FFmpeg+SDL实现播放器

 一、序言：

 

     之前做嵌入式移动端设备播放都是基于Android平台的（SurfaceView显示+AudioTrack播放声音），要么是linux系统直接ffmpeg解码音视频数据后用framebuffer显示和tinyalsa播放声音，做好音视频同步。鉴于本文是用于学习入门ffmpeg的所以选择Ubuntu系统平台，省去大家去搭建Android或嵌入式linux开发环境。这三种平台都是大同小异的。

二、SDL播放wav文件代码

   先来看看sdl播放pcm的简单例子，比起Android的AudioTrack和直接用tinyalsa的pcm_open,pcm_write,pcm_close方式有些抽象。编译命令：

gcc -o mypcm mypcm.c -I /usr/local/include/SDL2/ -lSDL2

#include
#include

#include 

#define BUFFER_SIZE 81920

#define ID_RIFF 0x46464952
#define ID_WAVE 0x45564157
#define ID_FMT  0x20746d66
#define ID_DATA 0x61746164

struct riff_wave_header {
    uint32_t riff_id;
    uint32_t riff_sz;
    uint32_t wave_id;
};

struct chunk_header {
    uint32_t id;
    uint32_t sz;
};

struct chunk_fmt {
    uint16_t audio_format;
    uint16_t num_channels;
    uint32_t sample_rate;
    uint32_t byte_rate;
    uint16_t block_align;
    uint16_t bits_per_sample;
};


static Uint8      *data_buf       = NULL;
static Uint8      *consume_pos    = NULL;
static uint32_t   data_len        = 0;

void consume_audio_data(void *udata, Uint8 *stream, int len){

    if(data_len == 0){
		printf("consume_audio_data data_len == 0 return \n");
		return;
    }
	
    SDL_memset(stream, 0, len);

    len = (len < data_len) ? len : data_len;
    SDL_MixAudio(stream, consume_pos, len, SDL_MIX_MAXVOLUME);
	consume_pos += len;
}

int main(int argc, char *argv[]){
	
	FILE *wavFd = NULL;
	SDL_AudioSpec spec;
	int more_chunks = 1;
    struct riff_wave_header riff_wave_header;
    struct chunk_header chunk_header;
    struct chunk_fmt chunk_fmt;
	
	if(argc < 2) {
		printf("\n\n/Usage:./main xxxx.wav/\n");
	}
    //初始化SDL
    if(SDL_Init(SDL_INIT_VIDEO | SDL_INIT_AUDIO | SDL_INIT_TIMER)){
        printf("Could not initialize SDL - %s\n", SDL_GetError());
        return -1;
    }
	
    //打开wav文件
    wavFd = fopen(argv[1], "rb");
    if(!wavFd){
        fprintf(stderr, "Failed to open pcm file!\n");
        goto __FAIL;
    }
	
	//读取wav文件头
	fread(&riff_wave_header, sizeof(riff_wave_header), 1, wavFd);
	
    if ((riff_wave_header.riff_id != ID_RIFF) ||
        (riff_wave_header.wave_id != ID_WAVE)) {
        fprintf(stderr, "Error: '%s' is not a riff/wave file\n", argv[1]);
        fclose(wavFd);
        goto __FAIL;
    }
	
    do {
        fread(&chunk_header, sizeof(chunk_header), 1, wavFd);

        switch (chunk_header.id) {
        case ID_FMT:
            fread(&chunk_fmt, sizeof(chunk_fmt), 1, wavFd);
            if (chunk_header.sz > sizeof(chunk_fmt))
                fseek(wavFd, chunk_header.sz - sizeof(chunk_fmt), SEEK_CUR);
            break;
        case ID_DATA:
            more_chunks = 0;
            chunk_header.sz = le32toh(chunk_header.sz);
            break;
        default:
            fseek(wavFd, chunk_header.sz, SEEK_CUR);
        }
    } while (more_chunks);
	
    //分配buffer
    data_buf = (Uint8*)malloc(BUFFER_SIZE);
    if(!data_buf){
		printf("malloc data_buf fail!\n");
        goto __FAIL;
    }	
	//填充结构体各字段			
    spec.freq = chunk_fmt.sample_rate;
	
	switch (chunk_fmt.bits_per_sample){
			
		case 16:
			spec.format = AUDIO_S16SYS;//AUDIO_U16SYS;
			break;
			
		case 32:
			spec.format = AUDIO_S32SYS;
			break;	
			
		default:
			printf("not support this format\n");
			goto __FAIL;
	}
    
    spec.channels = chunk_fmt.num_channels;
    spec.silence = 0;
    spec.samples = 2048;
    spec.callback = consume_audio_data;//回调函数由SDL内部线程调用
    spec.userdata = NULL;	
	printf("spec.channels=%d,spec.freq=%d, chunk_fmt.bits_per_sample=%d\n", spec.channels, spec.freq, chunk_fmt.bits_per_sample);
    //打开sdl audio设备
    if(SDL_OpenAudio(&spec, NULL)){
        fprintf(stderr, "Failed to open audio device, %s\n", SDL_GetError());
        goto __FAIL;
    }

