tutorial05.c

// tutorial05.c
// A pedagogical video player that really works!
//
// This tutorial was written by Stephen Dranger (dranger@gmail.com).
//
// Code based on FFplay, Copyright (c) 2003 Fabrice Bellard,
// and a tutorial by Martin Bohme (boehme@inb.uni-luebeckREMOVETHIS.de)
// Tested on Gentoo, CVS version 5/01/07 compiled with GCC 4.1.1
//
// Use the Makefile to build all the samples.
//
// Run using
// tutorial05 myvideofile.mpg
//
// to play the video.

#include <libavcodec/avcodec.h>
#include <libavformat/avformat.h>
#include <libavformat/avio.h>
#include <libswresample/swresample.h>
#include <libswscale/swscale.h>
#include <libavutil/avstring.h>
#include <libavutil/opt.h>
#include <libavutil/time.h>
#include <SDL.h>
#include <SDL_thread.h>
#ifdef __MINGW32__
#undef main /* Prevents SDL from overriding main() */
#endif
#include <stdio.h>
#include <math.h>

#define SDL_AUDIO_BUFFER_SIZE 1024
#define MAX_AUDIO_FRAME_SIZE 192000
#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 FF_ALLOC_EVENT   (SDL_USEREVENT)
#define FF_REFRESH_EVENT (SDL_USEREVENT + 1)
#define FF_QUIT_EVENT (SDL_USEREVENT + 2)
#define VIDEO_PICTURE_QUEUE_SIZE 1

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

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

// 代表一个视频文件(包括音视频流)
typedef struct VideoState {
  AVFormatContext *pFormatCtx;                  // 流的编解码信息
  int videoStream, audioStream;                 // 音视频流的索引位置

  double          audio_clock;
  AVStream        *audio_st;                    // AVStream存储音视频流的结构体，这里存储音频流
  PacketQueue     audioq;                       // 包队列，这里表示音频包队列
  AVFrame         audio_frame;
  uint8_t         audio_buf[(MAX_AUDIO_FRAME_SIZE * 3) / 2];
  unsigned int    audio_buf_size;
  unsigned int    audio_buf_index;
  AVPacket        audio_pkt;          // AVPacket是存储压缩编码数据相关信息的结构体
  uint8_t         *audio_pkt_data;
  int             audio_pkt_size;
  int             audio_hw_buf_size;  
  double          frame_timer;
  double          frame_last_pts;
  double          frame_last_delay;
  double          video_clock; ///<pts of last decoded frame / predicted pts of next decoded frame
  AVStream        *video_st;         // AVStream存储音视频流的结构体，这里存储视频流
  PacketQueue     videoq;            // 包队列，这里表示视频包队列
  VideoPicture    pictq[VIDEO_PICTURE_QUEUE_SIZE];          // 视频缓冲,为了什么
  int             pictq_size, pictq_rindex, pictq_windex;   // 记录读写的位置
  SDL_mutex       *pictq_mutex;
  SDL_cond        *pictq_cond;
  SDL_Thread      *parse_tid;
  SDL_Thread      *video_tid;

  char            filename[1024];   // 视频文件名
  int             quit;

  // http://blog.csdn.net/leixiaohua1020/article/details/14215369
  AVIOContext     *io_context; // AVIOContext是FFMPEG管理输入输出数据的结构体。
  struct SwsContext *sws_ctx;
  struct SwsContext *sws_ctx_audio;
} VideoState;

SDL_Surface     *screen;

/* Since we only have one decoding thread, the Big Struct
   can be global in case we need it. */
VideoState *global_video_state;

// 初始化队列
void packet_queue_init(PacketQueue *q) {
  memset(q, 0, sizeof(PacketQueue));
  q->mutex = SDL_CreateMutex();
  q->cond = SDL_CreateCond();
}
//　将数据包放置到队列中
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;
  // 然后 SDL_CondSignal()会通过条件变量发送一个信号给接收函数（如果它在等待的话）来告诉它现在已经有数据了，然后解锁互斥量
  SDL_CondSignal(q->cond);
  SDL_UnlockMutex(q->mutex);
  return 0;
}

