Google Git
Sign in
nest-open-source / manifest_repos / ffmpeg / d18a1ff1ee3408962332c59ed996699166c5570d / . / fftools / ffmpeg.c
blob: b446d9b206b53608ccc496ab58605da3e48361a4 [file] [log] [blame]
/*
* 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 <ctype.h>
#include <string.h>
#include <math.h>
#include <stdlib.h>
#include <errno.h>
#include <limits.h>
#include <stdatomic.h>
#include <stdint.h>
#if HAVE_IO_H
#include <io.h>
#endif
#if HAVE_UNISTD_H
#include <unistd.h>
#endif
#include "libavformat/avformat.h"
#include "libavdevice/avdevice.h"
#include "libswresample/swresample.h"
#include "libavutil/opt.h"
#include "libavutil/channel_layout.h"
#include "libavutil/parseutils.h"
#include "libavutil/samplefmt.h"
#include "libavutil/fifo.h"
#include "libavutil/hwcontext.h"
#include "libavutil/internal.h"
#include "libavutil/intreadwrite.h"
#include "libavutil/dict.h"
#include "libavutil/display.h"
#include "libavutil/mathematics.h"
#include "libavutil/pixdesc.h"
#include "libavutil/avstring.h"
#include "libavutil/libm.h"
#include "libavutil/imgutils.h"
#include "libavutil/timestamp.h"
#include "libavutil/bprint.h"
#include "libavutil/time.h"
#include "libavutil/thread.h"
#include "libavutil/threadmessage.h"
#include "libavcodec/mathops.h"
#include "libavformat/os_support.h"
# include "libavfilter/avfilter.h"
# include "libavfilter/buffersrc.h"
# include "libavfilter/buffersink.h"
#if HAVE_SYS_RESOURCE_H
#include <sys/time.h>
#include <sys/types.h>
#include <sys/resource.h>
#elif HAVE_GETPROCESSTIMES
#include <windows.h>
#endif
#if HAVE_GETPROCESSMEMORYINFO
#include <windows.h>
#include <psapi.h>
#endif
#if HAVE_SETCONSOLECTRLHANDLER
#include <windows.h>
#endif
#if HAVE_SYS_SELECT_H
#include <sys/select.h>
#endif
#if HAVE_TERMIOS_H
#include <fcntl.h>
#include <sys/ioctl.h>
#include <sys/time.h>
#include <termios.h>
#elif HAVE_KBHIT
#include <conio.h>
#endif
#include <time.h>
#include "ffmpeg.h"
#include "cmdutils.h"
#include "libavutil/avassert.h"
const char program_name[] = "ffmpeg";
const int program_birth_year = 2000;
static FILE *vstats_file;
const char *const forced_keyframes_const_names[] = {
"n",
"n_forced",
"prev_forced_n",
"prev_forced_t",
"t",
NULL
};
typedef struct BenchmarkTimeStamps {
int64_t real_usec;
int64_t user_usec;
int64_t sys_usec;
} BenchmarkTimeStamps;
static void do_video_stats(OutputStream *ost, int frame_size);
static BenchmarkTimeStamps get_benchmark_time_stamps(void);
static int64_t getmaxrss(void);
static int ifilter_has_all_input_formats(FilterGraph *fg);
static int run_as_daemon = 0;
static int nb_frames_dup = 0;
static unsigned dup_warning = 1000;
static int nb_frames_drop = 0;
static int64_t decode_error_stat[2];
static int want_sdp = 1;
static BenchmarkTimeStamps current_time;
AVIOContext *progress_avio = NULL;
static uint8_t *subtitle_out;
InputStream **input_streams = NULL;
int nb_input_streams = 0;
InputFile **input_files = NULL;
int nb_input_files = 0;
OutputStream **output_streams = NULL;
int nb_output_streams = 0;
OutputFile **output_files = NULL;
int nb_output_files = 0;
FilterGraph **filtergraphs;
int nb_filtergraphs;
#if HAVE_TERMIOS_H
/* init terminal so that we can grab keys */
static struct termios oldtty;
static int restore_tty;
#endif
#if HAVE_THREADS
static void free_input_threads(void);
#endif
/* sub2video hack:
Convert subtitles to video with alpha to insert them in filter graphs.
This is a temporary solution until libavfilter gets real subtitles support.
*/
static int sub2video_get_blank_frame(InputStream *ist)
{
int ret;
AVFrame *frame = ist->sub2video.frame;
av_frame_unref(frame);
ist->sub2video.frame->width = ist->dec_ctx->width ? ist->dec_ctx->width : ist->sub2video.w;
ist->sub2video.frame->height = ist->dec_ctx->height ? ist->dec_ctx->height : ist->sub2video.h;
ist->sub2video.frame->format = AV_PIX_FMT_RGB32;
if ((ret = av_frame_get_buffer(frame, 0)) < 0)
return ret;
memset(frame->data[0], 0, frame->height * frame->linesize[0]);
return 0;
}
static void sub2video_copy_rect(uint8_t *dst, int dst_linesize, int w, int h,
AVSubtitleRect *r)
{
uint32_t *pal, *dst2;
uint8_t *src, *src2;
int x, y;
if (r->type != SUBTITLE_BITMAP) {
av_log(NULL, AV_LOG_WARNING, "sub2video: non-bitmap subtitle\n");
return;
}
if (r->x < 0 || r->x + r->w > w || r->y < 0 || r->y + r->h > h) {
av_log(NULL, AV_LOG_WARNING, "sub2video: rectangle (%d %d %d %d) overflowing %d %d\n",
r->x, r->y, r->w, r->h, w, h
);
return;
}
dst += r->y * dst_linesize + r->x * 4;
src = r->data[0];
pal = (uint32_t *)r->data[1];
for (y = 0; y < r->h; y++) {
dst2 = (uint32_t *)dst;
src2 = src;
for (x = 0; x < r->w; x++)
*(dst2++) = pal[*(src2++)];
dst += dst_linesize;
src += r->linesize[0];
}
}
static void sub2video_push_ref(InputStream *ist, int64_t pts)
{
AVFrame *frame = ist->sub2video.frame;
int i;
int ret;
av_assert1(frame->data[0]);
ist->sub2video.last_pts = frame->pts = pts;
for (i = 0; i < ist->nb_filters; i++) {
ret = av_buffersrc_add_frame_flags(ist->filters[i]->filter, frame,
AV_BUFFERSRC_FLAG_KEEP_REF |
AV_BUFFERSRC_FLAG_PUSH);
if (ret != AVERROR_EOF && ret < 0)
av_log(NULL, AV_LOG_WARNING, "Error while add the frame to buffer source(%s).\n",
av_err2str(ret));
}
}
void sub2video_update(InputStream *ist, int64_t heartbeat_pts, AVSubtitle *sub)
{
AVFrame *frame = ist->sub2video.frame;
int8_t *dst;
int dst_linesize;
int num_rects, i;
int64_t pts, end_pts;
if (!frame)
return;
if (sub) {
pts = av_rescale_q(sub->pts + sub->start_display_time * 1000LL,
AV_TIME_BASE_Q, ist->st->time_base);
end_pts = av_rescale_q(sub->pts + sub->end_display_time * 1000LL,
AV_TIME_BASE_Q, ist->st->time_base);
num_rects = sub->num_rects;
} else {
/* If we are initializing the system, utilize current heartbeat
PTS as the start time, and show until the following subpicture
is received. Otherwise, utilize the previous subpicture's end time
as the fall-back value. */
pts = ist->sub2video.initialize ?
heartbeat_pts : ist->sub2video.end_pts;
end_pts = INT64_MAX;
num_rects = 0;
}
if (sub2video_get_blank_frame(ist) < 0) {
av_log(ist->dec_ctx, AV_LOG_ERROR,
"Impossible to get a blank canvas.\n");
return;
}
dst = frame->data [0];
dst_linesize = frame->linesize[0];
for (i = 0; i < num_rects; i++)
sub2video_copy_rect(dst, dst_linesize, frame->width, frame->height, sub->rects[i]);
sub2video_push_ref(ist, pts);
ist->sub2video.end_pts = end_pts;
ist->sub2video.initialize = 0;
}
static void sub2video_heartbeat(InputStream *ist, int64_t pts)
{
InputFile *infile = input_files[ist->file_index];
int i, j, nb_reqs;
int64_t pts2;
/* When a frame is read from a file, examine all sub2video streams in
the same file and send the sub2video frame again. Otherwise, decoded
video frames could be accumulating in the filter graph while a filter
(possibly overlay) is desperately waiting for a subtitle frame. */
for (i = 0; i < infile->nb_streams; i++) {
InputStream *ist2 = input_streams[infile->ist_index + i];
if (!ist2->sub2video.frame)
continue;
/* subtitles seem to be usually muxed ahead of other streams;
if not, subtracting a larger time here is necessary */
pts2 = av_rescale_q(pts, ist->st->time_base, ist2->st->time_base) - 1;
/* do not send the heartbeat frame if the subtitle is already ahead */
if (pts2 <= ist2->sub2video.last_pts)
continue;
if (pts2 >= ist2->sub2video.end_pts || ist2->sub2video.initialize)
/* if we have hit the end of the current displayed subpicture,
or if we need to initialize the system, update the
overlayed subpicture and its start/end times */
sub2video_update(ist2, pts2 + 1, NULL);
for (j = 0, nb_reqs = 0; j < ist2->nb_filters; j++)
nb_reqs += av_buffersrc_get_nb_failed_requests(ist2->filters[j]->filter);
if (nb_reqs)
sub2video_push_ref(ist2, pts2);
}
}
static void sub2video_flush(InputStream *ist)
{
int i;
int ret;
if (ist->sub2video.end_pts < INT64_MAX)
sub2video_update(ist, INT64_MAX, NULL);
for (i = 0; i < ist->nb_filters; i++) {
ret = av_buffersrc_add_frame(ist->filters[i]->filter, NULL);
if (ret != AVERROR_EOF && ret < 0)
av_log(NULL, AV_LOG_WARNING, "Flush the frame error.\n");
}
}
/* end of sub2video hack */
static void term_exit_sigsafe(void)
{
#if HAVE_TERMIOS_H
if(restore_tty)
tcsetattr (0, TCSANOW, &oldtty);
#endif
}
void term_exit(void)
{
av_log(NULL, AV_LOG_QUIET, "%s", "");
term_exit_sigsafe();
}
static volatile int received_sigterm = 0;
static volatile int received_nb_signals = 0;
static atomic_int transcode_init_done = ATOMIC_VAR_INIT(0);
static volatile int ffmpeg_exited = 0;
static int main_return_code = 0;
static int64_t copy_ts_first_pts = AV_NOPTS_VALUE;
static void
sigterm_handler(int sig)
{
int ret;
received_sigterm = sig;
