title: ffmpeg_sample解读_transcoding
date: 2020-11-15 10:15:02
tags: [读书笔记]
typora-copy-images-to: ./imgs
typora-root-url: ./imgs
总结
* 这也是一个转换音视频文件的过程,同时这里加入了过滤器.把文件拆成流,然后解码出packet后.又经过过滤器的处理.
* 处理完成后才再次编码.然后写出到文件中
流程图
graph TB
isInput{isInput?}
-->|yes|oif[open_input_file]
isInput-->|no|oof[open_output_file]
oif-->afoi[avformat_open_input]
-->affsi[avformat_find_stream_info]
-->acfd[avcodec_find_decoder]
-->acac[avcodec_alloc_context3]
-->acptc[avcodec_parameters_to_context]
-->aco[avcodec_open2]
oof-->afaoc[avformat_alloc_output_context2]
-->afns[avformat_new_stream]
-->acfe[avcodec_find_encoder]
-->acoe[avcodec_open2]
-->acpfc[avcodec_parameters_from_context]
-->avo[avio_open]
-->afwh[avformat_write_header]
-->if[init_filters]
aco-->if[init_filter]
-->afia[avfilter_inout_alloc]
-->afga[avfilter_graph_alloc]
-->afgbn[avfilter_get_by_name]
-->afgcf[avfilter_graph_create_filter]
-->afgpp[avfilter_graph_parse_ptr]
-->afgc[avfilter_graph_config]
-->arf{av_read_frame>0?}
-->|no|fe[flush_encoder]
-->awt[av_write_trailer]
-->release[release]
arf-->|yes|afa[av_frame_alloc]
-->aprt[av_packet_rescale_ts]
-->acdv[avcodec_decode_video2]
-->fewf[filter_encode_write_frame]
-->abaff[av_buffersrc_add_frame_flags]
-->abgf[av_buffersink_get_frame]
-->ewf[encode_write_frame]
-->acev[avcodec_encode_video2]
-->aprto[av_packet_rescale_ts]
-->aiwf[av_interleaved_write_frame]
-->fe
这个代码流程图分两部分,第一部分是初始化输入输出的格式上下文,编码器上下文(对应输出),解码器上下文(对应输入,),以及过滤器.如下,
image-20201116170029996
然后是遍历解码输出的文件.获取packet,送入解码器解码出帧,再把帧送入过滤器中进行处理.处理完成后从过滤器中取出帧,然后再次编码成packet.最后写出到输出文件中.
image-20201116170254409
代码
/**
* @file
* API example for demuxing, decoding, filtering, encoding and muxing
* @example transcoding.c
*/
#include
#include
#include
#include
#include
#include
static AVFormatContext *ifmt_ctx;
static AVFormatContext *ofmt_ctx;
typedef struct FilteringContext {
AVFilterContext *buffersink_ctx;
AVFilterContext *buffersrc_ctx;
AVFilterGraph *filter_graph;
} FilteringContext;
static FilteringContext *filter_ctx;
typedef struct StreamContext {
AVCodecContext *dec_ctx;
AVCodecContext *enc_ctx;
} StreamContext;
static StreamContext *stream_ctx;
///打开输入文件.为每个数据流创建解码器上下文,格式上下文,与流索引对应起来
//对于输入文件来说.都是从输入文件的流中建立解码器,和解码器上下文,这是标准操作了
static int open_input_file(const char *filename) {
int ret;
unsigned int i;
ifmt_ctx = NULL;
//打开文件,初始化format格式上下文
if ((ret = avformat_open_input(&ifmt_ctx, filename, NULL, NULL)) < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot open input file\n");
return ret;
}
//找到合适的流
if ((ret = avformat_find_stream_info(ifmt_ctx, NULL)) < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot find stream information\n");
return ret;
}
//分配流信息数组,数组大小是 流的总数* streamContext 的大小. 也就是每个流都有编码解码上下文
stream_ctx = av_mallocz_array(ifmt_ctx->nb_streams, sizeof(*stream_ctx));
if (!stream_ctx)
return AVERROR(ENOMEM);
//根据所有的流信息,分配给stream_ctx里每个解码器上下文
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
//拿到流.及根据流的信息找到解码器
AVStream *stream = ifmt_ctx->streams[i];
AVCodec *dec = avcodec_find_decoder(stream->codecpar->codec_id);
AVCodecContext *codec_ctx;
if (!dec) {
av_log(NULL, AV_LOG_ERROR, "Failed to find decoder for stream #%u\n", i);
return AVERROR_DECODER_NOT_FOUND;
}
//通过解码器给解码器上下文分配内存
codec_ctx = avcodec_alloc_context3(dec);
if (!codec_ctx) {
av_log(NULL, AV_LOG_ERROR, "Failed to allocate the decoder context for stream #%u\n",
i);
return AVERROR(ENOMEM);
}
//拷贝流中的信息到解码器上下文中
