V2.0.0

1.修复声音问题

src/video/getvideothread.cpp

@@ -160,15 +160,19 @@ ErroCode GetVideoThread::init(QString videoDevName, bool useVideo, QString audio
 
     audioindex = -1;
     aCodecCtx = NULL;
+
     if (useAudio)
     {
 
         for(i=0; i<pFormatCtx->nb_streams; i++)
+        {
             if(pFormatCtx->streams[i]->codec->codec_type==AVMEDIA_TYPE_AUDIO)
             {
                 audioindex=i;
                 break;
             }
+        }
+
         if(audioindex==-1)
         {
             printf("Didn't find a video stream.（没有找到视频流）\n");
@@ -195,6 +199,71 @@ ErroCode GetVideoThread::init(QString videoDevName, bool useVideo, QString audio
 
         aFrame = av_frame_alloc();
 
+        //重采样设置选项-----------------------------------------------------------start
+        aFrame_ReSample = nullptr;
+
+        //frame->16bit 44100 PCM 统一音频采样格式与采样率
+        swrCtx = nullptr;
+
+        //输入的声道布局
+        int in_ch_layout;
+
+        //输出的声道布局
+        int out_ch_layout = av_get_default_channel_layout(audio_tgt_channels); ///AV_CH_LAYOUT_STEREO
+
+        out_ch_layout &= ~AV_CH_LAYOUT_STEREO;
+
+        /// 这里音频播放使用了固定的参数
+        /// 强制将音频重采样成44100 双声道  AV_SAMPLE_FMT_S16
+        /// SDL播放中也是用了同样的播放参数
+        //重采样设置选项----------------
+        //输入的采样格式
+        in_sample_fmt = aCodecCtx->sample_fmt;
+        //输出的采样格式 32bit PCM
+        out_sample_fmt = AV_SAMPLE_FMT_FLTP;
+        //输入的采样率
+        in_sample_rate = aCodecCtx->sample_rate;
+        //输入的声道布局
+        in_ch_layout = aCodecCtx->channel_layout;
+
+        //输出的采样率
+        out_sample_rate = 44100;
+        //输出的声道布局
+
+        out_ch_layout = AV_CH_LAYOUT_STEREO;
+
+        audio_tgt_channels = av_get_channel_layout_nb_channels(out_ch_layout);
+        out_ch_layout = av_get_default_channel_layout(audio_tgt_channels); ///AV_CH_LAYOUT_STEREO
+
+        if (in_ch_layout <= 0)
+        {
+            if (aCodecCtx->channels == 2)
+            {
+                in_ch_layout = AV_CH_LAYOUT_STEREO;
+            }
+            else
+            {
+                in_ch_layout = AV_CH_LAYOUT_MONO;
+            }
+            in_ch_layout = AV_CH_LAYOUT_STEREO;//av_get_default_channel_layout(aCodecCtx->channels);
+        }
+//qDebug()<<"1111:"<<in_sample_fmt<<in_sample_rate<<in_ch_layout<<aCodecCtx->channels<<out_sample_fmt<<out_sample_rate<<out_ch_layout<<audio_tgt_channels;
+        swrCtx = swr_alloc_set_opts(nullptr, out_ch_layout, out_sample_fmt, out_sample_rate,
+                                             in_ch_layout, in_sample_fmt, in_sample_rate, 0, nullptr);
+
+        /** Open the resampler with the specified parameters. */
+        int ret = swr_init(swrCtx);
+        if (ret < 0)
+        {
+            char buff[128]={0};
+            av_strerror(ret, buff, 128);
+
+            printf("Could not open resample context %s\n", buff);
+            swr_free(&swrCtx);
+            swrCtx = nullptr;
+
+            return AudioDecoderOpenFailed;
+        }
     }
 
     return SUCCEED;
@@ -392,15 +461,30 @@ void GetVideoThread::run()
 
             if (got_frame)
             {
-                if (m_saveVideoFileThread)
+                /// 这里重采样成44100 双声道 AV_SAMPLE_FMT_FLTP
+                if (aFrame_ReSample == nullptr)
                 {
-                    int size = av_samples_get_buffer_size(NULL,aCodecCtx->channels, aFrame->nb_samples,aCodecCtx->sample_fmt, 1);
+                    aFrame_ReSample = av_frame_alloc();
+
+                    aFrame_ReSample->nb_samples = av_rescale_rnd(swr_get_delay(swrCtx, out_sample_rate) + aFrame->nb_samples,
+                                out_sample_rate, in_sample_rate, AV_ROUND_UP);
 
