参考链接
avformat_find_stream_info()
- 该函数可以读取一部分视音频数据并且获得一些相关的信息
- avformat_find_stream_info()的声明位于libavformat\avformat.h,如下所示。
/**
* 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);
- 简单解释一下它的参数的含义:
- ic:输入的AVFormatContext。
- options:额外的选项,目前没有深入研究过。
- 函数正常执行后返回值大于等于0。
函数调用关系图
代码
int avformat_find_stream_info(AVFormatContext *ic, AVDictionary **options)
{
FFFormatContext *const si = ffformatcontext(ic);
int count = 0, ret = 0;
int64_t read_size;
AVPacket *pkt1 = si->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_int(ic, "skip_clear", 1, AV_OPT_SEARCH_CHILDREN);
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;
max_subtitle_analyze_duration = 30*AV_TIME_BASE;
if (!strcmp(ic->iformat->name, "flv"))
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) {
FFIOContext *const ctx = ffiocontext(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), ctx->bytes_read, ctx->seek_count, ic->nb_streams);
}
for (unsigned i = 0; i < ic->nb_streams; i++) {
const AVCodec *codec;
AVDictionary *thread_opt = NULL;
AVStream *const st = ic->streams[i];
FFStream *const sti = ffstream(st);
AVCodecContext *const avctx = sti->avctx;
if (st->codecpar->codec_type == AVMEDIA_TYPE_VIDEO ||
st->codecpar->codec_type == AVMEDIA_TYPE_SUBTITLE) {
/* if (!st->time_base.num)
st->time_base = */
if (!avctx->time_base.num)
avctx->time_base = st->time_base;
}
/* check if the caller has overridden the codec id */
// only for the split stuff
if (!sti->parser && !(ic->flags & AVFMT_FLAG_NOPARSE) && sti->request_probe <= 0) {
sti->parser = av_parser_init(st->codecpar->codec_id);
if (sti->parser) {
if (sti->need_parsing == AVSTREAM_PARSE_HEADERS) {
sti->parser->flags |= PARSER_FLAG_COMPLETE_FRAMES;
} else if (sti->need_parsing == AVSTREAM_PARSE_FULL_RAW) {
sti->parser->flags |= PARSER_FLAG_USE_CODEC_TS;
}
} else if (sti->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));
}
}
ret = avcodec_parameters_to_context(avctx, st->codecpar);
if (ret < 0)
goto find_stream_info_err;
if (sti->request_probe <= 0)
sti->avctx_inited = 1;
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);
// Try to just open decoders, in case this is enough to get parameters.
// Also ensure that subtitle_header is properly set.
if (!has_codec_parameters(st, NULL) && sti->request_probe <= 0 ||
st->codecpar->codec_type == AVMEDIA_TYPE_SUBTITLE) {
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);
}
read_size = 0;
for (;;) {
const AVPacket *pkt;
AVStream *st;
FFStream *sti;
AVCodecContext *avctx;
int analyzed_all_streams;
unsigned i;
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++) {
AVStream *const st = ic->streams[i];
FFStream *const sti = ffstream(st);
int fps_analyze_framecount = 20;
int count;
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(sti->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) ?
sti->info->codec_info_duration_fields/2 :
sti->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 (sti->info->frame_delay_evidence && count < 2 && sti->avctx->has_b_frames == 0)
break;
if (!sti->avctx->extradata &&
(!sti->extract_extradata.inited || sti->extract_extradata.bsf) &&
extract_extradata_check(st))
break;
if (sti->first_dts == AV_NOPTS_VALUE &&
!(ic->iformat->flags & AVFMT_NOTIMESTAMPS) &&
sti->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 (unsigned i = 0; i < ic->nb_streams; i++) {
AVStream *const st = ic->streams[i];
FFStream *const sti = ffstream(st);
if (!st->r_frame_rate.num &&
sti->info->duration_count <= 1 &&
st->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). */
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(&si->packet_buffer,
pkt1, NULL, 0);
