/* * 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 #if HAVE_ISATTY #include #endif #include "libavformat/avformat.h" #include "libavdevice/avdevice.h" #include "libswscale/swscale.h" #include "libswresample/swresample.h" #include "libavutil/opt.h" #include "libavutil/audioconvert.h" #include "libavutil/parseutils.h" #include "libavutil/samplefmt.h" #include "libavutil/colorspace.h" #include "libavutil/fifo.h" #include "libavutil/intreadwrite.h" #include "libavutil/dict.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 "libavformat/os_support.h" #include "libavformat/ffm.h" // not public API # include "libavfilter/avcodec.h" # include "libavfilter/avfilter.h" # include "libavfilter/avfiltergraph.h" # include "libavfilter/buffersrc.h" # include "libavfilter/buffersink.h" #if HAVE_SYS_RESOURCE_H #include #include #elif HAVE_GETPROCESSTIMES #include #endif #if HAVE_GETPROCESSMEMORYINFO #include #include #endif #if HAVE_SYS_SELECT_H #include #endif #if HAVE_TERMIOS_H #include #include #include #include #elif HAVE_KBHIT #include #endif #if HAVE_PTHREADS #include #endif #include #include "cmdutils.h" #include "libavutil/avassert.h" #define VSYNC_AUTO -1 #define VSYNC_PASSTHROUGH 0 #define VSYNC_CFR 1 #define VSYNC_VFR 2 #define VSYNC_DROP 0xff const char program_name[] = "ffmpeg"; const int program_birth_year = 2000; /* select an input stream for an output stream */ typedef struct StreamMap { int disabled; /** 1 is this mapping is disabled by a negative map */ int file_index; int stream_index; int sync_file_index; int sync_stream_index; char *linklabel; /** name of an output link, for mapping lavfi outputs */ } StreamMap; typedef struct { int file_idx, stream_idx, channel_idx; // input int ofile_idx, ostream_idx; // output } AudioChannelMap; static const OptionDef *options; #define MAX_STREAMS 1024 /* arbitrary sanity check value */ static int frame_bits_per_raw_sample = 0; static int video_discard = 0; static int same_quant = 0; static int do_deinterlace = 0; static int intra_dc_precision = 8; static int qp_hist = 0; static int intra_only = 0; static const char *video_codec_name = NULL; static const char *audio_codec_name = NULL; static const char *subtitle_codec_name = NULL; static int file_overwrite = 0; static int no_file_overwrite = 0; static int do_benchmark = 0; static int do_benchmark_all = 0; static int do_hex_dump = 0; static int do_pkt_dump = 0; static int do_psnr = 0; static int do_pass = 0; static const char *pass_logfilename_prefix; static int video_sync_method = VSYNC_AUTO; static int audio_sync_method = 0; static float audio_drift_threshold = 0.1; static int copy_ts = 0; static int copy_tb = -1; static int opt_shortest = 0; static char *vstats_filename; static FILE *vstats_file; static int audio_volume = 256; static int exit_on_error = 0; static int stdin_interaction = 1; static int run_as_daemon = 0; static volatile int received_nb_signals = 0; static int64_t video_size = 0; static int64_t audio_size = 0; static int64_t subtitle_size = 0; static int64_t extra_size = 0; static int nb_frames_dup = 0; static int nb_frames_drop = 0; static int input_sync; static float dts_delta_threshold = 10; static float dts_error_threshold = 3600*30; static int print_stats = 1; static int debug_ts = 0; static int current_time; static AVIOContext *progress_avio = NULL; static uint8_t *subtitle_out; #if HAVE_PTHREADS /* signal to input threads that they should exit; set by the main thread */ static int transcoding_finished; #endif #define DEFAULT_PASS_LOGFILENAME_PREFIX "ffmpeg2pass" typedef struct InputFilter { AVFilterContext *filter; struct InputStream *ist; struct FilterGraph *graph; uint8_t *name; } InputFilter; typedef struct OutputFilter { AVFilterContext *filter; struct OutputStream *ost; struct FilterGraph *graph; uint8_t *name; /* temporary storage until stream maps are processed */ AVFilterInOut *out_tmp; } OutputFilter; typedef struct FilterGraph { int index; const char *graph_desc; AVFilterGraph *graph; InputFilter **inputs; int nb_inputs; OutputFilter **outputs; int nb_outputs; } FilterGraph; typedef struct InputStream { int file_index; AVStream *st; int discard; /* true if stream data should be discarded */ int decoding_needed; /* true if the packets must be decoded in 'raw_fifo' */ AVCodec *dec; AVFrame *decoded_frame; int64_t start; /* time when read started */ /* predicted dts of the next packet read for this stream or (when there are * several frames in a packet) of the next frame in current packet (in AV_TIME_BASE units) */ int64_t next_dts; int64_t dts; ///< dts of the last packet read for this stream (in AV_TIME_BASE units) int64_t next_pts; ///< synthetic pts for the next decode frame (in AV_TIME_BASE units) int64_t pts; ///< current pts of the decoded frame (in AV_TIME_BASE units) int wrap_correction_done; double ts_scale; int is_start; /* is 1 at the start and after a discontinuity */ int saw_first_ts; int showed_multi_packet_warning; AVDictionary *opts; AVRational framerate; /* framerate forced with -r */ int top_field_first; int resample_height; int resample_width; int resample_pix_fmt; int resample_sample_fmt; int resample_sample_rate; int resample_channels; uint64_t resample_channel_layout; struct sub2video { int64_t last_pts; AVFilterBufferRef *ref; int w, h; } sub2video; /* a pool of free buffers for decoded data */ FrameBuffer *buffer_pool; int dr1; /* decoded data from this stream goes into all those filters * currently video and audio only */ InputFilter **filters; int nb_filters; } InputStream; typedef struct InputFile { AVFormatContext *ctx; int eof_reached; /* true if eof reached */ int unavailable; /* true if the file is unavailable (possibly temporarily) */ int ist_index; /* index of first stream in input_streams */ int64_t ts_offset; int nb_streams; /* number of stream that ffmpeg is aware of; may be different from ctx.nb_streams if new streams appear during av_read_frame() */ int nb_streams_warn; /* number of streams that the user was warned of */ int rate_emu; #if HAVE_PTHREADS pthread_t thread; /* thread reading from this file */ int finished; /* the thread has exited */ int joined; /* the thread has been joined */ pthread_mutex_t fifo_lock; /* lock for access to fifo */ pthread_cond_t fifo_cond; /* the main thread will signal on this cond after reading from fifo */ AVFifoBuffer *fifo; /* demuxed packets are stored here; freed by the main thread */ #endif } InputFile; typedef struct OutputStream { int file_index; /* file index */ int index; /* stream index in the output file */ int source_index; /* InputStream index */ AVStream *st; /* stream in the output file */ int encoding_needed; /* true if encoding needed for this stream */ int frame_number; /* input pts and corresponding output pts for A/V sync */ struct InputStream *sync_ist; /* input stream to sync against */ int64_t sync_opts; /* output frame counter, could be changed to some true timestamp */ // FIXME look at frame_number /* pts of the first frame encoded for this stream, used for limiting * recording time */ int64_t first_pts; AVBitStreamFilterContext *bitstream_filters; AVCodec *enc; int64_t max_frames; AVFrame *filtered_frame; /* video only */ AVRational frame_rate; int force_fps; int top_field_first; float frame_aspect_ratio; float last_quality; /* forced key frames */ int64_t *forced_kf_pts; int forced_kf_count; int forced_kf_index; char *forced_keyframes; /* audio only */ int audio_channels_map[SWR_CH_MAX]; /* list of the channels id to pick from the source stream */ int audio_channels_mapped; /* number of channels in audio_channels_map */ FILE *logfile; OutputFilter *filter; char *avfilter; int64_t sws_flags; int64_t swr_dither_method; double swr_dither_scale; AVDictionary *opts; int is_past_recording_time; int unavailable; /* true if the steram is unavailable (possibly temporarily) */ int stream_copy; const char *attachment_filename; int copy_initial_nonkeyframes; int keep_pix_fmt; } OutputStream; #if HAVE_TERMIOS_H /* init terminal so that we can grab keys */ static struct termios oldtty; static int restore_tty; #endif typedef struct OutputFile { AVFormatContext *ctx; AVDictionary *opts; int ost_index; /* index of the first stream in output_streams */ int64_t recording_time; ///< desired length of the resulting file in microseconds == AV_TIME_BASE units int64_t start_time; ///< start time in microseconds == AV_TIME_BASE units uint64_t limit_filesize; /* filesize limit expressed in bytes */ } OutputFile; static InputStream **input_streams = NULL; static int nb_input_streams = 0; static InputFile **input_files = NULL; static int nb_input_files = 0; static OutputStream **output_streams = NULL; static int nb_output_streams = 0; static OutputFile **output_files = NULL; static int nb_output_files = 0; static FilterGraph **filtergraphs; int nb_filtergraphs; typedef struct OptionsContext { /* input/output options */ int64_t start_time; const char *format; SpecifierOpt *codec_names; int nb_codec_names; SpecifierOpt *audio_channels; int nb_audio_channels; SpecifierOpt *audio_sample_rate; int nb_audio_sample_rate; SpecifierOpt *frame_rates; int nb_frame_rates; SpecifierOpt *frame_sizes; int nb_frame_sizes; SpecifierOpt *frame_pix_fmts; int nb_frame_pix_fmts; /* input options */ int64_t input_ts_offset; int rate_emu; SpecifierOpt *ts_scale; int nb_ts_scale; SpecifierOpt *dump_attachment; int nb_dump_attachment; /* output options */ StreamMap *stream_maps; int nb_stream_maps; AudioChannelMap *audio_channel_maps; /* one info entry per -map_channel */ int nb_audio_channel_maps; /* number of (valid) -map_channel settings */ int metadata_global_manual; int metadata_streams_manual; int metadata_chapters_manual; const char **attachments; int nb_attachments; int chapters_input_file; int64_t recording_time; uint64_t limit_filesize; float mux_preload; float mux_max_delay; int video_disable; int audio_disable; int subtitle_disable; int data_disable; /* indexed by output file stream index */ int *streamid_map; int nb_streamid_map; SpecifierOpt *metadata; int nb_metadata; SpecifierOpt *max_frames; int nb_max_frames; SpecifierOpt *bitstream_filters; int nb_bitstream_filters; SpecifierOpt *codec_tags; int nb_codec_tags; SpecifierOpt *sample_fmts; int nb_sample_fmts; SpecifierOpt *qscale; int nb_qscale; SpecifierOpt *forced_key_frames; int nb_forced_key_frames; SpecifierOpt *force_fps; int nb_force_fps; SpecifierOpt *frame_aspect_ratios; int nb_frame_aspect_ratios; SpecifierOpt *rc_overrides; int nb_rc_overrides; SpecifierOpt *intra_matrices; int nb_intra_matrices; SpecifierOpt *inter_matrices; int nb_inter_matrices; SpecifierOpt *top_field_first; int nb_top_field_first; SpecifierOpt *metadata_map; int nb_metadata_map; SpecifierOpt *presets; int nb_presets; SpecifierOpt *copy_initial_nonkeyframes; int nb_copy_initial_nonkeyframes; SpecifierOpt *filters; int nb_filters; } OptionsContext; static void do_video_stats(AVFormatContext *os, OutputStream *ost, int frame_size); #define MATCH_PER_STREAM_OPT(name, type, outvar, fmtctx, st)\ {\ int i, ret;\ for (i = 0; i < o->nb_ ## name; i++) {\ char *spec = o->name[i].specifier;\ if ((ret = check_stream_specifier(fmtctx, st, spec)) > 0)\ outvar = o->name[i].u.type;\ else if (ret < 0)\ exit_program(1);\ }\ } static int64_t getutime(void) { #if HAVE_GETRUSAGE struct rusage rusage; getrusage(RUSAGE_SELF, &rusage); return (rusage.ru_utime.tv_sec * 1000000LL) + rusage.ru_utime.tv_usec; #elif HAVE_GETPROCESSTIMES HANDLE proc; FILETIME c, e, k, u; proc = GetCurrentProcess(); GetProcessTimes(proc, &c, &e, &k, &u); return ((int64_t) u.dwHighDateTime << 32 | u.dwLowDateTime) / 10; #else return av_gettime(); #endif } static void update_benchmark(const char *fmt, ...) { if (do_benchmark_all) { int64_t t = getutime(); va_list va; char buf[1024]; if (fmt) { va_start(va, fmt); vsnprintf(buf, sizeof(buf), fmt, va); va_end(va); printf("bench: %8"PRIu64" %s \n", t - current_time, buf); } current_time = t; } } /* 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_prepare(InputStream *ist) { AVFormatContext *avf = input_files[ist->file_index]->ctx; int i, ret, w, h; uint8_t *image[4]; int linesize[4]; /* Compute the size of the canvas for the subtitles stream. If the subtitles codec has set a size, use it. Otherwise use the maximum dimensions of the video streams in the same file. */ w = ist->st->codec->width; h = ist->st->codec->height; if (!