    //0:播放，1:暂停
    SDL_PauseAudio(0);	
	do{
        //读取pcm数据
        data_len = fread(data_buf, 1, BUFFER_SIZE, wavFd);
      //  fprintf(stderr, "fread data_len = %d\n", data_len);
		consume_pos = data_buf;
        //sdl内部线程还没有播放完数据，这里延时等待
        while(consume_pos < (data_buf + data_len)) {
           SDL_Delay(1);
        }

    }while(data_len !=0);
	
    SDL_CloseAudio();
	
__FAIL:	
    if(data_buf){
        free(data_buf);
    }

    if(wavFd){
        fclose(wavFd);
    }

    SDL_Quit();	
}

三、SDL显示YUV数据

可以自己用ffmpeg命令把mp4转成yuv。

ffmpeg -i U1.mp4 -ss 00:00:20 -t 10 -s 320x240 -pix_fmt yuv420p U1_320X240_yuv420p.yuv

编译命令：

gcc -o myplayer myplayer .c -I /usr/local/include/SDL2/ -lSDL2

执行：./myplayer ../../U1_320X240_yuv420p.yuv

#include 
#include 

#include 


//event message
#define REFRESH_EVENT  (SDL_USEREVENT + 1)
#define QUIT_EVENT  (SDL_USEREVENT + 2)

int thread_exit = 0;

int refresh_video(void *udata){

    thread_exit=0;

    while (!thread_exit) {
        SDL_Event event;
        event.type = REFRESH_EVENT;
        SDL_PushEvent(&event);
//40ms就是25帧
        SDL_Delay(40);
    }

    thread_exit=0;

    //push quit event
    SDL_Event event;
    event.type = QUIT_EVENT;
    SDL_PushEvent(&event);

    return 0;
}

int main(int argc, char* argv[])
{

    FILE *file_fd = NULL;

    SDL_Event event;
    SDL_Rect rect;

    Uint32 pixformat = 0;
    Uint8 *frame_buf = NULL;
    SDL_Window *win = NULL;
    SDL_Renderer *renderer = NULL;
    SDL_Texture *texture = NULL;

    SDL_Thread *refresh_thread = NULL;

    int video_width = 320, video_height = 240;
    //yuv每个像素使用1.5byte
    unsigned int yuv_frame_size = video_width * video_height * 12 / 8;


    frame_buf = malloc(yuv_frame_size);
    memset(frame_buf, 0, yuv_frame_size);


    //initialize SDL
    if(SDL_Init(SDL_INIT_VIDEO)) {
        fprintf( stderr, "Could not initialize SDL - %s\n", SDL_GetError());
        return -1;
    }

    //creat window from SDL
    win = SDL_CreateWindow("YUV Player",
                           SDL_WINDOWPOS_UNDEFINED,
                           SDL_WINDOWPOS_UNDEFINED,
                           video_width, video_height,
                           SDL_WINDOW_OPENGL);
    if(!win) {
        fprintf(stderr, "Failed to create window, %s\n",SDL_GetError());
        goto __FAIL;
    }

    renderer = SDL_CreateRenderer(win, -1, 0);

    //IYUV: Y + U + V  (3 planes)
    //YV12: Y + V + U  (3 planes)
    pixformat= SDL_PIXELFORMAT_IYUV;

    //create texture for render
    texture = SDL_CreateTexture(renderer,
                                pixformat,
                                SDL_TEXTUREACCESS_STREAMING,
                                video_width,
                                video_height);

    //open yuv file
    file_fd = fopen(argv[1], "rb");
    if( !file_fd ){
        fprintf(stderr, "Failed to open yuv file\n");
        goto __FAIL;
    }

    refresh_thread = SDL_CreateThread(refresh_video,“refresh_video”,NULL);

    do {
        //Wait
        SDL_WaitEvent(&event);
        if(event.type==REFRESH_EVENT){
            memset(frame_buf, 0, yuv_frame_size);
            fread(frame_buf, 1, yuv_frame_size, file_fd);
			//更新纹理
            SDL_UpdateTexture(texture, NULL, frame_buf, video_width);

            rect.x = 0;
            rect.y = 0;
            rect.w = video_width;
            rect.h = video_height;
			//清除渲染器，把纹理复制到渲染器，然后显示。
            SDL_RenderClear(renderer);
            SDL_RenderCopy(renderer, texture, NULL, &rect);
            SDL_RenderPresent(renderer);

        }else if(event.type==SDL_QUIT){
            thread_exit = 1;
        }else if(event.type==QUIT_EVENT){
            break;
        }
    }while ( 1 );

__FAIL:

    //close file
    if(file_fd){
        fclose(file_fd);
    }

    SDL_Quit();

    return 0;
}

四、完整的视频播放器

        前面我们单独实现了简单的音乐播放和yuv视频播放。一个完整的播放器还需要解封装分离视频和音频数据，音视频数据解码以及音视频播放同步机制，也就是把上面两个demo组合起来加上ffmpeg解封装，解码和音视频同步就是一个完整的视频播放器啦。

