【FFmpeg】av_read_frame函数
返回流的下一帧1.此函数返回存储在文件中的内容，而不验证是否存在用于解码器的有效帧。它将把存储在文件中的内容分割成帧，并为每次调用返回一个帧。它不会省略有效帧之间的无效数据，以便为解码器提供可能用于解码的最大信息2.如果成功，返回的数据包将被引用计数(pkt->但已设置)并无限期有效。当不再需要该数据包时，必须使用av_packet_unref()释放该数据包。对于视频，数据包只包含一帧。对于音频
·
目录
参考：
ffmpeg 源代码简单分析 ： av_read_frame()
FFmpeg相关记录：
示例工程：
【FFmpeg】调用ffmpeg库实现264软编
【FFmpeg】调用ffmpeg库实现264软解
【FFmpeg】调用ffmpeg库进行RTMP推流和拉流
【FFmpeg】调用ffmpeg库进行SDL2解码后渲染
流程分析：
【FFmpeg】编码链路上主要函数的简单分析
【FFmpeg】解码链路上主要函数的简单分析
结构体分析：
【FFmpeg】AVCodec结构体
【FFmpeg】AVCodecContext结构体
【FFmpeg】AVStream结构体
【FFmpeg】AVFormatContext结构体
【FFmpeg】AVIOContext结构体
【FFmpeg】AVPacket结构体
函数分析：
【FFmpeg】avformat_open_input函数
【FFmpeg】avformat_find_stream_info函数
【FFmpeg】avformat_alloc_output_context2函数
【FFmpeg】avio_open2函数
【FFmpeg】avformat_write_header函数
av_read_frame函数内调用关系如下
1.av_read_frame
av_read_frame用于读取输入数据流当中的下一个帧，具体实现方式如下
/**
* Return the next frame of a stream.
* This function returns what is stored in the file, and does not validate
* that what is there are valid frames for the decoder. It will split what is
* stored in the file into frames and return one for each call. It will not
* omit invalid data between valid frames so as to give the decoder the maximum
* information possible for decoding.
*
* On success, the returned packet is reference-counted (pkt->buf is set) and
* valid indefinitely. The packet must be freed with av_packet_unref() when
* it is no longer needed. For video, the packet contains exactly one frame.
* For audio, it contains an integer number of frames if each frame has
* a known fixed size (e.g. PCM or ADPCM data). If the audio frames have
* a variable size (e.g. MPEG audio), then it contains one frame.
*
* pkt->pts, pkt->dts and pkt->duration are always set to correct
* values in AVStream.time_base units (and guessed if the format cannot
* provide them). pkt->pts can be AV_NOPTS_VALUE if the video format
* has B-frames, so it is better to rely on pkt->dts if you do not
* decompress the payload.
*
* @return 0 if OK, < 0 on error or end of file. On error, pkt will be blank
* (as if it came from av_packet_alloc()).
*
* @note pkt will be initialized, so it may be uninitialized, but it must not
* contain data that needs to be freed.
*/
// 返回流的下一帧
// 1.此函数返回存储在文件中的内容，而不验证是否存在用于解码器的有效帧。它将把存储在文件中的内容分割成帧，
// 并为每次调用返回一个帧。它不会省略有效帧之间的无效数据，以便为解码器提供可能用于解码的最大信息
// 2.如果成功，返回的数据包将被引用计数(pkt->但已设置)并无限期有效。当不再需要该数据包时，必须使用
// av_packet_unref()释放该数据包。对于视频，数据包只包含一帧。对于音频，如果每帧有一个已知的固定大小
// (例如PCM或ADPCM数据)，它包含一个整数帧数。如果音频帧具有可变大小(例如MPEG音频)，则它包含一个帧
// 3.pkt->pts, pkt->dts和pkt->duration在AVStream中总是设置为正确的值。Time_base单位
// (并猜测格式是否不能提供它们)。如果视频格式有b帧，pkt->pts可以是AV_NOPTS_VALUE，
// 所以如果不解压缩有效载荷，最好依赖pkt->dts
// @return: 返回0则成功，如果return小于0则出错或者到达文件末尾，如果出错pkt为空
// @note: PKT将被初始化，因此它可能是未初始化的，但它必须不包含需要释放的数据
int av_read_frame(AVFormatContext *s, AVPacket *pkt)
{
FFFormatContext *const si = ffformatcontext(s);
// AVFMT_FLAG_GENPTS: 生成丢失的pts，即使它需要解析未来的帧
const int genpts = s->flags & AVFMT_FLAG_GENPTS;
int eof = 0;
int ret;
AVStream *st;
// 1.数据包已被缓冲但未解码
// 只有当数据包已经被缓冲但还没有解码时才需要这个缓冲区，例如在MPEG流中获取编解码器参数
// genpts表示是否需要生成丢失的pts，一般情况下是不需要的，默认会进入下述分支
if (!genpts) {
ret = si->packet_buffer.head
? avpriv_packet_list_get(&si->packet_buffer, pkt) // 从packet buffer中获取1帧
: read_frame_internal(s, pkt); // 从流中读取一帧到pkt
if (ret < 0)
return ret;
goto return_packet;
}
// 需要生成丢失的pts
for (;;) {
PacketListEntry *pktl = si->packet_buffer.head;
if (pktl) {
AVPacket *next_pkt = &pktl->pkt;
if (next_pkt->dts != AV_NOPTS_VALUE) {
// pts_wrap_bits用于处理时间戳的溢出问题，它允许时间戳在溢出之前使用更多的位
// 例如设置pts_wrap_bits为24，时间戳将在达到2^24时溢出
int wrap_bits = s->streams[next_pkt->stream_index]->pts_wrap_bits;
// last dts seen for this stream. if any of packets following
// current one had no dts, we will set this to AV_NOPTS_VALUE.
