1 files changed, 23 insertions, 159 deletions

diff --git a/rotord/rendercontext.cpp b/rotord/rendercontext.cpp
index 9e6d958..422ef08 100644
--- a/rotord/rendercontext.cpp
+++ b/rotord/rendercontext.cpp
@@ -269,190 +269,54 @@ Command_response Render_context::session_command(const std::vector<std::string>&
 	}
 	return response;
 }
-/*
 
-//http://blog.tomaka17.com/2012/03/libavcodeclibavformat-tutorial/
-//great to use c++11 features
-bool Render_context::load_audio(const string &filename,vector<Base_audio_processor*> processors){
-    
-    audioloader.setup(filename);
-
-    av_dump_format(audioloader.formatContext, 0, 0, false); //avformat.h line 1256
-	int samples = ((audioloader.formatContext->duration + 5000)*audioloader.codecContext->sample_rate)/AV_TIME_BASE;
-	graph.duration=((float)audioloader.formatContext->duration)/AV_TIME_BASE;
-
-
-    for (auto p: processors) {
-		if(!p->init(audioloader.codecContext->channels,audioloader.codecContext->bits_per_raw_sample,samples,audioloader.codecContext->sample_rate) ){
-			cerr<<"Plugin failed to initialse"<<endl;
-			return false;
-		}
-	}
 
-    return true;
-}
-*/
 bool Render_context::load_audio(const string &filename,vector<Base_audio_processor*> processors){
+	
+	cerr<<"Rotor: starting audio analysis"<<endl;
+	
+	libav::audioloader loader;
+	loader.setup(filename);
 
-	av_register_all();
-
-	AVFrame* frame = avcodec_alloc_frame();
-	if (!frame)
-	{
-		std::cout << "Error allocating the frame" << std::endl;
-		return false;
-	}
-
-	AVFormatContext* formatContext = NULL;
-	if (avformat_open_input(&formatContext, filename.c_str(), NULL, NULL) != 0)
-	{
-		av_free(frame);
-		std::cout << "Error opening the file" << std::endl;
-		return false;
-	}
-
-
-	if (avformat_find_stream_info(formatContext, NULL) < 0)
-	{
-		av_free(frame);
-		avformat_close_input(&formatContext);
-		std::cout << "Error finding the stream info" << std::endl;
-		return false;
-	}
+	graph.duration=((float)loader.formatContext->duration)/AV_TIME_BASE;
 
-	AVStream* audioStream = NULL;
-	for (unsigned int i = 0; i < formatContext->nb_streams; ++i)
-	{
-		if (formatContext->streams[i]->codec->codec_type == AVMEDIA_TYPE_AUDIO)
-		{
-			audioStream = formatContext->streams[i];
-			break;
-		}
-	}
-
-	if (audioStream == NULL)
-	{
-		av_free(frame);
-		avformat_close_input(&formatContext);
-		std::cout << "Could not find any audio stream in the file" << std::endl;
-		return false;
-	}
-
-	AVCodecContext* codecContext = audioStream->codec;
-
-	codecContext->codec = avcodec_find_decoder(codecContext->codec_id);
-	if (codecContext->codec == NULL)
-	{
-		av_free(frame);
-		avformat_close_input(&formatContext);
-		std::cout << "Couldn't find a proper decoder" << std::endl;
-		return false;
-	}
-	else if (avcodec_open2(codecContext, codecContext->codec, NULL) != 0)
-	{
-		av_free(frame);
-		avformat_close_input(&formatContext);
-		std::cout << "Couldn't open the context with the decoder" << std::endl;
-		return false;
-	}
-
-	av_dump_format(formatContext, 0, 0, false); //avformat.h line 1256
-	int samples = ((formatContext->duration + 5000)*codecContext->sample_rate)/AV_TIME_BASE;
-	graph.duration=((float)formatContext->duration)/AV_TIME_BASE;
-
-	std::cout << "This stream has " << codecContext->channels << " channels, a sample rate of " << codecContext->sample_rate << "Hz and "<<samples <<" samples" << std::endl;
-	std::cout << "The data is in format " <<codecContext->sample_fmt<< " (aka "<< av_get_sample_fmt_name(codecContext->sample_fmt) << ")"<<std::endl;
-	//std::cout << "Decoding to format " <<frame->format<< " at "<<frame->sample_rate<<" Hz"<<std::endl;
-
-	//frame->sample_rate=codecContext->sample_rate;
+    int rate = loader.codecContext->sample_rate;
+	int samples = ((loader.formatContext->duration + 5000)*rate)/AV_TIME_BASE; //why 5000 more?
+	int channels= loader.codecContext->channels;
+	int bits = loader.codecContext->bits_per_raw_sample;
 
 	for (auto p: processors) {
-		if(!p->init(codecContext->channels,16,samples,codecContext->sample_rate) ){
+		if(!p->init(channels,bits,samples,rate) ){
 			cerr<<"Plugin failed to initialse"<<endl;
 			return false;
 		}
 	}
 
