Analysis of the relationship between ffmpeg.c source code and functions

introduce

1. FFmpeg is a software that can process audio and video. It has very powerful functions, mainly including codec conversion, package format conversion, and filter effects.
2. FFmpeg supports various network protocols, supports push-pull streams of high-level protocols such as RTMP, RTSP, and HLS, and also supports push-pull streams of lower-level TCP/UDP protocols.
3. FFmpeg can run on Windows, Linux, Mac, iOS, Android and other operating systems.
4. FFmpeg is the abbreviation of " Fast Forward mpeg ";
5. FFMPEG is divided into several modules functionally, namely core tool (libutils), media format (libavformat), codec (libavcodec), device (libavdevice) and post-processing (libavfilter, libswscale, libpostproc), responsible for providing public Functions, realize the reading and writing of multimedia files, complete audio and video encoding and decoding, manage the operation of audio and video equipment, and perform audio and video post-processing.
6. The executable file of ffmpeg is a conversion tool officially provided by FFmpeg. It is a command-line tool. The core code is mainly in the ffmpeg.c file.

General diagram of ffmpeg.c function relationship analysis

Introduction to key functions

transcode()

1. The core function of conversion is mainly in the transcode() function. The core of this function is transcode_step(), which completes the core capability of audio and video conversion.
2. Among them, transcode_init() mainly completes some initialization work, and internally uses init_input_stream() to call the API function avcodec_open2() to complete the opening of the decoder.
   

transcode_step()

1. transcode_step() is the core function to complete audio and video transcoding, where process_input() completes the decoding function module, and reap_filter() completes the encoding function module.
   

process_input()

1. The process_input() function implements the decoding function, among which process_input_packet() is the core function to complete the decoding.
   
2. In process_input_packet(), different functions will be called according to different audio and video decoding needs. The audio call is decode_audio(), the video call is the decode_video() function, and the subtitle call is the transcode_subtitles() function. If only the copy function is performed, The do_streamcopy() function needs to be called.
   
3. In the decode_video() function, the functions of decoding and sending frame are mainly completed, and the API functions avcodec_send_packet() and avcodec_receive_frame() are called in decode() to complete the decoding function module of audio and video multimedia; send_frame_to_filters() is mainly for The decoded frames are sent to the filter, which is convenient for the next step of encoding.
   

reap_filter()

1. The reap_filter() function implements the encoding function. The core function of video encoding is the do_video_out() function, and the core function of audio encoding is the do_audio_out() function.
   
2. The do_video_out() function completes the process from video frame to packet, that is, the encoding function. Among them, the API functions avcodec_send_frame() and avcodec_receive_packet() are called to complete the encoding. And output_packet() completes the function of outputting the final video packet packet.
   

Official Transcoding Example

1. This example mainly completes the function of audio and video transcoding according to the new API.

/*
 * Copyright (c) 2010 Nicolas George
 * Copyright (c) 2011 Stefano Sabatini
 * Copyright (c) 2014 Andrey Utkin
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 * THE SOFTWARE.
 */

/**
 * @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;

static int open_input_file(const char *filename)
{
    
    
    int ret;
    unsigned int i;

    ifmt_ctx = NULL;
    if ((ret = avformat_open_input(&ifmt_ctx, filename, NULL, NULL)) < 0) {
    
    
        av_log(NULL, AV_LOG_ERROR, "Cannot open input file\n");
        return ret;
    }

    if ((ret = avformat_find_stream_info(ifmt_ctx, NULL)) < 0) {
    
    
        av_log(NULL, AV_LOG_ERROR, "Cannot find stream information\n");
        return ret;
    }

    stream_ctx = av_mallocz_array(ifmt_ctx->nb_streams, sizeof(*stream_ctx));
    if (!stream_ctx)
        return AVERROR(ENOMEM);

    for (i = 0; i < ifmt_ctx->nb_streams; i++) {
    
    
        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;
        }
        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);
        }
        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)
                codec_ctx->framerate = av_guess_frame_rate(ifmt_ctx, stream, NULL);
            /* Open decoder */
            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;
            }
        }
        stream_ctx[i].dec_ctx = codec_ctx;
    }

    av_dump_format(ifmt_ctx, 0, filename, 0);
    return 0;
}

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;
    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++) {
    
    
        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;
        }

        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 */
            encoder = avcodec_find_encoder(dec_ctx->codec_id);
            if (!encoder) {
    
    
                av_log(NULL, AV_LOG_FATAL, "Necessary encoder not found\n");
                return AVERROR_INVALIDDATA;
            }
            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 */
            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 {
    
    
                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 */
            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;
            }
            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;
            }

            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 */
            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)) {
    
    
        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 */
    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;
}

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();
    AVFilterGraph *filter_graph = avfilter_graph_alloc();

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

    if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO) {
    
    
        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;
        }

        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);

        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;
        }

        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;
        }

        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) {
    
    
        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;
    }

    if ((ret = avfilter_graph_parse_ptr(filter_graph, filter_spec,
                    &inputs, &outputs, NULL)) < 0)
        goto end;

    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;
    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;
}

static int encode_write_frame(AVFrame *filt_frame, unsigned int stream_index, int *got_frame) {
    
    
    int ret;
    int got_frame_local;
    AVPacket enc_pkt;
    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);
    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;
    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 */
    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 */
    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");
        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;
}

int 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;
    }

    if ((ret = open_input_file(argv[1])) < 0)
        goto end;
    if ((ret = open_output_file(argv[2])) < 0)
        goto end;
    if ((ret = init_filters()) < 0)
        goto end;

    /* read all packets */
    while (1) {
    
    
        if ((ret = av_read_frame(ifmt_ctx, &packet)) < 0)
            break;
        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;
            }
            av_packet_rescale_ts(&packet,
                                 ifmt_ctx->streams[stream_index]->time_base,
                                 stream_ctx[stream_index].dec_ctx->time_base);
            dec_func = (type == AVMEDIA_TYPE_VIDEO) ? avcodec_decode_video2 :
                avcodec_decode_audio4;
            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;
                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);
    }

    /* 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;
        }
    }

    av_write_trailer(ofmt_ctx);
end:
    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;
}

reference

1. http://ffmpeg.org/