参考链接
av_write_frame()
- av_write_frame()用于输出一帧视音频数据，它的声明位于libavformat\avformat.h，如下所示。
/**
* Write a packet to an output media file.
*
* This function passes the packet directly to the muxer, without any buffering
* or reordering. The caller is responsible for correctly interleaving the
* packets if the format requires it. Callers that want libavformat to handle
* the interleaving should call av_interleaved_write_frame() instead of this
* function.
*
* @param s media file handle
* @param pkt The packet containing the data to be written. Note that unlike
* av_interleaved_write_frame(), this function does not take
* ownership of the packet passed to it (though some muxers may make
* an internal reference to the input packet).
* <br>
* This parameter can be NULL (at any time, not just at the end), in
* order to immediately flush data buffered within the muxer, for
* muxers that buffer up data internally before writing it to the
* output.
* <br>
* Packet's @ref AVPacket.stream_index "stream_index" field must be
* set to the index of the corresponding stream in @ref
* AVFormatContext.streams "s->streams".
* <br>
* The timestamps (@ref AVPacket.pts "pts", @ref AVPacket.dts "dts")
* must be set to correct values in the stream's timebase (unless the
* output format is flagged with the AVFMT_NOTIMESTAMPS flag, then
* they can be set to AV_NOPTS_VALUE).
* The dts for subsequent packets passed to this function must be strictly
* increasing when compared in their respective timebases (unless the
* output format is flagged with the AVFMT_TS_NONSTRICT, then they
* merely have to be nondecreasing). @ref AVPacket.duration
* "duration") should also be set if known.
* @return < 0 on error, = 0 if OK, 1 if flushed and there is no more data to flush
*
* @see av_interleaved_write_frame()
*/
int av_write_frame(AVFormatContext *s, AVPacket *pkt);
- 简单解释一下它的参数的含义：
- s：用于输出的AVFormatContext。
- pkt：等待输出的AVPacket。
- 函数正常执行后返回值等于0。
- av_write_frame()的定义位于libavformat\mux.c，如下所示。
int av_write_frame(AVFormatContext *s, AVPacket *in)
{
FFFormatContext *const si = ffformatcontext(s);
AVPacket *pkt = si->parse_pkt;
int ret;
if (!in) {
if (s->oformat->flags & AVFMT_ALLOW_FLUSH) {
ret = s->oformat->write_packet(s, NULL);
flush_if_needed(s);
if (ret >= 0 && s->pb && s->pb->error < 0)
ret = s->pb->error;
return ret;
}
return 1;
}
if (in->flags & AV_PKT_FLAG_UNCODED_FRAME) {
pkt = in;
} else {
/* We don't own in, so we have to make sure not to modify it.
* (ff_write_chained() relies on this fact.)
* The following avoids copying in's data unnecessarily.
* Copying side data is unavoidable as a bitstream filter
* may change it, e.g. free it on errors. */
pkt->data = in->data;
pkt->size = in->size;
ret = av_packet_copy_props(pkt, in);
if (ret < 0)
return ret;
if (in->buf) {
pkt->buf = av_buffer_ref(in->buf);
if (!pkt->buf) {
ret = AVERROR(ENOMEM);