(w && h)) { for (i = 0; i < avf->nb_streams; i++) { if (avf->streams[i]->codec->codec_type == AVMEDIA_TYPE_VIDEO) { w = FFMAX(w, avf->streams[i]->codec->width); h = FFMAX(h, avf->streams[i]->codec->height); } } if (!(w && h)) { w = FFMAX(w, 720); h = FFMAX(h, 576); } av_log(avf, AV_LOG_INFO, "sub2video: using %dx%d canvas\n", w, h); } ist->sub2video.w = ist->st->codec->width = w; ist->sub2video.h = ist->st->codec->height = h; /* rectangles are PIX_FMT_PAL8, but we have no guarantee that the palettes for all rectangles are identical or compatible */ ist->st->codec->pix_fmt = PIX_FMT_RGB32; ret = av_image_alloc(image, linesize, w, h, PIX_FMT_RGB32, 32); if (ret < 0) return ret; memset(image[0], 0, h * linesize[0]); ist->sub2video.ref = avfilter_get_video_buffer_ref_from_arrays( image, linesize, AV_PERM_READ | AV_PERM_PRESERVE, w, h, PIX_FMT_RGB32); if (!ist->sub2video.ref) { av_free(image[0]); return AVERROR(ENOMEM); } 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 overflowing\n"); return; } dst += r->y * dst_linesize + r->x * 4; src = r->pict.data[0]; pal = (uint32_t *)r->pict.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->pict.linesize[0]; } } static void sub2video_push_ref(InputStream *ist, int64_t pts) { AVFilterBufferRef *ref = ist->sub2video.ref; int i; ist->sub2video.last_pts = ref->pts = pts; for (i = 0; i < ist->nb_filters; i++) av_buffersrc_add_ref(ist->filters[i]->filter, avfilter_ref_buffer(ref, ~0), AV_BUFFERSRC_FLAG_NO_CHECK_FORMAT | AV_BUFFERSRC_FLAG_NO_COPY); } static void sub2video_update(InputStream *ist, AVSubtitle *sub, int64_t pts) { int w = ist->sub2video.w, h = ist->sub2video.h; AVFilterBufferRef *ref = ist->sub2video.ref; int8_t *dst; int dst_linesize; int i; if (!ref) return; dst = ref->data [0]; dst_linesize = ref->linesize[0]; memset(dst, 0, h * dst_linesize); for (i = 0; i < sub->num_rects; i++) sub2video_copy_rect(dst, dst_linesize, w, h, sub->rects[i]); sub2video_push_ref(ist, pts); } 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.ref) continue; /* subtitles seem to be usually muxed ahead of other streams; if not, substracting 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; 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; for (i = 0; i < ist->nb_filters; i++) av_buffersrc_add_ref(ist->filters[i]->filter, NULL, 0); } /* end of sub2video hack */ static void reset_options(OptionsContext *o, int is_input) { const OptionDef *po = options; OptionsContext bak= *o; int i; /* all OPT_SPEC and OPT_STRING can be freed in generic way */ while (po->name) { void *dst = (uint8_t*)o + po->u.off; if (po->flags & OPT_SPEC) { SpecifierOpt **so = dst; int i, *count = (int*)(so + 1); for (i = 0; i < *count; i++) { av_freep(&(*so)[i].specifier); if (po->flags & OPT_STRING) av_freep(&(*so)[i].u.str); } av_freep(so); *count = 0; } else if (po->flags & OPT_OFFSET && po->flags & OPT_STRING) av_freep(dst); po++; } for (i = 0; i < o->nb_stream_maps; i++) av_freep(&o->stream_maps[i].linklabel); av_freep(&o->stream_maps); av_freep(&o->audio_channel_maps); av_freep(&o->streamid_map); memset(o, 0, sizeof(*o)); if (is_input) { o->recording_time = bak.recording_time; if (o->recording_time != INT64_MAX) av_log(NULL, AV_LOG_WARNING, "-t is not an input option, keeping it for the next output;" " consider fixing your command line.\n"); } else o->recording_time = INT64_MAX; o->mux_max_delay = 0.7; o->limit_filesize = UINT64_MAX; o->chapters_input_file = INT_MAX; uninit_opts(); init_opts(); } static enum PixelFormat choose_pixel_fmt(AVStream *st, AVCodec *codec, enum PixelFormat target) { if (codec && codec->pix_fmts) { const enum PixelFormat *p = codec->pix_fmts; int has_alpha= av_pix_fmt_descriptors[target].nb_components % 2 == 0; enum PixelFormat best= PIX_FMT_NONE; if (st->codec->strict_std_compliance <= FF_COMPLIANCE_UNOFFICIAL) { if (st->codec->codec_id == AV_CODEC_ID_MJPEG) { p = (const enum PixelFormat[]) { PIX_FMT_YUVJ420P, PIX_FMT_YUVJ422P, PIX_FMT_YUV420P, PIX_FMT_YUV422P, PIX_FMT_NONE }; } else if (st->codec->codec_id == AV_CODEC_ID_LJPEG) { p = (const enum PixelFormat[]) { PIX_FMT_YUVJ420P, PIX_FMT_YUVJ422P, PIX_FMT_YUVJ444P, PIX_FMT_YUV420P, PIX_FMT_YUV422P, PIX_FMT_YUV444P, PIX_FMT_BGRA, PIX_FMT_NONE }; } } for (; *p != PIX_FMT_NONE; p++) { best= avcodec_find_best_pix_fmt2(best, *p, target, has_alpha, NULL); if (*p == target) break; } if (*p == PIX_FMT_NONE) { if (target != PIX_FMT_NONE) av_log(NULL, AV_LOG_WARNING, "Incompatible pixel format '%s' for codec '%s', auto-selecting format '%s'\n", av_pix_fmt_descriptors[target].name, codec->name, av_pix_fmt_descriptors[best].name); return best; } } return target; } static char *choose_pix_fmts(OutputStream *ost) { if (ost->keep_pix_fmt) { if (ost->filter) avfilter_graph_set_auto_convert(ost->filter->graph->graph, AVFILTER_AUTO_CONVERT_NONE); if (ost->st->codec->pix_fmt == PIX_FMT_NONE) return NULL; return av_strdup(av_get_pix_fmt_name(ost->st->codec->pix_fmt)); } if (ost->st->codec->pix_fmt != PIX_FMT_NONE) { return av_strdup(av_get_pix_fmt_name(choose_pixel_fmt(ost->st, ost->enc, ost->st->codec->pix_fmt))); } else if (ost->enc && ost->enc->pix_fmts) { const enum PixelFormat *p; AVIOContext *s = NULL; uint8_t *ret; int len; if (avio_open_dyn_buf(&s) < 0) exit_program(1); p = ost->enc->pix_fmts; if (ost->st->codec->strict_std_compliance <= FF_COMPLIANCE_UNOFFICIAL) { if (ost->st->codec->codec_id == AV_CODEC_ID_MJPEG) { p = (const enum PixelFormat[]) { PIX_FMT_YUVJ420P, PIX_FMT_YUVJ422P, PIX_FMT_YUV420P, PIX_FMT_YUV422P, PIX_FMT_NONE }; } else if (ost->st->codec->codec_id == AV_CODEC_ID_LJPEG) { p = (const enum PixelFormat[]) { PIX_FMT_YUVJ420P, PIX_FMT_YUVJ422P, PIX_FMT_YUVJ444P, PIX_FMT_YUV420P, PIX_FMT_YUV422P, PIX_FMT_YUV444P, PIX_FMT_BGRA, PIX_FMT_NONE }; } } for (; *p != PIX_FMT_NONE; p++) { const char *name = av_get_pix_fmt_name(*p); avio_printf(s, "%s:", name); } len = avio_close_dyn_buf(s, &ret); ret[len - 1] = 0; return ret; } else return NULL; } /** * Define a function for building a string containing a list of * allowed formats, */ #define DEF_CHOOSE_FORMAT(type, var, supported_list, none, get_name, separator) \ static char *choose_ ## var ## s(OutputStream *ost) \ { \ if (ost->st->codec->var != none) { \ get_name(ost->st->codec->var); \ return av_strdup(name); \ } else if (ost->enc->supported_list) { \ const type *p; \ AVIOContext *s = NULL; \ uint8_t *ret; \ int len; \ \ if (avio_open_dyn_buf(&s) < 0) \ exit_program(1); \ \ for (p = ost->enc->supported_list; *p != none; p++) { \ get_name(*p); \ avio_printf(s, "%s" separator, name); \ } \ len = avio_close_dyn_buf(s, &ret); \ ret[len - 1] = 0; \ return ret; \ } else \ return NULL; \ } #define GET_PIX_FMT_NAME(pix_fmt)\ const char *name = av_get_pix_fmt_name(pix_fmt); // DEF_CHOOSE_FORMAT(enum PixelFormat, pix_fmt, pix_fmts, PIX_FMT_NONE, // GET_PIX_FMT_NAME, ":") #define GET_SAMPLE_FMT_NAME(sample_fmt)\ const char *name = av_get_sample_fmt_name(sample_fmt) DEF_CHOOSE_FORMAT(enum AVSampleFormat, sample_fmt, sample_fmts, AV_SAMPLE_FMT_NONE, GET_SAMPLE_FMT_NAME, ",") #define GET_SAMPLE_RATE_NAME(rate)\ char name[16];\ snprintf(name, sizeof(name), "%d", rate); DEF_CHOOSE_FORMAT(int, sample_rate, supported_samplerates, 0, GET_SAMPLE_RATE_NAME, ",") #define GET_CH_LAYOUT_NAME(ch_layout)\ char name[16];\ snprintf(name, sizeof(name), "0x%"PRIx64, ch_layout); DEF_CHOOSE_FORMAT(uint64_t, channel_layout, channel_layouts, 0, GET_CH_LAYOUT_NAME, ",") static FilterGraph *init_simple_filtergraph(InputStream *ist, OutputStream *ost) { FilterGraph *fg = av_mallocz(sizeof(*fg)); if (!fg) exit_program(1); fg->index = nb_filtergraphs; fg->outputs = grow_array(fg->outputs, sizeof(*fg->outputs), &fg->nb_outputs, fg->nb_outputs + 1); if (!(fg->outputs[0] = av_mallocz(sizeof(*fg->outputs[0])))) exit_program(1); fg->outputs[0]->ost = ost; fg->outputs[0]->graph = fg; ost->filter = fg->outputs[0]; fg->inputs = grow_array(fg->inputs, sizeof(*fg->inputs), &fg->nb_inputs, fg->nb_inputs + 1); if (!(fg->inputs[0] = av_mallocz(sizeof(*fg->inputs[0])))) exit_program(1); fg->inputs[0]->ist = ist; fg->inputs[0]->graph = fg; ist->filters = grow_array(ist->filters, sizeof(*ist->filters), &ist->nb_filters, ist->nb_filters + 1); ist->filters[ist->nb_filters - 1] = fg->inputs[0]; filtergraphs = grow_array(filtergraphs, sizeof(*filtergraphs), &nb_filtergraphs, nb_filtergraphs + 1); filtergraphs[nb_filtergraphs - 1] = fg; return fg; } static void init_input_filter(FilterGraph *fg, AVFilterInOut *in) { InputStream *ist = NULL; enum AVMediaType type = avfilter_pad_get_type(in->filter_ctx->input_pads, in->pad_idx); int i; // TODO: support other filter types if (type != AVMEDIA_TYPE_VIDEO && type != AVMEDIA_TYPE_AUDIO) { av_log(NULL, AV_LOG_FATAL, "Only video and audio filters supported " "currently.\n"); exit_program(1); } if (in->name) { AVFormatContext *s; AVStream *st = NULL; char *p; int file_idx = strtol(in->name, &p, 0); if (file_idx < 0 || file_idx >= nb_input_files) { av_log(NULL, AV_LOG_FATAL, "Invalid file index %d in filtergraph description %s.\n", file_idx, fg->graph_desc); exit_program(1); } s = input_files[file_idx]->ctx; for (i = 0; i < s->nb_streams; i++) { enum AVMediaType stream_type = s->streams[i]->codec->codec_type; if (stream_type != type && !(stream_type == AVMEDIA_TYPE_SUBTITLE && type == AVMEDIA_TYPE_VIDEO /* sub2video hack */)) continue; if (check_stream_specifier(s, s->streams[i], *p == ':' ? p + 1 : p) == 1) { st = s->streams[i]; break; } } if (!st) { av_log(NULL, AV_LOG_FATAL, "Stream specifier '%s' in filtergraph description %s " "matches no streams.\n", p, fg->graph_desc); exit_program(1); } ist = input_streams[input_files[file_idx]->ist_index + st->index]; } else { /* find the first unused stream of corresponding type */ for (i = 0; i < nb_input_streams; i++) { ist = input_streams[i]; if (ist->st->codec->codec_type == type && ist->discard) break; } if (i == nb_input_streams) { av_log(NULL, AV_LOG_FATAL, "Cannot find a matching stream for " "unlabeled input pad %d on filter %s\n", in->pad_idx, in->filter_ctx->name); exit_program(1); } } av_assert0(ist); ist->discard = 0; ist->decoding_needed = 1; ist->st->discard = AVDISCARD_NONE; fg->inputs = grow_array(fg->inputs, sizeof(*fg->inputs), &fg->nb_inputs, fg->nb_inputs + 1); if (!