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
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
|
extern "C" {
#include "libavcodec/avcodec.h"
#include "libavformat/avformat.h"
#include "libavutil/opt.h"
#include "libavutil/channel_layout.h"
#include "libavutil/common.h"
#include "libavutil/imgutils.h"
#include "libavutil/mathematics.h"
#include "libavutil/samplefmt.h"
#include <libavutil/imgutils.h>
#include <libavutil/samplefmt.h>
//#include <libavutil/timestamp.h>
}
#include <libavutil/imgutils.h>
#include <libavutil/samplefmt.h>
#include <iostream>
#include <fstream>
int main(int argc, char** argv)
{
av_register_all();
if (argc<1) {
cerr<< "use: test audiofile" << endl;
return 1;
}
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);
av_close_input_file(formatContext);
std::cout << "Error finding the stream info" << std::endl;
return false;
}
AVStream* audioStream = NULL;
// Find the audio stream (some container files can have multiple streams in them)
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);
av_close_input_file(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);
av_close_input_file(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);
av_close_input_file(formatContext);
std::cout << "Couldn't open the context with the decoder" << std::endl;
return false;
}
/*
//
// why is the file truncated???
//if(codecContext->codec->capabilities & CODEC_CAP_TRUNCATED) codecContext->codec->capabilities|=CODEC_FLAG_TRUNCATED;
//
//
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;
//we can now tell the processors the format
//we can work out the number of samples at this point
for (auto p: processors) {
p->init(codecContext->channels,16,samples);
}
AVPacket packet;
av_init_packet(&packet);
int sample_processed=0;
bool diag=true;
// Read the packets in a loop
while (true)
//while(sample_processed<samples)
{
int ret=av_read_frame(formatContext, &packet);
if (ret<0) {
cerr << "finished with code "<<ret <<(ret==AVERROR_EOF?" ,EOF":"")<<endl;
break;
}
//av_read_frame(formatContext, &packet); //hangs once the packets have been read
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)
if (diag) {
cerr << "first frame: "<<bytes << ", "<<frame->nb_samples<<" samples in "<<av_get_sample_fmt_name(frame->format)<<" format with channel layout "<<frame->channel_layout<< std::endl;
diag=false;
}
//std::cout << "Got a frame: bytes " << bytes << ", "<<frame->nb_samples<<" samples"<<std::endl;
//now we can pass the data to the processor(s)
for (auto p: processors) {
sample_processed=p->process_frame(frame->data[0],frame->nb_samples);
}
mutex.lock();
progress=((double)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); //crashes here!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! SIGSEV In _int_free (av=0xb4600010, p=0xb46025c8, have_lock=0) at malloc.c:4085 ()
}
// 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 processed: "<<sample_processed << " samples of "<<samples<<" , "<<((double)sample_processed*100)/samples<<"%"<< std::endl;
*/
// Clean up!
av_free(frame);
avcodec_close(codecContext);
av_close_input_file(formatContext);
return 0;
}
|