-                    memcpy(audio_buf + audio_buf_size, aFrame->data[0], size);
-                    audio_buf_size += size;
+                    av_samples_fill_arrays(aFrame_ReSample->data, aFrame_ReSample->linesize, audio_buf_resample, audio_tgt_channels, aFrame_ReSample->nb_samples, out_sample_fmt, 0);
+
+                }
+
+                int len2 = swr_convert(swrCtx, aFrame_ReSample->data, aFrame_ReSample->nb_samples, (const uint8_t**)aFrame->data, aFrame->nb_samples);
+                int resampled_data_size = len2 * audio_tgt_channels * av_get_bytes_per_sample(out_sample_fmt);
+
+//qDebug()<<"audio info:"<<aCodecCtx->bit_rate<<aCodecCtx->sample_fmt<<aCodecCtx->sample_rate<<aCodecCtx->channels<<audio_tgt_channels;
+
+                if (m_saveVideoFileThread)
+                {
+                    memcpy(audio_buf + audio_buf_size, audio_buf_resample, resampled_data_size);
+                    audio_buf_size += resampled_data_size;
 
                     int index = 0;
-                    int ONEAudioSize = m_saveVideoFileThread->audio_input_frame_size;//4096
+                    int ONEAudioSize = m_saveVideoFileThread->getONEFrameSize();
 
                     int totalSize = audio_buf_size;
                     int leftSize  = audio_buf_size;
@@ -428,6 +512,45 @@ void GetVideoThread::run()
                     }
                 }
             }
+
+//            if (got_frame)
+//            {
+//                if (m_saveVideoFileThread)
+//                {
+//                    int size = av_samples_get_buffer_size(NULL,aCodecCtx->channels, aFrame->nb_samples,aCodecCtx->sample_fmt, 1);
+
+//                    memcpy(audio_buf + audio_buf_size, aFrame->data[0], size);
+//                    audio_buf_size += size;
+
+//                    int index = 0;
+//                    int ONEAudioSize = m_saveVideoFileThread->audio_input_frame_size;//4096
+
+//                    int totalSize = audio_buf_size;
+//                    int leftSize  = audio_buf_size;
+
+//                    while(1)
+//                    {
+//                        if (leftSize >= ONEAudioSize)
+//                        {
+//                            uint8_t * buffer = (uint8_t *)malloc(ONEAudioSize);
+//                            memcpy(buffer, audio_buf+index, ONEAudioSize);
+//                            m_saveVideoFileThread->audioDataQuene_Input((uint8_t*)buffer, ONEAudioSize);
+
+//                            index    += ONEAudioSize;
+//                            leftSize -= ONEAudioSize;
+//                        }
+//                        else
+//                        {
+//                            if (leftSize > 0)
+//                            {
+//                                memcpy(audio_buf, audio_buf+index, leftSize);
+//                            }
+//                            audio_buf_size = leftSize;
+//                            break;
+//                        }
+//                    }
+//                }
+//            }
         }
 
         av_packet_unref(packet);

src/video/getvideothread.h

@@ -56,11 +56,32 @@ private:
 
     AVFormatContext	*pFormatCtx;
     int				i, videoindex ,audioindex;
-    AVCodecContext	*pCodecCtx,*aCodecCtx;
 
-    AVFrame	*pFrame,*aFrame,*pFrameYUV;
+    ///视频相关
+    AVCodecContext *pCodecCtx;
+    AVCodec *pCodec;
+    AVFrame	*pFrame,*pFrameYUV;
     uint8_t *out_buffer;
 