(fg->inputs[fg->nb_inputs - 1] = av_mallocz(sizeof(*fg->inputs[0])))) exit_program(1); fg->inputs[fg->nb_inputs - 1]->ist = ist; fg->inputs[fg->nb_inputs - 1]->graph = fg; ist->filters = grow_array(ist->filters, sizeof(*ist->filters), &ist->nb_filters, ist->nb_filters + 1); ist->filters[ist->nb_filters - 1] = fg->inputs[fg->nb_inputs - 1]; } static int configure_output_video_filter(FilterGraph *fg, OutputFilter *ofilter, AVFilterInOut *out) { char *pix_fmts; OutputStream *ost = ofilter->ost; AVCodecContext *codec = ost->st->codec; AVFilterContext *last_filter = out->filter_ctx; int pad_idx = out->pad_idx; int ret; char name[255]; AVBufferSinkParams *buffersink_params = av_buffersink_params_alloc(); snprintf(name, sizeof(name), "output stream %d:%d", ost->file_index, ost->index); ret = avfilter_graph_create_filter(&ofilter->filter, avfilter_get_by_name("buffersink"), name, NULL, NULL/*buffersink_params*/, fg->graph); av_freep(&buffersink_params); if (ret < 0) return ret; if (codec->width || codec->height) { char args[255]; AVFilterContext *filter; snprintf(args, sizeof(args), "%d:%d:flags=0x%X", codec->width, codec->height, (unsigned)ost->sws_flags); snprintf(name, sizeof(name), "scaler for output stream %d:%d", ost->file_index, ost->index); if ((ret = avfilter_graph_create_filter(&filter, avfilter_get_by_name("scale"), name, args, NULL, fg->graph)) < 0) return ret; if ((ret = avfilter_link(last_filter, pad_idx, filter, 0)) < 0) return ret; last_filter = filter; pad_idx = 0; } if ((pix_fmts = choose_pix_fmts(ost))) { AVFilterContext *filter; snprintf(name, sizeof(name), "pixel format for output stream %d:%d", ost->file_index, ost->index); if ((ret = avfilter_graph_create_filter(&filter, avfilter_get_by_name("format"), "format", pix_fmts, NULL, fg->graph)) < 0) return ret; if ((ret = avfilter_link(last_filter, pad_idx, filter, 0)) < 0) return ret; last_filter = filter; pad_idx = 0; av_freep(&pix_fmts); } if (ost->frame_rate.num && 0) { AVFilterContext *fps; char args[255]; snprintf(args, sizeof(args), "fps=%d/%d", ost->frame_rate.num, ost->frame_rate.den); snprintf(name, sizeof(name), "fps for output stream %d:%d", ost->file_index, ost->index); ret = avfilter_graph_create_filter(&fps, avfilter_get_by_name("fps"), name, args, NULL, fg->graph); if (ret < 0) return ret; ret = avfilter_link(last_filter, pad_idx, fps, 0); if (ret < 0) return ret; last_filter = fps; pad_idx = 0; } if ((ret = avfilter_link(last_filter, pad_idx, ofilter->filter, 0)) < 0) return ret; return 0; } static int configure_output_audio_filter(FilterGraph *fg, OutputFilter *ofilter, AVFilterInOut *out) { OutputStream *ost = ofilter->ost; AVCodecContext *codec = ost->st->codec; AVFilterContext *last_filter = out->filter_ctx; int pad_idx = out->pad_idx; char *sample_fmts, *sample_rates, *channel_layouts; char name[255]; int ret; snprintf(name, sizeof(name), "output stream %d:%d", ost->file_index, ost->index); ret = avfilter_graph_create_filter(&ofilter->filter, avfilter_get_by_name("abuffersink"), name, NULL, NULL, fg->graph); if (ret < 0) return ret; #define AUTO_INSERT_FILTER(opt_name, filter_name, arg) do { \ AVFilterContext *filt_ctx; \ \ av_log(NULL, AV_LOG_INFO, opt_name " is forwarded to lavfi " \ "similarly to -af " filter_name "=%s.\n", arg); \ \ ret = avfilter_graph_create_filter(&filt_ctx, \ avfilter_get_by_name(filter_name), \ filter_name, arg, NULL, fg->graph); \ if (ret < 0) \ return ret; \ \ ret = avfilter_link(last_filter, pad_idx, filt_ctx, 0); \ if (ret < 0) \ return ret; \ \ last_filter = filt_ctx; \ pad_idx = 0; \ } while (0) if (ost->audio_channels_mapped) { int i; AVBPrint pan_buf; av_bprint_init(&pan_buf, 256, 8192); av_bprintf(&pan_buf, "0x%"PRIx64, av_get_default_channel_layout(ost->audio_channels_mapped)); for (i = 0; i < ost->audio_channels_mapped; i++) if (ost->audio_channels_map[i] != -1) av_bprintf(&pan_buf, ":c%d=c%d", i, ost->audio_channels_map[i]); AUTO_INSERT_FILTER("-map_channel", "pan", pan_buf.str); av_bprint_finalize(&pan_buf, NULL); } if (codec->channels && !codec->channel_layout) codec->channel_layout = av_get_default_channel_layout(codec->channels); sample_fmts = choose_sample_fmts(ost); sample_rates = choose_sample_rates(ost); channel_layouts = choose_channel_layouts(ost); if (sample_fmts || sample_rates || channel_layouts) { AVFilterContext *format; char args[256]; int len = 0; if (sample_fmts) len += snprintf(args + len, sizeof(args) - len, "sample_fmts=%s:", sample_fmts); if (sample_rates) len += snprintf(args + len, sizeof(args) - len, "sample_rates=%s:", sample_rates); if (channel_layouts) len += snprintf(args + len, sizeof(args) - len, "channel_layouts=%s:", channel_layouts); args[len - 1] = 0; av_freep(&sample_fmts); av_freep(&sample_rates); av_freep(&channel_layouts); snprintf(name, sizeof(name), "audio format for output stream %d:%d", ost->file_index, ost->index); ret = avfilter_graph_create_filter(&format, avfilter_get_by_name("aformat"), name, args, NULL, fg->graph); if (ret < 0) return ret; ret = avfilter_link(last_filter, pad_idx, format, 0); if (ret < 0) return ret; last_filter = format; pad_idx = 0; } if (audio_volume != 256 && 0) { char args[256]; snprintf(args, sizeof(args), "%f", audio_volume / 256.); AUTO_INSERT_FILTER("-vol", "volume", args); } if ((ret = avfilter_link(last_filter, pad_idx, ofilter->filter, 0)) < 0) return ret; return 0; } #define DESCRIBE_FILTER_LINK(f, inout, in) \ { \ AVFilterContext *ctx = inout->filter_ctx; \ AVFilterPad *pads = in ? ctx->input_pads : ctx->output_pads; \ int nb_pads = in ? ctx->input_count : ctx->output_count; \ AVIOContext *pb; \ \ if (avio_open_dyn_buf(&pb) < 0) \ exit_program(1); \ \ avio_printf(pb, "%s", ctx->filter->name); \ if (nb_pads > 1) \ avio_printf(pb, ":%s", avfilter_pad_get_name(pads, inout->pad_idx));\ avio_w8(pb, 0); \ avio_close_dyn_buf(pb, &f->name); \ } static int configure_output_filter(FilterGraph *fg, OutputFilter *ofilter, AVFilterInOut *out) { av_freep(&ofilter->name); DESCRIBE_FILTER_LINK(ofilter, out, 0); switch (avfilter_pad_get_type(out->filter_ctx->output_pads, out->pad_idx)) { case AVMEDIA_TYPE_VIDEO: return configure_output_video_filter(fg, ofilter, out); case AVMEDIA_TYPE_AUDIO: return configure_output_audio_filter(fg, ofilter, out); default: av_assert0(0); } } static int configure_input_video_filter(FilterGraph *fg, InputFilter *ifilter, AVFilterInOut *in) { AVFilterContext *first_filter = in->filter_ctx; AVFilter *filter = avfilter_get_by_name("buffer"); InputStream *ist = ifilter->ist; AVRational tb = ist->framerate.num ? av_inv_q(ist->framerate) : ist->st->time_base; AVRational fr = ist->framerate.num ? ist->framerate : ist->st->r_frame_rate; AVRational sar; AVBPrint args; char name[255]; int pad_idx = in->pad_idx; int ret; if (ist->st->codec->codec_type == AVMEDIA_TYPE_SUBTITLE) { ret = sub2video_prepare(ist); if (ret < 0) return ret; } sar = ist->st->sample_aspect_ratio.num ? ist->st->sample_aspect_ratio : ist->st->codec->sample_aspect_ratio; if(!sar.den) sar = (AVRational){0,1}; av_bprint_init(&args, 0, 1); av_bprintf(&args, "video_size=%dx%d:pix_fmt=%d:time_base=%d/%d:" "pixel_aspect=%d/%d:sws_param=flags=%d", ist->st->codec->width, ist->st->codec->height, ist->st->codec->pix_fmt, tb.num, tb.den, sar.num, sar.den, SWS_BILINEAR + ((ist->st->codec->flags&CODEC_FLAG_BITEXACT) ? SWS_BITEXACT:0)); if (fr.num && fr.den) av_bprintf(&args, ":frame_rate=%d/%d", fr.num, fr.den); snprintf(name, sizeof(name), "graph %d input from stream %d:%d", fg->index, ist->file_index, ist->st->index); if ((ret = avfilter_graph_create_filter(&ifilter->filter, filter, name, args.str, NULL, fg->graph)) < 0) return ret; if (ist->framerate.num) { AVFilterContext *setpts; snprintf(name, sizeof(name), "force CFR for input from stream %d:%d", ist->file_index, ist->st->index); if ((ret = avfilter_graph_create_filter(&setpts, avfilter_get_by_name("setpts"), name, "N", NULL, fg->graph)) < 0) return ret; if ((ret = avfilter_link(setpts, 0, first_filter, pad_idx)) < 0) return ret; first_filter = setpts; pad_idx = 0; } if ((ret = avfilter_link(ifilter->filter, 0, first_filter, pad_idx)) < 0) return ret; return 0; } static int configure_input_audio_filter(FilterGraph *fg, InputFilter *ifilter, AVFilterInOut *in) { AVFilterContext *first_filter = in->filter_ctx; AVFilter *filter = avfilter_get_by_name("abuffer"); InputStream *ist = ifilter->ist; int pad_idx = in->pad_idx; char args[255], name[255]; int ret; snprintf(args, sizeof(args), "time_base=%d/%d:sample_rate=%d:sample_fmt=%s" ":channel_layout=0x%"PRIx64, 1, ist->st->codec->sample_rate, ist->st->codec->sample_rate, av_get_sample_fmt_name(ist->st->codec->sample_fmt), ist->st->codec->channel_layout); snprintf(name, sizeof(name), "graph %d input from stream %d:%d", fg->index, ist->file_index, ist->st->index); if ((ret = avfilter_graph_create_filter(&ifilter->filter, filter, name, args, NULL, fg->graph)) < 0) return ret; #define AUTO_INSERT_FILTER_INPUT(opt_name, filter_name, arg) do { \ AVFilterContext *filt_ctx; \ \ av_log(NULL, AV_LOG_INFO, opt_name " is forwarded to lavfi " \ "similarly to -af " filter_name "=%s.\n", arg); \ \ snprintf(name, sizeof(name), "graph %d %s for input stream %d:%d", \ fg->index, filter_name, ist->file_index, ist->st->index); \ ret = avfilter_graph_create_filter(&filt_ctx, \ avfilter_get_by_name(filter_name), \ name, arg, NULL, fg->graph); \ if (ret < 0) \ return ret; \ \ ret = avfilter_link(filt_ctx, 0, first_filter, pad_idx); \ if (ret < 0) \ return ret; \ \ first_filter = filt_ctx; \ } while (0) if (audio_sync_method > 0) { char args[256] = {0}; av_strlcatf(args, sizeof(args), "min_comp=0.001:min_hard_comp=%f", audio_drift_threshold); if (audio_sync_method > 1) av_strlcatf(args, sizeof(args), ":max_soft_comp=%f", audio_sync_method/(double)ist->st->codec->sample_rate); AUTO_INSERT_FILTER_INPUT("-async", "aresample", args); } // if (ost->audio_channels_mapped) { // int i; // AVBPrint pan_buf; // av_bprint_init(&pan_buf, 256, 8192); // av_bprintf(&pan_buf, "0x%"PRIx64, // av_get_default_channel_layout(ost->audio_channels_mapped)); // for (i = 0; i < ost->audio_channels_mapped; i++) // if (ost->audio_channels_map[i] != -1) // av_bprintf(&pan_buf, ":c%d=c%d", i, ost->audio_channels_map[i]); // AUTO_INSERT_FILTER_INPUT("-map_channel", "pan", pan_buf.str); // av_bprint_finalize(&pan_buf, NULL); // } if (audio_volume != 256) { char args[256]; snprintf(args, sizeof(args), "%f", audio_volume / 256.); AUTO_INSERT_FILTER_INPUT("-vol", "volume", args); } if ((ret = avfilter_link(ifilter->filter, 0, first_filter, pad_idx)) < 0) return ret; return 0; } static int configure_input_filter(FilterGraph *fg, InputFilter *ifilter, AVFilterInOut *in) { av_freep(&ifilter->name); DESCRIBE_FILTER_LINK(ifilter, in, 1); switch (avfilter_pad_get_type(in->filter_ctx->input_pads, in->pad_idx)) { case AVMEDIA_TYPE_VIDEO: return configure_input_video_filter(fg, ifilter, in); case AVMEDIA_TYPE_AUDIO: return configure_input_audio_filter(fg, ifilter, in); default: av_assert0(0); } } static int configure_filtergraph(FilterGraph *fg) { AVFilterInOut *inputs, *outputs, *cur; int ret, i, init = !fg->graph, simple = !fg->graph_desc; const char *graph_desc = simple ? fg->outputs[0]->ost->avfilter : fg->graph_desc; avfilter_graph_free(&fg->graph); if (!(fg->graph = avfilter_graph_alloc())) return AVERROR(ENOMEM); if (simple) { OutputStream *ost = fg->outputs[0]->ost; char args[255]; snprintf(args, sizeof(args), "flags=0x%X", (unsigned)ost->sws_flags); fg->graph->scale_sws_opts = av_strdup(args); } if ((ret = avfilter_graph_parse2(fg->graph, graph_desc, &inputs, &outputs)) < 0) return ret; if (simple && (!inputs || inputs->next || !outputs || outputs->next)) { av_log(NULL, AV_LOG_ERROR, "Simple filtergraph '%s' does not have " "exactly one input and output.\n", graph_desc); return AVERROR(EINVAL); } for (cur = inputs; !simple && init && cur; cur = cur->next) init_input_filter(fg, cur); for (cur = inputs, i = 0; cur; cur = cur->next, i++) if ((ret = configure_input_filter(fg, fg->inputs[i], cur)) < 0) return ret; avfilter_inout_free(&inputs); if (!init || simple) { /* we already know the mappings between lavfi outputs and output streams, * so we can finish the setup */ for (cur = outputs, i = 0; cur; cur = cur->next, i++) configure_output_filter(fg, fg->outputs[i], cur); avfilter_inout_free(&outputs); if ((ret = avfilter_graph_config(fg->graph, NULL)) < 0) return ret; } else { /* wait until output mappings are processed */ for (cur = outputs; cur;) { fg->outputs = grow_array(fg->outputs, sizeof(*fg->outputs), &fg->nb_outputs, fg->nb_outputs + 1); if (!