FFmepg中文例子—指导2：加入音频

#include "libavformat/avformat.h"  
#include "libswscale/swscale.h"  
#include <windows.h>  
  
#include <stdlib.h>  
#include <stdio.h>  
#include <string.h>  
#include <math.h>  
#include <SDL/SDL.h>  
#include <SDL/SDL_thread.h>  
  
#ifdef main  
#undef main  
#endif  
  
#define SDL_AUDIO_BUFFER_SIZE 1024  
static int sws_flags = SWS_BICUBIC;  
  
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 = (AVPacketList *)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;  
}  
  
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;  
    for(;;)  
    {  
        while(audio_pkt_size > 0)  
        {  
            data_size = buf_size;  
            len1 = avcodec_decode_audio2(aCodecCtx, (int16_t *)audio_buf, &data_size, audio_pkt_data, audio_pkt_size);  
            if(len1 < 0)  
            {   
                audio_pkt_size = 0;  
                break;  
            }  
            audio_pkt_data += len1;  
            audio_pkt_size -= len1;  
            if(data_size <= 0)  
            {   
                continue;  
            }   
            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[(AVCODEC_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)  
        {   
            audio_size = audio_decode_frame(aCodecCtx, audio_buf, sizeof(audio_buf));  
            if(audio_size < 0)  
            {   
                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;  
    int i, videoStream(-1), audioStream(-1);  
    AVCodecContext *pCodecCtx;  
    AVCodec *pCodec;  
    AVFrame *pFrame;  
    AVPacket packet;  
    int frameFinished;  
    float aspect_ratio;  
    AVCodecContext *aCodecCtx;  
    AVCodec *aCodec;  
    SDL_Overlay *bmp;  
    SDL_Surface *screen;  
    SDL_Rect rect;  
    SDL_Event event;  
    SDL_AudioSpec wanted_spec, spec;  
    if(argc < 2)  
    {  
        fprintf(stderr, "Usage: test \n");  
        exit(1);  
    }  
  
    av_register_all();  
    pFormatCtx = av_alloc_format_context();  
    if (!pFormatCtx) {  
        fprintf(stderr, "Memory error\n");  
        exit(1);  
    }  
    if(av_open_input_file(&pFormatCtx, argv[1], NULL, 0, NULL)!=0)  
        return -1; // Couldn't open file  
    if(av_find_stream_info(pFormatCtx)<0)  
        return -1; // Couldn't find stream information  
    // Dump information about file onto standard error  
    dump_format(pFormatCtx, 0, argv[1], 0);  
  
    // Find the first video stream  
    for(i=0; i<pFormatCtx->nb_streams; i++)  
    {  
        if(pFormatCtx->streams[i]->codec->codec_type==CODEC_TYPE_VIDEO && videoStream<0)  
        {  
            videoStream=i;  
        }  
        if(pFormatCtx->streams[i]->codec->codec_type==CODEC_TYPE_AUDIO && audioStream<0)  
        {  
            audioStream=i;  
        }  
    }  
    if(videoStream==-1||audioStream==-1)  
      return -1; // Didn't find a video stream  
  
    // Get a pointer to the codec context for the video stream  
  
    aCodecCtx=pFormatCtx->streams[audioStream]->codec;  
    wanted_spec.freq = aCodecCtx->sample_rate;  
    wanted_spec.format = AUDIO_S16SYS;  
    wanted_spec.channels = aCodecCtx->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\n", SDL_GetError());  
        return -1;  
    }  
    aCodec = avcodec_find_decoder(aCodecCtx->codec_id);  
    if(!aCodec)  
    {  
        fprintf(stderr, "Unsupported codec!\n"); return -1;  
    }  
    avcodec_open(aCodecCtx, aCodec); // audio_st = pFormatCtx->streams[index]  
    packet_queue_init(&audioq);  
    SDL_PauseAudio(0);  
  
    pCodecCtx=pFormatCtx->streams[videoStream]->codec;  
    pCodec=avcodec_find_decoder(pCodecCtx->codec_id);  
    if(pCodec==NULL)  
    {  
        fprintf(stderr, "Unsupported codec!\n");  
        return -1; // Codec not found  
    }  
    // Open codec  
    if(avcodec_open(pCodecCtx, pCodec)<0)  
        return -1; // Could not open codec  
  
    // Allocate video frame  
    pFrame=avcodec_alloc_frame();  
    // Allocate an AVFrame structure  
    uint8_t *buffer;  
    int numBytes;  
    // Determine required buffer size and allocate buffer  
    numBytes=avpicture_get_size(PIX_FMT_RGB24, pCodecCtx->width,  
        pCodecCtx->height);  
    buffer=(uint8_t *)av_malloc(numBytes*sizeof(uint8_t));  
  
    // Assign appropriate parts of buffer to image planes in pFrameRGB  
    if(SDL_Init(SDL_INIT_VIDEO | SDL_INIT_AUDIO | SDL_INIT_TIMER))  
    {  
        fprintf(stderr, "Could not initialize SDL - %s\n", SDL_GetError());  
        exit(1);  
    }  
  
