ffmpeg音频播放代码示例-avcodec_decode_audio4

一、概述

最近在学习ffmpeg解码的内容，参考了官方的教程http://dranger.com/ffmpeg/tutorial03.html，结果发现这个音频解码的教程有点问题。参考了各种博客，并同时啃ffplay.c的源码，发现avcodec_decode_audio4多了一个resample（重采样）的概念。

其解码以及播放音频的思路为：

首先，ffmpeg设置本机的audio播放参数（target format），如freq(频率）为44100，format为AV_SAMPLE_FMT_S16，channels为2。这个播放参数是SDL实际播放音频时使用的参数。

但是！但是我们的audio file（如mp3文件）的audio数据很可能有其自己的audio播放参数（source format），而这些参数不同于我们实际的SDL播放参数，于是ffmpeg在其中插入resample（重采用）的过程，将source format转换成target format。

简单的说就是一个audio参数设置思路的转变：

这个思路转变最大的好处，就是本机播放的格式可以不用再迁就audio file，而是可以根据自己的需要自行设定，缺点很显然就是ffmpeg的CPU开销会增大。

二、代码示例（源码见“附录”）

源码在官方教程基础上把其中视频部分删除，在main函数最后加上一个无限循环，并添加resample函数，最后将resample插入到sdl的回调函数之中。

源码中关于queue的代码为官网教程原版复制，其主要作用就是让main函数和SDL audio线程互斥的push queue和get queue，以下不再赘述。

1、main函数代码结构

main函数伪代码结构如下：

SDL Initialization
ffmpeg open audio file
Set SDL audio parameters
Set ffmpeg audio parameters(target format)
while(ffmpeg_read_frame(pkt)) {
    packet_queue_put(pkt);
}
while(1) {
    sleep(1);
}

ffmpeg从audio file中不停的读取数据，并将读出的packet放入queue中。此时我们要清楚，另外还有一个SDL audio线程在等待queue中的数据。

2、SDL audio线程

SDL audio线程主要执行一个回调函数，对应源码中的函数为audio_callback(void * userdata, Uint8 * stream, int len)。这个函数的使命就是将解码后的数据放入参数stream这个缓冲区中，以便SDL audio线程从stream缓冲区中获取数据play。这个缓冲区的大小为参数len，而userdata则是用户自定的参数。其伪代码结构如下：

audio_buf_index = 0;
while(len > 0) {
    audio_size = audio_decode_frame(audio_buf_tmp);
    memcpy(stream, audio_buf_tmp, audio_size);
    len -= audio_size;
    stream += audio_size;
    audio_buf_index += audio_size;
}

其中audio_decode_frame函数会从queue中取出packet，并对packet中的frame进行解码和resample，然后将数据放入audio_buf_tmp缓冲区中。

3、Resample函数

Resample的过程和结构体SwrContext息息相关。使用这个结构体共需要2步。

1、先初始化SwrContex，指定target format和source format；

2、使用已初始化的SwrContext，对frame进行resample。

Resample的伪代码如下：

struct SwrContext * swr_ctx = NULL;
audio_hw_params_src = audio_hw_params_tgt
int resample(AVFrame * af, uint8_t * audio_buf, int * audio_buf_size)
{
    if(audio_hw_params_src != audio_hw_params(af)) {
        swr_ctx = swr_alloc_set_opts(audio_hw_params_tgt, audio_hw_params(af));
        audio_hw_params_src = audio_hw_params(af);
    }
    in = af;
    swr_convert(swr_ctx, out, in);
    audio_buf = out;
} 

一开始，audio_hw_parames_src（source format）被初始化为target format，在resample获得第一个frame后，会从该frame中提取source format，并将其赋值给audio_hw_params_src，同时初始化SwrContext这个结构体，指定target format和source format。然后swr_convert对输入的frame进行resample(swr_convert），然后将resample后得到的数据放进resample函数指定的缓冲区（audio_buf）中。

附录：

#include <libavcodec/avcodec.h>
#include <libavformat/avformat.h>
#include <libswscale/swscale.h>
#include <libswresample/swresample.h>