if (ret < 0)
goto unref_then_goto_end;
pkt = &si->packet_buffer.tail->pkt;
} else {
pkt = pkt1;
}
st = ic->streams[pkt->stream_index];
sti = ffstream(st);
if (!(st->disposition & AV_DISPOSITION_ATTACHED_PIC))
read_size += pkt->size;
avctx = sti->avctx;
if (!sti->avctx_inited) {
ret = avcodec_parameters_to_context(avctx, st->codecpar);
if (ret < 0)
goto unref_then_goto_end;
sti->avctx_inited = 1;
}
if (pkt->dts != AV_NOPTS_VALUE && sti->codec_info_nb_frames > 1) {
/* check for non-increasing dts */
if (sti->info->fps_last_dts != AV_NOPTS_VALUE &&
sti->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, sti->info->fps_last_dts_idx,
sti->info->fps_last_dts, sti->codec_info_nb_frames,
pkt->dts);
sti->info->fps_first_dts =
sti->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 (sti->info->fps_last_dts != AV_NOPTS_VALUE &&
sti->info->fps_last_dts_idx > sti->info->fps_first_dts_idx &&
(pkt->dts - (uint64_t)sti->info->fps_last_dts) / 1000 >
(sti->info->fps_last_dts - (uint64_t)sti->info->fps_first_dts) /
(sti->info->fps_last_dts_idx - sti->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, sti->info->fps_last_dts_idx,
sti->info->fps_last_dts, sti->codec_info_nb_frames,
pkt->dts);
sti->info->fps_first_dts =
sti->info->fps_last_dts = AV_NOPTS_VALUE;
}
/* update stored dts values */
if (sti->info->fps_first_dts == AV_NOPTS_VALUE) {
sti->info->fps_first_dts = pkt->dts;
sti->info->fps_first_dts_idx = sti->codec_info_nb_frames;
}
sti->info->fps_last_dts = pkt->dts;
sti->info->fps_last_dts_idx = sti->codec_info_nb_frames;
}
if (sti->codec_info_nb_frames > 1) {
int64_t t = 0;
int64_t limit;
if (st->time_base.den > 0)
t = av_rescale_q(sti->info->codec_info_duration, st->time_base, AV_TIME_BASE_Q);
if (st->avg_frame_rate.num > 0)
t = FFMAX(t, av_rescale_q(sti->codec_info_nb_frames, av_inv_q(st->avg_frame_rate), AV_TIME_BASE_Q));
if ( t == 0
&& sti->codec_info_nb_frames > 30
&& sti->info->fps_first_dts != AV_NOPTS_VALUE
&& sti->info->fps_last_dts != AV_NOPTS_VALUE) {
int64_t dur = av_sat_sub64(sti->info->fps_last_dts, sti->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 > 0) {
if (avctx->codec_type == AVMEDIA_TYPE_SUBTITLE && pkt->pts != AV_NOPTS_VALUE && st->start_time != AV_NOPTS_VALUE && pkt->pts >= st->start_time
&& (uint64_t)pkt->pts - st->start_time < INT64_MAX
) {
sti->info->codec_info_duration = FFMIN(pkt->pts - st->start_time, sti->info->codec_info_duration + pkt->duration);
} else
sti->info->codec_info_duration += pkt->duration;
sti->info->codec_info_duration_fields += sti->parser && sti->need_parsing && avctx->ticks_per_frame == 2
? sti->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)
sti->info->frame_delay_evidence = 1;
}
if (!sti->avctx->extradata) {
ret = extract_extradata(si, 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);
sti->codec_info_nb_frames++;
count++;
}
if (eof_reached) {
for (unsigned stream_index = 0; stream_index < ic->nb_streams; stream_index++) {
AVStream *const st = ic->streams[stream_index];
AVCodecContext *const avctx = ffstream(st)->avctx;
if (!has_codec_parameters(st, NULL)) {
const AVCodec *codec = find_probe_decoder(ic, st, st->codecpar->codec_id);
if (codec && !avctx->codec) {
AVDictionary *opts = NULL;
if (ic->codec_whitelist)
av_dict_set(&opts, "codec_whitelist", ic->codec_whitelist, 0);
if (avcodec_open2(avctx, codec, (options && stream_index < orig_nb_streams) ? &options[stream_index] : &opts) < 0)
av_log(ic, AV_LOG_WARNING,
"Failed to open codec in %s\n",__FUNCTION__);
av_dict_free(&opts);
}
}
// EOF already reached while reading the stream above.
// So continue with reoordering DTS with whatever delay we have.
