ffmpeg.c

            if (got_packet) {
                if (pkt.pts == AV_NOPTS_VALUE && !(enc->codec->capabilities & CODEC_CAP_DELAY))
                    pkt.pts = ost->sync_opts;

                if (pkt.pts != AV_NOPTS_VALUE)
                    pkt.pts = av_rescale_q(pkt.pts, enc->time_base, ost->st->time_base);
                if (pkt.dts != AV_NOPTS_VALUE)
                    pkt.dts = av_rescale_q(pkt.dts, enc->time_base, ost->st->time_base);

                if (debug_ts) {
                    av_log(NULL, AV_LOG_INFO, "encoder -> type:video "
                           "pkt_pts:%s pkt_pts_time:%s pkt_dts:%s pkt_dts_time:%s\n",
                           av_ts2str(pkt.pts), av_ts2timestr(pkt.pts, &ost->st->time_base),
                           av_ts2str(pkt.dts), av_ts2timestr(pkt.dts, &ost->st->time_base));
                }

                write_frame(s, &pkt, ost);
                frame_size = pkt.size;
                video_size += pkt.size;
                av_free_packet(&pkt);

                /* if two pass, output log */
                if (ost->logfile && enc->stats_out) {
                    fprintf(ost->logfile, "%s", enc->stats_out);
                }
            }
        }
        ost->sync_opts++;
        /*
         * For video, number of frames in == number of packets out.
         * But there may be reordering, so we can't throw away frames on encoder
         * flush, we need to limit them here, before they go into encoder.
         */
        ost->frame_number++;
    }
    if (vstats_filename && frame_size)
        do_video_stats(output_files[ost->file_index]->ctx, ost, frame_size);
}

/* check for new output on any of the filtergraphs */
static int poll_filters(void)
{
    AVFilterBufferRef *picref;
    AVFrame *filtered_frame = NULL;
    int i, ret;

    for (i = 0; i < nb_output_streams; i++) {
        OutputStream *ost = output_streams[i];
        OutputFile    *of = output_files[ost->file_index];

        if (!ost->filter || ost->is_past_recording_time)
            continue;

        if (!ost->filtered_frame && !(ost->filtered_frame = avcodec_alloc_frame())) {
            return AVERROR(ENOMEM);
        } else
            avcodec_get_frame_defaults(ost->filtered_frame);
        filtered_frame = ost->filtered_frame;

        while (avfilter_poll_frame(ost->filter->filter->inputs[0])) {
            AVRational ist_pts_tb = ost->filter->filter->inputs[0]->time_base;
            if ((ret = av_buffersink_get_buffer_ref(ost->filter->filter,
                                                            &picref,
                                                            0)) < 0) {
                av_log(NULL, AV_LOG_WARNING, "AV Filter told us it has a frame available but failed to output one\n");
                return ret;
            }
            filtered_frame->pts = av_rescale_q(picref->pts, ist_pts_tb, AV_TIME_BASE_Q);
//             if (ost->source_index >= 0)
//                 *filtered_frame= *input_streams[ost->source_index]->decoded_frame; //for me_threshold

            if (of->start_time && filtered_frame->pts < of->start_time)
                return 0;

            switch (ost->filter->filter->inputs[0]->type) {
            case AVMEDIA_TYPE_VIDEO:
                avfilter_fill_frame_from_video_buffer_ref(filtered_frame, picref);
                if (!ost->frame_aspect_ratio)
                    ost->st->codec->sample_aspect_ratio = picref->video->sample_aspect_ratio;

                do_video_out(of->ctx, ost, filtered_frame,
                             same_quant ? ost->last_quality :
                                          ost->st->codec->global_quality);
                break;
            default:
                // TODO support audio/subtitle filters
                av_assert0(0);
            }

            avfilter_unref_buffer(picref);
        }
    }
    return 0;
}

static void print_report(int is_last_report, int64_t timer_start, int64_t cur_time)
{
    char buf[1024];
    OutputStream *ost;
    AVFormatContext *oc;
    int64_t total_size;
    AVCodecContext *enc;
    int frame_number, vid, i;
    double bitrate;
    int64_t pts = INT64_MAX;
    static int64_t last_time = -1;
    static int qp_histogram[52];
    int hours, mins, secs, us;

    if (!print_stats && !is_last_report)
        return;

    if (!is_last_report) {
        if (last_time == -1) {
            last_time = cur_time;
            return;
        }
        if ((cur_time - last_time) < 500000)
            return;
        last_time = cur_time;
    }


    oc = output_files[0]->ctx;

    total_size = avio_size(oc->pb);
    if (total_size < 0) { // FIXME improve avio_size() so it works with non seekable output too
        total_size = avio_tell(oc->pb);
        if (total_size < 0)
            total_size = 0;
    }