received_nb_signals++;
term_exit_sigsafe();
if(received_nb_signals > 3) {
ret = write(2/*STDERR_FILENO*/, "Received > 3 system signals, hard exiting\n",
strlen("Received > 3 system signals, hard exiting\n"));
if (ret < 0) { /* Do nothing */ };
exit(123);
}
}
#if HAVE_SETCONSOLECTRLHANDLER
static BOOL WINAPI CtrlHandler(DWORD fdwCtrlType)
{
av_log(NULL, AV_LOG_DEBUG, "\nReceived windows signal %ld\n", fdwCtrlType);
switch (fdwCtrlType)
{
case CTRL_C_EVENT:
case CTRL_BREAK_EVENT:
sigterm_handler(SIGINT);
return TRUE;
case CTRL_CLOSE_EVENT:
case CTRL_LOGOFF_EVENT:
case CTRL_SHUTDOWN_EVENT:
sigterm_handler(SIGTERM);
/* Basically, with these 3 events, when we return from this method the
process is hard terminated, so stall as long as we need to
to try and let the main thread(s) clean up and gracefully terminate
(we have at most 5 seconds, but should be done far before that). */
while (!ffmpeg_exited) {
Sleep(0);
}
return TRUE;
default:
av_log(NULL, AV_LOG_ERROR, "Received unknown windows signal %ld\n", fdwCtrlType);
return FALSE;
}
}
#endif
void term_init(void)
{
#if HAVE_TERMIOS_H
if (!run_as_daemon && stdin_interaction) {
struct termios tty;
if (tcgetattr (0, &tty) == 0) {
oldtty = tty;
restore_tty = 1;
tty.c_iflag &= ~(IGNBRK|BRKINT|PARMRK|ISTRIP
|INLCR|IGNCR|ICRNL|IXON);
tty.c_oflag |= OPOST;
tty.c_lflag &= ~(ECHO|ECHONL|ICANON|IEXTEN);
tty.c_cflag &= ~(CSIZE|PARENB);
tty.c_cflag |= CS8;
tty.c_cc[VMIN] = 1;
tty.c_cc[VTIME] = 0;
tcsetattr (0, TCSANOW, &tty);
}
signal(SIGQUIT, sigterm_handler); /* Quit (POSIX). */
}
#endif
signal(SIGINT , sigterm_handler); /* Interrupt (ANSI). */
signal(SIGTERM, sigterm_handler); /* Termination (ANSI). */
#ifdef SIGXCPU
signal(SIGXCPU, sigterm_handler);
#endif
#ifdef SIGPIPE
signal(SIGPIPE, SIG_IGN); /* Broken pipe (POSIX). */
#endif
#if HAVE_SETCONSOLECTRLHANDLER
SetConsoleCtrlHandler((PHANDLER_ROUTINE) CtrlHandler, TRUE);
#endif
}
/* read a key without blocking */
static int read_key(void)
{
unsigned char ch;
#if HAVE_TERMIOS_H
int n = 1;
struct timeval tv;
fd_set rfds;
FD_ZERO(&rfds);
FD_SET(0, &rfds);
tv.tv_sec = 0;
tv.tv_usec = 0;
n = select(1, &rfds, NULL, NULL, &tv);
if (n > 0) {
n = read(0, &ch, 1);
if (n == 1)
return ch;
return n;
}
#elif HAVE_KBHIT
# if HAVE_PEEKNAMEDPIPE
static int is_pipe;
static HANDLE input_handle;
DWORD dw, nchars;
if(!input_handle){
input_handle = GetStdHandle(STD_INPUT_HANDLE);
is_pipe = !GetConsoleMode(input_handle, &dw);
}
if (is_pipe) {
/* When running under a GUI, you will end here. */
if (!PeekNamedPipe(input_handle, NULL, 0, NULL, &nchars, NULL)) {
// input pipe may have been closed by the program that ran ffmpeg
return -1;
}
//Read it
if(nchars != 0) {
read(0, &ch, 1);
return ch;
}else{
return -1;
}
}
# endif
if(kbhit())
return(getch());
#endif
return -1;
}
static int decode_interrupt_cb(void *ctx)
{
return received_nb_signals > atomic_load(&transcode_init_done);
}
const AVIOInterruptCB int_cb = { decode_interrupt_cb, NULL };
static void ffmpeg_cleanup(int ret)
{
int i, j;
if (do_benchmark) {
int maxrss = getmaxrss() / 1024;
av_log(NULL, AV_LOG_INFO, "bench: maxrss=%ikB\n", maxrss);
}
for (i = 0; i < nb_filtergraphs; i++) {
FilterGraph *fg = filtergraphs[i];
avfilter_graph_free(&fg->graph);
for (j = 0; j < fg->nb_inputs; j++) {
InputFilter *ifilter = fg->inputs[j];
struct InputStream *ist = ifilter->ist;
while (av_fifo_size(ifilter->frame_queue)) {
AVFrame *frame;
av_fifo_generic_read(ifilter->frame_queue, &frame,
sizeof(frame), NULL);
av_frame_free(&frame);
}
av_fifo_freep(&ifilter->frame_queue);
if (ist->sub2video.sub_queue) {
while (av_fifo_size(ist->sub2video.sub_queue)) {
AVSubtitle sub;
av_fifo_generic_read(ist->sub2video.sub_queue,
&sub, sizeof(sub), NULL);
avsubtitle_free(&sub);
}
av_fifo_freep(&ist->sub2video.sub_queue);
}
av_buffer_unref(&ifilter->hw_frames_ctx);
av_freep(&ifilter->name);
av_freep(&fg->inputs[j]);
}
av_freep(&fg->inputs);
for (j = 0; j < fg->nb_outputs; j++) {
OutputFilter *ofilter = fg->outputs[j];
avfilter_inout_free(&ofilter->out_tmp);
av_freep(&ofilter->name);
av_freep(&ofilter->formats);
av_freep(&ofilter->channel_layouts);
av_freep(&ofilter->sample_rates);
av_freep(&fg->outputs[j]);
}
av_freep(&fg->outputs);
av_freep(&fg->graph_desc);
av_freep(&filtergraphs[i]);
}
av_freep(&filtergraphs);
av_freep(&subtitle_out);
/* close files */
for (i = 0; i < nb_output_files; i++) {
OutputFile *of = output_files[i];
AVFormatContext *s;
if (!of)
continue;
s = of->ctx;
if (s && s->oformat && !(s->oformat->flags & AVFMT_NOFILE))
avio_closep(&s->pb);
avformat_free_context(s);
av_dict_free(&of->opts);
av_freep(&output_files[i]);
}
for (i = 0; i < nb_output_streams; i++) {
OutputStream *ost = output_streams[i];
if (!ost)
continue;
av_bsf_free(&ost->bsf_ctx);
av_frame_free(&ost->filtered_frame);
av_frame_free(&ost->last_frame);
av_dict_free(&ost->encoder_opts);
av_freep(&ost->forced_keyframes);
av_expr_free(ost->forced_keyframes_pexpr);
av_freep(&ost->avfilter);
av_freep(&ost->logfile_prefix);
av_freep(&ost->audio_channels_map);
ost->audio_channels_mapped = 0;
av_dict_free(&ost->sws_dict);
av_dict_free(&ost->swr_opts);
avcodec_free_context(&ost->enc_ctx);
avcodec_parameters_free(&ost->ref_par);
if (ost->muxing_queue) {
while (av_fifo_size(ost->muxing_queue)) {
AVPacket pkt;
av_fifo_generic_read(ost->muxing_queue, &pkt, sizeof(pkt), NULL);
av_packet_unref(&pkt);
}
av_fifo_freep(&ost->muxing_queue);
}
av_freep(&output_streams[i]);
}
#if HAVE_THREADS
free_input_threads();
#endif
for (i = 0; i < nb_input_files; i++) {
avformat_close_input(&input_files[i]->ctx);
av_freep(&input_files[i]);
}
for (i = 0; i < nb_input_streams; i++) {
InputStream *ist = input_streams[i];
av_frame_free(&ist->decoded_frame);
av_frame_free(&ist->filter_frame);
av_dict_free(&ist->decoder_opts);
avsubtitle_free(&ist->prev_sub.subtitle);
av_frame_free(&ist->sub2video.frame);
av_freep(&ist->filters);
av_freep(&ist->hwaccel_device);
av_freep(&ist->dts_buffer);
avcodec_free_context(&ist->dec_ctx);
av_freep(&input_streams[i]);
}
if (vstats_file) {
if (fclose(vstats_file))
av_log(NULL, AV_LOG_ERROR,
"Error closing vstats file, loss of information possible: %s\n",
av_err2str(AVERROR(errno)));
}
av_freep(&vstats_filename);
av_freep(&input_streams);
av_freep(&input_files);
av_freep(&output_streams);
av_freep(&output_files);
uninit_opts();
avformat_network_deinit();
if (received_sigterm) {
av_log(NULL, AV_LOG_INFO, "Exiting normally, received signal %d.\n",
(int) received_sigterm);
} else if (ret && atomic_load(&transcode_init_done)) {
av_log(NULL, AV_LOG_INFO, "Conversion failed!\n");
}
term_exit();
ffmpeg_exited = 1;
}
void remove_avoptions(AVDictionary **a, AVDictionary *b)
{
AVDictionaryEntry *t = NULL;
while ((t = av_dict_get(b, "", t, AV_DICT_IGNORE_SUFFIX))) {
av_dict_set(a, t->key, NULL, AV_DICT_MATCH_CASE);
}
}
void assert_avoptions(AVDictionary *m)
{
AVDictionaryEntry *t;
if ((t = av_dict_get(m, "", NULL, AV_DICT_IGNORE_SUFFIX))) {
av_log(NULL, AV_LOG_FATAL, "Option %s not found.\n", t->key);
exit_program(1);
}
}
static void abort_codec_experimental(AVCodec *c, int encoder)
{
exit_program(1);
}
static void update_benchmark(const char *fmt, ...)
{
if (do_benchmark_all) {
BenchmarkTimeStamps t = get_benchmark_time_stamps();
va_list va;
char buf[1024];
if (fmt) {
va_start(va, fmt);
vsnprintf(buf, sizeof(buf), fmt, va);
va_end(va);
av_log(NULL, AV_LOG_INFO,
"bench: %8" PRIu64 " user %8" PRIu64 " sys %8" PRIu64 " real %s \n",
t.user_usec - current_time.user_usec,
t.sys_usec - current_time.sys_usec,
t.real_usec - current_time.real_usec, buf);
}
current_time = t;
}
}
static void close_all_output_streams(OutputStream *ost, OSTFinished this_stream, OSTFinished others)
{
int i;
for (i = 0; i < nb_output_streams; i++) {
OutputStream *ost2 = output_streams[i];
ost2->finished |= ost == ost2 ? this_stream : others;
}
}
static void write_packet(OutputFile *of, AVPacket *pkt, OutputStream *ost, int unqueue)
{
AVFormatContext *s = of->ctx;
AVStream *st = ost->st;
int ret;
/*
* 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().
* Do not count the packet when unqueued because it has been counted when queued.
*/
if (!(st->codecpar->codec_type == AVMEDIA_TYPE_VIDEO && ost->encoding_needed) && !unqueue) {
if (ost->frame_number >= ost->max_frames) {
av_packet_unref(pkt);
return;
}
ost->frame_number++;
}
if (!of->header_written) {
AVPacket tmp_pkt = {0};
/* the muxer is not initialized yet, buffer the packet */
if (!av_fifo_space(ost->muxing_queue)) {
unsigned int are_we_over_size =
(ost->muxing_queue_data_size + pkt->size) > ost->muxing_queue_data_threshold;
int new_size = are_we_over_size ?