(fg->outputs[fg->nb_outputs - 1] = av_mallocz(sizeof(*fg->outputs[0])))) exit_program(1); fg->outputs[fg->nb_outputs - 1]->graph = fg; fg->outputs[fg->nb_outputs - 1]->out_tmp = cur; cur = cur->next; fg->outputs[fg->nb_outputs - 1]->out_tmp->next = NULL; } } return 0; } static int configure_complex_filters(void) { int i, ret = 0; for (i = 0; i < nb_filtergraphs; i++) if (!filtergraphs[i]->graph && (ret = configure_filtergraph(filtergraphs[i])) < 0) return ret; return 0; } static int ist_in_filtergraph(FilterGraph *fg, InputStream *ist) { int i; for (i = 0; i < fg->nb_inputs; i++) if (fg->inputs[i]->ist == ist) return 1; return 0; } static void term_exit(void) { av_log(NULL, AV_LOG_QUIET, "%s", ""); #if HAVE_TERMIOS_H if(restore_tty) tcsetattr (0, TCSANOW, &oldtty); #endif } static volatile int received_sigterm = 0; static void sigterm_handler(int sig) { received_sigterm = sig; received_nb_signals++; term_exit(); if(received_nb_signals > 3) exit(123); } static void term_init(void) { #if HAVE_TERMIOS_H if(!run_as_daemon){ struct termios tty; int istty = 1; #if HAVE_ISATTY istty = isatty(0) && isatty(2); #endif if (istty && tcgetattr (0, &tty) == 0) { oldtty = tty; restore_tty = 1; atexit(term_exit); 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 avformat_network_deinit(); signal(SIGINT , sigterm_handler); /* Interrupt (ANSI). */ signal(SIGTERM, sigterm_handler); /* Termination (ANSI). */ #ifdef SIGXCPU signal(SIGXCPU, sigterm_handler); #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 (stdin->_cnt > 0) { read(0, &ch, 1); return ch; } if (is_pipe) { /* When running under a GUI, you will end here. */ if (!PeekNamedPipe(input_handle, NULL, 0, NULL, &nchars, NULL)) 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 > 1; } static const AVIOInterruptCB int_cb = { decode_interrupt_cb, NULL }; void av_noreturn exit_program(int ret) { int i, j; for (i = 0; i < nb_filtergraphs; i++) { avfilter_graph_free(&filtergraphs[i]->graph); for (j = 0; j < filtergraphs[i]->nb_inputs; j++) { av_freep(&filtergraphs[i]->inputs[j]->name); av_freep(&filtergraphs[i]->inputs[j]); } av_freep(&filtergraphs[i]->inputs); for (j = 0; j < filtergraphs[i]->nb_outputs; j++) { av_freep(&filtergraphs[i]->outputs[j]->name); av_freep(&filtergraphs[i]->outputs[j]); } av_freep(&filtergraphs[i]->outputs); av_freep(&filtergraphs[i]); } av_freep(&filtergraphs); av_freep(&subtitle_out); /* close files */ for (i = 0; i < nb_output_files; i++) { AVFormatContext *s = output_files[i]->ctx; if (!(s->oformat->flags & AVFMT_NOFILE) && s->pb) avio_close(s->pb); avformat_free_context(s); av_dict_free(&output_files[i]->opts); av_freep(&output_files[i]); } for (i = 0; i < nb_output_streams; i++) { AVBitStreamFilterContext *bsfc = output_streams[i]->bitstream_filters; while (bsfc) { AVBitStreamFilterContext *next = bsfc->next; av_bitstream_filter_close(bsfc); bsfc = next; } output_streams[i]->bitstream_filters = NULL; av_freep(&output_streams[i]->forced_keyframes); av_freep(&output_streams[i]->filtered_frame); av_freep(&output_streams[i]->avfilter); av_freep(&output_streams[i]); } 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++) { av_freep(&input_streams[i]->decoded_frame); av_dict_free(&input_streams[i]->opts); free_buffer_pool(&input_streams[i]->buffer_pool); avfilter_unref_bufferp(&input_streams[i]->sub2video.ref); av_freep(&input_streams[i]->filters); av_freep(&input_streams[i]); } if (vstats_file) fclose(vstats_file); av_free(vstats_filename); av_freep(&input_streams); av_freep(&input_files); av_freep(&output_streams); av_freep(&output_files); uninit_opts(); avfilter_uninit(); avformat_network_deinit(); if (received_sigterm) { av_log(NULL, AV_LOG_INFO, "Received signal %d: terminating.\n", (int) received_sigterm); exit (255); } exit(ret); } static void assert_avoptions(AVDictionary *m) { 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 assert_codec_experimental(AVCodecContext *c, int encoder) { const char *codec_string = encoder ? "encoder" : "decoder"; AVCodec *codec; if (c->codec->capabilities & CODEC_CAP_EXPERIMENTAL && c->strict_std_compliance > FF_COMPLIANCE_EXPERIMENTAL) { av_log(NULL, AV_LOG_FATAL, "%s '%s' is experimental and might produce bad " "results.\nAdd '-strict experimental' if you want to use it.\n", codec_string, c->codec->name); codec = encoder ? avcodec_find_encoder(c->codec->id) : avcodec_find_decoder(c->codec->id); if (!(codec->capabilities & CODEC_CAP_EXPERIMENTAL)) av_log(NULL, AV_LOG_FATAL, "Or use the non experimental %s '%s'.\n", codec_string, codec->name); exit_program(1); } } static void choose_sample_fmt(AVStream *st, AVCodec *codec) { if (codec && codec->sample_fmts) { const enum AVSampleFormat *p = codec->sample_fmts; for (; *p != -1; p++) { if (*p == st->codec->sample_fmt) break; } if (*p == -1) { if((codec->capabilities & CODEC_CAP_LOSSLESS) && av_get_sample_fmt_name(st->codec->sample_fmt) > av_get_sample_fmt_name(codec->sample_fmts[0])) av_log(NULL, AV_LOG_ERROR, "Conversion will not be lossless.\n"); if(av_get_sample_fmt_name(st->codec->sample_fmt)) av_log(NULL, AV_LOG_WARNING, "Incompatible sample format '%s' for codec '%s', auto-selecting format '%s'\n", av_get_sample_fmt_name(st->codec->sample_fmt), codec->name, av_get_sample_fmt_name(codec->sample_fmts[0])); st->codec->sample_fmt = codec->sample_fmts[0]; } } } static void write_frame(AVFormatContext *s, AVPacket *pkt, OutputStream *ost) { AVBitStreamFilterContext *bsfc = ost->bitstream_filters; AVCodecContext *avctx = ost->st->codec; int ret; if ((avctx->codec_type == AVMEDIA_TYPE_VIDEO && video_sync_method == VSYNC_DROP) || (avctx->codec_type == AVMEDIA_TYPE_AUDIO && audio_sync_method < 0)) pkt->pts = pkt->dts = AV_NOPTS_VALUE; if (avctx->codec_type == AVMEDIA_TYPE_AUDIO && pkt->dts != AV_NOPTS_VALUE) { int64_t max = ost->st->cur_dts + !(s->oformat->flags & AVFMT_TS_NONSTRICT); if (ost->st->cur_dts && ost->st->cur_dts != AV_NOPTS_VALUE && max > pkt->dts) { av_log(s, max - pkt->dts > 2 ? AV_LOG_WARNING : AV_LOG_DEBUG, "Audio timestamp %"PRId64" < %"PRId64" invalid, cliping\n", pkt->dts, max); pkt->pts = pkt->dts = max; } } /* * Audio encoders may split the packets -- #frames in != #packets out. * But there is no reordering, so we can limit the number of output packets * by simply dropping them here. * Counting encoded video frames needs to be done separately because of * reordering, see do_video_out() */ if (!(avctx->codec_type == AVMEDIA_TYPE_VIDEO && avctx->codec)) { if (ost->frame_number >= ost->max_frames) { av_free_packet(pkt); return; } ost->frame_number++; } while (bsfc) { AVPacket new_pkt = *pkt; int a = av_bitstream_filter_filter(bsfc, avctx, NULL, &new_pkt.data, &new_pkt.size, pkt->data, pkt->size, pkt->flags & AV_PKT_FLAG_KEY); if (a > 0) { av_free_packet(pkt); new_pkt.destruct = av_destruct_packet; } else if (a < 0) { av_log(NULL, AV_LOG_ERROR, "Failed to open bitstream filter %s for stream %d with codec %s", bsfc->filter->name, pkt->stream_index, avctx->codec ? avctx->codec->name : "copy"); print_error("", a); if (exit_on_error) exit_program(1); } *pkt = new_pkt; bsfc = bsfc->next; } pkt->stream_index = ost->index; ret = av_interleaved_write_frame(s, pkt); if (ret < 0) { print_error("av_interleaved_write_frame()", ret); 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->st->codec->time_base, of->recording_time, AV_TIME_BASE_Q) >= 0) { ost->is_past_recording_time = 1; return 0; } return 1; } static void do_audio_out(AVFormatContext *s, OutputStream *ost, AVFrame *frame) { AVCodecContext *enc = ost->st->codec; AVPacket pkt; int got_packet = 0; av_init_packet(&pkt); pkt.data = NULL; pkt.size = 0; 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; av_assert0(pkt.size || !pkt.data); update_benchmark(NULL); if (avcodec_encode_audio2(enc, &pkt, frame, &got_packet) < 0) { av_log(NULL, AV_LOG_FATAL, "Audio encoding failed (avcodec_encode_audio2)\n"); exit_program(1); } update_benchmark("encode_audio %d.%d", ost->file_index, ost->index); if (got_packet) { if (pkt.pts != AV_NOPTS_VALUE) pkt.pts = av_rescale_q(pkt.pts, enc->time_base, ost->st->time_base); if (pkt.dts != AV_NOPTS_VALUE) pkt.dts = av_rescale_q(pkt.dts, enc->time_base, ost->st->time_base); if (pkt.duration > 0) pkt.duration = av_rescale_q(pkt.duration, enc->time_base, ost->st->time_base); if (debug_ts) { av_log(NULL, AV_LOG_INFO, "encoder -> type:audio " "pkt_pts:%s pkt_pts_time:%s pkt_dts:%s pkt_dts_time:%s\n", av_ts2str(pkt.pts), av_ts2timestr(pkt.pts, &ost->st->time_base), av_ts2str(pkt.dts), av_ts2timestr(pkt.dts, &ost->st->time_base)); } write_frame(s, &pkt, ost); audio_size += pkt.size; av_free_packet(&pkt); } } static void pre_process_video_frame(InputStream *ist, AVPicture *picture, void **bufp) { AVCodecContext *dec; AVPicture *picture2; AVPicture picture_tmp; uint8_t *buf = 0; dec = ist->st->codec; /* deinterlace : must be done before any resize */ if (do_deinterlace) { int size; /* create temporary picture */ size = avpicture_get_size(dec->pix_fmt, dec->width, dec->height); buf = av_malloc(size); if (!buf) return; picture2 = &picture_tmp; avpicture_fill(picture2, buf, dec->pix_fmt, dec->width, dec->height); if (avpicture_deinterlace(picture2, picture, dec->pix_fmt, dec->width, dec->height) < 0) { /* if error, do not deinterlace */ av_log(NULL, AV_LOG_WARNING, "Deinterlacing failed\n"); av_free(buf); buf = NULL; picture2 = picture; } } else { picture2 = picture; } if (picture != picture2) *picture = *picture2; *bufp = buf; } static void do_subtitle_out(AVFormatContext *s, OutputStream *ost, InputStream *ist, AVSubtitle *sub, int64_t pts) { int subtitle_out_max_size = 1024 * 1024; int subtitle_out_size, nb, i; AVCodecContext *enc; AVPacket pkt; if (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->st->codec; if (!subtitle_out) { subtitle_out = av_malloc(subtitle_out_max_size); } /* 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 = av_rescale_q(pts, ist->st->time_base, AV_TIME_BASE_Q) - output_files[ost->file_index]->start_time; for (i = 0; i < nb; i++) { ost->sync_opts = av_rescale_q(pts, AV_TIME_BASE_Q, enc->time_base); if (!check_recording_time(ost)) return; 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; subtitle_out_size = avcodec_encode_subtitle(enc, subtitle_out, subtitle_out_max_size, sub); if (subtitle_out_size < 0) { av_log(NULL, AV_LOG_FATAL, "Subtitle encoding failed\n"); exit_program(1); } av_init_packet(&pkt); pkt.data = subtitle_out; pkt.size = subtitle_out_size; pkt.pts = av_rescale_q(sub->pts, AV_TIME_BASE_Q, ost->st->time_base); pkt.duration = av_rescale_q(sub->end_display_time, (AVRational){ 1, 1000 }, ost->st->time_base); 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 += 90 * sub->start_display_time; else pkt.pts += 90 * sub->end_display_time; } write_frame(s, &pkt, ost); subtitle_size += pkt.size; } } static void do_video_out(AVFormatContext *s, OutputStream *ost, AVFrame *in_picture, float quality) { int ret, format_video_sync; AVPacket pkt; AVCodecContext *enc = ost->st->codec; int nb_frames, i; double sync_ipts, delta; double duration = 0; int frame_size = 0; InputStream *ist = NULL; if (ost->source_index >= 0) ist = input_streams[ost->source_index]; if(ist && ist->st->start_time != AV_NOPTS_VALUE && ist->st->first_dts != AV_NOPTS_VALUE && ost->frame_rate.num) duration = 1/(av_q2d(ost->frame_rate) * av_q2d(enc->time_base)); sync_ipts = in_picture->pts; delta = sync_ipts - ost->sync_opts + duration; /* by default, we output a single frame */ nb_frames = 1; format_video_sync = video_sync_method; if (format_video_sync == VSYNC_AUTO) format_video_sync = (s->oformat->flags & AVFMT_VARIABLE_FPS) ? ((s->oformat->flags & AVFMT_NOTIMESTAMPS) ? VSYNC_PASSTHROUGH : VSYNC_VFR) : 1; switch (format_video_sync) { case VSYNC_CFR: // FIXME set to 0.5 after we fix some dts/pts bugs like in avidec.c if (delta < -1.1) nb_frames = 0; else if (delta > 1.1) nb_frames = lrintf(delta); break; case VSYNC_VFR: if (delta <= -0.6) nb_frames = 0; else if (delta > 0.6) ost->sync_opts = lrint(sync_ipts); break; case VSYNC_DROP: case VSYNC_PASSTHROUGH: ost->sync_opts = lrint(sync_ipts); break; default: av_assert0(0); } nb_frames = FFMIN(nb_frames, ost->max_frames - ost->frame_number); if (nb_frames == 0) { nb_frames_drop++; av_log(NULL, AV_LOG_VERBOSE, "*** drop!