编译命令：

gcc -o player6 player6.c  -I /usr/local/include/SDL2/ -lSDL2 -lavcodec -lavutil -lavformat -lswresample -lswscale

完整的例子（参考ffplay源码精简的）

#include 
#include 
#include 

#include 

#include 
#include 
#include 
#include 

// compatibility with newer API
#if LIBAVCODEC_VERSION_INT < AV_VERSION_INT(55,28,1)
#define av_frame_alloc avcodec_alloc_frame
#define av_frame_free avcodec_free_frame
#endif

#define SDL_AUDIO_BUFFER_SIZE 1024
#define MAX_AUDIO_FRAME_SIZE 192000 //channels(2) * data_size(2) * sample_rate(48000)

#define MAX_AUDIOQ_SIZE (5 * 16 * 1024)
#define MAX_VIDEOQ_SIZE (5 * 256 * 1024)

#define AV_SYNC_THRESHOLD 0.01
#define AV_NOSYNC_THRESHOLD 10.0

#define SAMPLE_CORRECTION_PERCENT_MAX 10
#define AUDIO_DIFF_AVG_NB 20

#define FF_REFRESH_EVENT (SDL_USEREVENT)
#define FF_QUIT_EVENT (SDL_USEREVENT + 1)

#define VIDEO_PICTURE_QUEUE_SIZE 1

#define DEFAULT_AV_SYNC_TYPE AV_SYNC_AUDIO_MASTER //AV_SYNC_VIDEO_MASTER

typedef struct PacketQueue {
  AVPacketList *first_pkt, *last_pkt;
  int nb_packets;
  int size;
  SDL_mutex *mutex;
  SDL_cond *cond;
} PacketQueue;


typedef struct VideoPicture {
  AVPicture *bmp;
  int width, height; /* source height & width */
  int allocated;
  double pts;
} VideoPicture;

typedef struct VideoState {

  //multi-media file
  char            filename[1024];
  AVFormatContext *pFormatCtx;
  int             videoStream, audioStream;

  //sync
  int             av_sync_type;
  double          external_clock; /* external clock base */
  int64_t         external_clock_time;

  double          audio_diff_cum; /* used for AV difference average computation */
  double          audio_diff_avg_coef;
  double          audio_diff_threshold;
  int             audio_diff_avg_count;

  double          audio_clock;
  double          frame_timer;
  double          frame_last_pts;
  double          frame_last_delay;

  double          video_clock; ///mutex = SDL_CreateMutex();
  q->cond = SDL_CreateCond();
}
int packet_queue_put(PacketQueue *q, AVPacket *pkt) {

  AVPacketList *pkt1;
  if(av_dup_packet(pkt) < 0) {
    return -1;
  }
  pkt1 = av_malloc(sizeof(AVPacketList));
  if (!pkt1)
    return -1;
  pkt1->pkt = *pkt;
  pkt1->next = NULL;
  
  SDL_LockMutex(q->mutex);

  if (!q->last_pkt)
    q->first_pkt = pkt1;
  else
    q->last_pkt->next = pkt1;
  q->last_pkt = pkt1;
  q->nb_packets++;
  q->size += pkt1->pkt.size;
  SDL_CondSignal(q->cond);
  
  SDL_UnlockMutex(q->mutex);
  return 0;
}

int packet_queue_get(PacketQueue *q, AVPacket *pkt, int block)
{
  AVPacketList *pkt1;
  int ret;

  SDL_LockMutex(q->mutex);
  
  for(;;) {
    
    if(global_video_state->quit) {
      ret = -1;
      break;
    }

    pkt1 = q->first_pkt;
    if (pkt1) {
      q->first_pkt = pkt1->next;
      if (!q->first_pkt)
	q->last_pkt = NULL;
      q->nb_packets--;
      q->size -= pkt1->pkt.size;
      *pkt = pkt1->pkt;
      av_free(pkt1);
      ret = 1;
      break;
    } else if (!block) {
      ret = 0;
      break;
    } else {
      SDL_CondWait(q->cond, q->mutex);
    }
  }
  SDL_UnlockMutex(q->mutex);
  return ret;
}

double get_audio_clock(VideoState *is) {
  double pts;
  int hw_buf_size, bytes_per_sec, n;
  
  pts = is->audio_clock; /* maintained in the audio thread */
  hw_buf_size = is->audio_buf_size - is->audio_buf_index;
  bytes_per_sec = 0;
  n = is->audio_ctx->channels * 2;
  if(is->audio_st) {
    bytes_per_sec = is->audio_ctx->sample_rate * n;
  }
  if(bytes_per_sec) {
    pts -= (double)hw_buf_size / bytes_per_sec;
  }
  return pts;
}
double get_video_clock(VideoState *is) {
  double delta;

  delta = (av_gettime() - is->video_current_pts_time) / 1000000.0;
  return is->video_current_pts + delta;
}
double get_external_clock(VideoState *is) {
  return av_gettime() / 1000000.0;
}

double get_master_clock(VideoState *is) {
  if(is->av_sync_type == AV_SYNC_VIDEO_MASTER) {
    return get_video_clock(is);
  } else if(is->av_sync_type == AV_SYNC_AUDIO_MASTER) {
    return get_audio_clock(is);
  } else {
    return get_external_clock(is);
  }
}