FFMIN(2 * av_fifo_size(ost->muxing_queue),
ost->max_muxing_queue_size) :
2 * av_fifo_size(ost->muxing_queue);
if (new_size <= av_fifo_size(ost->muxing_queue)) {
av_log(NULL, AV_LOG_ERROR,
"Too many packets buffered for output stream %d:%d.\n",
ost->file_index, ost->st->index);
exit_program(1);
}
ret = av_fifo_realloc2(ost->muxing_queue, new_size);
if (ret < 0)
exit_program(1);
}
ret = av_packet_make_refcounted(pkt);
if (ret < 0)
exit_program(1);
av_packet_move_ref(&tmp_pkt, pkt);
ost->muxing_queue_data_size += tmp_pkt.size;
av_fifo_generic_write(ost->muxing_queue, &tmp_pkt, sizeof(tmp_pkt), NULL);
return;
}
if ((st->codecpar->codec_type == AVMEDIA_TYPE_VIDEO && video_sync_method == VSYNC_DROP) ||
(st->codecpar->codec_type == AVMEDIA_TYPE_AUDIO && audio_sync_method < 0))
pkt->pts = pkt->dts = AV_NOPTS_VALUE;
if (st->codecpar->codec_type == AVMEDIA_TYPE_VIDEO) {
int i;
uint8_t *sd = av_packet_get_side_data(pkt, AV_PKT_DATA_QUALITY_STATS,
NULL);
ost->quality = sd ? AV_RL32(sd) : -1;
ost->pict_type = sd ? sd[4] : AV_PICTURE_TYPE_NONE;
for (i = 0; i<FF_ARRAY_ELEMS(ost->error); i++) {
if (sd && i < sd[5])
ost->error[i] = AV_RL64(sd + 8 + 8*i);
else
ost->error[i] = -1;
}
if (ost->frame_rate.num && ost->is_cfr) {
if (pkt->duration > 0)
av_log(NULL, AV_LOG_WARNING, "Overriding packet duration by frame rate, this should not happen\n");
pkt->duration = av_rescale_q(1, av_inv_q(ost->frame_rate),
ost->mux_timebase);
}
}
av_packet_rescale_ts(pkt, ost->mux_timebase, ost->st->time_base);
if (!(s->oformat->flags & AVFMT_NOTIMESTAMPS)) {
if (pkt->dts != AV_NOPTS_VALUE &&
pkt->pts != AV_NOPTS_VALUE &&
pkt->dts > pkt->pts) {
av_log(s, AV_LOG_WARNING, "Invalid DTS: %"PRId64" PTS: %"PRId64" in output stream %d:%d, replacing by guess\n",
pkt->dts, pkt->pts,
ost->file_index, ost->st->index);
pkt->pts =
pkt->dts = pkt->pts + pkt->dts + ost->last_mux_dts + 1
- FFMIN3(pkt->pts, pkt->dts, ost->last_mux_dts + 1)
- FFMAX3(pkt->pts, pkt->dts, ost->last_mux_dts + 1);
}
if ((st->codecpar->codec_type == AVMEDIA_TYPE_AUDIO || st->codecpar->codec_type == AVMEDIA_TYPE_VIDEO || st->codecpar->codec_type == AVMEDIA_TYPE_SUBTITLE) &&
pkt->dts != AV_NOPTS_VALUE &&
!(st->codecpar->codec_id == AV_CODEC_ID_VP9 && ost->stream_copy) &&
ost->last_mux_dts != AV_NOPTS_VALUE) {
int64_t max = ost->last_mux_dts + !(s->oformat->flags & AVFMT_TS_NONSTRICT);
if (pkt->dts < max) {
int loglevel = max - pkt->dts > 2 || st->codecpar->codec_type == AVMEDIA_TYPE_VIDEO ? AV_LOG_WARNING : AV_LOG_DEBUG;
if (exit_on_error)
loglevel = AV_LOG_ERROR;
av_log(s, loglevel, "Non-monotonous DTS in output stream "
"%d:%d; previous: %"PRId64", current: %"PRId64"; ",
ost->file_index, ost->st->index, ost->last_mux_dts, pkt->dts);
if (exit_on_error) {
av_log(NULL, AV_LOG_FATAL, "aborting.\n");
exit_program(1);
}
av_log(s, loglevel, "changing to %"PRId64". This may result "
"in incorrect timestamps in the output file.\n",
max);
if (pkt->pts >= pkt->dts)
pkt->pts = FFMAX(pkt->pts, max);
pkt->dts = max;
}
}
}
ost->last_mux_dts = pkt->dts;
ost->data_size += pkt->size;
ost->packets_written++;
pkt->stream_index = ost->index;
if (debug_ts) {
av_log(NULL, AV_LOG_INFO, "muxer <- type:%s "
"pkt_pts:%s pkt_pts_time:%s pkt_dts:%s pkt_dts_time:%s size:%d\n",
av_get_media_type_string(ost->enc_ctx->codec_type),
av_ts2str(pkt->pts), av_ts2timestr(pkt->pts, &ost->st->time_base),
av_ts2str(pkt->dts), av_ts2timestr(pkt->dts, &ost->st->time_base),
pkt->size
);
}
ret = av_interleaved_write_frame(s, pkt);
if (ret < 0) {
print_error("av_interleaved_write_frame()", ret);
main_return_code = 1;
close_all_output_streams(ost, MUXER_FINISHED | ENCODER_FINISHED, ENCODER_FINISHED);
}
av_packet_unref(pkt);
}
static void close_output_stream(OutputStream *ost)
{
OutputFile *of = output_files[ost->file_index];
ost->finished |= ENCODER_FINISHED;
if (of->shortest) {
int64_t end = av_rescale_q(ost->sync_opts - ost->first_pts, ost->enc_ctx->time_base, AV_TIME_BASE_Q);
of->recording_time = FFMIN(of->recording_time, end);
}
}
/*
* Send a single packet to the output, applying any bitstream filters
* associated with the output stream. This may result in any number
* of packets actually being written, depending on what bitstream
* filters are applied. The supplied packet is consumed and will be
* blank (as if newly-allocated) when this function returns.
*
* If eof is set, instead indicate EOF to all bitstream filters and
* therefore flush any delayed packets to the output. A blank packet
* must be supplied in this case.
*/
static void output_packet(OutputFile *of, AVPacket *pkt,
OutputStream *ost, int eof)
{
int ret = 0;
/* apply the output bitstream filters */
if (ost->bsf_ctx) {
ret = av_bsf_send_packet(ost->bsf_ctx, eof ? NULL : pkt);
if (ret < 0)
goto finish;
while ((ret = av_bsf_receive_packet(ost->bsf_ctx, pkt)) >= 0)
write_packet(of, pkt, ost, 0);
if (ret == AVERROR(EAGAIN))
ret = 0;
} else if (!eof)
write_packet(of, pkt, ost, 0);
finish:
if (ret < 0 && ret != AVERROR_EOF) {
av_log(NULL, AV_LOG_ERROR, "Error applying bitstream filters to an output "
"packet for stream #%d:%d.\n", ost->file_index, ost->index);
if(exit_on_error)
exit_program(1);
}
}
static int check_recording_time(OutputStream *ost)
{
OutputFile *of = output_files[ost->file_index];
if (of->recording_time != INT64_MAX &&
av_compare_ts(ost->sync_opts - ost->first_pts, ost->enc_ctx->time_base, of->recording_time,
AV_TIME_BASE_Q) >= 0) {
close_output_stream(ost);
return 0;
}
return 1;
}
static double adjust_frame_pts_to_encoder_tb(OutputFile *of, OutputStream *ost,
AVFrame *frame)
{
double float_pts = AV_NOPTS_VALUE; // this is identical to frame.pts but with higher precision
AVCodecContext *enc = ost->enc_ctx;
if (!frame || frame->pts == AV_NOPTS_VALUE ||
!enc || !ost->filter || !ost->filter->graph->graph)
goto early_exit;
{
AVFilterContext *filter = ost->filter->filter;
int64_t start_time = (of->start_time == AV_NOPTS_VALUE) ? 0 : of->start_time;
AVRational filter_tb = av_buffersink_get_time_base(filter);
AVRational tb = enc->time_base;
int extra_bits = av_clip(29 - av_log2(tb.den), 0, 16);
tb.den <<= extra_bits;
float_pts =
av_rescale_q(frame->pts, filter_tb, tb) -
av_rescale_q(start_time, AV_TIME_BASE_Q, tb);
float_pts /= 1 << extra_bits;
// avoid exact midoints to reduce the chance of rounding differences, this can be removed in case the fps code is changed to work with integers
float_pts += FFSIGN(float_pts) * 1.0 / (1<<17);
frame->pts =
av_rescale_q(frame->pts, filter_tb, enc->time_base) -
av_rescale_q(start_time, AV_TIME_BASE_Q, enc->time_base);
}
early_exit:
if (debug_ts) {
av_log(NULL, AV_LOG_INFO, "filter -> pts:%s pts_time:%s exact:%f time_base:%d/%d\n",
frame ? av_ts2str(frame->pts) : "NULL",
frame ? av_ts2timestr(frame->pts, &enc->time_base) : "NULL",
float_pts,
enc ? enc->time_base.num : -1,
enc ? enc->time_base.den : -1);
}
return float_pts;
}
static int init_output_stream(OutputStream *ost, AVFrame *frame,
char *error, int error_len);
static int init_output_stream_wrapper(OutputStream *ost, AVFrame *frame,
unsigned int fatal)
{
int ret = AVERROR_BUG;
char error[1024] = {0};
if (ost->initialized)
return 0;
ret = init_output_stream(ost, frame, error, sizeof(error));
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Error initializing output stream %d:%d -- %s\n",
ost->file_index, ost->index, error);
if (fatal)
exit_program(1);
}
return ret;
}
static void do_audio_out(OutputFile *of, OutputStream *ost,
AVFrame *frame)
{
AVCodecContext *enc = ost->enc_ctx;
AVPacket pkt;
int ret;
av_init_packet(&pkt);
pkt.data = NULL;
pkt.size = 0;
adjust_frame_pts_to_encoder_tb(of, ost, frame);
if (!check_recording_time(ost))
return;
if (frame->pts == AV_NOPTS_VALUE || audio_sync_method < 0)
frame->pts = ost->sync_opts;
ost->sync_opts = frame->pts + frame->nb_samples;
ost->samples_encoded += frame->nb_samples;
ost->frames_encoded++;
av_assert0(pkt.size || !pkt.data);
update_benchmark(NULL);
if (debug_ts) {
av_log(NULL, AV_LOG_INFO, "encoder <- type:audio "
"frame_pts:%s frame_pts_time:%s time_base:%d/%d\n",
av_ts2str(frame->pts), av_ts2timestr(frame->pts, &enc->time_base),
enc->time_base.num, enc->time_base.den);
}
ret = avcodec_send_frame(enc, frame);
if (ret < 0)
goto error;
while (1) {
ret = avcodec_receive_packet(enc, &pkt);
if (ret == AVERROR(EAGAIN))
break;
if (ret < 0)
goto error;
update_benchmark("encode_audio %d.%d", ost->file_index, ost->index);
av_packet_rescale_ts(&pkt, enc->time_base, ost->mux_timebase);
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, &enc->time_base),
av_ts2str(pkt.dts), av_ts2timestr(pkt.dts, &enc->time_base));
}
output_packet(of, &pkt, ost, 0);
}
return;
error:
av_log(NULL, AV_LOG_FATAL, "Audio encoding failed\n");
exit_program(1);
}
static void do_subtitle_out(OutputFile *of,
OutputStream *ost,
AVSubtitle *sub)
{
int subtitle_out_max_size = 1024 * 1024;
int subtitle_out_size, nb, i;
AVCodecContext *enc;
AVPacket pkt;
int64_t pts;
if (sub->pts == AV_NOPTS_VALUE) {
av_log(NULL, AV_LOG_ERROR, "Subtitle packets must have a pts\n");
if (exit_on_error)
exit_program(1);
return;
}
enc = ost->enc_ctx;
if (!subtitle_out) {
subtitle_out = av_malloc(subtitle_out_max_size);
if (!subtitle_out) {
av_log(NULL, AV_LOG_FATAL, "Failed to allocate subtitle_out\n");
exit_program(1);
}
}
/* Note: DVB subtitle need one packet to draw them and one other
packet to clear them */
/* XXX: signal it in the codec context ? */
if (enc->codec_id == AV_CODEC_ID_DVB_SUBTITLE)
nb = 2;
else
nb = 1;
/* shift timestamp to honor -ss and make check_recording_time() work with -t */
pts = sub->pts;
if (output_files[ost->file_index]->start_time != AV_NOPTS_VALUE)
pts -= output_files[ost->file_index]->start_time;
for (i = 0; i < nb; i++) {
unsigned save_num_rects = sub->num_rects;
ost->sync_opts = av_rescale_q(pts, AV_TIME_BASE_Q, enc->time_base);
if (!check_recording_time(ost))
return;
sub->pts = pts;
// start_display_time is required to be 0
sub->pts += av_rescale_q(sub->start_display_time, (AVRational){ 1, 1000 }, AV_TIME_BASE_Q);
sub->end_display_time -= sub->start_display_time;
sub->start_display_time = 0;
if (i == 1)
sub->num_rects = 0;
ost->frames_encoded++;
subtitle_out_size = avcodec_encode_subtitle(enc, subtitle_out,
subtitle_out_max_size, sub);
if (i == 1)
sub->num_rects = save_num_rects;
if (subtitle_out_size < 0) {
av_log(NULL, AV_LOG_FATAL, "Subtitle encoding failed\n");
exit_program(1);
}
av_init_packet(&pkt);
pkt.data = subtitle_out;
pkt.size = subtitle_out_size;
pkt.pts = av_rescale_q(sub->pts, AV_TIME_BASE_Q, ost->mux_timebase);
pkt.duration = av_rescale_q(sub->end_display_time, (AVRational){ 1, 1000 }, ost->mux_timebase);
if (enc->codec_id == AV_CODEC_ID_DVB_SUBTITLE) {
/* XXX: the pts correction is handled here. Maybe handling
it in the codec would be better */
if (i == 0)
pkt.pts += av_rescale_q(sub->start_display_time, (AVRational){ 1, 1000 }, ost->mux_timebase);
else
pkt.pts += av_rescale_q(sub->end_display_time, (AVRational){ 1, 1000 }, ost->mux_timebase);
}
pkt.dts = pkt.pts;
output_packet(of, &pkt, ost, 0);
}
}
static void do_video_out(OutputFile *of,
OutputStream *ost,
AVFrame *next_picture)
{
int ret, format_video_sync;
AVPacket pkt;
AVCodecContext *enc = ost->enc_ctx;
AVRational frame_rate;
int nb_frames, nb0_frames, i;
double delta, delta0;
double duration = 0;
double sync_ipts = AV_NOPTS_VALUE;
int frame_size = 0;
InputStream *ist = NULL;
AVFilterContext *filter = ost->filter->filter;
init_output_stream_wrapper(ost, next_picture, 1);
sync_ipts = adjust_frame_pts_to_encoder_tb(of, ost, next_picture);
if (ost->source_index >= 0)
ist = input_streams[ost->source_index];
frame_rate = av_buffersink_get_frame_rate(filter);
if (frame_rate.num > 0 && frame_rate.den > 0)
duration = 1/(av_q2d(frame_rate) * av_q2d(enc->time_base));
if(ist && ist->st->start_time != AV_NOPTS_VALUE && ist->st->first_dts != AV_NOPTS_VALUE && ost->frame_rate.num)
duration = FFMIN(duration, 1/(av_q2d(ost->frame_rate) * av_q2d(enc->time_base)));
if (!ost->filters_script &&
!ost->filters &&
(nb_filtergraphs == 0 || !filtergraphs[0]->graph_desc) &&
next_picture &&
ist &&
lrintf(next_picture->pkt_duration * av_q2d(ist->st->time_base) / av_q2d(enc->time_base)) > 0) {
duration = lrintf(next_picture->pkt_duration * av_q2d(ist->st->time_base) / av_q2d(enc->time_base));
}
if (!next_picture) {
//end, flushing
nb0_frames = nb_frames = mid_pred(ost->last_nb0_frames[0],
ost->last_nb0_frames[1],
ost->last_nb0_frames[2]);
} else {
delta0 = sync_ipts - ost->sync_opts; // delta0 is the "drift" between the input frame (next_picture) and where it would fall in the output.