#include <SDL.h>
#include <SDL_thread.h>

#ifdef __MINGW32__
#undef main /* Prevents SDL from overriding main() */
#endif

#include <stdio.h>
#include <assert.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>

// 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

#include <signal.h>

typedef struct AudioParams {
    int freq;
    int channels;
    int64_t channel_layout;
    enum AVSampleFormat fmt;
    int frame_size;
    int bytes_per_sec;
} AudioParams;
int sample_rate, nb_channels;
int64_t channel_layout;
AudioParams audio_hw_params_tgt;
AudioParams audio_hw_params_src;

int resample(AVFrame * af, uint8_t * audio_buf, int * audio_buf_size);

struct SwrContext * swr_ctx = NULL;

int resample(AVFrame * af, uint8_t * audio_buf, int * audio_buf_size)
{
    int data_size = 0;
    int resampled_data_size = 0;
    int64_t dec_channel_layout;
    data_size = av_samples_get_buffer_size(NULL, 
            av_frame_get_channels(af),
            af->nb_samples,
            af->format,
            1);

    dec_channel_layout =
        (af->channel_layout && av_frame_get_channels(af) == av_get_channel_layout_nb_channels(af->channel_layout)) ?
        af->channel_layout : av_get_default_channel_layout(av_frame_get_channels(af));
    if(     af->format              != audio_hw_params_src.fmt                 ||
            af->sample_rate     != audio_hw_params_src.freq              ||
            dec_channel_layout     != audio_hw_params_src.channel_layout     ||
            !swr_ctx) {
        swr_free(&swr_ctx);
        swr_ctx = swr_alloc_set_opts(NULL, 
                                        audio_hw_params_tgt.channel_layout, audio_hw_params_tgt.fmt, audio_hw_params_tgt.freq, 
                                        dec_channel_layout, af->format, af->sample_rate, 
                                        0, NULL);
        if (!swr_ctx || swr_init(swr_ctx) < 0) {
            av_log(NULL, AV_LOG_ERROR,
                   "Cannot create sample rate converter for conversion of %d Hz %s %d channels to %d Hz %s %d channels!
",
                    af->sample_rate, av_get_sample_fmt_name(af->format), av_frame_get_channels(af),
                    audio_hw_params_tgt.freq, av_get_sample_fmt_name(audio_hw_params_tgt.fmt), audio_hw_params_tgt.channels);
            swr_free(&swr_ctx);
            return -1;
        }
        printf("swr_init
");
        audio_hw_params_src.channels = av_frame_get_channels(af);
        audio_hw_params_src.fmt = af->format;
        audio_hw_params_src.freq = af->sample_rate;
    }

    if (swr_ctx) {
        const uint8_t **in = (const uint8_t **)af->extended_data;
        uint8_t **out = &audio_buf;
        int out_count = (int64_t)af->nb_samples * audio_hw_params_tgt.freq / af->sample_rate + 256;
        int out_size  = av_samples_get_buffer_size(NULL, audio_hw_params_tgt.channels, out_count, audio_hw_params_tgt.fmt, 0);
        int len2;
        if (out_size < 0) {
            av_log(NULL, AV_LOG_ERROR, "av_samples_get_buffer_size() failed
");
            return -1;
        }
        av_fast_malloc(&audio_buf, audio_buf_size, out_size);
        if (!audio_buf)
            return AVERROR(ENOMEM);
        len2 = swr_convert(swr_ctx, out, out_count, in, af->nb_samples);
        if (len2 < 0) {
            av_log(NULL, AV_LOG_ERROR, "swr_convert() failed
");
            return -1;
        }
        if (len2 == out_count) {
            av_log(NULL, AV_LOG_WARNING, "audio buffer is probably too small
");
            if (swr_init(swr_ctx) < 0)
                swr_free(&swr_ctx);
        }
        resampled_data_size = len2 * audio_hw_params_tgt.channels * av_get_bytes_per_sample(audio_hw_params_tgt.fmt);
    } else {
        audio_buf = af->data[0];
        resampled_data_size = data_size;
    }

    return resampled_data_size;
}

static void sigterm_handler(int sig)
{
    exit(123);
}

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

PacketQueue audioq;

int quit = 0;

void packet_queue_init(PacketQueue *q) {
  memset(q, 0, sizeof(PacketQueue));
  q->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;
}
static int packet_queue_get(PacketQueue *q, AVPacket *pkt, int block)
{
  AVPacketList *pkt1;
  int ret;
  