    buf[0] = '\0';
    vid = 0;
    for (i = 0; i < nb_output_streams; i++) {
        float q = -1;
        ost = output_streams[i];
        enc = ost->st->codec;
        if (!ost->stream_copy && enc->coded_frame)
            q = enc->coded_frame->quality / (float)FF_QP2LAMBDA;
        if (vid && enc->codec_type == AVMEDIA_TYPE_VIDEO) {
            snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf), "q=%2.1f ", q);
        }
        if (!vid && enc->codec_type == AVMEDIA_TYPE_VIDEO) {
            float fps, t = (cur_time-timer_start) / 1000000.0;

            frame_number = ost->frame_number;
            fps = t > 1 ? frame_number / t : 0;
            snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf), "frame=%5d fps=%3.*f q=%3.1f ",
                     frame_number, fps < 9.95, fps, q);
            if (is_last_report)
                snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf), "L");
            if (qp_hist) {
                int j;
                int qp = lrintf(q);
                if (qp >= 0 && qp < FF_ARRAY_ELEMS(qp_histogram))
                    qp_histogram[qp]++;
                for (j = 0; j < 32; j++)
                    snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf), "%X", (int)lrintf(log(qp_histogram[j] + 1) / log(2)));
            }
            if (enc->flags&CODEC_FLAG_PSNR) {
                int j;
                double error, error_sum = 0;
                double scale, scale_sum = 0;
                char type[3] = { 'Y','U','V' };
                snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf), "PSNR=");
                for (j = 0; j < 3; j++) {
                    if (is_last_report) {
                        error = enc->error[j];
                        scale = enc->width * enc->height * 255.0 * 255.0 * frame_number;
                    } else {
                        error = enc->coded_frame->error[j];
                        scale = enc->width * enc->height * 255.0 * 255.0;
                    }
                    if (j)
                        scale /= 4;
                    error_sum += error;
                    scale_sum += scale;
                    snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf), "%c:%2.2f ", type[j], psnr(error / scale));
                }
                snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf), "*:%2.2f ", psnr(error_sum / scale_sum));
            }
            vid = 1;
        }
        /* compute min output value */
        pts = FFMIN(pts, av_rescale_q(ost->st->pts.val,
                                      ost->st->time_base, AV_TIME_BASE_Q));
    }

    secs = pts / AV_TIME_BASE;
    us = pts % AV_TIME_BASE;
    mins = secs / 60;
    secs %= 60;
    hours = mins / 60;
    mins %= 60;

    bitrate = pts ? total_size * 8 / (pts / 1000.0) : 0;

    snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf),
             "size=%8.0fkB time=", total_size / 1024.0);
    snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf),
             "%02d:%02d:%02d.%02d ", hours, mins, secs,
             (100 * us) / AV_TIME_BASE);
    snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf),
             "bitrate=%6.1fkbits/s", bitrate);

    if (nb_frames_dup || nb_frames_drop)
        snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf), " dup=%d drop=%d",
                nb_frames_dup, nb_frames_drop);

    av_log(NULL, AV_LOG_INFO, "%s    \r", buf);

    fflush(stderr);

    if (is_last_report) {
        int64_t raw= audio_size + video_size + extra_size;
        av_log(NULL, AV_LOG_INFO, "\n");
        av_log(NULL, AV_LOG_INFO, "video:%1.0fkB audio:%1.0fkB global headers:%1.0fkB muxing overhead %f%%\n",
               video_size / 1024.0,
               audio_size / 1024.0,
               extra_size / 1024.0,
               100.0 * (total_size - raw) / raw
        );
        if(video_size + audio_size + extra_size == 0){
            av_log(NULL, AV_LOG_WARNING, "Output file is empty, nothing was encoded (check -ss / -t / -frames parameters if used)\n");
        }
    }
}

static void flush_encoders(void)
{
    int i, ret;

    for (i = 0; i < nb_output_streams; i++) {
        OutputStream   *ost = output_streams[i];
        AVCodecContext *enc = ost->st->codec;
        AVFormatContext *os = output_files[ost->file_index]->ctx;
        int stop_encoding = 0;

        if (!ost->encoding_needed)
            continue;

        if (ost->st->codec->codec_type == AVMEDIA_TYPE_AUDIO && enc->frame_size <= 1)
            continue;
        if (ost->st->codec->codec_type == AVMEDIA_TYPE_VIDEO && (os->oformat->flags & AVFMT_RAWPICTURE) && enc->codec->id == CODEC_ID_RAWVIDEO)
            continue;

        for (;;) {
            AVPacket pkt;
            int fifo_bytes, got_packet;
            av_init_packet(&pkt);
            pkt.data = NULL;
            pkt.size = 0;

            switch (ost->st->codec->codec_type) {
            case AVMEDIA_TYPE_AUDIO:
                fifo_bytes = av_fifo_size(ost->fifo);
                if (fifo_bytes > 0) {
                    /* encode any samples remaining in fifo */
                    int frame_bytes = fifo_bytes;

                    av_fifo_generic_read(ost->fifo, audio_buf, fifo_bytes, NULL);