// 这条流的最后一次DTS。如果当前数据包之后的任何数据包没有dts，将其设置为AV_NOPTS_VALUE
int64_t last_dts = next_pkt->dts;
av_assert2(wrap_bits <= 64);
while (pktl && next_pkt->pts == AV_NOPTS_VALUE) {
// 如果当前pkt和下一个pkt同属一个stream
// av_compare_mod用于比较两个整数a和b相对于模数mod的大小关系
// 如果返回值小于0，表示整数a在模数mod下的值小于整数b
if (pktl->pkt.stream_index == next_pkt->stream_index &&
av_compare_mod(next_pkt->dts, pktl->pkt.dts, 2ULL << (wrap_bits - 1)) < 0) {
if (av_compare_mod(pktl->pkt.pts, pktl->pkt.dts, 2ULL << (wrap_bits - 1))) {
// not B-frame
// 修正pts
next_pkt->pts = pktl->pkt.dts;
}
if (last_dts != AV_NOPTS_VALUE) {
// Once last dts was set to AV_NOPTS_VALUE, we don't change it.
last_dts = pktl->pkt.dts;
}
}
pktl = pktl->next;
}
if (eof && next_pkt->pts == AV_NOPTS_VALUE && last_dts != AV_NOPTS_VALUE) {
// Fixing the last reference frame had none pts issue (For MXF etc).
// We only do this when
// 1. eof.
// 2. we are not able to resolve a pts value for current packet.
// 3. the packets for this stream at the end of the files had valid dts.
// 修复最后一个参考帧的pts问题
// 1.到达文件末尾
// 2.无法解析当前数据包的PTS值
// 3.该流在文件末尾的数据包具有有效的DTS
next_pkt->pts = last_dts + next_pkt->duration;
}
pktl = si->packet_buffer.head;
}
/* read packet from packet buffer, if there is data */
// 如果有数据，则从packet buffer中取出数据
st = s->streams[next_pkt->stream_index];
if (!(next_pkt->pts == AV_NOPTS_VALUE && st->discard < AVDISCARD_ALL &&
next_pkt->dts != AV_NOPTS_VALUE && !eof)) {
ret = avpriv_packet_list_get(&si->packet_buffer, pkt);
goto return_packet;
}
}
// 读取帧
ret = read_frame_internal(s, pkt);
if (ret < 0) {
if (pktl && ret != AVERROR(EAGAIN)) {
eof = 1;
continue;
} else
return ret;
}
// 将pkt放入packet buffer当中
ret = avpriv_packet_list_put(&si->packet_buffer,
pkt, NULL, 0);
if (ret < 0) {
av_packet_unref(pkt);
return ret;
}
}
return_packet:
st = s->streams[pkt->stream_index];
if ((s->iformat->flags & AVFMT_GENERIC_INDEX) && pkt->flags & AV_PKT_FLAG_KEY) {
ff_reduce_index(s, st->index);
av_add_index_entry(st, pkt->pos, pkt->dts, 0, 0, AVINDEX_KEYFRAME);
}
if (is_relative(pkt->dts))
pkt->dts -= RELATIVE_TS_BASE;
if (is_relative(pkt->pts))
pkt->pts -= RELATIVE_TS_BASE;
return ret;
}
1.2 从pkt buffer中读取帧（avpriv_packet_list_get）
函数会从pkt的buffer当中读取一帧，位于libavcodec\avpkt.c中
/**
* Remove the oldest AVPacket in the list and return it.
*
* @note The pkt will be overwritten completely on success. The caller
* owns the packet and must unref it by itself.
*
* @param head A pointer to a PacketList struct
* @param pkt Pointer to an AVPacket struct
* @return 0 on success, and a packet is returned. AVERROR(EAGAIN) if
* the list was empty.
*/
// 删除列表中最早的AVPacket并返回它
// @note: 一旦成功，pkt将被完全覆盖。调用者拥有packet，必须由调用者释放
int avpriv_packet_list_get(PacketList *pkt_buffer,
AVPacket *pkt)
{
PacketListEntry *pktl = pkt_buffer->head;
if (!pktl)
return AVERROR(EAGAIN);
*pkt = pktl->pkt;
pkt_buffer->head = pktl->next;
if (!pkt_buffer->head)
pkt_buffer->tail = NULL;
av_freep(&pktl);
return 0;
}
1.3 从流当中读取帧（read_frame_internal）
函数的定义位于libavformat\demux.c中，其主要的目的是从流当中读取一帧，函数大体可以分为几个部分：
（1）读取帧并且解析
（2）如果有必要则更新context
（3）时间戳等信息的检查
（4）检查discard和side data
在这些流程之中，最核心的内容是读取帧（ff_read_packet）并且解析（parse_packet），其中解析packet是只在有必要时进行，这需要提前检查
static int read_frame_internal(AVFormatContext *s, AVPacket *pkt)
{
FFFormatContext *const si = ffformatcontext(s);
int ret, got_packet = 0;
AVDictionary *metadata = NULL;
// 没有获取packet则持续读取
while (!got_packet && !si->parse_queue.head) {
AVStream *st;
FFStream *sti;
// 1.读取帧并且考虑解析
/* read next packet */
// 读取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)
// 解析packet
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 */
// 2.如果有必要则更新context
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");
ret = codec_close(sti);
sti->info->found_decoder = 0;
if (ret < 0)
return ret;
}
/* 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->codec_desc = avcodec_descriptor_get(sti->avctx->codec_id);
sti->need_context_update = 0;
}
// 3.时间戳等信息的检查
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;
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);
// 4.检查discard和side data
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 FF_API_AVSTREAM_SIDE_DATA
if (sti->inject_global_side_data) {
for (int i = 0; i < st->codecpar->nb_coded_side_data; i++) {
const AVPacketSideData *const src_sd = &st->codecpar->coded_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;
}
#endif
}
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;
}
1.3.1 读取帧（ff_read_packet）
ff_read_packet用于从媒体文件中读取数据包，该函数会根据具体输入的媒体格式，调用具体的read_packet函数进行，核心函数为.read_packet
/**
* Read a transport packet from a media file.