\n"); return; } else if (nb_frames > 1) { if (nb_frames > dts_error_threshold * 30) { av_log(NULL, AV_LOG_ERROR, "%d frame duplication too large, skiping\n", nb_frames - 1); nb_frames_drop++; return; } nb_frames_dup += nb_frames - 1; av_log(NULL, AV_LOG_VERBOSE, "*** %d dup!\n", nb_frames - 1); } /* duplicates frame if needed */ for (i = 0; i < nb_frames; i++) { av_init_packet(&pkt); pkt.data = NULL; pkt.size = 0; in_picture->pts = ost->sync_opts; if (!check_recording_time(ost)) return; if (s->oformat->flags & AVFMT_RAWPICTURE && enc->codec->id == AV_CODEC_ID_RAWVIDEO) { /* raw pictures are written as AVPicture structure to avoid any copies. We support temporarily the older method. */ enc->coded_frame->interlaced_frame = in_picture->interlaced_frame; enc->coded_frame->top_field_first = in_picture->top_field_first; pkt.data = (uint8_t *)in_picture; pkt.size = sizeof(AVPicture); pkt.pts = av_rescale_q(in_picture->pts, enc->time_base, ost->st->time_base); pkt.flags |= AV_PKT_FLAG_KEY; write_frame(s, &pkt, ost); video_size += pkt.size; } else { int got_packet; AVFrame big_picture; big_picture = *in_picture; /* better than nothing: use input picture interlaced settings */ big_picture.interlaced_frame = in_picture->interlaced_frame; if (ost->st->codec->flags & (CODEC_FLAG_INTERLACED_DCT|CODEC_FLAG_INTERLACED_ME)) { if (ost->top_field_first == -1) big_picture.top_field_first = in_picture->top_field_first; else big_picture.top_field_first = !!ost->top_field_first; } /* handles same_quant here. This is not correct because it may not be a global option */ big_picture.quality = quality; if (!enc->me_threshold) big_picture.pict_type = 0; if (ost->forced_kf_index < ost->forced_kf_count && big_picture.pts >= ost->forced_kf_pts[ost->forced_kf_index]) { big_picture.pict_type = AV_PICTURE_TYPE_I; ost->forced_kf_index++; } update_benchmark(NULL); ret = avcodec_encode_video2(enc, &pkt, &big_picture, &got_packet); update_benchmark("encode_video %d.%d", ost->file_index, ost->index); if (ret < 0) { av_log(NULL, AV_LOG_FATAL, "Video encoding failed\n"); exit_program(1); } if (got_packet) { if (pkt.pts == AV_NOPTS_VALUE && !(enc->codec->capabilities & CODEC_CAP_DELAY)) pkt.pts = ost->sync_opts; if (pkt.pts != AV_NOPTS_VALUE) pkt.pts = av_rescale_q(pkt.pts, enc->time_base, ost->st->time_base); if (pkt.dts != AV_NOPTS_VALUE) pkt.dts = av_rescale_q(pkt.dts, enc->time_base, ost->st->time_base); if (debug_ts) { av_log(NULL, AV_LOG_INFO, "encoder -> type:video " "pkt_pts:%s pkt_pts_time:%s pkt_dts:%s pkt_dts_time:%s\n", av_ts2str(pkt.pts), av_ts2timestr(pkt.pts, &ost->st->time_base), av_ts2str(pkt.dts), av_ts2timestr(pkt.dts, &ost->st->time_base)); } write_frame(s, &pkt, ost); frame_size = pkt.size; video_size += pkt.size; av_free_packet(&pkt); /* if two pass, output log */ if (ost->logfile && enc->stats_out) { fprintf(ost->logfile, "%s", enc->stats_out); } } } ost->sync_opts++; /* * For video, number of frames in == number of packets out. * But there may be reordering, so we can't throw away frames on encoder * flush, we need to limit them here, before they go into encoder. */ ost->frame_number++; } if (vstats_filename && frame_size) do_video_stats(output_files[ost->file_index]->ctx, ost, frame_size); } static double psnr(double d) { return -10.0 * log(d) / log(10.0); } static void do_video_stats(AVFormatContext *os, OutputStream *ost, int frame_size) { AVCodecContext *enc; int frame_number; double ti1, bitrate, avg_bitrate; /* this is executed just the first time do_video_stats is called */ if (!vstats_file) { vstats_file = fopen(vstats_filename, "w"); if (!vstats_file) { perror("fopen"); exit_program(1); } } enc = ost->st->codec; if (enc->codec_type == AVMEDIA_TYPE_VIDEO) { frame_number = ost->frame_number; fprintf(vstats_file, "frame= %5d q= %2.1f ", frame_number, enc->coded_frame->quality / (float)FF_QP2LAMBDA); if (enc->flags&CODEC_FLAG_PSNR) fprintf(vstats_file, "PSNR= %6.2f ", psnr(enc->coded_frame->error[0] / (enc->width * enc->height * 255.0 * 255.0))); fprintf(vstats_file,"f_size= %6d ", frame_size); /* compute pts value */ ti1 = ost->sync_opts * av_q2d(enc->time_base); if (ti1 < 0.01) ti1 = 0.01; bitrate = (frame_size * 8) / av_q2d(enc->time_base) / 1000.0; avg_bitrate = (double)(video_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)video_size / 1024, ti1, bitrate, avg_bitrate); fprintf(vstats_file, "type= %c\n", av_get_picture_type_char(enc->coded_frame->pict_type)); } } /* check for new output on any of the filtergraphs */ static int poll_filters(void) { AVFilterBufferRef *picref; AVFrame *filtered_frame = NULL; int i, ret, ret_all; unsigned nb_success = 1, av_uninit(nb_eof); int64_t frame_pts; while (1) { /* 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]; int ret = 0; if (!ost->filter) continue; if (!ost->filtered_frame && !(ost->filtered_frame = avcodec_alloc_frame())) { return AVERROR(ENOMEM); } else avcodec_get_frame_defaults(ost->filtered_frame); filtered_frame = ost->filtered_frame; while (1) { ret = av_buffersink_get_buffer_ref(ost->filter->filter, &picref, AV_BUFFERSINK_FLAG_NO_REQUEST); if (ret < 0) { if (ret != AVERROR(EAGAIN) && ret != AVERROR_EOF) { char buf[256]; av_strerror(ret, buf, sizeof(buf)); av_log(NULL, AV_LOG_WARNING, "Error in av_buffersink_get_buffer_ref(): %s\n", buf); } break; } frame_pts = AV_NOPTS_VALUE; if (picref->pts != AV_NOPTS_VALUE) { filtered_frame->pts = frame_pts = av_rescale_q(picref->pts, ost->filter->filter->inputs[0]->time_base, ost->st->codec->time_base) - av_rescale_q(of->start_time, AV_TIME_BASE_Q, ost->st->codec->time_base); if (of->start_time && filtered_frame->pts < 0) { avfilter_unref_buffer(picref); continue; } } //if (ost->source_index >= 0) // *filtered_frame= *input_streams[ost->source_index]->decoded_frame; //for me_threshold switch (ost->filter->filter->inputs[0]->type) { case AVMEDIA_TYPE_VIDEO: avfilter_copy_buf_props(filtered_frame, picref); filtered_frame->pts = frame_pts; if (!ost->frame_aspect_ratio) ost->st->codec->sample_aspect_ratio = picref->video->sample_aspect_ratio; do_video_out(of->ctx, ost, filtered_frame, same_quant ? ost->last_quality : ost->st->codec->global_quality); break; case AVMEDIA_TYPE_AUDIO: avfilter_copy_buf_props(filtered_frame, picref); filtered_frame->pts = frame_pts; do_audio_out(of->ctx, ost, filtered_frame); break; default: // TODO support subtitle filters av_assert0(0); } avfilter_unref_buffer(picref); } } if (!nb_success) /* from last round */ break; /* Request frames through all the graphs */ ret_all = nb_success = nb_eof = 0; for (i = 0; i < nb_filtergraphs; i++) { ret = avfilter_graph_request_oldest(filtergraphs[i]->graph); if (!ret) { nb_success++; } else if (ret == AVERROR_EOF) { nb_eof++; } else if (ret != AVERROR(EAGAIN)) { char buf[256]; av_strerror(ret, buf, sizeof(buf)); av_log(NULL, AV_LOG_WARNING, "Error in request_frame(): %s\n", buf); ret_all = ret; } } /* Try again if anything succeeded */ } return nb_eof == nb_filtergraphs ? AVERROR_EOF : ret_all; } static void print_report(int is_last_report, int64_t timer_start, int64_t cur_time) { char buf[1024]; AVBPrint buf_script; OutputStream *ost; AVFormatContext *oc; int64_t total_size; AVCodecContext *enc; int frame_number, vid, i; double bitrate; int64_t pts = INT64_MAX; static int64_t last_time = -1; static int qp_histogram[52]; int hours, mins, secs, us; if (!print_stats && !is_last_report && !progress_avio) return; if (!is_last_report) { if (last_time == -1) { last_time = cur_time; return; } if ((cur_time - last_time) < 500000) return; last_time = cur_time; } oc = output_files[0]->ctx; total_size = avio_size(oc->pb); if (total_size < 0) { // FIXME improve avio_size() so it works with non seekable output too total_size = avio_tell(oc->pb); if (total_size < 0) total_size = 0; } buf[0] = '\0'; vid = 0; av_bprint_init(&buf_script, 0, 1); for (i = 0; i < nb_output_streams; i++) { float q = -1; ost = output_streams[i]; enc = ost->st->codec; if (!ost->stream_copy && enc->coded_frame) q = enc->coded_frame->quality / (float)FF_QP2LAMBDA; if (vid && enc->codec_type == AVMEDIA_TYPE_VIDEO) { snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf), "q=%2.1f ", q); av_bprintf(&buf_script, "stream_%d_%d_q=%.1f\n", ost->file_index, ost->index, q); } if (!vid && enc->codec_type == AVMEDIA_TYPE_VIDEO) { float fps, t = (cur_time-timer_start) / 1000000.0; frame_number = ost->frame_number; fps = t > 1 ? frame_number / t : 0; snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf), "frame=%5d fps=%3.*f q=%3.1f ", frame_number, fps < 9.95, fps, q); av_bprintf(&buf_script, "frame=%d\n", frame_number); av_bprintf(&buf_script, "fps=%.1f\n", fps); av_bprintf(&buf_script, "stream_%d_%d_q=%.1f\n", ost->file_index, ost->index, q); if (is_last_report) snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf), "L"); if (qp_hist) { int j; int qp = lrintf(q); if (qp >= 0 && qp < FF_ARRAY_ELEMS(qp_histogram)) qp_histogram[qp]++; for (j = 0; j < 32; j++) snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf), "%X", (int)lrintf(log(qp_histogram[j] + 1) / log(2))); } if (enc->flags&CODEC_FLAG_PSNR) { int j; double error, error_sum = 0; double scale, scale_sum = 0; double p; char type[3] = { 'Y','U','V' }; snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf), "PSNR="); for (j = 0; j < 3; j++) { if (is_last_report) { error = enc->error[j]; scale = enc->width * enc->height * 255.0 * 255.0 * frame_number; } else { error = enc->coded_frame->error[j]; scale = enc->width * enc->height * 255.0 * 255.0; } if (j) scale /= 4; error_sum += error; scale_sum += scale; p = psnr(error / scale); snprintf(buf + strlen(buf), sizeof(buf) - strlen(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[i] | 32, p); } p = psnr(error_sum / scale_sum); snprintf(buf + strlen(buf), sizeof(buf) - strlen(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 */ pts = FFMIN(pts, av_rescale_q(ost->st->pts.val, ost->st->time_base, AV_TIME_BASE_Q)); } secs = pts / AV_TIME_BASE; us = pts % AV_TIME_BASE; mins = secs / 60; secs %= 60; hours = mins / 60; mins %= 60; bitrate = pts ? total_size * 8 / (pts / 1000.0) : 0; snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf), "size=%8.0fkB time=", total_size / 1024.0); snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf), "%02d:%02d:%02d.%02d ", hours, mins, secs, (100 * us) / AV_TIME_BASE); snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf), "bitrate=%6.1fkbits/s", bitrate); av_bprintf(&buf_script, "total_size=%"PRId64"\n", total_size); av_bprintf(&buf_script, "out_time_ms=%"PRId64"\n", pts); av_bprintf(&buf_script, "out_time=%02d:%02d:%02d.