                    /* pad last frame with silence if needed */
                    if (!(enc->codec->capabilities & CODEC_CAP_SMALL_LAST_FRAME)) {
                        frame_bytes = enc->frame_size * enc->channels *
                                      av_get_bytes_per_sample(enc->sample_fmt);
                        if (allocated_audio_buf_size < frame_bytes)
                            exit_program(1);
                        generate_silence(audio_buf+fifo_bytes, enc->sample_fmt, frame_bytes - fifo_bytes);
                    }
                    encode_audio_frame(os, ost, audio_buf, frame_bytes);
                } else {
                    /* flush encoder with NULL frames until it is done
                       returning packets */
                    if (encode_audio_frame(os, ost, NULL, 0) == 0) {
                        stop_encoding = 1;
                        break;
                    }
                }
                break;
            case AVMEDIA_TYPE_VIDEO:
                update_benchmark(NULL);
                ret = avcodec_encode_video2(enc, &pkt, NULL, &got_packet);
                update_benchmark("encode_video %d.%d", ost->file_index, ost->index);
                if (ret < 0) {
                    av_log(NULL, AV_LOG_FATAL, "Video encoding failed\n");
                    exit_program(1);
                }
                video_size += pkt.size;
                if (ost->logfile && enc->stats_out) {
                    fprintf(ost->logfile, "%s", enc->stats_out);
                }
                if (!got_packet) {
                    stop_encoding = 1;
                    break;
                }
                if (pkt.pts != AV_NOPTS_VALUE)
                    pkt.pts = av_rescale_q(pkt.pts, enc->time_base, ost->st->time_base);
                if (pkt.dts != AV_NOPTS_VALUE)
                    pkt.dts = av_rescale_q(pkt.dts, enc->time_base, ost->st->time_base);
                write_frame(os, &pkt, ost);
                break;
            default:
                stop_encoding = 1;
            }
            if (stop_encoding)
                break;
        }
    }
}

/*
 * Check whether a packet from ist should be written into ost at this time
 */
static int check_output_constraints(InputStream *ist, OutputStream *ost)
{
    OutputFile *of = output_files[ost->file_index];
    int ist_index  = input_files[ist->file_index]->ist_index + ist->st->index;

    if (ost->source_index != ist_index)
        return 0;

    if (of->start_time && ist->pts < of->start_time)
        return 0;

    if (of->recording_time != INT64_MAX &&
        av_compare_ts(ist->pts, AV_TIME_BASE_Q, of->recording_time + of->start_time,
                      (AVRational){ 1, 1000000 }) >= 0) {
        ost->is_past_recording_time = 1;
        return 0;
    }

    return 1;
}

static void do_streamcopy(InputStream *ist, OutputStream *ost, const AVPacket *pkt)
{
    OutputFile *of = output_files[ost->file_index];
    int64_t ost_tb_start_time = av_rescale_q(of->start_time, AV_TIME_BASE_Q, ost->st->time_base);
    AVPicture pict;
    AVPacket opkt;

    av_init_packet(&opkt);

    if ((!ost->frame_number && !(pkt->flags & AV_PKT_FLAG_KEY)) &&
        !ost->copy_initial_nonkeyframes)
        return;

    /* force the input stream PTS */
    if (ost->st->codec->codec_type == AVMEDIA_TYPE_AUDIO)
        audio_size += pkt->size;
    else if (ost->st->codec->codec_type == AVMEDIA_TYPE_VIDEO) {
        video_size += pkt->size;
        ost->sync_opts++;
    }

    if (pkt->pts != AV_NOPTS_VALUE)
        opkt.pts = av_rescale_q(pkt->pts, ist->st->time_base, ost->st->time_base) - ost_tb_start_time;
    else
        opkt.pts = AV_NOPTS_VALUE;

    if (pkt->dts == AV_NOPTS_VALUE)
        opkt.dts = av_rescale_q(ist->dts, AV_TIME_BASE_Q, ost->st->time_base);
    else
        opkt.dts = av_rescale_q(pkt->dts, ist->st->time_base, ost->st->time_base);
    opkt.dts -= ost_tb_start_time;

    opkt.duration = av_rescale_q(pkt->duration, ist->st->time_base, ost->st->time_base);
    opkt.flags    = pkt->flags;