*
* @param s media file handle
* @param pkt is filled
* @return 0 if OK, AVERROR_xxx on error
*/
// 从媒体文件中读取传输数据包
int ff_read_packet(AVFormatContext *s, AVPacket *pkt)
{
FFFormatContext *const si = ffformatcontext(s);
int err;
#if FF_API_INIT_PACKET
FF_DISABLE_DEPRECATION_WARNINGS // 禁用FFmpeg中的弃用警告
pkt->data = NULL;
pkt->size = 0;
av_init_packet(pkt);
FF_ENABLE_DEPRECATION_WARNINGS // 启用FFmpeg中的弃用警告
#else
av_packet_unref(pkt);
#endif
for (;;) {
PacketListEntry *pktl = si->raw_packet_buffer.head;
if (pktl) {
AVStream *const st = s->streams[pktl->pkt.stream_index];
if (si->raw_packet_buffer_size >= s->probesize)
if ((err = probe_codec(s, st, NULL)) < 0)
return err;
if (ffstream(st)->request_probe <= 0) {
avpriv_packet_list_get(&si->raw_packet_buffer, pkt);
si->raw_packet_buffer_size -= pkt->size;
return 0;
}
}
// 具体读取packet的函数
err = ffifmt(s->iformat)->read_packet(s, pkt);
if (err < 0) {
av_packet_unref(pkt);
/* 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 (err == FFERROR_REDO)
continue;
if (!pktl || err == AVERROR(EAGAIN))
return err;
for (unsigned i = 0; i < s->nb_streams; i++) {
AVStream *const st = s->streams[i];
FFStream *const sti = ffstream(st);
if (sti->probe_packets || sti->request_probe > 0)
if ((err = probe_codec(s, st, NULL)) < 0)
return err;
av_assert0(sti->request_probe <= 0);
}
continue;
}
err = av_packet_make_refcounted(pkt);
if (err < 0) {
av_packet_unref(pkt);
return err;
}
err = handle_new_packet(s, pkt, 1);
if (err <= 0) /* Error or passthrough */
return err;
}
}
在上面的函数当中，最核心的地方是read_packet，会根据不同的FFInputFormat来调用不同的方式，例如FLV格式，会调用flv_read_packet，定义如下
const FFInputFormat ff_flv_demuxer = {
.p.name = "flv",
.p.long_name = NULL_IF_CONFIG_SMALL("FLV (Flash Video)"),
.p.extensions = "flv",
.p.priv_class = &flv_kux_class,
.priv_data_size = sizeof(FLVContext),
.read_probe = flv_probe,
.read_header = flv_read_header,
.read_packet = flv_read_packet,
.read_seek = flv_read_seek,
.read_close = flv_read_close,
};
其中，flv_read_packet的定义如下。主要的工作是根据FLV格式，进行逐层的Tag解析以及TagData，获取Tag和TagData，流程如下
（1）解析tag header
（2）解析tag data
（3）其他信息配置
static int flv_read_packet(AVFormatContext *s, AVPacket *pkt)
{
FLVContext *flv = s->priv_data;
int ret, i, size, flags;
enum FlvTagType type;
int stream_type=-1;
int64_t next, pos, meta_pos;
int64_t dts, pts = AV_NOPTS_VALUE;
int av_uninit(channels);
int av_uninit(sample_rate);
AVStream *st = NULL;
int last = -1;
int orig_size;
int enhanced_flv = 0;
uint32_t video_codec_id = 0;
retry:
/* pkt size is repeated at end. skip it */
// 1.解析tag header
pos = avio_tell(s->pb);
// tag的类型
type = (avio_r8(s->pb) & 0x1F);
// datasize的大小
orig_size =
size = avio_rb24(s->pb);
flv->sum_flv_tag_size += size + 11LL;
// 时间戳
dts = avio_rb24(s->pb);
dts |= (unsigned)avio_r8(s->pb) << 24;
av_log(s, AV_LOG_TRACE, "type:%d, size:%d, last:%d, dts:%"PRId64" pos:%"PRId64"\n", type, size, last, dts, avio_tell(s->pb));
if (avio_feof(s->pb))
return AVERROR_EOF;
// 流id
avio_skip(s->pb, 3); /* stream id, always 0 */
// 解析tag header结束
flags = 0;
if (flv->validate_next < flv->validate_count) {
int64_t validate_pos = flv->validate_index[flv->validate_next].pos;
if (pos == validate_pos) {
if (FFABS(dts - flv->validate_index[flv->validate_next].dts) <=
VALIDATE_INDEX_TS_THRESH) {
flv->validate_next++;
} else {
clear_index_entries(s, validate_pos);
flv->validate_count = 0;
}
} else if (pos > validate_pos) {
clear_index_entries(s, validate_pos);
flv->validate_count = 0;
}
}
if (size == 0) {
ret = FFERROR_REDO;
goto leave;
}
next = size + avio_tell(s->pb);
if (type == FLV_TAG_TYPE_AUDIO) { // 音频
stream_type = FLV_STREAM_TYPE_AUDIO;
// tag data的第一个字节
flags = avio_r8(s->pb);
size--;
} else if (type == FLV_TAG_TYPE_VIDEO) { // 视频
stream_type = FLV_STREAM_TYPE_VIDEO;
// tag data的第一个字节
flags = avio_r8(s->pb);
video_codec_id = flags & FLV_VIDEO_CODECID_MASK;
/*
* Reference Enhancing FLV 2023-03-v1.0.0-B.8
* https://github.com/veovera/enhanced-rtmp/blob/main/enhanced-rtmp-v1.pdf
* */
enhanced_flv = (flags >> 7) & 1;
size--;
if (enhanced_flv) {
video_codec_id = avio_rb32(s->pb);