ret = avcodec_parameters_to_context(codec_ctx, stream->codecpar);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Failed to copy decoder parameters to input decoder context "
"for stream #%u\n", i);
return ret;
}
/* Reencode video & audio and remux subtitles etc. */
if (codec_ctx->codec_type == AVMEDIA_TYPE_VIDEO
|| codec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
if (codec_ctx->codec_type == AVMEDIA_TYPE_VIDEO)
//根据流信息和格式上下文,猜猜视频的帧率
codec_ctx->framerate = av_guess_frame_rate(ifmt_ctx, stream, NULL);
/* Open decoder */
//打开解码器上下文
ret = avcodec_open2(codec_ctx, dec, NULL);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Failed to open decoder for stream #%u\n", i);
return ret;
}
}
//保存到对应流索引的解码器上下文中
stream_ctx[i].dec_ctx = codec_ctx;
}
//打印格式信息
av_dump_format(ifmt_ctx, 0, filename, 0);
return 0;
}
//大家输出文件.初始化输出的编码器上下文.和格式上下文,都保存在同一个数组 stream_ctx中了
//输出文件的编码器上下文.则需要我们自己设定一些参数.或者从编码器上下文中拷贝
static int open_output_file(const char *filename) {
AVStream *out_stream;
AVStream *in_stream;
AVCodecContext *dec_ctx, *enc_ctx;
AVCodec *encoder;
int ret;
unsigned int i;
ofmt_ctx = NULL;
//分配输出格式上下文空间
avformat_alloc_output_context2(&ofmt_ctx, NULL, NULL, filename);
if (!ofmt_ctx) {
av_log(NULL, AV_LOG_ERROR, "Could not create output context\n");
return AVERROR_UNKNOWN;
}
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
//创建输出流.此时输出流中没有东西
out_stream = avformat_new_stream(ofmt_ctx, NULL);
if (!out_stream) {
av_log(NULL, AV_LOG_ERROR, "Failed allocating output stream\n");
return AVERROR_UNKNOWN;
}
//输入流中的解码上下文
in_stream = ifmt_ctx->streams[i];
dec_ctx = stream_ctx[i].dec_ctx;
if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO
|| dec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
/* in this example, we choose transcoding to same codec */
//找到输入流中的编码器,输入输出流使用相同的编解码id
encoder = avcodec_find_encoder(dec_ctx->codec_id);
if (!encoder) {
av_log(NULL, AV_LOG_FATAL, "Necessary encoder not found\n");
return AVERROR_INVALIDDATA;
}
//根据编码器获为编码器上下文分配空间
enc_ctx = avcodec_alloc_context3(encoder);
if (!enc_ctx) {
av_log(NULL, AV_LOG_FATAL, "Failed to allocate the encoder context\n");
return AVERROR(ENOMEM);
}
/* In this example, we transcode to same properties (picture size,
* sample rate etc.). These properties can be changed for output
* streams easily using filters */
// 视频流的输出参数和输入参数保持一致
if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO) {
enc_ctx->height = dec_ctx->height;
enc_ctx->width = dec_ctx->width;
enc_ctx->sample_aspect_ratio = dec_ctx->sample_aspect_ratio;
/* take first format from list of supported formats */
if (encoder->pix_fmts)
enc_ctx->pix_fmt = encoder->pix_fmts[0];
else
enc_ctx->pix_fmt = dec_ctx->pix_fmt;
/* video time_base can be set to whatever is handy and supported by encoder */
enc_ctx->time_base = av_inv_q(dec_ctx->framerate);
} else {//音频流.输出的编码器上下文和输入的解码器上下文参数也一致
enc_ctx->sample_rate = dec_ctx->sample_rate;
enc_ctx->channel_layout = dec_ctx->channel_layout;
enc_ctx->channels = av_get_channel_layout_nb_channels(enc_ctx->channel_layout);
/* take first format from list of supported formats */
enc_ctx->sample_fmt = encoder->sample_fmts[0];
enc_ctx->time_base = (AVRational) {1, enc_ctx->sample_rate};
}
if (ofmt_ctx->oformat->flags & AVFMT_GLOBALHEADER)
enc_ctx->flags |= AV_CODEC_FLAG_GLOBAL_HEADER;
/* Third parameter can be used to pass settings to encoder */
//打开编码器上下文