    // FIXME remove the following 2 lines they shall be replaced by the bitstream filters
    if (  ost->st->codec->codec_id != CODEC_ID_H264
       && ost->st->codec->codec_id != CODEC_ID_MPEG1VIDEO
       && ost->st->codec->codec_id != CODEC_ID_MPEG2VIDEO
       && ost->st->codec->codec_id != CODEC_ID_VC1
       ) {
        if (av_parser_change(ist->st->parser, ost->st->codec, &opkt.data, &opkt.size, pkt->data, pkt->size, pkt->flags & AV_PKT_FLAG_KEY))
            opkt.destruct = av_destruct_packet;
    } else {
        opkt.data = pkt->data;
        opkt.size = pkt->size;
    }
    if (of->ctx->oformat->flags & AVFMT_RAWPICTURE) {
        /* store AVPicture in AVPacket, as expected by the output format */
        avpicture_fill(&pict, opkt.data, ost->st->codec->pix_fmt, ost->st->codec->width, ost->st->codec->height);
        opkt.data = (uint8_t *)&pict;
        opkt.size = sizeof(AVPicture);
        opkt.flags |= AV_PKT_FLAG_KEY;
    }

    write_frame(of->ctx, &opkt, ost);
    ost->st->codec->frame_number++;
    av_free_packet(&opkt);
}

static void rate_emu_sleep(InputStream *ist)
{
    if (input_files[ist->file_index]->rate_emu) {
        int64_t pts = av_rescale(ist->dts, 1000000, AV_TIME_BASE);
        int64_t now = av_gettime() - ist->start;
        if (pts > now)
            usleep(pts - now);
    }
}

static int transcode_audio(InputStream *ist, AVPacket *pkt, int *got_output)
{
    AVFrame *decoded_frame;
    AVCodecContext *avctx = ist->st->codec;
    int bps = av_get_bytes_per_sample(ist->st->codec->sample_fmt);
    int i, ret;

    if (!ist->decoded_frame && !(ist->decoded_frame = avcodec_alloc_frame()))
        return AVERROR(ENOMEM);
    else
        avcodec_get_frame_defaults(ist->decoded_frame);
    decoded_frame = ist->decoded_frame;

    update_benchmark(NULL);
    ret = avcodec_decode_audio4(avctx, decoded_frame, got_output, pkt);
    update_benchmark("decode_audio %d.%d", ist->file_index, ist->st->index);
    if (ret < 0) {
        return ret;
    }
    if (avctx->sample_rate <= 0) {
        av_log(avctx, AV_LOG_ERROR, "Sample rate %d invalid\n", avctx->sample_rate);
        return AVERROR_INVALIDDATA;
    }

    if (!*got_output) {
        /* no audio frame */
        return ret;
    }

    /* if the decoder provides a pts, use it instead of the last packet pts.
       the decoder could be delaying output by a packet or more. */
    if (decoded_frame->pts != AV_NOPTS_VALUE)
        ist->dts = ist->next_dts = ist->pts = ist->next_pts = decoded_frame->pts;

    /* increment next_dts to use for the case where the input stream does not
       have timestamps or there are multiple frames in the packet */
    ist->next_pts += ((int64_t)AV_TIME_BASE * decoded_frame->nb_samples) /
                     avctx->sample_rate;
    ist->next_dts += ((int64_t)AV_TIME_BASE * decoded_frame->nb_samples) /
                     avctx->sample_rate;


    // preprocess audio (volume)
    if (audio_volume != 256) {
        int decoded_data_size = decoded_frame->nb_samples * avctx->channels * bps;
        void *samples = decoded_frame->data[0];
        switch (avctx->sample_fmt) {
        case AV_SAMPLE_FMT_U8:
        {
            uint8_t *volp = samples;
            for (i = 0; i < (decoded_data_size / sizeof(*volp)); i++) {
                int v = (((*volp - 128) * audio_volume + 128) >> 8) + 128;
                *volp++ = av_clip_uint8(v);
            }
            break;
        }
        case AV_SAMPLE_FMT_S16:
        {
            int16_t *volp = samples;
            for (i = 0; i < (decoded_data_size / sizeof(*volp)); i++) {
                int v = ((*volp) * audio_volume + 128) >> 8;
                *volp++ = av_clip_int16(v);
            }
            break;
        }
        case AV_SAMPLE_FMT_S32:
        {
            int32_t *volp = samples;
            for (i = 0; i < (decoded_data_size / sizeof(*volp)); i++) {
                int64_t v = (((int64_t)*volp * audio_volume + 128) >> 8);
                *volp++ = av_clipl_int32(v);
            }
            break;
        }
        case AV_SAMPLE_FMT_FLT:
        {
            float *volp = samples;
            float scale = audio_volume / 256.f;
            for (i = 0; i < (decoded_data_size / sizeof(*volp)); i++) {
                *volp++ *= scale;
            }
            break;
        }
        case AV_SAMPLE_FMT_DBL:
        {
            double *volp = samples;
            double scale = audio_volume / 256.;
            for (i = 0; i < (decoded_data_size / sizeof(*volp)); i++) {
                *volp++ *= scale;
            }
            break;
        }
        default:
            av_log(NULL, AV_LOG_FATAL,
                   "Audio volume adjustment on sample format %s is not supported.\n",
                   av_get_sample_fmt_name(ist->st->codec->sample_fmt));
            exit_program(1);
        }
    }

    rate_emu_sleep(ist);

    for (i = 0; i < nb_output_streams; i++) {
        OutputStream *ost = output_streams[i];

        if (!check_output_constraints(ist, ost) || !ost->encoding_needed)
            continue;
        do_audio_out(output_files[ost->file_index]->ctx, ost, ist, decoded_frame);
    }