%06d\n", hours, mins, secs, us); if (nb_frames_dup || nb_frames_drop) snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf), " dup=%d drop=%d", nb_frames_dup, nb_frames_drop); av_bprintf(&buf_script, "dup_frames=%d\n", nb_frames_dup); av_bprintf(&buf_script, "drop_frames=%d\n", nb_frames_drop); if (print_stats || is_last_report) { av_log(NULL, AV_LOG_INFO, "%s \r", buf); fflush(stderr); } 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) { avio_close(progress_avio); progress_avio = NULL; } } if (is_last_report) { int64_t raw= audio_size + video_size + subtitle_size + extra_size; av_log(NULL, AV_LOG_INFO, "\n"); av_log(NULL, AV_LOG_INFO, "video:%1.0fkB audio:%1.0fkB subtitle:%1.0f global headers:%1.0fkB muxing overhead %f%%\n", video_size / 1024.0, audio_size / 1024.0, subtitle_size / 1024.0, extra_size / 1024.0, 100.0 * (total_size - raw) / raw ); if(video_size + audio_size + subtitle_size + extra_size == 0){ av_log(NULL, AV_LOG_WARNING, "Output file is empty, nothing was encoded (check -ss / -t / -frames parameters if used)\n"); } } } static void flush_encoders(void) { int i, ret; for (i = 0; i < nb_output_streams; i++) { OutputStream *ost = output_streams[i]; AVCodecContext *enc = ost->st->codec; AVFormatContext *os = output_files[ost->file_index]->ctx; int stop_encoding = 0; if (!ost->encoding_needed) continue; if (ost->st->codec->codec_type == AVMEDIA_TYPE_AUDIO && enc->frame_size <= 1) continue; if (ost->st->codec->codec_type == AVMEDIA_TYPE_VIDEO && (os->oformat->flags & AVFMT_RAWPICTURE) && enc->codec->id == AV_CODEC_ID_RAWVIDEO) continue; for (;;) { int (*encode)(AVCodecContext*, AVPacket*, const AVFrame*, int*) = NULL; const char *desc; int64_t *size; switch (ost->st->codec->codec_type) { case AVMEDIA_TYPE_AUDIO: encode = avcodec_encode_audio2; desc = "Audio"; size = &audio_size; break; case AVMEDIA_TYPE_VIDEO: encode = avcodec_encode_video2; desc = "Video"; size = &video_size; break; default: stop_encoding = 1; } if (encode) { AVPacket pkt; int got_packet; av_init_packet(&pkt); pkt.data = NULL; pkt.size = 0; update_benchmark(NULL); ret = encode(enc, &pkt, NULL, &got_packet); update_benchmark("flush %s %d.%d", desc, ost->file_index, ost->index); if (ret < 0) { av_log(NULL, AV_LOG_FATAL, "%s encoding failed\n", desc); exit_program(1); } *size += pkt.size; if (ost->logfile && enc->stats_out) { fprintf(ost->logfile, "%s", enc->stats_out); } if (!got_packet) { stop_encoding = 1; break; } if (pkt.pts != AV_NOPTS_VALUE) pkt.pts = av_rescale_q(pkt.pts, enc->time_base, ost->st->time_base); if (pkt.dts != AV_NOPTS_VALUE) pkt.dts = av_rescale_q(pkt.dts, enc->time_base, ost->st->time_base); write_frame(os, &pkt, ost); } if (stop_encoding) break; } } } /* * Check whether a packet from ist should be written into ost at this time */ static int check_output_constraints(InputStream *ist, OutputStream *ost) { OutputFile *of = output_files[ost->file_index]; int ist_index = input_files[ist->file_index]->ist_index + ist->st->index; if (ost->source_index != ist_index) return 0; if (of->start_time && ist->pts < of->start_time) return 0; return 1; } static void do_streamcopy(InputStream *ist, OutputStream *ost, const AVPacket *pkt) { OutputFile *of = output_files[ost->file_index]; int64_t ost_tb_start_time = av_rescale_q(of->start_time, AV_TIME_BASE_Q, ost->st->time_base); AVPicture pict; AVPacket opkt; av_init_packet(&opkt); if ((!ost->frame_number && !(pkt->flags & AV_PKT_FLAG_KEY)) && !ost->copy_initial_nonkeyframes) return; if (of->recording_time != INT64_MAX && ist->pts >= of->recording_time + of->start_time) { ost->is_past_recording_time = 1; return; } /* force the input stream PTS */ if (ost->st->codec->codec_type == AVMEDIA_TYPE_AUDIO) audio_size += pkt->size; else if (ost->st->codec->codec_type == AVMEDIA_TYPE_VIDEO) { video_size += pkt->size; ost->sync_opts++; } else if (ost->st->codec->codec_type == AVMEDIA_TYPE_SUBTITLE) { subtitle_size += pkt->size; } if (pkt->pts != AV_NOPTS_VALUE) opkt.pts = av_rescale_q(pkt->pts, ist->st->time_base, ost->st->time_base) - ost_tb_start_time; else opkt.pts = AV_NOPTS_VALUE; if (pkt->dts == AV_NOPTS_VALUE) opkt.dts = av_rescale_q(ist->dts, AV_TIME_BASE_Q, ost->st->time_base); else opkt.dts = av_rescale_q(pkt->dts, ist->st->time_base, ost->st->time_base); opkt.dts -= ost_tb_start_time; opkt.duration = av_rescale_q(pkt->duration, ist->st->time_base, ost->st->time_base); opkt.flags = pkt->flags; // FIXME remove the following 2 lines they shall be replaced by the bitstream filters if ( ost->st->codec->codec_id != AV_CODEC_ID_H264 && ost->st->codec->codec_id != AV_CODEC_ID_MPEG1VIDEO && ost->st->codec->codec_id != AV_CODEC_ID_MPEG2VIDEO && ost->st->codec->codec_id != AV_CODEC_ID_VC1 ) { if (av_parser_change(ist->st->parser, ost->st->codec, &opkt.data, &opkt.size, pkt->data, pkt->size, pkt->flags & AV_PKT_FLAG_KEY)) opkt.destruct = av_destruct_packet; } else { opkt.data = pkt->data; opkt.size = pkt->size; } if (ost->st->codec->codec_type == AVMEDIA_TYPE_VIDEO && (of->ctx->oformat->flags & AVFMT_RAWPICTURE)) { /* store AVPicture in AVPacket, as expected by the output format */ avpicture_fill(&pict, opkt.data, ost->st->codec->pix_fmt, ost->st->codec->width, ost->st->codec->height); opkt.data = (uint8_t *)&pict; opkt.size = sizeof(AVPicture); opkt.flags |= AV_PKT_FLAG_KEY; } write_frame(of->ctx, &opkt, ost); ost->st->codec->frame_number++; av_free_packet(&opkt); } static void rate_emu_sleep(InputStream *ist) { if (input_files[ist->file_index]->rate_emu) { int64_t pts = av_rescale(ist->dts, 1000000, AV_TIME_BASE); int64_t now = av_gettime() - ist->start; if (pts > now) av_usleep(pts - now); } } static int guess_input_channel_layout(InputStream *ist) { AVCodecContext *dec = ist->st->codec; if (!dec->channel_layout) { char layout_name[256]; dec->channel_layout = av_get_default_channel_layout(dec->channels); if (!dec->channel_layout) return 0; av_get_channel_layout_string(layout_name, sizeof(layout_name), dec->channels, dec->channel_layout); av_log(NULL, AV_LOG_WARNING, "Guessed Channel Layout for Input Stream " "#%d.%d : %s\n", ist->file_index, ist->st->index, layout_name); } return 1; } static int decode_audio(InputStream *ist, AVPacket *pkt, int *got_output) { AVFrame *decoded_frame; AVCodecContext *avctx = ist->st->codec; int i, ret, resample_changed; AVRational decoded_frame_tb; if (!ist->decoded_frame && !(ist->decoded_frame = avcodec_alloc_frame())) return AVERROR(ENOMEM); else avcodec_get_frame_defaults(ist->decoded_frame); decoded_frame = ist->decoded_frame; update_benchmark(NULL); ret = avcodec_decode_audio4(avctx, decoded_frame, got_output, pkt); update_benchmark("decode_audio %d.%d", ist->file_index, ist->st->index); if (ret < 0) { return ret; } if (avctx->sample_rate <= 0) { av_log(avctx, AV_LOG_ERROR, "Sample rate %d invalid\n", avctx->sample_rate); return AVERROR_INVALIDDATA; } if (!*got_output) { /* no audio frame */ if (!pkt->size) for (i = 0; i < ist->nb_filters; i++) av_buffersrc_add_ref(ist->filters[i]->filter, NULL, AV_BUFFERSRC_FLAG_NO_COPY); return ret; } #if 1 /* 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; #endif rate_emu_sleep(ist); resample_changed = ist->resample_sample_fmt != decoded_frame->format || ist->resample_channels != avctx->channels || ist->resample_channel_layout != decoded_frame->channel_layout || ist->resample_sample_rate != decoded_frame->sample_rate; if (resample_changed) { char layout1[64], layout2[64]; if (!guess_input_channel_layout(ist)) { av_log(NULL, AV_LOG_FATAL, "Unable to find default channel " "layout for Input Stream #%d.%d\n", ist->file_index, ist->st->index); exit_program(1); } decoded_frame->channel_layout = avctx->channel_layout; av_get_channel_layout_string(layout1, sizeof(layout1), ist->resample_channels, ist->resample_channel_layout); av_get_channel_layout_string(layout2, sizeof(layout2), avctx->channels, decoded_frame->channel_layout); av_log(NULL, AV_LOG_INFO, "Input stream #%d:%d frame changed from rate:%d fmt:%s ch:%d chl:%s to rate:%d fmt:%s ch:%d chl:%s\n", ist->file_index, ist->st->index, ist->resample_sample_rate, av_get_sample_fmt_name(ist->resample_sample_fmt), ist->resample_channels, layout1, decoded_frame->sample_rate, av_get_sample_fmt_name(decoded_frame->format), avctx->channels, layout2); ist->resample_sample_fmt = decoded_frame->format; ist->resample_sample_rate = decoded_frame->sample_rate; ist->resample_channel_layout = decoded_frame->channel_layout; ist->resample_channels = avctx->channels; for (i = 0; i < nb_filtergraphs; i++) if (ist_in_filtergraph(filtergraphs[i], ist)) { FilterGraph *fg = filtergraphs[i]; int j; if (configure_filtergraph(fg) < 0) { av_log(NULL, AV_LOG_FATAL, "Error reinitializing filters!\n"); exit_program(1); } for (j = 0; j < fg->nb_outputs; j++) { OutputStream *ost = fg->outputs[j]->ost; if (ost->enc->type == AVMEDIA_TYPE_AUDIO && !(ost->enc->capabilities & CODEC_CAP_VARIABLE_FRAME_SIZE)) av_buffersink_set_frame_size(ost->filter->filter, ost->st->codec->frame_size); } } } /* if the decoder provides a pts, use it instead of the last packet pts. the decoder could be delaying output by a packet or more. */ if (decoded_frame->pts != AV_NOPTS_VALUE) { ist->dts = ist->next_dts = ist->pts = ist->next_pts = av_rescale_q(decoded_frame->pts, avctx->time_base, AV_TIME_BASE_Q); decoded_frame_tb = avctx->time_base; } else if (decoded_frame->pkt_pts != AV_NOPTS_VALUE) { decoded_frame->pts = decoded_frame->pkt_pts; pkt->pts = AV_NOPTS_VALUE; decoded_frame_tb = ist->st->time_base; } else if (pkt->pts != AV_NOPTS_VALUE) { decoded_frame->pts = pkt->pts; pkt->pts = AV_NOPTS_VALUE; decoded_frame_tb = ist->st->time_base; }else { decoded_frame->pts = ist->dts; decoded_frame_tb = AV_TIME_BASE_Q; } if (decoded_frame->pts != AV_NOPTS_VALUE) decoded_frame->pts = av_rescale_q(decoded_frame->pts, decoded_frame_tb, (AVRational){1, ist->st->codec->sample_rate}); for (i = 0; i < ist->nb_filters; i++) av_buffersrc_add_frame(ist->filters[i]->filter, decoded_frame, 0); decoded_frame->pts = AV_NOPTS_VALUE; return ret; } static int decode_video(InputStream *ist, AVPacket *pkt, int *got_output) { AVFrame *decoded_frame; void *buffer_to_free = NULL; int i, ret = 0, resample_changed; int64_t best_effort_timestamp; AVRational *frame_sample_aspect; float quality; if (!ist->decoded_frame && !(ist->decoded_frame = avcodec_alloc_frame())) return AVERROR(ENOMEM); else avcodec_get_frame_defaults(ist->decoded_frame); decoded_frame = ist->decoded_frame; pkt->dts = av_rescale_q(ist->dts, AV_TIME_BASE_Q, ist->st->time_base); update_benchmark(NULL); ret = avcodec_decode_video2(ist->st->codec, decoded_frame, got_output, pkt); update_benchmark("decode_video %d.%d", ist->file_index, ist->st->index); if (ret < 0) return ret; quality = same_quant ? decoded_frame->quality : 0; if (!*got_output) { /* no picture yet */ if (!pkt->size) for (i = 0; i < ist->nb_filters; i++) av_buffersrc_add_ref(ist->filters[i]->filter, NULL, AV_BUFFERSRC_FLAG_NO_COPY); return ret; } if(ist->top_field_first>=0) decoded_frame->top_field_first = ist->top_field_first; best_effort_timestamp= av_frame_get_best_effort_timestamp(decoded_frame); if(best_effort_timestamp != AV_NOPTS_VALUE) ist->next_pts = ist->pts = av_rescale_q(decoded_frame->pts = best_effort_timestamp, ist->st->time_base, AV_TIME_BASE_Q); 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 \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); } pkt->size = 0; pre_process_video_frame(ist, (AVPicture *)decoded_frame, &buffer_to_free); rate_emu_sleep(ist); if (ist->st->sample_aspect_ratio.num) decoded_frame->sample_aspect_ratio = ist->st->sample_aspect_ratio; resample_changed = ist->resample_width != decoded_frame->width || ist->resample_height != decoded_frame->height || ist->resample_pix_fmt != decoded_frame->format; if (resample_changed) { av_log(NULL, AV_LOG_INFO, "Input stream #%d:%d frame changed from size:%dx%d fmt:%s to size:%dx%d fmt:%s\n", ist->file_index, ist->st->index, ist->resample_width, ist->resample_height, av_get_pix_fmt_name(ist->resample_pix_fmt), decoded_frame->width, decoded_frame->height, av_get_pix_fmt_name(decoded_frame->format)); ist->resample_width = decoded_frame->width; ist->resample_height = decoded_frame->height; ist->resample_pix_fmt = decoded_frame->format; for (i = 0; i < nb_filtergraphs; i++) if (ist_in_filtergraph(filtergraphs[i], ist) && configure_filtergraph(filtergraphs[i]) < 0) { av_log(NULL, AV_LOG_FATAL, "Error reinitializing filters!