if (si->packet_buffer.head && !has_decode_delay_been_guessed(st)) {
update_dts_from_pts(ic, stream_index, si->packet_buffer.head);
}
}
}
if (flush_codecs) {
AVPacket *empty_pkt = si->pkt;
int err = 0;
av_packet_unref(empty_pkt);
for (unsigned i = 0; i < ic->nb_streams; i++) {
AVStream *const st = ic->streams[i];
FFStream *const sti = ffstream(st);
/* flush the decoders */
if (sti->info->found_decoder == 1) {
err = try_decode_frame(ic, st, empty_pkt,
(options && i < orig_nb_streams)
? &options[i] : NULL);
if (err < 0) {
av_log(ic, AV_LOG_INFO,
"decoding for stream %d failed\n", st->index);
}
}
}
}
ff_rfps_calculate(ic);
for (unsigned i = 0; i < ic->nb_streams; i++) {
AVStream *const st = ic->streams[i];
FFStream *const sti = ffstream(st);
AVCodecContext *const avctx = sti->avctx;
if (avctx->codec_type == AVMEDIA_TYPE_VIDEO) {
if (avctx->codec_id == AV_CODEC_ID_RAWVIDEO && !avctx->codec_tag && !avctx->bits_per_coded_sample) {
uint32_t tag= avcodec_pix_fmt_to_codec_tag(avctx->pix_fmt);
if (avpriv_pix_fmt_find(PIX_FMT_LIST_RAW, tag) == avctx->pix_fmt)
avctx->codec_tag= tag;
}
/* estimate average framerate if not set by demuxer */
if (sti->info->codec_info_duration_fields &&
!st->avg_frame_rate.num &&
sti->info->codec_info_duration) {
int best_fps = 0;
double best_error = 0.01;
AVRational codec_frame_rate = avctx->framerate;
if (sti->info->codec_info_duration >= INT64_MAX / st->time_base.num / 2||
sti->info->codec_info_duration_fields >= INT64_MAX / st->time_base.den ||
sti->info->codec_info_duration < 0)
continue;
av_reduce(&st->avg_frame_rate.num, &st->avg_frame_rate.den,
sti->info->codec_info_duration_fields * (int64_t) st->time_base.den,
sti->info->codec_info_duration * 2 * (int64_t) st->time_base.num, 60000);
/* Round guessed framerate to a "standard" framerate if it's
* within 1% of the original estimate. */
for (int j = 0; j < MAX_STD_TIMEBASES; j++) {
AVRational std_fps = { get_std_framerate(j), 12 * 1001 };
double error = fabs(av_q2d(st->avg_frame_rate) /
av_q2d(std_fps) - 1);
if (error < best_error) {
best_error = error;
best_fps = std_fps.num;
}
if (si->prefer_codec_framerate && codec_frame_rate.num > 0 && codec_frame_rate.den > 0) {
error = fabs(av_q2d(codec_frame_rate) /
av_q2d(std_fps) - 1);
if (error < best_error) {
best_error = error;
best_fps = std_fps.num;
}
}
}
if (best_fps)
av_reduce(&st->avg_frame_rate.num, &st->avg_frame_rate.den,
best_fps, 12 * 1001, INT_MAX);
}
if (!st->r_frame_rate.num) {
if ( avctx->time_base.den * (int64_t) st->time_base.num
<= avctx->time_base.num * (uint64_t)avctx->ticks_per_frame * st->time_base.den) {
av_reduce(&st->r_frame_rate.num, &st->r_frame_rate.den,
avctx->time_base.den, (int64_t)avctx->time_base.num * avctx->ticks_per_frame, INT_MAX);
} else {
st->r_frame_rate.num = st->time_base.den;
st->r_frame_rate.den = st->time_base.num;
}
}
if (sti->display_aspect_ratio.num && sti->display_aspect_ratio.den) {
AVRational hw_ratio = { avctx->height, avctx->width };
st->sample_aspect_ratio = av_mul_q(sti->display_aspect_ratio,
hw_ratio);
}
} else if (avctx->codec_type == AVMEDIA_TYPE_AUDIO) {
if (!avctx->bits_per_coded_sample)
avctx->bits_per_coded_sample =
av_get_bits_per_sample(avctx->codec_id);
// set stream disposition based on audio service type
switch (avctx->audio_service_type) {
case AV_AUDIO_SERVICE_TYPE_EFFECTS:
st->disposition = AV_DISPOSITION_CLEAN_EFFECTS;
break;
case AV_AUDIO_SERVICE_TYPE_VISUALLY_IMPAIRED:
st->disposition = AV_DISPOSITION_VISUAL_IMPAIRED;
break;
case AV_AUDIO_SERVICE_TYPE_HEARING_IMPAIRED:
