asp网站开发人员招聘/如何申请一个网站域名

前言

打算写一系列关于ffmpeg的文章，先写一些ffmpeg自带的example 分析，然后总结一些常用的ffmpeg的命令。我们都知道音视频编解码分为几个步骤 。以解码为例，解协议->解封装->音视频解码.。而编码就是以上步骤的反过程。今天来分析下muxing.c的代码讲解。 这个demo的功能是编码一个音视频文件。下面为代码结构的流程图

接下来我附上我自己理解添加了注释的代码

#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <math.h>#include <libavutil/avassert.h>
#include <libavutil/channel_layout.h>
#include <libavutil/opt.h>
#include <libavutil/mathematics.h>
#include <libavutil/timestamp.h>
#include <libavformat/avformat.h>
#include <libswscale/swscale.h>
#include <libswresample/swresample.h>#define STREAM_DURATION   10.0
#define STREAM_FRAME_RATE 25 /* 25 images/s */
#define STREAM_PIX_FMT    AV_PIX_FMT_YUV420P /* default pix_fmt */#define SCALE_FLAGS SWS_BICUBIC// a wrapper around a single output AVStream
typedef struct OutputStream {AVStream *st;AVCodecContext *enc;/* pts of the next frame that will be generated */int64_t next_pts;int samples_count;AVFrame *frame;AVFrame *tmp_frame;float t, tincr, tincr2;struct SwsContext *sws_ctx;struct SwrContext *swr_ctx;
} OutputStream;static void log_packet(const AVFormatContext *fmt_ctx, const AVPacket *pkt)
{AVRational *time_base = &fmt_ctx->streams[pkt->stream_index]->time_base;printf("pts:%s pts_time:%s dts:%s dts_time:%s duration:%s duration_time:%s stream_index:%d\n",av_ts2str(pkt->pts), av_ts2timestr(pkt->pts, time_base),av_ts2str(pkt->dts), av_ts2timestr(pkt->dts, time_base),av_ts2str(pkt->duration), av_ts2timestr(pkt->duration, time_base),pkt->stream_index);
}static int write_frame(AVFormatContext *fmt_ctx, AVCodecContext *c,AVStream *st, AVFrame *frame)
{int ret;// send the frame to the encoder//发送帧数据给编码器ret = avcodec_send_frame(c, frame);if (ret < 0) {fprintf(stderr, "Error sending a frame to the encoder: %s\n",av_err2str(ret));exit(1);}while (ret >= 0) {AVPacket pkt = { 0 };//接受压缩数据ret = avcodec_receive_packet(c, &pkt);if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF)break;else if (ret < 0) {fprintf(stderr, "Error encoding a frame: %s\n", av_err2str(ret));exit(1);}//把Packet的pts从编码器上下文的时间基转换成以流的时间基的pts/* rescale output packet timestamp values from codec to stream timebase */av_packet_rescale_ts(&pkt, c->time_base, st->time_base);pkt.stream_index = st->index;/* Write the compressed frame to the media file. */log_packet(fmt_ctx, &pkt);//写压缩数据到文件ret = av_interleaved_write_frame(fmt_ctx, &pkt);av_packet_unref(&pkt);if (ret < 0) {fprintf(stderr, "Error while writing output packet: %s\n", av_err2str(ret));exit(1);}}return ret == AVERROR_EOF ? 1 : 0;
}/* Add an output stream. */
static void add_stream(OutputStream *ost, AVFormatContext *oc,const AVCodec **codec,enum AVCodecID codec_id)
{AVCodecContext *c;int i;/* find the encoder *///根据id得到相应的编码器结构体*codec = avcodec_find_encoder(codec_id);if (!(*codec)) {//没找到退出fprintf(stderr, "Could not find encoder for '%s'\n",avcodec_get_name(codec_id));exit(1);}//新建一路流 第二参数无用的，填NULL就可以ost->st = avformat_new_stream(oc, NULL);if (!ost->st) {fprintf(stderr, "Could not allocate stream\n");exit(1);}//设置流id,这里使用流的总数-1 ，即流的id从0开始增加ost->st->id = oc->nb_streams-1;//根据编解码器结构体分配个编解码器上下文c = avcodec_alloc_context3(*codec);if (!c) {fprintf(stderr, "Could not alloc an encoding context\n");exit(1);}ost->enc = c;//给编解码器上下文赋值参数switch ((*codec)->type) {//音频 采样格式 、比特率 采样率、通道数、通道样式 、流时间基case AVMEDIA_TYPE_AUDIO://采样格式 如果支持的列表不为空取第一个否则取AV_SAMPLE_FMT_FLTP float planar模式c->sample_fmt  = (*codec)->sample_fmts ?