goto fail;
}
}
}
ret = write_packets_common(s, pkt, 0/*non-interleaved*/);
fail:
// Uncoded frames using the noninterleaved codepath are also freed here
av_packet_unref(pkt);
return ret;
}
- 从源代码可以看出，av_write_frame()主要完成了以下几步工作：版本差异
- （1）调用check_packet()做一些简单的检测，新版本目前将check_packet放进write_packets_common函数内
- （2）调用compute_pkt_fields2()设置AVPacket的一些属性值 compute_pkt_fields2函数感觉已被弃用，其功能合并进其余函数
- （3）调用write_packets_common()写入数据
- 如果AVPacket中的flag标记中包含AV_PKT_FLAG_UNCODED_FRAME，就会调用AVOutputFormat的write_uncoded_frame()函数（对应上文代码，pkt=in）；如果不包含那个标记，就会调用write_packet()函数（执行else里面的内容）。
av_write_frame
static int write_packets_common(AVFormatContext *s, AVPacket *pkt, int interleaved)
{
AVStream *st;
FFStream *sti;
int ret = check_packet(s, pkt);
if (ret < 0)
return ret;
st = s->streams[pkt->stream_index];
sti = ffstream(st);
ret = prepare_input_packet(s, st, pkt);
if (ret < 0)
return ret;
ret = check_bitstream(s, sti, pkt);
if (ret < 0)
return ret;
if (sti->bsfc) {
return write_packets_from_bsfs(s, st, pkt, interleaved);
} else {
return write_packet_common(s, st, pkt, interleaved);
}
}
check_packet()
- check_packet()定义位于libavformat\mux.c，如下所示。
- 从代码中可以看出，check_packet()的功能比较简单：
- 然后检查一下AVPacket的stream_index（标记了该AVPacket所属的AVStream）设置是否正常，如果为负数或者大于AVStream的个数，则返回错误信息；
- 最后检查AVPacket所属的AVStream是否属于attachment stream，这个地方没见过，目前还没有研究。
static int check_packet(AVFormatContext *s, AVPacket *pkt)
{
if (pkt->stream_index < 0 || pkt->stream_index >= s->nb_streams) {
av_log(s, AV_LOG_ERROR, "Invalid packet stream index: %d\n",
pkt->stream_index);
return AVERROR(EINVAL);
}
if (s->streams[pkt->stream_index]->codecpar->codec_type == AVMEDIA_TYPE_ATTACHMENT) {
av_log(s, AV_LOG_ERROR, "Received a packet for an attachment stream.\n");
return AVERROR(EINVAL);
}
return 0;
}
AVOutputFormat->write_packet()
- write_packet()函数的定义位于libavformat\mux.c，如下所示。
/**
* Write a packet. If AVFMT_ALLOW_FLUSH is set in flags,
* pkt can be NULL in order to flush data buffered in the muxer.
* When flushing, return 0 if there still is more data to flush,
* or 1 if everything was flushed and there is no more buffered
* data.
*/
int (*write_packet)(struct AVFormatContext *, AVPacket *pkt);
static int write_packet(AVFormatContext *s1, AVPacket *pkt)
{
const V4L2Context *s = s1->priv_data;
if (write(s->fd, pkt->data, pkt->size) == -1)
return AVERROR(errno);
return 0;
}
- write_packet()实际上是一个函数指针，指向特定的AVOutputFormat中的实现函数。
- 例如，我们看一下FLV对应的AVOutputFormat，位于libavformat\flvenc.c，如下所示。
const AVOutputFormat ff_flv_muxer = {
.name = "flv",
.long_name = NULL_IF_CONFIG_SMALL("FLV (Flash Video)"),
.mime_type = "video/x-flv",
.extensions = "flv",
.priv_data_size = sizeof(FLVContext),
.audio_codec = CONFIG_LIBMP3LAME ? AV_CODEC_ID_MP3 : AV_CODEC_ID_ADPCM_SWF,
.video_codec = AV_CODEC_ID_FLV1,
.init = flv_init,
.write_header = flv_write_header,
.write_packet = flv_write_packet,