st->disposition = AV_DISPOSITION_HEARING_IMPAIRED;
break;
case AV_AUDIO_SERVICE_TYPE_COMMENTARY:
st->disposition = AV_DISPOSITION_COMMENT;
break;
case AV_AUDIO_SERVICE_TYPE_KARAOKE:
st->disposition = AV_DISPOSITION_KARAOKE;
break;
}
}
}
if (probesize)
estimate_timings(ic, old_offset);
av_opt_set_int(ic, "skip_clear", 0, AV_OPT_SEARCH_CHILDREN);
if (ret >= 0 && ic->nb_streams)
/* We could not have all the codec parameters before EOF. */
ret = -1;
for (unsigned i = 0; i < ic->nb_streams; i++) {
AVStream *const st = ic->streams[i];
FFStream *const sti = ffstream(st);
const char *errmsg;
/* if no packet was ever seen, update context now for has_codec_parameters */
if (!sti->avctx_inited) {
if (st->codecpar->codec_type == AVMEDIA_TYPE_AUDIO &&
st->codecpar->format == AV_SAMPLE_FMT_NONE)
st->codecpar->format = sti->avctx->sample_fmt;
ret = avcodec_parameters_to_context(sti->avctx, st->codecpar);
if (ret < 0)
goto find_stream_info_err;
}
if (!has_codec_parameters(st, &errmsg)) {
char buf[256];
avcodec_string(buf, sizeof(buf), sti->avctx, 0);
av_log(ic, AV_LOG_WARNING,
"Could not find codec parameters for stream %d (%s): %s\n"
"Consider increasing the value for the 'analyzeduration' (%"PRId64") and 'probesize' (%"PRId64") options\n",
i, buf, errmsg, ic->max_analyze_duration, ic->probesize);
} else {
ret = 0;
}
}
ret = compute_chapters_end(ic);
if (ret < 0)
goto find_stream_info_err;
/* update the stream parameters from the internal codec contexts */
for (unsigned i = 0; i < ic->nb_streams; i++) {
AVStream *const st = ic->streams[i];
FFStream *const sti = ffstream(st);
if (sti->avctx_inited) {
ret = avcodec_parameters_from_context(st->codecpar, sti->avctx);
if (ret < 0)
goto find_stream_info_err;
ret = add_coded_side_data(st, sti->avctx);
if (ret < 0)
goto find_stream_info_err;
}
sti->avctx_inited = 0;
}
find_stream_info_err:
for (unsigned i = 0; i < ic->nb_streams; i++) {
AVStream *const st = ic->streams[i];
FFStream *const sti = ffstream(st);
if (sti->info) {
av_freep(&sti->info->duration_error);
av_freep(&sti->info);
}
avcodec_close(sti->avctx);
// FIXME: avcodec_close() frees AVOption settable fields which includes ch_layout,
// so we need to restore it.
av_channel_layout_copy(&sti->avctx->ch_layout, &st->codecpar->ch_layout);
av_bsf_free(&sti->extract_extradata.bsf);
}
if (ic->pb) {
FFIOContext *const ctx = ffiocontext(ic->pb);
av_log(ic, AV_LOG_DEBUG, "After avformat_find_stream_info() pos: %"PRId64" bytes read:%"PRId64" seeks:%d frames:%d\n",
avio_tell(ic->pb), ctx->bytes_read, ctx->seek_count, count);
}
return ret;
unref_then_goto_end:
av_packet_unref(pkt1);
goto find_stream_info_err;
}
- 由于avformat_find_stream_info()代码比较长,难以全部分析,在这里只能简单记录一下它的要点。
- 该函数主要用于给每个媒体流(音频/视频)的AVStream结构体赋值。
- 我们大致浏览一下这个函数的代码,会发现它其实已经实现了解码器的查找,解码器的打开,视音频帧的读取,视音频帧的解码等工作。
- 换句话说,该函数实际上已经“走通”的解码的整个流程。
- 下面看一下除了成员变量赋值之外,该函数的几个关键流程。
- 1.查找解码器:find_decoder() 此函数已经弃用;新版的好像使用的是find_probe_decoder
- 2.打开解码器:avcodec_open2()
- 3.读取完整的一帧压缩编码的数据:read_frame_internal() 注:av_read_frame()内部实际上就是调用的read_frame_internal()。
- 4.解码一些压缩编码数据:try_decode_frame()
- 下面选择上述流程中几个关键函数的代码简单看一下。
find_probe_decoder
static const AVCodec *find_probe_decoder(AVFormatContext *s, const AVStream *st, enum AVCodecID codec_id)
{
const AVCodec *codec;
#if CONFIG_H264_DECODER
/* Other parts of the code assume this decoder to be used for h264,
* so force it if possible. */
if (codec_id == AV_CODEC_ID_H264)
return avcodec_find_decoder_by_name("h264");
#endif
codec = ff_find_decoder(s, st, codec_id);