(*codec)->sample_fmts[0] : AV_SAMPLE_FMT_FLTP;c->bit_rate    = 64000;//64kc->sample_rate = 44100;if ((*codec)->supported_samplerates) {c->sample_rate = (*codec)->supported_samplerates[0];for (i = 0; (*codec)->supported_samplerates[i]; i++) {if ((*codec)->supported_samplerates[i] == 44100)c->sample_rate = 44100;}}//根据通道布局获取通道数c->channels        = av_get_channel_layout_nb_channels(c->channel_layout);c->channel_layout = AV_CH_LAYOUT_STEREO;//默认立体声if ((*codec)->channel_layouts) {c->channel_layout = (*codec)->channel_layouts[0];for (i = 0; (*codec)->channel_layouts[i]; i++) {if ((*codec)->channel_layouts[i] == AV_CH_LAYOUT_STEREO)c->channel_layout = AV_CH_LAYOUT_STEREO;}}c->channels        = av_get_channel_layout_nb_channels(c->channel_layout);//以采样率为时间基，时间基的(1/c->sample_rate) *时间戳等于秒数//AVRational为2个变量一个分子、一个分母的结构ost->st->time_base = (AVRational){ 1, c->sample_rate };break;//视频 编码器id 、比特率、视频宽高、流时间基case AVMEDIA_TYPE_VIDEO:c->codec_id = codec_id;c->bit_rate = 400000;//分辨率必须为2的倍数/* Resolution must be a multiple of two. */c->width    = 352;c->height   = 288;/* timebase: This is the fundamental unit of time (in seconds) in terms* of which frame timestamps are represented. For fixed-fps content,* timebase should be 1/framerate and timestamp increments should be* identical to 1. *///用帧率表示ost->st->time_base = (AVRational){ 1, STREAM_FRAME_RATE };c->time_base       = ost->st->time_base;//gop画面组大小，2个I帧的间距c->gop_size      = 12; /* emit one intra frame every twelve frames at most */c->pix_fmt       = STREAM_PIX_FMT;if (c->codec_id == AV_CODEC_ID_MPEG2VIDEO) {/* just for testing, we also add B-frames *///设置最大b帧c->max_b_frames = 2;}if (c->codec_id == AV_CODEC_ID_MPEG1VIDEO) {//需要避免使用一些coeffs溢出的宏块，正常的视频不会发生/* Needed to avoid using macroblocks in which some coeffs overflow.* This does not happen with normal video, it just happens here as* the motion of the chroma plane does not match the luma plane. */c->mb_decision = 2;}break;default:break;}//有些格式希望流头是分开的/* Some formats want stream headers to be separate. */if (oc->oformat->flags & AVFMT_GLOBALHEADER)c->flags |= AV_CODEC_FLAG_GLOBAL_HEADER;
}/**************************************************************/
/* audio output */static AVFrame *alloc_audio_frame(enum AVSampleFormat sample_fmt,uint64_t channel_layout,int sample_rate, int nb_samples)
{    //分配原始音频帧存储，设置参数AVFrame *frame = av_frame_alloc();int ret;if (!frame) {fprintf(stderr, "Error allocating an audio frame\n");exit(1);}frame->format = sample_fmt;//采样格式frame->channel_layout = channel_layout;//通道frame->sample_rate = sample_rate;//采样率frame->nb_samples = nb_samples;//每帧采样个数if (nb_samples) {ret = av_frame_get_buffer(frame, 0);if (ret < 0) {fprintf(stderr, "Error allocating an audio buffer\n");exit(1);}}return frame;
}static void open_audio(AVFormatContext *oc, const AVCodec *codec,OutputStream *ost, AVDictionary *opt_arg)
{AVCodecContext *c;int nb_samples;int ret;AVDictionary *opt = NULL;c = ost->enc;//拷贝参数/* open it */av_dict_copy(&opt, opt_arg, 0);ret = avcodec_open2(c, codec, &opt);av_dict_free(&opt);if (ret < 0) {fprintf(stderr, "Could not open audio codec: %s\n", av_err2str(ret));exit(1);}/* init signal generator */ost->t     = 0;ost->tincr = 2 * M_PI * 110.0 / c->sample_rate;/* increment frequency by 110 Hz per second */ost->tincr2 = 2 * M_PI * 110.0 / c->sample_rate / c->sample_rate;//如果是固定的样本数，每一帧音频的样本数，如果是可变的填10000，不是每个编码器都有固定的数值if (c->codec->capabilities & AV_CODEC_CAP_VARIABLE_FRAME_SIZE)nb_samples = 10000;elsenb_samples = c->frame_size;//分配帧空间ost->frame     = alloc_audio_frame(c->sample_fmt, c->channel_layout,c->sample_rate, nb_samples);因为我们编码数据的时候是采用AV_SAMPLE_FMT_S16存放数据的，如果编码器的c->sample_fmt对不上我们就要转换成编码器中的采样类型ost->tmp_frame = alloc_audio_frame(AV_SAMPLE_FMT_S16, c->channel_layout,c->sample_rate, nb_samples);//拷贝参数/* copy the stream parameters to the muxer */ret = avcodec_parameters_from_context(ost->st->codecpar, c);if (ret < 0) {fprintf(stderr, "Could not copy the stream parameters\n");exit(1);}//初始化音频格式变化 变换采样格式/* create resampler context */ost->swr_ctx = swr_alloc();if (!ost->swr_ctx) {fprintf(stderr, "Could not allocate resampler context\n");exit(1);}/* set options */av_opt_set_int       (ost->swr_ctx, "in_channel_count",   c->channels,       0);av_opt_set_int       (ost->swr_ctx, "in_sample_rate",     c->sample_rate,    0);av_opt_set_sample_fmt(ost->swr_ctx, "in_sample_fmt",      AV_SAMPLE_FMT_S16, 0);av_opt_set_int       (ost->swr_ctx, "out_channel_count",  c->channels,       0);av_opt_set_int       (ost->swr_ctx, "out_sample_rate",    c->sample_rate,    0);av_opt_set_sample_fmt(ost->swr_ctx, "out_sample_fmt",     c->sample_fmt,     0);/* initialize the resampling context */if ((ret = swr_init(ost->swr_ctx)) < 0) {fprintf(stderr, "Failed to initialize the resampling context\n");exit(1);}
}/* Prepare a 16 bit dummy audio frame of 'frame_size' samples and* 'nb_channels' channels. */
static AVFrame *get_audio_frame(OutputStream *ost)
{AVFrame *frame = ost->tmp_frame;int j, i, v;int16_t *q = (int16_t*)frame->data[0];//录制视频为10秒，大于10秒结束/* check if we want to generate more frames */if (av_compare_ts(ost->next_pts, ost->enc->time_base,STREAM_DURATION, (AVRational){ 1, 1 }) > 0)return NULL;for (j = 0; j <frame->nb_samples; j++) {v = (int)(sin(ost->t) * 10000);for (i = 0; i < ost->enc->channels; i++)*q++ = v;ost->t     += ost->tincr;ost->tincr += ost->tincr2;}//音频帧时间戳pts的计算，因为音频time_base是以采样率来计算的，如采样率44100 就1秒44100个采样，所以这里时间戳就可以用每帧的采样个数累加起来计算//当累加起来有44100个采样刚好1秒frame->pts = ost->next_pts;ost->next_pts  += frame->nb_samples;return frame;
}/** encode one audio frame and send it to the muxer* return 1 when encoding is finished, 0 otherwise*/
static int write_audio_frame(AVFormatContext *oc, OutputStream *ost)
{AVCodecContext *c;AVFrame *frame;int ret;int dst_nb_samples;c = ost->enc;frame = get_audio_frame(ost);if (frame) {/* convert samples from native format to destination codec format, using the resampler *//* compute destination number of samples */// av_rescale_rnd(int64_t 	a,int64_t 	b,int64_t 	c,enum AVRounding 	rnd ) 类似等同于a*b/c操作	//swr_get_delay(ost->swr_ctx, c->sample_rate)得到音频重采样时所花费的时间（这里第二个参数为采样率，所以返回的是采样个数）dst_nb_samples = av_rescale_rnd(swr_get_delay(ost->swr_ctx, c->sample_rate) + frame->nb_samples,c->sample_rate, c->sample_rate, AV_ROUND_UP);//断言                                av_assert0(dst_nb_samples == frame->nb_samples);/* when we pass a frame to the encoder, it may keep a reference to it* internally;* make sure we do not overwrite it here*/ret = av_frame_make_writable(ost->frame);if (ret < 0)exit(1);
//转换成指定格式/* convert to destination format */ret = swr_convert(ost->swr_ctx,ost->frame->data, dst_nb_samples,(const uint8_t **)frame->data, frame->nb_samples);if (ret < 0) {fprintf(stderr, "Error while converting\n");exit(1);}frame = ost->frame;//转换以c tiame_base为基的时间戳frame->pts = av_rescale_q(ost->samples_count, (AVRational){1, c->sample_rate}, c->time_base);ost->samples_count += dst_nb_samples;}return write_frame(oc, c, ost->st, frame);
}/**************************************************************/
/* video output */static AVFrame *alloc_picture(enum AVPixelFormat pix_fmt, int width, int height)