/* Add or subtract samples to get a better sync, return new
   audio buffer size */
int synchronize_audio(VideoState *is, short *samples,
		      int samples_size, double pts) {
  int n;
  double ref_clock;

  n = 2 * is->audio_ctx->channels;
  
  if(is->av_sync_type != AV_SYNC_AUDIO_MASTER) {
    double diff, avg_diff;
    int wanted_size, min_size, max_size /*, nb_samples */;
    
    ref_clock = get_master_clock(is);
    diff = get_audio_clock(is) - ref_clock;

    if(diff < AV_NOSYNC_THRESHOLD) {
      // accumulate the diffs
      is->audio_diff_cum = diff + is->audio_diff_avg_coef
	* is->audio_diff_cum;
      if(is->audio_diff_avg_count < AUDIO_DIFF_AVG_NB) {
	is->audio_diff_avg_count++;
      } else {
	avg_diff = is->audio_diff_cum * (1.0 - is->audio_diff_avg_coef);
	if(fabs(avg_diff) >= is->audio_diff_threshold) {
	  wanted_size = samples_size + ((int)(diff * is->audio_ctx->sample_rate) * n);
	  min_size = samples_size * ((100 - SAMPLE_CORRECTION_PERCENT_MAX) / 100);
	  max_size = samples_size * ((100 + SAMPLE_CORRECTION_PERCENT_MAX) / 100);
	  if(wanted_size < min_size) {
	    wanted_size = min_size;
	  } else if (wanted_size > max_size) {
	    wanted_size = max_size;
	  }
	  if(wanted_size < samples_size) {
	    /* remove samples */
	    samples_size = wanted_size;
	  } else if(wanted_size > samples_size) {
	    uint8_t *samples_end, *q;
	    int nb;

	    /* add samples by copying final sample*/
	    nb = (samples_size - wanted_size);
	    samples_end = (uint8_t *)samples + samples_size - n;
	    q = samples_end + n;
	    while(nb > 0) {
	      memcpy(q, samples_end, n);
	      q += n;
	      nb -= n;
	    }
	    samples_size = wanted_size;
	  }
	}
      }
    } else {
      /* difference is TOO big; reset diff stuff */
      is->audio_diff_avg_count = 0;
      is->audio_diff_cum = 0;
    }
  }
  return samples_size;
}

int audio_decode_frame(VideoState *is, uint8_t *audio_buf, int buf_size, double *pts_ptr) {

  int len1, data_size = 0;
  AVPacket *pkt = &is->audio_pkt;
  double pts;
  int n;


  for(;;) {
    while(is->audio_pkt_size > 0) {
      int got_frame = 0;
      len1 = avcodec_decode_audio4(is->audio_ctx, &is->audio_frame, &got_frame, pkt);
      if(len1 < 0) {
	/* if error, skip frame */
	is->audio_pkt_size = 0;
	break;
      }
      data_size = 0;
      if(got_frame) {
        /*
	data_size = av_samples_get_buffer_size(NULL, 
					       is->audio_ctx->channels,
					       is->audio_frame.nb_samples,
					       is->audio_ctx->sample_fmt,
					       1);
        */
        data_size = 2 * is->audio_frame.nb_samples * 2;
	assert(data_size <= buf_size);

        swr_convert(is->audio_swr_ctx,
                        &audio_buf,
                        MAX_AUDIO_FRAME_SIZE*3/2,
                        (const uint8_t **)is->audio_frame.data,
                        is->audio_frame.nb_samples);

        fwrite(audio_buf, 1, data_size, audiofd);
	//memcpy(audio_buf, is->audio_frame.data[0], data_size);
      }
      is->audio_pkt_data += len1;
      is->audio_pkt_size -= len1;
      if(data_size <= 0) {
	/* No data yet, get more frames */
	continue;
      }
      pts = is->audio_clock;
      *pts_ptr = pts;
      n = 2 * is->audio_ctx->channels;
      is->audio_clock += (double)data_size /
	(double)(n * is->audio_ctx->sample_rate);
      /* We have data, return it and come back for more later */
      return data_size;
    }
    if(pkt->data)
      av_free_packet(pkt);

    if(is->quit) {
      return -1;
    }
    /* next packet */
    if(packet_queue_get(&is->audioq, pkt, 1) < 0) {
      return -1;
    }
    is->audio_pkt_data = pkt->data;
    is->audio_pkt_size = pkt->size;
    /* if update, update the audio clock w/pts */
    if(pkt->pts != AV_NOPTS_VALUE) {
      is->audio_clock = av_q2d(is->audio_st->time_base)*pkt->pts;
    }
  }
}

void audio_callback(void *userdata, Uint8 *stream, int len) {

  VideoState *is = (VideoState *)userdata;
  int len1, audio_size;
  double pts;