if (!codec)
return NULL;
if (codec->capabilities & AV_CODEC_CAP_AVOID_PROBING) {
const AVCodec *probe_codec = NULL;
void *iter = NULL;
while ((probe_codec = av_codec_iterate(&iter))) {
if (probe_codec->id == codec->id &&
av_codec_is_decoder(probe_codec) &&
!(probe_codec->capabilities & (AV_CODEC_CAP_AVOID_PROBING | AV_CODEC_CAP_EXPERIMENTAL))) {
return probe_codec;
}
}
}
return codec;
}
ff_find_decoder
- ff_find_decoder 函数和先前的find_decoder()函数雷同,用于找到合适的解码器,它的定义如下所示。
const AVCodec *ff_find_decoder(AVFormatContext *s, const AVStream *st,
enum AVCodecID codec_id)
{
switch (st->codecpar->codec_type) {
case AVMEDIA_TYPE_VIDEO:
if (s->video_codec) return s->video_codec;
break;
case AVMEDIA_TYPE_AUDIO:
if (s->audio_codec) return s->audio_codec;
break;
case AVMEDIA_TYPE_SUBTITLE:
if (s->subtitle_codec) return s->subtitle_codec;
break;
}
return avcodec_find_decoder(codec_id);
}
- 从代码中可以看出,如果指定的AVStream已经包含了解码器,则函数什么也不做直接返回。
- 否则调用avcodec_find_decoder()获取解码器。
- avcodec_find_decoder()是一个FFmpeg的API函数,在这里不做详细分析。
avcodec_find_decoder
const AVCodec *avcodec_find_decoder(enum AVCodecID id)
{
return find_codec(id, av_codec_is_decoder);
}
read_frame_internal()
- read_frame_internal()的功能是读取一帧压缩码流数据。
- FFmpeg的API函数av_read_frame()内部调用的就是read_frame_internal()。
- 因此,可以认为read_frame_internal()和av_read_frame()的功能基本上是等同的。
static int read_frame_internal(AVFormatContext *s, AVPacket *pkt)
{
FFFormatContext *const si = ffformatcontext(s);
int ret, got_packet = 0;
AVDictionary *metadata = NULL;
while (!got_packet && !si->parse_queue.head) {
AVStream *st;
FFStream *sti;
/* read next packet */
ret = ff_read_packet(s, pkt);
if (ret < 0) {
if (ret == AVERROR(EAGAIN))
return ret;
/* flush the parsers */
for (unsigned i = 0; i < s->nb_streams; i++) {
AVStream *const st = s->streams[i];
FFStream *const sti = ffstream(st);
if (sti->parser && sti->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];
sti = ffstream(st);
st->event_flags |= AVSTREAM_EVENT_FLAG_NEW_PACKETS;
/* update context if required */
if (sti->need_context_update) {
if (avcodec_is_open(sti->avctx)) {
av_log(s, AV_LOG_DEBUG, "Demuxer context update while decoder is open, closing and trying to re-open\n");
avcodec_close(sti->avctx);
sti->info->found_decoder = 0;
}
/* close parser, because it depends on the codec */
if (sti->parser && sti->avctx->codec_id != st->codecpar->codec_id) {
av_parser_close(sti->parser);
sti->parser = NULL;
}
ret = avcodec_parameters_to_context(sti->avctx, st->codecpar);
if (ret < 0) {
av_packet_unref(pkt);
return ret;
}
sti->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 (sti->need_parsing && !sti->parser && !(s->flags & AVFMT_FLAG_NOPARSE)) {
sti->parser = av_parser_init(st->codecpar->codec_id);
if (!sti->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 */
sti->need_parsing = AVSTREAM_PARSE_NONE;
} else if (sti->need_parsing == AVSTREAM_PARSE_HEADERS)
sti->parser->flags |= PARSER_FLAG_COMPLETE_FRAMES;
else if (sti->need_parsing == AVSTREAM_PARSE_FULL_ONCE)
sti->parser->flags |= PARSER_FLAG_ONCE;
else if (sti->need_parsing == AVSTREAM_PARSE_FULL_RAW)
sti->parser->flags |= PARSER_FLAG_USE_CODEC_TS;
}
if (!sti->need_parsing || !sti->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 = sti->avctx->sample_rate;
st->codecpar->bit_rate = sti->avctx->bit_rate;
#if FF_API_OLD_CHANNEL_LAYOUT
FF_DISABLE_DEPRECATION_WARNINGS
st->codecpar->channels = sti->avctx->ch_layout.nb_channels;
st->codecpar->channel_layout = sti->avctx->ch_layout.order == AV_CHANNEL_ORDER_NATIVE ?