    return ret;
}

static int transcode_video(InputStream *ist, AVPacket *pkt, int *got_output, int64_t *pkt_pts)
{
    AVFrame *decoded_frame;
    void *buffer_to_free = NULL;
    int i, ret = 0, resample_changed;
    int64_t *best_effort_timestamp;
    AVRational *frame_sample_aspect;
    float quality;

    if (!ist->decoded_frame && !(ist->decoded_frame = avcodec_alloc_frame()))
        return AVERROR(ENOMEM);
    else
        avcodec_get_frame_defaults(ist->decoded_frame);
    decoded_frame = ist->decoded_frame;
    pkt->pts  = *pkt_pts;
    pkt->dts  = ist->dts;
    *pkt_pts  = AV_NOPTS_VALUE;

    update_benchmark(NULL);
    ret = avcodec_decode_video2(ist->st->codec,
                                decoded_frame, got_output, pkt);
    update_benchmark("decode_video %d.%d", ist->file_index, ist->st->index);
    if (ret < 0)
        return ret;

    quality = same_quant ? decoded_frame->quality : 0;
    if (!*got_output) {
        /* no picture yet */
        if (!pkt->size)
            for (i = 0; i < ist->nb_filters; i++)
                av_buffersrc_buffer(ist->filters[i]->filter, NULL);
        return ret;
    }

    best_effort_timestamp= av_opt_ptr(avcodec_get_frame_class(), decoded_frame, "best_effort_timestamp");
    if(*best_effort_timestamp != AV_NOPTS_VALUE)
        ist->next_pts = ist->pts = decoded_frame->pts = *best_effort_timestamp;

    pkt->size = 0;

    pre_process_video_frame(ist, (AVPicture *)decoded_frame, &buffer_to_free);

    rate_emu_sleep(ist);

    if (ist->st->sample_aspect_ratio.num)
        decoded_frame->sample_aspect_ratio = ist->st->sample_aspect_ratio;

    resample_changed = ist->resample_width   != decoded_frame->width  ||
                       ist->resample_height  != decoded_frame->height ||
                       ist->resample_pix_fmt != decoded_frame->format;
    if (resample_changed) {
        av_log(NULL, AV_LOG_INFO,
               "Input stream #%d:%d frame changed from size:%dx%d fmt:%s to size:%dx%d fmt:%s\n",
               ist->file_index, ist->st->index,
               ist->resample_width,  ist->resample_height,  av_get_pix_fmt_name(ist->resample_pix_fmt),
               decoded_frame->width, decoded_frame->height, av_get_pix_fmt_name(decoded_frame->format));

        ist->resample_width   = decoded_frame->width;
        ist->resample_height  = decoded_frame->height;
        ist->resample_pix_fmt = decoded_frame->format;

        for (i = 0; i < nb_filtergraphs; i++)
            if (ist_in_filtergraph(filtergraphs[i], ist) &&
                configure_filtergraph(filtergraphs[i]) < 0) {
                av_log(NULL, AV_LOG_FATAL, "Error reinitializing filters!\n");
                exit_program(1);
            }
    }

    frame_sample_aspect= av_opt_ptr(avcodec_get_frame_class(), decoded_frame, "sample_aspect_ratio");
    for (i = 0; i < ist->nb_filters; i++) {
        int changed =      ist->st->codec->width   != ist->filters[i]->filter->outputs[0]->w
                        || ist->st->codec->height  != ist->filters[i]->filter->outputs[0]->h
                        || ist->st->codec->pix_fmt != ist->filters[i]->filter->outputs[0]->format;
        // XXX what an ugly hack
        if (ist->filters[i]->graph->nb_outputs == 1)
            ist->filters[i]->graph->outputs[0]->ost->last_quality = quality;

        if (!frame_sample_aspect->num)
            *frame_sample_aspect = ist->st->sample_aspect_ratio;
        if (ist->dr1 && decoded_frame->type==FF_BUFFER_TYPE_USER && !changed) {
            FrameBuffer      *buf = decoded_frame->opaque;
            AVFilterBufferRef *fb = avfilter_get_video_buffer_ref_from_arrays(
                                        decoded_frame->data, decoded_frame->linesize,
                                        AV_PERM_READ | AV_PERM_PRESERVE,
                                        ist->st->codec->width, ist->st->codec->height,
                                        ist->st->codec->pix_fmt);

            avfilter_copy_frame_props(fb, decoded_frame);
            fb->buf->priv           = buf;
            fb->buf->free           = filter_release_buffer;

            buf->refcount++;
            av_buffersrc_buffer(ist->filters[i]->filter, fb);
        } else
        if(av_vsrc_buffer_add_frame(ist->filters[i]->filter, decoded_frame,AV_VSRC_BUF_FLAG_OVERWRITE)<0) {
            av_log(NULL, AV_LOG_FATAL, "Failed to inject frame into filter network\n");
            exit_program(1);
        }