  SDL_memset(stream, 0, len);

  while(len > 0) {
    if(is->audio_buf_index >= is->audio_buf_size) {
      /* We have already sent all our data; get more */
      audio_size = audio_decode_frame(is, is->audio_buf, sizeof(is->audio_buf), &pts);
      if(audio_size < 0) {
	/* If error, output silence */
	is->audio_buf_size = 1024 * 2 * 2;
	memset(is->audio_buf, 0, is->audio_buf_size);
      } else {
	audio_size = synchronize_audio(is, (int16_t *)is->audio_buf,
				       audio_size, pts);
	is->audio_buf_size = audio_size;
      }
      is->audio_buf_index = 0;
    }
    len1 = is->audio_buf_size - is->audio_buf_index;
    if(len1 > len)
      len1 = len;
    SDL_MixAudio(stream,(uint8_t *)is->audio_buf + is->audio_buf_index, len1, SDL_MIX_MAXVOLUME);
    //memcpy(stream, (uint8_t *)is->audio_buf + is->audio_buf_index, len1);
    len -= len1;
    stream += len1;
    is->audio_buf_index += len1;
  }
}

static Uint32 sdl_refresh_timer_cb(Uint32 interval, void *opaque) {
  SDL_Event event;
  event.type = FF_REFRESH_EVENT;
  event.user.data1 = opaque;
  SDL_PushEvent(&event);
  return 0; /* 0 means stop timer */
}

/* schedule a video refresh in 'delay' ms */
static void schedule_refresh(VideoState *is, int delay) {
  SDL_AddTimer(delay, sdl_refresh_timer_cb, is);
}

void video_display(VideoState *is) {

  SDL_Rect rect;
  VideoPicture *vp;
  float aspect_ratio;
  int w, h, x, y;
  int i;

  vp = &is->pictq[is->pictq_rindex];
  if(vp->bmp) {

    SDL_UpdateYUVTexture( texture, NULL, 
                          vp->bmp->data[0], vp->bmp->linesize[0],
                          vp->bmp->data[1], vp->bmp->linesize[1],
                          vp->bmp->data[2], vp->bmp->linesize[2]);

    rect.x = 0;
    rect.y = 0;
    rect.w = is->video_ctx->width;
    rect.h = is->video_ctx->height;
    SDL_LockMutex(text_mutex);
    SDL_RenderClear( renderer );
    SDL_RenderCopy( renderer, texture, NULL, &rect);
    SDL_RenderPresent( renderer );
    SDL_UnlockMutex(text_mutex);

  }
}

void video_refresh_timer(void *userdata) {

  VideoState *is = (VideoState *)userdata;
  VideoPicture *vp;
  double actual_delay, delay, sync_threshold, ref_clock, diff;
  
  if(is->video_st) {
    if(is->pictq_size == 0) {
      schedule_refresh(is, 1);
      //fprintf(stderr, "no picture in the queue!!!\n");
    } else {
      //fprintf(stderr, "get picture from queue!!!\n");
      vp = &is->pictq[is->pictq_rindex];
      
      is->video_current_pts = vp->pts;
      is->video_current_pts_time = av_gettime();
      delay = vp->pts - is->frame_last_pts; /* the pts from last time */
      if(delay <= 0 || delay >= 1.0) {
	/* if incorrect delay, use previous one */
	delay = is->frame_last_delay;
      }
      /* save for next time */
      is->frame_last_delay = delay;
      is->frame_last_pts = vp->pts;

      /* update delay to sync to audio if not master source */
      if(is->av_sync_type != AV_SYNC_VIDEO_MASTER) {
	ref_clock = get_master_clock(is);
	diff = vp->pts - ref_clock;
	
	/* Skip or repeat the frame. Take delay into account
	   FFPlay still doesn't "know if this is the best guess." */
	sync_threshold = (delay > AV_SYNC_THRESHOLD) ? delay : AV_SYNC_THRESHOLD;
	if(fabs(diff) < AV_NOSYNC_THRESHOLD) {
	  if(diff <= -sync_threshold) {
	    delay = 0;
	  } else if(diff >= sync_threshold) {
	    delay = 2 * delay;
	  }
	}
      }
      is->frame_timer += delay;
      /* computer the REAL delay */
      actual_delay = is->frame_timer - (av_gettime() / 1000000.0);
      if(actual_delay < 0.010) {
	/* Really it should skip the picture instead */
	actual_delay = 0.010;
      }
      schedule_refresh(is, (int)(actual_delay * 1000 + 0.5));
      
      /* show the picture! */
      video_display(is);
      