sti->avctx->ch_layout.u.mask : 0;
FF_ENABLE_DEPRECATION_WARNINGS
#endif
ret = av_channel_layout_copy(&st->codecpar->ch_layout, &sti->avctx->ch_layout);
if (ret < 0)
return ret;
st->codecpar->codec_id = sti->avctx->codec_id;
} else {
/* free packet */
av_packet_unref(pkt);
}
if (pkt->flags & AV_PKT_FLAG_KEY)
sti->skip_to_keyframe = 0;
if (sti->skip_to_keyframe) {
av_packet_unref(pkt);
got_packet = 0;
}
}
if (!got_packet && si->parse_queue.head)
ret = avpriv_packet_list_get(&si->parse_queue, pkt);
if (ret >= 0) {
AVStream *const st = s->streams[pkt->stream_index];
FFStream *const sti = ffstream(st);
int discard_padding = 0;
if (sti->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);
int64_t duration = ts_to_samples(st, pkt->duration);
int64_t end_sample = sample + duration;
if (duration > 0 && end_sample >= sti->first_discard_sample &&
sample < sti->last_discard_sample)
discard_padding = FFMIN(end_sample - sti->first_discard_sample, duration);
}
if (sti->start_skip_samples && (pkt->pts == 0 || pkt->pts == RELATIVE_TS_BASE))
sti->skip_samples = sti->start_skip_samples;
sti->skip_samples = FFMAX(0, sti->skip_samples);
if (sti->skip_samples || discard_padding) {
uint8_t *p = av_packet_new_side_data(pkt, AV_PKT_DATA_SKIP_SAMPLES, 10);
if (p) {
AV_WL32(p, sti->skip_samples);
AV_WL32(p + 4, discard_padding);
av_log(s, AV_LOG_DEBUG, "demuxer injecting skip %u / discard %u\n",
(unsigned)sti->skip_samples, (unsigned)discard_padding);
}
sti->skip_samples = 0;
}
if (sti->inject_global_side_data) {
for (int i = 0; i < st->nb_side_data; i++) {
const AVPacketSideData *const 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);
}
sti->inject_global_side_data = 0;
}
}
if (!si->metafree) {
int metaret = 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);
}
si->metafree = metaret == AVERROR_OPTION_NOT_FOUND;
}
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;
}
try_decode_frame()
- try_decode_frame()的功能可以从字面上的意思进行理解:“尝试解码一些帧”,它的定义如下所示
/* returns 1 or 0 if or if not decoded data was returned, or a negative error */
static int try_decode_frame(AVFormatContext *s, AVStream *st,
const AVPacket *avpkt, AVDictionary **options)
{
FFStream *const sti = ffstream(st);
AVCodecContext *const avctx = sti->avctx;
const AVCodec *codec;
int got_picture = 1, ret = 0;
AVFrame *frame = av_frame_alloc();
AVSubtitle subtitle;
AVPacket pkt = *avpkt;
int do_skip_frame = 0;
enum AVDiscard skip_frame;
if (!frame)
return AVERROR(ENOMEM);
if (!avcodec_is_open(avctx) &&
sti->info->found_decoder <= 0 &&
(st->codecpar->codec_id != -sti->info->found_decoder || !st->codecpar->codec_id)) {
AVDictionary *thread_opt = NULL;
codec = find_probe_decoder(s, st, st->codecpar->codec_id);
if (!codec) {
sti->info->found_decoder = -st->codecpar->codec_id;
ret = -1;
goto fail;
}
/* 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 : &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 : &thread_opt, "lowres", "0", 0);
if (s->codec_whitelist)
av_dict_set(options ? options : &thread_opt, "codec_whitelist", s->codec_whitelist, 0);
ret = avcodec_open2(avctx, codec, options ? options : &thread_opt);
if (!options)
av_dict_free(&thread_opt);
if (ret < 0) {
sti->info->found_decoder = -avctx->codec_id;
goto fail;
}
sti->info->found_decoder = 1;
} else if (!sti->info->found_decoder)
sti->info->found_decoder = 1;
if (sti->info->found_decoder < 0) {
ret = -1;
goto fail;
}
if (avpriv_codec_get_cap_skip_frame_fill_param(avctx->codec)) {
do_skip_frame = 1;
skip_frame = avctx->skip_frame;
avctx->skip_frame = AVDISCARD_ALL;
}
while ((pkt.size > 0 || (!pkt.data && got_picture)) &&