{AVFrame *picture;int ret;picture = av_frame_alloc();if (!picture)return NULL;picture->format = pix_fmt;//数据格式picture->width  = width;//宽度picture->height = height;//高度/* allocate the buffers for the frame data */ret = av_frame_get_buffer(picture, 0);if (ret < 0) {fprintf(stderr, "Could not allocate frame data.\n");exit(1);}return picture;
}static void open_video(AVFormatContext *oc, const AVCodec *codec,OutputStream *ost, AVDictionary *opt_arg)
{int ret;AVCodecContext *c = ost->enc;AVDictionary *opt = NULL;//拷贝参数    av_dict_copy(&opt, opt_arg, 0);//打开编码器/* open the codec */ret = avcodec_open2(c, codec, &opt);av_dict_free(&opt);if (ret < 0) {fprintf(stderr, "Could not open video codec: %s\n", av_err2str(ret));exit(1);}//分配原始数据AVFrame的大小/* allocate and init a re-usable frame */ost->frame = alloc_picture(c->pix_fmt, c->width, c->height);if (!ost->frame) {fprintf(stderr, "Could not allocate video frame\n");exit(1);}/* If the output format is not YUV420P, then a temporary YUV420P* picture is needed too. It is then converted to the required* output format. */ost->tmp_frame = NULL;//因为我们编码数据的时候是采用AV_PIX_FMT_YUV420存放数据的，如果编码器的pix_fmt对不上我们就要转换成编码器中的采样类型if (c->pix_fmt != AV_PIX_FMT_YUV420P) {ost->tmp_frame = alloc_picture(AV_PIX_FMT_YUV420P, c->width, c->height);if (!ost->tmp_frame) {fprintf(stderr, "Could not allocate temporary picture\n");exit(1);}}//从上编码上下文中拷贝参数到流/* copy the stream parameters to the muxer */ret = avcodec_parameters_from_context(ost->st->codecpar, c);if (ret < 0) {fprintf(stderr, "Could not copy the stream parameters\n");exit(1);}
}/* Prepare a dummy image. */
static void fill_yuv_image(AVFrame *pict, int frame_index,int width, int height)
{int x, y, i;i = frame_index;/* Y */for (y = 0; y < height; y++)for (x = 0; x < width; x++)pict->data[0][y * pict->linesize[0] + x] = x + y + i * 3;/* Cb and Cr */for (y = 0; y < height / 2; y++) {for (x = 0; x < width / 2; x++) {pict->data[1][y * pict->linesize[1] + x] = 128 + y + i * 2;pict->data[2][y * pict->linesize[2] + x] = 64 + x + i * 5;}}
}static AVFrame *get_video_frame(OutputStream *ost)
{AVCodecContext *c = ost->enc;//大于10秒不录制了/* check if we want to generate more frames */if (av_compare_ts(ost->next_pts, c->time_base,STREAM_DURATION, (AVRational){ 1, 1 }) > 0)return NULL;//如果帧是可写的，则不执行任何操作，如果不是，则分配新的缓冲区并复制数据。/* when we pass a frame to the encoder, it may keep a reference to it* internally; make sure we do not overwrite it here */if (av_frame_make_writable(ost->frame) < 0)exit(1);if (c->pix_fmt != AV_PIX_FMT_YUV420P) {// AV_PIX_FMT_YUV420P重采样为目标的的格式/* as we only generate a YUV420P picture, we must convert it* to the codec pixel format if needed */if (!ost->sws_ctx) {ost->sws_ctx = sws_getContext(c->width, c->height,AV_PIX_FMT_YUV420P,c->width, c->height,c->pix_fmt,SCALE_FLAGS, NULL, NULL, NULL);if (!ost->sws_ctx) {fprintf(stderr,"Could not initialize the conversion context\n");exit(1);}}fill_yuv_image(ost->tmp_frame, ost->next_pts, c->width, c->height);sws_scale(ost->sws_ctx, (const uint8_t * const *) ost->tmp_frame->data,ost->tmp_frame->linesize, 0, c->height, ost->frame->data,ost->frame->linesize);} else {//填充视频帧数据fill_yuv_image(ost->frame, ost->next_pts, c->width, c->height);}//赋值pts 视频的时间基是1/帧率 所以这里每完成1帧pts时间戳加1 ost->frame->pts = ost->next_pts++;return ost->frame;
}/** encode one video frame and send it to the muxer* return 1 when encoding is finished, 0 otherwise*/
static int write_video_frame(AVFormatContext *oc, OutputStream *ost)
{return write_frame(oc, ost->enc, ost->st, get_video_frame(ost));
}static void close_stream(AVFormatContext *oc, OutputStream *ost)
{avcodec_free_context(&ost->enc);av_frame_free(&ost->frame);av_frame_free(&ost->tmp_frame);sws_freeContext(ost->sws_ctx);swr_free(&ost->swr_ctx);