size -= 4;
}
// 如果是增强的flv格式
if (enhanced_flv && stream_type == FLV_STREAM_TYPE_VIDEO && (flags & FLV_VIDEO_FRAMETYPE_MASK) == FLV_FRAME_VIDEO_INFO_CMD) {
int pkt_type = flags & 0x0F;
if (pkt_type == PacketTypeMetadata) {
int ret = flv_parse_video_color_info(s, st, next);
av_log(s, AV_LOG_DEBUG, "enhanced flv parse metadata ret %d and skip\n", ret);
}
goto skip;
} else if ((flags & FLV_VIDEO_FRAMETYPE_MASK) == FLV_FRAME_VIDEO_INFO_CMD) {
goto skip;
}
} else if (type == FLV_TAG_TYPE_META) { // 如果是元数据
stream_type=FLV_STREAM_TYPE_SUBTITLE; // 字幕
if (size > 13 + 1 + 4) { // Header-type metadata stuff
int type;
meta_pos = avio_tell(s->pb);
type = flv_read_metabody(s, next);
if (type == 0 && dts == 0 || type < 0) {
if (type < 0 && flv->validate_count &&
flv->validate_index[0].pos > next &&
flv->validate_index[0].pos - 4 < next) {
av_log(s, AV_LOG_WARNING, "Adjusting next position due to index mismatch\n");
next = flv->validate_index[0].pos - 4;
}
goto skip;
} else if (type == TYPE_ONTEXTDATA) {
avpriv_request_sample(s, "OnTextData packet");
return flv_data_packet(s, pkt, dts, next);
} else if (type == TYPE_ONCAPTION) {
return flv_data_packet(s, pkt, dts, next);
} else if (type == TYPE_UNKNOWN) {
stream_type = FLV_STREAM_TYPE_DATA;
}
avio_seek(s->pb, meta_pos, SEEK_SET);
}
} else { // 跳过
av_log(s, AV_LOG_DEBUG,
"Skipping flv packet: type %d, size %d, flags %d.\n",
type, size, flags);
skip:
if (avio_seek(s->pb, next, SEEK_SET) != next) {
// This can happen if flv_read_metabody above read past
// next, on a non-seekable input, and the preceding data has
// been flushed out from the IO buffer.
av_log(s, AV_LOG_ERROR, "Unable to seek to the next packet\n");
return AVERROR_INVALIDDATA;
}
ret = FFERROR_REDO;
goto leave;
}
/* skip empty data packets */
if (!size) {
ret = FFERROR_REDO;
goto leave;
}
/* now find stream */
// 寻找流
for (i = 0; i < s->nb_streams; i++) {
st = s->streams[i];
if (stream_type == FLV_STREAM_TYPE_AUDIO) {
// flv_same_audio_codec用于确保在转换为FLV格式时音频编码格式不变
if (st->codecpar->codec_type == AVMEDIA_TYPE_AUDIO &&
(s->audio_codec_id || flv_same_audio_codec(st->codecpar, flags)))
break;
} else if (stream_type == FLV_STREAM_TYPE_VIDEO) {
// flv_same_viedo_codec用于确保在转换为FLV格式时保持视频编码格式不变
if (st->codecpar->codec_type == AVMEDIA_TYPE_VIDEO &&
(s->video_codec_id || flv_same_video_codec(st->codecpar, video_codec_id)))
break;
} else if (stream_type == FLV_STREAM_TYPE_SUBTITLE) {
if (st->codecpar->codec_type == AVMEDIA_TYPE_SUBTITLE)
break;
} else if (stream_type == FLV_STREAM_TYPE_DATA) {
if (st->codecpar->codec_type == AVMEDIA_TYPE_DATA)
break;
}
}
// 2.获取TagData
// 根据读取的信息，创建一条流，将信息填充到流当中
if (i == s->nb_streams) {
static const enum AVMediaType stream_types[] = {AVMEDIA_TYPE_VIDEO, AVMEDIA_TYPE_AUDIO, AVMEDIA_TYPE_SUBTITLE, AVMEDIA_TYPE_DATA};
st = create_stream(s, stream_types[stream_type]);
if (!st)
return AVERROR(ENOMEM);
}
av_log(s, AV_LOG_TRACE, "%d %X %d \n", stream_type, flags, st->discard);
if (flv->time_pos <= pos) {
dts += flv->time_offset;
}
if ((s->pb->seekable & AVIO_SEEKABLE_NORMAL) &&
((flags & FLV_VIDEO_FRAMETYPE_MASK) == FLV_FRAME_KEY ||
stream_type == FLV_STREAM_TYPE_AUDIO))
av_add_index_entry(st, pos, dts, size, 0, AVINDEX_KEYFRAME);
if ((st->discard >= AVDISCARD_NONKEY && !((flags & FLV_VIDEO_FRAMETYPE_MASK) == FLV_FRAME_KEY || stream_type == FLV_STREAM_TYPE_AUDIO)) ||
(st->discard >= AVDISCARD_BIDIR && ((flags & FLV_VIDEO_FRAMETYPE_MASK) == FLV_FRAME_DISP_INTER && stream_type == FLV_STREAM_TYPE_VIDEO)) ||
st->discard >= AVDISCARD_ALL) {
avio_seek(s->pb, next, SEEK_SET);
ret = FFERROR_REDO;
goto leave;
}
// if not streamed and no duration from metadata then seek to end to find
// the duration from the timestamps
// 如果没有流化并且没有从元数据中获取持续时间，则寻求结束以从时间戳中查找持续时间
if ((s->pb->seekable & AVIO_SEEKABLE_NORMAL) &&
(!s->duration || s->duration == AV_NOPTS_VALUE) &&
!flv->searched_for_end) {
int size;
const int64_t pos = avio_tell(s->pb);
// Read the last 4 bytes of the file, this should be the size of the
// previous FLV tag. Use the timestamp of its payload as duration.