    }

    av_free(buffer_to_free);
    return ret;
}

static int transcode_subtitles(InputStream *ist, AVPacket *pkt, int *got_output)
{
    AVSubtitle subtitle;
    int i, ret = avcodec_decode_subtitle2(ist->st->codec,
                                          &subtitle, got_output, pkt);
    if (ret < 0)
        return ret;
    if (!*got_output)
        return ret;

    rate_emu_sleep(ist);

    for (i = 0; i < nb_output_streams; i++) {
        OutputStream *ost = output_streams[i];

        if (!check_output_constraints(ist, ost) || !ost->encoding_needed)
            continue;

        do_subtitle_out(output_files[ost->file_index]->ctx, ost, ist, &subtitle, pkt->pts);
    }

    avsubtitle_free(&subtitle);
    return ret;
}

/* pkt = NULL means EOF (needed to flush decoder buffers) */
static int output_packet(InputStream *ist, const AVPacket *pkt)
{
    int ret = 0, i;
    int got_output;
    int64_t pkt_pts = AV_NOPTS_VALUE;

    AVPacket avpkt;

    if (ist->next_dts == AV_NOPTS_VALUE)
        ist->next_dts = ist->dts;
    if (ist->next_pts == AV_NOPTS_VALUE)
        ist->next_pts = ist->pts;

    if (pkt == NULL) {
        /* EOF handling */
        av_init_packet(&avpkt);
        avpkt.data = NULL;
        avpkt.size = 0;
        goto handle_eof;
    } else {
        avpkt = *pkt;
    }

    if (pkt->dts != AV_NOPTS_VALUE) {
        ist->next_dts = ist->dts = av_rescale_q(pkt->dts, ist->st->time_base, AV_TIME_BASE_Q);
        if (ist->st->codec->codec_type != AVMEDIA_TYPE_VIDEO || !ist->decoding_needed)
            ist->next_pts = ist->pts = av_rescale_q(pkt->dts, ist->st->time_base, AV_TIME_BASE_Q);
    }
    if(pkt->pts != AV_NOPTS_VALUE)
        pkt_pts = av_rescale_q(pkt->pts, ist->st->time_base, AV_TIME_BASE_Q);

    // while we have more to decode or while the decoder did output something on EOF
    while (ist->decoding_needed && (avpkt.size > 0 || (!pkt && got_output))) {
        int duration;
    handle_eof:

        ist->pts = ist->next_pts;
        ist->dts = ist->next_dts;

        if (avpkt.size && avpkt.size != pkt->size) {
            av_log(NULL, ist->showed_multi_packet_warning ? AV_LOG_VERBOSE : AV_LOG_WARNING,
                   "Multiple frames in a packet from stream %d\n", pkt->stream_index);
            ist->showed_multi_packet_warning = 1;
        }

        switch (ist->st->codec->codec_type) {
        case AVMEDIA_TYPE_AUDIO:
            ret = transcode_audio    (ist, &avpkt, &got_output);
            break;
        case AVMEDIA_TYPE_VIDEO:
            ret = transcode_video    (ist, &avpkt, &got_output, &pkt_pts);
            if (avpkt.duration) {
                duration = av_rescale_q(avpkt.duration, ist->st->time_base, AV_TIME_BASE_Q);
            } else if(ist->st->codec->time_base.num != 0 && ist->st->codec->time_base.den != 0) {
                int ticks= ist->st->parser ? ist->st->parser->repeat_pict+1 : ist->st->codec->ticks_per_frame;
                duration = ((int64_t)AV_TIME_BASE *
                                ist->st->codec->time_base.num * ticks) /
                                ist->st->codec->time_base.den;
            } else
                duration = 0;

            if(ist->dts != AV_NOPTS_VALUE && duration) {
                ist->next_dts += duration;
            }else
                ist->next_dts = AV_NOPTS_VALUE;

            if (got_output)
                ist->next_pts += duration; //FIXME the duration is not correct in some cases
            break;
        case AVMEDIA_TYPE_SUBTITLE:
            ret = transcode_subtitles(ist, &avpkt, &got_output);
            break;
        default:
            return -1;
        }

        if (ret < 0)
            return ret;

        avpkt.dts=
        avpkt.pts= AV_NOPTS_VALUE;

        // touch data and size only if not EOF
        if (pkt) {
            if(ist->st->codec->codec_type != AVMEDIA_TYPE_AUDIO)
                ret = avpkt.size;
            avpkt.data += ret;
            avpkt.size -= ret;
        }
        if (!got_output) {
            continue;
        }
    }