+    ///音频相关
+    AVCodecContext *aCodecCtx;
+    AVCodec *aCodec;
+    AVFrame *aFrame;
+
+    ///以下变量用于音频重采样
+    /// 由于新版ffmpeg编码aac只支持AV_SAMPLE_FMT_FLTP，因此采集到音频数据后直接进行重采样
+    /// 重采样成44100的32 bits 双声道数据(AV_SAMPLE_FMT_FLTP)
+    AVFrame *aFrame_ReSample;
+    SwrContext *swrCtx;
+
+    enum AVSampleFormat in_sample_fmt; //输入的采样格式
+    enum AVSampleFormat out_sample_fmt;//输出的采样格式 16bit PCM
+    int in_sample_rate;//输入的采样率
+    int out_sample_rate;//输出的采样率
+    int audio_tgt_channels; ///av_get_channel_layout_nb_channels(out_ch_layout);
+    DECLARE_ALIGNED(16, uint8_t, audio_buf_resample) [AVCODEC_MAX_AUDIO_FRAME_SIZE * 4];
+
+
     int pic_x;
     int pic_y;
     int pic_w;

src/video/savevideofile.cpp

@@ -43,6 +43,46 @@
 //    return av_interleaved_write_frame(fmt_ctx, pkt);
 //}
 
+/**
+*  Add ADTS header at the beginning of each and every AAC packet.
+*  This is needed as MediaCodec encoder generates a packet of raw
+*  AAC data.
+*
+*  Note the packetLen must count in the ADTS header itself !!! .
+*注意，这里的packetLen参数为raw aac Packet Len + 7; 7 bytes adts header
+**/
+void addADTStoPacket(uint8_t* packet, int packetLen)
+{
+   int profile = 2;  //AAC LC，MediaCodecInfo.CodecProfileLevel.AACObjectLC;
+   int freqIdx = 4;  //32K, 见后面注释avpriv_mpeg4audio_sample_rates中32000对应的数组下标，来自ffmpeg源码
+   int chanCfg = 2;  //见后面注释channel_configuration，Stero双声道立体声
+
+   /*int avpriv_mpeg4audio_sample_rates[] = {
+       96000, 88200, 64000, 48000, 44100, 32000,
+               24000, 22050, 16000, 12000, 11025, 8000, 7350
+   };
+   channel_configuration: 表示声道数chanCfg
+   0: Defined in AOT Specifc Config
+   1: 1 channel: front-center
+   2: 2 channels: front-left, front-right
+   3: 3 channels: front-center, front-left, front-right
+   4: 4 channels: front-center, front-left, front-right, back-center
+   5: 5 channels: front-center, front-left, front-right, back-left, back-right
+   6: 6 channels: front-center, front-left, front-right, back-left, back-right, LFE-channel
+   7: 8 channels: front-center, front-left, front-right, side-left, side-right, back-left, back-right, LFE-channel
+   8-15: Reserved
+   */
+
+   // fill in ADTS data
+   packet[0] = (uint8_t)0xFF;
+   packet[1] = (uint8_t)0xF9;
+   packet[2] = (uint8_t)(((profile-1)<<6) + (freqIdx<<2) +(chanCfg>>2));
+   packet[3] = (uint8_t)(((chanCfg&3)<<6) + (packetLen>>11));
+   packet[4] = (uint8_t)((packetLen&0x7FF) >> 3);
+   packet[5] = (uint8_t)(((packetLen&7)<<5) + 0x1F);
+   packet[6] = (uint8_t)0xFC;
+}
+
 SaveVideoFileThread::SaveVideoFileThread()
 {
     isStop = false;
@@ -250,7 +290,7 @@ void SaveVideoFileThread::add_audio_stream(OutputStream *ost, AVFormatContext *o
                                                 AVCodec **codec,
                                                 enum AVCodecID codec_id)
 {
-    AVCodecContext *c;
+    AVCodecContext *aCodecCtx;
     int i;
 