// 从队列获取数据包
static 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_st->codec->channels * 2;
  if(is->audio_st) {
    bytes_per_sec = is->audio_st->codec->sample_rate * n;
  }
  if(bytes_per_sec) {
    pts -= (double)hw_buf_size / bytes_per_sec;
  }
  return pts;
}

int decode_frame_from_packet(VideoState *is, AVFrame decoded_frame)
{
	int64_t src_ch_layout, dst_ch_layout;
	int src_rate, dst_rate;
	uint8_t **src_data = NULL, **dst_data = NULL;
	int src_nb_channels = 0, dst_nb_channels = 0;
	int src_linesize, dst_linesize;
	int src_nb_samples, dst_nb_samples, max_dst_nb_samples;
	enum AVSampleFormat src_sample_fmt, dst_sample_fmt;
	int dst_bufsize;
	int ret;

	src_nb_samples = decoded_frame.nb_samples;
	src_linesize = (int) decoded_frame.linesize;
	src_data = decoded_frame.data;

	if (decoded_frame.channel_layout == 0) {
		decoded_frame.channel_layout = av_get_default_channel_layout(decoded_frame.channels);
	}

	src_rate = decoded_frame.sample_rate;
	dst_rate = decoded_frame.sample_rate;
	src_ch_layout = decoded_frame.channel_layout;
	dst_ch_layout = decoded_frame.channel_layout;
	src_sample_fmt = decoded_frame.format;
	dst_sample_fmt = AV_SAMPLE_FMT_S16;

	av_opt_set_int(is->sws_ctx_audio, "in_channel_layout", src_ch_layout, 0);
	av_opt_set_int(is->sws_ctx_audio, "out_channel_layout", dst_ch_layout,  0);
	av_opt_set_int(is->sws_ctx_audio, "in_sample_rate", src_rate, 0);
	av_opt_set_int(is->sws_ctx_audio, "out_sample_rate", dst_rate, 0);
	av_opt_set_sample_fmt(is->sws_ctx_audio, "in_sample_fmt", src_sample_fmt, 0);
	av_opt_set_sample_fmt(is->sws_ctx_audio, "out_sample_fmt", dst_sample_fmt,  0);

	/* initialize the resampling context */
	if ((ret = swr_init(is->sws_ctx_audio)) < 0) {
		fprintf(stderr, "Failed to initialize the resampling context\n");
		return -1;
	}

	/* allocate source and destination samples buffers */
	src_nb_channels = av_get_channel_layout_nb_channels(src_ch_layout);
	ret = av_samples_alloc_array_and_samples(&src_data, &src_linesize, src_nb_channels, src_nb_samples, src_sample_fmt, 0);
	if (ret < 0) {
		fprintf(stderr, "Could not allocate source samples\n");
		return -1;
	}

	/* compute the number of converted samples: buffering is avoided
	 * ensuring that the output buffer will contain at least all the
	 * converted input samples */
	max_dst_nb_samples = dst_nb_samples = av_rescale_rnd(src_nb_samples, dst_rate, src_rate, AV_ROUND_UP);

	/* buffer is going to be directly written to a rawaudio file, no alignment */
	dst_nb_channels = av_get_channel_layout_nb_channels(dst_ch_layout);
	ret = av_samples_alloc_array_and_samples(&dst_data, &dst_linesize, dst_nb_channels, dst_nb_samples, dst_sample_fmt, 0);
	if (ret < 0) {
		fprintf(stderr, "Could not allocate destination samples\n");
		return -1;
	}

	/* compute destination number of samples */
	dst_nb_samples = av_rescale_rnd(swr_get_delay(is->sws_ctx_audio, src_rate) + src_nb_samples, dst_rate, src_rate, AV_ROUND_UP);
	/* convert to destination format */
	ret = swr_convert(is->sws_ctx_audio, dst_data, dst_nb_samples, (const uint8_t **)decoded_frame.data, src_nb_samples);
	if (ret < 0) {
		fprintf(stderr, "Error while converting\n");
		return -1;
	}

	dst_bufsize = av_samples_get_buffer_size(&dst_linesize, dst_nb_channels, ret, dst_sample_fmt, 1);
	if (dst_bufsize < 0) {
		fprintf(stderr, "Could not get sample buffer size\n");
		return -1;
	}

