avformat_find_stream_info讀資料時的幾個快取資料的流向
簡介
瞭解ffmpeg在使用幾個讀資料的函式時,原始資料是怎樣讀到記憶體中,在記憶體中又是從哪個結構體轉到哪個結構體,
我覺得這是很關鍵的。因為ffmpeg就是處理資料的。只知道幾個API的呼叫,不知道資料的流轉方向,對於細緻的
處理來說很難。
分析流資訊時的資料流轉
資料存放基本介紹
此圖中涉及到的快取區位置包括如下:
AVIOContext:AVFormatContext->pb,原始資料都是先進到這裡。
AVFormatInternal :AVFormatContext->internal
struct AVFormatInternal {
/**
* Number of streams relevant for interleaving.
* Muxing only.
*/
int nb_interleaved_streams;
/**
* This buffer is only needed when packets were already buffered but
* not decoded, for example to get the codec parameters in MPEG
* streams.
*/
struct AVPacketList *packet_buffer;
struct AVPacketList *packet_buffer_end;
/* av_seek_frame() support */
int64_t data_offset; /**< offset of the first packet */
/**
* Raw packets from the demuxer, prior to parsing and decoding.
* This buffer is used for buffering packets until the codec can
* be identified, as parsing cannot be done without knowing the
* codec.
*/
struct AVPacketList *raw_packet_buffer;
struct AVPacketList *raw_packet_buffer_end;
/**
* Packets split by the parser get queued here.
*/
struct AVPacketList *parse_queue;
struct AVPacketList *parse_queue_end;
/**
* Remaining size available for raw_packet_buffer, in bytes.
*/
#define RAW_PACKET_BUFFER_SIZE 2500000
int raw_packet_buffer_remaining_size;
/**
* Offset to remap timestamps to be non-negative.
* Expressed in timebase units.
* @see AVStream.mux_ts_offset
*/
int64_t offset;
/**
* Timebase for the timestamp offset.
*/
AVRational offset_timebase;
#if FF_API_COMPUTE_PKT_FIELDS2
int missing_ts_warning;
#endif
int inject_global_side_data;
int avoid_negative_ts_use_pts;
/**
* Whether or not a header has already been written
*/
int header_written;
int write_header_ret;
};
raw_packet_buffer和raw_packet_buffer_end:在ff_read_packet()中會用到。這個還沒分析清楚
parse_queue和parse_queue_end:在read_frame_internal()中由於讀到的資料可能是多包,在此過程中就不能每分析到一包就返回,所以用這個快取去來存放分析到為一包的資料。
packet_buffer和packet_buffer_end:在read_frame_internal()中會從parse_queue中讀資料,將分析到的每包都放到這個連結串列中。是為了防止資料丟失,給之後的轉碼過程提供資料。在轉碼讀資料的時候就是先檢視這個連結串列裡面有沒有資料。
這些連結串列中存放的都是沒有解碼的資料。在分析碼流的最後會嘗試解碼,並釋放解碼後的資料。
資料流轉圖
幾個涉及到的函式
以下將對幾個函式進行分析。從前到後對資料的開始讀入到解碼成功做一個梳理。
av_probe_input_buffer函式中的資料流向
av_probe_input_buffer函式中的資料流向
這篇文章對在探查幀格式的過程中,資料的快取做了分析。這是對輸入流的第一步分析。
最後將探查過的資料存放到了AVIOContext *pb的buf_ptr到buf_end中。
avformat_find_stream_info
最後分析完的資料都儲存在了packet_buffer和packet_buffer_end中。提供給之後的轉碼流程。
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, *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;
flush_codecs = probesize > 0;
av_opt_set(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)
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);
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 = */
if (!avctx->time_base.num)
avctx->time_base = st->time_base;
}
// only for the split stuff
if (!st->parser && !(ic->flags & AVFMT_FLAG_NOPARSE) && st->request_probe <= 0) {
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));
}
}
/* 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
if (st->codecpar->codec_id != st->internal->orig_codec_id)
st->internal->orig_codec_id = st->codecpar->codec_id;
ret = avcodec_parameters_to_context(avctx, st->codecpar);
if (ret < 0)
goto find_stream_info_err;
if (st->request_probe <= 0)
st->internal->avctx_inited = 1;
codec = find_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);
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 av_find_stream_info\n");
}
// Try to just open decoders, in case this is enough to get parameters.