    /* handle stream copy */
    if (!ist->decoding_needed) {
        rate_emu_sleep(ist);
        ist->dts = ist->next_dts;
        switch (ist->st->codec->codec_type) {
        case AVMEDIA_TYPE_AUDIO:
            ist->next_dts += ((int64_t)AV_TIME_BASE * ist->st->codec->frame_size) /
                             ist->st->codec->sample_rate;
            break;
        case AVMEDIA_TYPE_VIDEO:
            if (pkt->duration) {
                ist->next_dts += av_rescale_q(pkt->duration, ist->st->time_base, AV_TIME_BASE_Q);
            } else if(ist->st->codec->time_base.num != 0) {
                int ticks= ist->st->parser ? ist->st->parser->repeat_pict + 1 : ist->st->codec->ticks_per_frame;
                ist->next_dts += ((int64_t)AV_TIME_BASE *
                                  ist->st->codec->time_base.num * ticks) /
                                  ist->st->codec->time_base.den;
            }
            break;
        }
        ist->pts = ist->dts;
        ist->next_pts = ist->next_dts;
    }
    for (i = 0; pkt && i < nb_output_streams; i++) {
        OutputStream *ost = output_streams[i];

        if (!check_output_constraints(ist, ost) || ost->encoding_needed)
            continue;

        do_streamcopy(ist, ost, pkt);
    }

    return 0;
}

static void print_sdp(void)
{
    char sdp[2048];
    int i;
    AVFormatContext **avc = av_malloc(sizeof(*avc) * nb_output_files);

    if (!avc)
        exit_program(1);
    for (i = 0; i < nb_output_files; i++)
        avc[i] = output_files[i]->ctx;

    av_sdp_create(avc, nb_output_files, sdp, sizeof(sdp));
    printf("SDP:\n%s\n", sdp);
    fflush(stdout);
    av_freep(&avc);
}

static int init_input_stream(int ist_index, char *error, int error_len)
{
    int i;
    InputStream *ist = input_streams[ist_index];

    if (ist->decoding_needed) {
        AVCodec *codec = ist->dec;
        if (!codec) {
            snprintf(error, error_len, "Decoder (codec %s) not found for input stream #%d:%d",
                    avcodec_get_name(ist->st->codec->codec_id), ist->file_index, ist->st->index);
            return AVERROR(EINVAL);
        }

        ist->dr1 = codec->capabilities & CODEC_CAP_DR1;
        if (codec->type == AVMEDIA_TYPE_VIDEO && ist->dr1) {
            ist->st->codec->get_buffer     = codec_get_buffer;
            ist->st->codec->release_buffer = codec_release_buffer;
            ist->st->codec->opaque         = ist;
        }

        if (!av_dict_get(ist->opts, "threads", NULL, 0))
            av_dict_set(&ist->opts, "threads", "auto", 0);
        if (avcodec_open2(ist->st->codec, codec, &ist->opts) < 0) {
            snprintf(error, error_len, "Error while opening decoder for input stream #%d:%d",
                    ist->file_index, ist->st->index);
            return AVERROR(EINVAL);
        }
        assert_codec_experimental(ist->st->codec, 0);
        assert_avoptions(ist->opts);

        if (ist->st->codec->codec_type == AVMEDIA_TYPE_AUDIO) {
            for (i = 0; i < nb_output_streams; i++) {
                OutputStream *ost = output_streams[i];
                if (ost->source_index == ist_index) {
                    if (!ist->st->codec->channel_layout || !ost->st->codec->channel_layout)
                        get_default_channel_layouts(ost, ist);
                    break;
                }
            }
        }
    }

    ist->dts = ist->st->avg_frame_rate.num ? - ist->st->codec->has_b_frames * AV_TIME_BASE / av_q2d(ist->st->avg_frame_rate) : 0;
    ist->next_pts = AV_NOPTS_VALUE;
    ist->next_dts = AV_NOPTS_VALUE;
    ist->is_start = 1;

    return 0;
}

static InputStream *get_input_stream(OutputStream *ost)
{
    if (ost->source_index >= 0)
        return input_streams[ost->source_index];

    if (ost->filter) {
        FilterGraph *fg = ost->filter->graph;
        int i;

        for (i = 0; i < fg->nb_inputs; i++)
            if (fg->inputs[i]->ist->st->codec->codec_type == ost->st->codec->codec_type)
                return fg->inputs[i]->ist;
    }

    return NULL;
}

static int transcode_init(void)
{
    int ret = 0, i, j, k;
    AVFormatContext *oc;
    AVCodecContext *codec, *icodec;
    OutputStream *ost;
    InputStream *ist;
    char error[1024];
    int want_sdp = 1;

    /* init framerate emulation */
    for (i = 0; i < nb_input_files; i++) {
        InputFile *ifile = input_files[i];
        if (ifile->rate_emu)
            for (j = 0; j < ifile->nb_streams; j++)
                input_streams[j + ifile->ist_index]->start = av_gettime();
    }

    /* output stream init */
    for (i = 0; i < nb_output_files; i++) {
        oc = output_files[i]->ctx;
        if (!oc->nb_streams && !(oc->oformat->flags & AVFMT_NOSTREAMS)) {
            av_dump_format(oc, i, oc->filename, 1);
            av_log(NULL, AV_LOG_ERROR, "Output file #%d does not contain any stream\n", i);
            return AVERROR(EINVAL);
        }
    }