// 读取文件的最后4个字节，这应该是前一个FLV标记的大小。使用其有效负载的时间戳作为持续时间
int64_t fsize = avio_size(s->pb);
retry_duration:
avio_seek(s->pb, fsize - 4, SEEK_SET);
size = avio_rb32(s->pb);
if (size > 0 && size < fsize) {
// Seek to the start of the last FLV tag at position (fsize - 4 - size)
// but skip the byte indicating the type.
avio_seek(s->pb, fsize - 3 - size, SEEK_SET);
if (size == avio_rb24(s->pb) + 11) {
uint32_t ts = avio_rb24(s->pb);
ts |= (unsigned)avio_r8(s->pb) << 24;
if (ts)
s->duration = ts * (int64_t)AV_TIME_BASE / 1000;
else if (fsize >= 8 && fsize - 8 >= size) {
fsize -= size+4;
goto retry_duration;
}
}
}
avio_seek(s->pb, pos, SEEK_SET);
flv->searched_for_end = 1;
}
// 3.其他信息配置
// 如果流类型是音频，进行一些检查和配置
if (stream_type == FLV_STREAM_TYPE_AUDIO) {
int bits_per_coded_sample;
channels = (flags & FLV_AUDIO_CHANNEL_MASK) == FLV_STEREO ? 2 : 1;
sample_rate = 44100 << ((flags & FLV_AUDIO_SAMPLERATE_MASK) >>
FLV_AUDIO_SAMPLERATE_OFFSET) >> 3;
bits_per_coded_sample = (flags & FLV_AUDIO_SAMPLESIZE_MASK) ? 16 : 8;
if (!av_channel_layout_check(&st->codecpar->ch_layout) ||
!st->codecpar->sample_rate ||
!st->codecpar->bits_per_coded_sample) {
av_channel_layout_default(&st->codecpar->ch_layout, channels);
st->codecpar->sample_rate = sample_rate;
st->codecpar->bits_per_coded_sample = bits_per_coded_sample;
}
if (!st->codecpar->codec_id) {
flv_set_audio_codec(s, st, st->codecpar,
flags & FLV_AUDIO_CODECID_MASK);
flv->last_sample_rate =
sample_rate = st->codecpar->sample_rate;
flv->last_channels =
channels = st->codecpar->ch_layout.nb_channels;
} else {
AVCodecParameters *par = avcodec_parameters_alloc();
if (!par) {
ret = AVERROR(ENOMEM);
goto leave;
}
par->sample_rate = sample_rate;
par->bits_per_coded_sample = bits_per_coded_sample;
flv_set_audio_codec(s, st, par, flags & FLV_AUDIO_CODECID_MASK);
sample_rate = par->sample_rate;
avcodec_parameters_free(&par);
}
} else if (stream_type == FLV_STREAM_TYPE_VIDEO) { // 如果是视频，则进行video coedc的配置
int ret = flv_set_video_codec(s, st, video_codec_id, 1);
if (ret < 0)
return ret;
size -= ret;
} else if (stream_type == FLV_STREAM_TYPE_SUBTITLE) {
st->codecpar->codec_id = AV_CODEC_ID_TEXT;
} else if (stream_type == FLV_STREAM_TYPE_DATA) {
st->codecpar->codec_id = AV_CODEC_ID_NONE; // Opaque AMF data
}
// 相对比于雷博记录的版本，这里新增了HEVC、AV1和VP9
if (st->codecpar->codec_id == AV_CODEC_ID_AAC ||
st->codecpar->codec_id == AV_CODEC_ID_H264 ||
st->codecpar->codec_id == AV_CODEC_ID_MPEG4 ||
st->codecpar->codec_id == AV_CODEC_ID_HEVC ||
st->codecpar->codec_id == AV_CODEC_ID_AV1 ||
st->codecpar->codec_id == AV_CODEC_ID_VP9) {
int type = 0;
if (enhanced_flv && stream_type == FLV_STREAM_TYPE_VIDEO) {
type = flags & 0x0F;
} else {
type = avio_r8(s->pb);
size--;
}
if (size < 0) {
ret = AVERROR_INVALIDDATA;
goto leave;
}
if (enhanced_flv && stream_type == FLV_STREAM_TYPE_VIDEO && flv->meta_color_info_flag) {
// 更新packet的side data
flv_update_video_color_info(s, st); // update av packet side data
flv->meta_color_info_flag = 0;
}
// H264 或 H265
if (st->codecpar->codec_id == AV_CODEC_ID_H264 || st->codecpar->codec_id == AV_CODEC_ID_MPEG4 ||
(st->codecpar->codec_id == AV_CODEC_ID_HEVC && type == PacketTypeCodedFrames)) {
// sign extension
// 对应的composition time
int32_t cts = (avio_rb24(s->pb) + 0xff800000) ^ 0xff800000;
pts = av_sat_add64(dts, cts);
if (cts < 0) { // dts might be wrong
if (!flv->wrong_dts)
av_log(s, AV_LOG_WARNING,
"Negative cts, previous timestamps might be wrong.\n");
