1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
|
#include "libavaudioloader.h"
bool libav::Audioloader::setup(const std::string &filename){
av_register_all();
frame = avcodec_alloc_frame();
if (!frame)
{
std::cout << "Error allocating the frame" << std::endl;
return false;
}
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;
}
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;
}
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;
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;
av_init_packet(&packet);
//sample_processed=0;
ready=true;
return true;
}
AVFrame* libav::Audioloader::get_frame() {
if (!ready) return nullptr;
int frameFinished = 0;
while (!frameFinished) {
int ret=av_read_frame(formatContext, &packet);
if (ret<0) {
std::cerr << "finished with code "<<ret <<(ret==AVERROR_EOF?" ,EOF":"")<<std::endl;
ready=false;
return nullptr;
}
if (packet.stream_index == audioStream->index)
{
//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
}
// You *must* call av_free_packet() after each call to av_read_frame() or else you'll leak memory
av_free_packet(&packet);
}
return 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;
*/
uint16_t* libav::Audioloader::get_samples(int num){ //presumes 16bpc here
//std::cerr << "request "<<num<<" samples: "<<(ready?"ready":"not ready")<<std::endl;
if(!ready) return nullptr;
//shuffle down samples
if (sample_start>0){
for (int i=0;i<sample_end-sample_start;i++){
for (int j=0;j<frame->channels;j++) {
buffer[(i*frame->channels)+j]=buffer[((sample_start+i)*frame->channels)+j];
}
}
sample_start=sample_end-sample_start;
}
sample_end=sample_start;
while (sample_end<num) {
frame=get_frame();
if (((sample_end+frame->nb_samples)*frame->channels)>buffer.size()){
buffer.reserve((sample_end+frame->nb_samples)*frame->channels);
}
if (!frame) {
for (int i=0;i<num*frame->channels;i++){
buffer[sample_end+i]=0;
}
}
for (int i=0;i<frame->nb_samples;i++) {
for (int j=0;j<frame->channels;j++) {
buffer[((sample_end+i)*frame->channels)+j]= ((uint16_t*) frame->buf[0])[(i*frame->channels)+j];
}
}
sample_end+=frame->nb_samples;
//avcodec_free_frame(&frame);
}
if (sample_end>num) {
sample_start=num;
}
else {
sample_start=0;
}
return (uint16_t*)(&buffer[0]);
}
bool libav::Audioloader::close() {
av_free(frame);
avcodec_close(codecContext);
avformat_close_input(&formatContext);
return true;
}
|