	memcpy(is->audio_buf, dst_data[0], dst_bufsize);

	if (src_data) {
		av_freep(&src_data[0]);
	}
	av_freep(&src_data);

	if (dst_data) {
		av_freep(&dst_data[0]);
	}
	av_freep(&dst_data);

	return dst_bufsize;
}

int audio_decode_frame(VideoState *is, double *pts_ptr) {
  int len1, data_size = 0, n;
  AVPacket *pkt = &is->audio_pkt;
  double pts;

  for(;;) {
    while(is->audio_pkt_size > 0) {
      int got_frame = 0;
      len1 = avcodec_decode_audio4(is->audio_st->codec, &is->audio_frame, &got_frame, pkt);
      if(len1 < 0) {
	/* if error, skip frame */
	is->audio_pkt_size = 0;
	break;
      }
      if (got_frame)
      {
    	  if (is->audio_frame.format != AV_SAMPLE_FMT_S16) {
    		  data_size = decode_frame_from_packet(is, is->audio_frame);
    	  } else {
            data_size =
              av_samples_get_buffer_size
              (
                  NULL,
                  is->audio_st->codec->channels,
                  is->audio_frame.nb_samples,
                  is->audio_st->codec->sample_fmt,
                  1
              );
            memcpy(is->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_st->codec->channels;
      is->audio_clock += (double)data_size /
	(double)(n * is->audio_st->codec->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;

  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, &pts);
      if(audio_size < 0) {
	/* If error, output silence */
	is->audio_buf_size = 1024;
	memset(is->audio_buf, 0, is->audio_buf_size);
      } else {
	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;
    memcpy(stream, (uint8_t *)is->audio_buf + is->audio_buf_index, len1);
    len -= len1;
    stream += len1;
    is->audio_buf_index += len1;
  }
}

// 触发事件
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 */
// SDL_AddTimer()是一个 SDL 函数，在一个特定的毫秒数里它简单地回调了用户指定函数（可选择携带一些用户数据）
static void schedule_refresh(VideoState *is, int delay) {
  SDL_AddTimer(delay, sdl_refresh_timer_cb, is);
}


// 视频播放的函数
void video_display(VideoState *is) {

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

  vp = &is->pictq[is->pictq_rindex];
  if(vp->bmp) {
    if(is->video_st->codec->sample_aspect_ratio.num == 0) {
      aspect_ratio = 0;
    } else {
      aspect_ratio = av_q2d(is->video_st->codec->sample_aspect_ratio) *
	is->video_st->codec->width / is->video_st->codec->height;
    }
    if(aspect_ratio <= 0.0) {
      aspect_ratio = (float)is->video_st->codec->width /(float)is->video_st->codec->height;
    }
    h = screen->h;
    w = ((int)rint(h * aspect_ratio)) & -3;
    if(w > screen->w) {
      w = screen->w;
      h = ((int)rint(w / aspect_ratio)) & -3;
    }
    x = (screen->w - w) / 2;
    y = (screen->h - h) / 2;

    rect.x = x;
    rect.y = y;
    rect.w = w;
    rect.h = h;
    SDL_DisplayYUVOverlay(vp->bmp, &rect);
  }
}


// 它会从队列里面拉出数据，设置下一帧播放时间，调用 vidoe_display 来使视频显示到屏幕中，队列计数值加 1， 然后减小它的尺寸。
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);
    } else {
      vp = &is->pictq[is->pictq_rindex];

      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 */
      ref_clock = get_audio_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) {

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

  vp = &is->pictq[is->pictq_windex];
  if(vp->bmp) {
    // we already have one make another, bigger/smaller
    SDL_FreeYUVOverlay(vp->bmp);
  }
  // Allocate a place to put our YUV image on that screen
  vp->bmp = SDL_CreateYUVOverlay(is->video_st->codec->width,
				 is->video_st->codec->height,
				 SDL_YV12_OVERLAY,
				 screen);
  vp->width = is->video_st->codec->width;
  vp->height = is->video_st->codec->height;

  SDL_LockMutex(is->pictq_mutex);
  vp->allocated = 1;
  SDL_CondSignal(is->pictq_cond);
  SDL_UnlockMutex(is->pictq_mutex);

