/* * Copyright (c) 2000-2003 Fabrice Bellard * * This file is part of FFmpeg. * * FFmpeg is free software; you can redistribute it and/or * modify it under the terms of the GNU Lesser General Public * License as published by the Free Software Foundation; either * version 2.1 of the License, or (at your option) any later version. * * FFmpeg is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * Lesser General Public License for more details. * * You should have received a copy of the GNU Lesser General Public * License along with FFmpeg; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA */ /** * @file * multimedia converter based on the FFmpeg libraries */ #include "config.h" #include #include #include #include #include #include #include #include #if HAVE_IO_H #include #endif #if HAVE_UNISTD_H #include #endif #include "libavformat/avformat.h" #include "libavdevice/avdevice.h" #include "libswresample/swresample.h" #include "libavutil/opt.h" #include "libavutil/channel_layout.h" #include "libavutil/parseutils.h" #include "libavutil/samplefmt.h" #include "libavutil/fifo.h" #include "libavutil/hwcontext.h" #include "libavutil/internal.h" #include "libavutil/intreadwrite.h" #include "libavutil/dict.h" #include "libavutil/display.h" #include "libavutil/mathematics.h" #include "libavutil/pixdesc.h" #include "libavutil/avstring.h" #include "libavutil/libm.h" #include "libavutil/imgutils.h" #include "libavutil/timestamp.h" #include "libavutil/bprint.h" #include "libavutil/time.h" #include "libavutil/thread.h" #include "libavutil/threadmessage.h" #include "libavcodec/mathops.h" #include "libavcodec/version.h" #include "libavformat/os_support.h" # include "libavfilter/avfilter.h" # include "libavfilter/buffersrc.h" # include "libavfilter/buffersink.h" #if HAVE_SYS_RESOURCE_H #include #include #include #elif HAVE_GETPROCESSTIMES #include #endif #if HAVE_GETPROCESSMEMORYINFO #include #include #endif #if HAVE_SETCONSOLECTRLHANDLER #include #endif #if HAVE_SYS_SELECT_H #include #endif #if HAVE_TERMIOS_H #include #include #include #include #elif HAVE_KBHIT #include #endif #include #include "ffmpeg.h" #include "cmdutils.h" #include "sync_queue.h" #include "libavutil/avassert.h" const char program_name[] = "ffmpeg"; const int program_birth_year = 2000; static FILE *vstats_file; const char *const forced_keyframes_const_names[] = { "n", "n_forced", "prev_forced_n", "prev_forced_t", "t", NULL }; typedef struct BenchmarkTimeStamps { int64_t real_usec; int64_t user_usec; int64_t sys_usec; } BenchmarkTimeStamps; static BenchmarkTimeStamps get_benchmark_time_stamps(void); static int64_t getmaxrss(void); static int ifilter_has_all_input_formats(FilterGraph *fg); static int64_t nb_frames_dup = 0; static uint64_t dup_warning = 1000; static int64_t nb_frames_drop = 0; static int64_t decode_error_stat[2]; unsigned nb_output_dumped = 0; static BenchmarkTimeStamps current_time; AVIOContext *progress_avio = NULL; InputStream **input_streams = NULL; int nb_input_streams = 0; InputFile **input_files = NULL; int nb_input_files = 0; OutputStream **output_streams = NULL; int nb_output_streams = 0; OutputFile **output_files = NULL; int nb_output_files = 0; FilterGraph **filtergraphs; int nb_filtergraphs; #if HAVE_TERMIOS_H /* init terminal so that we can grab keys */ static struct termios oldtty; static int restore_tty; #endif /* sub2video hack: Convert subtitles to video with alpha to insert them in filter graphs. This is a temporary solution until libavfilter gets real subtitles support. */ static int sub2video_get_blank_frame(InputStream *ist) { int ret; AVFrame *frame = ist->sub2video.frame; av_frame_unref(frame); ist->sub2video.frame->width = ist->dec_ctx->width ? ist->dec_ctx->width : ist->sub2video.w; ist->sub2video.frame->height = ist->dec_ctx->height ? ist->dec_ctx->height : ist->sub2video.h; ist->sub2video.frame->format = AV_PIX_FMT_RGB32; if ((ret = av_frame_get_buffer(frame, 0)) < 0) return ret; memset(frame->data[0], 0, frame->height * frame->linesize[0]); return 0; } static void sub2video_copy_rect(uint8_t *dst, int dst_linesize, int w, int h, AVSubtitleRect *r) { uint32_t *pal, *dst2; uint8_t *src, *src2; int x, y; if (r->type != SUBTITLE_BITMAP) { av_log(NULL, AV_LOG_WARNING, "sub2video: non-bitmap subtitle\n"); return; } if (r->x < 0 || r->x + r->w > w || r->y < 0 || r->y + r->h > h) { av_log(NULL, AV_LOG_WARNING, "sub2video: rectangle (%d %d %d %d) overflowing %d %d\n", r->x, r->y, r->w, r->h, w, h ); return; } dst += r->y * dst_linesize + r->x * 4; src = r->data[0]; pal = (uint32_t *)r->data[1]; for (y = 0; y < r->h; y++) { dst2 = (uint32_t *)dst; src2 = src; for (x = 0; x < r->w; x++) *(dst2++) = pal[*(src2++)]; dst += dst_linesize; src += r->linesize[0]; } } static void sub2video_push_ref(InputStream *ist, int64_t pts) { AVFrame *frame = ist->sub2video.frame; int i; int ret; av_assert1(frame->data[0]); ist->sub2video.last_pts = frame->pts = pts; for (i = 0; i < ist->nb_filters; i++) { ret = av_buffersrc_add_frame_flags(ist->filters[i]->filter, frame, AV_BUFFERSRC_FLAG_KEEP_REF | AV_BUFFERSRC_FLAG_PUSH); if (ret != AVERROR_EOF && ret < 0) av_log(NULL, AV_LOG_WARNING, "Error while add the frame to buffer source(%s).\n", av_err2str(ret)); } } void sub2video_update(InputStream *ist, int64_t heartbeat_pts, AVSubtitle *sub) { AVFrame *frame = ist->sub2video.frame; int8_t *dst; int dst_linesize; int num_rects, i; int64_t pts, end_pts; if (!frame) return; if (sub) { pts = av_rescale_q(sub->pts + sub->start_display_time * 1000LL, AV_TIME_BASE_Q, ist->st->time_base); end_pts = av_rescale_q(sub->pts + sub->end_display_time * 1000LL, AV_TIME_BASE_Q, ist->st->time_base); num_rects = sub->num_rects; } else { /* If we are initializing the system, utilize current heartbeat PTS as the start time, and show until the following subpicture is received. Otherwise, utilize the previous subpicture's end time as the fall-back value. */ pts = ist->sub2video.initialize ? heartbeat_pts : ist->sub2video.end_pts; end_pts = INT64_MAX; num_rects = 0; } if (sub2video_get_blank_frame(ist) < 0) { av_log(NULL, AV_LOG_ERROR, "Impossible to get a blank canvas.\n"); return; } dst = frame->data [0]; dst_linesize = frame->linesize[0]; for (i = 0; i < num_rects; i++) sub2video_copy_rect(dst, dst_linesize, frame->width, frame->height, sub->rects[i]); sub2video_push_ref(ist, pts); ist->sub2video.end_pts = end_pts; ist->sub2video.initialize = 0; } static void sub2video_heartbeat(InputStream *ist, int64_t pts) { InputFile *infile = input_files[ist->file_index]; int i, j, nb_reqs; int64_t pts2; /* When a frame is read from a file, examine all sub2video streams in the same file and send the sub2video frame again. Otherwise, decoded video frames could be accumulating in the filter graph while a filter (possibly overlay) is desperately waiting for a subtitle frame. */ for (i = 0; i < infile->nb_streams; i++) { InputStream *ist2 = input_streams[infile->ist_index + i]; if (!ist2->sub2video.frame) continue; /* subtitles seem to be usually muxed ahead of other streams; if not, subtracting a larger time here is necessary */ pts2 = av_rescale_q(pts, ist->st->time_base, ist2->st->time_base) - 1; /* do not send the heartbeat frame if the subtitle is already ahead */ if (pts2 <= ist2->sub2video.last_pts) continue; if (pts2 >= ist2->sub2video.end_pts || ist2->sub2video.initialize) /* if we have hit the end of the current displayed subpicture, or if we need to initialize the system, update the overlayed subpicture and its start/end times */ sub2video_update(ist2, pts2 + 1, NULL); for (j = 0, nb_reqs = 0; j < ist2->nb_filters; j++) nb_reqs += av_buffersrc_get_nb_failed_requests(ist2->filters[j]->filter); if (nb_reqs) sub2video_push_ref(ist2, pts2); } } static void sub2video_flush(InputStream *ist) { int i; int ret; if (ist->sub2video.end_pts < INT64_MAX) sub2video_update(ist, INT64_MAX, NULL); for (i = 0; i < ist->nb_filters; i++) { ret = av_buffersrc_add_frame(ist->filters[i]->filter, NULL); if (ret != AVERROR_EOF && ret < 0) av_log(NULL, AV_LOG_WARNING, "Flush the frame error.\n"); } } /* end of sub2video hack */ static void term_exit_sigsafe(void) { #if HAVE_TERMIOS_H if(restore_tty) tcsetattr (0, TCSANOW, &oldtty); #endif } void term_exit(void) { av_log(NULL, AV_LOG_QUIET, "%s", ""); term_exit_sigsafe(); } static volatile int received_sigterm = 0; static volatile int received_nb_signals = 0; static atomic_int transcode_init_done = ATOMIC_VAR_INIT(0); static volatile int ffmpeg_exited = 0; int main_return_code = 0; static int64_t copy_ts_first_pts = AV_NOPTS_VALUE; static void sigterm_handler(int sig) { int ret; received_sigterm = sig; received_nb_signals++; term_exit_sigsafe(); if(received_nb_signals > 3) { ret = write(2/*STDERR_FILENO*/, "Received > 3 system signals, hard exiting\n", strlen("Received > 3 system signals, hard exiting\n")); if (ret < 0) { /* Do nothing */ }; exit(123); } } #if HAVE_SETCONSOLECTRLHANDLER static BOOL WINAPI CtrlHandler(DWORD fdwCtrlType) { av_log(NULL, AV_LOG_DEBUG, "\nReceived windows signal %ld\n", fdwCtrlType); switch (fdwCtrlType) { case CTRL_C_EVENT: case CTRL_BREAK_EVENT: sigterm_handler(SIGINT); return TRUE; case CTRL_CLOSE_EVENT: case CTRL_LOGOFF_EVENT: case CTRL_SHUTDOWN_EVENT: sigterm_handler(SIGTERM); /* Basically, with these 3 events, when we return from this method the process is hard terminated, so stall as long as we need to to try and let the main thread(s) clean up and gracefully terminate (we have at most 5 seconds, but should be done far before that). */ while (!ffmpeg_exited) { Sleep(0); } return TRUE; default: av_log(NULL, AV_LOG_ERROR, "Received unknown windows signal %ld\n", fdwCtrlType); return FALSE; } } #endif #ifdef __linux__ #define SIGNAL(sig, func) \ do { \ action.sa_handler = func; \ sigaction(sig, &action, NULL); \ } while (0) #else #define SIGNAL(sig, func) \ signal(sig, func) #endif void term_init(void) { #if defined __linux__ struct sigaction action = {0}; action.sa_handler = sigterm_handler; /* block other interrupts while processing this one */ sigfillset(&action.sa_mask); /* restart interruptible functions (i.e. don't fail with EINTR) */ action.sa_flags = SA_RESTART; #endif #if HAVE_TERMIOS_H if (stdin_interaction) { struct termios tty; if (tcgetattr (0, &tty) == 0) { oldtty = tty; restore_tty = 1; tty.c_iflag &= ~(IGNBRK|BRKINT|PARMRK|ISTRIP |INLCR|IGNCR|ICRNL|IXON); tty.c_oflag |= OPOST; tty.c_lflag &= ~(ECHO|ECHONL|ICANON|IEXTEN); tty.c_cflag &= ~(CSIZE|PARENB); tty.c_cflag |= CS8; tty.c_cc[VMIN] = 1; tty.c_cc[VTIME] = 0; tcsetattr (0, TCSANOW, &tty); } SIGNAL(SIGQUIT, sigterm_handler); /* Quit (POSIX). */ } #endif SIGNAL(SIGINT , sigterm_handler); /* Interrupt (ANSI). */ SIGNAL(SIGTERM, sigterm_handler); /* Termination (ANSI). */ #ifdef SIGXCPU SIGNAL(SIGXCPU, sigterm_handler); #endif #ifdef SIGPIPE signal(SIGPIPE, SIG_IGN); /* Broken pipe (POSIX). */ #endif #if HAVE_SETCONSOLECTRLHANDLER SetConsoleCtrlHandler((PHANDLER_ROUTINE) CtrlHandler, TRUE); #endif } /* read a key without blocking */ static int read_key(void) { unsigned char ch; #if HAVE_TERMIOS_H int n = 1; struct timeval tv; fd_set rfds; FD_ZERO(&rfds); FD_SET(0, &rfds); tv.tv_sec = 0; tv.tv_usec = 0; n = select(1, &rfds, NULL, NULL, &tv); if (n > 0) { n = read(0, &ch, 1); if (n == 1) return ch; return n; } #elif HAVE_KBHIT # if HAVE_PEEKNAMEDPIPE static int is_pipe; static HANDLE input_handle; DWORD dw, nchars; if(!input_handle){ input_handle = GetStdHandle(STD_INPUT_HANDLE); is_pipe = !GetConsoleMode(input_handle, &dw); } if (is_pipe) { /* When running under a GUI, you will end here. */ if (!PeekNamedPipe(input_handle, NULL, 0, NULL, &nchars, NULL)) { // input pipe may have been closed by the program that ran ffmpeg return -1; } //Read it if(nchars != 0) { read(0, &ch, 1); return ch; }else{ return -1; } } # endif if(kbhit()) return(getch()); #endif return -1; } static int decode_interrupt_cb(void *ctx) { return received_nb_signals > atomic_load(&transcode_init_done); } const AVIOInterruptCB int_cb = { decode_interrupt_cb, NULL }; static void ffmpeg_cleanup(int ret) { int i, j; if (do_benchmark) { int maxrss = getmaxrss() / 1024; av_log(NULL, AV_LOG_INFO, "bench: maxrss=%ikB\n", maxrss); } for (i = 0; i < nb_filtergraphs; i++) { FilterGraph *fg = filtergraphs[i]; avfilter_graph_free(&fg->graph); for (j = 0; j < fg->nb_inputs; j++) { InputFilter *ifilter = fg->inputs[j]; struct InputStream *ist = ifilter->ist; if (ifilter->frame_queue) { AVFrame *frame; while (av_fifo_read(ifilter->frame_queue, &frame, 1) >= 0) av_frame_free(&frame); av_fifo_freep2(&ifilter->frame_queue); } av_freep(&ifilter->displaymatrix); if (ist->sub2video.sub_queue) { AVSubtitle sub; while (av_fifo_read(ist->sub2video.sub_queue, &sub, 1) >= 0) avsubtitle_free(&sub); av_fifo_freep2(&ist->sub2video.sub_queue); } av_buffer_unref(&ifilter->hw_frames_ctx); av_freep(&ifilter->name); av_freep(&fg->inputs[j]); } av_freep(&fg->inputs); for (j = 0; j < fg->nb_outputs; j++) { OutputFilter *ofilter = fg->outputs[j]; avfilter_inout_free(&ofilter->out_tmp); av_freep(&ofilter->name); av_channel_layout_uninit(&ofilter->ch_layout); av_freep(&fg->outputs[j]); } av_freep(&fg->outputs); av_freep(&fg->graph_desc); av_freep(&filtergraphs[i]); } av_freep(&filtergraphs); /* close files */ for (i = 0; i < nb_output_files; i++) of_close(&output_files[i]); for (i = 0; i < nb_output_streams; i++) { OutputStream *ost = output_streams[i]; if (!ost) continue; av_bsf_free(&ost->bsf_ctx); av_frame_free(&ost->filtered_frame); av_frame_free(&ost->sq_frame); av_frame_free(&ost->last_frame); av_packet_free(&ost->pkt); av_dict_free(&ost->encoder_opts); av_freep(&ost->forced_keyframes); av_expr_free(ost->forced_keyframes_pexpr); av_freep(&ost->avfilter); av_freep(&ost->logfile_prefix); #if FFMPEG_OPT_MAP_CHANNEL av_freep(&ost->audio_channels_map); ost->audio_channels_mapped = 0; #endif av_dict_free(&ost->sws_dict); av_dict_free(&ost->swr_opts); if (ost->enc_ctx) av_freep(&ost->enc_ctx->stats_in); avcodec_free_context(&ost->enc_ctx); av_freep(&output_streams[i]); } free_input_threads(); for (i = 0; i < nb_input_files; i++) { avformat_close_input(&input_files[i]->ctx); av_freep(&input_files[i]); } for (i = 0; i < nb_input_streams; i++) { InputStream *ist = input_streams[i]; av_frame_free(&ist->decoded_frame); av_packet_free(&ist->pkt); av_dict_free(&ist->decoder_opts); avsubtitle_free(&ist->prev_sub.subtitle); av_frame_free(&ist->sub2video.frame); av_freep(&ist->filters); av_freep(&ist->hwaccel_device); av_freep(&ist->dts_buffer); avcodec_free_context(&ist->dec_ctx); av_freep(&input_streams[i]); } if (vstats_file) { if (fclose(vstats_file)) av_log(NULL, AV_LOG_ERROR, "Error closing vstats file, loss of information possible: %s\n", av_err2str(AVERROR(errno))); } av_freep(&vstats_filename); av_freep(&filter_nbthreads); av_freep(&input_streams); av_freep(&input_files); av_freep(&output_streams); av_freep(&output_files); uninit_opts(); avformat_network_deinit(); if (received_sigterm) { av_log(NULL, AV_LOG_INFO, "Exiting normally, received signal %d.\n", (int) received_sigterm); } else if (ret && atomic_load(&transcode_init_done)) { av_log(NULL, AV_LOG_INFO, "Conversion failed!\n"); } term_exit(); ffmpeg_exited = 1; } void remove_avoptions(AVDictionary **a, AVDictionary *b) { const AVDictionaryEntry *t = NULL; while ((t = av_dict_get(b, "", t, AV_DICT_IGNORE_SUFFIX))) { av_dict_set(a, t->key, NULL, AV_DICT_MATCH_CASE); } } void assert_avoptions(AVDictionary *m) { const AVDictionaryEntry *t; if ((t = av_dict_get(m, "", NULL, AV_DICT_IGNORE_SUFFIX))) { av_log(NULL, AV_LOG_FATAL, "Option %s not found.\n", t->key); exit_program(1); } } static void abort_codec_experimental(const AVCodec *c, int encoder) { exit_program(1); } static void update_benchmark(const char *fmt, ...) { if (do_benchmark_all) { BenchmarkTimeStamps t = get_benchmark_time_stamps(); va_list va; char buf[1024]; if (fmt) { va_start(va, fmt); vsnprintf(buf, sizeof(buf), fmt, va); va_end(va); av_log(NULL, AV_LOG_INFO, "bench: %8" PRIu64 " user %8" PRIu64 " sys %8" PRIu64 " real %s \n", t.user_usec - current_time.user_usec, t.sys_usec - current_time.sys_usec, t.real_usec - current_time.real_usec, buf); } current_time = t; } } static void close_output_stream(OutputStream *ost) { OutputFile *of = output_files[ost->file_index]; ost->finished |= ENCODER_FINISHED; if (ost->sq_idx_encode >= 0) sq_send(of->sq_encode, ost->sq_idx_encode, SQFRAME(NULL)); } /* * Send a single packet to the output, applying any bitstream filters * associated with the output stream. This may result in any number * of packets actually being written, depending on what bitstream * filters are applied. The supplied packet is consumed and will be * blank (as if newly-allocated) when this function returns. * * If eof is set, instead indicate EOF to all bitstream filters and * therefore flush any delayed packets to the output. A blank packet * must be supplied in this case. */ static void output_packet(OutputFile *of, AVPacket *pkt, OutputStream *ost, int eof) { const char *err_msg; int ret = 0; if (!eof && pkt->dts != AV_NOPTS_VALUE) ost->last_mux_dts = av_rescale_q(pkt->dts, ost->mux_timebase, AV_TIME_BASE_Q); /* apply the output bitstream filters */ if (ost->bsf_ctx) { int bsf_eof = 0; ret = av_bsf_send_packet(ost->bsf_ctx, eof ? NULL : pkt); if (ret < 0) { err_msg = "submitting a packet for bitstream filtering"; goto fail; } while (!bsf_eof) { ret = av_bsf_receive_packet(ost->bsf_ctx, pkt); if (ret == AVERROR(EAGAIN)) return; else if (ret == AVERROR_EOF) bsf_eof = 1; else if (ret < 0) { err_msg = "applying bitstream filters to a packet"; goto fail; } ret = of_submit_packet(of, bsf_eof ? NULL : pkt, ost); if (ret < 0) goto mux_fail; } } else { ret = of_submit_packet(of, eof ? NULL : pkt, ost); if (ret < 0) goto mux_fail; } return; mux_fail: err_msg = "submitting a packet to the muxer"; fail: av_log(NULL, AV_LOG_ERROR, "Error %s for output stream #%d:%d.\n", err_msg, ost->file_index, ost->index); if (exit_on_error) exit_program(1); } static int check_recording_time(OutputStream *ost) { OutputFile *of = output_files[ost->file_index]; if (of->recording_time != INT64_MAX && av_compare_ts(ost->sync_opts - ost->first_pts, ost->enc_ctx->time_base, of->recording_time, AV_TIME_BASE_Q) >= 0) { close_output_stream(ost); return 0; } return 1; } static double adjust_frame_pts_to_encoder_tb(OutputFile *of, OutputStream *ost, AVFrame *frame) { double float_pts = AV_NOPTS_VALUE; // this is identical to frame.pts but with higher precision int64_t orig_pts = AV_NOPTS_VALUE; AVCodecContext *enc = ost->enc_ctx; AVRational filter_tb = (AVRational){ -1, -1 }; if (!frame || frame->pts == AV_NOPTS_VALUE || !enc || !ost->filter || !ost->filter->graph->graph) goto early_exit; { AVFilterContext *filter = ost->filter->filter; int64_t start_time = (of->start_time == AV_NOPTS_VALUE) ? 0 : of->start_time; AVRational tb = enc->time_base; int extra_bits = av_clip(29 - av_log2(tb.den), 0, 16); filter_tb = av_buffersink_get_time_base(filter); orig_pts = frame->pts; tb.den <<= extra_bits; float_pts = av_rescale_q(frame->pts, filter_tb, tb) - av_rescale_q(start_time, AV_TIME_BASE_Q, tb); float_pts /= 1 << extra_bits; // avoid exact midoints to reduce the chance of rounding differences, this can be removed in case the fps code is changed to work with integers float_pts += FFSIGN(float_pts) * 1.0 / (1<<17); frame->pts = av_rescale_q(frame->pts, filter_tb, enc->time_base) - av_rescale_q(start_time, AV_TIME_BASE_Q, enc->time_base); } early_exit: if (debug_ts) { av_log(NULL, AV_LOG_INFO, "filter_raw -> pts:%s pts_time:%s time_base:%d/%d\n", frame ? av_ts2str(orig_pts) : "NULL", frame ? av_ts2timestr(orig_pts, &filter_tb) : "NULL", filter_tb.num, filter_tb.den); av_log(NULL, AV_LOG_INFO, "filter -> pts:%s pts_time:%s exact:%f time_base:%d/%d\n", frame ? av_ts2str(frame->pts) : "NULL", (enc && frame) ? av_ts2timestr(frame->pts, &enc->time_base) : "NULL", float_pts, enc ? enc->time_base.num : -1, enc ? enc->time_base.den : -1); } return float_pts; } static int init_output_stream(OutputStream *ost, AVFrame *frame, char *error, int error_len); static int init_output_stream_wrapper(OutputStream *ost, AVFrame *frame, unsigned int fatal) { int ret = AVERROR_BUG; char error[1024] = {0}; if (ost->initialized) return 0; ret = init_output_stream(ost, frame, error, sizeof(error)); if (ret < 0) { av_log(NULL, AV_LOG_ERROR, "Error initializing output stream %d:%d -- %s\n", ost->file_index, ost->index, error); if (fatal) exit_program(1); } return ret; } static double psnr(double d) { return -10.0 * log10(d); } static void update_video_stats(OutputStream *ost, const AVPacket *pkt, int write_vstats) { const uint8_t *sd = av_packet_get_side_data(pkt, AV_PKT_DATA_QUALITY_STATS, NULL); AVCodecContext *enc = ost->enc_ctx; int64_t frame_number; double ti1, bitrate, avg_bitrate; ost->quality = sd ? AV_RL32(sd) : -1; ost->pict_type = sd ? sd[4] : AV_PICTURE_TYPE_NONE; for (int i = 0; ierror); i++) { if (sd && i < sd[5]) ost->error[i] = AV_RL64(sd + 8 + 8*i); else ost->error[i] = -1; } if (!write_vstats) return; /* this is executed just the first time update_video_stats is called */ if (!vstats_file) { vstats_file = fopen(vstats_filename, "w"); if (!vstats_file) { perror("fopen"); exit_program(1); } } frame_number = ost->packets_encoded; if (vstats_version <= 1) { fprintf(vstats_file, "frame= %5"PRId64" q= %2.1f ", frame_number, ost->quality / (float)FF_QP2LAMBDA); } else { fprintf(vstats_file, "out= %2d st= %2d frame= %5"PRId64" q= %2.1f ", ost->file_index, ost->index, frame_number, ost->quality / (float)FF_QP2LAMBDA); } if (ost->error[0]>=0 && (enc->flags & AV_CODEC_FLAG_PSNR)) fprintf(vstats_file, "PSNR= %6.2f ", psnr(ost->error[0] / (enc->width * enc->height * 255.0 * 255.0))); fprintf(vstats_file,"f_size= %6d ", pkt->size); /* compute pts value */ ti1 = pkt->dts * av_q2d(ost->mux_timebase); if (ti1 < 0.01) ti1 = 0.01; bitrate = (pkt->size * 8) / av_q2d(enc->time_base) / 1000.0; avg_bitrate = (double)(ost->data_size * 8) / ti1 / 1000.0; fprintf(vstats_file, "s_size= %8.0fkB time= %0.3f br= %7.1fkbits/s avg_br= %7.1fkbits/s ", (double)ost->data_size / 1024, ti1, bitrate, avg_bitrate); fprintf(vstats_file, "type= %c\n", av_get_picture_type_char(ost->pict_type)); } static int encode_frame(OutputFile *of, OutputStream *ost, AVFrame *frame) { AVCodecContext *enc = ost->enc_ctx; AVPacket *pkt = ost->pkt; const char *type_desc = av_get_media_type_string(enc->codec_type); const char *action = frame ? "encode" : "flush"; int ret; if (frame) { ost->frames_encoded++; ost->samples_encoded += frame->nb_samples; if (debug_ts) { av_log(NULL, AV_LOG_INFO, "encoder <- type:%s " "frame_pts:%s frame_pts_time:%s time_base:%d/%d\n", type_desc, av_ts2str(frame->pts), av_ts2timestr(frame->pts, &enc->time_base), enc->time_base.num, enc->time_base.den); } frame->reordered_opaque = (int64_t)frame->opaque; } update_benchmark(NULL); ret = avcodec_send_frame(enc, frame); if (ret < 0 && !(ret == AVERROR_EOF && !frame)) { av_log(NULL, AV_LOG_ERROR, "Error submitting %s frame to the encoder\n", type_desc); return ret; } while (1) { ret = avcodec_receive_packet(enc, pkt); update_benchmark("%s_%s %d.