2,543
社区成员
发帖
与我相关
我的任务
分享
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <math.h>
#include <iostream>
#ifndef M_PI
#define M_PI 3.14159265358979323846
#endif
extern "C" {
#include <libavformat/avformat.h>
#include <libswscale/swscale.h>
}
#undef exit
/* 5 seconds stream duration */
#define STREAM_DURATION 50.0
#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 */
#define INPUT_FILE ""
#define OUTPUT_FILE "test.flv";
using namespace std;
static int sws_flags = SWS_BICUBIC;
/**************************************************************/
/* audio output */
float t, tincr, tincr2;
int16_t *samples;
uint8_t *audio_outbuf;
int audio_outbuf_size;
int audio_input_frame_size;
int audioStream = -1;
AVFormatContext *InFmtCtx = NULL;
AVCodecContext *InCodecCtx = NULL;
AVCodec *Incodec = NULL;
/*
*打开一个音频文件并找到相应的解码器和编码器
*/
static int open_input_audio(const char *infile)
{
if (av_open_input_file(&InFmtCtx,infile,NULL,0,NULL)!=0)
{
cout<<"open "<<infile<<"failed!"<<endl;
return 1;
}
if(InFmtCtx==NULL)
{
cout<<"open "<<infile<<"sucess but the AVFormatContext is NULL!"<<endl;
return 1;
}
//查找文件当中的音频流
if (av_find_stream_info(InFmtCtx) < 0)
{
cout<<"find stream info failed!"<<endl;
return 1;
}
//找到第一路音频流
for (int i=0; i<InFmtCtx->nb_streams; ++i)
{
if (InFmtCtx->streams[i]->codec->codec_type == CODEC_TYPE_AUDIO)
{
audioStream = i;
break;
}
}
if (-1 == audioStream)
{
cout<<"input file have no audio stream"<<endl;
return 1;
}
//找到解码器并打开
InCodecCtx = InFmtCtx->streams[audioStream]->codec;
Incodec = avcodec_find_decoder(InCodecCtx->codec_id);
if (avcodec_open(InCodecCtx,Incodec) < 0)
{
cout<<"open decoder failed!"<<endl;
return 1;
}
dump_format(InFmtCtx,0,infile,0);
return 0;
}
/*
* add an audio output stream
*/
static AVStream *add_audio_stream(AVFormatContext *oc,int codec_id)
{
AVCodecContext *c;
AVStream *st;
st = av_new_stream(oc, 1);
if (!st) {
fprintf(stderr, "Could not alloc stream\n");
exit(1);
}
c = st->codec;
c->codec_id = CodecID(codec_id);
c->codec_type = CODEC_TYPE_AUDIO;
/* put sample parameters */
c->bit_rate = InFmtCtx->streams[audioStream]->codec->bit_rate;
c->sample_rate = InFmtCtx->streams[audioStream]->codec->sample_rate;
c->channels = InFmtCtx->streams[audioStream]->codec->channels;
return st;
}
/*
*
*/
static void open_audio(AVFormatContext *oc, AVStream *st)
{
AVCodecContext *c;
AVCodec *codec;
c = st->codec;
/* find the audio encoder */
codec = avcodec_find_encoder(c->codec_id);
if (!codec) {
fprintf(stderr, "codec not found\n");
exit(1);
}
/* open it */
if (avcodec_open(c, codec) < 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;
audio_outbuf_size = 10000;
audio_outbuf = (uint8_t *)av_malloc(audio_outbuf_size);
/* ugly hack for PCM codecs (will be removed ASAP with new PCM
support to compute the input frame size in samples */
if (c->frame_size <= 1) {
audio_input_frame_size = audio_outbuf_size / c->channels;
switch(st->codec->codec_id) {
case CODEC_ID_PCM_S16LE:
case CODEC_ID_PCM_S16BE:
case CODEC_ID_PCM_U16LE:
case CODEC_ID_PCM_U16BE:
audio_input_frame_size >>= 1;
break;
default:
break;
}
} else {
audio_input_frame_size = c->frame_size;
}
samples = (int16_t *)av_malloc(audio_input_frame_size * 2 * c->channels);
}
/* prepare a 16 bit dummy audio frame of 'frame_size' samples and
*这儿应该是从输入文件中读取一帧数据
'nb_channels' channels */
static int get_audio_frame(int16_t *samples, int frame_size, int nb_channels)
{
static AVPacket packet;
int len = -1;
if (av_read_frame(InFmtCtx, &packet)>=0)
{
int out_size = AVCODEC_MAX_AUDIO_FRAME_SIZE;
if(packet.stream_index==audioStream)
len = avcodec_decode_audio2(InCodecCtx,(short*)samples,&out_size,packet.data,packet.size);
if (len<0)
{
cout<<"decode error!\n";
return -1;
}
else
{
return 1;
}
}
else
{
return 0;
}
}
static void write_audio_frame(AVFormatContext *oc, AVStream *st)
{
AVCodecContext *c;
AVPacket pkt;
av_init_packet(&pkt);
c = st->codec;
get_audio_frame(samples, audio_input_frame_size, c->channels);
pkt.size= avcodec_encode_audio(c, audio_outbuf, audio_outbuf_size, samples);
if (c->coded_frame->pts != /*AV_NOPTS_VALUE*/0x8000000000000000)
pkt.pts= av_rescale_q(c->coded_frame->pts, c->time_base, st->time_base);