if (!has_codec_parameters(st, NULL) && st->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 av_find_stream_info\n");
}
if (!options)
av_dict_free(&thread_opt);
}
for (i = 0; i < ic->nb_streams; i++) {
#if FF_API_R_FRAME_RATE
ic->streams[i]->info->last_dts = AV_NOPTS_VALUE;
#endif
ic->streams[i]->info->fps_first_dts = AV_NOPTS_VALUE;
ic->streams[i]->info->fps_last_dts = AV_NOPTS_VALUE;
}
read_size = 0;
for (;;) {
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;
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 */
if (!(st->r_frame_rate.num && st->avg_frame_rate.num) &&
st->codecpar->codec_type == AVMEDIA_TYPE_VIDEO) {
int count = (ic->iformat->flags & AVFMT_NOTIMESTAMPS) ?
st->info->codec_info_duration_fields/2 :
st->info->duration_count;
if (count < fps_analyze_framecount)
break;
}
if (st->parser && st->parser->parser->split &&
!st->codecpar->extradata)
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 (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]->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). */
ret = read_frame_internal(ic, &pkt1);
if (ret == AVERROR(EAGAIN))
continue;
if (ret < 0) {
/* EOF or error*/
eof_reached = 1;
break;
}
pkt = &pkt1;
if (!(ic->flags & AVFMT_FLAG_NOBUFFER)) {
ret = add_to_pktbuf(&ic->internal->packet_buffer, pkt,
&ic->internal->packet_buffer_end, 0);
if (ret < 0)
goto find_stream_info_err;
}
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 find_stream_info_err;
st->internal->avctx_inited = 1;
}
if (pkt->dts != AV_NOPTS_VALUE && st->codec_info_nb_frames > 1) {
/* check for non-increasing dts */
if (st->info->fps_last_dts != AV_NOPTS_VALUE &&
st->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->info->fps_last_dts_idx,
st->info->fps_last_dts, st->codec_info_nb_frames,
pkt->dts);
st->info->fps_first_dts =
st->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->info->fps_last_dts != AV_NOPTS_VALUE &&
st->info->fps_last_dts_idx > st->info->fps_first_dts_idx &&
(pkt->dts - st->info->fps_last_dts) / 1000 >
(st->info->fps_last_dts - st->info->fps_first_dts) /
(st->info->fps_last_dts_idx - st->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->info->fps_last_dts_idx,
st->info->fps_last_dts, st->codec_info_nb_frames,
pkt->dts);
st->info->fps_first_dts =
st->info->fps_last_dts = AV_NOPTS_VALUE;
}
/* update stored dts values */
if (st->info->fps_first_dts == AV_NOPTS_VALUE) {
st->info->fps_first_dts = pkt->dts;
st->info->fps_first_dts_idx = st->codec_info_nb_frames;
}
st->info->fps_last_dts = pkt->dts;
st->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->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->info->fps_first_dts != AV_NOPTS_VALUE
&& st->info->fps_last_dts != AV_NOPTS_VALUE)
t = FFMAX(t, av_rescale_q(st->info->fps_last_dts - st->info->fps_first_dts, 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(pkt);
break;
}
if (pkt->duration) {
if (avctx->codec_type == AVMEDIA_TYPE_SUBTITLE && pkt->pts != AV_NOPTS_VALUE && pkt->pts >= st->start_time) {
st->info->codec_info_duration = FFMIN(pkt->pts - st->start_time, st->info->codec_info_duration + pkt->duration);
} else
st->info->codec_info_duration += pkt->duration;
st->info->codec_info_duration_fields += st->parser && st->need_parsing && avctx->ticks_per_frame ==2 ? st->parser->repeat_pict + 1 : 2;
}
}
#if FF_API_R_FRAME_RATE
if (st->codecpar->codec_type == AVMEDIA_TYPE_VIDEO)
ff_rfps_add_frame(ic, st, pkt->dts);
#endif
if (st->parser && st->parser->parser->split && !avctx->extradata) {
int i = st->parser->parser->split(avctx, pkt->data, pkt->size);
if (i > 0 && i < FF_MAX_EXTRADATA_SIZE) {
avctx->extradata_size = i;
avctx->extradata = av_mallocz(avctx->extradata_size +
AV_INPUT_BUFFER_PADDING_SIZE);
if (!avctx->extradata)
return AVERROR(ENOMEM);
memcpy(avctx->extradata, pkt->data,
avctx->extradata_size);
}
}
/* 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(pkt);
st->codec_info_nb_frames++;
