV_DISPOSITION_ATTACHED_PIC)
fps_analyze_framecount = 0;
/* variable fps and no guess at the real fps */
count = (ic->iformat->flags & AVFMT_NOTIMESTAMPS) ?
st->internal->info->codec_info_duration_fields/2 :
st->internal->info->duration_count;
if (!(st->r_frame_rate.num && st->avg_frame_rate.num) &&
st->codecpar->codec_type == AVMEDIA_TYPE_VIDEO) {
if (count < fps_analyze_framecount)
break;
}
// Look at the first 3 frames if there is evidence of frame delay
// but the decoder delay is not set.
if (st->internal->info->frame_delay_evidence && count < 2 && st->internal->avctx->has_b_frames == 0)
break;
if (!st->internal->avctx->extradata &&
(!st->internal->extract_extradata.inited ||
st->internal->extract_extradata.bsf) &&
extract_extradata_check(st))
break;
if (st->first_dts == AV_NOPTS_VALUE &&
!(ic->iformat->flags & AVFMT_NOTIMESTAMPS) &&
st->codec_info_nb_frames < ((st->disposition & AV_DISPOSITION_ATTACHED_PIC) ? 1 : ic->max_ts_probe) &&
(st->codecpar->codec_type == AVMEDIA_TYPE_VIDEO ||
st->codecpar->codec_type == AVMEDIA_TYPE_AUDIO))
break;
}
analyzed_all_streams = 0;
if (!missing_streams || !*missing_streams)
if (i == ic->nb_streams) {
analyzed_all_streams = 1;
/* NOTE: If the format has no header, then we need to read some
* packets to get most of the streams, so we cannot stop here. */
if (!(ic->ctx_flags & AVFMTCTX_NOHEADER)) {
/* If we found the info for all the codecs, we can stop. */
ret = count;
av_log(ic, AV_LOG_DEBUG, "All info found\n");
flush_codecs = 0;
break;
}
}
/* We did not get all the codec info, but we read too much data. */
if (read_size >= probesize) {
ret = count;
av_log(ic, AV_LOG_DEBUG,
"Probe buffer size limit of %"PRId64" bytes reached\n", probesize);
for (i = 0; i < ic->nb_streams; i++)
if (!ic->streams[i]->r_frame_rate.num &&
ic->streams[i]->internal->info->duration_count <= 1 &&
ic->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_VIDEO &&
strcmp(ic->iformat->name, "image2"))
av_log(ic, AV_LOG_WARNING,
"Stream #%d: not enough frames to estimate rate; "
"consider increasing probesize\n", i);
break;
}
/* NOTE: A new stream can be added there if no header in file
* (AVFMTCTX_NOHEADER). */
//读取一个packet, 然后调用上面创建的AVCodecParserContext,解析packet中的内容,比如在h264流中就会根据当前块是否为sps解析宽高,根据其余帧解析时长等。
ret = read_frame_internal(ic, pkt1);
if (ret == AVERROR(EAGAIN))
continue;
if (ret < 0) {
/* EOF or error*/
eof_reached = 1;
break;
}
if (!(ic->flags & AVFMT_FLAG_NOBUFFER)) {
ret = avpriv_packet_list_put(&ic->internal->packet_buffer,
&ic->internal->packet_buffer_end,
pkt1, NULL, 0);
if (ret < 0)
goto unref_then_goto_end;
pkt = &ic->internal->packet_buffer_end->pkt;
} else {
pkt = pkt1;
}
st = ic->streams[pkt->stream_index];
if (!(st->disposition & AV_DISPOSITION_ATTACHED_PIC))
read_size += pkt->size;
avctx = st->internal->avctx;
if (!st->internal->avctx_inited) {
ret = avcodec_parameters_to_context(avctx, st->codecpar);
if (ret < 0)
goto unref_then_goto_end;
st->internal->avctx_inited = 1;
}
if (pkt->dts != AV_NOPTS_VALUE && st->codec_info_nb_frames > 1) {
/* check for non-increasing dts */
if (st->internal->info->fps_last_dts != AV_NOPTS_VALUE &&
st->internal->info->fps_last_dts >= pkt->dts) {
av_log(ic, AV_LOG_DEBUG,
"Non-increasing DTS in stream %d: packet %d with DTS "
"%"PRId64", packet %d with DTS %"PRId64"\n",
st->index, st->internal->info->fps_last_dts_idx,
st->internal->info->fps_last_dts, st->codec_info_nb_frames,
pkt->dts);
st->internal->info->fps_first_dts =
st->internal->info->fps_last_dts = AV_NOPTS_VALUE;
}
/* Check for a discontinuity in dts. If the difference in dts
* is more than 1000 times the average packet duration in the