ret >= 0 &&
(!has_codec_parameters(st, NULL) || !has_decode_delay_been_guessed(st) ||
(!sti->codec_info_nb_frames &&
(avctx->codec->capabilities & AV_CODEC_CAP_CHANNEL_CONF)))) {
got_picture = 0;
if (avctx->codec_type == AVMEDIA_TYPE_VIDEO ||
avctx->codec_type == AVMEDIA_TYPE_AUDIO) {
ret = avcodec_send_packet(avctx, &pkt);
if (ret < 0 && ret != AVERROR(EAGAIN) && ret != AVERROR_EOF)
break;
if (ret >= 0)
pkt.size = 0;
ret = avcodec_receive_frame(avctx, frame);
if (ret >= 0)
got_picture = 1;
if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF)
ret = 0;
} else if (avctx->codec_type == AVMEDIA_TYPE_SUBTITLE) {
ret = avcodec_decode_subtitle2(avctx, &subtitle,
&got_picture, &pkt);
if (got_picture)
avsubtitle_free(&subtitle);
if (ret >= 0)
pkt.size = 0;
}
if (ret >= 0) {
if (got_picture)
sti->nb_decoded_frames++;
ret = got_picture;
}
}
fail:
if (do_skip_frame) {
avctx->skip_frame = skip_frame;
}
av_frame_free(&frame);
return ret;
}
- 从try_decode_frame()的定义可以看出,该函数首先判断视音频流的解码器是否已经打开,如果没有打开的话,先打开相应的解码器。
- 接下来根据视音频流类型的不同,调用不同的解码函数进行解码:。
- 解码的循环会一直持续下去直到满足了while()的所有条件。
while()语句的条件中有一个has_codec_parameters()函数,用于判断AVStream中的成员变量是否都已经设置完毕。该函数在avformat_find_stream_info()中的多个地方被使用过。
has_codec_parameters()
- has_codec_parameters()用于检查AVStream中的成员变量是否都已经设置完毕。
- 函数的定义如下
static int has_codec_parameters(const AVStream *st, const char **errmsg_ptr)
{
const FFStream *const sti = cffstream(st);
const AVCodecContext *const avctx = sti->avctx;
#define FAIL(errmsg) do { \
if (errmsg_ptr) \
*errmsg_ptr = errmsg; \
return 0; \
} while (0)
if ( avctx->codec_id == AV_CODEC_ID_NONE
&& avctx->codec_type != AVMEDIA_TYPE_DATA)
FAIL("unknown codec");
switch (avctx->codec_type) {
case AVMEDIA_TYPE_AUDIO:
if (!avctx->frame_size && determinable_frame_size(avctx))
FAIL("unspecified frame size");
if (sti->info->found_decoder >= 0 &&
avctx->sample_fmt == AV_SAMPLE_FMT_NONE)
FAIL("unspecified sample format");
if (!avctx->sample_rate)
FAIL("unspecified sample rate");
if (!avctx->ch_layout.nb_channels)
FAIL("unspecified number of channels");
if (sti->info->found_decoder >= 0 && !sti->nb_decoded_frames && avctx->codec_id == AV_CODEC_ID_DTS)
FAIL("no decodable DTS frames");
break;
case AVMEDIA_TYPE_VIDEO:
if (!avctx->width)
FAIL("unspecified size");
if (sti->info->found_decoder >= 0 && avctx->pix_fmt == AV_PIX_FMT_NONE)
FAIL("unspecified pixel format");
if (st->codecpar->codec_id == AV_CODEC_ID_RV30 || st->codecpar->codec_id == AV_CODEC_ID_RV40)
if (!st->sample_aspect_ratio.num && !st->codecpar->sample_aspect_ratio.num && !sti->codec_info_nb_frames)
FAIL("no frame in rv30/40 and no sar");
break;
case AVMEDIA_TYPE_SUBTITLE:
if (avctx->codec_id == AV_CODEC_ID_HDMV_PGS_SUBTITLE && !avctx->width)
FAIL("unspecified size");
break;
case AVMEDIA_TYPE_DATA:
if (avctx->codec_id == AV_CODEC_ID_NONE) return 1;
}
return 1;
}
estimate_timings()
- estimate_timings()位于avformat_find_stream_info()最后面,用于估算AVFormatContext以及AVStream的时长duration。
- 它的代码如下所示。
static void estimate_timings(AVFormatContext *ic, int64_t old_offset)
{
int64_t file_size;
/* get the file size, if possible */
if (ic->iformat->flags & AVFMT_NOFILE) {
file_size = 0;
} else {
file_size = avio_size(ic->pb);
file_size = FFMAX(0, file_size);
}
if ((!strcmp(ic->iformat->name, "mpeg") ||
!strcmp(ic->iformat->name, "mpegts")) &&
file_size && (ic->pb->seekable & AVIO_SEEKABLE_NORMAL)) {
/* get accurate estimate from the PTSes */
estimate_timings_from_pts(ic, old_offset);
ic->duration_estimation_method = AVFMT_DURATION_FROM_PTS;
} else if (has_duration(ic)) {