count++;
}
if (eof_reached) {
int stream_index;
for (stream_index = 0; stream_index < ic->nb_streams; stream_index++) {
st = ic->streams[stream_index];
avctx = st->internal->avctx;
if (!has_codec_parameters(st, NULL)) {
const AVCodec *codec = find_decoder(ic, st, st->codecpar->codec_id);
if (codec && !avctx->codec) {
if (avcodec_open2(avctx, codec, (options && stream_index < orig_nb_streams) ? &options[stream_index] : NULL) < 0)
av_log(ic, AV_LOG_WARNING,
"Failed to open codec in av_find_stream_info\n");
}
}
// EOF already reached while reading the stream above.
// So continue with reoordering DTS with whatever delay we have.
if (ic->internal->packet_buffer && !has_decode_delay_been_guessed(st)) {
update_dts_from_pts(ic, stream_index, ic->internal->packet_buffer);
}
}
}
if (flush_codecs) {
AVPacket empty_pkt = { 0 };
int err = 0;
av_init_packet(&empty_pkt);
for (i = 0; i < ic->nb_streams; i++) {
st = ic->streams[i];
/* flush the decoders */
if (st->info->found_decoder == 1) {
do {
err = try_decode_frame(ic, st, &empty_pkt,
(options && i < orig_nb_streams)
? &options[i] : NULL);
} while (err > 0 && !has_codec_parameters(st, NULL));
if (err < 0) {
av_log(ic, AV_LOG_INFO,
"decoding for stream %d failed\n", st->index);
}
}
}
}
// close codecs which were opened in try_decode_frame()
for (i = 0; i < ic->nb_streams; i++) {
st = ic->streams[i];
avcodec_close(st->internal->avctx);
}
ff_rfps_calculate(ic);
for (i = 0; i < ic->nb_streams; i++) {
st = ic->streams[i];
avctx = st->internal->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_find_pix_fmt(avpriv_get_raw_pix_fmt_tags(), tag) == avctx->pix_fmt)
avctx->codec_tag= tag;
}
/* estimate average framerate if not set by demuxer */
if (st->info->codec_info_duration_fields &&
!st->avg_frame_rate.num &&
st->info->codec_info_duration) {
int best_fps = 0;
double best_error = 0.01;
if (st->info->codec_info_duration >= INT64_MAX / st->time_base.num / 2||
st->info->codec_info_duration_fields >= INT64_MAX / st->time_base.den ||
st->info->codec_info_duration < 0)
continue;
av_reduce(&st->avg_frame_rate.num, &st->avg_frame_rate.den,
st->info->codec_info_duration_fields * (int64_t) st->time_base.den,
st->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 (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 (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 * avctx->ticks_per_frame * (int64_t) st->time_base.den) {
st->r_frame_rate.num = avctx->time_base.den;
st->r_frame_rate.den = avctx->time_base.num * avctx->ticks_per_frame;
} else {
st->r_frame_rate.num = st->time_base.den;
st->r_frame_rate.den = st->time_base.num;
}
}
if (st->display_aspect_ratio.num && st->display_aspect_ratio.den) {
AVRational hw_ratio = { avctx->height, avctx->width };
st->sample_aspect_ratio = av_mul_q(st->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(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 (i = 0; i < ic->nb_streams; i++) {
const char *errmsg;
st = ic->streams[i];
/* if no packet was ever seen, update context now for has_codec_parameters */
if (!st->internal->avctx_inited) {
if (st->codecpar->codec_type == AVMEDIA_TYPE_AUDIO &&
st->codecpar->format == AV_SAMPLE_FMT_NONE)
st->codecpar->format = st->internal->avctx->sample_fmt;
ret = avcodec_parameters_to_context(st->internal->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), st->internal->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' and 'probesize' options\n",
i, buf, errmsg);
} else {
ret = 0;
}
}
compute_chapters_end(ic);
/* update the stream parameters from the internal codec contexts */
for (i = 0; i < ic->nb_streams; i++) {
st = ic->streams[i];
if (st->internal->avctx_inited) {
int orig_w = st->codecpar->width;
int orig_h = st->codecpar->height;
ret = avcodec_parameters_from_context(st->codecpar, st->internal->avctx);
if (ret < 0)
goto find_stream_info_err;
// The decoder might reduce the video size by the lowres factor.