.write_trailer = flv_write_trailer,
.check_bitstream= flv_check_bitstream,
.codec_tag = (const AVCodecTag* const []) {
flv_video_codec_ids, flv_audio_codec_ids, 0
},
.flags = AVFMT_GLOBALHEADER | AVFMT_VARIABLE_FPS |
AVFMT_TS_NONSTRICT,
.priv_class = &flv_muxer_class,
};
- 从ff_flv_muxer的定义可以看出，write_packet()指向的是flv_write_packet()函数。
- 在看flv_write_packet()函数的定义之前，我们先回顾一下FLV封装格式的结构。
FLV封装格式
- FLV封装格式如下图所示。
- PS：原图是网上找的，感觉画的很清晰，比官方的Video File Format Specification更加通俗易懂。但是图中有一个错误，就是TagHeader中的StreamID字段的长度写错了（查看了一下官方标准，应该是3字节，现在已经改过来了）。
- 从FLV的封装格式结构可以看出，它的文件数据是一个一个的Tag连接起来的，中间间隔包含着Previous Tag Size。
- 因此，flv_write_packet()函数的任务就是写入一个Tag和Previous Tag Size。
- 下面简单记录一下Tag Data的格式。
- Tag Data根据Tag的Type不同而不同：可以分为音频Tag Data，视频Tag Data以及Script Tag Data。
- 下面简述一下音频Tag Data和视频Tag Data。
Audio Tag Data
- Audio Tag开始的第1个字节包含了音频数据的参数信息，从第2个字节开始为音频流数据。
- 第1个字节的前4位的数值表示了音频数据格式：
- 0 = Linear PCM, platform endian
- 1 = ADPCM 2 = MP3
- 3 = Linear PCM, little endian
- 4 = Nellymoser 16-kHz mono
- 5 = Nellymoser 8-kHz mono
- 6 = Nellymoser
- 7 = G.711 A-law logarithmic PCM
- 8 = G.711 mu-law logarithmic PCM
- 9 = reserved
- 10 = AAC
- 14 = MP3 8-Khz
- 15 = Device-specific sound
- 第1个字节的第5-6位的数值表示采样率：0 = 5.5kHz，1 = 11KHz，2 = 22 kHz，3 = 44 kHz。
- 第1个字节的第7位表示采样精度：0 = 8bits，1 = 16bits。
- 第1个字节的第8位表示音频类型：0 = sndMono，1 = sndStereo。
- 其中，当音频编码为AAC的时候，第一个字节后面存储的是AACAUDIODATA，格式如下所示。
Video Tag Data
- Video Tag也用开始的第1个字节包含视频数据的参数信息，从第2个字节为视频流数据。
- 第1个字节的前4位的数值表示帧类型（FrameType）：
- 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1个字节的后4位的数值表示视频编码ID（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
- 其中，当音频编码为AVC（H.264）的时候，第一个字节后面存储的是AVCVIDEOPACKET，格式如下所示
flv_write_packet()
- 下面我们看一下FLV格式中write_packet()对应的实现函数flv_write_packet()的定义，位于libavformat\flvenc.c，如下所示。
static int flv_write_packet(AVFormatContext *s, AVPacket *pkt)
{
AVIOContext *pb = s->pb;
AVCodecParameters *par = s->streams[pkt->stream_index]->codecpar;
FLVContext *flv = s->priv_data;
FLVStreamContext *sc = s->streams[pkt->stream_index]->priv_data;
unsigned ts;
int size = pkt->size;
uint8_t *data = NULL;
int flags = -1, flags_size, ret = 0;
int64_t cur_offset = avio_tell(pb);
if (par->codec_type == AVMEDIA_TYPE_AUDIO && !pkt->size) {
av_log(s, AV_LOG_WARNING, "Empty audio Packet\n");
return AVERROR(EINVAL);
}
if (par->codec_id == AV_CODEC_ID_VP6F || par->codec_id == AV_CODEC_ID_VP6A ||
par->codec_id == AV_CODEC_ID_VP6 || par->codec_id == AV_CODEC_ID_AAC)
flags_size = 2;
else if (par->codec_id == AV_CODEC_ID_H264 || par->codec_id == AV_CODEC_ID_MPEG4)
flags_size = 5;
else
flags_size = 1;
if (par->codec_id == AV_CODEC_ID_AAC || par->codec_id == AV_CODEC_ID_H264
|| par->codec_id == AV_CODEC_ID_MPEG4) {
size_t side_size;
uint8_t *side = av_packet_get_side_data(pkt, AV_PKT_DATA_NEW_EXTRADATA, &side_size);
if (side && side_size > 0 && (side_size != par->extradata_size || memcmp(side, par->extradata, side_size))) {