      /* update queue for next picture! */
      if(++is->pictq_rindex == VIDEO_PICTURE_QUEUE_SIZE) {
	is->pictq_rindex = 0;
      }
      SDL_LockMutex(is->pictq_mutex);
      is->pictq_size--;
      SDL_CondSignal(is->pictq_cond);
      SDL_UnlockMutex(is->pictq_mutex);
    }
  } else {
    schedule_refresh(is, 100);
  }
}
      
void alloc_picture(void *userdata) {

  int ret;

  VideoState *is = (VideoState *)userdata;
  VideoPicture *vp;

  vp = &is->pictq[is->pictq_windex];
  if(vp->bmp) {

    // we already have one make another, bigger/smaller
    avpicture_free(vp->bmp);
    free(vp->bmp);

    vp->bmp = NULL;
  }

  // Allocate a place to put our YUV image on that screen
  SDL_LockMutex(text_mutex);

  vp->bmp = (AVPicture*)malloc(sizeof(AVPicture));
  ret = avpicture_alloc(vp->bmp, AV_PIX_FMT_YUV420P, is->video_ctx->width, is->video_ctx->height);
  if (ret < 0) {
      fprintf(stderr, "Could not allocate temporary picture: %s\n", av_err2str(ret));
  }

  SDL_UnlockMutex(text_mutex);

  vp->width = is->video_ctx->width;
  vp->height = is->video_ctx->height;
  vp->allocated = 1;

}

int queue_picture(VideoState *is, AVFrame *pFrame, double pts) {

  VideoPicture *vp;

  /* wait until we have space for a new pic */
  SDL_LockMutex(is->pictq_mutex);
  while(is->pictq_size >= VIDEO_PICTURE_QUEUE_SIZE &&
	!is->quit) {
    SDL_CondWait(is->pictq_cond, is->pictq_mutex);
  }
  SDL_UnlockMutex(is->pictq_mutex);

  if(is->quit)
    return -1;

  // windex is set to 0 initially
  vp = &is->pictq[is->pictq_windex];

  /* allocate or resize the buffer! */
  if(!vp->bmp ||
     vp->width != is->video_ctx->width ||
     vp->height != is->video_ctx->height) {

    vp->allocated = 0;
    alloc_picture(is);
    if(is->quit) {
      return -1;
    }
  }
  
  /* We have a place to put our picture on the queue */
  if(vp->bmp) {

    vp->pts = pts;
    
    // Convert the image into YUV format that SDL uses
    sws_scale(is->video_sws_ctx, (uint8_t const * const *)pFrame->data,
	      pFrame->linesize, 0, is->video_ctx->height,
	      vp->bmp->data, vp->bmp->linesize);
   
    /* now we inform our display thread that we have a pic ready */
    if(++is->pictq_windex == VIDEO_PICTURE_QUEUE_SIZE) {
      is->pictq_windex = 0;
    }

    SDL_LockMutex(is->pictq_mutex);
    is->pictq_size++;
    SDL_UnlockMutex(is->pictq_mutex);
  }
  return 0;
}

double synchronize_video(VideoState *is, AVFrame *src_frame, double pts) {

  double frame_delay;

  if(pts != 0) {
    /* if we have pts, set video clock to it */
    is->video_clock = pts;
  } else {
    /* if we aren't given a pts, set it to the clock */
    pts = is->video_clock;
  }
  /* update the video clock */
  frame_delay = av_q2d(is->video_ctx->time_base);
  /* if we are repeating a frame, adjust clock accordingly */
  frame_delay += src_frame->repeat_pict * (frame_delay * 0.5);
  is->video_clock += frame_delay;
  return pts;
}

int decode_video_thread(void *arg) {
  VideoState *is = (VideoState *)arg;
  AVPacket pkt1, *packet = &pkt1;
  int frameFinished;
  AVFrame *pFrame;
  double pts;

  pFrame = av_frame_alloc();

  for(;;) {
    if(packet_queue_get(&is->videoq, packet, 1) < 0) {
      // means we quit getting packets
      break;
    }
    pts = 0;

    // Decode video frame
    avcodec_decode_video2(is->video_ctx, pFrame, &frameFinished, packet);

    if((pts = av_frame_get_best_effort_timestamp(pFrame)) != AV_NOPTS_VALUE) {
    } else {
      pts = 0;
    }
    pts *= av_q2d(is->video_st->time_base);

    // Did we get a video frame?
    if(frameFinished) {
      pts = synchronize_video(is, pFrame, pts);
      if(queue_picture(is, pFrame, pts) < 0) {
	break;
      }
    }
    av_free_packet(packet);
  }
  av_frame_free(&pFrame);
  return 0;
}

int stream_component_open(VideoState *is, int stream_index) {

  AVFormatContext *pFormatCtx = is->pFormatCtx;
  AVCodecContext *codecCtx = NULL;
  AVCodec *codec = NULL;
  SDL_AudioSpec wanted_spec, spec;

  if(stream_index < 0 || stream_index >= pFormatCtx->nb_streams) {
    return -1;
  }

  codecCtx = avcodec_alloc_context3(NULL);