     /* find the video encoder */
@@ -267,175 +307,102 @@ void SaveVideoFileThread::add_audio_stream(OutputStream *ost, AVFormatContext *o
     }
 
     ost->st->id = oc->nb_streams-1;
-    c = avcodec_alloc_context3(*codec);
-    if (!c) {
+
+    const AVCodec* aCodec = *codec;
+
+    aCodecCtx = avcodec_alloc_context3(aCodec);
+    if (!aCodecCtx)
+    {
         fprintf(stderr, "Could not alloc an encoding context\n");
         exit(1);
     }
-    ost->enc = c;
 
-    c->sample_fmt  = (*codec)->sample_fmts ? (*codec)->sample_fmts[0] : AV_SAMPLE_FMT_FLTP;
-    c->bit_rate    = 64000;
-    c->sample_rate = 44100;
+    ///先用这句话找出 aac编码器支持的 sample_fmt
+    /// 我找出的是 AV_SAMPLE_FMT_FLTP
+    const enum AVSampleFormat *p = aCodec->sample_fmts;
+    fprintf(stderr, "aac encoder sample format is: %s \n",av_get_sample_fmt_name(*p));
+
+    ost->enc = aCodecCtx;
+
+//    aCodecCtx->codec_type = AVMEDIA_TYPE_AUDIO;
+    aCodecCtx->sample_fmt = AV_SAMPLE_FMT_FLTP;
+    aCodecCtx->sample_rate= 44100;
+    aCodecCtx->channels = 2;
+    aCodecCtx->channel_layout=av_get_default_channel_layout(aCodecCtx->channels);
+
+//    aCodecCtx->channels       = av_get_channel_layout_nb_channels(aCodecCtx->channel_layout);
+//    aCodecCtx->channel_layout = AV_CH_LAYOUT_STEREO;
+
+//    aCodecCtx->profile=FF_PROFILE_AAC_LOW; //（可参考AAC格式简介）
+//    aCodecCtx->strict_std_compliance = FF_COMPLIANCE_EXPERIMENTAL;
 
-    if ((*codec)->supported_samplerates) {
-        c->sample_rate = (*codec)->supported_samplerates[0];
-        for (i = 0; (*codec)->supported_samplerates[i]; i++) {
+//    aCodecCtx->bit_rate = 64000;
+
+#if 0
+    if ((*codec)->supported_samplerates)
+    {
+        aCodecCtx->sample_rate = (*codec)->supported_samplerates[0];
+
+        for (i = 0; (*codec)->supported_samplerates[i]; i++)
+        {
             if ((*codec)->supported_samplerates[i] == 44100)
-                c->sample_rate = 44100;
+                aCodecCtx->sample_rate = 44100;
         }
     }
-    c->channels        = av_get_channel_layout_nb_channels(c->channel_layout);
-    c->channel_layout = AV_CH_LAYOUT_STEREO;
+
     if ((*codec)->channel_layouts)
     {
-        c->channel_layout = (*codec)->channel_layouts[0];
+        aCodecCtx->channel_layout = (*codec)->channel_layouts[0];
         for (i = 0; (*codec)->channel_layouts[i]; i++)
         {
             if ((*codec)->channel_layouts[i] == AV_CH_LAYOUT_STEREO)
-                c->channel_layout = AV_CH_LAYOUT_STEREO;
+                aCodecCtx->channel_layout = AV_CH_LAYOUT_STEREO;
         }
     }
-    c->channels        = av_get_channel_layout_nb_channels(c->channel_layout);
-    ost->st->time_base.num = 1; // = (AVRational){ 1, c->sample_rate };
-    ost->st->time_base.den = c->sample_rate;
-
-//qDebug()<<__FUNCTION__<<c<<c->codec<<c->codec_id;
-//qDebug()<<__FUNCTION__<<ost->enc<<ost->enc->codec<<ost->enc->codec_id;
-//    c->codec_id = codec_id;
-//    c->codec_type = AVMEDIA_TYPE_AUDIO;
-
-//    /* put sample parameters */
-//    c->sample_fmt = AV_SAMPLE_FMT_S16;
-//    c->bit_rate = 64000;
-//    c->sample_rate = 44100;
-//    c->channels = 2;
-//qDebug()<<__FUNCTION__<<ost->enc<<ost->enc->codec<<ost->enc->codec_id;
-////    c->bit_rate = 9600;
-////    c->sample_rate = 11025;
-////    c->channels = 1;
-
-}
-
-static AVFrame *alloc_audio_frame(enum AVSampleFormat sample_fmt,
-                                  uint64_t channel_layout,
-                                  int sample_rate, int nb_samples)
-{
-    AVFrame *frame = av_frame_alloc();
-    int ret;
-
-    if (!frame) {
-        fprintf(stderr, "Error allocating an audio frame\n");
-        exit(1);
-    }
-
-    frame->format = sample_fmt;
-    frame->channel_layout = channel_layout;
-    frame->sample_rate = sample_rate;
-    frame->nb_samples = nb_samples;
+    aCodecCtx->channels        = av_get_channel_layout_nb_channels(aCodecCtx->channel_layout);
+#endif
 