%d", action, type_desc, ost->file_index, ost->index); /* if two pass, output log on success and EOF */ if ((ret >= 0 || ret == AVERROR_EOF) && ost->logfile && enc->stats_out) fprintf(ost->logfile, "%s", enc->stats_out); if (ret == AVERROR(EAGAIN)) { av_assert0(frame); // should never happen during flushing return 0; } else if (ret == AVERROR_EOF) { output_packet(of, pkt, ost, 1); return ret; } else if (ret < 0) { av_log(NULL, AV_LOG_ERROR, "%s encoding failed\n", type_desc); return ret; } if (enc->codec->capabilities & AV_CODEC_CAP_ENCODER_REORDERED_OPAQUE) pkt->opaque = (void*)enc->reordered_opaque; else if (frame) pkt->opaque = frame->opaque; if (debug_ts) { av_log(NULL, AV_LOG_INFO, "encoder -> type:%s " "pkt_pts:%s pkt_pts_time:%s pkt_dts:%s pkt_dts_time:%s " "duration:%s duration_time:%s\n", type_desc, av_ts2str(pkt->pts), av_ts2timestr(pkt->pts, &enc->time_base), av_ts2str(pkt->dts), av_ts2timestr(pkt->dts, &enc->time_base), av_ts2str(pkt->duration), av_ts2timestr(pkt->duration, &enc->time_base)); } av_packet_rescale_ts(pkt, enc->time_base, ost->mux_timebase); if (debug_ts) { av_log(NULL, AV_LOG_INFO, "encoder -> type:%s " "pkt_pts:%s pkt_pts_time:%s pkt_dts:%s pkt_dts_time:%s " "duration:%s duration_time:%s\n", type_desc, av_ts2str(pkt->pts), av_ts2timestr(pkt->pts, &enc->time_base), av_ts2str(pkt->dts), av_ts2timestr(pkt->dts, &enc->time_base), av_ts2str(pkt->duration), av_ts2timestr(pkt->duration, &enc->time_base)); } if (enc->codec_type == AVMEDIA_TYPE_VIDEO) update_video_stats(ost, pkt, !!vstats_filename); ost->packets_encoded++; output_packet(of, pkt, ost, 0); } av_assert0(0); } static int submit_encode_frame(OutputFile *of, OutputStream *ost, AVFrame *frame) { int ret; if (ost->sq_idx_encode < 0) return encode_frame(of, ost, frame); if (frame) { ret = av_frame_ref(ost->sq_frame, frame); if (ret < 0) return ret; frame = ost->sq_frame; } ret = sq_send(of->sq_encode, ost->sq_idx_encode, SQFRAME(frame)); if (ret < 0) { if (frame) av_frame_unref(frame); if (ret != AVERROR_EOF) return ret; } while (1) { AVFrame *enc_frame = ost->sq_frame; ret = sq_receive(of->sq_encode, ost->sq_idx_encode, SQFRAME(enc_frame)); if (ret == AVERROR_EOF) { enc_frame = NULL; } else if (ret < 0) { return (ret == AVERROR(EAGAIN)) ? 0 : ret; } ret = encode_frame(of, ost, enc_frame); if (enc_frame) av_frame_unref(enc_frame); if (ret < 0) { if (ret == AVERROR_EOF) close_output_stream(ost); return ret; } } } static void do_audio_out(OutputFile *of, OutputStream *ost, AVFrame *frame) { int ret; adjust_frame_pts_to_encoder_tb(of, ost, frame); if (!check_recording_time(ost)) return; if (frame->pts == AV_NOPTS_VALUE || audio_sync_method < 0) frame->pts = ost->sync_opts; ost->sync_opts = frame->pts + frame->nb_samples; ret = submit_encode_frame(of, ost, frame); if (ret < 0 && ret != AVERROR_EOF) exit_program(1); } static void do_subtitle_out(OutputFile *of, OutputStream *ost, AVSubtitle *sub) { int subtitle_out_max_size = 1024 * 1024; int subtitle_out_size, nb, i, ret; AVCodecContext *enc; AVPacket *pkt = ost->pkt; int64_t pts; if (sub->pts == AV_NOPTS_VALUE) { av_log(NULL, AV_LOG_ERROR, "Subtitle packets must have a pts\n"); if (exit_on_error) exit_program(1); return; } enc = ost->enc_ctx; /* Note: DVB subtitle need one packet to draw them and one other packet to clear them */ /* XXX: signal it in the codec context ? */ if (enc->codec_id == AV_CODEC_ID_DVB_SUBTITLE) nb = 2; else nb = 1; /* shift timestamp to honor -ss and make check_recording_time() work with -t */ pts = sub->pts; if (output_files[ost->file_index]->start_time != AV_NOPTS_VALUE) pts -= output_files[ost->file_index]->start_time; for (i = 0; i < nb; i++) { unsigned save_num_rects = sub->num_rects; ost->sync_opts = av_rescale_q(pts, AV_TIME_BASE_Q, enc->time_base); if (!check_recording_time(ost)) return; ret = av_new_packet(pkt, subtitle_out_max_size); if (ret < 0) { av_log(NULL, AV_LOG_FATAL, "Failed to allocate subtitle encode buffer\n"); exit_program(1); } sub->pts = pts; // start_display_time is required to be 0 sub->pts += av_rescale_q(sub->start_display_time, (AVRational){ 1, 1000 }, AV_TIME_BASE_Q); sub->end_display_time -= sub->start_display_time; sub->start_display_time = 0; if (i == 1) sub->num_rects = 0; ost->frames_encoded++; subtitle_out_size = avcodec_encode_subtitle(enc, pkt->data, pkt->size, sub); if (i == 1) sub->num_rects = save_num_rects; if (subtitle_out_size < 0) { av_log(NULL, AV_LOG_FATAL, "Subtitle encoding failed\n"); exit_program(1); } av_shrink_packet(pkt, subtitle_out_size); pkt->pts = av_rescale_q(sub->pts, AV_TIME_BASE_Q, ost->mux_timebase); pkt->duration = av_rescale_q(sub->end_display_time, (AVRational){ 1, 1000 }, ost->mux_timebase); if (enc->codec_id == AV_CODEC_ID_DVB_SUBTITLE) { /* XXX: the pts correction is handled here. Maybe handling it in the codec would be better */ if (i == 0) pkt->pts += av_rescale_q(sub->start_display_time, (AVRational){ 1, 1000 }, ost->mux_timebase); else pkt->pts += av_rescale_q(sub->end_display_time, (AVRational){ 1, 1000 }, ost->mux_timebase); } pkt->dts = pkt->pts; output_packet(of, pkt, ost, 0); } } /* May modify/reset next_picture */ static void do_video_out(OutputFile *of, OutputStream *ost, AVFrame *next_picture) { int ret; AVCodecContext *enc = ost->enc_ctx; AVRational frame_rate; int64_t nb_frames, nb0_frames, i; double delta, delta0; double duration = 0; double sync_ipts = AV_NOPTS_VALUE; InputStream *ist = NULL; AVFilterContext *filter = ost->filter->filter; init_output_stream_wrapper(ost, next_picture, 1); sync_ipts = adjust_frame_pts_to_encoder_tb(of, ost, next_picture); if (ost->source_index >= 0) ist = input_streams[ost->source_index]; frame_rate = av_buffersink_get_frame_rate(filter); if (frame_rate.num > 0 && frame_rate.den > 0) duration = 1/(av_q2d(frame_rate) * av_q2d(enc->time_base)); if(ist && ist->st->start_time != AV_NOPTS_VALUE && ist->first_dts != AV_NOPTS_VALUE && ost->frame_rate.num) duration = FFMIN(duration, 1/(av_q2d(ost->frame_rate) * av_q2d(enc->time_base))); if (!ost->filters_script && !ost->filters && (nb_filtergraphs == 0 || !filtergraphs[0]->graph_desc) && next_picture && ist && lrintf(next_picture->duration * av_q2d(ist->st->time_base) / av_q2d(enc->time_base)) > 0) { duration = lrintf(next_picture->duration * av_q2d(ist->st->time_base) / av_q2d(enc->time_base)); } if (!next_picture) { //end, flushing nb0_frames = nb_frames = mid_pred(ost->last_nb0_frames[0], ost->last_nb0_frames[1], ost->last_nb0_frames[2]); } else { delta0 = sync_ipts - ost->sync_opts; // delta0 is the "drift" between the input frame (next_picture) and where it would fall in the output. delta = delta0 + duration; /* by default, we output a single frame */ nb0_frames = 0; // tracks the number of times the PREVIOUS frame should be duplicated, mostly for variable framerate (VFR) nb_frames = 1; if (delta0 < 0 && delta > 0 && ost->vsync_method != VSYNC_PASSTHROUGH && ost->vsync_method != VSYNC_DROP) { if (delta0 < -0.6) { av_log(NULL, AV_LOG_VERBOSE, "Past duration %f too large\n", -delta0); } else av_log(NULL, AV_LOG_DEBUG, "Clipping frame in rate conversion by %f\n", -delta0); sync_ipts = ost->sync_opts; duration += delta0; delta0 = 0; } switch (ost->vsync_method) { case VSYNC_VSCFR: if (ost->vsync_frame_number == 0 && delta0 >= 0.5) { av_log(NULL, AV_LOG_DEBUG, "Not duplicating %d initial frames\n", (int)lrintf(delta0)); delta = duration; delta0 = 0; ost->sync_opts = llrint(sync_ipts); } case VSYNC_CFR: // FIXME set to 0.5 after we fix some dts/pts bugs like in avidec.c if (frame_drop_threshold && delta < frame_drop_threshold && ost->vsync_frame_number) { nb_frames = 0; } else if (delta < -1.1) nb_frames = 0; else if (delta > 1.1) { nb_frames = llrintf(delta); if (delta0 > 1.1) nb0_frames = llrintf(delta0 - 0.6); } next_picture->duration = 1; break; case VSYNC_VFR: if (delta <= -0.6) nb_frames = 0; else if (delta > 0.6) ost->sync_opts = llrint(sync_ipts); next_picture->duration = duration; break; case VSYNC_DROP: case VSYNC_PASSTHROUGH: next_picture->duration = duration; ost->sync_opts = llrint(sync_ipts); break; default: av_assert0(0); } } /* * 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. */ nb_frames = FFMIN(nb_frames, ost->max_frames - ost->vsync_frame_number); nb0_frames = FFMIN(nb0_frames, nb_frames); memmove(ost->last_nb0_frames + 1, ost->last_nb0_frames, sizeof(ost->last_nb0_frames[0]) * (FF_ARRAY_ELEMS(ost->last_nb0_frames) - 1)); ost->last_nb0_frames[0] = nb0_frames; if (nb0_frames == 0 && ost->last_dropped) { nb_frames_drop++; av_log(NULL, AV_LOG_VERBOSE, "*** dropping frame %"PRId64" from stream %d at ts %"PRId64"\n", ost->vsync_frame_number, ost->st->index, ost->last_frame->pts); } if (nb_frames > (nb0_frames && ost->last_dropped) + (nb_frames > nb0_frames)) { if (nb_frames > dts_error_threshold * 30) { av_log(NULL, AV_LOG_ERROR, "%"PRId64" frame duplication too large, skipping\n", nb_frames - 1); nb_frames_drop++; return; } nb_frames_dup += nb_frames - (nb0_frames && ost->last_dropped) - (nb_frames > nb0_frames); av_log(NULL, AV_LOG_VERBOSE, "*** %"PRId64" dup!\n", nb_frames - 1); if (nb_frames_dup > dup_warning) { av_log(NULL, AV_LOG_WARNING, "More than %"PRIu64" frames duplicated\n", dup_warning); dup_warning *= 10; } } ost->last_dropped = nb_frames == nb0_frames && next_picture; ost->dropped_keyframe = ost->last_dropped && next_picture && next_picture->key_frame; /* duplicates frame if needed */ for (i = 0; i < nb_frames; i++) { AVFrame *in_picture; int forced_keyframe = 0; double pts_time; if (i < nb0_frames && ost->last_frame->buf[0]) { in_picture = ost->last_frame; } else in_picture = next_picture; if (!in_picture) return; in_picture->pts = ost->sync_opts; if (!check_recording_time(ost)) return; in_picture->quality = enc->global_quality; in_picture->pict_type = 0; if (ost->forced_kf_ref_pts == AV_NOPTS_VALUE && in_picture->pts != AV_NOPTS_VALUE) ost->forced_kf_ref_pts = in_picture->pts; pts_time = in_picture->pts != AV_NOPTS_VALUE ? (in_picture->pts - ost->forced_kf_ref_pts) * av_q2d(enc->time_base) : NAN; if (ost->forced_kf_index < ost->forced_kf_count && in_picture->pts >= ost->forced_kf_pts[ost->forced_kf_index]) { ost->forced_kf_index++; forced_keyframe = 1; } else if (ost->forced_keyframes_pexpr) { double res; ost->forced_keyframes_expr_const_values[FKF_T] = pts_time; res = av_expr_eval(ost->forced_keyframes_pexpr, ost->forced_keyframes_expr_const_values, NULL); ff_dlog(NULL, "force_key_frame: n:%f n_forced:%f prev_forced_n:%f t:%f prev_forced_t:%f -> res:%f\n", ost->forced_keyframes_expr_const_values[FKF_N], ost->forced_keyframes_expr_const_values[FKF_N_FORCED], ost->forced_keyframes_expr_const_values[FKF_PREV_FORCED_N], ost->forced_keyframes_expr_const_values[FKF_T], ost->forced_keyframes_expr_const_values[FKF_PREV_FORCED_T], res); if (res) { forced_keyframe = 1; ost->forced_keyframes_expr_const_values[FKF_PREV_FORCED_N] = ost->forced_keyframes_expr_const_values[FKF_N]; ost->forced_keyframes_expr_const_values[FKF_PREV_FORCED_T] = ost->forced_keyframes_expr_const_values[FKF_T]; ost->forced_keyframes_expr_const_values[FKF_N_FORCED] += 1; } ost->forced_keyframes_expr_const_values[FKF_N] += 1; } else if ( ost->forced_keyframes && !strncmp(ost->forced_keyframes, "source", 6) && in_picture->key_frame==1 && !i) { forced_keyframe = 1; } else if ( ost->forced_keyframes && !strncmp(ost->forced_keyframes, "source_no_drop", 14) && !i) { forced_keyframe = (in_picture->key_frame == 1) || ost->dropped_keyframe; ost->dropped_keyframe = 0; } if (forced_keyframe) { in_picture->pict_type = AV_PICTURE_TYPE_I; av_log(NULL, AV_LOG_DEBUG, "Forced keyframe at time %f\n", pts_time); } ret = submit_encode_frame(of, ost, in_picture); if (ret < 0 && ret != AVERROR_EOF) exit_program(1); ost->sync_opts++; ost->vsync_frame_number++; } av_frame_unref(ost->last_frame); if (next_picture) av_frame_move_ref(ost->last_frame, next_picture); } /** * Get and encode new output from any of the filtergraphs, without causing * activity. * * @return 0 for success, <0 for severe errors */ static int reap_filters(int flush) { AVFrame *filtered_frame = NULL; int i; /* Reap all buffers present in the buffer sinks */ for (i = 0; i < nb_output_streams; i++) { OutputStream *ost = output_streams[i]; OutputFile *of = output_files[ost->file_index]; AVFilterContext *filter; AVCodecContext *enc = ost->enc_ctx; int ret = 0; if (!ost->filter || !ost->filter->graph->graph) continue; filter = ost->filter->filter; /* * Unlike video, with audio the audio frame size matters. * Currently we are fully reliant on the lavfi filter chain to * do the buffering deed for us, and thus the frame size parameter * needs to be set accordingly. Where does one get the required * frame size? From the initialized AVCodecContext of an audio * encoder. Thus, if we have gotten to an audio stream, initialize * the encoder earlier than receiving the first AVFrame. */ if (av_buffersink_get_type(filter) == AVMEDIA_TYPE_AUDIO) init_output_stream_wrapper(ost, NULL, 1); filtered_frame = ost->filtered_frame; while (1) { ret = av_buffersink_get_frame_flags(filter, filtered_frame, AV_BUFFERSINK_FLAG_NO_REQUEST); if (ret < 0) { if (ret != AVERROR(EAGAIN) && ret != AVERROR_EOF) { av_log(NULL, AV_LOG_WARNING, "Error in av_buffersink_get_frame_flags(): %s\n", av_err2str(ret)); } else if (flush && ret == AVERROR_EOF) { if (av_buffersink_get_type(filter) == AVMEDIA_TYPE_VIDEO) do_video_out(of, ost, NULL); } break; } if (ost->finished) { av_frame_unref(filtered_frame); continue; } if (filtered_frame->pts != AV_NOPTS_VALUE) { AVRational tb = av_buffersink_get_time_base(filter); ost->last_filter_pts = av_rescale_q(filtered_frame->pts, tb, AV_TIME_BASE_Q); } switch (av_buffersink_get_type(filter)) { case AVMEDIA_TYPE_VIDEO: if (!ost->frame_aspect_ratio.num) enc->sample_aspect_ratio = filtered_frame->sample_aspect_ratio; do_video_out(of, ost, filtered_frame); break; case AVMEDIA_TYPE_AUDIO: if (!