delta = delta0 + duration;
/* by default, we output a single frame */
nb0_frames = 0; // tracks the number of times the PREVIOUS frame should be duplicated, mostly for variable framerate (VFR)
nb_frames = 1;
format_video_sync = video_sync_method;
if (format_video_sync == VSYNC_AUTO) {
if(!strcmp(of->ctx->oformat->name, "avi")) {
format_video_sync = VSYNC_VFR;
} else
format_video_sync = (of->ctx->oformat->flags & AVFMT_VARIABLE_FPS) ? ((of->ctx->oformat->flags & AVFMT_NOTIMESTAMPS) ? VSYNC_PASSTHROUGH : VSYNC_VFR) : VSYNC_CFR;
if ( ist
&& format_video_sync == VSYNC_CFR
&& input_files[ist->file_index]->ctx->nb_streams == 1
&& input_files[ist->file_index]->input_ts_offset == 0) {
format_video_sync = VSYNC_VSCFR;
}
if (format_video_sync == VSYNC_CFR && copy_ts) {
format_video_sync = VSYNC_VSCFR;
}
}
ost->is_cfr = (format_video_sync == VSYNC_CFR || format_video_sync == VSYNC_VSCFR);
if (delta0 < 0 &&
delta > 0 &&
format_video_sync != VSYNC_PASSTHROUGH &&
format_video_sync != VSYNC_DROP) {
if (delta0 < -0.6) {
av_log(NULL, AV_LOG_VERBOSE, "Past duration %f too large\n", -delta0);
} else
av_log(NULL, AV_LOG_DEBUG, "Clipping frame in rate conversion by %f\n", -delta0);
sync_ipts = ost->sync_opts;
duration += delta0;
delta0 = 0;
}
switch (format_video_sync) {
case VSYNC_VSCFR:
if (ost->frame_number == 0 && delta0 >= 0.5) {
av_log(NULL, AV_LOG_DEBUG, "Not duplicating %d initial frames\n", (int)lrintf(delta0));
delta = duration;
delta0 = 0;
ost->sync_opts = llrint(sync_ipts);
}
case VSYNC_CFR:
// FIXME set to 0.5 after we fix some dts/pts bugs like in avidec.c
if (frame_drop_threshold && delta < frame_drop_threshold && ost->frame_number) {
nb_frames = 0;
} else if (delta < -1.1)
nb_frames = 0;
else if (delta > 1.1) {
nb_frames = lrintf(delta);
if (delta0 > 1.1)
nb0_frames = llrintf(delta0 - 0.6);
}
break;
case VSYNC_VFR:
if (delta <= -0.6)
nb_frames = 0;
else if (delta > 0.6)
ost->sync_opts = llrint(sync_ipts);
break;
case VSYNC_DROP:
case VSYNC_PASSTHROUGH:
ost->sync_opts = llrint(sync_ipts);
break;
default:
av_assert0(0);
}
}
nb_frames = FFMIN(nb_frames, ost->max_frames - ost->frame_number);
nb0_frames = FFMIN(nb0_frames, nb_frames);
memmove(ost->last_nb0_frames + 1,
ost->last_nb0_frames,
sizeof(ost->last_nb0_frames[0]) * (FF_ARRAY_ELEMS(ost->last_nb0_frames) - 1));
ost->last_nb0_frames[0] = nb0_frames;
if (nb0_frames == 0 && ost->last_dropped) {
nb_frames_drop++;
av_log(NULL, AV_LOG_VERBOSE,
"*** dropping frame %d from stream %d at ts %"PRId64"\n",
ost->frame_number, ost->st->index, ost->last_frame->pts);
}
if (nb_frames > (nb0_frames && ost->last_dropped) + (nb_frames > nb0_frames)) {
if (nb_frames > dts_error_threshold * 30) {
av_log(NULL, AV_LOG_ERROR, "%d frame duplication too large, skipping\n", nb_frames - 1);
nb_frames_drop++;
return;
}
nb_frames_dup += nb_frames - (nb0_frames && ost->last_dropped) - (nb_frames > nb0_frames);
av_log(NULL, AV_LOG_VERBOSE, "*** %d dup!\n", nb_frames - 1);
if (nb_frames_dup > dup_warning) {
av_log(NULL, AV_LOG_WARNING, "More than %d frames duplicated\n", dup_warning);
dup_warning *= 10;
}
}
ost->last_dropped = nb_frames == nb0_frames && next_picture;
/* duplicates frame if needed */
for (i = 0; i < nb_frames; i++) {
AVFrame *in_picture;
int forced_keyframe = 0;
double pts_time;
av_init_packet(&pkt);
pkt.data = NULL;
pkt.size = 0;
if (i < nb0_frames && ost->last_frame) {
in_picture = ost->last_frame;
} else
in_picture = next_picture;
if (!in_picture)
return;
in_picture->pts = ost->sync_opts;
if (!check_recording_time(ost))
return;
in_picture->quality = enc->global_quality;
in_picture->pict_type = 0;
if (ost->forced_kf_ref_pts == AV_NOPTS_VALUE &&
in_picture->pts != AV_NOPTS_VALUE)
ost->forced_kf_ref_pts = in_picture->pts;
pts_time = in_picture->pts != AV_NOPTS_VALUE ?
(in_picture->pts - ost->forced_kf_ref_pts) * av_q2d(enc->time_base) : NAN;
if (ost->forced_kf_index < ost->forced_kf_count &&
in_picture->pts >= ost->forced_kf_pts[ost->forced_kf_index]) {
ost->forced_kf_index++;
forced_keyframe = 1;
} else if (ost->forced_keyframes_pexpr) {
double res;
ost->forced_keyframes_expr_const_values[FKF_T] = pts_time;
res = av_expr_eval(ost->forced_keyframes_pexpr,
ost->forced_keyframes_expr_const_values, NULL);
ff_dlog(NULL, "force_key_frame: n:%f n_forced:%f prev_forced_n:%f t:%f prev_forced_t:%f -> res:%f\n",
ost->forced_keyframes_expr_const_values[FKF_N],
ost->forced_keyframes_expr_const_values[FKF_N_FORCED],
ost->forced_keyframes_expr_const_values[FKF_PREV_FORCED_N],
ost->forced_keyframes_expr_const_values[FKF_T],
ost->forced_keyframes_expr_const_values[FKF_PREV_FORCED_T],
res);
if (res) {
forced_keyframe = 1;
ost->forced_keyframes_expr_const_values[FKF_PREV_FORCED_N] =
ost->forced_keyframes_expr_const_values[FKF_N];
ost->forced_keyframes_expr_const_values[FKF_PREV_FORCED_T] =
ost->forced_keyframes_expr_const_values[FKF_T];
ost->forced_keyframes_expr_const_values[FKF_N_FORCED] += 1;
}
ost->forced_keyframes_expr_const_values[FKF_N] += 1;
} else if ( ost->forced_keyframes
&& !strncmp(ost->forced_keyframes, "source", 6)
&& in_picture->key_frame==1
&& !i) {
forced_keyframe = 1;
}
if (forced_keyframe) {
in_picture->pict_type = AV_PICTURE_TYPE_I;
av_log(NULL, AV_LOG_DEBUG, "Forced keyframe at time %f\n", pts_time);
}
update_benchmark(NULL);
if (debug_ts) {
av_log(NULL, AV_LOG_INFO, "encoder <- type:video "
"frame_pts:%s frame_pts_time:%s time_base:%d/%d\n",
av_ts2str(in_picture->pts), av_ts2timestr(in_picture->pts, &enc->time_base),
enc->time_base.num, enc->time_base.den);
}
ost->frames_encoded++;
ret = avcodec_send_frame(enc, in_picture);
if (ret < 0)
goto error;
// Make sure Closed Captions will not be duplicated
av_frame_remove_side_data(in_picture, AV_FRAME_DATA_A53_CC);
while (1) {
ret = avcodec_receive_packet(enc, &pkt);
update_benchmark("encode_video %d.%d", ost->file_index, ost->index);
if (ret == AVERROR(EAGAIN))
break;
if (ret < 0)
goto error;
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, &enc->time_base),
av_ts2str(pkt.dts), av_ts2timestr(pkt.dts, &enc->time_base));
}
if (pkt.pts == AV_NOPTS_VALUE && !(enc->codec->capabilities & AV_CODEC_CAP_DELAY))
pkt.pts = ost->sync_opts;
av_packet_rescale_ts(&pkt, enc->time_base, ost->mux_timebase);
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->mux_timebase),
av_ts2str(pkt.dts), av_ts2timestr(pkt.dts, &ost->mux_timebase));
}
frame_size = pkt.size;
output_packet(of, &pkt, ost, 0);
/* 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(ost, frame_size);
}
if (!ost->last_frame)
ost->last_frame = av_frame_alloc();
av_frame_unref(ost->last_frame);
if (next_picture && ost->last_frame)
av_frame_ref(ost->last_frame, next_picture);
else
av_frame_free(&ost->last_frame);
return;
error:
av_log(NULL, AV_LOG_FATAL, "Video encoding failed\n");
exit_program(1);
}
static double psnr(double d)
{
return -10.0 * log10(d);
}
static void do_video_stats(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->enc_ctx;
if (enc->codec_type == AVMEDIA_TYPE_VIDEO) {
frame_number = ost->st->nb_frames;
if (vstats_version <= 1) {
fprintf(vstats_file, "frame= %5d q= %2.1f ", frame_number,
ost->quality / (float)FF_QP2LAMBDA);
} else {
fprintf(vstats_file, "out= %2d st= %2d frame= %5d q= %2.1f ", ost->file_index, ost->index, frame_number,
ost->quality / (float)FF_QP2LAMBDA);
}
if (ost->error[0]>=0 && (enc->flags & AV_CODEC_FLAG_PSNR))
fprintf(vstats_file, "PSNR= %6.2f ", psnr(ost->error[0] / (enc->width * enc->height * 255.0 * 255.0)));
fprintf(vstats_file,"f_size= %6d ", frame_size);
/* compute pts value */
ti1 = av_stream_get_end_pts(ost->st) * av_q2d(ost->st->time_base);
if (ti1 < 0.01)
ti1 = 0.01;
bitrate = (frame_size * 8) / av_q2d(enc->time_base) / 1000.0;
avg_bitrate = (double)(ost->data_size * 8) / ti1 / 1000.0;
fprintf(vstats_file, "s_size= %8.0fkB time= %0.3f br= %7.1fkbits/s avg_br= %7.1fkbits/s ",
(double)ost->data_size / 1024, ti1, bitrate, avg_bitrate);
fprintf(vstats_file, "type= %c\n", av_get_picture_type_char(ost->pict_type));
}
}
static void finish_output_stream(OutputStream *ost)
{
OutputFile *of = output_files[ost->file_index];
int i;
ost->finished = ENCODER_FINISHED | MUXER_FINISHED;
if (of->shortest) {
for (i = 0; i < of->ctx->nb_streams; i++)
output_streams[of->ost_index + i]->finished = ENCODER_FINISHED | MUXER_FINISHED;
}
}
/**
* Get and encode new output from any of the filtergraphs, without causing
* activity.
*
* @return 0 for success, <0 for severe errors
*/
static int reap_filters(int flush)
{
AVFrame *filtered_frame = NULL;
int i;
/* Reap all buffers present in the buffer sinks */
for (i = 0; i < nb_output_streams; i++) {
OutputStream *ost = output_streams[i];
OutputFile *of = output_files[ost->file_index];
AVFilterContext *filter;
AVCodecContext *enc = ost->enc_ctx;
int ret = 0;
if (!ost->filter || !ost->filter->graph->graph)
continue;
filter = ost->filter->filter;
/*
* Unlike video, with audio the audio frame size matters.
* Currently we are fully reliant on the lavfi filter chain to
* do the buffering deed for us, and thus the frame size parameter
* needs to be set accordingly. Where does one get the required
* frame size? From the initialized AVCodecContext of an audio
* encoder. Thus, if we have gotten to an audio stream, initialize
* the encoder earlier than receiving the first AVFrame.
*/
if (av_buffersink_get_type(filter) == AVMEDIA_TYPE_AUDIO)
init_output_stream_wrapper(ost, NULL, 1);
if (!ost->filtered_frame && !(ost->filtered_frame = av_frame_alloc())) {
return AVERROR(ENOMEM);
}
filtered_frame = ost->filtered_frame;
while (1) {
ret = av_buffersink_get_frame_flags(filter, filtered_frame,
AV_BUFFERSINK_FLAG_NO_REQUEST);
if (ret < 0) {
if (ret != AVERROR(EAGAIN) && ret != AVERROR_EOF) {
av_log(NULL, AV_LOG_WARNING,
"Error in av_buffersink_get_frame_flags(): %s\n", av_err2str(ret));
} else if (flush && ret == AVERROR_EOF) {
if (av_buffersink_get_type(filter) == AVMEDIA_TYPE_VIDEO)
do_video_out(of, ost, NULL);
}
break;
}
if (ost->finished) {
av_frame_unref(filtered_frame);
continue;
}
switch (av_buffersink_get_type(filter)) {
case AVMEDIA_TYPE_VIDEO:
if (!ost->frame_aspect_ratio.num)
enc->sample_aspect_ratio = filtered_frame->sample_aspect_ratio;
do_video_out(of, ost, filtered_frame);
break;
case AVMEDIA_TYPE_AUDIO:
if (!(enc->codec->capabilities & AV_CODEC_CAP_PARAM_CHANGE) &&
enc->channels != filtered_frame->channels) {
av_log(NULL, AV_LOG_ERROR,
"Audio filter graph output is not normalized and encoder does not support parameter changes\n");
break;
}
do_audio_out(of, ost, filtered_frame);
break;
default:
// TODO support subtitle filters
av_assert0(0);
}
av_frame_unref(filtered_frame);
}
}
return 0;
}
static void print_final_stats(int64_t total_size)
{
uint64_t video_size = 0, audio_size = 0, extra_size = 0, other_size = 0;
uint64_t subtitle_size = 0;
uint64_t data_size = 0;
float percent = -1.0;
int i, j;
int pass1_used = 1;
for (i = 0; i < nb_output_streams; i++) {
OutputStream *ost = output_streams[i];
switch (ost->enc_ctx->codec_type) {
case AVMEDIA_TYPE_VIDEO: video_size += ost->data_size; break;
case AVMEDIA_TYPE_AUDIO: audio_size += ost->data_size; break;
case AVMEDIA_TYPE_SUBTITLE: subtitle_size += ost->data_size; break;
default: other_size += ost->data_size; break;
}
extra_size += ost->enc_ctx->extradata_size;
data_size += ost->data_size;
if ( (ost->enc_ctx->flags & (AV_CODEC_FLAG_PASS1 | AV_CODEC_FLAG_PASS2))
!= AV_CODEC_FLAG_PASS1)
pass1_used = 0;
}
if (data_size && total_size>0 && total_size >= data_size)
percent = 100.0 * (total_size - data_size) / data_size;
av_log(NULL, AV_LOG_INFO, "video:%1.0fkB audio:%1.0fkB subtitle:%1.0fkB other streams:%1.0fkB global headers:%1.0fkB muxing overhead: ",
video_size / 1024.0,
audio_size / 1024.0,
subtitle_size / 1024.0,
other_size / 1024.0,
extra_size / 1024.0);
if (percent >= 0.0)
av_log(NULL, AV_LOG_INFO, "%f%%", percent);
else
av_log(NULL, AV_LOG_INFO, "unknown");
av_log(NULL, AV_LOG_INFO, "\n");
/* print verbose per-stream stats */
for (i = 0; i < nb_input_files; i++) {
InputFile *f = input_files[i];
uint64_t total_packets = 0, total_size = 0;
av_log(NULL, AV_LOG_VERBOSE, "Input file #%d (%s):\n",
i, f->ctx->url);
for (j = 0; j < f->nb_streams; j++) {
InputStream *ist = input_streams[f->ist_index + j];
enum AVMediaType type = ist->dec_ctx->codec_type;
total_size += ist->data_size;
total_packets += ist->nb_packets;
av_log(NULL, AV_LOG_VERBOSE, " Input stream #%d:%d (%s): ",
i, j, media_type_string(type));
av_log(NULL, AV_LOG_VERBOSE, "%"PRIu64" packets read (%"PRIu64" bytes); ",
ist->nb_packets, ist->data_size);
if (ist->decoding_needed) {
av_log(NULL, AV_LOG_VERBOSE, "%"PRIu64" frames decoded",
ist->frames_decoded);
if (type == AVMEDIA_TYPE_AUDIO)
av_log(NULL, AV_LOG_VERBOSE, " (%"PRIu64" samples)", ist->samples_decoded);
av_log(NULL, AV_LOG_VERBOSE, "; ");
}
av_log(NULL, AV_LOG_VERBOSE, "\n");
}
av_log(NULL, AV_LOG_VERBOSE, " Total: %"PRIu64" packets (%"PRIu64" bytes) demuxed\n",
total_packets, total_size);
}
for (i = 0; i < nb_output_files; i++) {
OutputFile *of = output_files[i];
uint64_t total_packets = 0, total_size = 0;
av_log(NULL, AV_LOG_VERBOSE, "Output file #%d (%s):\n",
i, of->ctx->url);
for (j = 0; j < of->ctx->nb_streams; j++) {
OutputStream *ost = output_streams[of->ost_index + j];
enum AVMediaType type = ost->enc_ctx->codec_type;
total_size += ost->data_size;
total_packets += ost->packets_written;
av_log(NULL, AV_LOG_VERBOSE, " Output stream #%d:%d (%s): ",
i, j, media_type_string(type));
if (ost->encoding_needed) {
av_log(NULL, AV_LOG_VERBOSE, "%"PRIu64" frames encoded",
ost->frames_encoded);
if (type == AVMEDIA_TYPE_AUDIO)
av_log(NULL, AV_LOG_VERBOSE, " (%"PRIu64" samples)", ost->samples_encoded);
av_log(NULL, AV_LOG_VERBOSE, "; ");
}
av_log(NULL, AV_LOG_VERBOSE, "%"PRIu64" packets muxed (%"PRIu64" bytes); ",
ost->packets_written, ost->data_size);
av_log(NULL, AV_LOG_VERBOSE, "\n");
}
av_log(NULL, AV_LOG_VERBOSE, " Total: %"PRIu64" packets (%"PRIu64" bytes) muxed\n",
total_packets, total_size);
}
if(video_size + data_size + audio_size + subtitle_size + extra_size == 0){
av_log(NULL, AV_LOG_WARNING, "Output file is empty, nothing was encoded ");
if (pass1_used) {
av_log(NULL, AV_LOG_WARNING, "\n");
} else {
av_log(NULL, AV_LOG_WARNING, "(check -ss / -t / -frames parameters if used)\n");
}
}
}
static void print_report(int is_last_report, int64_t timer_start, int64_t cur_time)
{
AVBPrint buf, buf_script;
OutputStream *ost;
AVFormatContext *oc;
int64_t total_size;
AVCodecContext *enc;
int frame_number, vid, i;
double bitrate;
double speed;
int64_t pts = INT64_MIN + 1;
static int64_t last_time = -1;
static int qp_histogram[52];
int hours, mins, secs, us;
const char *hours_sign;
int ret;
float t;
if (!print_stats && !is_last_report && !progress_avio)
return;
if (!is_last_report) {
if (last_time == -1) {
last_time = cur_time;
return;
}
if ((cur_time - last_time) < 500000)
return;
last_time = cur_time;
}
t = (cur_time-timer_start) / 1000000.0;
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);
vid = 0;
av_bprint_init(&buf, 0, AV_BPRINT_SIZE_AUTOMATIC);
av_bprint_init(&buf_script, 0, AV_BPRINT_SIZE_AUTOMATIC);
for (i = 0; i < nb_output_streams; i++) {
float q = -1;
ost = output_streams[i];
enc = ost->enc_ctx;
if (!ost->stream_copy)
q = ost->quality / (float) FF_QP2LAMBDA;
if (vid && enc->codec_type == AVMEDIA_TYPE_VIDEO) {
av_bprintf(&buf, "q=%2.1f ", q);
av_bprintf(&buf_script, "stream_%d_%d_q=%.1f\n",
ost->file_index, ost->index, q);
}
if (!vid && enc->codec_type == AVMEDIA_TYPE_VIDEO) {
float fps;
frame_number = ost->frame_number;
fps = t > 1 ? frame_number / t : 0;
av_bprintf(&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=%.2f\n", fps);
av_bprintf(&buf_script, "stream_%d_%d_q=%.1f\n",
ost->file_index, ost->index, q);
if (is_last_report)
av_bprintf(&buf, "L");
if (qp_hist) {
int j;
int qp = lrintf(q);
if (qp >= 0 && qp < FF_ARRAY_ELEMS(qp_histogram))
qp_histogram[qp]++;
for (j = 0; j < 32; j++)
av_bprintf(&buf, "%X", av_log2(qp_histogram[j] + 1));
}
if ((enc->flags & AV_CODEC_FLAG_PSNR) && (ost->pict_type != AV_PICTURE_TYPE_NONE || is_last_report)) {
int j;
double error, error_sum = 0;
double scale, scale_sum = 0;
double p;
char type[3] = { 'Y','U','V' };
av_bprintf(&buf, "PSNR=");
for (j = 0; j < 3; j++) {
if (is_last_report) {
error = enc->error[j];
scale = enc->width * enc->height * 255.0 * 255.0 * frame_number;
} else {
error = ost->error[j];
scale = enc->width * enc->height * 255.0 * 255.0;
}
if (j)
scale /= 4;
error_sum += error;
scale_sum += scale;
p = psnr(error / scale);
av_bprintf(&buf, "%c:%2.2f ", type[j], p);
av_bprintf(&buf_script, "stream_%d_%d_psnr_%c=%2.2f\n",
ost->file_index, ost->index, type[j] | 32, p);
}
p = psnr(error_sum / scale_sum);
av_bprintf(&buf, "*:%2.2f ", psnr(error_sum / scale_sum));
av_bprintf(&buf_script, "stream_%d_%d_psnr_all=%2.2f\n",
ost->file_index, ost->index, p);
}
vid = 1;
}
/* compute min output value */
if (av_stream_get_end_pts(ost->st) != AV_NOPTS_VALUE) {
pts = FFMAX(pts, av_rescale_q(av_stream_get_end_pts(ost->st),
ost->st->time_base, AV_TIME_BASE_Q));
if (copy_ts) {
if (copy_ts_first_pts == AV_NOPTS_VALUE && pts > 1)
copy_ts_first_pts = pts;
if (copy_ts_first_pts != AV_NOPTS_VALUE)
pts -= copy_ts_first_pts;
}
}
if (is_last_report)
nb_frames_drop += ost->last_dropped;
}
secs = FFABS(pts) / AV_TIME_BASE;
us = FFABS(pts) % AV_TIME_BASE;
mins = secs / 60;
secs %= 60;
hours = mins / 60;
mins %= 60;
hours_sign = (pts < 0) ? "-" : "";
bitrate = pts && total_size >= 0 ? total_size * 8 / (pts / 1000.0) : -1;
speed = t != 0.0 ? (double)pts / AV_TIME_BASE / t : -1;
if (total_size < 0) av_bprintf(&buf, "size=N/A time=");
else av_bprintf(&buf, "size=%8.0fkB time=", total_size / 1024.0);
if (pts == AV_NOPTS_VALUE) {
av_bprintf(&buf, "N/A ");
} else {
av_bprintf(&buf, "%s%02d:%02d:%02d.%02d ",
hours_sign, hours, mins, secs, (100 * us) / AV_TIME_BASE);
}
if (bitrate < 0) {
av_bprintf(&buf, "bitrate=N/A");
av_bprintf(&buf_script, "bitrate=N/A\n");
}else{
av_bprintf(&buf, "bitrate=%6.1fkbits/s", bitrate);
av_bprintf(&buf_script, "bitrate=%6.1fkbits/s\n", bitrate);
}
if (total_size < 0) av_bprintf(&buf_script, "total_size=N/A\n");
else av_bprintf(&buf_script, "total_size=%"PRId64"\n", total_size);
if (pts == AV_NOPTS_VALUE) {
av_bprintf(&buf_script, "out_time_us=N/A\n");
av_bprintf(&buf_script, "out_time_ms=N/A\n");
av_bprintf(&buf_script, "out_time=N/A\n");
} else {
av_bprintf(&buf_script, "out_time_us=%"PRId64"\n", pts);
av_bprintf(&buf_script, "out_time_ms=%"PRId64"\n", pts);
av_bprintf(&buf_script, "out_time=%s%02d:%02d:%02d.%06d\n",
hours_sign, hours, mins, secs, us);
}
if (nb_frames_dup || nb_frames_drop)
av_bprintf(&buf, " dup=%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 (speed < 0) {
av_bprintf(&buf, " speed=N/A");
av_bprintf(&buf_script, "speed=N/A\n");
} else {
av_bprintf(&buf, " speed=%4.3gx", speed);
av_bprintf(&buf_script, "speed=%4.3gx\n", speed);
}
if (print_stats || is_last_report) {
const char end = is_last_report ? '\n' : '\r';
if (print_stats==1 && AV_LOG_INFO > av_log_get_level()) {
fprintf(stderr, "%s %c", buf.str, end);
} else
av_log(NULL, AV_LOG_INFO, "%s %c", buf.str, end);
fflush(stderr);
}
av_bprint_finalize(&buf, NULL);
if (progress_avio) {
av_bprintf(&buf_script, "progress=%s\n",
is_last_report ? "end" : "continue");
avio_write(progress_avio, buf_script.str,
FFMIN(buf_script.len, buf_script.size - 1));
avio_flush(progress_avio);
av_bprint_finalize(&buf_script, NULL);
if (is_last_report) {
if ((ret = avio_closep(&progress_avio)) < 0)
av_log(NULL, AV_LOG_ERROR,
"Error closing progress log, loss of information possible: %s\n", av_err2str(ret));
}
}
if (is_last_report)
print_final_stats(total_size);
}
static void ifilter_parameters_from_codecpar(InputFilter *ifilter, AVCodecParameters *par)
{
// We never got any input. Set a fake format, which will
// come from libavformat.
ifilter->format = par->format;
ifilter->sample_rate = par->sample_rate;
ifilter->channels = par->channels;
ifilter->channel_layout = par->channel_layout;
ifilter->width = par->width;
ifilter->height = par->height;
ifilter->sample_aspect_ratio = par->sample_aspect_ratio;
}
static void flush_encoders(void)
{
int i, ret;
for (i = 0; i < nb_output_streams; i++) {
OutputStream *ost = output_streams[i];
AVCodecContext *enc = ost->enc_ctx;
OutputFile *of = output_files[ost->file_index];
if (!ost->encoding_needed)
continue;
// Try to enable encoding with no input frames.
// Maybe we should just let encoding fail instead.
if (!ost->initialized) {
FilterGraph *fg = ost->filter->graph;
av_log(NULL, AV_LOG_WARNING,
"Finishing stream %d:%d without any data written to it.\n",
ost->file_index, ost->st->index);
if (ost->filter && !fg->graph) {
int x;
for (x = 0; x < fg->nb_inputs; x++) {
InputFilter *ifilter = fg->inputs[x];
if (ifilter->format < 0)
ifilter_parameters_from_codecpar(ifilter, ifilter->ist->st->codecpar);
}
if (!ifilter_has_all_input_formats(fg))
continue;
ret = configure_filtergraph(fg);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Error configuring filter graph\n");
exit_program(1);
}
finish_output_stream(ost);
}
init_output_stream_wrapper(ost, NULL, 1);
}
if (enc->codec_type != AVMEDIA_TYPE_VIDEO && enc->codec_type != AVMEDIA_TYPE_AUDIO)
continue;
for (;;) {
const char *desc = NULL;
AVPacket pkt;
int pkt_size;
switch (enc->codec_type) {
case AVMEDIA_TYPE_AUDIO:
desc = "audio";
break;
case AVMEDIA_TYPE_VIDEO:
desc = "video";
break;
default:
av_assert0(0);
}
av_init_packet(&pkt);
pkt.data = NULL;
pkt.size = 0;
update_benchmark(NULL);
while ((ret = avcodec_receive_packet(enc, &pkt)) == AVERROR(EAGAIN)) {
ret = avcodec_send_frame(enc, NULL);
if (ret < 0) {
av_log(NULL, AV_LOG_FATAL, "%s encoding failed: %s\n",
desc,
av_err2str(ret));
exit_program(1);
}
}
update_benchmark("flush_%s %d.%d", desc, ost->file_index, ost->index);
if (ret < 0 && ret != AVERROR_EOF) {
av_log(NULL, AV_LOG_FATAL, "%s encoding failed: %s\n",
desc,
av_err2str(ret));
exit_program(1);
}
if (ost->logfile && enc->stats_out) {
fprintf(ost->logfile, "%s", enc->stats_out);
}
if (ret == AVERROR_EOF) {
output_packet(of, &pkt, ost, 1);
break;
}
if (ost->finished & MUXER_FINISHED) {
av_packet_unref(&pkt);
continue;
}
av_packet_rescale_ts(&pkt, enc->time_base, ost->mux_timebase);
pkt_size = pkt.size;
output_packet(of, &pkt, ost, 0);
if (ost->enc_ctx->codec_type == AVMEDIA_TYPE_VIDEO && vstats_filename) {
do_video_stats(ost, pkt_size);
}
}
}
}
/*
* Check whether a packet from ist should be written into ost at this time
*/
static int check_output_constraints(InputStream *ist, OutputStream *ost)
{
OutputFile *of = output_files[ost->file_index];
int ist_index = input_files[ist->file_index]->ist_index + ist->st->index;
if (ost->source_index != ist_index)
return 0;
if (ost->finished)
return 0;
if (of->start_time != AV_NOPTS_VALUE && ist->pts < of->start_time)
return 0;
return 1;
}
static void do_streamcopy(InputStream *ist, OutputStream *ost, const AVPacket *pkt)
{
OutputFile *of = output_files[ost->file_index];
InputFile *f = input_files [ist->file_index];
int64_t start_time = (of->start_time == AV_NOPTS_VALUE) ? 0 : of->start_time;
int64_t ost_tb_start_time = av_rescale_q(start_time, AV_TIME_BASE_Q, ost->mux_timebase);
AVPacket opkt;
// EOF: flush output bitstream filters.
if (!pkt) {
av_init_packet(&opkt);
opkt.data = NULL;
opkt.size = 0;
output_packet(of, &opkt, ost, 1);
return;
}
if ((!ost->frame_number && !(pkt->flags & AV_PKT_FLAG_KEY)) &&
!ost->copy_initial_nonkeyframes)
return;
if (!ost->frame_number && !ost->copy_prior_start) {
int64_t comp_start = start_time;
if (copy_ts && f->start_time != AV_NOPTS_VALUE)
comp_start = FFMAX(start_time, f->start_time + f->ts_offset);
if (pkt->pts == AV_NOPTS_VALUE ?
ist->pts < comp_start :
pkt->pts < av_rescale_q(comp_start, AV_TIME_BASE_Q, ist->st->time_base))
return;
}
if (of->recording_time != INT64_MAX &&
ist->pts >= of->recording_time + start_time) {
close_output_stream(ost);
return;
}
if (f->recording_time != INT64_MAX) {
start_time = f->ctx->start_time;
if (f->start_time != AV_NOPTS_VALUE && copy_ts)
start_time += f->start_time;
if (ist->pts >= f->recording_time + start_time) {
close_output_stream(ost);
return;
}
}
/* force the input stream PTS */
if (ost->enc_ctx->codec_type == AVMEDIA_TYPE_VIDEO)
ost->sync_opts++;
if (av_packet_ref(&opkt, pkt) < 0)
exit_program(1);
if (pkt->pts != AV_NOPTS_VALUE)
opkt.pts = av_rescale_q(pkt->pts, ist->st->time_base, ost->mux_timebase) - ost_tb_start_time;
if (pkt->dts == AV_NOPTS_VALUE) {
opkt.dts = av_rescale_q(ist->dts, AV_TIME_BASE_Q, ost->mux_timebase);
} else if (ost->st->codecpar->codec_type == AVMEDIA_TYPE_AUDIO) {
int duration = av_get_audio_frame_duration(ist->dec_ctx, pkt->size);
if(!duration)
duration = ist->dec_ctx->frame_size;
opkt.dts = av_rescale_delta(ist->st->time_base, pkt->dts,
(AVRational){1, ist->dec_ctx->sample_rate}, duration,
&ist->filter_in_rescale_delta_last, ost->mux_timebase);
/* dts will be set immediately afterwards to what pts is now */
opkt.pts = opkt.dts - ost_tb_start_time;
} else
opkt.dts = av_rescale_q(pkt->dts, ist->st->time_base, ost->mux_timebase);
opkt.dts -= ost_tb_start_time;
opkt.duration = av_rescale_q(pkt->duration, ist->st->time_base, ost->mux_timebase);
output_packet(of, &opkt, ost, 0);
}
int guess_input_channel_layout(InputStream *ist)
{
AVCodecContext *dec = ist->dec_ctx;
if (!dec->channel_layout) {
char layout_name[256];
if (dec->channels > ist->guess_layout_max)
return 0;
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 void check_decode_result(InputStream *ist, int *got_output, int ret)
{
if (*got_output || ret<0)
decode_error_stat[ret<0] ++;
if (ret < 0 && exit_on_error)
exit_program(1);
if (*got_output && ist) {
if (ist->decoded_frame->decode_error_flags || (ist->decoded_frame->flags & AV_FRAME_FLAG_CORRUPT)) {
av_log(NULL, exit_on_error ? AV_LOG_FATAL : AV_LOG_WARNING,
"%s: corrupt decoded frame in stream %d\n", input_files[ist->file_index]->ctx->url, ist->st->index);
if (exit_on_error)
exit_program(1);
}
}
}
// Filters can be configured only if the formats of all inputs are known.
static int ifilter_has_all_input_formats(FilterGraph *fg)
{
int i;
for (i = 0; i < fg->nb_inputs; i++) {
if (fg->inputs[i]->format < 0 && (fg->inputs[i]->type == AVMEDIA_TYPE_AUDIO ||
fg->inputs[i]->type == AVMEDIA_TYPE_VIDEO))
return 0;
}
return 1;
}
static int ifilter_send_frame(InputFilter *ifilter, AVFrame *frame)
{
FilterGraph *fg = ifilter->graph;
int need_reinit, ret, i;
/* determine if the parameters for this input changed */
need_reinit = ifilter->format != frame->format;
switch (ifilter->ist->st->codecpar->codec_type) {
case AVMEDIA_TYPE_AUDIO:
need_reinit |= ifilter->sample_rate != frame->sample_rate ||
ifilter->channels != frame->channels ||
ifilter->channel_layout != frame->channel_layout;
break;
case AVMEDIA_TYPE_VIDEO:
need_reinit |= ifilter->width != frame->width ||
ifilter->height != frame->height;
break;
}
if (!ifilter->ist->reinit_filters && fg->graph)
need_reinit = 0;
if (!!ifilter->hw_frames_ctx != !!frame->hw_frames_ctx ||
(ifilter->hw_frames_ctx && ifilter->hw_frames_ctx->data != frame->hw_frames_ctx->data))
need_reinit = 1;
if (need_reinit) {
ret = ifilter_parameters_from_frame(ifilter, frame);
if (ret < 0)
return ret;
}
/* (re)init the graph if possible, otherwise buffer the frame and return */
if (need_reinit || !fg->graph) {
for (i = 0; i < fg->nb_inputs; i++) {
if (!ifilter_has_all_input_formats(fg)) {
AVFrame *tmp = av_frame_clone(frame);
if (!tmp)
return AVERROR(ENOMEM);
av_frame_unref(frame);
if (!av_fifo_space(ifilter->frame_queue)) {
ret = av_fifo_realloc2(ifilter->frame_queue, 2 * av_fifo_size(ifilter->frame_queue));
if (ret < 0) {
av_frame_free(&tmp);
return ret;
}
}
av_fifo_generic_write(ifilter->frame_queue, &tmp, sizeof(tmp), NULL);
return 0;
}
}
ret = reap_filters(1);
if (ret < 0 && ret != AVERROR_EOF) {
av_log(NULL, AV_LOG_ERROR, "Error while filtering: %s\n", av_err2str(ret));
return ret;
}
ret = configure_filtergraph(fg);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Error reinitializing filters!\n");
return ret;
}
}
ret = av_buffersrc_add_frame_flags(ifilter->filter, frame, AV_BUFFERSRC_FLAG_PUSH);
if (ret < 0) {
if (ret != AVERROR_EOF)
av_log(NULL, AV_LOG_ERROR, "Error while filtering: %s\n", av_err2str(ret));
return ret;
}
return 0;
}
static int ifilter_send_eof(InputFilter *ifilter, int64_t pts)
{
int ret;
ifilter->eof = 1;
if (ifilter->filter) {
ret = av_buffersrc_close(ifilter->filter, pts, AV_BUFFERSRC_FLAG_PUSH);
if (ret < 0)
return ret;
} else {
// the filtergraph was never configured
if (ifilter->format < 0)
ifilter_parameters_from_codecpar(ifilter, ifilter->ist->st->codecpar);
if (ifilter->format < 0 && (ifilter->type == AVMEDIA_TYPE_AUDIO || ifilter->type == AVMEDIA_TYPE_VIDEO)) {
av_log(NULL, AV_LOG_ERROR, "Cannot determine format of input stream %d:%d after EOF\n", ifilter->ist->file_index, ifilter->ist->st->index);
return AVERROR_INVALIDDATA;
}
}
return 0;
}
// This does not quite work like avcodec_decode_audio4/avcodec_decode_video2.
// There is the following difference: if you got a frame, you must call
// it again with pkt=NULL. pkt==NULL is treated differently from pkt->size==0
// (pkt==NULL means get more output, pkt->size==0 is a flush/drain packet)
static int decode(AVCodecContext *avctx, AVFrame *frame, int *got_frame, AVPacket *pkt)
{
int ret;
*got_frame = 0;
if (pkt) {
ret = avcodec_send_packet(avctx, pkt);
// In particular, we don't expect AVERROR(EAGAIN), because we read all
// decoded frames with avcodec_receive_frame() until done.
if (ret < 0 && ret != AVERROR_EOF)
return ret;
}
ret = avcodec_receive_frame(avctx, frame);
if (ret < 0 && ret != AVERROR(EAGAIN))
return ret;
if (ret >= 0)
*got_frame = 1;
return 0;
}
static int send_frame_to_filters(InputStream *ist, AVFrame *decoded_frame)
{
int i, ret;
AVFrame *f;
av_assert1(ist->nb_filters > 0); /* ensure ret is initialized */
for (i = 0; i < ist->nb_filters; i++) {
if (i < ist->nb_filters - 1) {
f = ist->filter_frame;
ret = av_frame_ref(f, decoded_frame);
if (ret < 0)
break;
} else
f = decoded_frame;
ret = ifilter_send_frame(ist->filters[i], f);
if (ret == AVERROR_EOF)
ret = 0; /* ignore */
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR,
"Failed to inject frame into filter network: %s\n", av_err2str(ret));
break;
}
}
return ret;
}
static int decode_audio(InputStream *ist, AVPacket *pkt, int *got_output,
int *decode_failed)
{
AVFrame *decoded_frame;
AVCodecContext *avctx = ist->dec_ctx;
int ret, err = 0;
AVRational decoded_frame_tb;
if (!ist->decoded_frame && !(ist->decoded_frame = av_frame_alloc()))
return AVERROR(ENOMEM);
if (!ist->filter_frame && !(ist->filter_frame = av_frame_alloc()))
return AVERROR(ENOMEM);
decoded_frame = ist->decoded_frame;
update_benchmark(NULL);
ret = decode(avctx, decoded_frame, got_output, pkt);
update_benchmark("decode_audio %d.%d", ist->file_index, ist->st->index);
if (ret < 0)
*decode_failed = 1;
if (ret >= 0 && avctx->sample_rate <= 0) {
av_log(avctx, AV_LOG_ERROR, "Sample rate %d invalid\n", avctx->sample_rate);
ret = AVERROR_INVALIDDATA;
}
if (ret != AVERROR_EOF)
check_decode_result(ist, got_output, ret);
if (!*got_output || ret < 0)
return ret;
ist->samples_decoded += decoded_frame->nb_samples;
ist->frames_decoded++;
/* increment next_dts to use for the case where the input stream does not
have timestamps or there are multiple frames in the packet */
ist->next_pts += ((int64_t)AV_TIME_BASE * decoded_frame->nb_samples) /
avctx->sample_rate;
ist->next_dts += ((int64_t)AV_TIME_BASE * decoded_frame->nb_samples) /
avctx->sample_rate;
if (decoded_frame->pts != AV_NOPTS_VALUE) {
decoded_frame_tb = ist->st->time_base;
} else if (pkt && pkt->pts != AV_NOPTS_VALUE) {
decoded_frame->pts = pkt->pts;
decoded_frame_tb = ist->st->time_base;
}else {
decoded_frame->pts = ist->dts;
decoded_frame_tb = AV_TIME_BASE_Q;
}
if (decoded_frame->pts != AV_NOPTS_VALUE)
decoded_frame->pts = av_rescale_delta(decoded_frame_tb, decoded_frame->pts,
(AVRational){1, avctx->sample_rate}, decoded_frame->nb_samples, &ist->filter_in_rescale_delta_last,
(AVRational){1, avctx->sample_rate});
ist->nb_samples = decoded_frame->nb_samples;
err = send_frame_to_filters(ist, decoded_frame);
av_frame_unref(ist->filter_frame);
av_frame_unref(decoded_frame);
return err < 0 ? err : ret;
}
static int decode_video(InputStream *ist, AVPacket *pkt, int *got_output, int64_t *duration_pts, int eof,
int *decode_failed)
{
AVFrame *decoded_frame;
int i, ret = 0, err = 0;
int64_t best_effort_timestamp;
int64_t dts = AV_NOPTS_VALUE;
AVPacket avpkt;
// With fate-indeo3-2, we're getting 0-sized packets before EOF for some
// reason. This seems like a semi-critical bug. Don't trigger EOF, and
// skip the packet.
if (!eof && pkt && pkt->size == 0)
return 0;
if (!ist->decoded_frame && !(ist->decoded_frame = av_frame_alloc()))
return AVERROR(ENOMEM);
if (!ist->filter_frame && !(ist->filter_frame = av_frame_alloc()))
return AVERROR(ENOMEM);
decoded_frame = ist->decoded_frame;
if (ist->dts != AV_NOPTS_VALUE)
dts = av_rescale_q(ist->dts, AV_TIME_BASE_Q, ist->st->time_base);
if (pkt) {
avpkt = *pkt;
avpkt.dts = dts; // ffmpeg.c probably shouldn't do this
}
// The old code used to set dts on the drain packet, which does not work
// with the new API anymore.