}

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

  VideoPicture *vp;
  AVPicture pict;

  /* wait until we have space for a new pic */
  // 队列满的时候，那么等待有空间让我放置
  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_st->codec->width ||
     vp->height != is->video_st->codec->height) {
    SDL_Event event;

    vp->allocated = 0;
    /* we have to do it in the main thread */
    event.type = FF_ALLOC_EVENT;
    event.user.data1 = is;
    SDL_PushEvent(&event);

    /* wait until we have a picture allocated */
    SDL_LockMutex(is->pictq_mutex);
    while(!vp->allocated && !is->quit) {
      SDL_CondWait(is->pictq_cond, is->pictq_mutex);
    }
    SDL_UnlockMutex(is->pictq_mutex);
    if(is->quit) {
      return -1;
    }
  }
  /* We have a place to put our picture on the queue */
  /* If we are skipping a frame, do we set this to null 
     but still return vp->allocated = 1? */


  if(vp->bmp) {

    SDL_LockYUVOverlay(vp->bmp);
    
    /* point pict at the queue */

    pict.data[0] = vp->bmp->pixels[0];
    pict.data[1] = vp->bmp->pixels[2];
    pict.data[2] = vp->bmp->pixels[1];

    pict.linesize[0] = vp->bmp->pitches[0];
    pict.linesize[1] = vp->bmp->pitches[2];
    pict.linesize[2] = vp->bmp->pitches[1];

    // Convert the image into YUV format that SDL uses
    sws_scale
    (
        is->sws_ctx,
        (uint8_t const * const *)pFrame->data,
        pFrame->linesize,
        0,
        is->video_st->codec->height,
        pict.data,
        pict.linesize
    );

    SDL_UnlockYUVOverlay(vp->bmp);
    vp->pts = pts;

    /* 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_st->codec->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;
}
uint64_t global_video_pkt_pts = AV_NOPTS_VALUE;

/* These are called whenever we allocate a frame
 * buffer. We use this to store the global_pts in
 * a frame at the time it is allocated.
 */
int our_get_buffer(struct AVCodecContext *c, AVFrame *pic) {
  int ret = avcodec_default_get_buffer(c, pic);
  uint64_t *pts = av_malloc(sizeof(uint64_t));
  *pts = global_video_pkt_pts;
  pic->opaque = pts;
  return ret;
}
void our_release_buffer(struct AVCodecContext *c, AVFrame *pic) {
  if(pic) av_freep(&pic->opaque);
  avcodec_default_release_buffer(c, pic);
}

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

  pFrame = av_frame_alloc();

  for(;;) {
    // 从队列里面获取数据出错就退出
    if(packet_queue_get(&is->videoq, packet, 1) < 0) {
      // means we quit getting packets
      break;
    }
    pts = 0;

    // Save global pts to be stored in pFrame in first call
    global_video_pkt_pts = packet->pts;
    // Decode video frame
    avcodec_decode_video2(is->video_st->codec, pFrame, &frameFinished,
				packet);
    if(packet->dts == AV_NOPTS_VALUE
       && pFrame->opaque && *(uint64_t*)pFrame->opaque != AV_NOPTS_VALUE) {
      pts = *(uint64_t *)pFrame->opaque;
    } else if(packet->dts != AV_NOPTS_VALUE) {
      pts = packet->dts;
    } 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_free(pFrame);
  return 0;
}

// stream_component_open()函数的作用是找到解码器，设置音频参数，保存重要信息到大结构体中，然后启动音频和视频线程。
int stream_component_open(VideoState *is, int stream_index) {
  AVFormatContext *pFormatCtx = is->pFormatCtx;
  AVCodecContext *codecCtx = NULL;
  AVCodec *codec = NULL;
  AVDictionary *optionsDict = NULL;
  SDL_AudioSpec wanted_spec, spec;