ret = ff_alloc_extradata(par, side_size);
if (ret < 0)
return ret;
memcpy(par->extradata, side, side_size);
flv_write_codec_header(s, par, pkt->dts);
}
}
if (flv->delay == AV_NOPTS_VALUE)
flv->delay = -pkt->dts;
if (pkt->dts < -flv->delay) {
av_log(s, AV_LOG_WARNING,
"Packets are not in the proper order with respect to DTS\n");
return AVERROR(EINVAL);
}
if (par->codec_id == AV_CODEC_ID_H264 || par->codec_id == AV_CODEC_ID_MPEG4) {
if (pkt->pts == AV_NOPTS_VALUE) {
av_log(s, AV_LOG_ERROR, "Packet is missing PTS\n");
return AVERROR(EINVAL);
}
}
ts = pkt->dts;
if (s->event_flags & AVSTREAM_EVENT_FLAG_METADATA_UPDATED) {
write_metadata(s, ts);
s->event_flags &= ~AVSTREAM_EVENT_FLAG_METADATA_UPDATED;
}
avio_write_marker(pb, av_rescale(ts, AV_TIME_BASE, 1000),
pkt->flags & AV_PKT_FLAG_KEY && (flv->video_par ? par->codec_type == AVMEDIA_TYPE_VIDEO : 1) ? AVIO_DATA_MARKER_SYNC_POINT : AVIO_DATA_MARKER_BOUNDARY_POINT);
switch (par->codec_type) {
case AVMEDIA_TYPE_VIDEO:
avio_w8(pb, FLV_TAG_TYPE_VIDEO);
flags = ff_codec_get_tag(flv_video_codec_ids, par->codec_id);
flags |= pkt->flags & AV_PKT_FLAG_KEY ? FLV_FRAME_KEY : FLV_FRAME_INTER;
break;
case AVMEDIA_TYPE_AUDIO:
flags = get_audio_flags(s, par);
av_assert0(size);
avio_w8(pb, FLV_TAG_TYPE_AUDIO);
break;
case AVMEDIA_TYPE_SUBTITLE:
case AVMEDIA_TYPE_DATA:
avio_w8(pb, FLV_TAG_TYPE_META);
break;
default:
return AVERROR(EINVAL);
}
if (par->codec_id == AV_CODEC_ID_H264 || par->codec_id == AV_CODEC_ID_MPEG4) {
/* check if extradata looks like mp4 formatted */
if (par->extradata_size > 0 && *(uint8_t*)par->extradata != 1)
if ((ret = ff_avc_parse_nal_units_buf(pkt->data, &data, &size)) < 0)
return ret;
} else if (par->codec_id == AV_CODEC_ID_AAC && pkt->size > 2 &&
(AV_RB16(pkt->data) & 0xfff0) == 0xfff0) {
if (!s->streams[pkt->stream_index]->nb_frames) {
av_log(s, AV_LOG_ERROR, "Malformed AAC bitstream detected: "
"use the audio bitstream filter 'aac_adtstoasc' to fix it "
"('-bsf:a aac_adtstoasc' option with ffmpeg)\n");
return AVERROR_INVALIDDATA;
}
av_log(s, AV_LOG_WARNING, "aac bitstream error\n");
}
/* check Speex packet duration */
if (par->codec_id == AV_CODEC_ID_SPEEX && ts - sc->last_ts > 160)
av_log(s, AV_LOG_WARNING, "Warning: Speex stream has more than "
"8 frames per packet. Adobe Flash "
"Player cannot handle this!\n");
if (sc->last_ts < ts)
sc->last_ts = ts;
if (size + flags_size >= 1<<24) {
av_log(s, AV_LOG_ERROR, "Too large packet with size %u >= %u\n",
size + flags_size, 1<<24);
ret = AVERROR(EINVAL);
goto fail;
}
avio_wb24(pb, size + flags_size);
put_timestamp(pb, ts);
avio_wb24(pb, flv->reserved);
if (par->codec_type == AVMEDIA_TYPE_DATA ||
par->codec_type == AVMEDIA_TYPE_SUBTITLE ) {
int data_size;
int64_t metadata_size_pos = avio_tell(pb);
if (par->codec_id == AV_CODEC_ID_TEXT) {
// legacy FFmpeg magic?