if (av_codec_get_lowres(st->internal->avctx) && orig_w) {
st->codecpar->width = orig_w;
st->codecpar->height = orig_h;
}
}
#if FF_API_LAVF_AVCTX
FF_DISABLE_DEPRECATION_WARNINGS
ret = avcodec_parameters_to_context(st->codec, st->codecpar);
if (ret < 0)
goto find_stream_info_err;
// The old API (AVStream.codec) "requires" the resolution to be adjusted
// by the lowres factor.
if (av_codec_get_lowres(st->internal->avctx) && st->internal->avctx->width) {
av_codec_set_lowres(st->codec, av_codec_get_lowres(st->internal->avctx));
st->codec->width = st->internal->avctx->width;
st->codec->height = st->internal->avctx->height;
}
if (st->codec->codec_tag != MKTAG('t','m','c','d'))
st->codec->time_base = st->internal->avctx->time_base;
st->codec->framerate = st->avg_frame_rate;
if (st->internal->avctx->subtitle_header) {
st->codec->subtitle_header = av_malloc(st->internal->avctx->subtitle_header_size);
if (!st->codec->subtitle_header)
goto find_stream_info_err;
st->codec->subtitle_header_size = st->internal->avctx->subtitle_header_size;
memcpy(st->codec->subtitle_header, st->internal->avctx->subtitle_header,
st->codec->subtitle_header_size);
}
// Fields unavailable in AVCodecParameters
st->codec->coded_width = st->internal->avctx->coded_width;
st->codec->coded_height = st->internal->avctx->coded_height;
st->codec->properties = st->internal->avctx->properties;
FF_ENABLE_DEPRECATION_WARNINGS
#endif
st->internal->avctx_inited = 0;
}
find_stream_info_err:
for (i = 0; i < ic->nb_streams; i++) {
st = ic->streams[i];
if (st->info)
av_freep(&st->info->duration_error);
av_freep(&ic->streams[i]->info);
}
if (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), ic->pb->bytes_read, ic->pb->seek_count, count);
return ret;
}
ff_read_packet
int ff_read_packet(AVFormatContext *s, AVPacket *pkt)
{
int ret, i, err;
AVStream *st;
for (;;) {
//首先在這個連結串列中找。
AVPacketList *pktl = s->internal->raw_packet_buffer;
//如果連結串列中有包從連結串列中取,一開始進來時是空的。
if (pktl) {
*pkt = pktl->pkt;
st = s->streams[pkt->stream_index];
//預設是RAW_PACKET_BUFFER_SIZE=2500000
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);
//此函式如果是h264的原始流的話呼叫的是ff_raw_read_partial_packet,
//在檔案libavformat\rawdec.c中
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)
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;
}
}
ff_raw_read_partial_packet
int ff_raw_read_partial_packet(AVFormatContext *s, AVPacket *pkt)
{
int ret, size;
size = RAW_PACKET_SIZE;
//為pkt分配必要的記憶體,後面有詳解
if (av_new_packet(pkt, size) < 0)
return AVERROR(ENOMEM);
pkt->pos= avio_tell(s->pb);
pkt->stream_index = 0;
//呼叫在s->pb中註冊的讀函式將size個數據讀入pkt->data中。後面有詳解
ret = ffio_read_partial(s->pb, pkt->data, size);
if (ret < 0) {
//pkt是帶引用計數的。如果失敗就拿這個函式釋放。
av_packet_unref(pkt);
return ret;
}
//把返回的ret當pkt中資料的大小進行設定,並將最後的AV_INPUT_BUFFER_PADDING_SIZE個位元組設為0.