\n"); exit_program(1); } } frame_sample_aspect= av_opt_ptr(avcodec_get_frame_class(), decoded_frame, "sample_aspect_ratio"); for (i = 0; i < ist->nb_filters; i++) { int changed = ist->st->codec->width != ist->filters[i]->filter->outputs[0]->w || ist->st->codec->height != ist->filters[i]->filter->outputs[0]->h || ist->st->codec->pix_fmt != ist->filters[i]->filter->outputs[0]->format; // XXX what an ugly hack if (ist->filters[i]->graph->nb_outputs == 1) ist->filters[i]->graph->outputs[0]->ost->last_quality = quality; if (!frame_sample_aspect->num) *frame_sample_aspect = ist->st->sample_aspect_ratio; if (ist->dr1 && decoded_frame->type==FF_BUFFER_TYPE_USER && !changed) { FrameBuffer *buf = decoded_frame->opaque; AVFilterBufferRef *fb = avfilter_get_video_buffer_ref_from_arrays( decoded_frame->data, decoded_frame->linesize, AV_PERM_READ | AV_PERM_PRESERVE, ist->st->codec->width, ist->st->codec->height, ist->st->codec->pix_fmt); avfilter_copy_frame_props(fb, decoded_frame); fb->buf->priv = buf; fb->buf->free = filter_release_buffer; av_assert0(buf->refcount>0); buf->refcount++; av_buffersrc_add_ref(ist->filters[i]->filter, fb, AV_BUFFERSRC_FLAG_NO_CHECK_FORMAT | AV_BUFFERSRC_FLAG_NO_COPY); } else if(av_buffersrc_add_frame(ist->filters[i]->filter, decoded_frame, 0)<0) { av_log(NULL, AV_LOG_FATAL, "Failed to inject frame into filter network\n"); exit_program(1); } } av_free(buffer_to_free); return ret; } static int transcode_subtitles(InputStream *ist, AVPacket *pkt, int *got_output) { AVSubtitle subtitle; int i, ret = avcodec_decode_subtitle2(ist->st->codec, &subtitle, got_output, pkt); if (ret < 0 || !*got_output) { if (!pkt->size) sub2video_flush(ist); return ret; } rate_emu_sleep(ist); sub2video_update(ist, &subtitle, pkt->pts); for (i = 0; i < nb_output_streams; i++) { OutputStream *ost = output_streams[i]; if (!check_output_constraints(ist, ost) || !ost->encoding_needed) continue; do_subtitle_out(output_files[ost->file_index]->ctx, ost, ist, &subtitle, pkt->pts); } avsubtitle_free(&subtitle); return ret; } /* pkt = NULL means EOF (needed to flush decoder buffers) */ static int output_packet(InputStream *ist, const AVPacket *pkt) { int ret = 0, i; int got_output; AVPacket avpkt; if (!ist->saw_first_ts) { ist->dts = ist->st->avg_frame_rate.num ? - ist->st->codec->has_b_frames * AV_TIME_BASE / av_q2d(ist->st->avg_frame_rate) : 0; ist->pts = 0; if (pkt != NULL && pkt->pts != AV_NOPTS_VALUE && !ist->decoding_needed) { 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 == NULL) { /* EOF handling */ av_init_packet(&avpkt); avpkt.data = NULL; avpkt.size = 0; goto handle_eof; } else { avpkt = *pkt; } if (pkt->dts != AV_NOPTS_VALUE) { ist->next_dts = ist->dts = av_rescale_q(pkt->dts, ist->st->time_base, AV_TIME_BASE_Q); if (ist->st->codec->codec_type != AVMEDIA_TYPE_VIDEO || !ist->decoding_needed) ist->next_pts = ist->pts = av_rescale_q(pkt->dts, ist->st->time_base, AV_TIME_BASE_Q); } // while we have more to decode or while the decoder did output something on EOF while (ist->decoding_needed && (avpkt.size > 0 || (!pkt && got_output))) { int duration; handle_eof: ist->pts = ist->next_pts; ist->dts = ist->next_dts; if (avpkt.size && avpkt.size != pkt->size) { av_log(NULL, ist->showed_multi_packet_warning ? AV_LOG_VERBOSE : AV_LOG_WARNING, "Multiple frames in a packet from stream %d\n", pkt->stream_index); ist->showed_multi_packet_warning = 1; } switch (ist->st->codec->codec_type) { case AVMEDIA_TYPE_AUDIO: ret = decode_audio (ist, &avpkt, &got_output); break; case AVMEDIA_TYPE_VIDEO: ret = decode_video (ist, &avpkt, &got_output); if (avpkt.duration) { duration = av_rescale_q(avpkt.duration, ist->st->time_base, AV_TIME_BASE_Q); } else if(ist->st->codec->time_base.num != 0 && ist->st->codec->time_base.den != 0) { int ticks= ist->st->parser ? ist->st->parser->repeat_pict+1 : ist->st->codec->ticks_per_frame; duration = ((int64_t)AV_TIME_BASE * ist->st->codec->time_base.num * ticks) / ist->st->codec->time_base.den; } else duration = 0; if(ist->dts != AV_NOPTS_VALUE && duration) { ist->next_dts += duration; }else ist->next_dts = AV_NOPTS_VALUE; if (got_output) ist->next_pts += duration; //FIXME the duration is not correct in some cases break; case AVMEDIA_TYPE_SUBTITLE: ret = transcode_subtitles(ist, &avpkt, &got_output); break; default: return -1; } if (ret < 0) return ret; avpkt.dts= avpkt.pts= AV_NOPTS_VALUE; // touch data and size only if not EOF if (pkt) { if(ist->st->codec->codec_type != AVMEDIA_TYPE_AUDIO) ret = avpkt.size; avpkt.data += ret; avpkt.size -= ret; } if (!got_output) { continue; } } /* handle stream copy */ if (!ist->decoding_needed) { rate_emu_sleep(ist); ist->dts = ist->next_dts; switch (ist->st->codec->codec_type) { case AVMEDIA_TYPE_AUDIO: ist->next_dts += ((int64_t)AV_TIME_BASE * ist->st->codec->frame_size) / ist->st->codec->sample_rate; break; case AVMEDIA_TYPE_VIDEO: if (pkt->duration) { ist->next_dts += av_rescale_q(pkt->duration, ist->st->time_base, AV_TIME_BASE_Q); } else if(ist->st->codec->time_base.num != 0) { int ticks= ist->st->parser ? ist->st->parser->repeat_pict + 1 : ist->st->codec->ticks_per_frame; ist->next_dts += ((int64_t)AV_TIME_BASE * ist->st->codec->time_base.num * ticks) / ist->st->codec->time_base.den; } break; } ist->pts = ist->dts; ist->next_pts = ist->next_dts; } for (i = 0; pkt && i < nb_output_streams; i++) { OutputStream *ost = output_streams[i]; if (!check_output_constraints(ist, ost) || ost->encoding_needed) continue; do_streamcopy(ist, ost, pkt); } return 0; } static void print_sdp(void) { char sdp[2048]; int i; AVFormatContext **avc = av_malloc(sizeof(*avc) * nb_output_files); if (!avc) exit_program(1); for (i = 0; i < nb_output_files; i++) avc[i] = output_files[i]->ctx; av_sdp_create(avc, nb_output_files, sdp, sizeof(sdp)); printf("SDP:\n%s\n", sdp); fflush(stdout); av_freep(&avc); } static int init_input_stream(int ist_index, char *error, int error_len) { InputStream *ist = input_streams[ist_index]; if (ist->decoding_needed) { AVCodec *codec = ist->dec; if (!codec) { snprintf(error, error_len, "Decoder (codec %s) not found for input stream #%d:%d", avcodec_get_name(ist->st->codec->codec_id), ist->file_index, ist->st->index); return AVERROR(EINVAL); } ist->dr1 = (codec->capabilities & CODEC_CAP_DR1) && !do_deinterlace; if (codec->type == AVMEDIA_TYPE_VIDEO && ist->dr1) { ist->st->codec->get_buffer = codec_get_buffer; ist->st->codec->release_buffer = codec_release_buffer; ist->st->codec->opaque = &ist->buffer_pool; } if (!av_dict_get(ist->opts, "threads", NULL, 0)) av_dict_set(&ist->opts, "threads", "auto", 0); if (avcodec_open2(ist->st->codec, codec, &ist->opts) < 0) { snprintf(error, error_len, "Error while opening decoder for input stream #%d:%d", ist->file_index, ist->st->index); return AVERROR(EINVAL); } assert_codec_experimental(ist->st->codec, 0); assert_avoptions(ist->opts); } ist->next_pts = AV_NOPTS_VALUE; ist->next_dts = AV_NOPTS_VALUE; ist->is_start = 1; return 0; } static InputStream *get_input_stream(OutputStream *ost) { if (ost->source_index >= 0) return input_streams[ost->source_index]; return NULL; } static void parse_forced_key_frames(char *kf, OutputStream *ost, AVCodecContext *avctx) { char *p; int n = 1, i; int64_t t; for (p = kf; *p; p++) if (*p == ',') n++; ost->forced_kf_count = n; ost->forced_kf_pts = av_malloc(sizeof(*ost->forced_kf_pts) * n); if (!ost->forced_kf_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; t = parse_time_or_die("force_key_frames", p, 1); ost->forced_kf_pts[i] = av_rescale_q(t, AV_TIME_BASE_Q, avctx->time_base); p = next; } } static void report_new_stream(int input_index, AVPacket *pkt) { InputFile *file = input_files[input_index]; AVStream *st = file->ctx->streams[pkt->stream_index]; if (pkt->stream_index < file->nb_streams_warn) return; av_log(file->ctx, AV_LOG_WARNING, "New %s stream %d:%d at pos:%"PRId64" and DTS:%ss\n", av_get_media_type_string(st->codec->codec_type), input_index, pkt->stream_index, pkt->pos, av_ts2timestr(pkt->dts, &st->time_base)); file->nb_streams_warn = pkt->stream_index + 1; } static int transcode_init(void) { int ret = 0, i, j, k; AVFormatContext *oc; AVCodecContext *codec, *icodec = NULL; OutputStream *ost; InputStream *ist; char error[1024]; int want_sdp = 1; /* init framerate emulation */ for (i = 0; i < nb_input_files; i++) { InputFile *ifile = input_files[i]; if (ifile->rate_emu) for (j = 0; j < ifile->nb_streams; j++) input_streams[j + ifile->ist_index]->start = av_gettime(); } /* output stream init */ for (i = 0; i < nb_output_files; i++) { oc = output_files[i]->ctx; if (!oc->nb_streams && !(oc->oformat->flags & AVFMT_NOSTREAMS)) { av_dump_format(oc, i, oc->filename, 1); av_log(NULL, AV_LOG_ERROR, "Output file #%d does not contain any stream\n", i); return AVERROR(EINVAL); } } /* init complex filtergraphs */ for (i = 0; i < nb_filtergraphs; i++) if ((ret = avfilter_graph_config(filtergraphs[i]->graph, NULL)) < 0) return ret; /* for each output stream, we compute the right encoding parameters */ for (i = 0; i < nb_output_streams; i++) { ost = output_streams[i]; oc = output_files[ost->file_index]->ctx; ist = get_input_stream(ost); if (ost->attachment_filename) continue; codec = ost->st->codec; if (ist) { icodec = ist->st->codec; ost->st->disposition = ist->st->disposition; codec->bits_per_raw_sample = icodec->bits_per_raw_sample; codec->chroma_sample_location = icodec->chroma_sample_location; } if (ost->stream_copy) { uint64_t extra_size; av_assert0(ist && !ost->filter); extra_size = (uint64_t)icodec->extradata_size + FF_INPUT_BUFFER_PADDING_SIZE; if (extra_size > INT_MAX) { return AVERROR(EINVAL); } /* if stream_copy is selected, no need to decode or encode */ codec->codec_id = icodec->codec_id; codec->codec_type = icodec->codec_type; if (!codec->codec_tag) { if (!oc->oformat->codec_tag || av_codec_get_id (oc->oformat->codec_tag, icodec->codec_tag) == codec->codec_id || av_codec_get_tag(oc->oformat->codec_tag, icodec->codec_id) <= 0) codec->codec_tag = icodec->codec_tag; } codec->bit_rate = icodec->bit_rate; codec->rc_max_rate = icodec->rc_max_rate; codec->rc_buffer_size = icodec->rc_buffer_size; codec->field_order = icodec->field_order; codec->extradata = av_mallocz(extra_size); if (!codec->extradata) { return AVERROR(ENOMEM); } memcpy(codec->extradata, icodec->extradata, icodec->extradata_size); codec->extradata_size= icodec->extradata_size; codec->bits_per_coded_sample = icodec->bits_per_coded_sample; codec->time_base = ist->st->time_base; /* * Avi is a special case here because it supports variable fps but * having the fps and timebase differe significantly adds quite some * overhead */ if(!strcmp(oc->oformat->name, "avi")) { if ( copy_tb<0 && av_q2d(ist->st->r_frame_rate) >= av_q2d(ist->st->avg_frame_rate) && 0.5/av_q2d(ist->st->r_frame_rate) > av_q2d(ist->st->time_base) && 0.5/av_q2d(ist->st->r_frame_rate) > av_q2d(icodec->time_base) && av_q2d(ist->st->time_base) < 1.0/500 && av_q2d(icodec->time_base) < 1.0/500 || copy_tb==2){ codec->time_base.num = ist->st->r_frame_rate.den; codec->time_base.den = 2*ist->st->r_frame_rate.num; codec->ticks_per_frame = 2; } else if ( copy_tb<0 && av_q2d(icodec->time_base)*icodec->ticks_per_frame > 2*av_q2d(ist->st->time_base) && av_q2d(ist->st->time_base) < 1.0/500 || copy_tb==0){ codec->time_base = icodec->time_base; codec->time_base.num *= icodec->ticks_per_frame; codec->time_base.den *= 2; codec->ticks_per_frame = 2; } } else if(!