-    if (nb_samples) {
-        ret = av_frame_get_buffer(frame, 0);
-        if (ret < 0) {
-            fprintf(stderr, "Error allocating an audio buffer\n");
-            exit(1);
-        }
-    }
+    ost->st->time_base.num = 1; // = (AVRational){ 1, c->sample_rate };
+    ost->st->time_base.den = aCodecCtx->sample_rate;
 
-    return frame;
 }
 
 void SaveVideoFileThread::open_audio(AVFormatContext *oc, AVCodec *codec, OutputStream *ost)
 {
-    AVCodecContext *c;
-    int nb_samples;
-    int ret;
-
-    c = ost->enc;
+    AVCodecContext *aCodecCtx = ost->enc;
 
     /* open it */
-    if (avcodec_open2(c, codec, NULL) < 0) {
+    if (avcodec_open2(aCodecCtx, codec, NULL) < 0)
+    {
         qDebug("could not open codec\n");
         exit(1);
     }
 
-    /* init signal generator */
-    ost->t     = 0;
-    ost->tincr = 2 * M_PI * 110.0 / c->sample_rate;
-    /* increment frequency by 110 Hz per second */
-    ost->tincr2 = 2 * M_PI * 110.0 / c->sample_rate / c->sample_rate;
+    mONEFrameSize = av_samples_get_buffer_size(NULL, aCodecCtx->channels, aCodecCtx->frame_size, aCodecCtx->sample_fmt, 1);
 
-//    if (c->codec->capabilities & AV_CODEC_CAP_VARIABLE_FRAME_SIZE)
-//        nb_samples = 10000;
-//    else
-//        nb_samples = c->frame_size;
+    ost->frame           = av_frame_alloc();
+    ost->frameBuffer     = (uint8_t *)av_malloc(mONEFrameSize);
+    ost->frameBufferSize = mONEFrameSize;
 
-    if (codec->capabilities & AV_CODEC_CAP_VARIABLE_FRAME_SIZE)
-        nb_samples = 10000;
-    else
-        nb_samples = c->frame_size;
+    ///这句话必须要(设置这个frame里面的采样点个数)
+    int oneChannelBufferSize = mONEFrameSize / aCodecCtx->channels; //计算出一个声道的数据
+    int nb_samplesize = oneChannelBufferSize / av_get_bytes_per_sample(aCodecCtx->sample_fmt); //计算出采样点个数
+    ost->frame->nb_samples = nb_samplesize;
 
-    ost->frame     = alloc_audio_frame(c->sample_fmt, c->channel_layout,
-                                       c->sample_rate, nb_samples);
-    ost->tmp_frame = alloc_audio_frame(AV_SAMPLE_FMT_S16, c->channel_layout,
-                                       c->sample_rate, nb_samples);
+    ///这2种方式都可以
+//    avcodec_fill_audio_frame(ost->frame, aCodecCtx->channels, aCodecCtx->sample_fmt,(const uint8_t*)ost->frameBuffer, mONEFrameSize, 0);
+    av_samples_fill_arrays(ost->frame->data, ost->frame->linesize, ost->frameBuffer, aCodecCtx->channels, ost->frame->nb_samples, aCodecCtx->sample_fmt, 0);
 