av_shrink_packet(pkt, ret);
return ret;
}
av_new_packet
給AVPacket分配具體放資料的空間,
int av_new_packet(AVPacket *pkt, int size)
{
AVBufferRef *buf = NULL;
//這個函式做了幾個記憶體分配
/*
AVBufferRef *buf(malloc)
AVBuffer *buf->buffer(malloc)
uint8_t *buf->buffer->data(malloc)
buf->data = buf->buffer->data
buf->size = buf->data的size
buf->buffer->refcount =1引用計數
*/
int ret = packet_alloc(&buf, size);
if (ret < 0)
return ret;
//最後將所有分配的記憶體都放到pkt中
av_init_packet(pkt);
pkt->buf = buf;
pkt->data = buf->data;
pkt->size = size;
return 0;
}
struct AVBuffer {
uint8_t *data; /**< data described by this buffer */
int size; /**< size of data in bytes */
/**
* number of existing AVBufferRef instances referring to this buffer
*/
volatile int refcount;
/**
* a callback for freeing the data
*/
void (*free)(void *opaque, uint8_t *data);
/**
* an opaque pointer, to be used by the freeing callback
*/
void *opaque;
/**
* A combination of BUFFER_FLAG_*
*/
int flags;
};
/**
* A reference to a data buffer.
*
* The size of this struct is not a part of the public ABI and it is not meant
* to be allocated directly.
*/
typedef struct AVBufferRef {
AVBuffer *buffer;
/**
* The data buffer. It is considered writable if and only if
* this is the only reference to the buffer, in which case
* av_buffer_is_writable() returns 1.
*/
uint8_t *data;
/**
* Size of data in bytes.
*/
int size;
} AVBufferRef;
avio_tell
/**
* ftell() equivalent for AVIOContext.
* @return position or AVERROR.
*/
static av_always_inline int64_t avio_tell(AVIOContext *s)
{
return avio_seek(s, 0, SEEK_CUR);
}
ffio_read_partial
最終呼叫的還是在s中註冊的read函式。如果是記憶體讀取如下注冊。
AVIOContext * inpb = avio_alloc_context(Buf, BUF_SIZE, 0, dataFromUser, read_data, NULL, NULL);
s->read_packet(s->opaque, buf, size);呼叫的就是上面註冊的read_data函式。
int ffio_read_partial(AVIOContext *s, unsigned char *buf, int size)
{
int len;
if (size < 0)
return -1;
if (s->read_packet && s->write_flag) {
len = s->read_packet(s->opaque, buf, size);
if (len > 0)
s->pos += len;
return len;
}
//如果s的buff中無資料就用fill_buffer函式讀取,並放到s的buff中。具體介紹在《av_probe_input_buffer函式中的資料流向》中有介紹
len = s->buf_end - s->buf_ptr;
if (len == 0) {
/* Reset the buf_end pointer to the start of the buffer, to make sure
* the fill_buffer call tries to read as much data as fits into the
* full buffer, instead of just what space is left after buf_end.
* This avoids returning partial packets at the end of the buffer,
* for packet based inputs.