(oc->oformat->flags & AVFMT_VARIABLE_FPS) && strcmp(oc->oformat->name, "mov") && strcmp(oc->oformat->name, "mp4") && strcmp(oc->oformat->name, "3gp") && strcmp(oc->oformat->name, "3g2") && strcmp(oc->oformat->name, "psp") && strcmp(oc->oformat->name, "ipod") ) { if( copy_tb<0 && av_q2d(icodec->time_base)*icodec->ticks_per_frame > av_q2d(ist->st->time_base) && av_q2d(ist->st->time_base) < 1.0/500 || copy_tb==0){ codec->time_base = icodec->time_base; codec->time_base.num *= icodec->ticks_per_frame; } } if(ost->frame_rate.num) codec->time_base = av_inv_q(ost->frame_rate); av_reduce(&codec->time_base.num, &codec->time_base.den, codec->time_base.num, codec->time_base.den, INT_MAX); switch (codec->codec_type) { case AVMEDIA_TYPE_AUDIO: if (audio_volume != 256) { av_log(NULL, AV_LOG_FATAL, "-acodec copy and -vol are incompatible (frames are not decoded)\n"); exit_program(1); } codec->channel_layout = icodec->channel_layout; codec->sample_rate = icodec->sample_rate; codec->channels = icodec->channels; codec->frame_size = icodec->frame_size; codec->audio_service_type = icodec->audio_service_type; codec->block_align = icodec->block_align; if((codec->block_align == 1 || codec->block_align == 1152) && codec->codec_id == AV_CODEC_ID_MP3) codec->block_align= 0; if(codec->codec_id == AV_CODEC_ID_AC3) codec->block_align= 0; break; case AVMEDIA_TYPE_VIDEO: codec->pix_fmt = icodec->pix_fmt; codec->width = icodec->width; codec->height = icodec->height; codec->has_b_frames = icodec->has_b_frames; if (!codec->sample_aspect_ratio.num) { codec->sample_aspect_ratio = ost->st->sample_aspect_ratio = ist->st->sample_aspect_ratio.num ? ist->st->sample_aspect_ratio : ist->st->codec->sample_aspect_ratio.num ? ist->st->codec->sample_aspect_ratio : (AVRational){0, 1}; } ost->st->avg_frame_rate = ist->st->avg_frame_rate; break; case AVMEDIA_TYPE_SUBTITLE: codec->width = icodec->width; codec->height = icodec->height; break; case AVMEDIA_TYPE_DATA: case AVMEDIA_TYPE_ATTACHMENT: break; default: abort(); } } else { if (!ost->enc) ost->enc = avcodec_find_encoder(codec->codec_id); if (!ost->enc) { /* should only happen when a default codec is not present. */ snprintf(error, sizeof(error), "Encoder (codec %s) not found for output stream #%d:%d", avcodec_get_name(ost->st->codec->codec_id), ost->file_index, ost->index); ret = AVERROR(EINVAL); goto dump_format; } if (ist) ist->decoding_needed = 1; ost->encoding_needed = 1; if (!ost->filter && (codec->codec_type == AVMEDIA_TYPE_VIDEO || codec->codec_type == AVMEDIA_TYPE_AUDIO)) { FilterGraph *fg; fg = init_simple_filtergraph(ist, ost); if (configure_filtergraph(fg)) { av_log(NULL, AV_LOG_FATAL, "Error opening filters!\n"); exit(1); } } if (codec->codec_type == AVMEDIA_TYPE_VIDEO) { if (ost->filter && !ost->frame_rate.num) ost->frame_rate = av_buffersink_get_frame_rate(ost->filter->filter); if (ist && !ost->frame_rate.num) ost->frame_rate = ist->st->r_frame_rate.num ? ist->st->r_frame_rate : (AVRational){25, 1}; // ost->frame_rate = ist->st->avg_frame_rate.num ? ist->st->avg_frame_rate : (AVRational){25, 1}; if (ost->enc && 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]; } } switch (codec->codec_type) { case AVMEDIA_TYPE_AUDIO: codec->sample_fmt = ost->filter->filter->inputs[0]->format; codec->sample_rate = ost->filter->filter->inputs[0]->sample_rate; codec->channel_layout = ost->filter->filter->inputs[0]->channel_layout; codec->channels = av_get_channel_layout_nb_channels(codec->channel_layout); codec->time_base = (AVRational){ 1, codec->sample_rate }; break; case AVMEDIA_TYPE_VIDEO: codec->time_base = av_inv_q(ost->frame_rate); if (ost->filter && !(codec->time_base.num && codec->time_base.den)) codec->time_base = ost->filter->filter->inputs[0]->time_base; if ( av_q2d(codec->time_base) < 0.001 && video_sync_method != VSYNC_PASSTHROUGH && (video_sync_method == VSYNC_CFR || (video_sync_method == VSYNC_AUTO && !(oc->oformat->flags & AVFMT_VARIABLE_FPS)))){ av_log(oc, 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 -vsync 2\n"); } for (j = 0; j < ost->forced_kf_count; j++) ost->forced_kf_pts[j] = av_rescale_q(ost->forced_kf_pts[j], AV_TIME_BASE_Q, codec->time_base); codec->width = ost->filter->filter->inputs[0]->w; codec->height = ost->filter->filter->inputs[0]->h; codec->sample_aspect_ratio = ost->st->sample_aspect_ratio = ost->frame_aspect_ratio ? // overridden by the -aspect cli option av_d2q(ost->frame_aspect_ratio * codec->height/codec->width, 255) : ost->filter->filter->inputs[0]->sample_aspect_ratio; codec->pix_fmt = ost->filter->filter->inputs[0]->format; if (!icodec || codec->width != icodec->width || codec->height != icodec->height || codec->pix_fmt != icodec->pix_fmt) { codec->bits_per_raw_sample = frame_bits_per_raw_sample; } if (ost->forced_keyframes) parse_forced_key_frames(ost->forced_keyframes, ost, ost->st->codec); break; case AVMEDIA_TYPE_SUBTITLE: codec->time_base = (AVRational){1, 1000}; break; default: abort(); break; } /* two pass mode */ if (codec->flags & (CODEC_FLAG_PASS1 | CODEC_FLAG_PASS2)) { char logfilename[1024]; FILE *f; snprintf(logfilename, sizeof(logfilename), "%s-%d.log", pass_logfilename_prefix ? pass_logfilename_prefix : DEFAULT_PASS_LOGFILENAME_PREFIX, i); if (!strcmp(ost->enc->name, "libx264")) { av_dict_set(&ost->opts, "stats", logfilename, AV_DICT_DONT_OVERWRITE); } else { if (codec->flags & CODEC_FLAG_PASS2) { char *logbuffer; size_t logbuffer_size; if (cmdutils_read_file(logfilename, &logbuffer, &logbuffer_size) < 0) { av_log(NULL, AV_LOG_FATAL, "Error reading log file '%s' for pass-2 encoding\n", logfilename); exit_program(1); } codec->stats_in = logbuffer; } if (codec->flags & CODEC_FLAG_PASS1) { f = fopen(logfilename, "wb"); if (!f) { av_log(NULL, AV_LOG_FATAL, "Cannot write log file '%s' for pass-1 encoding: %s\n", logfilename, strerror(errno)); exit_program(1); } ost->logfile = f; } } } } } /* open each encoder */ for (i = 0; i < nb_output_streams; i++) { ost = output_streams[i]; if (ost->encoding_needed) { AVCodec *codec = ost->enc; AVCodecContext *dec = NULL; if ((ist = get_input_stream(ost))) dec = ist->st->codec; if (dec && dec->subtitle_header) { /* ASS code assumes this buffer is null terminated so add extra byte. */ ost->st->codec->subtitle_header = av_mallocz(dec->subtitle_header_size + 1); if (!ost->st->codec->subtitle_header) { ret = AVERROR(ENOMEM); goto dump_format; } memcpy(ost->st->codec->subtitle_header, dec->subtitle_header, dec->subtitle_header_size); ost->st->codec->subtitle_header_size = dec->subtitle_header_size; } if (!av_dict_get(ost->opts, "threads", NULL, 0)) av_dict_set(&ost->opts, "threads", "auto", 0); if (avcodec_open2(ost->st->codec, codec, &ost->opts) < 0) { snprintf(error, sizeof(error), "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); ret = AVERROR(EINVAL); goto dump_format; } if (ost->enc->type == AVMEDIA_TYPE_AUDIO && !(ost->enc->capabilities & CODEC_CAP_VARIABLE_FRAME_SIZE)) av_buffersink_set_frame_size(ost->filter->filter, ost->st->codec->frame_size); assert_codec_experimental(ost->st->codec, 1); assert_avoptions(ost->opts); if (ost->st->codec->bit_rate && ost->st->codec->bit_rate < 1000) av_log(NULL, AV_LOG_WARNING, "The bitrate parameter is set too low." " It takes bits/s as argument, not kbits/s\n"); extra_size += ost->st->codec->extradata_size; if (ost->st->codec->me_threshold) input_streams[ost->source_index]->st->codec->debug |= FF_DEBUG_MV; } } /* init input streams */ for (i = 0; i < nb_input_streams; i++) if ((ret = init_input_stream(i, error, sizeof(error))) < 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; } } /* open files and write file headers */ for (i = 0; i < nb_output_files; i++) { oc = output_files[i]->ctx; oc->interrupt_callback = int_cb; if ((ret = avformat_write_header(oc, &output_files[i]->opts)) < 0) { char errbuf[128]; const char *errbuf_ptr = errbuf; if (av_strerror(ret, errbuf, sizeof(errbuf)) < 0) errbuf_ptr = strerror(AVUNERROR(ret)); snprintf(error, sizeof(error), "Could not write header for output file #%d (incorrect codec parameters ?): %s", i, errbuf_ptr); ret = AVERROR(EINVAL); goto dump_format; } // assert_avoptions(output_files[i]->opts); if (strcmp(oc->oformat->name, "rtp")) { want_sdp = 0; } } dump_format: /* dump the file output parameters - cannot be done before in case of stream copy */ for (i = 0; i < nb_output_files; i++) { av_dump_format(output_files[i]->ctx, i, output_files[i]->ctx->filename, 1); } /* 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 (ist->filters[j]->graph->graph_desc) { 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 && ost->filter->graph->graph_desc) { /* 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->sync_ist != input_streams[ost->source_index]) av_log(NULL, AV_LOG_INFO, " [sync #%d:%d]", ost->sync_ist->file_index, ost->sync_ist->st->index); if (ost->stream_copy) av_log(NULL, AV_LOG_INFO, " (copy)"); else av_log(NULL, AV_LOG_INFO, " (%s -> %s)", input_streams[ost->source_index]->dec ? input_streams[ost->source_index]->dec->name : "?", ost->enc ? ost->enc->name : "?"); av_log(NULL, AV_LOG_INFO, "\n"); } if (ret) { av_log(NULL, AV_LOG_ERROR, "%s\n", error); return ret; } if (want_sdp) { print_sdp(); } return 0; } /** * @return 1 if there are still 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]; OutputFile *of = output_files[ost->file_index]; AVFormatContext *os = output_files[ost->file_index]->ctx; if (ost->is_past_recording_time || (os->pb && avio_tell(os->pb) >= of->limit_filesize)) continue; if (ost->frame_number >= ost->max_frames) { int j; for (j = 0; j < of->ctx->nb_streams; j++) output_streams[of->ost_index + j]->is_past_recording_time = 1; continue; } return 1; } return 0; } static int input_acceptable(InputStream *ist) { av_assert1(!ist->discard); return !input_files[ist->file_index]->unavailable && !input_files[ist->file_index]->eof_reached; } static int find_graph_input(FilterGraph *graph) { int i, nb_req_max = 0, file_index = -1; for (i = 0; i < graph->nb_inputs; i++) { int nb_req = av_buffersrc_get_nb_failed_requests(graph->inputs[i]->filter); if (nb_req > nb_req_max) { InputStream *ist = graph->inputs[i]->ist; if (input_acceptable(ist)) { nb_req_max = nb_req; file_index = ist->file_index; } } } return file_index; } /** * Select the input file to read from. * * @return >=0 index of the input file to use; * -1 if no file is acceptable; * -2 to read from filters without reading from a file */ static int select_input_file(void) { int i, ret, nb_active_out = nb_output_streams, ost_index = -1; int64_t opts_min; OutputStream *ost; AVFilterBufferRef *dummy; for (i = 0; i < nb_output_streams; i++) nb_active_out -= output_streams[i]->unavailable = output_streams[i]->is_past_recording_time; while (nb_active_out) { opts_min = INT64_MAX; ost_index = -1; for (i = 0; i < nb_output_streams; i++) { OutputStream *ost = output_streams[i]; int64_t opts = av_rescale_q(ost->st->cur_dts, ost->st->time_base, AV_TIME_BASE_Q); if (!ost->unavailable && opts < opts_min) { opts_min = opts; ost_index = i; } } if (ost_index < 0) return -1; ost = output_streams[ost_index]; if (ost->source_index >= 0) { /* ost is directly connected to an input */ InputStream *ist = input_streams[ost->source_index]; if (input_acceptable(ist)) return ist->file_index; } else { /* ost is connected to a complex filtergraph */ av_assert1(ost->filter); ret = av_buffersink_get_buffer_ref(ost->filter->filter, &dummy, AV_BUFFERSINK_FLAG_PEEK); if (ret >= 0) return -2; ret = find_graph_input(ost->filter->graph); if (ret >= 0) return ret; } ost->unavailable = 1; nb_active_out--; } return -1; } 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 && !run_as_daemon){ key = read_key(); last_time = cur_time; }else key = -1; if (key == 'q') 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 == 'h'){ if (do_hex_dump){ do_hex_dump = do_pkt_dump = 0; } else if(do_pkt_dump){ do_hex_dump = 1; } else do_pkt_dump = 1; av_log_set_level(AV_LOG_DEBUG); } 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: