ffmpeg/doc/examples/muxing.c

546 lines
16 KiB
C
Raw Normal View History

/*
* Copyright (c) 2003 Fabrice Bellard
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
/**
* @file
* libavformat API example.
*
* Output a media file in any supported libavformat format.
* The default codecs are used.
*/
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <math.h>
#include <libavutil/mathematics.h>
#include <libavformat/avformat.h>
#include <libswscale/swscale.h>
#undef exit
/* 5 seconds stream duration */
2011-10-02 23:05:07 +02:00
#define STREAM_DURATION 200.0
#define STREAM_FRAME_RATE 25 /* 25 images/s */
#define STREAM_NB_FRAMES ((int)(STREAM_DURATION * STREAM_FRAME_RATE))
#define STREAM_PIX_FMT PIX_FMT_YUV420P /* default pix_fmt */
static int sws_flags = SWS_BICUBIC;
/**************************************************************/
/* audio output */
static float t, tincr, tincr2;
static int16_t *samples;
static int audio_input_frame_size;
/*
* add an audio output stream
*/
static AVStream *add_audio_stream(AVFormatContext *oc, enum CodecID codec_id)
{
AVCodecContext *c;
AVStream *st;
AVCodec *codec;
/* find the audio encoder */
codec = avcodec_find_encoder(codec_id);
if (!codec) {
fprintf(stderr, "codec not found\n");
exit(1);
}
st = avformat_new_stream(oc, codec);
if (!st) {
fprintf(stderr, "Could not alloc stream\n");
exit(1);
}
st->id = 1;
c = st->codec;
/* put sample parameters */
c->sample_fmt = AV_SAMPLE_FMT_S16;
c->bit_rate = 64000;
c->sample_rate = 44100;
c->channels = 2;
// some formats want stream headers to be separate
if (oc->oformat->flags & AVFMT_GLOBALHEADER)
c->flags |= CODEC_FLAG_GLOBAL_HEADER;
return st;
}
static void open_audio(AVFormatContext *oc, AVStream *st)
{
AVCodecContext *c;
c = st->codec;
/* open it */
if (avcodec_open2(c, NULL, NULL) < 0) {
fprintf(stderr, "could not open codec\n");
exit(1);
}
/* init signal generator */
t = 0;
tincr = 2 * M_PI * 110.0 / c->sample_rate;
/* increment frequency by 110 Hz per second */
tincr2 = 2 * M_PI * 110.0 / c->sample_rate / c->sample_rate;
if (c->codec->capabilities & CODEC_CAP_VARIABLE_FRAME_SIZE)
audio_input_frame_size = 10000;
else
audio_input_frame_size = c->frame_size;
samples = av_malloc(audio_input_frame_size *
av_get_bytes_per_sample(c->sample_fmt) *
c->channels);
}
/* Prepare a 16 bit dummy audio frame of 'frame_size' samples and
* 'nb_channels' channels. */
static void get_audio_frame(int16_t *samples, int frame_size, int nb_channels)
{
int j, i, v;
int16_t *q;
q = samples;
for (j = 0; j < frame_size; j++) {
v = (int)(sin(t) * 10000);
for (i = 0; i < nb_channels; i++)
*q++ = v;
t += tincr;
tincr += tincr2;
}
}
static void write_audio_frame(AVFormatContext *oc, AVStream *st)
{
AVCodecContext *c;
AVPacket pkt = { 0 }; // data and size must be 0;
AVFrame *frame = avcodec_alloc_frame();
int got_packet;
av_init_packet(&pkt);
c = st->codec;
get_audio_frame(samples, audio_input_frame_size, c->channels);
frame->nb_samples = audio_input_frame_size;
avcodec_fill_audio_frame(frame, c->channels, c->sample_fmt,
(uint8_t *)samples,
audio_input_frame_size *
av_get_bytes_per_sample(c->sample_fmt) *
c->channels, 1);
avcodec_encode_audio2(c, &pkt, frame, &got_packet);
if (!got_packet)
return;
pkt.stream_index = st->index;
/* Write the compressed frame to the media file. */
if (av_interleaved_write_frame(oc, &pkt) != 0) {
fprintf(stderr, "Error while writing audio frame\n");
exit(1);
}
}
static void close_audio(AVFormatContext *oc, AVStream *st)
{
avcodec_close(st->codec);
av_free(samples);
}
/**************************************************************/
/* video output */
static AVFrame *picture, *tmp_picture;
static uint8_t *video_outbuf;
static int frame_count, video_outbuf_size;
/* Add a video output stream. */
static AVStream *add_video_stream(AVFormatContext *oc, enum CodecID codec_id)
{
AVCodecContext *c;
AVStream *st;
AVCodec *codec;
/* find the video encoder */
codec = avcodec_find_encoder(codec_id);
if (!codec) {
fprintf(stderr, "codec not found\n");
exit(1);
}
st = avformat_new_stream(oc, codec);
if (!st) {
fprintf(stderr, "Could not alloc stream\n");
exit(1);
}
c = st->codec;
/* find the video encoder */
codec = avcodec_find_encoder(codec_id);
if (!codec) {
fprintf(stderr, "codec not found\n");
exit(1);
}
avcodec_get_context_defaults3(c, codec);
c->codec_id = codec_id;
/* Put sample parameters. */
c->bit_rate = 400000;
/* Resolution must be a multiple of two. */
c->width = 352;
c->height = 288;
/* timebase: This is the fundamental unit of time (in seconds) in terms
* of which frame timestamps are represented. For fixed-fps content,
* timebase should be 1/framerate and timestamp increments should be
* identical to 1. */
c->time_base.den = STREAM_FRAME_RATE;
c->time_base.num = 1;
c->gop_size = 12; /* emit one intra frame every twelve frames at most */
c->pix_fmt = STREAM_PIX_FMT;
if (c->codec_id == CODEC_ID_MPEG2VIDEO) {
/* just for testing, we also add B frames */
c->max_b_frames = 2;
}
if (c->codec_id == CODEC_ID_MPEG1VIDEO) {
/* Needed to avoid using macroblocks in which some coeffs overflow.
* This does not happen with normal video, it just happens here as
* the motion of the chroma plane does not match the luma plane. */
c->mb_decision = 2;
}
/* Some formats want stream headers to be separate. */
if (oc->oformat->flags & AVFMT_GLOBALHEADER)
c->flags |= CODEC_FLAG_GLOBAL_HEADER;
return st;
}
static AVFrame *alloc_picture(enum PixelFormat pix_fmt, int width, int height)
{
AVFrame *picture;
uint8_t *picture_buf;
int size;
picture = avcodec_alloc_frame();
if (!picture)
return NULL;
size = avpicture_get_size(pix_fmt, width, height);
picture_buf = av_malloc(size);
if (!picture_buf) {
av_free(picture);
return NULL;
}
avpicture_fill((AVPicture *)picture, picture_buf,
pix_fmt, width, height);
return picture;
}
static void open_video(AVFormatContext *oc, AVStream *st)
{
AVCodecContext *c;
c = st->codec;
/* open the codec */
if (avcodec_open2(c, NULL, NULL) < 0) {
fprintf(stderr, "could not open codec\n");
exit(1);
}
video_outbuf = NULL;
if (!(oc->oformat->flags & AVFMT_RAWPICTURE)) {
/* Allocate output buffer. */
/* XXX: API change will be done. */
/* Buffers passed into lav* can be allocated any way you prefer,
* as long as they're aligned enough for the architecture, and
* they're freed appropriately (such as using av_free for buffers
* allocated with av_malloc). */
video_outbuf_size = 200000;
video_outbuf = av_malloc(video_outbuf_size);
}
/* Allocate the encoded raw picture. */
picture = alloc_picture(c->pix_fmt, c->width, c->height);
if (!picture) {
fprintf(stderr, "Could not allocate picture\n");
exit(1);
}
/* If the output format is not YUV420P, then a temporary YUV420P
* picture is needed too. It is then converted to the required
* output format. */
tmp_picture = NULL;
if (c->pix_fmt != PIX_FMT_YUV420P) {
tmp_picture = alloc_picture(PIX_FMT_YUV420P, c->width, c->height);
if (!tmp_picture) {
fprintf(stderr, "Could not allocate temporary picture\n");
exit(1);
}
}
}
/* Prepare a dummy image. */
static void fill_yuv_image(AVFrame *pict, int frame_index,
int width, int height)
{
int x, y, i;
i = frame_index;
/* Y */
for (y = 0; y < height; y++)
for (x = 0; x < width; x++)
pict->data[0][y * pict->linesize[0] + x] = x + y + i * 3;
/* Cb and Cr */
for (y = 0; y < height / 2; y++) {
for (x = 0; x < width / 2; x++) {
pict->data[1][y * pict->linesize[1] + x] = 128 + y + i * 2;
pict->data[2][y * pict->linesize[2] + x] = 64 + x + i * 5;
}
}
}
static void write_video_frame(AVFormatContext *oc, AVStream *st)
{
int out_size, ret;
AVCodecContext *c;
static struct SwsContext *img_convert_ctx;
c = st->codec;
if (frame_count >= STREAM_NB_FRAMES) {
/* No more frames to compress. The codec has a latency of a few
* frames if using B-frames, so we get the last frames by
* passing the same picture again. */
} else {
if (c->pix_fmt != PIX_FMT_YUV420P) {
/* as we only generate a YUV420P picture, we must convert it
* to the codec pixel format if needed */
if (img_convert_ctx == NULL) {
img_convert_ctx = sws_getContext(c->width, c->height,
PIX_FMT_YUV420P,
c->width, c->height,
c->pix_fmt,
sws_flags, NULL, NULL, NULL);
if (img_convert_ctx == NULL) {
fprintf(stderr,
"Cannot initialize the conversion context\n");
exit(1);
}
}
fill_yuv_image(tmp_picture, frame_count, c->width, c->height);
sws_scale(img_convert_ctx, tmp_picture->data, tmp_picture->linesize,
0, c->height, picture->data, picture->linesize);
} else {
fill_yuv_image(picture, frame_count, c->width, c->height);
}
}
if (oc->oformat->flags & AVFMT_RAWPICTURE) {
/* Raw video case - the API will change slightly in the near
* future for that. */
AVPacket pkt;
av_init_packet(&pkt);
pkt.flags |= AV_PKT_FLAG_KEY;
pkt.stream_index = st->index;
pkt.data = (uint8_t *)picture;
pkt.size = sizeof(AVPicture);
ret = av_interleaved_write_frame(oc, &pkt);
} else {
/* encode the image */
out_size = avcodec_encode_video(c, video_outbuf,
video_outbuf_size, picture);
/* If size is zero, it means the image was buffered. */
if (out_size > 0) {
AVPacket pkt;
av_init_packet(&pkt);
if (c->coded_frame->pts != AV_NOPTS_VALUE)
pkt.pts = av_rescale_q(c->coded_frame->pts,
c->time_base, st->time_base);
if (c->coded_frame->key_frame)
pkt.flags |= AV_PKT_FLAG_KEY;
pkt.stream_index = st->index;
pkt.data = video_outbuf;
pkt.size = out_size;
/* Write the compressed frame to the media file. */
ret = av_interleaved_write_frame(oc, &pkt);
} else {
ret = 0;
}
}
if (ret != 0) {
fprintf(stderr, "Error while writing video frame\n");
exit(1);
}
frame_count++;
}
static void close_video(AVFormatContext *oc, AVStream *st)
{
avcodec_close(st->codec);
av_free(picture->data[0]);
av_free(picture);
if (tmp_picture) {
av_free(tmp_picture->data[0]);
av_free(tmp_picture);
}
av_free(video_outbuf);
}
/**************************************************************/
/* media file output */
int main(int argc, char **argv)
{
const char *filename;
AVOutputFormat *fmt;
AVFormatContext *oc;
AVStream *audio_st, *video_st;
double audio_pts, video_pts;
int i;
/* Initialize libavcodec, and register all codecs and formats. */
av_register_all();
if (argc != 2) {
printf("usage: %s output_file\n"
"API example program to output a media file with libavformat.\n"
"The output format is automatically guessed according to the file extension.\n"
"Raw images can also be output by using '%%d' in the filename\n"
"\n", argv[0]);
return 1;
}
filename = argv[1];
/* allocate the output media context */
avformat_alloc_output_context2(&oc, NULL, NULL, filename);
if (!oc) {
printf("Could not deduce output format from file extension: using MPEG.\n");
avformat_alloc_output_context2(&oc, NULL, "mpeg", filename);
}
if (!oc) {
return 1;
}
fmt = oc->oformat;
/* Add the audio and video streams using the default format codecs
* and initialize the codecs. */
video_st = NULL;
audio_st = NULL;
if (fmt->video_codec != CODEC_ID_NONE) {
video_st = add_video_stream(oc, fmt->video_codec);
}
if (fmt->audio_codec != CODEC_ID_NONE) {
audio_st = add_audio_stream(oc, fmt->audio_codec);
}
/* Now that all the parameters are set, we can open the audio and
* video codecs and allocate the necessary encode buffers. */
if (video_st)
open_video(oc, video_st);
if (audio_st)
open_audio(oc, audio_st);
av_dump_format(oc, 0, filename, 1);
/* open the output file, if needed */
if (!(fmt->flags & AVFMT_NOFILE)) {
if (avio_open(&oc->pb, filename, AVIO_FLAG_WRITE) < 0) {
fprintf(stderr, "Could not open '%s'\n", filename);
return 1;
}
}
/* Write the stream header, if any. */
avformat_write_header(oc, NULL);
picture->pts = 0;
for (;;) {
/* Compute current audio and video time. */
if (audio_st)
audio_pts = (double)audio_st->pts.val * audio_st->time_base.num / audio_st->time_base.den;
else
audio_pts = 0.0;
if (video_st)
video_pts = (double)video_st->pts.val * video_st->time_base.num /
video_st->time_base.den;
else
video_pts = 0.0;
if ((!audio_st || audio_pts >= STREAM_DURATION) &&
(!video_st || video_pts >= STREAM_DURATION))
break;
/* write interleaved audio and video frames */
if (!video_st || (video_st && audio_st && audio_pts < video_pts)) {
write_audio_frame(oc, audio_st);
} else {
write_video_frame(oc, video_st);
picture->pts++;
}
}
/* Write the trailer, if any. The trailer must be written before you
* close the CodecContexts open when you wrote the header; otherwise
* av_write_trailer() may try to use memory that was freed on
* av_codec_close(). */
av_write_trailer(oc);
/* Close each codec. */
if (video_st)
close_video(oc, video_st);
if (audio_st)
close_audio(oc, audio_st);
/* Free the streams. */
for (i = 0; i < oc->nb_streams; i++) {
av_freep(&oc->streams[i]->codec);
av_freep(&oc->streams[i]);
}
if (!(fmt->flags & AVFMT_NOFILE))
/* Close the output file. */
avio_close(oc->pb);
/* free the stream */
av_free(oc);
return 0;
}