/* at least one component has timings - we use them for all
* the components */
fill_all_stream_timings(ic);
/* nut demuxer estimate the duration from PTS */
if (!strcmp(ic->iformat->name, "nut"))
ic->duration_estimation_method = AVFMT_DURATION_FROM_PTS;
else
ic->duration_estimation_method = AVFMT_DURATION_FROM_STREAM;
} else {
/* less precise: use bitrate info */
estimate_timings_from_bit_rate(ic);
ic->duration_estimation_method = AVFMT_DURATION_FROM_BITRATE;
}
update_stream_timings(ic);
for (unsigned i = 0; i < ic->nb_streams; i++) {
AVStream *const st = ic->streams[i];
if (st->time_base.den)
av_log(ic, AV_LOG_TRACE, "stream %u: start_time: %s duration: %s\n", i,
av_ts2timestr(st->start_time, &st->time_base),
av_ts2timestr(st->duration, &st->time_base));
}
av_log(ic, AV_LOG_TRACE,
"format: start_time: %s duration: %s (estimate from %s) bitrate=%"PRId64" kb/s\n",
av_ts2timestr(ic->start_time, &AV_TIME_BASE_Q),
av_ts2timestr(ic->duration, &AV_TIME_BASE_Q),
duration_estimate_name(ic->duration_estimation_method),
(int64_t)ic->bit_rate / 1000);
}
从estimate_timings()的代码中可以看出,有3种估算方法:
- (1)通过pts(显示时间戳)。该方法调用estimate_timings_from_pts()。它的基本思想就是读取视音频流中的结束位置AVPacket的PTS和起始位置AVPacket的PTS,两者相减得到时长信息。
- (2)通过已知流的时长。该方法调用fill_all_stream_timings()。它的代码没有细看,但从函数的注释的意思来说,应该是当有些视音频流有时长信息的时候,直接赋值给其他视音频流。
- (3)通过bitrate(码率)。该方法调用estimate_timings_from_bit_rate()。它的基本思想就是获得整个文件大小,以及整个文件的bitrate,两者相除之后得到时长信息。
estimate_timings_from_bit_rate()
- 在这里附上上述几种方法中最简单的函数estimate_timings_from_bit_rate()的代码。
static void estimate_timings_from_bit_rate(AVFormatContext *ic)
{
FFFormatContext *const si = ffformatcontext(ic);
int show_warning = 0;
/* if bit_rate is already set, we believe it */
if (ic->bit_rate <= 0) {
int64_t bit_rate = 0;
for (unsigned i = 0; i < ic->nb_streams; i++) {
const AVStream *const st = ic->streams[i];
const FFStream *const sti = cffstream(st);
if (st->codecpar->bit_rate <= 0 && sti->avctx->bit_rate > 0)
st->codecpar->bit_rate = sti->avctx->bit_rate;
if (st->codecpar->bit_rate > 0) {
if (INT64_MAX - st->codecpar->bit_rate < bit_rate) {
bit_rate = 0;
break;
}
bit_rate += st->codecpar->bit_rate;
} else if (st->codecpar->codec_type == AVMEDIA_TYPE_VIDEO && sti->codec_info_nb_frames > 1) {
// If we have a videostream with packets but without a bitrate
// then consider the sum not known
bit_rate = 0;
break;
}
}
ic->bit_rate = bit_rate;
}
/* if duration is already set, we believe it */
if (ic->duration == AV_NOPTS_VALUE &&
ic->bit_rate != 0) {
int64_t filesize = ic->pb ? avio_size(ic->pb) : 0;
if (filesize > si->data_offset) {
filesize -= si->data_offset;
for (unsigned i = 0; i < ic->nb_streams; i++) {
AVStream *const st = ic->streams[i];
if ( st->time_base.num <= INT64_MAX / ic->bit_rate
&& st->duration == AV_NOPTS_VALUE) {
st->duration = av_rescale(filesize, 8LL * st->time_base.den,
ic->bit_rate *
(int64_t) st->time_base.num);
show_warning = 1;
}
}
}
}
if (show_warning)
av_log(ic, AV_LOG_WARNING,
"Estimating duration from bitrate, this may be inaccurate\n");
}
- 从代码中可以看出,该函数做了两步工作:
- (1)如果AVFormatContext中没有bit_rate信息,就把所有AVStream的bit_rate加起来作为AVFormatContext的bit_rate信息。
- (2)使用文件大小filesize除以bitrate得到时长信息。
- 具体的方法是:
- AVStream->duration=(filesize*8/bit_rate)/time_base
- PS:
- 1)filesize乘以8是因为需要把Byte转换为Bit
- 2)具体的实现函数是那个av_rescale()函数。x=av_rescale(a,b,c)的含义是x=a*b/c。
- 3)之所以要除以time_base,是因为AVStream中的duration的单位是time_base,注意这和AVFormatContext中的duration的单位(单位是AV_TIME_BASE,固定取值为1000000)是不一样的。
int64_t av_rescale(int64_t a, int64_t b, int64_t c)
{
return av_rescale_rnd(a, b, c, AV_ROUND_NEAR_INF);
}
- 至此,avformat_find_stream_info()主要的函数就分析完了。