  int ret = avcodec_parameters_to_context(codecCtx, pFormatCtx->streams[stream_index]->codecpar);
  if (ret < 0)
    return -1;

  codec = avcodec_find_decoder(codecCtx->codec_id);
  if(!codec) {
    fprintf(stderr, "Unsupported codec!\n");
    return -1;
  }


  if(codecCtx->codec_type == AVMEDIA_TYPE_AUDIO) {

      // Set audio settings from codec info
      wanted_spec.freq = codecCtx->sample_rate;
      wanted_spec.format = AUDIO_S16SYS;
      wanted_spec.channels = 2;//codecCtx->channels;
      wanted_spec.silence = 0;
      wanted_spec.samples = SDL_AUDIO_BUFFER_SIZE;
      wanted_spec.callback = audio_callback;
      wanted_spec.userdata = is;

      fprintf(stderr, "wanted spec: channels:%d, sample_fmt:%d, sample_rate:%d \n",
            2, AUDIO_S16SYS, codecCtx->sample_rate);

      if(SDL_OpenAudio(&wanted_spec, &spec) < 0) {
          fprintf(stderr, "SDL_OpenAudio: %s\n", SDL_GetError());
          return -1;
      }
      is->audio_hw_buf_size = spec.size;
  }

  if(avcodec_open2(codecCtx, codec, NULL) < 0) {
    fprintf(stderr, "Unsupported codec!\n");
    return -1;
  }

  switch(codecCtx->codec_type) {
  case AVMEDIA_TYPE_AUDIO:
    is->audioStream = stream_index;
    is->audio_st = pFormatCtx->streams[stream_index];
    is->audio_ctx = codecCtx;
    is->audio_buf_size = 0;
    is->audio_buf_index = 0;
    memset(&is->audio_pkt, 0, sizeof(is->audio_pkt));
    packet_queue_init(&is->audioq);

    //Out Audio Param
    uint64_t out_channel_layout=AV_CH_LAYOUT_STEREO;

    //AAC:1024  MP3:1152
    int out_nb_samples= is->audio_ctx->frame_size;
    //AVSampleFormat out_sample_fmt = AV_SAMPLE_FMT_S16;

    int out_sample_rate=is->audio_ctx->sample_rate;
    int out_channels=av_get_channel_layout_nb_channels(out_channel_layout);
    //Out Buffer Size
    /*
    int out_buffer_size=av_samples_get_buffer_size(NULL,
                                                   out_channels,
                                                   out_nb_samples,
                                                   AV_SAMPLE_FMT_S16,
                                                   1);
                                                   */

    //uint8_t *out_buffer=(uint8_t *)av_malloc(MAX_AUDIO_FRAME_SIZE*2);
    int64_t in_channel_layout=av_get_default_channel_layout(is->audio_ctx->channels);

    struct SwrContext *audio_convert_ctx;
    audio_convert_ctx = swr_alloc();
    swr_alloc_set_opts(audio_convert_ctx,
                       out_channel_layout,
                       AV_SAMPLE_FMT_S16,
                       out_sample_rate,
                       in_channel_layout,
                       is->audio_ctx->sample_fmt,
                       is->audio_ctx->sample_rate,
                       0,
                       NULL);
    fprintf(stderr, "swr opts: out_channel_layout:%lld, out_sample_fmt:%d, out_sample_rate:%d, in_channel_layout:%lld, in_sample_fmt:%d, in_sample_rate:%d",
            out_channel_layout, AV_SAMPLE_FMT_S16, out_sample_rate, in_channel_layout, is->audio_ctx->sample_fmt, is->audio_ctx->sample_rate);
    swr_init(audio_convert_ctx);

    is->audio_swr_ctx = audio_convert_ctx;

    SDL_PauseAudio(0);
    break;
  case AVMEDIA_TYPE_VIDEO:
    is->videoStream = stream_index;
    is->video_st = pFormatCtx->streams[stream_index];
    is->video_ctx = codecCtx;

    is->frame_timer = (double)av_gettime() / 1000000.0;
    is->frame_last_delay = 40e-3;
    is->video_current_pts_time = av_gettime();

    packet_queue_init(&is->videoq);
    is->video_sws_ctx = sws_getContext(is->video_ctx->width, is->video_ctx->height,
				 is->video_ctx->pix_fmt, is->video_ctx->width,
				 is->video_ctx->height, AV_PIX_FMT_YUV420P,
				 SWS_BILINEAR, NULL, NULL, NULL
				 );
    is->video_tid = SDL_CreateThread(decode_video_thread, "decode_video_thread", is);
    break;
  default:
    break;
  }
}

int demux_thread(void *arg) {

  int err_code;
  char errors[1024] = {0,};

  VideoState *is = (VideoState *)arg;
  AVFormatContext *pFormatCtx;
  AVPacket pkt1, *packet = &pkt1;

  int video_index = -1;
  int audio_index = -1;
  int i;

  is->videoStream=-1;
  is->audioStream=-1;

  global_video_state = is;