*/
s->buf_end = s->buf_ptr = s->buffer;
fill_buffer(s);
len = s->buf_end - s->buf_ptr;
}
//取資料返回。
if (len > size)
len = size;
memcpy(buf, s->buf_ptr, len);
s->buf_ptr += len;
if (!len) {
if (s->error) return s->error;
if (avio_feof(s)) return AVERROR_EOF;
}
return len;
}
av_shrink_packet
如果讀到的比分配的空間小的情況下,需要將pkt中的大小重新設定,並將真是資料的後AV_INPUT_BUFFER_PADDING_SIZE個
位元組設為0.防止讀越界。
void av_shrink_packet(AVPacket *pkt, int size)
{
if (pkt->size <= size)
return;
pkt->size = size;
memset(pkt->data + size, 0, AV_INPUT_BUFFER_PADDING_SIZE);
}
parse_packet
將資料放到av_parser_parse2函式去解析,如果解析成功,並且有返回的包就將包放到s->internal->parse_queue的連結串列中。在av_parser_parse2中應該有自己的快取處理之前放入的資料。
/**
* Parse a packet, add all split parts to parse_queue.
*
* @param pkt Packet to parse, NULL when flushing the parser at end of stream.
*/
static int parse_packet(AVFormatContext *s, AVPacket *pkt, int stream_index)
{
AVPacket out_pkt = { 0 }, flush_pkt = { 0 };
AVStream *st = s->streams[stream_index];
uint8_t *data = pkt ? pkt->data : NULL;
int size = pkt ? pkt->size : 0;
int ret = 0, got_output = 0;
if (!pkt) {
av_init_packet(&flush_pkt);
pkt = &flush_pkt;
got_output = 1;
} else if (!size && st->parser->flags & PARSER_FLAG_COMPLETE_FRAMES) {
// preserve 0-size sync packets
compute_pkt_fields(s, st, st->parser, pkt, AV_NOPTS_VALUE, AV_NOPTS_VALUE);
}
while (size > 0 || (pkt == &flush_pkt && got_output)) {
int len;
int64_t next_pts = pkt->pts;
int64_t next_dts = pkt->dts;
av_init_packet(&out_pkt);
len = av_parser_parse2(st->parser, st->internal->avctx,
&out_pkt.data, &out_pkt.size, data, size,
pkt->pts, pkt->dts, pkt->pos);
pkt->pts = pkt->dts = AV_NOPTS_VALUE;
pkt->pos = -1;
/* increment read pointer */
data += len;
size -= len;
got_output = !!out_pkt.size;
if (!out_pkt.size)
continue;
if (pkt->side_data) {
out_pkt.side_data = pkt->side_data;
out_pkt.side_data_elems = pkt->side_data_elems;
pkt->side_data = NULL;
pkt->side_data_elems = 0;
}
/* set the duration */
out_pkt.duration = (st->parser->flags & PARSER_FLAG_COMPLETE_FRAMES) ? pkt->duration : 0;
if (st->codecpar->codec_type == AVMEDIA_TYPE_AUDIO) {
if (st->internal->avctx->sample_rate > 0) {
out_pkt.duration =
av_rescale_q_rnd(st->parser->duration,
(AVRational) { 1, st->internal->avctx->sample_rate },
st->time_base,
AV_ROUND_DOWN);
}
}
out_pkt.stream_index = st->index;
out_pkt.pts = st->parser->pts;
out_pkt.dts = st->parser->dts;
out_pkt.pos = st->parser->pos;
if (st->need_parsing == AVSTREAM_PARSE_FULL_RAW)
out_pkt.pos = st->parser->frame_offset;
if (st->parser->key_frame == 1 ||
(st->parser->key_frame == -1 &&
st->parser->pict_type == AV_PICTURE_TYPE_I))
out_pkt.flags |= AV_PKT_FLAG_KEY;
if (st->parser->key_frame == -1 && st->parser->pict_type ==AV_PICTURE_TYPE_NONE && (pkt->flags&AV_PKT_FLAG_KEY))
out_pkt.flags |= AV_PKT_FLAG_KEY;
compute_pkt_fields(s, st, st->parser, &out_pkt, next_dts, next_pts);
ret = add_to_pktbuf(&s->internal->parse_queue, &out_pkt,
&s->internal->parse_queue_end, 1);
av_packet_unref(&out_pkt);
if (ret < 0)
goto fail;
}
/* end of the stream => close and free the parser */
if (pkt == &flush_pkt) {
av_parser_close(st->parser);
st->parser = NULL;
}
fail:
av_packet_unref(pkt);
return ret;
}