(enc->codec->capabilities & AV_CODEC_CAP_PARAM_CHANGE) && enc->ch_layout.nb_channels != filtered_frame->ch_layout.nb_channels) { av_log(NULL, AV_LOG_ERROR, "Audio filter graph output is not normalized and encoder does not support parameter changes\n"); break; } do_audio_out(of, ost, filtered_frame); break; default: // TODO support subtitle filters av_assert0(0); } av_frame_unref(filtered_frame); } } return 0; } static void print_final_stats(int64_t total_size) { uint64_t video_size = 0, audio_size = 0, extra_size = 0, other_size = 0; uint64_t subtitle_size = 0; uint64_t data_size = 0; float percent = -1.0; int i, j; int pass1_used = 1; for (i = 0; i < nb_output_streams; i++) { OutputStream *ost = output_streams[i]; AVCodecParameters *par = ost->st->codecpar; switch (par->codec_type) { case AVMEDIA_TYPE_VIDEO: video_size += ost->data_size; break; case AVMEDIA_TYPE_AUDIO: audio_size += ost->data_size; break; case AVMEDIA_TYPE_SUBTITLE: subtitle_size += ost->data_size; break; default: other_size += ost->data_size; break; } extra_size += par->extradata_size; data_size += ost->data_size; if (ost->enc_ctx && (ost->enc_ctx->flags & (AV_CODEC_FLAG_PASS1 | AV_CODEC_FLAG_PASS2)) != AV_CODEC_FLAG_PASS1) pass1_used = 0; } if (data_size && total_size>0 && total_size >= data_size) percent = 100.0 * (total_size - data_size) / data_size; av_log(NULL, AV_LOG_INFO, "video:%1.0fkB audio:%1.0fkB subtitle:%1.0fkB other streams:%1.0fkB global headers:%1.0fkB muxing overhead: ", video_size / 1024.0, audio_size / 1024.0, subtitle_size / 1024.0, other_size / 1024.0, extra_size / 1024.0); if (percent >= 0.0) av_log(NULL, AV_LOG_INFO, "%f%%", percent); else av_log(NULL, AV_LOG_INFO, "unknown"); av_log(NULL, AV_LOG_INFO, "\n"); /* print verbose per-stream stats */ for (i = 0; i < nb_input_files; i++) { InputFile *f = input_files[i]; uint64_t total_packets = 0, total_size = 0; av_log(NULL, AV_LOG_VERBOSE, "Input file #%d (%s):\n", i, f->ctx->url); for (j = 0; j < f->nb_streams; j++) { InputStream *ist = input_streams[f->ist_index + j]; enum AVMediaType type = ist->st->codecpar->codec_type; total_size += ist->data_size; total_packets += ist->nb_packets; av_log(NULL, AV_LOG_VERBOSE, " Input stream #%d:%d (%s): ", i, j, av_get_media_type_string(type)); av_log(NULL, AV_LOG_VERBOSE, "%"PRIu64" packets read (%"PRIu64" bytes); ", ist->nb_packets, ist->data_size); if (ist->decoding_needed) { av_log(NULL, AV_LOG_VERBOSE, "%"PRIu64" frames decoded", ist->frames_decoded); if (type == AVMEDIA_TYPE_AUDIO) av_log(NULL, AV_LOG_VERBOSE, " (%"PRIu64" samples)", ist->samples_decoded); av_log(NULL, AV_LOG_VERBOSE, "; "); } av_log(NULL, AV_LOG_VERBOSE, "\n"); } av_log(NULL, AV_LOG_VERBOSE, " Total: %"PRIu64" packets (%"PRIu64" bytes) demuxed\n", total_packets, total_size); } for (i = 0; i < nb_output_files; i++) { OutputFile *of = output_files[i]; uint64_t total_packets = 0, total_size = 0; av_log(NULL, AV_LOG_VERBOSE, "Output file #%d (%s):\n", i, of->url); for (j = 0; j < of->nb_streams; j++) { OutputStream *ost = output_streams[of->ost_index + j]; enum AVMediaType type = ost->st->codecpar->codec_type; total_size += ost->data_size; total_packets += atomic_load(&ost->packets_written); av_log(NULL, AV_LOG_VERBOSE, " Output stream #%d:%d (%s): ", i, j, av_get_media_type_string(type)); if (ost->enc_ctx) { av_log(NULL, AV_LOG_VERBOSE, "%"PRIu64" frames encoded", ost->frames_encoded); if (type == AVMEDIA_TYPE_AUDIO) av_log(NULL, AV_LOG_VERBOSE, " (%"PRIu64" samples)", ost->samples_encoded); av_log(NULL, AV_LOG_VERBOSE, "; "); } av_log(NULL, AV_LOG_VERBOSE, "%"PRIu64" packets muxed (%"PRIu64" bytes); ", atomic_load(&ost->packets_written), ost->data_size); av_log(NULL, AV_LOG_VERBOSE, "\n"); } av_log(NULL, AV_LOG_VERBOSE, " Total: %"PRIu64" packets (%"PRIu64" bytes) muxed\n", total_packets, total_size); } if(video_size + data_size + audio_size + subtitle_size + extra_size == 0){ av_log(NULL, AV_LOG_WARNING, "Output file is empty, nothing was encoded "); if (pass1_used) { av_log(NULL, AV_LOG_WARNING, "\n"); } else { av_log(NULL, AV_LOG_WARNING, "(check -ss / -t / -frames parameters if used)\n"); } } } static void print_report(int is_last_report, int64_t timer_start, int64_t cur_time) { AVBPrint buf, buf_script; int64_t total_size = of_filesize(output_files[0]); int vid, i; double bitrate; double speed; int64_t pts = INT64_MIN + 1; static int64_t last_time = -1; static int first_report = 1; static int qp_histogram[52]; int hours, mins, secs, us; const char *hours_sign; int ret; float t; if (!print_stats && !is_last_report && !progress_avio) return; if (!is_last_report) { if (last_time == -1) { last_time = cur_time; } if (((cur_time - last_time) < stats_period && !first_report) || (first_report && nb_output_dumped < nb_output_files)) return; last_time = cur_time; } t = (cur_time-timer_start) / 1000000.0; vid = 0; av_bprint_init(&buf, 0, AV_BPRINT_SIZE_AUTOMATIC); av_bprint_init(&buf_script, 0, AV_BPRINT_SIZE_AUTOMATIC); for (i = 0; i < nb_output_streams; i++) { OutputStream * const ost = output_streams[i]; const AVCodecContext * const enc = ost->enc_ctx; const float q = enc ? ost->quality / (float) FF_QP2LAMBDA : -1; if (vid && ost->st->codecpar->codec_type == AVMEDIA_TYPE_VIDEO) { av_bprintf(&buf, "q=%2.1f ", q); av_bprintf(&buf_script, "stream_%d_%d_q=%.1f\n", ost->file_index, ost->index, q); } if (!vid && ost->st->codecpar->codec_type == AVMEDIA_TYPE_VIDEO) { float fps; uint64_t frame_number = atomic_load(&ost->packets_written); fps = t > 1 ? frame_number / t : 0; av_bprintf(&buf, "frame=%5"PRId64" fps=%3.*f q=%3.1f ", frame_number, fps < 9.95, fps, q); av_bprintf(&buf_script, "frame=%"PRId64"\n", frame_number); av_bprintf(&buf_script, "fps=%.2f\n", fps); av_bprintf(&buf_script, "stream_%d_%d_q=%.1f\n", ost->file_index, ost->index, q); if (is_last_report) av_bprintf(&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++) av_bprintf(&buf, "%X", av_log2(qp_histogram[j] + 1)); } if (enc && (enc->flags & AV_CODEC_FLAG_PSNR) && (ost->pict_type != AV_PICTURE_TYPE_NONE || is_last_report)) { int j; double error, error_sum = 0; double scale, scale_sum = 0; double p; char type[3] = { 'Y','U','V' }; av_bprintf(&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 = ost->error[j]; scale = enc->width * enc->height * 255.0 * 255.0; } if (j) scale /= 4; error_sum += error; scale_sum += scale; p = psnr(error / scale); av_bprintf(&buf, "%c:%2.2f ", type[j], p); av_bprintf(&buf_script, "stream_%d_%d_psnr_%c=%2.2f\n", ost->file_index, ost->index, type[j] | 32, p); } p = psnr(error_sum / scale_sum); av_bprintf(&buf, "*:%2.2f ", psnr(error_sum / scale_sum)); av_bprintf(&buf_script, "stream_%d_%d_psnr_all=%2.2f\n", ost->file_index, ost->index, p); } vid = 1; } /* compute min output value */ if (ost->last_mux_dts != AV_NOPTS_VALUE) { pts = FFMAX(pts, ost->last_mux_dts); if (copy_ts) { if (copy_ts_first_pts == AV_NOPTS_VALUE && pts > 1) copy_ts_first_pts = pts; if (copy_ts_first_pts != AV_NOPTS_VALUE) pts -= copy_ts_first_pts; } } if (is_last_report) nb_frames_drop += ost->last_dropped; } secs = FFABS(pts) / AV_TIME_BASE; us = FFABS(pts) % AV_TIME_BASE; mins = secs / 60; secs %= 60; hours = mins / 60; mins %= 60; hours_sign = (pts < 0) ? "-" : ""; bitrate = pts && total_size >= 0 ? total_size * 8 / (pts / 1000.0) : -1; speed = t != 0.0 ? (double)pts / AV_TIME_BASE / t : -1; if (total_size < 0) av_bprintf(&buf, "size=N/A time="); else av_bprintf(&buf, "size=%8.0fkB time=", total_size / 1024.0); if (pts == AV_NOPTS_VALUE) { av_bprintf(&buf, "N/A "); } else { av_bprintf(&buf, "%s%02d:%02d:%02d.%02d ", hours_sign, hours, mins, secs, (100 * us) / AV_TIME_BASE); } if (bitrate < 0) { av_bprintf(&buf, "bitrate=N/A"); av_bprintf(&buf_script, "bitrate=N/A\n"); }else{ av_bprintf(&buf, "bitrate=%6.1fkbits/s", bitrate); av_bprintf(&buf_script, "bitrate=%6.1fkbits/s\n", bitrate); } if (total_size < 0) av_bprintf(&buf_script, "total_size=N/A\n"); else av_bprintf(&buf_script, "total_size=%"PRId64"\n", total_size); if (pts == AV_NOPTS_VALUE) { av_bprintf(&buf_script, "out_time_us=N/A\n"); av_bprintf(&buf_script, "out_time_ms=N/A\n"); av_bprintf(&buf_script, "out_time=N/A\n"); } else { av_bprintf(&buf_script, "out_time_us=%"PRId64"\n", pts); av_bprintf(&buf_script, "out_time_ms=%"PRId64"\n", pts); av_bprintf(&buf_script, "out_time=%s%02d:%02d:%02d.%06d\n", hours_sign, hours, mins, secs, us); } if (nb_frames_dup || nb_frames_drop) av_bprintf(&buf, " dup=%"PRId64" drop=%"PRId64, nb_frames_dup, nb_frames_drop); av_bprintf(&buf_script, "dup_frames=%"PRId64"\n", nb_frames_dup); av_bprintf(&buf_script, "drop_frames=%"PRId64"\n", nb_frames_drop); if (speed < 0) { av_bprintf(&buf, " speed=N/A"); av_bprintf(&buf_script, "speed=N/A\n"); } else { av_bprintf(&buf, " speed=%4.3gx", speed); av_bprintf(&buf_script, "speed=%4.3gx\n", speed); } if (print_stats || is_last_report) { const char end = is_last_report ? '\n' : '\r'; if (print_stats==1 && AV_LOG_INFO > av_log_get_level()) { fprintf(stderr, "%s %c", buf.str, end); } else av_log(NULL, AV_LOG_INFO, "%s %c", buf.str, end); fflush(stderr); } av_bprint_finalize(&buf, NULL); if (progress_avio) { av_bprintf(&buf_script, "progress=%s\n", is_last_report ? "end" : "continue"); avio_write(progress_avio, buf_script.str, FFMIN(buf_script.len, buf_script.size - 1)); avio_flush(progress_avio); av_bprint_finalize(&buf_script, NULL); if (is_last_report) { if ((ret = avio_closep(&progress_avio)) < 0) av_log(NULL, AV_LOG_ERROR, "Error closing progress log, loss of information possible: %s\n", av_err2str(ret)); } } first_report = 0; if (is_last_report) print_final_stats(total_size); } static int ifilter_parameters_from_codecpar(InputFilter *ifilter, AVCodecParameters *par) { int ret; // We never got any input. Set a fake format, which will // come from libavformat. ifilter->format = par->format; ifilter->sample_rate = par->sample_rate; ifilter->width = par->width; ifilter->height = par->height; ifilter->sample_aspect_ratio = par->sample_aspect_ratio; ret = av_channel_layout_copy(&ifilter->ch_layout, &par->ch_layout); if (ret < 0) return ret; return 0; } static void flush_encoders(void) { int i, ret; for (i = 0; i < nb_output_streams; i++) { OutputStream *ost = output_streams[i]; AVCodecContext *enc = ost->enc_ctx; OutputFile *of = output_files[ost->file_index]; if (!enc) continue; // Try to enable encoding with no input frames. // Maybe we should just let encoding fail instead. if (!ost->initialized) { FilterGraph *fg = ost->filter->graph; av_log(NULL, AV_LOG_WARNING, "Finishing stream %d:%d without any data written to it.