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

  // pCodecCtx 包含了这个流在用的编解码的所有信息，但我们仍需要通过他获得特定的解码器然后打开他。
  codecCtx = pFormatCtx->streams[stream_index]->codec;
  if(codecCtx->codec_type == AVMEDIA_TYPE_AUDIO) {
    // Set audio settings from codec info
    // 获取编解码信息设置音频
    wanted_spec.freq = codecCtx->sample_rate;
    wanted_spec.format = AUDIO_S16SYS;
    wanted_spec.channels = codecCtx->channels;
    wanted_spec.silence = 0;
    wanted_spec.samples = SDL_AUDIO_BUFFER_SIZE;
    wanted_spec.callback = audio_callback;
    wanted_spec.userdata = is;

    // http://wiki.libsdl.org/SDL_OpenAudio
    // 打开音频设备
    if(SDL_OpenAudio(&wanted_spec, &spec) < 0) {
      fprintf(stderr, "SDL_OpenAudio: %s\n", SDL_GetError());
      return -1;
    }
    is->audio_hw_buf_size = spec.size;
  }

  // 为视频流获取特定的解码器。
  codec = avcodec_find_decoder(codecCtx->codec_id);
  // 打开解码器
  if(!codec || (avcodec_open2(codecCtx, codec, &optionsDict) < 0)) {
    fprintf(stderr, "Unsupported codec!\n");
    return -1;
  }

  switch(codecCtx->codec_type) {
  case AVMEDIA_TYPE_AUDIO:    // 音频
    is->audioStream = stream_index;
    is->audio_st = pFormatCtx->streams[stream_index];
    is->audio_buf_size = 0;
    is->audio_buf_index = 0;

	is->sws_ctx_audio = swr_alloc();
	if (!is->sws_ctx_audio) {
		fprintf(stderr, "Could not allocate resampler context\n");
		return -1;
	}
    memset(&is->audio_pkt, 0, sizeof(is->audio_pkt));
    packet_queue_init(&is->audioq);         // 初始化音频队列
    SDL_PauseAudio(0);
    break;
  case AVMEDIA_TYPE_VIDEO:    // 视频
    is->videoStream = stream_index;
    is->video_st = pFormatCtx->streams[stream_index];

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

    packet_queue_init(&is->videoq);     // 初始化视频队列
    // 启动视频线程
    is->video_tid = SDL_CreateThread(video_thread, is);
    is->sws_ctx =
        sws_getContext
        (
            is->video_st->codec->width,
            is->video_st->codec->height,
            is->video_st->codec->pix_fmt,
            is->video_st->codec->width,
            is->video_st->codec->height,
            AV_PIX_FMT_YUV420P,
            SWS_BILINEAR,
            NULL,
            NULL,
            NULL
        );
    codecCtx->get_buffer2 = our_get_buffer;
    //codecCtx->release_buffer = our_release_buffer;
    break;
  default:
    break;
  }

  return 0;
}

int decode_interrupt_cb(void *opaque) {
  return (global_video_state && global_video_state->quit);
}

int decode_thread(void *arg) {
// 上半部分的函数没什么新东西；它的工作就是打开文件和找到视频流和音频流的索引。
// 唯一不同的地方是把格式内容保存到大结构体中。当找到流后，调用另一个将要定义的函数 stream_component_open()。
// 这是一个一般的分离的方法，自从我们设置很多相似的视频和音频解码的代码，我们通过编写这个函数来重用它们。
  VideoState *is = (VideoState *)arg;
  AVFormatContext *pFormatCtx = NULL;
  AVPacket pkt1, *packet = &pkt1;
  // http://www.ffmpeg.org/doxygen/3.1/group__lavu__dict.html#details
  AVDictionary *io_dict = NULL; // AVDictionary 元数据,Simple key:value store.
  // http://www.ffmpeg.org/doxygen/3.1/structAVIOInterruptCB.html#details
  AVIOInterruptCB callback;     // Callback for checking whether to abort blocking functions.

