title: ffmpeg_sample解讀_transcoding
date: 2020-11-15 10:15:02
tags: [讀書筆記]
typora-copy-images-to: ./imgs
typora-root-url: ./imgs

總結

* 這也是一個轉換音視頻文件的過程,同時這里加入了過濾器.把文件拆成流,然后解碼出packet后.又經(jīng)過過濾器的處理.
* 處理完成后才再次編碼.然后寫出到文件中

流程圖

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

這個代碼流程圖分兩部分,第一部分是初始化輸入輸出的格式上下文,編碼器上下文(對應輸出),解碼器上下文(對應輸入,),以及過濾器.如下,

image-20201116170029996

然后是遍歷解碼輸出的文件.獲取packet,送入解碼器解碼出幀,再把幀送入過濾器中進行處理.處理完成后從過濾器中取出幀,然后再次編碼成packet.最后寫出到輸出文件中.

image-20201116170254409

代碼

/**
 * @file
 * API example for demuxing, decoding, filtering, encoding and muxing
 * @example transcoding.c
 */

#include <libavcodec/avcodec.h>
#include <libavformat/avformat.h>
#include <libavfilter/buffersink.h>
#include <libavfilter/buffersrc.h>
#include <libavutil/opt.h>
#include <libavutil/pixdesc.h>

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;

///打開輸入文件.為每個數(shù)據(jù)流創(chuàng)建解碼器上下文,格式上下文,與流索引對應起來
//對于輸入文件來說.都是從輸入文件的流中建立解碼器,和解碼器上下文,這是標準操作了
static int open_input_file(const char *filename) {
    int ret;
    unsigned int i;

    ifmt_ctx = NULL;
    //打開文件,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;
    }
//找到合適的流
    if ((ret = avformat_find_stream_info(ifmt_ctx, NULL)) < 0) {
        av_log(NULL, AV_LOG_ERROR, "Cannot find stream information\n");
        return ret;
    }
    //分配流信息數(shù)組,數(shù)組大小是 流的總數(shù)* streamContext 的大小. 也就是每個流都有編碼解碼上下文
    stream_ctx = av_mallocz_array(ifmt_ctx->nb_streams, sizeof(*stream_ctx));
    if (!stream_ctx)
        return AVERROR(ENOMEM);
    //根據(jù)所有的流信息,分配給stream_ctx里每個解碼器上下文
    for (i = 0; i < ifmt_ctx->nb_streams; i++) {
        //拿到流.及根據(jù)流的信息找到解碼器
        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;
        }
        //通過解碼器給解碼器上下文分配內存
        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);
        }
        //拷貝流中的信息到解碼器上下文中
        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)
                //根據(jù)流信息和格式上下文,猜猜視頻的幀率
                codec_ctx->framerate = av_guess_frame_rate(ifmt_ctx, stream, NULL);
            /* Open decoder */
            //打開解碼器上下文
            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;
            }
        }
        //保存到對應流索引的解碼器上下文中
        stream_ctx[i].dec_ctx = codec_ctx;
    }
    //打印格式信息
    av_dump_format(ifmt_ctx, 0, filename, 0);
    return 0;
}

//大家輸出文件.初始化輸出的編碼器上下文.和格式上下文,都保存在同一個數(shù)組 stream_ctx中了
//輸出文件的編碼器上下文.則需要我們自己設定一些參數(shù).或者從編碼器上下文中拷貝
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;
    //分配輸出格式上下文空間
    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++) {
        //創(chuàng)建輸出流.此時輸出流中沒有東西
        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;
        }
//輸入流中的解碼上下文
        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 */
            //找到輸入流中的編碼器,輸入輸出流使用相同的編解碼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;
            }
            //根據(jù)編碼器獲為編碼器上下文分配空間
            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 */
//            視頻流的輸出參數(shù)和輸入?yún)?shù)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 {//音頻流.輸出的編碼器上下文和輸入的解碼器上下文參數(shù)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 */
            //打開編碼器上下文
            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;
            }
            //用編碼器上下文的參數(shù)填充輸出流的編碼參數(shù), 和上邊輸入文件的處理不一樣
            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;
            }
//保持編碼器上下文
            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 */
            //拷貝輸入?yún)?shù)到輸出參數(shù),這是既非音頻流也非食品流,直接拷貝輸入流參數(shù)到輸出流中
            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)) {
        //打開輸出文件,綁定avio上下文.寫出模式
        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 */
    //寫出header內容
    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;
}
/**
 * 初始化過濾器,這里還有一個通過字符串filter_spec來創(chuàng)建的過濾器
 * @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();
    //過濾器圖形.用來連接多個過濾器的
    AVFilterGraph *filter_graph = avfilter_graph_alloc();

    if (!outputs || !inputs || !filter_graph) {
        ret = AVERROR(ENOMEM);
        goto end;
    }