-	AVPacket packet;
-	av_init_packet(&packet);
+	AVFrame* frame=loader.get_frame();
 	int sample_processed=0;
 
-	while (true)
+	while (frame)
 	{
-		int ret=av_read_frame(formatContext, &packet);
-		if (ret<0) {
-			cerr << "finished with code "<<ret <<(ret==AVERROR_EOF?" ,EOF":"")<<endl;
-			break;
+		//now we can pass the data to the processor(s)
+		for (auto p: processors) {
+			p->process_frame(frame->data[0],frame->nb_samples);
 		}
-		if (packet.stream_index == audioStream->index)
-		{
-			// Try to decode the packet into a frame
-			int frameFinished = 0;
-			//int bytes =
-			avcodec_decode_audio4(codecContext, frame, &frameFinished, &packet);
-
-			// Some frames rely on multiple packets, so we have to make sure the frame is finished before
-			// we can use it
-			if (frameFinished)
-			{
-				// frame now has usable audio data in it. How it's stored in the frame depends on the format of
-				// the audio. If it's packed audio, all the data will be in frame->data[0]. If it's in planar format,
-				// the data will be in frame->data and possibly frame->extended_data. Look at frame->data, frame->nb_samples,
-				// frame->linesize, and other related fields on the FFmpeg docs. I don't know how you're actually using
-				// the audio data, so I won't add any junk here that might confuse you. Typically, if I want to find
-				// documentation on an FFmpeg structure or function, I just type "<name> doxygen" into google (like
-				// "AVFrame doxygen" for AVFrame's docs)
-
-				//av_get_channel_layout_string (char *buf, int buf_size, int nb_channels, uint64_t channel_layout)
+		sample_processed+=frame->nb_samples;
+		//mutex.lock();
+		progress=((float)sample_processed)/samples;
+		//mutex.unlock();
 
-
-				//now we can pass the data to the processor(s)
-				for (auto p: processors) {
-					p->process_frame(frame->data[0],frame->nb_samples);
-				}
-				sample_processed+=frame->nb_samples;
-				//mutex.lock();
-				progress=((float)sample_processed)/samples;
-				//mutex.unlock();
-			}
-		}
-		// You *must* call av_free_packet() after each call to av_read_frame() or else you'll leak memory
-		av_free_packet(&packet);
+		frame=loader.get_frame();
 	}
 
-	// Some codecs will cause frames to be buffered up in the decoding process. If the CODEC_CAP_DELAY flag
-	// is set, there can be buffered up frames that need to be flushed, so we'll do that
-	if (codecContext->codec->capabilities & CODEC_CAP_DELAY)
-	{
-		av_init_packet(&packet);
-		// Decode all the remaining frames in the buffer, until the end is reached
-		int frameFinished = 0;
-		int bytes = avcodec_decode_audio4(codecContext, frame, &frameFinished, &packet);
-		while (bytes >= 0 && frameFinished)
-		{
-			for (auto p: processors) {
-				p->process_frame(frame->data[0],frame->nb_samples);
-			}
-			//mutex.lock();
-			progress=((double)sample_processed)/samples;
-			//mutex.unlock();
-		}
-	}
-
-	cerr << "finished processing: "<<sample_processed << " samples of  "<<samples<<", "<<((double)sample_processed*100)/samples<<"%"<<  std::endl;
+	loader.close();
 
-	// Clean up!
 	for (auto p: processors) {
 		p->cleanup();
 		p->print_summary();
 	}
 
-
-	av_free(frame);
-	avcodec_close(codecContext);
-	avformat_close_input(&formatContext);
-
-	return true;
+	cerr<<"Rotor: finished audio analysis"<<endl;
 }
 bool Render_context::load_video(const string &nodeID,const string &filename){
 	//this is a good standard example of how to find