pkt.flags |= PKT_FLAG_KEY;
pkt.stream_index= st->index;
pkt.data= audio_outbuf;
/* write the compressed frame in the media file */
if (av_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);
av_free(audio_outbuf);
}
/**************************************************************/
/* video output */
AVFrame *picture, *tmp_picture;
uint8_t *video_outbuf;
int frame_count, video_outbuf_size;
/* add a video output stream */
static AVStream *add_video_stream(AVFormatContext *oc, int codec_id)
{
AVCodecContext *c;
AVStream *st;
st = av_new_stream(oc, 0);
if (!st) {
fprintf(stderr, "Could not alloc stream\n");
exit(1);
}
c = st->codec;
c->codec_id = CodecID(codec_id);
c->codec_type = CODEC_TYPE_VIDEO;
/* put sample parameters */
c->bit_rate = 400000;
/* resolution must be a multiple of two */
c->width = 352;
c->height = 288;
/* time base: 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
identically 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(!strcmp(oc->oformat->name, "mp4") || !strcmp(oc->oformat->name, "mov") || !strcmp(oc->oformat->name, "3gp"))
c->flags |= CODEC_FLAG_GLOBAL_HEADER;
return st;
}
static AVFrame *alloc_picture(int 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 = (uint8_t *)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)
{
AVCodec *codec;
AVCodecContext *c;
c = st->codec;
/* find the video encoder */
codec = avcodec_find_encoder(c->codec_id);
if (!codec) {
fprintf(stderr, "codec not found\n");
exit(1);
}
/* open the codec */
if (avcodec_open(c, codec) < 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 = (uint8_t *)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 frame 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
futur for that */
AVPacket pkt;
av_init_packet(&pkt);
pkt.flags |= PKT_FLAG_KEY;
pkt.stream_index= st->index;
pkt.data= (uint8_t *)picture;
pkt.size= sizeof(AVPicture);
ret = av_write_frame(oc, &pkt);
} else {
/* encode the image */
out_size = avcodec_encode_video(c, video_outbuf, video_outbuf_size, picture);
/* if zero size, it means the image was buffered */
if (out_size > 0) {
AVPacket pkt;
av_init_packet(&pkt);
if (c->coded_frame->pts != /*AV_NOPTS_VALUE*/0x8000000000000000)
pkt.pts= av_rescale_q(c->coded_frame->pts, c->time_base, st->time_base);
if(c->coded_frame->key_frame)
pkt.flags |= PKT_FLAG_KEY;
pkt.stream_index= st->index;
pkt.data= video_outbuf;
pkt.size= out_size;
/* write the compressed frame in the media file */
ret = av_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()
{
const char *filename = OUTPUT_FILE;
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 (open_input_audio("test.mp3") !=0)
{
cout<<"open input file failed!\n";
return -1;
}
/* auto detect the output format from the name. default is
mpeg. */
fmt = guess_format(NULL, filename, NULL);
if (!fmt) {
printf("Could not deduce output format from file extension: using MPEG.\n");
fmt = guess_format("mpeg", NULL, NULL);
}
if (!fmt) {
fprintf(stderr, "Could not find suitable output format\n");
exit(1);
}
/* allocate the output media context */
oc = av_alloc_format_context();
if (!oc) {
fprintf(stderr, "Memory error\n");
exit(1);
}
oc->oformat = fmt;
// snprintf(oc->filename, sizeof(oc->filename), "%s", filename);
/* 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);
}
/* set the output parameters (must be done even if no
parameters). */
if (av_set_parameters(oc, NULL) < 0) {
fprintf(stderr, "Invalid output format parameters\n");
exit(1);
}
dump_format(oc, 0, filename, 1);
/* 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);
/* open the output file, if needed */
if (!(fmt->flags & AVFMT_NOFILE)) {
if (url_fopen(&oc->pb, filename, URL_WRONLY) < 0) {
fprintf(stderr, "Could not open '%s'\n", filename);
exit(1);
}
}
/* write the stream header, if any */
av_write_header(oc);
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);
}
}
/* close each codec */
if (video_st)
close_video(oc, video_st);
if (audio_st)
close_audio(oc, audio_st);
/* write the trailer, if any */
av_write_trailer(oc);
/* 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 */
url_fclose(oc->pb);
}
/* free the stream */
av_free(oc);
return 0;
}
[/code]