flv->wrong_dts = 1;
} else if (FFABS(dts - pts) > 1000*60*15) {
av_log(s, AV_LOG_WARNING,
"invalid timestamps %"PRId64" %"PRId64"\n", dts, pts);
dts = pts = AV_NOPTS_VALUE;
}
size -= 3;
}
if (type == 0 && (!st->codecpar->extradata || st->codecpar->codec_id == AV_CODEC_ID_AAC ||
st->codecpar->codec_id == AV_CODEC_ID_H264 || st->codecpar->codec_id == AV_CODEC_ID_HEVC ||
st->codecpar->codec_id == AV_CODEC_ID_AV1 || st->codecpar->codec_id == AV_CODEC_ID_VP9)) {
AVDictionaryEntry *t;
if (st->codecpar->extradata) {
if ((ret = flv_queue_extradata(flv, s->pb, stream_type, size)) < 0)
return ret;
ret = FFERROR_REDO;
goto leave;
}
if ((ret = flv_get_extradata(s, st, size)) < 0)
return ret;
/* Workaround for buggy Omnia A/XE encoder */
t = av_dict_get(s->metadata, "Encoder", NULL, 0);
if (st->codecpar->codec_id == AV_CODEC_ID_AAC && t && !strcmp(t->value, "Omnia A/XE"))
st->codecpar->extradata_size = 2;
ret = FFERROR_REDO;
goto leave;
}
}
/* skip empty data packets */
if (!size) {
ret = FFERROR_REDO;
goto leave;
}
// 获取pkt
ret = av_get_packet(s->pb, pkt, size);
if (ret < 0)
return ret;
// 配置dts和pts等信息
pkt->dts = dts;
pkt->pts = pts == AV_NOPTS_VALUE ? dts : pts;
pkt->stream_index = st->index;
pkt->pos = pos;
if (flv->new_extradata[stream_type]) {
int ret = av_packet_add_side_data(pkt, AV_PKT_DATA_NEW_EXTRADATA,
flv->new_extradata[stream_type],
flv->new_extradata_size[stream_type]);
if (ret >= 0) {
flv->new_extradata[stream_type] = NULL;
flv->new_extradata_size[stream_type] = 0;
}
}
if (stream_type == FLV_STREAM_TYPE_AUDIO &&
(sample_rate != flv->last_sample_rate ||
channels != flv->last_channels)) {
flv->last_sample_rate = sample_rate;
flv->last_channels = channels;
ff_add_param_change(pkt, channels, 0, sample_rate, 0, 0);
}
if (stream_type == FLV_STREAM_TYPE_AUDIO ||
(flags & FLV_VIDEO_FRAMETYPE_MASK) == FLV_FRAME_KEY ||
stream_type == FLV_STREAM_TYPE_SUBTITLE ||
stream_type == FLV_STREAM_TYPE_DATA)
pkt->flags |= AV_PKT_FLAG_KEY; // 关键帧的配置
leave:
last = avio_rb32(s->pb);
if (!flv->trust_datasize) {
if (last != orig_size + 11 && last != orig_size + 10 &&
!avio_feof(s->pb) &&
(last != orig_size || !last) && last != flv->sum_flv_tag_size &&
!flv->broken_sizes) {
av_log(s, AV_LOG_ERROR, "Packet mismatch %d %d %"PRId64"\n", last, orig_size + 11, flv->sum_flv_tag_size);
avio_seek(s->pb, pos + 1, SEEK_SET);
ret = resync(s);
av_packet_unref(pkt);
if (ret >= 0) {
goto retry;
}
}
}
if (ret >= 0)
flv->last_ts = pkt->dts;
return ret;
}
参考雷博的文章知道FLV格式如下
从上图可以看出，FLV格式的媒体文件包含几个部分：FLV Header和FLV Body，Header中包括了Signature，Version，Flags和Header Size，Body包括Previous Tag、Tag Header和Tag Data，Tag Header中又包括了Type、Datasize、Timestamp、Tiemstamp_ex和StreamID。其中，Video Tag Data的定义如下
第一个字节记录了FrameType和CodecID，从第二个字节开始记录VideoData。其中，第一个字节的前面4位表示的是帧类型：
1: keyframe (for AVC, a seekableframe)（关键帧）
2: inter frame (for AVC, a nonseekableframe)
3: disposable inter frame (H.263only)
4: generated keyframe (reservedfor server use only)
5: video info/command frame
第一个字节的后面4位表示的是CodecID：
1: JPEG (currently unused)
2: Sorenson H.263
3: Screen video
4: On2 VP6
5: On2 VP6 with alpha channel
6: Screen video version 2
7: AVC
1.3.2 解析packet（parse_packet）
函数的定义位于libavformat\demux.c中，用于解析packet，并且将解析出来的信息添加到parse_queue之中。函数最核心的内容是调用了av_parser_parse2进行pkt的解析，随后根据解析的信息对一些变量进行配置
/**
* Parse a packet, add all split parts to parse_queue.
*
* @param pkt Packet to parse; must not be NULL.
* @param flush Indicates whether to flush. If set, pkt must be blank.