    if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO) {
        //輸入輸出的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;
        }
//賦值過濾器參數(shù),寬高,格式,時間基,寬高比
        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);
//用參數(shù)和buffer初始化輸入的過濾器上下文,并添加到過濾器圖形中
        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;
        }
//初始化輸出的過濾器上下文,并添加到圖形中
        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;
        }
//輸出過濾器上下文,設置參數(shù)
        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) {
        //音頻和視頻類似.知識設置的參數(shù)不同. 時間基,采樣率,采樣格式,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;
    }
//在鏈接字符串構成的過濾器到過濾器圖形中,所以這里最后應該有三個過濾器.兩個上邊創(chuàng)建的.一個由字符串組成的
    if ((ret = avfilter_graph_parse_ptr(filter_graph, filter_spec,
                                        &inputs, &outputs, NULL)) < 0)
        goto end;
//檢查鏈接過濾器
    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;
    //分配過濾器上下文數(shù)組,每個流是一個元素
    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;
}
/**
 * 編碼并寫出數(shù)據(jù)
 * @param filt_frame 過濾玩的幀
 * @param stream_index 流索引
 * @param got_frame 返回的壓縮后的數(shù)據(jù)
 * @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;
    //這里又是一個函數(shù)指針, 分解流類型選擇音頻或者視頻編碼
    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數(shù)據(jù)送入編碼器, 取出編碼玩的 enc_pkt got_frame 表示enc_pkt是否為空,0為空,1為不空
    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;
//    轉換編碼后的paket 的時間戳 轉換為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 */
    //封裝編碼后的數(shù)據(jù).用正確的交錯來寫出該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 */
    //把解碼后的數(shù)據(jù)放入過濾器的輸入上下文中
    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");
        //從過濾器輸出上下文中取回完成過濾器轉換的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;
}

/**
 * 這也是一個轉換音視頻文件的過程,同時這里加入了過濾器.把文件拆成流,然后解碼出packet后.又經(jīng)過過濾器的處理.
 * 處理完成后才再次編碼.然后寫出到文件中
 * @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 <input file> <output file>\n", argv[0]);
        return 1;
    }
//打開輸入輸出的文件,初始化解碼器上下文
    if ((ret = open_input_file(argv[1])) < 0)
        goto end;
    //打開輸出文件,初始化編碼上下
    if ((ret = open_output_file(argv[2])) < 0)
        goto end;
    //初始化說要過濾器
    if ((ret = init_filters()) < 0)
        goto end;

    /* read all packets */
    while (1) {//讀入一個解封裝后的packet
        if ((ret = av_read_frame(ifmt_ctx, &packet)) < 0)
            break;
        //流索引和流類型
        stream_index = packet.stream_index;
        type = ifmt_ctx->streams[packet.stream_index]->codecpar->codec_type;
        av_log(NULL, AV_LOG_DEBUG, "Demuxer gave frame of stream_index %u\n",
               stream_index);

        if (filter_ctx[stream_index].filter_graph) {
            av_log(NULL, AV_LOG_DEBUG, "Going to reencode&filter the frame\n");
            frame = av_frame_alloc();
            if (!frame) {
                ret = AVERROR(ENOMEM);
                break;
            }
            //轉換包的時間基,
            av_packet_rescale_ts(&packet,
                                 ifmt_ctx->streams[stream_index]->time_base,
                                 stream_ctx[stream_index].dec_ctx->time_base);
            //這是一個函數(shù)指針,指向一個函數(shù)的地址
            dec_func = (type == AVMEDIA_TYPE_VIDEO) ? avcodec_decode_video2 :
                       avcodec_decode_audio4;
//            根據(jù)類型解碼音頻或視頻, 解碼后的數(shù)據(jù)在got_frame里
            ret = dec_func(stream_ctx[stream_index].dec_ctx, frame,
                           &got_frame, &packet);
            if (ret < 0) {
                av_frame_free(&frame);
                av_log(NULL, AV_LOG_ERROR, "Decoding failed\n");
                break;
            }

            if (got_frame) {
                frame->pts = frame->best_effort_timestamp;
                //使用過濾器過濾解碼后的幀,然后在寫出幀數(shù)據(jù)
                ret = filter_encode_write_frame(frame, stream_index);
                av_frame_free(&frame);
                if (ret < 0)
                    goto end;
            } else {
                av_frame_free(&frame);
            }
        } else {
            /* remux this frame without reencoding */
            av_packet_rescale_ts(&packet,
                                 ifmt_ctx->streams[stream_index]->time_base,
                                 ofmt_ctx->streams[stream_index]->time_base);

            ret = av_interleaved_write_frame(ofmt_ctx, &packet);
            if (ret < 0)
                goto end;
        }
        av_packet_unref(&packet);
    }
//在通過傳入null刷新編碼器中的參數(shù)
    /* flush filters and encoders */
    for (i = 0; i < ifmt_ctx->nb_streams; i++) {
        /* flush filter */
        if (!filter_ctx[i].filter_graph)
            continue;
        ret = filter_encode_write_frame(NULL, i);
        if (ret < 0) {
            av_log(NULL, AV_LOG_ERROR, "Flushing filter failed\n");
            goto end;
        }

        /* flush encoder */
        ret = flush_encoder(i);
        if (ret < 0) {
            av_log(NULL, AV_LOG_ERROR, "Flushing encoder failed\n");
            goto end;
        }
    }
//在寫出數(shù)據(jù)尾部,
    av_write_trailer(ofmt_ctx);
    end:
    //最后是是否所有資源
    av_packet_unref(&packet);
    av_frame_free(&frame);
    for (i = 0; i < ifmt_ctx->nb_streams; i++) {
        avcodec_free_context(&stream_ctx[i].dec_ctx);
        if (ofmt_ctx && ofmt_ctx->nb_streams > i && ofmt_ctx->streams[i] && stream_ctx[i].enc_ctx)
            avcodec_free_context(&stream_ctx[i].enc_ctx);
        if (filter_ctx && filter_ctx[i].filter_graph)
            avfilter_graph_free(&filter_ctx[i].filter_graph);
    }
    av_free(filter_ctx);
    av_free(stream_ctx);
    avformat_close_input(&ifmt_ctx);
    if (ofmt_ctx && !(ofmt_ctx->oformat->flags & AVFMT_NOFILE))
        avio_closep(&ofmt_ctx->pb);
    avformat_free_context(ofmt_ctx);

    if (ret < 0)
        av_log(NULL, AV_LOG_ERROR, "Error occurred: %s\n", av_err2str(ret));

    return ret ? 1 : 0;
}