ret = avcodec_open2(enc_ctx, encoder, NULL);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot open video encoder for stream #%u\n", i);
return ret;
}
//用编码器上下文的参数填充输出流的编码参数, 和上边输入文件的处理不一样
ret = avcodec_parameters_from_context(out_stream->codecpar, enc_ctx);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR,
"Failed to copy encoder parameters to output stream #%u\n", i);
return ret;
}
//保持编码器上下文
out_stream->time_base = enc_ctx->time_base;
stream_ctx[i].enc_ctx = enc_ctx;
} else if (dec_ctx->codec_type == AVMEDIA_TYPE_UNKNOWN) {
av_log(NULL, AV_LOG_FATAL, "Elementary stream #%d is of unknown type, cannot proceed\n",
i);
return AVERROR_INVALIDDATA;
} else {
/* if this stream must be remuxed */
//拷贝输入参数到输出参数,这是既非音频流也非食品流,直接拷贝输入流参数到输出流中
ret = avcodec_parameters_copy(out_stream->codecpar, in_stream->codecpar);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Copying parameters for stream #%u failed\n", i);
return ret;
}
out_stream->time_base = in_stream->time_base;
}
}
av_dump_format(ofmt_ctx, 0, filename, 1);
if (!(ofmt_ctx->oformat->flags & AVFMT_NOFILE)) {
//打开输出文件,绑定avio上下文.写出模式
ret = avio_open(&ofmt_ctx->pb, filename, AVIO_FLAG_WRITE);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Could not open output file '%s'", filename);
return ret;
}
}
/* init muxer, write output file header */
//写出header内容
ret = avformat_write_header(ofmt_ctx, NULL);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Error occurred when opening output file\n");
return ret;
}
return 0;
}
/**
* 初始化过滤器,这里还有一个通过字符串filter_spec来创建的过滤器
* @param fctx
* @param dec_ctx
* @param enc_ctx
* @param filter_spec
* @return
*/
static int init_filter(FilteringContext *fctx, AVCodecContext *dec_ctx,
AVCodecContext *enc_ctx, const char *filter_spec) {
char args[512];
int ret = 0;
const AVFilter *buffersrc = NULL;
const AVFilter *buffersink = NULL;
AVFilterContext *buffersrc_ctx = NULL;
AVFilterContext *buffersink_ctx = NULL;
AVFilterInOut *outputs = avfilter_inout_alloc();
AVFilterInOut *inputs = avfilter_inout_alloc();
//过滤器图形.用来连接多个过滤器的
AVFilterGraph *filter_graph = avfilter_graph_alloc();
if (!outputs || !inputs || !filter_graph) {
ret = AVERROR(ENOMEM);
goto end;
}
if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO) {
//输入输出的buffer
buffersrc = avfilter_get_by_name("buffer");
buffersink = avfilter_get_by_name("buffersink");
if (!buffersrc || !buffersink) {
av_log(NULL, AV_LOG_ERROR, "filtering source or sink element not found\n");
ret = AVERROR_UNKNOWN;
goto end;
}
//赋值过滤器参数,宽高,格式,时间基,宽高比
snprintf(args, sizeof(args),
"video_size=%dx%d:pix_fmt=%d:time_base=%d/%d:pixel_aspect=%d/%d",
dec_ctx->width, dec_ctx->height, dec_ctx->pix_fmt,
dec_ctx->time_base.num, dec_ctx->time_base.den,
dec_ctx->sample_aspect_ratio.num,
dec_ctx->sample_aspect_ratio.den);
//用参数和buffer初始化输入的过滤器上下文,并添加到过滤器图形中
ret = avfilter_graph_create_filter(&buffersrc_ctx, buffersrc, "in",
args, NULL, filter_graph);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot create buffer source\n");
goto end;
}
//初始化输出的过滤器上下文,并添加到图形中
ret = avfilter_graph_create_filter(&buffersink_ctx, buffersink, "out",
NULL, NULL, filter_graph);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot create buffer sink\n");
goto end;
}
//输出过滤器上下文,设置参数
ret = av_opt_set_bin(buffersink_ctx, "pix_fmts",
(uint8_t *) &enc_ctx->pix_fmt, sizeof(enc_ctx->pix_fmt),
AV_OPT_SEARCH_CHILDREN);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot set output pixel format\n");
goto end;
}