*/
static int parse_packet(AVFormatContext *s, AVPacket *pkt,
int stream_index, int flush)
{
FFFormatContext *const si = ffformatcontext(s);
AVPacket *out_pkt = si->parse_pkt;
AVStream *st = s->streams[stream_index];
FFStream *const sti = ffstream(st);
const uint8_t *data = pkt->data;
int size = pkt->size;
int ret = 0, got_output = flush;
if (!size && !flush && sti->parser->flags & PARSER_FLAG_COMPLETE_FRAMES) {
// preserve 0-size sync packets
// 计算和设置AVPakcet中的属性值
compute_pkt_fields(s, st, sti->parser, pkt, AV_NOPTS_VALUE, AV_NOPTS_VALUE);
}
while (size > 0 || (flush && got_output)) {
int64_t next_pts = pkt->pts;
int64_t next_dts = pkt->dts;
int len;
// 解析packet
len = av_parser_parse2(sti->parser, sti->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 */
av_assert1(data || !len);
data = len ? data + len : data;
size -= len;
got_output = !!out_pkt->size;
if (!out_pkt->size)
continue;
if (pkt->buf && out_pkt->data == pkt->data) {
/* reference pkt->buf only when out_pkt->data is guaranteed to point
* to data in it and not in the parser's internal buffer. */
/* XXX: Ensure this is the case with all parsers when sti->parser->flags
* is PARSER_FLAG_COMPLETE_FRAMES and check for that instead? */
out_pkt->buf = av_buffer_ref(pkt->buf);
if (!out_pkt->buf) {
ret = AVERROR(ENOMEM);
goto fail;
}
} else {
ret = av_packet_make_refcounted(out_pkt);
if (ret < 0)
goto fail;
}
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 */
// 设置duration
out_pkt->duration = (sti->parser->flags & PARSER_FLAG_COMPLETE_FRAMES) ? pkt->duration : 0;
if (st->codecpar->codec_type == AVMEDIA_TYPE_AUDIO) {
if (sti->avctx->sample_rate > 0) {
out_pkt->duration =
av_rescale_q_rnd(sti->parser->duration,
(AVRational) { 1, sti->avctx->sample_rate },
st->time_base,
AV_ROUND_DOWN);
}
} else if (st->codecpar->codec_id == AV_CODEC_ID_GIF) {
if (st->time_base.num > 0 && st->time_base.den > 0 &&
sti->parser->duration) {
out_pkt->duration = sti->parser->duration;
}
}
// 设置pkt的一些属性值
out_pkt->stream_index = st->index;
out_pkt->pts = sti->parser->pts;
out_pkt->dts = sti->parser->dts;
out_pkt->pos = sti->parser->pos;
out_pkt->flags |= pkt->flags & (AV_PKT_FLAG_DISCARD | AV_PKT_FLAG_CORRUPT);
if (sti->need_parsing == AVSTREAM_PARSE_FULL_RAW)
out_pkt->pos = sti->parser->frame_offset;
if (sti->parser->key_frame == 1 ||
(sti->parser->key_frame == -1 &&
sti->parser->pict_type == AV_PICTURE_TYPE_I))
out_pkt->flags |= AV_PKT_FLAG_KEY;
if (sti->parser->key_frame == -1 && sti->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, sti->parser, out_pkt, next_dts, next_pts);
// 将packet添加到parse_queue之中
ret = avpriv_packet_list_put(&si->parse_queue,
out_pkt, NULL, 0);
if (ret < 0)
goto fail;
}
/* end of the stream => close and free the parser */
if (flush) {
av_parser_close(sti->parser);
sti->parser = NULL;
}
fail:
if (ret < 0)
av_packet_unref(out_pkt);
av_packet_unref(pkt);
return ret;
}
上面代码的核心函数是av_parser_parse2，下面进行记录
1.3.2.1 解析（av_parser_parse2）
av_parser_parse2的定义位于libavcodec\parser.c中，定义如下
// 解析数据获得一个Packet, 从输入的数据流中分离出一帧一帧的压缩编码数据
// poutbuf: 解析后输出的压缩编码数据帧
// buf: 解析前的压缩编码数据帧
// 如果函数执行完后输出数据为空（poutbuf_size为0），则代表解析还没有完成，还需要再次调用av_parser_parse2()解析一部分数据才可以得到解析后的数据帧。
// 当函数执行完后输出数据不为空的时候，代表解析完成，可以将poutbuf中的这帧数据取出来做后续处理
int av_parser_parse2(AVCodecParserContext *s, AVCodecContext *avctx,
uint8_t **poutbuf, int *poutbuf_size,
const uint8_t *buf, int buf_size,
int64_t pts, int64_t dts, int64_t pos)
{
int index, i;
uint8_t dummy_buf[AV_INPUT_BUFFER_PADDING_SIZE];
// 检查当前的codec id是否不为空
av_assert1(avctx->codec_id != AV_CODEC_ID_NONE);
/* Parsers only work for the specified codec ids. */
// 检查当前的parser的codec类型
av_assert1(avctx->codec_id == s->parser->codec_ids[0] ||
avctx->codec_id == s->parser->codec_ids[1] ||
avctx->codec_id == s->parser->codec_ids[2] ||
avctx->codec_id == s->parser->codec_ids[3] ||
avctx->codec_id == s->parser->codec_ids[4] ||
avctx->codec_id == s->parser->codec_ids[5] ||
avctx->codec_id == s->parser->codec_ids[6]);
/* 第一次进入时，flags为0，会进入if将offset设置成当前pkt的pos */
if (!(s->flags & PARSER_FLAG_FETCHED_OFFSET)) {
s->next_frame_offset =
s->cur_offset = pos;
s->flags |= PARSER_FLAG_FETCHED_OFFSET;
}
if (buf_size == 0) {
/* padding is always necessary even if EOF, so we add it here */
memset(dummy_buf, 0, sizeof(dummy_buf));
buf = dummy_buf;
} else if (s->cur_offset + buf_size != s->cur_frame_end[s->cur_frame_start_index]) { /* skip remainder packets */
/* add a new packet descriptor */
// 保留一下cur_offset, frame_end 信息, 有4个槽位供使用, 方便知道数据偏移量
i = (s->cur_frame_start_index + 1) & (AV_PARSER_PTS_NB - 1);
s->cur_frame_start_index = i;
s->cur_frame_offset[i] = s->cur_offset;
s->cur_frame_end[i] = s->cur_offset + buf_size;