if (eof) {
void *new = av_realloc_array(ist->dts_buffer, ist->nb_dts_buffer + 1, sizeof(ist->dts_buffer[0]));
if (!new)
return AVERROR(ENOMEM);
ist->dts_buffer = new;
ist->dts_buffer[ist->nb_dts_buffer++] = dts;
}
update_benchmark(NULL);
ret = decode(ist->dec_ctx, decoded_frame, got_output, pkt ? &avpkt : NULL);
update_benchmark("decode_video %d.%d", ist->file_index, ist->st->index);
if (ret < 0)
*decode_failed = 1;
// The following line may be required in some cases where there is no parser
// or the parser does not has_b_frames correctly
if (ist->st->codecpar->video_delay < ist->dec_ctx->has_b_frames) {
if (ist->dec_ctx->codec_id == AV_CODEC_ID_H264) {
ist->st->codecpar->video_delay = ist->dec_ctx->has_b_frames;
} else
av_log(ist->dec_ctx, AV_LOG_WARNING,
"video_delay is larger in decoder than demuxer %d > %d.\n"
"If you want to help, upload a sample "
"of this file to https://streams.videolan.org/upload/ "
"and contact the ffmpeg-devel mailing list. (ffmpeg-devel@ffmpeg.org)\n",
ist->dec_ctx->has_b_frames,
ist->st->codecpar->video_delay);
}
if (ret != AVERROR_EOF)
check_decode_result(ist, got_output, ret);
if (*got_output && ret >= 0) {
if (ist->dec_ctx->width != decoded_frame->width ||
ist->dec_ctx->height != decoded_frame->height ||
ist->dec_ctx->pix_fmt != decoded_frame->format) {
av_log(NULL, AV_LOG_DEBUG, "Frame parameters mismatch context %d,%d,%d != %d,%d,%d\n",
decoded_frame->width,
decoded_frame->height,
decoded_frame->format,
ist->dec_ctx->width,
ist->dec_ctx->height,
ist->dec_ctx->pix_fmt);
}
}
if (!*got_output || ret < 0)
return ret;
if(ist->top_field_first>=0)
decoded_frame->top_field_first = ist->top_field_first;
ist->frames_decoded++;
if (ist->hwaccel_retrieve_data && decoded_frame->format == ist->hwaccel_pix_fmt) {
err = ist->hwaccel_retrieve_data(ist->dec_ctx, decoded_frame);
if (err < 0)
goto fail;
}
ist->hwaccel_retrieved_pix_fmt = decoded_frame->format;
best_effort_timestamp= decoded_frame->best_effort_timestamp;
*duration_pts = decoded_frame->pkt_duration;
if (ist->framerate.num)
best_effort_timestamp = ist->cfr_next_pts++;
if (eof && best_effort_timestamp == AV_NOPTS_VALUE && ist->nb_dts_buffer > 0) {
best_effort_timestamp = ist->dts_buffer[0];
for (i = 0; i < ist->nb_dts_buffer - 1; i++)
ist->dts_buffer[i] = ist->dts_buffer[i + 1];
ist->nb_dts_buffer--;
}
if(best_effort_timestamp != AV_NOPTS_VALUE) {
int64_t ts = av_rescale_q(decoded_frame->pts = best_effort_timestamp, ist->st->time_base, AV_TIME_BASE_Q);
if (ts != AV_NOPTS_VALUE)
ist->next_pts = ist->pts = ts;
}
if (debug_ts) {
av_log(NULL, AV_LOG_INFO, "decoder -> ist_index:%d type:video "
"frame_pts:%s frame_pts_time:%s best_effort_ts:%"PRId64" best_effort_ts_time:%s keyframe:%d frame_type:%d time_base:%d/%d\n",
ist->st->index, av_ts2str(decoded_frame->pts),
av_ts2timestr(decoded_frame->pts, &ist->st->time_base),
best_effort_timestamp,
av_ts2timestr(best_effort_timestamp, &ist->st->time_base),
decoded_frame->key_frame, decoded_frame->pict_type,
ist->st->time_base.num, ist->st->time_base.den);
}
if (ist->st->sample_aspect_ratio.num)
decoded_frame->sample_aspect_ratio = ist->st->sample_aspect_ratio;
err = send_frame_to_filters(ist, decoded_frame);
fail:
av_frame_unref(ist->filter_frame);
av_frame_unref(decoded_frame);
return err < 0 ? err : ret;
}
static int transcode_subtitles(InputStream *ist, AVPacket *pkt, int *got_output,
int *decode_failed)
{
AVSubtitle subtitle;
int free_sub = 1;
int i, ret = avcodec_decode_subtitle2(ist->dec_ctx,
&subtitle, got_output, pkt);
check_decode_result(NULL, got_output, ret);
if (ret < 0 || !*got_output) {
*decode_failed = 1;
if (!pkt->size)
sub2video_flush(ist);
return ret;
}
if (ist->fix_sub_duration) {
int end = 1;
if (ist->prev_sub.got_output) {
end = av_rescale(subtitle.pts - ist->prev_sub.subtitle.pts,
1000, AV_TIME_BASE);
if (end < ist->prev_sub.subtitle.end_display_time) {
av_log(ist->dec_ctx, AV_LOG_DEBUG,
"Subtitle duration reduced from %"PRId32" to %d%s\n",
ist->prev_sub.subtitle.end_display_time, end,
end <= 0 ? ", dropping it" : "");
ist->prev_sub.subtitle.end_display_time = end;
}
}
FFSWAP(int, *got_output, ist->prev_sub.got_output);
FFSWAP(int, ret, ist->prev_sub.ret);
FFSWAP(AVSubtitle, subtitle, ist->prev_sub.subtitle);
if (end <= 0)
goto out;
}
if (!*got_output)
return ret;
if (ist->sub2video.frame) {
sub2video_update(ist, INT64_MIN, &subtitle);
} else if (ist->nb_filters) {
if (!ist->sub2video.sub_queue)
ist->sub2video.sub_queue = av_fifo_alloc(8 * sizeof(AVSubtitle));
if (!ist->sub2video.sub_queue)
exit_program(1);
if (!av_fifo_space(ist->sub2video.sub_queue)) {
ret = av_fifo_realloc2(ist->sub2video.sub_queue, 2 * av_fifo_size(ist->sub2video.sub_queue));
if (ret < 0)
exit_program(1);
}
av_fifo_generic_write(ist->sub2video.sub_queue, &subtitle, sizeof(subtitle), NULL);
free_sub = 0;
}
if (!subtitle.num_rects)
goto out;
ist->frames_decoded++;
for (i = 0; i < nb_output_streams; i++) {
OutputStream *ost = output_streams[i];
if (!check_output_constraints(ist, ost) || !ost->encoding_needed
|| ost->enc->type != AVMEDIA_TYPE_SUBTITLE)
continue;
do_subtitle_out(output_files[ost->file_index], ost, &subtitle);
}
out:
if (free_sub)
avsubtitle_free(&subtitle);
return ret;
}
static int send_filter_eof(InputStream *ist)
{
int i, ret;
/* TODO keep pts also in stream time base to avoid converting back */
int64_t pts = av_rescale_q_rnd(ist->pts, AV_TIME_BASE_Q, ist->st->time_base,
AV_ROUND_NEAR_INF | AV_ROUND_PASS_MINMAX);
for (i = 0; i < ist->nb_filters; i++) {
ret = ifilter_send_eof(ist->filters[i], pts);
if (ret < 0)
return ret;
}
return 0;
}
/* pkt = NULL means EOF (needed to flush decoder buffers) */
static int process_input_packet(InputStream *ist, const AVPacket *pkt, int no_eof)
{
int ret = 0, i;
int repeating = 0;
int eof_reached = 0;
AVPacket avpkt;
if (!ist->saw_first_ts) {
ist->dts = ist->st->avg_frame_rate.num ? - ist->dec_ctx->has_b_frames * AV_TIME_BASE / av_q2d(ist->st->avg_frame_rate) : 0;
ist->pts = 0;
if (pkt && pkt->pts != AV_NOPTS_VALUE && !ist->decoding_needed) {
ist->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) {
/* EOF handling */
av_init_packet(&avpkt);
avpkt.data = NULL;
avpkt.size = 0;
} else {
avpkt = *pkt;
}
if (pkt && pkt->dts != AV_NOPTS_VALUE) {
ist->next_dts = ist->dts = av_rescale_q(pkt->dts, ist->st->time_base, AV_TIME_BASE_Q);
if (ist->dec_ctx->codec_type != AVMEDIA_TYPE_VIDEO || !ist->decoding_needed)
ist->next_pts = ist->pts = ist->dts;
}
// while we have more to decode or while the decoder did output something on EOF
while (ist->decoding_needed) {
int64_t duration_dts = 0;
int64_t duration_pts = 0;
int got_output = 0;
int decode_failed = 0;
ist->pts = ist->next_pts;
ist->dts = ist->next_dts;
switch (ist->dec_ctx->codec_type) {
case AVMEDIA_TYPE_AUDIO:
ret = decode_audio (ist, repeating ? NULL : &avpkt, &got_output,
&decode_failed);
break;
case AVMEDIA_TYPE_VIDEO:
ret = decode_video (ist, repeating ? NULL : &avpkt, &got_output, &duration_pts, !pkt,
&decode_failed);
if (!repeating || !pkt || got_output) {
if (pkt && pkt->duration) {
duration_dts = av_rescale_q(pkt->duration, ist->st->time_base, AV_TIME_BASE_Q);
} else if(ist->dec_ctx->framerate.num != 0 && ist->dec_ctx->framerate.den != 0) {
int ticks= av_stream_get_parser(ist->st) ? av_stream_get_parser(ist->st)->repeat_pict+1 : ist->dec_ctx->ticks_per_frame;
duration_dts = ((int64_t)AV_TIME_BASE *
ist->dec_ctx->framerate.den * ticks) /
ist->dec_ctx->framerate.num / ist->dec_ctx->ticks_per_frame;
}
if(ist->dts != AV_NOPTS_VALUE && duration_dts) {
ist->next_dts += duration_dts;
}else
ist->next_dts = AV_NOPTS_VALUE;
}
if (got_output) {
if (duration_pts > 0) {
ist->next_pts += av_rescale_q(duration_pts, ist->st->time_base, AV_TIME_BASE_Q);
} else {
ist->next_pts += duration_dts;
}
}
break;
case AVMEDIA_TYPE_SUBTITLE:
if (repeating)
break;
ret = transcode_subtitles(ist, &avpkt, &got_output, &decode_failed);
if (!pkt && ret >= 0)
ret = AVERROR_EOF;
break;
default:
return -1;
}
if (ret == AVERROR_EOF) {
eof_reached = 1;
break;
}
if (ret < 0) {
if (decode_failed) {
av_log(NULL, AV_LOG_ERROR, "Error while decoding stream #%d:%d: %s\n",
ist->file_index, ist->st->index, av_err2str(ret));
} else {
av_log(NULL, AV_LOG_FATAL, "Error while processing the decoded "
"data for stream #%d:%d\n", ist->file_index, ist->st->index);
}
if (!decode_failed || exit_on_error)
exit_program(1);
break;
}
if (got_output)
ist->got_output = 1;
if (!got_output)
break;
// During draining, we might get multiple output frames in this loop.
// ffmpeg.c does not drain the filter chain on configuration changes,
// which means if we send multiple frames at once to the filters, and
// one of those frames changes configuration, the buffered frames will
// be lost. This can upset certain FATE tests.
// Decode only 1 frame per call on EOF to appease these FATE tests.
// The ideal solution would be to rewrite decoding to use the new
// decoding API in a better way.
if (!pkt)
break;
repeating = 1;
}
/* after flushing, send an EOF on all the filter inputs attached to the stream */
/* except when looping we need to flush but not to send an EOF */
if (!pkt && ist->decoding_needed && eof_reached && !no_eof) {
int ret = send_filter_eof(ist);
if (ret < 0) {
av_log(NULL, AV_LOG_FATAL, "Error marking filters as finished\n");
exit_program(1);
}
}
/* handle stream copy */
if (!ist->decoding_needed && pkt) {
ist->dts = ist->next_dts;
switch (ist->dec_ctx->codec_type) {
case AVMEDIA_TYPE_AUDIO:
av_assert1(pkt-&g