-    ost->frameBuffer = (uint8_t *) av_malloc(AVCODEC_MAX_AUDIO_FRAME_SIZE);
-    ost->frameBufferSize = 0;
+    ost->tmp_frame = nullptr;
 
     /* copy the stream parameters to the muxer */
-    ret = avcodec_parameters_from_context(ost->st->codecpar, c);
-    if (ret < 0) {
+    int ret = avcodec_parameters_from_context(ost->st->codecpar, aCodecCtx);
+    if (ret < 0)
+    {
         fprintf(stderr, "Could not copy the stream parameters\n");
         exit(1);
     }
 
-
-    /* create resampler context */
-    ost->swr_ctx = swr_alloc();
-    if (!ost->swr_ctx) {
-        fprintf(stderr, "Could not allocate resampler context\n");
-        exit(1);
-    }
-
-    /* set options */
-    av_opt_set_int       (ost->swr_ctx, "in_channel_count",   c->channels,       0);
-    av_opt_set_int       (ost->swr_ctx, "in_sample_rate",     c->sample_rate,    0);
-    av_opt_set_sample_fmt(ost->swr_ctx, "in_sample_fmt",      AV_SAMPLE_FMT_S16, 0);
-    av_opt_set_int       (ost->swr_ctx, "out_channel_count",  c->channels,       0);
-    av_opt_set_int       (ost->swr_ctx, "out_sample_rate",    c->sample_rate,    0);
-    av_opt_set_sample_fmt(ost->swr_ctx, "out_sample_fmt",     c->sample_fmt,     0);
-
-    /* initialize the resampling context */
-    if ((ret = swr_init(ost->swr_ctx)) < 0) {
-        fprintf(stderr, "Failed to initialize the resampling context\n");
-        exit(1);
-    }
-
-    audio_input_frame_size = nb_samples * 4;
-
-}
-
-/* Prepare a 16 bit dummy audio frame of 'frame_size' samples and
- * 'nb_channels' channels. */
-static AVFrame *get_audio_frame(OutputStream *ost)
-{
-    AVFrame *frame = ost->tmp_frame;
-    int j, i, v;
-    int16_t *q = (int16_t*)frame->data[0];
-
-    for (j = 0; j <frame->nb_samples; j++) {
-        v = (int)(sin(ost->t) * 10000);
-        for (i = 0; i < ost->enc->channels; i++)
-            *q++ = v;
-        ost->t     += ost->tincr;
-        ost->tincr += ost->tincr2;
-    }
-
-    frame->pts = ost->next_pts;
-    ost->next_pts  += frame->nb_samples;
-
-    return frame;
 }
 
 /*
@@ -445,93 +412,78 @@ static AVFrame *get_audio_frame(OutputStream *ost)
 //static int write_audio_frame(AVFormatContext *oc, OutputStream *ost)
 bool SaveVideoFileThread::write_audio_frame(AVFormatContext *oc, OutputStream *ost)
 {
-    AVCodecContext *c;
-    AVPacket pkt = { 0 }; // data and size must be 0;
-    AVFrame *frame;
-    int ret = 0;
-    int got_packet;
-    int dst_nb_samples;
+    AVCodecContext *aCodecCtx = ost->enc;
 
-    c = ost->enc;
+    AVPacket pkt;
+    av_init_packet(&pkt);
+
+    AVPacket *packet = &pkt;
 
-#if 1
+    AVFrame *aFrame;
 
     BufferDataNode node;
 
     if (audioDataQuene_get(node))
     {
-        frame = ost->frame;
-    //        memset(frame->data[0], 0x0, frame->nb_samples);
-        memcpy(frame->data[0], node.buffer, frame->nb_samples);
-    //            memcpy(frame->data[0], node.buffer, node.bufferSize);
+        aFrame = ost->frame;
+
+        memcpy(ost->frameBuffer, node.buffer, node.bufferSize);
+
         free(node.buffer);
 