#ifndef __DARWIN__  
    screen = SDL_SetVideoMode(pCodecCtx->width, pCodecCtx->height, 0, 0);  
#else  
    screen = SDL_SetVideoMode(pCodecCtx->width, pCodecCtx->height, 24, 0);  
#endif  
    if(!screen)  
    {  
        fprintf(stderr, "SDL: could not set video mode - exiting\n");  
        exit(1);  
    }  
  
    bmp = SDL_CreateYUVOverlay(pCodecCtx->width, pCodecCtx->height,  
        SDL_YV12_OVERLAY, screen);  
  
    static struct SwsContext *img_convert_ctx;  
    if (img_convert_ctx == NULL)  
    {  
        img_convert_ctx = sws_getContext(pCodecCtx->width, pCodecCtx->height,  
                                         pCodecCtx->pix_fmt,  
                                         pCodecCtx->width, pCodecCtx->height,  
                                         PIX_FMT_YUV420P,  
                                         sws_flags, NULL, NULL, NULL);  
        if (img_convert_ctx == NULL)  
        {  
            fprintf(stderr, "Cannot initialize the conversion context\n");  
            exit(1);  
        }  
    }  
    i=0;  
    while(av_read_frame(pFormatCtx, &packet)>=0)  
    {  
        // Is this a packet from the video stream?  
        if(packet.stream_index==videoStream)  
        {  
            // Decode video frame  
            avcodec_decode_video3(pCodecCtx, pFrame, &frameFinished,  
                packet);  
            // Did we get a video frame?  
            if(frameFinished)  
            {  
                SDL_LockYUVOverlay(bmp);  
                AVPicture pict;  
                pict.data[0] = bmp->pixels[0];  
                pict.data[1] = bmp->pixels[2];  
                pict.data[2] = bmp->pixels[1];  
  
                pict.linesize[0] = bmp->pitches[0];  
                pict.linesize[1] = bmp->pitches[2];  
                pict.linesize[2] = bmp->pitches[1];  
  
                // Convert the image into YUV format that SDL uses  
                  
                sws_scale(img_convert_ctx, pFrame->data, pFrame->linesize,  
                    0, pCodecCtx->height, pict.data, pict.linesize);  
                SDL_UnlockYUVOverlay(bmp);  
                rect.x = 0;  
                rect.y = 0;  
                rect.w = pCodecCtx->width;  
                rect.h = pCodecCtx->height;  
                SDL_DisplayYUVOverlay(bmp, &rect);  
                Sleep(60);  
                av_free_packet(&packet);  
            }  
        }  
        else 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;  
        }  
    }  
    // Free the RGB image  
    av_free(buffer);  
    //av_free(pFrameRGB);  
    // Free the YUV frame  
    av_free(pFrame);  
    // Close the codec  
    avcodec_close(pCodecCtx);  
    // Close the video file  
    av_close_input_file(pFormatCtx);  
    return 0;  
}  

这个教程第一次用到了SDL的线程，涉及到了两个线程间的同步协调，有几个地方需要特别留意，SDL_OpenAudio库函数会打开音频设备（0是恢 复，其他的是暂停），SDL_PauseAudio库函数可以暂停或者恢复audio_callback函数的执行，程序中的这行代码 “SDL_PauseAudio(0);”执行后，让audio_callback函数开始反复的被调用。在这之前audio_callback回调函数 还没有被调用。

audio_callback函数

     原型为void callback(void *userdata, Uint8 *stream, int len)，userdata是输入，stream是输出，len是输入，len的值一般为4096（调试中发现的），audio_callback函数的 功能是调用audio_decode_frame函数，把解码后数据块audio_buf追加在stream的后面，通过SDL库对 audio_callback的不断调用，不断解码数据，然后放到stream的末尾，SDL库认为stream中数据够播放一帧音频了，就播放它,第三 个参数len是向stream中写数据的内存分配尺度，是分配给audio_callback函数写入缓存大小。

    假设len=4096，解码后数据块audio_buf的大小为4608，那么一次audio_callback调用不能把audio_buf中全部数据 写入stream末尾，就分两次，第一次先把audio_buf的前4096个字节写入stream末尾，第二次调用audio_callback函数 时，由于写缓存用光了，又分配4096个字节的缓存，再写剩余的512个字节到stream末尾，写缓存还剩余3584个字节留给下次 audio_callback调用使用。

audio_decode_frame函数

     原型：int audio_decode_frame(AVCodecContext *aCodecCtx, uint8_t *audio_buf, int buf_size)

     返回值：解码完一帧音频到缓存后，缓存占用的实际大小，以字节为单位，为负数表示失败

     aCodecCtx：输入，解码上下文

     audio_buf：输出，解码成功后，输出到的缓存的首地址

     buf_size：输入，audio_buf的预留空间

     该函数是实际上是从尾部开始执行的，先取得main线程放入队列的包，再用库函数avcodec_decode_audio2处理，如果一次调用没有处理 完一个包的数据，记录下处理到包的那个位置了，下次接着处理（这种情况可能是因为一个音频包，包含多个音频帧的数据引起）

库函数avcodec_decode_audio2

    原型:int avcodec_decode_audio2(AVCodecContext *avctx, int16_t *samples,
                         int *frame_size_ptr,
                         const uint8_t *buf, int buf_size);
    avctx ： 解码器上下文
    samples： 输出参数  输出数据的缓存首地址.
    frame_size_ptr：既是输入又是输出，无帧可解返回0，解码失败返回负数，解码成功返回，解码后一帧音频所占空间，以字节为单位
    buf： 输入参数，输入数据的缓存
    buf_size：输入参数，buf的大小
    返回值：无帧可解返回0，解码失败返回负数，解码成功返回解码前一帧音频所占空间

SDL_CondWait库函数

    等待消息时解锁，等到消息后加锁，该函数可以阻塞代码的执行，一般和SDL_CondSignal库函数（或SDL_CondBroadcast库函数）配对使用