\n", ost->file_index, ost->st->index); if (ost->filter && !fg->graph) { int x; for (x = 0; x < fg->nb_inputs; x++) { InputFilter *ifilter = fg->inputs[x]; if (ifilter->format < 0 && ifilter_parameters_from_codecpar(ifilter, ifilter->ist->st->codecpar) < 0) { av_log(NULL, AV_LOG_ERROR, "Error copying paramerets from input stream\n"); exit_program(1); } } if (!ifilter_has_all_input_formats(fg)) continue; ret = configure_filtergraph(fg); if (ret < 0) { av_log(NULL, AV_LOG_ERROR, "Error configuring filter graph\n"); exit_program(1); } output_packet(of, ost->pkt, ost, 1); } init_output_stream_wrapper(ost, NULL, 1); } if (enc->codec_type != AVMEDIA_TYPE_VIDEO && enc->codec_type != AVMEDIA_TYPE_AUDIO) continue; ret = submit_encode_frame(of, ost, NULL); if (ret != AVERROR_EOF) exit_program(1); } } /* * 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 (ost->finished & MUXER_FINISHED) return 0; if (of->start_time != AV_NOPTS_VALUE && ist->pts < of->start_time) return 0; return 1; } static void do_streamcopy(InputStream *ist, OutputStream *ost, const AVPacket *pkt) { OutputFile *of = output_files[ost->file_index]; InputFile *f = input_files [ist->file_index]; int64_t start_time = (of->start_time == AV_NOPTS_VALUE) ? 0 : of->start_time; int64_t ost_tb_start_time = av_rescale_q(start_time, AV_TIME_BASE_Q, ost->mux_timebase); AVPacket *opkt = ost->pkt; av_packet_unref(opkt); // EOF: flush output bitstream filters. if (!pkt) { output_packet(of, opkt, ost, 1); return; } if (!ost->streamcopy_started && !(pkt->flags & AV_PKT_FLAG_KEY) && !ost->copy_initial_nonkeyframes) return; if (!ost->streamcopy_started && !ost->copy_prior_start) { int64_t comp_start = start_time; if (copy_ts && f->start_time != AV_NOPTS_VALUE) comp_start = FFMAX(start_time, f->start_time + f->ts_offset); if (pkt->pts == AV_NOPTS_VALUE ? ist->pts < comp_start : pkt->pts < av_rescale_q(comp_start, AV_TIME_BASE_Q, ist->st->time_base)) return; } if (of->recording_time != INT64_MAX && ist->pts >= of->recording_time + start_time) { close_output_stream(ost); return; } if (f->recording_time != INT64_MAX) { start_time = 0; if (copy_ts) { start_time += f->start_time != AV_NOPTS_VALUE ? f->start_time : 0; start_time += start_at_zero ? 0 : f->ctx->start_time; } if (ist->pts >= f->recording_time + start_time) { close_output_stream(ost); return; } } if (av_packet_ref(opkt, pkt) < 0) exit_program(1); if (pkt->pts != AV_NOPTS_VALUE) opkt->pts = av_rescale_q(pkt->pts, ist->st->time_base, ost->mux_timebase) - ost_tb_start_time; if (pkt->dts == AV_NOPTS_VALUE) { opkt->dts = av_rescale_q(ist->dts, AV_TIME_BASE_Q, ost->mux_timebase); } else if (ost->st->codecpar->codec_type == AVMEDIA_TYPE_AUDIO) { int duration = av_get_audio_frame_duration2(ist->st->codecpar, pkt->size); if(!duration) duration = ist->st->codecpar->frame_size; opkt->dts = av_rescale_delta(ist->st->time_base, pkt->dts, (AVRational){1, ist->st->codecpar->sample_rate}, duration, &ist->filter_in_rescale_delta_last, ost->mux_timebase); /* dts will be set immediately afterwards to what pts is now */ opkt->pts = opkt->dts - ost_tb_start_time; } else opkt->dts = av_rescale_q(pkt->dts, ist->st->time_base, ost->mux_timebase); opkt->dts -= ost_tb_start_time; opkt->duration = av_rescale_q(pkt->duration, ist->st->time_base, ost->mux_timebase); ost->sync_opts += opkt->duration; output_packet(of, opkt, ost, 0); ost->streamcopy_started = 1; } static void check_decode_result(InputStream *ist, int *got_output, int ret) { if (*got_output || ret<0) decode_error_stat[ret<0] ++; if (ret < 0 && exit_on_error) exit_program(1); if (*got_output && ist) { if (ist->decoded_frame->decode_error_flags || (ist->decoded_frame->flags & AV_FRAME_FLAG_CORRUPT)) { av_log(NULL, exit_on_error ? AV_LOG_FATAL : AV_LOG_WARNING, "%s: corrupt decoded frame in stream %d\n", input_files[ist->file_index]->ctx->url, ist->st->index); if (exit_on_error) exit_program(1); } } } // Filters can be configured only if the formats of all inputs are known. static int ifilter_has_all_input_formats(FilterGraph *fg) { int i; for (i = 0; i < fg->nb_inputs; i++) { if (fg->inputs[i]->format < 0 && (fg->inputs[i]->type == AVMEDIA_TYPE_AUDIO || fg->inputs[i]->type == AVMEDIA_TYPE_VIDEO)) return 0; } return 1; } static int ifilter_send_frame(InputFilter *ifilter, AVFrame *frame, int keep_reference) { FilterGraph *fg = ifilter->graph; AVFrameSideData *sd; int need_reinit, ret; int buffersrc_flags = AV_BUFFERSRC_FLAG_PUSH; if (keep_reference) buffersrc_flags |= AV_BUFFERSRC_FLAG_KEEP_REF; /* determine if the parameters for this input changed */ need_reinit = ifilter->format != frame->format; switch (ifilter->ist->st->codecpar->codec_type) { case AVMEDIA_TYPE_AUDIO: need_reinit |= ifilter->sample_rate != frame->sample_rate || av_channel_layout_compare(&ifilter->ch_layout, &frame->ch_layout); break; case AVMEDIA_TYPE_VIDEO: need_reinit |= ifilter->width != frame->width || ifilter->height != frame->height; break; } if (!ifilter->ist->reinit_filters && fg->graph) need_reinit = 0; if (!!ifilter->hw_frames_ctx != !!frame->hw_frames_ctx || (ifilter->hw_frames_ctx && ifilter->hw_frames_ctx->data != frame->hw_frames_ctx->data)) need_reinit = 1; if (sd = av_frame_get_side_data(frame, AV_FRAME_DATA_DISPLAYMATRIX)) { if (!ifilter->displaymatrix || memcmp(sd->data, ifilter->displaymatrix, sizeof(int32_t) * 9)) need_reinit = 1; } else if (ifilter->displaymatrix) need_reinit = 1; if (need_reinit) { ret = ifilter_parameters_from_frame(ifilter, frame); if (ret < 0) return ret; } /* (re)init the graph if possible, otherwise buffer the frame and return */ if (need_reinit || !fg->graph) { if (!ifilter_has_all_input_formats(fg)) { AVFrame *tmp = av_frame_clone(frame); if (!tmp) return AVERROR(ENOMEM); ret = av_fifo_write(ifilter->frame_queue, &tmp, 1); if (ret < 0) av_frame_free(&tmp); return ret; } ret = reap_filters(1); if (ret < 0 && ret != AVERROR_EOF) { av_log(NULL, AV_LOG_ERROR, "Error while filtering: %s\n", av_err2str(ret)); return ret; } ret = configure_filtergraph(fg); if (ret < 0) { av_log(NULL, AV_LOG_ERROR, "Error reinitializing filters!\n"); return ret; } } ret = av_buffersrc_add_frame_flags(ifilter->filter, frame, buffersrc_flags); if (ret < 0) { if (ret != AVERROR_EOF) av_log(NULL, AV_LOG_ERROR, "Error while filtering: %s\n", av_err2str(ret)); return ret; } return 0; } static int ifilter_send_eof(InputFilter *ifilter, int64_t pts) { int ret; ifilter->eof = 1; if (ifilter->filter) { ret = av_buffersrc_close(ifilter->filter, pts, AV_BUFFERSRC_FLAG_PUSH); if (ret < 0) return ret; } else { // the filtergraph was never configured if (ifilter->format < 0) { ret = ifilter_parameters_from_codecpar(ifilter, ifilter->ist->st->codecpar); if (ret < 0) return ret; } if (ifilter->format < 0 && (ifilter->type == AVMEDIA_TYPE_AUDIO || ifilter->type == AVMEDIA_TYPE_VIDEO)) { av_log(NULL, AV_LOG_ERROR, "Cannot determine format of input stream %d:%d after EOF\n", ifilter->ist->file_index, ifilter->ist->st->index); return AVERROR_INVALIDDATA; } } return 0; } // This does not quite work like avcodec_decode_audio4/avcodec_decode_video2. // There is the following difference: if you got a frame, you must call // it again with pkt=NULL. pkt==NULL is treated differently from pkt->size==0 // (pkt==NULL means get more output, pkt->size==0 is a flush/drain packet) static int decode(AVCodecContext *avctx, AVFrame *frame, int *got_frame, AVPacket *pkt) { int ret; *got_frame = 0; if (pkt) { avctx->reordered_opaque = (int64_t)pkt->opaque; ret = avcodec_send_packet(avctx, pkt); // In particular, we don't expect AVERROR(EAGAIN), because we read all // decoded frames with avcodec_receive_frame() until done. if (ret < 0 && ret != AVERROR_EOF) return ret; } ret = avcodec_receive_frame(avctx, frame); if (ret < 0 && ret != AVERROR(EAGAIN)) return ret; if (ret >= 0) { *got_frame = 1; frame->opaque = (void*)frame->reordered_opaque; } return 0; } static int send_frame_to_filters(InputStream *ist, AVFrame *decoded_frame) { int i, ret; av_assert1(ist->nb_filters > 0); /* ensure ret is initialized */ for (i = 0; i < ist->nb_filters; i++) { ret = ifilter_send_frame(ist->filters[i], decoded_frame, i < ist->nb_filters - 1); if (ret == AVERROR_EOF) ret = 0; /* ignore */ if (ret < 0) { av_log(NULL, AV_LOG_ERROR, "Failed to inject frame into filter network: %s\n", av_err2str(ret)); break; } } return ret; } static int decode_audio(InputStream *ist, AVPacket *pkt, int *got_output, int *decode_failed) { AVFrame *decoded_frame = ist->decoded_frame; AVCodecContext *avctx = ist->dec_ctx; int ret, err = 0; AVRational decoded_frame_tb; update_benchmark(NULL); ret = decode(avctx, decoded_frame, got_output, pkt); update_benchmark("decode_audio %d.%d", ist->file_index, ist->st->index); if (ret < 0) *decode_failed = 1; if (ret >= 0 && avctx->sample_rate <= 0) { av_log(avctx, AV_LOG_ERROR, "Sample rate %d invalid\n", avctx->sample_rate); ret = AVERROR_INVALIDDATA; } if (ret != AVERROR_EOF) check_decode_result(ist, got_output, ret); if (!*got_output || ret < 0) return ret; ist->samples_decoded += decoded_frame->nb_samples; ist->frames_decoded++; /* 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; if (decoded_frame->pts != AV_NOPTS_VALUE) { decoded_frame_tb = ist->st->time_base; } else if (pkt && pkt->pts != AV_NOPTS_VALUE) { decoded_frame->pts = pkt->pts; decoded_frame_tb = ist->st->time_base; }else { decoded_frame->pts = ist->dts; decoded_frame_tb = AV_TIME_BASE_Q; } if (pkt && pkt->duration && ist->prev_pkt_pts != AV_NOPTS_VALUE && pkt->pts != AV_NOPTS_VALUE && pkt->pts - ist->prev_pkt_pts > pkt->duration) ist->filter_in_rescale_delta_last = AV_NOPTS_VALUE; if (pkt) ist->prev_pkt_pts = pkt->pts; if (decoded_frame->pts != AV_NOPTS_VALUE) decoded_frame->pts = av_rescale_delta(decoded_frame_tb, decoded_frame->pts, (AVRational){1, avctx->sample_rate}, decoded_frame->nb_samples, &ist->filter_in_rescale_delta_last, (AVRational){1, avctx->sample_rate}); ist->nb_samples = decoded_frame->nb_samples; err = send_frame_to_filters(ist, decoded_frame); av_frame_unref(decoded_frame); return err < 0 ? err : ret; } static int decode_video(InputStream *ist, AVPacket *pkt, int *got_output, int64_t *duration_pts, int eof, int *decode_failed) { AVFrame *decoded_frame = ist->decoded_frame; int i, ret = 0, err = 0; int64_t best_effort_timestamp; int64_t dts = AV_NOPTS_VALUE; // With fate-indeo3-2, we're getting 0-sized packets before EOF for some // reason. This seems like a semi-critical bug. Don't trigger EOF, and // skip the packet. if (!eof && pkt && pkt->size == 0) return 0; if (ist->dts != AV_NOPTS_VALUE) dts = av_rescale_q(ist->dts, AV_TIME_BASE_Q, ist->st->time_base); if (pkt) { pkt->dts = dts; // ffmpeg.c probably shouldn't do this } // The old code used to set dts on the drain packet, which does not work // with the new API anymore. if (eof) { void *new = av_realloc_array(ist->dts_buffer, ist->nb_dts_buffer + 1, sizeof(ist->dts_buffer[0])); if (!new) return AVERROR(ENOMEM); ist->dts_buffer = new; ist->dts_buffer[ist->nb_dts_buffer++] = dts; } update_benchmark(NULL); ret = decode(ist->dec_ctx, decoded_frame, got_output, pkt); update_benchmark("decode_video %d.%d", ist->file_index, ist->st->index); if (ret < 0) *decode_failed = 1; // The following line may be required in some cases where there is no parser // or the parser does not has_b_frames correctly if (ist->st->codecpar->video_delay < ist->dec_ctx->has_b_frames) { if (ist->dec_ctx->codec_id == AV_CODEC_ID_H264) { ist->st->codecpar->video_delay = ist->dec_ctx->has_b_frames; } else av_log(ist->dec_ctx, AV_LOG_WARNING, "video_delay is larger in decoder than demuxer %d > %d.\n" "If you want to help, upload a sample " "of this file to https://streams.videolan.org/upload/ " "and contact the ffmpeg-devel mailing list. (ffmpeg-devel@ffmpeg.org)\n", ist->dec_ctx->has_b_frames, ist->st->codecpar->video_delay); } if (ret != AVERROR_EOF) check_decode_result(ist, got_output, ret); if (*got_output && ret >= 0) { if (ist->dec_ctx->width != decoded_frame->width || ist->dec_ctx->height != decoded_frame->height || ist->dec_ctx->pix_fmt != decoded_frame->format) { av_log(NULL, AV_LOG_DEBUG, "Frame parameters mismatch context %d,%d,%d != %d,%d,%d\n", decoded_frame->width, decoded_frame->height, decoded_frame->format, ist->dec_ctx->width, ist->dec_ctx->height, ist->dec_ctx->pix_fmt); } } if (!