-        frame->pts = ost->next_pts;
-        ost->next_pts  += frame->nb_samples;
+        aFrame->pts = ost->next_pts;
+        ost->next_pts  += aFrame->nb_samples;
     }
     else
     {
         return false;
     }
 
-#else
-    frame = get_audio_frame(ost); //自动生成音频数据
-#endif
+    if (aFrame)
+    {
+        AVRational rational;
+        rational.num = 1;
+        rational.den = aCodecCtx->sample_rate;
+        aFrame->pts = av_rescale_q(ost->samples_count, rational, aCodecCtx->time_base);
+        ost->samples_count += aFrame->nb_samples;
+    }
 
-    if (frame)
+    /* send the frame for encoding */
+    int ret = avcodec_send_frame(aCodecCtx, aFrame);
+    if (ret < 0)
     {
-        /* convert samples from native format to destination codec format, using the resampler */
-        /* compute destination number of samples */
-        dst_nb_samples = av_rescale_rnd(swr_get_delay(ost->swr_ctx, c->sample_rate) + frame->nb_samples,
-                                        c->sample_rate, c->sample_rate, AV_ROUND_UP);
-        av_assert0(dst_nb_samples == frame->nb_samples);
-
-//        /* when we pass a frame to the encoder, it may keep a reference to it
-//         * internally;
-//         * make sure we do not overwrite it here
-//         */
-//        ret = av_frame_make_writable(ost->frame);
-//        if (ret < 0)
-//            exit(1);
+        fprintf(stderr, "Error sending the frame to the audio encoder\n");
+        return false;
+    }
 
-        /* convert to destination format */
-        ret = swr_convert(ost->swr_ctx,
-                          ost->frame->data, dst_nb_samples,
-                          (const uint8_t **)frame->data, frame->nb_samples);
-        if (ret < 0)
+    /* read all the available output packets (in general there may be any
+     * number of them */
+    while (ret >= 0)
+    {
+        ret = avcodec_receive_packet(aCodecCtx, packet);
+
+        if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF || ret < 0)
         {
             char errstr[AV_ERROR_MAX_STRING_SIZE] = {0};
             av_make_error_string(errstr, AV_ERROR_MAX_STRING_SIZE, ret);
-            QString logStr = QString("!!!!!!!!!! Error while converting: %1 ret=%2")
+            QString logStr = QString("!!!!!!!!!! Error encoding audio frame: %1 ret=%2")
                         .arg(QString(errstr))
                         .arg(ret);
             AppConfig::WriteLog(logStr);
+            return false;
         }
-        frame = ost->frame;
-
-        AVRational rational;
-        rational.num = 1;
-        rational.den = c->sample_rate;
-        frame->pts = av_rescale_q(ost->samples_count, rational, c->time_base);
-        ost->samples_count += dst_nb_samples;
-    }
-
-    ret = avcodec_encode_audio2(c, &pkt, frame, &got_packet);
 
-    if (ret < 0)
-    {
-        char errstr[AV_ERROR_MAX_STRING_SIZE] = {0};
-        av_make_error_string(errstr, AV_ERROR_MAX_STRING_SIZE, ret);
-        QString logStr = QString("!!!!!!!!!! Error encoding audio frame: %1 ret=%2")
-                    .arg(QString(errstr))
-                    .arg(ret);
-        AppConfig::WriteLog(logStr);
-    }
+#if 0 ///写入aac文件
+        uint8_t * aac_buf = (uint8_t *)malloc(packet->size+7);
+        addADTStoPacket(aac_buf, 7+packet->size);
+        memcpy(aac_buf+7, packet->data, packet->size);
+        static FILE *aacFp = fopen("out22.aac", "wb");
+        fwrite(aac_buf,1,packet->size+7,aacFp);
+#endif
 
-    if (got_packet)
-    {
+        ////
         /* rescale output packet timestamp values from codec to stream timebase */
-        av_packet_rescale_ts(&pkt, c->time_base, ost->st->time_base);
+        av_packet_rescale_ts(&pkt, aCodecCtx->time_base, ost->st->time_base);
         pkt.stream_index = ost->st->index;
 