} else if (dec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
//音频和视频类似.知识设置的参数不同. 时间基,采样率,采样格式,通道布局,
buffersrc = avfilter_get_by_name("abuffer");
buffersink = avfilter_get_by_name("abuffersink");
if (!buffersrc || !buffersink) {
av_log(NULL, AV_LOG_ERROR, "filtering source or sink element not found\n");
ret = AVERROR_UNKNOWN;
goto end;
}
if (!dec_ctx->channel_layout)
dec_ctx->channel_layout =
av_get_default_channel_layout(dec_ctx->channels);
snprintf(args, sizeof(args),
"time_base=%d/%d:sample_rate=%d:sample_fmt=%s:channel_layout=0x%"PRIx64,
dec_ctx->time_base.num, dec_ctx->time_base.den, dec_ctx->sample_rate,
av_get_sample_fmt_name(dec_ctx->sample_fmt),
dec_ctx->channel_layout);
ret = avfilter_graph_create_filter(&buffersrc_ctx, buffersrc, "in",
args, NULL, filter_graph);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot create audio buffer source\n");
goto end;
}
ret = avfilter_graph_create_filter(&buffersink_ctx, buffersink, "out",
NULL, NULL, filter_graph);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot create audio buffer sink\n");
goto end;
}
ret = av_opt_set_bin(buffersink_ctx, "sample_fmts",
(uint8_t *) &enc_ctx->sample_fmt, sizeof(enc_ctx->sample_fmt),
AV_OPT_SEARCH_CHILDREN);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot set output sample format\n");
goto end;
}
ret = av_opt_set_bin(buffersink_ctx, "channel_layouts",
(uint8_t *) &enc_ctx->channel_layout,
sizeof(enc_ctx->channel_layout), AV_OPT_SEARCH_CHILDREN);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot set output channel layout\n");
goto end;
}
ret = av_opt_set_bin(buffersink_ctx, "sample_rates",
(uint8_t *) &enc_ctx->sample_rate, sizeof(enc_ctx->sample_rate),
AV_OPT_SEARCH_CHILDREN);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot set output sample rate\n");
goto end;
}
} else {
ret = AVERROR_UNKNOWN;
goto end;
}
/* Endpoints for the filter graph. */
outputs->name = av_strdup("in");
outputs->filter_ctx = buffersrc_ctx;
outputs->pad_idx = 0;
outputs->next = NULL;
inputs->name = av_strdup("out");
inputs->filter_ctx = buffersink_ctx;
inputs->pad_idx = 0;
inputs->next = NULL;
if (!outputs->name || !inputs->name) {
ret = AVERROR(ENOMEM);
goto end;
}
//在链接字符串构成的过滤器到过滤器图形中,所以这里最后应该有三个过滤器.两个上边创建的.一个由字符串组成的
if ((ret = avfilter_graph_parse_ptr(filter_graph, filter_spec,
&inputs, &outputs, NULL)) < 0)
goto end;
//检查链接过滤器
if ((ret = avfilter_graph_config(filter_graph, NULL)) < 0)
goto end;
/* Fill FilteringContext */
fctx->buffersrc_ctx = buffersrc_ctx;
fctx->buffersink_ctx = buffersink_ctx;
fctx->filter_graph = filter_graph;
end:
avfilter_inout_free(&inputs);
avfilter_inout_free(&outputs);
return ret;
}
static int init_filters(void) {
const char *filter_spec;
unsigned int i;
int ret;
//分配过滤器上下文数组,每个流是一个元素
filter_ctx = av_malloc_array(ifmt_ctx->nb_streams, sizeof(*filter_ctx));
if (!filter_ctx)
return AVERROR(ENOMEM);
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
filter_ctx[i].buffersrc_ctx = NULL;
filter_ctx[i].buffersink_ctx = NULL;
filter_ctx[i].filter_graph = NULL;
if (!(ifmt_ctx->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_AUDIO
|| ifmt_ctx->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_VIDEO))
continue;
if (ifmt_ctx->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_VIDEO)
filter_spec = "null"; /* passthrough (dummy) filter for video */
else
filter_spec = "anull"; /* passthrough (dummy) filter for audio */
ret = init_filter(&filter_ctx[i], stream_ctx[i].dec_ctx,