  SDL_LockMutex(q->mutex);
  
  for(;;) {
    
    if(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;
}

AVFrame frame;
int audio_decode_frame(AVCodecContext *aCodecCtx, uint8_t *audio_buf, int buf_size) {

    static AVPacket pkt;
    static uint8_t *audio_pkt_data = NULL;
    static int audio_pkt_size = 0;

    int len1, data_size = 0;

    for(;;) {
        while(audio_pkt_size > 0) {
            int got_frame = 0;
            len1 = avcodec_decode_audio4(aCodecCtx, &frame, &got_frame, &pkt);
            if(len1 < 0) {
                /* if error, skip frame */
                audio_pkt_size = 0;
                break;
            }
            audio_pkt_data += len1;
            audio_pkt_size -= len1;
            data_size = 0;
            if(got_frame) {
                data_size = resample(&frame, audio_buf, &buf_size);
                // data_size = av_samples_get_buffer_size(NULL, 
                //         aCodecCtx->channels,
                //         frame.nb_samples,
                //         aCodecCtx->sample_fmt,
                //         1);
                assert(data_size <= buf_size);
                // memcpy(audio_buf, frame.data[0], data_size);
            }
            if(data_size <= 0) {
                /* No data yet, get more frames */
                continue;
            }
            // memcpy(audio_buf, frame.data[0], data_size);

            /* We have data, return it and come back for more later */
            return data_size;
        }
        if(pkt.data)
            av_free_packet(&pkt);

        if(quit) {
            return -1;
        }

        if(packet_queue_get(&audioq, &pkt, 1) < 0) {
            return -1;
        }
        audio_pkt_data = pkt.data;
        audio_pkt_size = pkt.size;
    }
}

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

  AVCodecContext *aCodecCtx = (AVCodecContext *)userdata;
  int len1, audio_size;

  static uint8_t audio_buf[(MAX_AUDIO_FRAME_SIZE * 3) / 2];
  static unsigned int audio_buf_size = 0;
  static unsigned int audio_buf_index = 0;

  while(len > 0) {
      if(audio_buf_index >= audio_buf_size) {
          /* We have already sent all our data; get more */
          audio_size = audio_decode_frame(aCodecCtx, audio_buf, sizeof(audio_buf));
          if(audio_size < 0) {
              /* If error, output silence */
              audio_buf_size = 1024; // arbitrary?
              memset(audio_buf, 0, audio_buf_size);
          } else {
              audio_buf_size = audio_size;
          }
          audio_buf_index = 0;
      }
      len1 = audio_buf_size - audio_buf_index;
      if(len1 > len)
          len1 = len;
      memcpy(stream, (uint8_t *)audio_buf + audio_buf_index, len1);
      len -= len1;
      stream += len1;
      audio_buf_index += len1;
  }
}

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

  AVFormatContext *pFormatCtx = NULL;
  int             i, audioStream;
  AVPacket        packet;
  
  AVCodecContext  *aCodecCtxOrig = NULL;
  AVCodecContext  *aCodecCtx = NULL;
  AVCodec         *aCodec = NULL;

  SDL_Event       event;
  SDL_AudioSpec   wanted_spec, spec;

  signal(SIGINT , sigterm_handler); /* Interrupt (ANSI).    */
  signal(SIGTERM, sigterm_handler); /* Termination (ANSI).  */

  if(argc < 2) {
    fprintf(stderr, "Usage: test <file>
");
    exit(1);
  }
  // Register all formats and codecs
  av_register_all();
  
  if(SDL_Init(SDL_INIT_AUDIO)) {
    fprintf(stderr, "Could not initialize SDL - %s
", SDL_GetError());
    exit(1);
  }

  // Open video file
  if(avformat_open_input(&pFormatCtx, argv[1], NULL, NULL)!=0)
    return -1; // Couldn't open file
  
  // 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, argv[1], 0);
    