}/**************************************************************/
/* media file output */int main(int argc, char **argv)
{OutputStream video_st = { 0 }, audio_st = { 0 };const AVOutputFormat *fmt;const char *filename;AVFormatContext *oc;const AVCodec *audio_codec, *video_codec;int ret;int have_video = 0, have_audio = 0;int encode_video = 0, encode_audio = 0;AVDictionary *opt = NULL;int i;if (argc < 2) {printf("usage: %s output_file\n""API example program to output a media file with libavformat.\n""This program generates a synthetic audio and video stream, encodes and\n""muxes them into a file named output_file.\n""The output format is automatically guessed according to the file extension.\n""Raw images can also be output by using '%%d' in the filename.\n""\n", argv[0]);return 1;}filename = argv[1];for (i = 2; i+1 < argc; i+=2) {if (!strcmp(argv[i], "-flags") || !strcmp(argv[i], "-fflags"))//argv[i]+1 等于flags 或者fflags  arg[i+1]就是下一个参数值//设置命令参数值对到AVDictionary 结构体中av_dict_set(&opt, argv[i]+1, argv[i+1], 0);}/* allocate the output media context *///分配输出格式上下文，第二个参数为 AVOutputFormat * 	oformat,第三个参数为const char * 	format_name//如果第二、第三个参数为空，则根据文件名来确定输出的格式avformat_alloc_output_context2(&oc, NULL, NULL, filename);if (!oc) {//无法从扩展名中推断出格式，就使用mpeg格式printf("Could not deduce output format from file extension: using MPEG.\n");avformat_alloc_output_context2(&oc, NULL, "mpeg", filename);}if (!oc)return 1;//AVOutputFormat 结构体则保存了格式的信息和一些常规设置如格式名称、mime_type、默认的视频、音频、字幕的编解码器id等fmt = oc->oformat;/* Add the audio and video streams using the default format codecs* and initialize the codecs. */if (fmt->video_codec != AV_CODEC_ID_NONE) {add_stream(&video_st, oc, &video_codec, fmt->video_codec);have_video = 1;encode_video = 1;}if (fmt->audio_codec != AV_CODEC_ID_NONE) {add_stream(&audio_st, oc, &audio_codec, fmt->audio_codec);have_audio = 1;encode_audio = 1;}//设置完参数，打开视频音频编码器，分配编码缓存区/* Now that all the parameters are set, we can open the audio and* video codecs and allocate the necessary encode buffers. */if (have_video)open_video(oc, video_codec, &video_st, opt);if (have_audio)open_audio(oc, audio_codec, &audio_st, opt);//打印出来av_dump_format(oc, 0, filename, 1);//创建并初始化AVIOContext，用于访问url所指示的资源/* open the output file, if needed */if (!(fmt->flags & AVFMT_NOFILE)) {ret = avio_open(&oc->pb, filename, AVIO_FLAG_WRITE);if (ret < 0) {fprintf(stderr, "Could not open '%s': %s\n", filename,av_err2str(ret));return 1;}}//写入头/* Write the stream header, if any. */ret = avformat_write_header(oc, &opt);if (ret < 0) {fprintf(stderr, "Error occurred when opening output file: %s\n",av_err2str(ret));return 1;}//开始编码写入数据while (encode_video || encode_audio) {/* select the stream to encode *///av_compare_ts 比较2个时间 如果视频时间比音频时间前就小于0 if (encode_video &&(!encode_audio || av_compare_ts(video_st.next_pts, video_st.enc->time_base,audio_st.next_pts, audio_st.enc->time_base) <= 0)) {encode_video = !write_video_frame(oc, &video_st);} else {encode_audio = !write_audio_frame(oc, &audio_st);}}//写入尾/* Write the trailer, if any. The trailer must be written before you* close the CodecContexts open when you wrote the header; otherwise* av_write_trailer() may try to use memory that was freed on* av_codec_close(). */av_write_trailer(oc);//释放内存/* Close each codec. */if (have_video)close_stream(oc, &video_st);if (have_audio)close_stream(oc, &audio_st);if (!(fmt->flags & AVFMT_NOFILE))/* Close the output file. */avio_closep(&oc->pb);/* free the stream */avformat_free_context(oc);return 0;
}