* sequence, we treat it as a discontinuity. */
if (st->internal->info->fps_last_dts != AV_NOPTS_VALUE &&
st->internal->info->fps_last_dts_idx > st->internal->info->fps_first_dts_idx &&
(pkt->dts - (uint64_t)st->internal->info->fps_last_dts) / 1000 >
(st->internal->info->fps_last_dts - (uint64_t)st->internal->info->fps_first_dts) /
(st->internal->info->fps_last_dts_idx - st->internal->info->fps_first_dts_idx)) {
av_log(ic, AV_LOG_WARNING,
"DTS discontinuity in stream %d: packet %d with DTS "
"%"PRId64", packet %d with DTS %"PRId64"\n",
st->index, st->internal->info->fps_last_dts_idx,
st->internal->info->fps_last_dts, st->codec_info_nb_frames,
pkt->dts);
st->internal->info->fps_first_dts =
st->internal->info->fps_last_dts = AV_NOPTS_VALUE;
}
/* update stored dts values */
if (st->internal->info->fps_first_dts == AV_NOPTS_VALUE) {
st->internal->info->fps_first_dts = pkt->dts;
st->internal->info->fps_first_dts_idx = st->codec_info_nb_frames;
}
st->internal->info->fps_last_dts = pkt->dts;
st->internal->info->fps_last_dts_idx = st->codec_info_nb_frames;
}
if (st->codec_info_nb_frames>1) {
int64_t t = 0;
int64_t limit;
if (st->time_base.den > 0)
t = av_rescale_q(st->internal->info->codec_info_duration, st->time_base, AV_TIME_BASE_Q);
if (st->avg_frame_rate.num > 0)
t = FFMAX(t, av_rescale_q(st->codec_info_nb_frames, av_inv_q(st->avg_frame_rate), AV_TIME_BASE_Q));
if ( t == 0
&& st->codec_info_nb_frames>30
&& st->internal->info->fps_first_dts != AV_NOPTS_VALUE
&& st->internal->info->fps_last_dts != AV_NOPTS_VALUE) {
int64_t dur = av_sat_sub64(st->internal->info->fps_last_dts, st->internal->info->fps_first_dts);
t = FFMAX(t, av_rescale_q(dur, st->time_base, AV_TIME_BASE_Q));
}
if (analyzed_all_streams) limit = max_analyze_duration;
else if (avctx->codec_type == AVMEDIA_TYPE_SUBTITLE) limit = max_subtitle_analyze_duration;
else limit = max_stream_analyze_duration;
if (t >= limit) {
av_log(ic, AV_LOG_VERBOSE, "max_analyze_duration %"PRId64" reached at %"PRId64" microseconds st:%d\n",
limit,
t, pkt->stream_index);
if (ic->flags & AVFMT_FLAG_NOBUFFER)
av_packet_unref(pkt1);
break;
}
if (pkt->duration) {
if (avctx->codec_type == AVMEDIA_TYPE_SUBTITLE && pkt->pts != AV_NOPTS_VALUE && st->start_time != AV_NOPTS_VALUE && pkt->pts >= st->start_time) {
st->internal->info->codec_info_duration = FFMIN(pkt->pts - st->start_time, st->internal->info->codec_info_duration + pkt->duration);
} else
st->internal->info->codec_info_duration += pkt->duration;
st->internal->info->codec_info_duration_fields += st->parser && st->need_parsing && avctx->ticks_per_frame ==2 ? st->parser->repeat_pict + 1 : 2;
}
}
if (st->codecpar->codec_type == AVMEDIA_TYPE_VIDEO) {
#if FF_API_R_FRAME_RATE
ff_rfps_add_frame(ic, st, pkt->dts);
#endif
if (pkt->dts != pkt->pts && pkt->dts != AV_NOPTS_VALUE && pkt->pts != AV_NOPTS_VALUE)
st->internal->info->frame_delay_evidence = 1;
}
if (!st->internal->avctx->extradata) {
ret = extract_extradata(st, pkt);
if (ret < 0)
goto unref_then_goto_end;
}
/* If still no information, we try to open the codec and to
* decompress the frame. We try to avoid that in most cases as
* it takes longer and uses more memory. For MPEG-4, we need to
* decompress for QuickTime.
*
* If AV_CODEC_CAP_CHANNEL_CONF is set this will force decoding of at
* least one frame of codec data, this makes sure the codec initializes
* the channel configuration and does not only trust the values from
* the container. */
try_decode_frame(ic, st, pkt,
(options && i < orig_nb_streams) ? &options[i] : NULL);
if (ic->flags & AVFMT_FLAG_NOBUFFER)
av_packet_unref(pkt1);
st->codec_info_nb_frames++;
count++;
}
//上面还没分析完