stream_ctx[i].enc_ctx, filter_spec);
if (ret)
return ret;
}
return 0;
}
/**
* 编码并写出数据
* @param filt_frame 过滤玩的帧
* @param stream_index 流索引
* @param got_frame 返回的压缩后的数据
* @return
*/
static int encode_write_frame(AVFrame *filt_frame, unsigned int stream_index, int *got_frame) {
int ret;
int got_frame_local;
AVPacket enc_pkt;
//这里又是一个函数指针, 分解流类型选择音频或者视频编码
int (*enc_func)(AVCodecContext *, AVPacket *, const AVFrame *, int *) =
(ifmt_ctx->streams[stream_index]->codecpar->codec_type ==
AVMEDIA_TYPE_VIDEO) ? avcodec_encode_video2 : avcodec_encode_audio2;
if (!got_frame)
got_frame = &got_frame_local;
av_log(NULL, AV_LOG_INFO, "Encoding frame\n");
/* encode filtered frame */
enc_pkt.data = NULL;
enc_pkt.size = 0;
av_init_packet(&enc_pkt);
//frame数据送入编码器, 取出编码玩的 enc_pkt got_frame 表示enc_pkt是否为空,0为空,1为不空
ret = enc_func(stream_ctx[stream_index].enc_ctx, &enc_pkt,
filt_frame, got_frame);
av_frame_free(&filt_frame);
if (ret < 0)
return ret;
if (!(*got_frame))
return 0;
/* prepare packet for muxing */
enc_pkt.stream_index = stream_index;
// 转换编码后的paket 的时间戳 转换为ofmt_ctx的世界基
av_packet_rescale_ts(&enc_pkt,
stream_ctx[stream_index].enc_ctx->time_base,
ofmt_ctx->streams[stream_index]->time_base);
av_log(NULL, AV_LOG_DEBUG, "Muxing frame\n");
/* mux encoded frame */
//封装编码后的数据.用正确的交错来写出该packet
ret = av_interleaved_write_frame(ofmt_ctx, &enc_pkt);
return ret;
}
static int filter_encode_write_frame(AVFrame *frame, unsigned int stream_index) {
int ret;
AVFrame *filt_frame;
av_log(NULL, AV_LOG_INFO, "Pushing decoded frame to filters\n");
/* push the decoded frame into the filtergraph */
//把解码后的数据放入过滤器的输入上下文中
ret = av_buffersrc_add_frame_flags(filter_ctx[stream_index].buffersrc_ctx,
frame, 0);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Error while feeding the filtergraph\n");
return ret;
}
/* pull filtered frames from the filtergraph */
while (1) {
filt_frame = av_frame_alloc();
if (!filt_frame) {
ret = AVERROR(ENOMEM);
break;
}
av_log(NULL, AV_LOG_INFO, "Pulling filtered frame from filters\n");
//从过滤器输出上下文中取回完成过滤器转换的frame
ret = av_buffersink_get_frame(filter_ctx[stream_index].buffersink_ctx,
filt_frame);
if (ret < 0) {
/* if no more frames for output - returns AVERROR(EAGAIN)
* if flushed and no more frames for output - returns AVERROR_EOF
* rewrite retcode to 0 to show it as normal procedure completion
*/
if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF)
ret = 0;
av_frame_free(&filt_frame);
break;
}
filt_frame->pict_type = AV_PICTURE_TYPE_NONE;
ret = encode_write_frame(filt_frame, stream_index, NULL);
if (ret < 0)
break;
}
return ret;
}
static int flush_encoder(unsigned int stream_index) {
int ret;
int got_frame;
if (!(stream_ctx[stream_index].enc_ctx->codec->capabilities &
AV_CODEC_CAP_DELAY))
return 0;
while (1) {
av_log(NULL, AV_LOG_INFO, "Flushing stream #%u encoder\n", stream_index);
ret = encode_write_frame(NULL, stream_index, &got_frame);
if (ret < 0)
break;
if (!got_frame)
return 0;
}
return ret;
}
/**
* 这也是一个转换音视频文件的过程,同时这里加入了过滤器.把文件拆成流,然后解码出packet后.又经过过滤器的处理.
* 处理完成后才再次编码.然后写出到文件中
* @param argc
* @param argv
* @return
*/
int transcoding_main(int argc, char **argv) {
int ret;
AVPacket packet = {.data = NULL, .size = 0};
AVFrame *frame = NULL;
enum AVMediaType type;
unsigned int stream_index;
unsigned int i;
int got_frame;
int (*dec_func)(AVCodecContext *, AVFrame *, int *, const AVPacket *);
if (argc != 3) {
av_log(NULL, AV_LOG_ERROR, "Usage: %s