s->cur_frame_pts[i] = pts;
s->cur_frame_dts[i] = dts;
s->cur_frame_pos[i] = pos;
}
if (s->fetch_timestamp) {
s->fetch_timestamp = 0;
s->last_pts = s->pts;
s->last_dts = s->dts;
s->last_pos = s->pos;
ff_fetch_timestamp(s, 0, 0, 0);
}
/* WARNING: the returned index can be negative */
index = s->parser->parser_parse(s, avctx, (const uint8_t **) poutbuf,
poutbuf_size, buf, buf_size);
av_assert0(index > -0x20000000); // The API does not allow returning AVERROR codes
#define FILL(name) if(s->name > 0 && avctx->name <= 0) avctx->name = s->name
if (avctx->codec_type == AVMEDIA_TYPE_VIDEO) {
FILL(field_order);
FILL(coded_width);
FILL(coded_height);
FILL(width);
FILL(height);
}
/* update the file pointer */
if (*poutbuf_size) {
/* fill the data for the current frame */
s->frame_offset = s->next_frame_offset;
/* offset of the next frame */
s->next_frame_offset = s->cur_offset + index;
s->fetch_timestamp = 1;
} else {
/* Don't return a pointer to dummy_buf. */
*poutbuf = NULL;
}
if (index < 0)
index = 0;
s->cur_offset += index;
return index;
}
函数的核心是parser_parse，假设初始化解析器时使用的是264格式，则会调用h264_parse，264格式的解析器定义如下
const AVCodecParser ff_h264_parser = {
.codec_ids = { AV_CODEC_ID_H264 },
.priv_data_size = sizeof(H264ParseContext),
.parser_init = init,
.parser_parse = h264_parse,
.parser_close = h264_close,
};
调用的h264_parse定义位于libavcodec\h264_parser.c中，如下所示
static int h264_parse(AVCodecParserContext *s,
AVCodecContext *avctx,
const uint8_t **poutbuf, int *poutbuf_size,
const uint8_t *buf, int buf_size)
{
H264ParseContext *p = s->priv_data;
ParseContext *pc = &p->pc;
AVRational time_base = { 0, 1 };
int next;
if (!p->got_first) {
p->got_first = 1;
if (avctx->extradata_size) {
// h264解码额外数据
// 用于解析AVCodecContext的extradata（里面实际上存储了H.264的SPS、PPS）
ff_h264_decode_extradata(avctx->extradata, avctx->extradata_size,
&p->ps, &p->is_avc, &p->nal_length_size,
avctx->err_recognition, avctx);
}
}
if (s->flags & PARSER_FLAG_COMPLETE_FRAMES) { // 解析成功一帧
next = buf_size;
} else {
next = h264_find_frame_end(p, buf, buf_size, avctx); // 找到一帧的结尾
if (ff_combine_frame(pc, next, &buf, &buf_size) < 0) {
*poutbuf = NULL;
*poutbuf_size = 0;
return buf_size;
}
if (next < 0 && next != END_NOT_FOUND) {
av_assert1(pc->last_index + next >= 0);
h264_find_frame_end(p, &pc->buffer[pc->last_index + next], -next, avctx); // update state
}
}
// 解析nal数据
parse_nal_units(s, avctx, buf, buf_size);
if (avctx->framerate.num)
time_base = av_inv_q(av_mul_q(avctx->framerate, (AVRational){2, 1}));
if (p->sei.picture_timing.cpb_removal_delay >= 0) {
s->dts_sync_point = p->sei.buffering_period.present;
s->dts_ref_dts_delta = p->sei.picture_timing.cpb_removal_delay;
s->pts_dts_delta = p->sei.picture_timing.dpb_output_delay;
} else {
s->dts_sync_point = INT_MIN;
s->dts_ref_dts_delta = INT_MIN;
s->pts_dts_delta = INT_MIN;
}
if (s->flags & PARSER_FLAG_ONCE) {
s->flags &= PARSER_FLAG_COMPLETE_FRAMES;
}
if (s->dts_sync_point >= 0) {
int64_t den = time_base.den * (int64_t)avctx->pkt_timebase.num;
if (den > 0) {
int64_t num = time_base.num * (int64_t)avctx->pkt_timebase.den;
if (s->dts != AV_NOPTS_VALUE) {
// got DTS from the stream, update reference timestamp
p->reference_dts = av_sat_sub64(s->dts, av_rescale(s->dts_ref_dts_delta, num, den));
} else if (p->reference_dts != AV_NOPTS_VALUE) {
// compute DTS based on reference timestamp
s->dts = av_sat_add64(p->reference_dts, av_rescale(s->dts_ref_dts_delta, num, den));
}
if (p->reference_dts != AV_NOPTS_VALUE && s->pts == AV_NOPTS_VALUE)
s->pts = s->dts + av_rescale(s->pts_dts_delta, num, den);
if (s->dts_sync_point > 0)
p->reference_dts = s->dts; // new reference
}
}
*poutbuf = buf;
*poutbuf_size = buf_size;
return next;
}
1.4 向pkt buffer中填充帧（avpriv_packet_list_put）
函数的主要作用是向pkt buffer中填充帧，位于libavcodec\avpkt.c中
int avpriv_packet_list_put(PacketList *packet_buffer,
AVPacket *pkt,
int (*copy)(AVPacket *dst, const AVPacket *src),
int flags)
{
PacketListEntry *pktl = av_malloc(sizeof(*pktl));
int ret;
if (!pktl)
return AVERROR(ENOMEM);
if (copy) {
get_packet_defaults(&pktl->pkt);
ret = copy(&pktl->pkt, pkt);
if (ret < 0) {
av_free(pktl);
return ret;
}
} else {
ret = av_packet_make_refcounted(pkt);
if (ret < 0) {
av_free(pktl);
return ret;
}
av_packet_move_ref(&pktl->pkt, pkt);
}
pktl->next = NULL;
if (packet_buffer->head)
packet_buffer->tail->next = pktl;
else
packet_buffer->head = pktl;
/* Add the packet in the buffered packet list. */
packet_buffer->tail = pktl;
return 0;
}
CSDN : https://blog.csdn.net/weixin_42877471
Github : https://github.com/DoFulangChen
开放原子开发者工作坊旨在鼓励更多人参与开源活动，与志同道合的开发者们相互交流开发经验、分享开发心得、获取前沿技术趋势。工作坊有多种形式的开发者活动，如meetup、训练营等，主打技术交流，干货满满，真诚地邀请各位开发者共同参与！
更多推荐
34
0- 0
已为社区贡献10条内容
所有评论(0)