*got_output || ret < 0) return ret; if(ist->top_field_first>=0) decoded_frame->top_field_first = ist->top_field_first; ist->frames_decoded++; if (ist->hwaccel_retrieve_data && decoded_frame->format == ist->hwaccel_pix_fmt) { err = ist->hwaccel_retrieve_data(ist->dec_ctx, decoded_frame); if (err < 0) goto fail; } best_effort_timestamp= decoded_frame->best_effort_timestamp; *duration_pts = decoded_frame->duration; if (ist->framerate.num) best_effort_timestamp = ist->cfr_next_pts++; if (eof && best_effort_timestamp == AV_NOPTS_VALUE && ist->nb_dts_buffer > 0) { best_effort_timestamp = ist->dts_buffer[0]; for (i = 0; i < ist->nb_dts_buffer - 1; i++) ist->dts_buffer[i] = ist->dts_buffer[i + 1]; ist->nb_dts_buffer--; } if(best_effort_timestamp != AV_NOPTS_VALUE) { int64_t ts = av_rescale_q(decoded_frame->pts = best_effort_timestamp, ist->st->time_base, AV_TIME_BASE_Q); if (ts != AV_NOPTS_VALUE) ist->next_pts = ist->pts = ts; } if (debug_ts) { av_log(NULL, AV_LOG_INFO, "decoder -> ist_index:%d type:video " "frame_pts:%s frame_pts_time:%s best_effort_ts:%"PRId64" best_effort_ts_time:%s keyframe:%d frame_type:%d time_base:%d/%d\n", ist->st->index, av_ts2str(decoded_frame->pts), av_ts2timestr(decoded_frame->pts, &ist->st->time_base), best_effort_timestamp, av_ts2timestr(best_effort_timestamp, &ist->st->time_base), decoded_frame->key_frame, decoded_frame->pict_type, ist->st->time_base.num, ist->st->time_base.den); } if (ist->st->sample_aspect_ratio.num) decoded_frame->sample_aspect_ratio = ist->st->sample_aspect_ratio; err = send_frame_to_filters(ist, decoded_frame); fail: av_frame_unref(decoded_frame); return err < 0 ? err : ret; } static int transcode_subtitles(InputStream *ist, AVPacket *pkt, int *got_output, int *decode_failed) { AVSubtitle subtitle; int free_sub = 1; int i, ret = avcodec_decode_subtitle2(ist->dec_ctx, &subtitle, got_output, pkt); check_decode_result(NULL, got_output, ret); if (ret < 0 || !*got_output) { *decode_failed = 1; if (!pkt->size) sub2video_flush(ist); return ret; } if (ist->fix_sub_duration) { int end = 1; if (ist->prev_sub.got_output) { end = av_rescale(subtitle.pts - ist->prev_sub.subtitle.pts, 1000, AV_TIME_BASE); if (end < ist->prev_sub.subtitle.end_display_time) { av_log(NULL, AV_LOG_DEBUG, "Subtitle duration reduced from %"PRId32" to %d%s\n", ist->prev_sub.subtitle.end_display_time, end, end <= 0 ? ", dropping it" : ""); ist->prev_sub.subtitle.end_display_time = end; } } FFSWAP(int, *got_output, ist->prev_sub.got_output); FFSWAP(int, ret, ist->prev_sub.ret); FFSWAP(AVSubtitle, subtitle, ist->prev_sub.subtitle); if (end <= 0) goto out; } if (!*got_output) return ret; if (ist->sub2video.frame) { sub2video_update(ist, INT64_MIN, &subtitle); } else if (ist->nb_filters) { if (!ist->sub2video.sub_queue) ist->sub2video.sub_queue = av_fifo_alloc2(8, sizeof(AVSubtitle), AV_FIFO_FLAG_AUTO_GROW); if (!ist->sub2video.sub_queue) exit_program(1); ret = av_fifo_write(ist->sub2video.sub_queue, &subtitle, 1); if (ret < 0) exit_program(1); free_sub = 0; } if (!subtitle.num_rects) goto out; ist->frames_decoded++; for (i = 0; i < nb_output_streams; i++) { OutputStream *ost = output_streams[i]; if (!check_output_constraints(ist, ost) || !ost->enc_ctx || ost->enc->type != AVMEDIA_TYPE_SUBTITLE) continue; do_subtitle_out(output_files[ost->file_index], ost, &subtitle); } out: if (free_sub) avsubtitle_free(&subtitle); return ret; } static int send_filter_eof(InputStream *ist) { int i, ret; /* TODO keep pts also in stream time base to avoid converting back */ int64_t pts = av_rescale_q_rnd(ist->pts, AV_TIME_BASE_Q, ist->st->time_base, AV_ROUND_NEAR_INF | AV_ROUND_PASS_MINMAX); for (i = 0; i < ist->nb_filters; i++) { ret = ifilter_send_eof(ist->filters[i], pts); if (ret < 0) return ret; } return 0; } /* pkt = NULL means EOF (needed to flush decoder buffers) */ static int process_input_packet(InputStream *ist, const AVPacket *pkt, int no_eof) { const AVCodecParameters *par = ist->st->codecpar; int ret = 0, i; int repeating = 0; int eof_reached = 0; AVPacket *avpkt = ist->pkt; if (!ist->saw_first_ts) { ist->first_dts = ist->dts = ist->st->avg_frame_rate.num ? - ist->dec_ctx->has_b_frames * AV_TIME_BASE / av_q2d(ist->st->avg_frame_rate) : 0; ist->pts = 0; if (pkt && pkt->pts != AV_NOPTS_VALUE && !ist->decoding_needed) { ist->first_dts = ist->dts += av_rescale_q(pkt->pts, ist->st->time_base, AV_TIME_BASE_Q); ist->pts = ist->dts; //unused but better to set it to a value thats not totally wrong } ist->saw_first_ts = 1; } 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) { av_packet_unref(avpkt); ret = av_packet_ref(avpkt, pkt); if (ret < 0) return ret; } if (pkt && pkt->dts != AV_NOPTS_VALUE) { ist->next_dts = ist->dts = av_rescale_q(pkt->dts, ist->st->time_base, AV_TIME_BASE_Q); if (par->codec_type != AVMEDIA_TYPE_VIDEO || !ist->decoding_needed) ist->next_pts = ist->pts = ist->dts; } // while we have more to decode or while the decoder did output something on EOF while (ist->decoding_needed) { int64_t duration_dts = 0; int64_t duration_pts = 0; int got_output = 0; int decode_failed = 0; ist->pts = ist->next_pts; ist->dts = ist->next_dts; switch (par->codec_type) { case AVMEDIA_TYPE_AUDIO: ret = decode_audio (ist, repeating ? NULL : avpkt, &got_output, &decode_failed); av_packet_unref(avpkt); break; case AVMEDIA_TYPE_VIDEO: ret = decode_video (ist, repeating ? NULL : avpkt, &got_output, &duration_pts, !pkt, &decode_failed); if (!repeating || !pkt || got_output) { if (pkt && pkt->duration) { duration_dts = av_rescale_q(pkt->duration, ist->st->time_base, AV_TIME_BASE_Q); } else if(ist->dec_ctx->framerate.num != 0 && ist->dec_ctx->framerate.den != 0) { int ticks= av_stream_get_parser(ist->st) ? av_stream_get_parser(ist->st)->repeat_pict+1 : ist->dec_ctx->ticks_per_frame; duration_dts = ((int64_t)AV_TIME_BASE * ist->dec_ctx->framerate.den * ticks) / ist->dec_ctx->framerate.num / ist->dec_ctx->ticks_per_frame; } if(ist->dts != AV_NOPTS_VALUE && duration_dts) { ist->next_dts += duration_dts; }else ist->next_dts = AV_NOPTS_VALUE; } if (got_output) { if (duration_pts > 0) { ist->next_pts += av_rescale_q(duration_pts, ist->st->time_base, AV_TIME_BASE_Q); } else { ist->next_pts += duration_dts; } } av_packet_unref(avpkt); break; case AVMEDIA_TYPE_SUBTITLE: if (repeating) break; ret = transcode_subtitles(ist, avpkt, &got_output, &decode_failed); if (!pkt && ret >= 0) ret = AVERROR_EOF; av_packet_unref(avpkt); break; default: return -1; } if (ret == AVERROR_EOF) { eof_reached = 1; break; } if (ret < 0) { if (decode_failed) { av_log(NULL, AV_LOG_ERROR, "Error while decoding stream #%d:%d: %s\n", ist->file_index, ist->st->index, av_err2str(ret)); } else { av_log(NULL, AV_LOG_FATAL, "Error while processing the decoded " "data for stream #%d:%d\n", ist->file_index, ist->st->index); } if (!decode_failed || exit_on_error) exit_program(1); break; } if (got_output) ist->got_output = 1; if (!got_output) break; // During draining, we might get multiple output frames in this loop. // ffmpeg.c does not drain the filter chain on configuration changes, // which means if we send multiple frames at once to the filters, and // one of those frames changes configuration, the buffered frames will // be lost. This can upset certain FATE tests. // Decode only 1 frame per call on EOF to appease these FATE tests. // The ideal solution would be to rewrite decoding to use the new // decoding API in a better way. if (!pkt) break; repeating = 1; } /* after flushing, send an EOF on all the filter inputs attached to the stream */ /* except when looping we need to flush but not to send an EOF */ if (!pkt && ist->decoding_needed && eof_reached && !no_eof) { int ret = send_filter_eof(ist); if (ret < 0) { av_log(NULL, AV_LOG_FATAL, "Error marking filters as finished\n"); exit_program(1); } } /* handle stream copy */ if (!ist->decoding_needed && pkt) { ist->dts = ist->next_dts; switch (par->codec_type) { case AVMEDIA_TYPE_AUDIO: av_assert1(pkt->duration >= 0); if (par->sample_rate) { ist->next_dts += ((int64_t)AV_TIME_BASE * par->frame_size) / par->sample_rate; } else { ist->next_dts += av_rescale_q(pkt->duration, ist->st->time_base, AV_TIME_BASE_Q); } break; case AVMEDIA_TYPE_VIDEO: if (ist->framerate.num) { // TODO: Remove work-around for c99-to-c89 issue 7 AVRational time_base_q = AV_TIME_BASE_Q; int64_t next_dts = av_rescale_q(ist->next_dts, time_base_q, av_inv_q(ist->framerate)); ist->next_dts = av_rescale_q(next_dts + 1, av_inv_q(ist->framerate), time_base_q); } else if (pkt->duration) { ist->next_dts += av_rescale_q(pkt->duration, ist->st->time_base, AV_TIME_BASE_Q); } else if(ist->dec_ctx->framerate.num != 0) { int ticks= av_stream_get_parser(ist->st) ? av_stream_get_parser(ist->st)->repeat_pict + 1 : ist->dec_ctx->ticks_per_frame; ist->next_dts += ((int64_t)AV_TIME_BASE * ist->dec_ctx->framerate.den * ticks) / ist->dec_ctx->framerate.num / ist->dec_ctx->ticks_per_frame; } break; } ist->pts = ist->dts; ist->next_pts = ist->next_dts; } else if (!ist->decoding_needed) eof_reached = 1; for (i = 0; i < nb_output_streams; i++) { OutputStream *ost = output_streams[i]; if (!check_output_constraints(ist, ost) || ost->enc_ctx || (!pkt && no_eof)) continue; do_streamcopy(ist, ost, pkt); } return !eof_reached; } static enum AVPixelFormat get_format(AVCodecContext *s, const enum AVPixelFormat *pix_fmts) { InputStream *ist = s->opaque; const enum AVPixelFormat *p; int ret; for (p = pix_fmts; *p != AV_PIX_FMT_NONE; p++) { const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(*p); const AVCodecHWConfig *config = NULL; int i; if (!(desc->flags & AV_PIX_FMT_FLAG_HWACCEL)) break; if (ist->hwaccel_id == HWACCEL_GENERIC || ist->hwaccel_id == HWACCEL_AUTO) { for (i = 0;; i++) { config = avcodec_get_hw_config(s->codec, i); if (!config) break; if (!(config->methods & AV_CODEC_HW_CONFIG_METHOD_HW_DEVICE_CTX)) continue; if (config->pix_fmt == *p) break; } } if (config && config->device_type == ist->hwaccel_device_type) { ret = hwaccel_decode_init(s); if (ret < 0) { if (ist->hwaccel_id == HWACCEL_GENERIC) { av_log(NULL, AV_LOG_FATAL, "%s hwaccel requested for input stream #%d:%d, " "but cannot be initialized.\n", av_hwdevice_get_type_name(config->device_type), ist->file_index, ist->st->index); return AV_PIX_FMT_NONE; } continue; } ist->hwaccel_pix_fmt = *p; break; } } return *p; } static int init_input_stream(int ist_index, char *error, int error_len) { int ret; InputStream *ist = input_streams[ist_index]; if (ist->decoding_needed) { const AVCodec *codec = ist->dec; if (!codec) { snprintf(error, error_len, "Decoder (codec %s) not found for input stream #%d:%d", avcodec_get_name(ist->dec_ctx->codec_id), ist->file_index, ist->st->index); return AVERROR(EINVAL); } ist->dec_ctx->opaque = ist; ist->dec_ctx->get_format = get_format; #if LIBAVCODEC_VERSION_MAJOR < 60 AV_NOWARN_DEPRECATED({ ist->dec_ctx->thread_safe_callbacks = 1; }) #endif if (ist->dec_ctx->codec_id == AV_CODEC_ID_DVB_SUBTITLE && (ist->decoding_needed & DECODING_FOR_OST)) { av_dict_set(&ist->decoder_opts, "compute_edt", "1", AV_DICT_DONT_OVERWRITE); if (ist->decoding_needed & DECODING_FOR_FILTER) av_log(NULL, AV_LOG_WARNING, "Warning using DVB subtitles for filtering and output at the same time is not fully supported, also see -compute_edt [0|1]\n"); } /* Useful for subtitles retiming by lavf (FIXME), skipping samples in * audio, and video decoders such as cuvid or mediacodec */ ist->dec_ctx->pkt_timebase = ist->st->time_base; if (!av_dict_get(ist->decoder_opts, "threads", NULL, 0)) av_dict_set(&ist->decoder_opts, "threads", "auto", 0); /* Attached pics are sparse, therefore we would not want to delay their decoding till EOF. */ if (ist->st->disposition & AV_DISPOSITION_ATTACHED_PIC) av_dict_set(&ist->decoder_opts, "threads", "1", 0); ret = hw_device_setup_for_decode(ist); if (ret < 0) { snprintf(error, error_len, "Device setup failed for " "decoder on input stream #%d:%d : %s", ist->file_index, ist->st->index, av_err2str(ret)); return ret; } if ((ret = avcodec_open2(ist->dec_ctx, codec, &ist->decoder_opts)) < 0) { if (ret == AVERROR_EXPERIMENTAL) abort_codec_experimental(codec, 0); snprintf(error, error_len, "Error while opening decoder for input stream " "#%d:%d : %s", ist->file_index, ist->st->index, av_err2str(ret)); return ret; } assert_avoptions(ist->decoder_opts); } ist->next_pts = AV_NOPTS_VALUE; ist->next_dts = AV_NOPTS_VALUE; return 0; } static InputStream *get_input_stream(OutputStream *ost) { if (ost->source_index >= 0) return input_streams[ost->source_index]; return NULL; } static int compare_int64(const void *a, const void *b) { return FFDIFFSIGN(*(const int64_t *)a, *(const int64_t *)b); } static int init_output_bsfs(OutputStream *ost) { AVBSFContext *ctx = ost->bsf_ctx; int ret; if (!ctx) return 0; ret = avcodec_parameters_copy(ctx->par_in, ost->st->codecpar); if (ret < 0) return ret; ctx->time_base_in = ost->st->time_base; ret = av_bsf_init(ctx); if (ret < 0) { av_log(NULL, AV_LOG_ERROR, "Error initializing bitstream filter: %s\n", ctx->filter->name); return ret; } ret = avcodec_parameters_copy(ost->st->codecpar, ctx->par_out); if (ret < 0) return ret; ost->st->time_base = ctx->time_base_out; return 0; } static int init_output_stream_streamcopy(OutputStream *ost) { OutputFile *of = output_files[ost->file_index]; InputStream *ist = get_input_stream(ost); AVCodecParameters *par = ost->st->codecpar; AVCodecContext *codec_ctx; AVRational sar; int i, ret; uint32_t codec_tag = par->codec_tag; av_assert0(ist && !ost->filter); codec_ctx = avcodec_alloc_context3(NULL); if (!codec_ctx) return AVERROR(ENOMEM); ret = avcodec_parameters_to_context(codec_ctx, ist->st->codecpar); if (ret >= 0) ret = av_opt_set_dict(codec_ctx, &ost->encoder_opts); if (ret < 0) { av_log(NULL, AV_LOG_FATAL, "Error setting up codec context options.