avio_w8(pb, AMF_DATA_TYPE_STRING);
put_amf_string(pb, "onTextData");
avio_w8(pb, AMF_DATA_TYPE_MIXEDARRAY);
avio_wb32(pb, 2);
put_amf_string(pb, "type");
avio_w8(pb, AMF_DATA_TYPE_STRING);
put_amf_string(pb, "Text");
put_amf_string(pb, "text");
avio_w8(pb, AMF_DATA_TYPE_STRING);
put_amf_string(pb, pkt->data);
put_amf_string(pb, "");
avio_w8(pb, AMF_END_OF_OBJECT);
} else {
// just pass the metadata through
avio_write(pb, data ? data : pkt->data, size);
}
/* write total size of tag */
data_size = avio_tell(pb) - metadata_size_pos;
avio_seek(pb, metadata_size_pos - 10, SEEK_SET);
avio_wb24(pb, data_size);
avio_seek(pb, data_size + 10 - 3, SEEK_CUR);
avio_wb32(pb, data_size + 11);
} else {
av_assert1(flags>=0);
avio_w8(pb,flags);
if (par->codec_id == AV_CODEC_ID_VP6)
avio_w8(pb,0);
if (par->codec_id == AV_CODEC_ID_VP6F || par->codec_id == AV_CODEC_ID_VP6A) {
if (par->extradata_size)
avio_w8(pb, par->extradata[0]);
else
avio_w8(pb, ((FFALIGN(par->width, 16) - par->width) << 4) |
(FFALIGN(par->height, 16) - par->height));
} else if (par->codec_id == AV_CODEC_ID_AAC)
avio_w8(pb, 1); // AAC raw
else if (par->codec_id == AV_CODEC_ID_H264 || par->codec_id == AV_CODEC_ID_MPEG4) {
avio_w8(pb, 1); // AVC NALU
avio_wb24(pb, pkt->pts - pkt->dts);
}
avio_write(pb, data ? data : pkt->data, size);
avio_wb32(pb, size + flags_size + 11); // previous tag size
flv->duration = FFMAX(flv->duration,
pkt->pts + flv->delay + pkt->duration);
}
if (flv->flags & FLV_ADD_KEYFRAME_INDEX) {
switch (par->codec_type) {
case AVMEDIA_TYPE_VIDEO:
flv->videosize += (avio_tell(pb) - cur_offset);
flv->lasttimestamp = flv->acurframeindex / flv->framerate;
flv->acurframeindex++;
if (pkt->flags & AV_PKT_FLAG_KEY) {
double ts = flv->lasttimestamp;
int64_t pos = cur_offset;
flv->lastkeyframetimestamp = ts;
flv->lastkeyframelocation = pos;
ret = flv_append_keyframe_info(s, flv, ts, pos);
if (ret < 0)
goto fail;
}
break;
case AVMEDIA_TYPE_AUDIO:
flv->audiosize += (avio_tell(pb) - cur_offset);
break;
default:
av_log(s, AV_LOG_WARNING, "par->codec_type is type = [%d]\n", par->codec_type);
break;
}
}
fail:
av_free(data);
return ret;
}
- 我们通过源代码简单梳理一下flv_write_packet()在写入H.264/AAC时候的流程：
- （1）写入Tag Header的Type，如果是视频，代码如下：avio_w8(pb, FLV_TAG_TYPE_VIDEO); 如果是音频，代码如下： avio_w8(pb, FLV_TAG_TYPE_AUDIO);
- （2）写入Tag Header的Datasize，Timestamp和StreamID（至此完成Tag Header）：
//Tag Header - Datasize
avio_wb24(pb, size + flags_size);
//Tag Header - Timestamp 无定义
avio_wb24(pb, ts & 0xFFFFFF);
avio_w8(pb, (ts >> 24) & 0x7F); // timestamps are 32 bits _signed_
//StreamID
avio_wb24(pb, flv->reserved);
- （3）写入Tag Data的第一字节（其中flag已经在前面的代码中设置完毕）：
- //First Byte of Tag Data
- avio_w8(pb,flags);
- （4）如果编码格式VP6作相应的处理（不研究）；编码格式为AAC，写入AACAUDIODATA；编码格式为H.264，写入AVCVIDEOPACKET：
if (enc->codec_id == AV_CODEC_ID_VP6F || enc->codec_id == AV_CODEC_ID_VP6A) {
if (enc->extradata_size)
avio_w8(pb, enc->extradata[0]);
else
avio_w8(pb, ((FFALIGN(enc->width, 16) - enc->width) << 4) |
(FFALIGN(enc->height, 16) - enc->height));
} else if (enc->codec_id == AV_CODEC_ID_AAC)
avio_w8(pb, 1); // AAC raw
else if (enc->codec_id == AV_CODEC_ID_H264 || enc->codec_id == AV_CODEC_ID_MPEG4) {
//AVCVIDEOPACKET-AVCPacketType
avio_w8(pb, 1); // AVC NALU
//AVCVIDEOPACKET-CompositionTime
avio_wb24(pb, pkt->pts - pkt->dts);
}
- （5）写入数据：avio_write(pb, data ? data : pkt->data, size); //Data
- （6） 写入previous tag size：avio_wb32(pb, size + flags_size + 11); // previous tag size
- 至此，flv_write_packet()就完成了一个Tag的写入。
扫一扫
4474
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