    /* init complex filtergraphs */
    for (i = 0; i < nb_filtergraphs; i++)
        if ((ret = avfilter_graph_config(filtergraphs[i]->graph, NULL)) < 0)
            return ret;

    /* for each output stream, we compute the right encoding parameters */
    for (i = 0; i < nb_output_streams; i++) {
        ost = output_streams[i];
        oc  = output_files[ost->file_index]->ctx;
        ist = get_input_stream(ost);

        if (ost->attachment_filename)
            continue;

        codec  = ost->st->codec;

        if (ist) {
            icodec = ist->st->codec;

            ost->st->disposition          = ist->st->disposition;
            codec->bits_per_raw_sample    = icodec->bits_per_raw_sample;
            codec->chroma_sample_location = icodec->chroma_sample_location;
        }

        if (ost->stream_copy) {
            uint64_t extra_size = (uint64_t)icodec->extradata_size + FF_INPUT_BUFFER_PADDING_SIZE;

            if (extra_size > INT_MAX) {
                return AVERROR(EINVAL);
            }

            /* if stream_copy is selected, no need to decode or encode */
            codec->codec_id   = icodec->codec_id;
            codec->codec_type = icodec->codec_type;

            if (!codec->codec_tag) {
                if (!oc->oformat->codec_tag ||
                     av_codec_get_id (oc->oformat->codec_tag, icodec->codec_tag) == codec->codec_id ||
                     av_codec_get_tag(oc->oformat->codec_tag, icodec->codec_id) <= 0)
                    codec->codec_tag = icodec->codec_tag;
            }

            codec->bit_rate       = icodec->bit_rate;
            codec->rc_max_rate    = icodec->rc_max_rate;
            codec->rc_buffer_size = icodec->rc_buffer_size;
            codec->field_order    = icodec->field_order;
            codec->extradata      = av_mallocz(extra_size);
            if (!codec->extradata) {
                return AVERROR(ENOMEM);
            }
            memcpy(codec->extradata, icodec->extradata, icodec->extradata_size);
            codec->extradata_size= icodec->extradata_size;

            codec->time_base = ist->st->time_base;
            /*
             * Avi is a special case here because it supports variable fps but
             * having the fps and timebase differe significantly adds quite some
             * overhead
             */
            if(!strcmp(oc->oformat->name, "avi")) {
                if (   copy_tb<0 && av_q2d(icodec->time_base)*icodec->ticks_per_frame > 2*av_q2d(ist->st->time_base)
                                 && av_q2d(ist->st->time_base) < 1.0/500
                    || copy_tb==0){
                    codec->time_base = icodec->time_base;
                    codec->time_base.num *= icodec->ticks_per_frame;
                    codec->time_base.den *= 2;
                    codec->ticks_per_frame = 2;
                }
            } else if(!(oc->oformat->flags & AVFMT_VARIABLE_FPS)
                      && strcmp(oc->oformat->name, "mov") && strcmp(oc->oformat->name, "mp4") && strcmp(oc->oformat->name, "3gp")
                      && strcmp(oc->oformat->name, "3g2") && strcmp(oc->oformat->name, "psp") && strcmp(oc->oformat->name, "ipod")
            ) {
                if(   copy_tb<0 && av_q2d(icodec->time_base)*icodec->ticks_per_frame > av_q2d(ist->st->time_base)
                                && av_q2d(ist->st->time_base) < 1.0/500
                   || copy_tb==0){
                    codec->time_base = icodec->time_base;
                    codec->time_base.num *= icodec->ticks_per_frame;
                }
            }
            av_reduce(&codec->time_base.num, &codec->time_base.den,
                        codec->time_base.num, codec->time_base.den, INT_MAX);

            switch (codec->codec_type) {
            case AVMEDIA_TYPE_AUDIO:
                if (audio_volume != 256) {
                    av_log(NULL, AV_LOG_FATAL, "-acodec copy and -vol are incompatible (frames are not decoded)\n");
                    exit_program(1);
                }
                codec->channel_layout     = icodec->channel_layout;
                codec->sample_rate        = icodec->sample_rate;
                codec->channels           = icodec->channels;
                codec->frame_size         = icodec->frame_size;
                codec->audio_service_type = icodec->audio_service_type;
                codec->block_align        = icodec->block_align;
                break;
            case AVMEDIA_TYPE_VIDEO:
                codec->pix_fmt            = icodec->pix_fmt;
                codec->width              = icodec->width;
                codec->height             = icodec->height;
                codec->has_b_frames       = icodec->has_b_frames;
                if (!codec->sample_aspect_ratio.num) {
                    codec->sample_aspect_ratio   =
                    ost->st->sample_aspect_ratio =
                        ist->st->sample_aspect_ratio.num ? ist->st->sample_aspect_ratio :
                        ist->st->codec->sample_aspect_ratio.num ?
                        ist->st->codec->sample_aspect_ratio : (AVRational){0, 1};
                }