\n"); avcodec_free_context(&codec_ctx); return ret; } ret = avcodec_parameters_from_context(par, codec_ctx); avcodec_free_context(&codec_ctx); if (ret < 0) { av_log(NULL, AV_LOG_FATAL, "Error getting reference codec parameters.\n"); return ret; } if (!codec_tag) { unsigned int codec_tag_tmp; if (!of->format->codec_tag || av_codec_get_id (of->format->codec_tag, par->codec_tag) == par->codec_id || !av_codec_get_tag2(of->format->codec_tag, par->codec_id, &codec_tag_tmp)) codec_tag = par->codec_tag; } par->codec_tag = codec_tag; if (!ost->frame_rate.num) ost->frame_rate = ist->framerate; if (ost->frame_rate.num) ost->st->avg_frame_rate = ost->frame_rate; else ost->st->avg_frame_rate = ist->st->avg_frame_rate; ret = avformat_transfer_internal_stream_timing_info(of->format, ost->st, ist->st, copy_tb); if (ret < 0) return ret; // copy timebase while removing common factors if (ost->st->time_base.num <= 0 || ost->st->time_base.den <= 0) { if (ost->frame_rate.num) ost->st->time_base = av_inv_q(ost->frame_rate); else ost->st->time_base = av_add_q(av_stream_get_codec_timebase(ost->st), (AVRational){0, 1}); } // copy estimated duration as a hint to the muxer if (ost->st->duration <= 0 && ist->st->duration > 0) ost->st->duration = av_rescale_q(ist->st->duration, ist->st->time_base, ost->st->time_base); if (ist->st->nb_side_data) { for (i = 0; i < ist->st->nb_side_data; i++) { const AVPacketSideData *sd_src = &ist->st->side_data[i]; uint8_t *dst_data; dst_data = av_stream_new_side_data(ost->st, sd_src->type, sd_src->size); if (!dst_data) return AVERROR(ENOMEM); memcpy(dst_data, sd_src->data, sd_src->size); } } if (ost->rotate_overridden) { uint8_t *sd = av_stream_new_side_data(ost->st, AV_PKT_DATA_DISPLAYMATRIX, sizeof(int32_t) * 9); if (sd) av_display_rotation_set((int32_t *)sd, -ost->rotate_override_value); } switch (par->codec_type) { case AVMEDIA_TYPE_AUDIO: if ((par->block_align == 1 || par->block_align == 1152 || par->block_align == 576) && par->codec_id == AV_CODEC_ID_MP3) par->block_align = 0; if (par->codec_id == AV_CODEC_ID_AC3) par->block_align = 0; break; case AVMEDIA_TYPE_VIDEO: if (ost->frame_aspect_ratio.num) { // overridden by the -aspect cli option sar = av_mul_q(ost->frame_aspect_ratio, (AVRational){ par->height, par->width }); av_log(NULL, AV_LOG_WARNING, "Overriding aspect ratio " "with stream copy may produce invalid files\n"); } else if (ist->st->sample_aspect_ratio.num) sar = ist->st->sample_aspect_ratio; else sar = par->sample_aspect_ratio; ost->st->sample_aspect_ratio = par->sample_aspect_ratio = sar; ost->st->avg_frame_rate = ist->st->avg_frame_rate; ost->st->r_frame_rate = ist->st->r_frame_rate; break; } ost->mux_timebase = ist->st->time_base; return 0; } static void set_encoder_id(OutputFile *of, OutputStream *ost) { uint8_t *encoder_string; int encoder_string_len; if (av_dict_get(ost->st->metadata, "encoder", NULL, 0)) return; encoder_string_len = sizeof(LIBAVCODEC_IDENT) + strlen(ost->enc->name) + 2; encoder_string = av_mallocz(encoder_string_len); if (!encoder_string) exit_program(1); if (!of->bitexact && !ost->bitexact) av_strlcpy(encoder_string, LIBAVCODEC_IDENT " ", encoder_string_len); else av_strlcpy(encoder_string, "Lavc ", encoder_string_len); av_strlcat(encoder_string, ost->enc->name, encoder_string_len); av_dict_set(&ost->st->metadata, "encoder", encoder_string, AV_DICT_DONT_STRDUP_VAL | AV_DICT_DONT_OVERWRITE); } static void parse_forced_key_frames(char *kf, OutputStream *ost, AVCodecContext *avctx) { char *p; int n = 1, i, size, index = 0; int64_t t, *pts; for (p = kf; *p; p++) if (*p == ',') n++; size = n; pts = av_malloc_array(size, sizeof(*pts)); if (!pts) { av_log(NULL, AV_LOG_FATAL, "Could not allocate forced key frames array.\n"); exit_program(1); } p = kf; for (i = 0; i < n; i++) { char *next = strchr(p, ','); if (next) *next++ = 0; if (!memcmp(p, "chapters", 8)) { OutputFile *of = output_files[ost->file_index]; AVChapter * const *ch; unsigned int nb_ch; int j; ch = of_get_chapters(of, &nb_ch); if (nb_ch > INT_MAX - size || !(pts = av_realloc_f(pts, size += nb_ch - 1, sizeof(*pts)))) { av_log(NULL, AV_LOG_FATAL, "Could not allocate forced key frames array.\n"); exit_program(1); } t = p[8] ? parse_time_or_die("force_key_frames", p + 8, 1) : 0; t = av_rescale_q(t, AV_TIME_BASE_Q, avctx->time_base); for (j = 0; j < nb_ch; j++) { const AVChapter *c = ch[j]; av_assert1(index < size); pts[index++] = av_rescale_q(c->start, c->time_base, avctx->time_base) + t; } } else { t = parse_time_or_die("force_key_frames", p, 1); av_assert1(index < size); pts[index++] = av_rescale_q(t, AV_TIME_BASE_Q, avctx->time_base); } p = next; } av_assert0(index == size); qsort(pts, size, sizeof(*pts), compare_int64); ost->forced_kf_count = size; ost->forced_kf_pts = pts; } static void init_encoder_time_base(OutputStream *ost, AVRational default_time_base) { InputStream *ist = get_input_stream(ost); AVCodecContext *enc_ctx = ost->enc_ctx; if (ost->enc_timebase.num > 0) { enc_ctx->time_base = ost->enc_timebase; return; } if (ost->enc_timebase.num < 0) { if (ist) { enc_ctx->time_base = ist->st->time_base; return; } av_log(NULL, AV_LOG_WARNING, "Input stream data for output stream #%d:%d not available, " "using default time base\n", ost->file_index, ost->index); } enc_ctx->time_base = default_time_base; } static int init_output_stream_encode(OutputStream *ost, AVFrame *frame) { InputStream *ist = get_input_stream(ost); AVCodecContext *enc_ctx = ost->enc_ctx; AVCodecContext *dec_ctx = NULL; OutputFile *of = output_files[ost->file_index]; int ret; set_encoder_id(output_files[ost->file_index], ost); if (ist) { dec_ctx = ist->dec_ctx; } if (enc_ctx->codec_type == AVMEDIA_TYPE_VIDEO) { if (!ost->frame_rate.num) ost->frame_rate = av_buffersink_get_frame_rate(ost->filter->filter); if (ist && !ost->frame_rate.num && !ost->max_frame_rate.num) { ost->frame_rate = (AVRational){25, 1}; av_log(NULL, AV_LOG_WARNING, "No information " "about the input framerate is available. Falling " "back to a default value of 25fps for output stream #%d:%d. Use the -r option " "if you want a different framerate.\n", ost->file_index, ost->index); } if (ost->max_frame_rate.num && (av_q2d(ost->frame_rate) > av_q2d(ost->max_frame_rate) || !ost->frame_rate.den)) ost->frame_rate = ost->max_frame_rate; if (ost->enc->supported_framerates && !ost->force_fps) { int idx = av_find_nearest_q_idx(ost->frame_rate, ost->enc->supported_framerates); ost->frame_rate = ost->enc->supported_framerates[idx]; } // reduce frame rate for mpeg4 to be within the spec limits if (enc_ctx->codec_id == AV_CODEC_ID_MPEG4) { av_reduce(&ost->frame_rate.num, &ost->frame_rate.den, ost->frame_rate.num, ost->frame_rate.den, 65535); } } switch (enc_ctx->codec_type) { case AVMEDIA_TYPE_AUDIO: enc_ctx->sample_fmt = av_buffersink_get_format(ost->filter->filter); enc_ctx->sample_rate = av_buffersink_get_sample_rate(ost->filter->filter); ret = av_buffersink_get_ch_layout(ost->filter->filter, &enc_ctx->ch_layout); if (ret < 0) return ret; if (ost->bits_per_raw_sample) enc_ctx->bits_per_raw_sample = ost->bits_per_raw_sample; else if (dec_ctx && ost->filter->graph->is_meta) enc_ctx->bits_per_raw_sample = FFMIN(dec_ctx->bits_per_raw_sample, av_get_bytes_per_sample(enc_ctx->sample_fmt) << 3); init_encoder_time_base(ost, av_make_q(1, enc_ctx->sample_rate)); break; case AVMEDIA_TYPE_VIDEO: init_encoder_time_base(ost, av_inv_q(ost->frame_rate)); if (!(enc_ctx->time_base.num && enc_ctx->time_base.den)) enc_ctx->time_base = av_buffersink_get_time_base(ost->filter->filter); if ( av_q2d(enc_ctx->time_base) < 0.001 && ost->vsync_method != VSYNC_PASSTHROUGH && (ost->vsync_method == VSYNC_CFR || ost->vsync_method == VSYNC_VSCFR || (ost->vsync_method == VSYNC_AUTO && !(of->format->flags & AVFMT_VARIABLE_FPS)))){ av_log(NULL, AV_LOG_WARNING, "Frame rate very high for a muxer not efficiently supporting it.\n" "Please consider specifying a lower framerate, a different muxer or " "setting vsync/fps_mode to vfr\n"); } enc_ctx->width = av_buffersink_get_w(ost->filter->filter); enc_ctx->height = av_buffersink_get_h(ost->filter->filter); enc_ctx->sample_aspect_ratio = ost->st->sample_aspect_ratio = ost->frame_aspect_ratio.num ? // overridden by the -aspect cli option av_mul_q(ost->frame_aspect_ratio, (AVRational){ enc_ctx->height, enc_ctx->width }) : av_buffersink_get_sample_aspect_ratio(ost->filter->filter); enc_ctx->pix_fmt = av_buffersink_get_format(ost->filter->filter); if (ost->bits_per_raw_sample) enc_ctx->bits_per_raw_sample = ost->bits_per_raw_sample; else if (dec_ctx && ost->filter->graph->is_meta) enc_ctx->bits_per_raw_sample = FFMIN(dec_ctx->bits_per_raw_sample, av_pix_fmt_desc_get(enc_ctx->pix_fmt)->comp[0].depth); if (frame) { enc_ctx->color_range = frame->color_range; enc_ctx->color_primaries = frame->color_primaries; enc_ctx->color_trc = frame->color_trc; enc_ctx->colorspace = frame->colorspace; enc_ctx->chroma_sample_location = frame->chroma_location; } enc_ctx->framerate = ost->frame_rate; ost->st->avg_frame_rate = ost->frame_rate; // Field order: autodetection if (frame) { if (enc_ctx->flags & (AV_CODEC_FLAG_INTERLACED_DCT | AV_CODEC_FLAG_INTERLACED_ME) && ost->top_field_first >= 0) frame->top_field_first = !!ost->top_field_first; if (frame->interlaced_frame) { if (enc_ctx->codec->id == AV_CODEC_ID_MJPEG) enc_ctx->field_order = frame->top_field_first ? AV_FIELD_TT:AV_FIELD_BB; else enc_ctx->field_order = frame->top_field_first ? AV_FIELD_TB:AV_FIELD_BT; } else enc_ctx->field_order = AV_FIELD_PROGRESSIVE; } // Field order: override if (ost->top_field_first == 0) { enc_ctx->field_order = AV_FIELD_BB; } else if (ost->top_field_first == 1) { enc_ctx->field_order = AV_FIELD_TT; } if (ost->forced_keyframes) { if (!strncmp(ost->forced_keyframes, "expr:", 5)) { ret = av_expr_parse(&ost->forced_keyframes_pexpr, ost->forced_keyframes+5, forced_keyframes_const_names, NULL, NULL, NULL, NULL, 0, NULL); if (ret < 0) { av_log(NULL, AV_LOG_ERROR, "Invalid force_key_frames expression '%s'\n", ost->forced_keyframes+5); return ret; } ost->forced_keyframes_expr_const_values[FKF_N] = 0; ost->forced_keyframes_expr_const_values[FKF_N_FORCED] = 0; ost->forced_keyframes_expr_const_values[FKF_PREV_FORCED_N] = NAN; ost->forced_keyframes_expr_const_values[FKF_PREV_FORCED_T] = NAN; // Don't parse the 'forced_keyframes' in