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

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

  global_video_state = is;
  // will interrupt blocking functions if we quit!
  callback.callback = decode_interrupt_cb;
  callback.opaque = is; // void * 类型

  // http://www.ffmpeg.org/doxygen/3.1/aviobuf_8c.html#ae8589aae955d16ca228b6b9d66ced33d
  // 使用is->filename的内容初始化is->io_context，用于管理文件的读写
  if (avio_open2(&is->io_context, is->filename, 0, &callback, &io_dict))
  {
    fprintf(stderr, "Unable to open I/O for %s\n", is->filename);
    return -1;
  }

  // 从传入的第二个参数获得文件路径，这个函数会读取文件头信息，并把信息保存在 pFormatCtx 结构体当中。
  // 这个函数后面两个参数分别是： 指定文件格式、格式化选项，当我们设置为 NULL 或 0 时，libavformat 会自动完成这些工作。
  if(avformat_open_input(&pFormatCtx, is->filename, NULL, NULL)!=0)
    return -1; // Couldn't open file

  is->pFormatCtx = pFormatCtx;

  // Retrieve stream information
  // 得到流信息
  if(avformat_find_stream_info(pFormatCtx, NULL)<0)
    return -1; // Couldn't find stream information

  // Dump information about file onto standard error
  // 这个函数填充了 pFormatCtx->streams 流信息， 可以通过 dump_format 把信息打印出来：
  av_dump_format(pFormatCtx, 0, is->filename, 0);

  // 查找一个音频和视频流
  for(i=0; i<pFormatCtx->nb_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;
    }
  }

  // stream_component_open()函数的作用是找到解码器，设置音频参数，保存重要信息到大结构体中，然后启动音频和视频线程。
  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;
  }

  // main decode loop
  // 上面都是打开文件和找到视频流和音频流的索引等工作，下面才是主循环
  for(;;) {
    if(is->quit) {
      break;  //控制循环是否退出
    }
    // seek stuff goes here
    if(is->audioq.size > MAX_AUDIOQ_SIZE ||
        is->videoq.size > MAX_VIDEOQ_SIZE) {
      SDL_Delay(10);    // 当队列中数据比较多的时候，就等待10ms
      continue;
    }
    // 读取码流中的音频若干帧或者视频一帧
    if(av_read_frame(is->pFormatCtx, packet) < 0) {
      if(is->pFormatCtx->pb->error == 0) {
	      SDL_Delay(100); // 如果没有读取到数据，同时没有出错，那么等待100ms然后继续
	      continue;
      } else {
	      break;
      }
    }
    // 获取到音视频包之后，放置到相应的队列
    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:
  {
    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 <file>\n");
    exit(1);
  }
  // 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);
  }

  // Make a screen to put our video
#ifndef __DARWIN__
        screen = SDL_SetVideoMode(640, 480, 0, 0);
#else
        screen = SDL_SetVideoMode(640, 480, 24, 0);
#endif
  if(!screen) {
    fprintf(stderr, "SDL: could not set video mode - exiting\n");
    exit(1);
  }

  av_strlcpy(is->filename, argv[1], 1024);
  // 初始化为视频缓冲准备的锁（pictq）
  // 因为一旦事件驱动调用视频函数， 视频函数会从 pictq 抽出预解码帧。
  // 同时， 视频解码器会把信息放进去， 我们不知道那个动作会先发生。
  is->pictq_mutex = SDL_CreateMutex();
  is->pictq_cond = SDL_CreateCond();

  // schedule_refresh 是一个将要定义的函数。它的动作是告诉系统在某个特定的毫秒数后弹出 FF_REFRESH_EVENT 事件。
  schedule_refresh(is, 40);

  // 生成一个新线程能完全访问原始进程中的内存，启动我们给的线程,在这种情况下， 调用 decode_thread()并与 VideoState 结构体连接。
  is->parse_tid = SDL_CreateThread(decode_thread, is);
  if(!is->parse_tid) {
    av_free(is);
    return -1;
  }

  // 处理事件循环
  for(;;) {
    SDL_WaitEvent(&event);
    switch(event.type) {
    case FF_QUIT_EVENT:
    case SDL_QUIT:
      is->quit = 1;
      /*
       * If the video has finished playing, then both the picture and
       * audio queues are waiting for more data.  Make them stop
       * waiting and terminate normally.
       */
      SDL_CondSignal(is->audioq.cond);
      SDL_CondSignal(is->videoq.cond);
      SDL_Quit();
      exit(0);
      break;
    case FF_ALLOC_EVENT:
      alloc_picture(event.user.data1);
      break;
    case FF_REFRESH_EVENT:
      video_refresh_timer(event.user.data1);
      break;
    default:
      break;
    }
  }
  return 0;
}