  // Find the first video stream
  audioStream=-1;
  for(i=0; i<pFormatCtx->nb_streams; i++) {
    if(pFormatCtx->streams[i]->codec->codec_type==AVMEDIA_TYPE_AUDIO &&
       audioStream < 0) {
      audioStream=i;
    }
  }
  // if(videoStream==-1)
  //   return -1; // Didn't find a video stream
  if(audioStream==-1)
    return -1;
   
  aCodecCtxOrig=pFormatCtx->streams[audioStream]->codec;
  aCodec = avcodec_find_decoder(aCodecCtxOrig->codec_id);
  if(!aCodec) {
    fprintf(stderr, "Unsupported codec!
");
    return -1;
  }

  // Copy context
  aCodecCtx = avcodec_alloc_context3(aCodec);
  if(avcodec_copy_context(aCodecCtx, aCodecCtxOrig) != 0) {
    fprintf(stderr, "Couldn't copy codec context");
    return -1; // Error copying codec context
  }

  avcodec_open2(aCodecCtx, aCodec, NULL);

  sample_rate = aCodecCtx->sample_rate;
  nb_channels = aCodecCtx->channels;
  channel_layout = aCodecCtx->channel_layout;

  printf("channel_layout=%" PRId64 "
", channel_layout);
  printf("nb_channels=%d
", nb_channels);
  printf("freq=%d
", sample_rate);

  if (!channel_layout || nb_channels != av_get_channel_layout_nb_channels(channel_layout)) {
      channel_layout = av_get_default_channel_layout(nb_channels);
      channel_layout &= ~AV_CH_LAYOUT_STEREO_DOWNMIX;
      printf("correction
");
  }

  // Set audio settings from codec info
  wanted_spec.freq = sample_rate;
  wanted_spec.format = AUDIO_S16SYS;
  wanted_spec.channels = nb_channels;
  wanted_spec.silence = 0;
  wanted_spec.samples = SDL_AUDIO_BUFFER_SIZE;
  wanted_spec.callback = audio_callback;
  wanted_spec.userdata = aCodecCtx;
  
  if(SDL_OpenAudio(&wanted_spec, &spec) < 0) {
    fprintf(stderr, "SDL_OpenAudio: %s
", SDL_GetError());
    return -1;
  }
  printf("freq: %d	channels: %d
", spec.freq, spec.channels);

  audio_hw_params_tgt.fmt = AV_SAMPLE_FMT_S16;
  audio_hw_params_tgt.freq = spec.freq;
  audio_hw_params_tgt.channel_layout = channel_layout;
  audio_hw_params_tgt.channels =  spec.channels;
  audio_hw_params_tgt.frame_size = av_samples_get_buffer_size(NULL, audio_hw_params_tgt.channels, 1, audio_hw_params_tgt.fmt, 1);
  audio_hw_params_tgt.bytes_per_sec = av_samples_get_buffer_size(NULL, audio_hw_params_tgt.channels, audio_hw_params_tgt.freq, audio_hw_params_tgt.fmt, 1);
  if (audio_hw_params_tgt.bytes_per_sec <= 0 || audio_hw_params_tgt.frame_size <= 0) {
      printf("size error
");
      return -1;
  }
  audio_hw_params_src = audio_hw_params_tgt;

  // audio_st = pFormatCtx->streams[index]
  packet_queue_init(&audioq);
  SDL_PauseAudio(0);

  // Read frames and save first five frames to disk
  i=0;
  while(av_read_frame(pFormatCtx, &packet)>=0) {
    if(packet.stream_index==audioStream) {
      packet_queue_put(&audioq, &packet);
    } else {
      av_free_packet(&packet);
    }
    // Free the packet that was allocated by av_read_frame
    SDL_PollEvent(&event);
    switch(event.type) {
    case SDL_QUIT:
      quit = 1;
      SDL_Quit();
      exit(0);
      break;
    default:
      break;
    }

  }

  while(1) SDL_Delay(1000);
  
  // Close the codecs
  avcodec_close(aCodecCtxOrig);
  avcodec_close(aCodecCtx);
  
  // Close the video file
  avformat_close_input(&pFormatCtx);
  
  return 0;
}

下载源码以及Makefile：

http://pan.baidu.com/s/1pJUXLZP