  /* open input file, and allocate format context */
  if ((err_code=avformat_open_input(&pFormatCtx, is->filename, NULL, NULL)) < 0) {
      av_strerror(err_code, errors, 1024);
      fprintf(stderr, "Could not open source file %s, %d(%s)\n", is->filename, err_code, errors);
      return -1;
  }

  is->pFormatCtx = pFormatCtx;
  
  // Retrieve stream information
  if(avformat_find_stream_info(pFormatCtx, NULL)<0)
    return -1; // Couldn't find stream information
  
  // Dump information about file onto standard error
  av_dump_format(pFormatCtx, 0, is->filename, 0);
  
  // Find the first video stream

  for(i=0; inb_streams; i++) {
    if(pFormatCtx->streams[i]->codec->codec_type==AVMEDIA_TYPE_VIDEO &&
       video_index < 0) {
      video_index=i;
    }
    if(pFormatCtx->streams[i]->codec->codec_type==AVMEDIA_TYPE_AUDIO &&
       audio_index < 0) {
      audio_index=i;
    }
  }
  if(audio_index >= 0) {
    stream_component_open(is, audio_index);
  }
  if(video_index >= 0) {
    stream_component_open(is, video_index);
  }   

  if(is->videoStream < 0 || is->audioStream < 0) {
    fprintf(stderr, "%s: could not open codecs\n", is->filename);
    goto fail;
  }

  //creat window from SDL
  win = SDL_CreateWindow("Media Player",
                         SDL_WINDOWPOS_UNDEFINED,
                         SDL_WINDOWPOS_UNDEFINED,
                         is->video_ctx->width, is->video_ctx->height,
                         SDL_WINDOW_OPENGL|SDL_WINDOW_RESIZABLE);
  if(!win) {
      fprintf(stderr, "SDL: could not set video mode - exiting\n");
      exit(1);
  }

  renderer = SDL_CreateRenderer(win, -1, 0);

  //IYUV: Y + U + V  (3 planes)
  //YV12: Y + V + U  (3 planes)
  Uint32 pixformat= SDL_PIXELFORMAT_IYUV;

  //create texture for render
  texture = SDL_CreateTexture(renderer,
                              pixformat,
                              SDL_TEXTUREACCESS_STREAMING,
                              is->video_ctx->width,
                              is->video_ctx->height);


  // main decode loop

  for(;;) {
    if(is->quit) {
      break;
    }
    // seek stuff goes here
    if(is->audioq.size > MAX_AUDIOQ_SIZE ||
       is->videoq.size > MAX_VIDEOQ_SIZE) {
      SDL_Delay(10);
      continue;
    }
    if(av_read_frame(is->pFormatCtx, packet) < 0) {
      if(is->pFormatCtx->pb->error == 0) {
	SDL_Delay(100); /* no error; wait for user input */
	continue;
      } else {
	break;
      }
    }
    // Is this a packet from the video stream?
    if(packet->stream_index == is->videoStream) {
      packet_queue_put(&is->videoq, packet);
    } else if(packet->stream_index == is->audioStream) {
      packet_queue_put(&is->audioq, packet);
    } else {
      av_free_packet(packet);
    }
  }
  /* all done - wait for it */
  while(!is->quit) {
    SDL_Delay(100);
  }

 fail:
  if(1){
    SDL_Event event;
    event.type = FF_QUIT_EVENT;
    event.user.data1 = is;
    SDL_PushEvent(&event);
  }
  return 0;
}

int main(int argc, char *argv[]) {


  SDL_Event       event;

  VideoState      *is;

  is = av_mallocz(sizeof(VideoState));

  if(argc < 2) {
    fprintf(stderr, "Usage: test \n");
    exit(1);
  }

  yuvfd = fopen("testout.yuv", "wb+");
  audiofd = fopen("testout.pcm", "wb+");
  // Register all formats and codecs
  av_register_all();

  if(SDL_Init(SDL_INIT_VIDEO | SDL_INIT_AUDIO | SDL_INIT_TIMER)) {
    fprintf(stderr, "Could not initialize SDL - %s\n", SDL_GetError());
    exit(1);
  }


  text_mutex = SDL_CreateMutex();

  av_strlcpy(is->filename, argv[1], sizeof(is->filename));

  is->pictq_mutex = SDL_CreateMutex();
  is->pictq_cond = SDL_CreateCond();

  schedule_refresh(is, 40);

  is->av_sync_type = DEFAULT_AV_SYNC_TYPE;
  is->parse_tid = SDL_CreateThread(demux_thread,"demux_thread", is);
  if(!is->parse_tid) {
    av_free(is);
    return -1;
  }
  for(;;) {

    SDL_WaitEvent(&event);
    switch(event.type) {
    case FF_QUIT_EVENT:
    case SDL_QUIT:
      is->quit = 1;
      SDL_Quit();
      return 0;
      break;
    case FF_REFRESH_EVENT:
      video_refresh_timer(event.user.data1);
      break;
    default:
      break;
    }
  }

  fclose(yuvfd);
  fclose(audiofd);
  return 0;

}