 //        audio_pts = pkt.pts;
@@ -552,19 +504,11 @@ bool SaveVideoFileThread::write_audio_frame(AVFormatContext *oc, OutputStream *o
             AppConfig::WriteLog(logStr);
         }
 
-        av_packet_unref(&pkt);
+        av_packet_unref(packet);
+        break;
     }
 
-//qDebug()<<__FUNCTION__<<"1111 99999";
-
-    if (ret < 0)
-    {
-        return false;
-    }
-    else
-    {
-        return (frame || got_packet) ? 0 : 1;
-    }
+    return true;
 
 }
 
@@ -572,9 +516,9 @@ void SaveVideoFileThread::close_audio(AVFormatContext *oc, OutputStream *ost)
 {
     avcodec_free_context(&ost->enc);
     av_frame_free(&ost->frame);
+
+    if (ost->tmp_frame != nullptr)
     av_frame_free(&ost->tmp_frame);
-    sws_freeContext(ost->sws_ctx);
-    swr_free(&ost->swr_ctx);
 
     if (ost->frameBuffer != NULL)
     {
@@ -854,7 +798,7 @@ bool SaveVideoFileThread::write_video_frame(AVFormatContext *oc, OutputStream *o
 
         memcpy(ost->frameBuffer, node->buffer, node->bufferSize);
 
-//不止为何下面这两种方式都不行
+//不知为何下面这两种方式都不行
 //        int y_size = c->width * c->height;
 //        memcpy(ost->frame->data[0], node->buffer, y_size * 3 / 2);
 
@@ -888,7 +832,6 @@ bool SaveVideoFileThread::write_video_frame(AVFormatContext *oc, OutputStream *o
         ///将Pts转换成毫秒的形式，这里pts仅仅用于显示，不会修改写入文件的pts
         video_pts = av_rescale_q(pkt.pts, ost->st->time_base, {1, 1000});
 
-
         /* Write the compressed frame to the media file. */
         ret = av_interleaved_write_frame(oc, &pkt);
         if (ret < 0)
@@ -912,10 +855,9 @@ void SaveVideoFileThread::close_video(AVFormatContext *oc, OutputStream *ost)
 {
     avcodec_free_context(&ost->enc);
     av_frame_free(&ost->frame);
+
     if (ost->tmp_frame != NULL)
         av_frame_free(&ost->tmp_frame);
-    sws_freeContext(ost->sws_ctx);
-    swr_free(&ost->swr_ctx);
 
     if (ost->frameBuffer != NULL)
     {
@@ -1062,7 +1004,7 @@ while(1)
 
     while(1)
     {
-//        qDebug()<<video_st.next_pts<<audio_st.next_pts<<video_pts<<audio_pts;
+//        qDebug()<<__FUNCTION__<<video_st.next_pts<<audio_st.next_pts<<video_pts<<audio_pts;
 
         /* select the stream to encode */
         if (!have_audio || (av_compare_ts(video_st.next_pts, video_st.enc->time_base, audio_st.next_pts, audio_st.enc->time_base) <= 0))

src/video/savevideofile.h

@@ -45,10 +45,6 @@ typedef struct OutputStream
     uint8_t *frameBuffer;
     int frameBufferSize;
 
-    float t, tincr, tincr2;
-
-    struct SwsContext *sws_ctx;
-    struct SwrContext *swr_ctx;
 } OutputStream;
 
 struct BufferDataNode
@@ -81,7 +77,7 @@ public:
     void audioDataQuene_Input(const uint8_t * buffer,const int &size);
     bool audioDataQuene_get(BufferDataNode &node);
 
-    int audio_input_frame_size;
+    int getONEFrameSize(){return mONEFrameSize;}
 
     void setContainsVideo(bool);
     void setContainsAudio(bool);
@@ -111,6 +107,8 @@ private:
 
     int mBitRate; //video bitRate
 
+    int mONEFrameSize;
+
     int WIDTH;
     int HEIGHT;