播放声音和播放视频数有点区别的。
这里将解码得到的音频AVPacket放到一个一个的队列中,然后在SDL的回调函数里面取每一个AVPacket,并将其解码,将得到的buffer填充到SDL请求获取的buffer中。
这里需要注意的是: 在audio_decode_frame的avcodec_decode_audio4函数里面,我们获取到的每一个AVFrame,都需要判断其格式,因为SDL需要的音频格式为
AV_SAMPLE_FMT_S16,因此从文件里面获取的音频格式若不是AV_SAMPLE_FMT_S16的话,需要做一个重采样。
下面是代码:
// tutorial03.c // A pedagogical video player that will stream through every video frame as fast as it can // and play audio (out of sync). // // This tutorial was written by Stephen Dranger ([email protected]). // // Code based on FFplay, Copyright (c) 2003 Fabrice Bellard, // and a tutorial by Martin Bohme ([email protected]) // Tested on Gentoo, CVS version 5/01/07 compiled with GCC 4.1.1 // // Use the Makefile to build all examples. // // Run using // tutorial03 myvideofile.mpg // // to play the stream on your screen. extern "C" { #include "libavutil/avstring.h" #include "libavutil/mathematics.h" #include "libavutil/pixdesc.h" #include "libavutil/imgutils.h" #include "libavutil/dict.h" #include "libavutil/parseutils.h" #include "libavutil/samplefmt.h" #include "libavutil/avassert.h" #include "libavutil/time.h" #include "libavformat/avformat.h" #include "libavdevice/avdevice.h" #include "libswscale/swscale.h" #include "libavutil/opt.h" #include "libavcodec/avfft.h" #include "libswresample/swresample.h" #include "SDL1.2/SDL.h" #include "SDL1.2/SDL_thread.h" } #pragma comment(lib, "avcodec.lib") #pragma comment(lib, "avformat.lib") #pragma comment(lib, "avutil.lib") #pragma comment(lib, "avdevice.lib") #pragma comment(lib, "avfilter.lib") #pragma comment(lib, "postproc.lib") #pragma comment(lib, "swresample.lib") #pragma comment(lib, "swscale.lib") #pragma comment(lib, "SDL.lib") #ifdef __MINGW32__ #undef main /* Prevents SDL from overriding main() */ #endif #include <stdio.h> #define SDL_AUDIO_BUFFER_SIZE 1024 #define MAX_AUDIO_FRAME_SIZE 192000 struct SwrContext *swr_ctx; DECLARE_ALIGNED(16, uint8_t, audio_buf2)[MAX_AUDIO_FRAME_SIZE * 4]; static inline double rint(double x) { return x >= 0 ? floor(x + 0.5) : ceil(x - 0.5); } 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; static AVFrame frame; 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; if (got_frame) { uint64_t dec_channel_layout = (aCodecCtx->channel_layout && aCodecCtx->channels == av_get_channel_layout_nb_channels(aCodecCtx->channel_layout)) ? aCodecCtx->channel_layout : av_get_default_channel_layout(aCodecCtx->channels); AVSampleFormat tgtFmt = AV_SAMPLE_FMT_S16; if( aCodecCtx->sample_fmt != tgtFmt ) { // 需要重采样 if( swr_ctx == NULL ) { swr_ctx = swr_alloc(); swr_ctx = swr_alloc_set_opts(swr_ctx, dec_channel_layout, tgtFmt, aCodecCtx->sample_rate, dec_channel_layout, aCodecCtx->sample_fmt, aCodecCtx->sample_rate, 0, NULL); if( !swr_ctx || swr_init(swr_ctx) < 0 ) { assert(false); } } if( swr_ctx ) { const uint8_t **in = (const uint8_t **)frame.extended_data; uint8_t *out[] = {audio_buf2}; int out_count = sizeof(audio_buf2) / aCodecCtx->channels / av_get_bytes_per_sample(aCodecCtx->sample_fmt); int len2 = swr_convert(swr_ctx, out, out_count, in, frame.nb_samples); if( len2 < 0 ) { LogPrintfA("swr_convert() failed\n"); break; } if( len2 == out_count ) { LogPrintfA("warning: audio buffer is probably too small\n"); swr_init(swr_ctx); } data_size = len2 * aCodecCtx->channels * av_get_bytes_per_sample(tgtFmt); memcpy(audio_buf, audio_buf2, data_size); } } else { // 不需要重采样 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; } /* 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, audio_buf_size); 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 _tmain() { AVFormatContext *pFormatCtx = NULL; int i, videoStream, audioStream; AVCodecContext *pCodecCtx = NULL; AVCodec *pCodec = NULL; AVFrame *pFrame = NULL; AVPacket packet; int frameFinished; //float aspect_ratio; AVCodecContext *aCodecCtx = NULL; AVCodec *aCodec = NULL; SDL_Overlay *bmp = NULL; SDL_Surface *screen = NULL; SDL_Rect rect; SDL_Event event; SDL_AudioSpec wanted_spec, spec; struct SwsContext *sws_ctx = NULL; AVDictionary *videoOptionsDict = NULL; AVDictionary *audioOptionsDict = NULL; char szFile[] = "song.flv"; // 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); } // Open video file if( avformat_open_input(&pFormatCtx, szFile, 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, szFile, 0); // Find the first video stream videoStream = -1; audioStream = -1; for( i = 0; i < pFormatCtx->nb_streams; i ++) { if( pFormatCtx->streams[i]->codec->codec_type == AVMEDIA_TYPE_VIDEO && videoStream < 0) { videoStream = 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; } aCodecCtx = pFormatCtx->streams[audioStream]->codec; // Set audio settings from codec info 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_open2(aCodecCtx, aCodec, &audioOptionsDict); // audio_st = pFormatCtx->streams[index] packet_queue_init(&audioq); SDL_PauseAudio(0); // Get a pointer to the codec context for the video stream pCodecCtx = pFormatCtx->streams[videoStream]->codec; // Find the decoder for the video stream pCodec = avcodec_find_decoder(pCodecCtx->codec_id); if( pCodec == NULL ) { fprintf(stderr, "Unsupported codec!\n"); return -1; // Codec not found } // Open codec if( avcodec_open2(pCodecCtx, pCodec, &videoOptionsDict) < 0 ) { return -1; // Could not open codec } // Allocate video frame pFrame = av_frame_alloc(); // Make a screen to put our video #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); } // Allocate a place to put our YUV image on that screen bmp = SDL_CreateYUVOverlay(pCodecCtx->width, pCodecCtx->height, SDL_YV12_OVERLAY, screen); sws_ctx = sws_getContext ( pCodecCtx->width, pCodecCtx->height, pCodecCtx->pix_fmt, pCodecCtx->width, pCodecCtx->height, PIX_FMT_YUV420P, SWS_BILINEAR, NULL, NULL, NULL ); // Read frames and save first five frames to disk 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_video2(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 ( sws_ctx, (uint8_t const * const *)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); av_free_packet(&packet); SDL_Delay(40); } } 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 YUV frame av_free(pFrame); // Close the codec avcodec_close(pCodecCtx); // Close the video file avformat_close_input(&pFormatCtx); return 0; }