case of 'keep-source-keyframes', // parse it only for static kf timings } else if(strncmp(ost->forced_keyframes, "source", 6)) { parse_forced_key_frames(ost->forced_keyframes, ost, ost->enc_ctx); } } break; case AVMEDIA_TYPE_SUBTITLE: enc_ctx->time_base = AV_TIME_BASE_Q; if (!enc_ctx->width) { enc_ctx->width = input_streams[ost->source_index]->st->codecpar->width; enc_ctx->height = input_streams[ost->source_index]->st->codecpar->height; } break; case AVMEDIA_TYPE_DATA: break; default: abort(); break; } if (ost->bitexact) enc_ctx->flags |= AV_CODEC_FLAG_BITEXACT; if (ost->sq_idx_encode >= 0) sq_set_tb(of->sq_encode, ost->sq_idx_encode, enc_ctx->time_base); ost->mux_timebase = enc_ctx->time_base; return 0; } static int init_output_stream(OutputStream *ost, AVFrame *frame, char *error, int error_len) { OutputFile *of = output_files[ost->file_index]; int ret = 0; if (ost->enc_ctx) { const AVCodec *codec = ost->enc; AVCodecContext *dec = NULL; InputStream *ist; ret = init_output_stream_encode(ost, frame); if (ret < 0) return ret; if ((ist = get_input_stream(ost))) dec = ist->dec_ctx; if (dec && dec->subtitle_header) { /* ASS code assumes this buffer is null terminated so add extra byte. */ ost->enc_ctx->subtitle_header = av_mallocz(dec->subtitle_header_size + 1); if (!ost->enc_ctx->subtitle_header) return AVERROR(ENOMEM); memcpy(ost->enc_ctx->subtitle_header, dec->subtitle_header, dec->subtitle_header_size); ost->enc_ctx->subtitle_header_size = dec->subtitle_header_size; } if (!av_dict_get(ost->encoder_opts, "threads", NULL, 0)) av_dict_set(&ost->encoder_opts, "threads", "auto", 0); ret = hw_device_setup_for_encode(ost); if (ret < 0) { snprintf(error, error_len, "Device setup failed for " "encoder on output stream #%d:%d : %s", ost->file_index, ost->index, av_err2str(ret)); return ret; } if (ist && ist->dec->type == AVMEDIA_TYPE_SUBTITLE && ost->enc->type == AVMEDIA_TYPE_SUBTITLE) { int input_props = 0, output_props = 0; AVCodecDescriptor const *input_descriptor = avcodec_descriptor_get(dec->codec_id); AVCodecDescriptor const *output_descriptor = avcodec_descriptor_get(ost->enc_ctx->codec_id); if (input_descriptor) input_props = input_descriptor->props & (AV_CODEC_PROP_TEXT_SUB | AV_CODEC_PROP_BITMAP_SUB); if (output_descriptor) output_props = output_descriptor->props & (AV_CODEC_PROP_TEXT_SUB | AV_CODEC_PROP_BITMAP_SUB); if (input_props && output_props && input_props != output_props) { snprintf(error, error_len, "Subtitle encoding currently only possible from text to text " "or bitmap to bitmap"); return AVERROR_INVALIDDATA; } } if ((ret = avcodec_open2(ost->enc_ctx, codec, &ost->encoder_opts)) < 0) { if (ret == AVERROR_EXPERIMENTAL) abort_codec_experimental(codec, 1); snprintf(error, error_len, "Error while opening encoder for output stream #%d:%d - " "maybe incorrect parameters such as bit_rate, rate, width or height", ost->file_index, ost->index); return ret; } if (ost->enc->type == AVMEDIA_TYPE_AUDIO && !(ost->enc->capabilities & AV_CODEC_CAP_VARIABLE_FRAME_SIZE)) av_buffersink_set_frame_size(ost->filter->filter, ost->enc_ctx->frame_size); assert_avoptions(ost->encoder_opts); if (ost->enc_ctx->bit_rate && ost->enc_ctx->bit_rate < 1000 && ost->enc_ctx->codec_id != AV_CODEC_ID_CODEC2 /* don't complain about 700 bit/s modes */) av_log(NULL, AV_LOG_WARNING, "The bitrate parameter is set too low." " It takes bits/s as argument, not kbits/s\n"); ret = avcodec_parameters_from_context(ost->st->codecpar, ost->enc_ctx); if (ret < 0) { av_log(NULL, AV_LOG_FATAL, "Error initializing the output stream codec context.\n"); exit_program(1); } if (ost->enc_ctx->nb_coded_side_data) { int i; for (i = 0; i < ost->enc_ctx->nb_coded_side_data; i++) { const AVPacketSideData *sd_src = &ost->enc_ctx->coded_side_data[i]; uint8_t *dst_data; dst_data = av_stream_new_side_data(ost->st, sd_src->type, sd_src->size); if (!dst_data) return AVERROR(ENOMEM); memcpy(dst_data, sd_src->data, sd_src->size); } } /* * Add global input side data. For now this is naive, and copies it * from the input stream's global side data. All side data should * really be funneled over AVFrame and libavfilter, then added back to * packet side data, and then potentially using the first packet for * global side data. */ if (ist) { int i; for (i = 0; i < ist->st->nb_side_data; i++) { AVPacketSideData *sd = &ist->st->side_data[i]; if (sd->type != AV_PKT_DATA_CPB_PROPERTIES) { uint8_t *dst = av_stream_new_side_data(ost->st, sd->type, sd->size); if (!dst) return AVERROR(ENOMEM); memcpy(dst, sd->data, sd->size); if (ist->autorotate && sd->type == AV_PKT_DATA_DISPLAYMATRIX) av_display_rotation_set((uint32_t *)dst, 0); } } } // copy timebase while removing common factors if (ost->st->time_base.num <= 0 || ost->st->time_base.den <= 0) ost->st->time_base = av_add_q(ost->enc_ctx->time_base, (AVRational){0, 1}); // copy estimated duration as a hint to the muxer if (ost->st->duration <= 0 && ist && ist->st->duration > 0) ost->st->duration = av_rescale_q(ist->st->duration, ist->st->time_base, ost->st->time_base); } else if (ost->source_index >= 0) { ret = init_output_stream_streamcopy(ost); if (ret < 0) return ret; } /* initialize bitstream filters for the output stream * needs to be done here, because the codec id for streamcopy is not * known until now */ ret = init_output_bsfs(ost); if (ret < 0) return ret; if (ost->sq_idx_mux >= 0) sq_set_tb(of->sq_mux, ost->sq_idx_mux, ost->mux_timebase); ost->initialized = 1; ret = of_check_init(output_files[ost->file_index]); if (ret < 0) return ret; return ret; } static int transcode_init(void) { int ret = 0, i, j, k; OutputStream *ost; InputStream *ist; char error[1024] = {0}; for (i = 0; i < nb_filtergraphs; i++) { FilterGraph *fg = filtergraphs[i]; for (j = 0; j < fg->nb_outputs; j++) { OutputFilter *ofilter = fg->outputs[j]; if (!ofilter->ost || ofilter->ost->source_index >= 0) continue; if (fg->nb_inputs != 1) continue; for (k = nb_input_streams-1; k >= 0 ; k--) if (fg->inputs[0]->ist == input_streams[k]) break; ofilter->ost->source_index = k; } } /* init framerate emulation */ for (i = 0; i < nb_input_files; i++) { InputFile *ifile = input_files[i]; if (ifile->readrate || ifile->rate_emu) for (j = 0; j < ifile->nb_streams; j++) input_streams[j + ifile->ist_index]->start = av_gettime_relative(); } /* init input streams */ for (i = 0; i < nb_input_streams; i++) if ((ret = init_input_stream(i, error, sizeof(error))) < 0) goto dump_format; /* * initialize stream copy and subtitle/data streams. * Encoded AVFrame based streams will get initialized as follows: * - when the first AVFrame is received in do_video_out * - just before the first AVFrame is received in either transcode_step * or reap_filters due to us requiring the filter chain buffer sink * to be configured with the correct audio frame size, which is only * known after the encoder is initialized. */ for (i = 0; i < nb_output_streams; i++) { if (output_streams[i]->enc_ctx && (output_streams[i]->st->codecpar->codec_type == AVMEDIA_TYPE_VIDEO || output_streams[i]->st->codecpar->codec_type == AVMEDIA_TYPE_AUDIO)) continue; ret = init_output_stream_wrapper(output_streams[i], NULL, 0); if (ret < 0) goto dump_format; } /* discard unused programs */ for (i = 0; i < nb_input_files; i++) { InputFile *ifile = input_files[i]; for (j = 0; j < ifile->ctx->nb_programs; j++) { AVProgram *p = ifile->ctx->programs[j]; int discard = AVDISCARD_ALL; for (k = 0; k < p->nb_stream_indexes; k++) if (!input_streams[ifile->ist_index + p->stream_index[k]]->discard) { discard = AVDISCARD_DEFAULT; break; } p->discard = discard; } } dump_format: /* dump the stream mapping */ av_log(NULL, AV_LOG_INFO, "Stream mapping:\n"); for (i = 0; i < nb_input_streams; i++) { ist = input_streams[i]; for (j = 0; j < ist->nb_filters; j++) { if (!filtergraph_is_simple(ist->filters[j]->graph)) { av_log(NULL, AV_LOG_INFO, " Stream #%d:%d (%s) -> %s", ist->file_index, ist->st->index, ist->dec ? ist->dec->name : "?", ist->filters[j]->name); if (nb_filtergraphs > 1) av_log(NULL, AV_LOG_INFO, " (graph %d)", ist->filters[j]->graph->index); av_log(NULL, AV_LOG_INFO, "\n"); } } } for (i = 0; i < nb_output_streams; i++) { ost = output_streams[i]; if (ost->attachment_filename) { /* an attached file */ av_log(NULL, AV_LOG_INFO, " File %s -> Stream #%d:%d\n", ost->attachment_filename, ost->file_index, ost->index); continue; } if (ost->filter && !filtergraph_is_simple(ost->filter->graph)) { /* output from a complex graph */ av_log(NULL, AV_LOG_INFO, " %s", ost->filter->name); if (nb_filtergraphs > 1) av_log(NULL, AV_LOG_INFO, " (graph %d)", ost->filter->graph->index); av_log(NULL, AV_LOG_INFO, " -> Stream #%d:%d (%s)\n", ost->file_index, ost->index, ost->enc ? ost->enc->name : "?"); continue; } av_log(NULL, AV_LOG_INFO, " Stream #%d:%d -> #%d:%d", input_streams[ost->source_index]->file_index, input_streams[ost->source_index]->st->index, ost->file_index, ost->index); if (ost->enc_ctx) { const AVCodec *in_codec = input_streams[ost->source_index]->dec; const AVCodec *out_codec = ost->enc; const char *decoder_name = "?"; const char *in_codec_name = "?"; const char *encoder_name = "?"; const char *out_codec_name = "?"; const AVCodecDescriptor *desc; if (in_codec) { decoder_name = in_codec->name; desc = avcodec_descriptor_get(in_codec->id); if (desc) in_codec_name = desc->name; if (!strcmp(decoder_name, in_codec_name)) decoder_name = "native"; } if (out_codec) { encoder_name = out_codec->name; desc = avcodec_descriptor_get(out_codec->id); if (desc) out_codec_name = desc->name; if (!strcmp(encoder_name, out_codec_name)) encoder_name = "native"; } av_log(NULL, AV_LOG_INFO, " (%s (%s) -> %s (%s))", in_codec_name, decoder_name, out_codec_name, encoder_name); } else av_log(NULL, AV_LOG_INFO, " (copy)"); av_log(NULL, AV_LOG_INFO, "\n"); } if (ret) { av_log(NULL, AV_LOG_ERROR, "%s\n", error); return ret; } atomic_store(&transcode_init_done, 1); return 0; } /* Return 1 if there remain streams where more output is wanted, 0 otherwise. */ static int need_output(void) { int i; for (i = 0; i < nb_output_streams; i++) { OutputStream *ost = output_streams[i]; if (ost->finished) continue; return 1; } return 0; } /** * Select the output stream to process. * * @return selected output stream, or NULL if none available */ static OutputStream *choose_output(void) { int i; int64_t opts_min = INT64_MAX; OutputStream *ost_min = NULL; for (i = 0; i < nb_output_streams; i++) { OutputStream *ost = output_streams[i]; int64_t opts; if (ost->filter && ost->last_filter_pts != AV_NOPTS_VALUE) { opts = ost->last_filter_pts; } else { opts = ost->last_mux_dts == AV_NOPTS_VALUE ? INT64_MIN : ost->last_mux_dts; if (ost->last_mux_dts == AV_NOPTS_VALUE) av_log(NULL, AV_LOG_DEBUG, "cur_dts is invalid st:%d (%d) [init:%d i_done:%d finish:%d] (this is harmless if it occurs once at the start per stream)\n", ost->st->index, ost->st->id, ost->initialized, ost->inputs_done, ost->finished); } if (!ost->initialized && !ost->inputs_done) return ost->unavailable ? NULL : ost; if (!ost->finished && opts < opts_min) { opts_min = opts; ost_min = ost->unavailable ? NULL : ost; } } return ost_min; } static void set_tty_echo(int on) { #if HAVE_TERMIOS_H struct termios tty; if (tcgetattr(0, &tty) == 0) { if (on) tty.c_lflag |= ECHO; else tty.c_lflag &= ~ECHO; tcsetattr(0, TCSANOW, &tty); } #endif } static int check_keyboard_interaction(int64_t cur_time) { int i, ret, key; static int64_t last_time; if (received_nb_signals) return AVERROR_EXIT; /* read_key() returns 0 on EOF */ if (cur_time - last_time >= 100000) { key = read_key(); last_time = cur_time; }else key = -1; if (key == 'q') { av_log(NULL, AV_LOG_INFO, "\n\n[q] command received. Exiting.\n\n"); return AVERROR_EXIT; } if (key == '+') av_log_set_level(av_log_get_level()+10); if (key == '-') av_log_set_level(av_log_get_level()-10); if (key == 's') qp_hist ^= 1; if (key == 'c' || key == 'C'){ char buf[4096], target[64], command[256], arg[256] = {0}; double time; int k, n = 0; fprintf(stderr, "\nEnter command: |all