diff --git a/.gitignore b/.gitignore
index bfd5ee2507a88b5ff0c4b8c185ab39d056e9f0bb..acf09d2b0104c7981c29d4b4fc7e0eb5b20348c4 100644
--- a/.gitignore
+++ b/.gitignore
@@ -7,3 +7,4 @@ cmake_install.cmake
.cache/*
Debug/*
compile_commands.json
+build/*
diff --git a/CMakeLists.txt b/CMakeLists.txt
index 0f11058346d8fdc2b869223465711b16b5258f79..3f1f09b48d35ce63ed520cc461be4accd6ee1c76 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -24,8 +24,16 @@ set(CMAKE_CXX_STANDARD_REQUIRED ON)
# endif()
#endif()
+set(THREADS_PREFER_PTHREAD_FLAG ON)
+
find_package(QT NAMES Qt6 Qt5 COMPONENTS Widgets REQUIRED)
find_package(Qt${QT_VERSION_MAJOR} COMPONENTS Widgets REQUIRED)
+find_package(Threads REQUIRED)
+find_package(X11 REQUIRED)
+find_library(AVCODEC_LIBRARY avcodec)
+find_library(AVUTIL_LIBRARY avutil)
+find_library(SWRESAMPLE_LIBRARY swresample)
+find_library(AVFORMAT_LIBRARY avformat)
set(PROJECT_SOURCES
main.cpp
@@ -51,6 +59,12 @@ else()
endif()
target_link_libraries(Violet PRIVATE Qt${QT_VERSION_MAJOR}::Widgets)
+target_link_libraries(Violet PRIVATE Threads::Threads)
+target_link_libraries(Violet PRIVATE ${X11_LIBRARIES})
+target_link_libraries(Violet PRIVATE ${AVCODEC_LIBRARY})
+target_link_libraries(Violet PRIVATE ${AVUTIL_LIBRARY})
+target_link_libraries(Violet PRIVATE ${SWRESAMPLE_LIBRARY})
+target_link_libraries(Violet PRIVATE ${AVFORMAT_LIBRARY})
set_target_properties(Violet PROPERTIES
MACOSX_BUNDLE_GUI_IDENTIFIER my.example.com
diff --git a/mainwindow.cpp b/mainwindow.cpp
index 6fdfb0fa2cfee732776ac651bef9441d3446ff24..067fadfe18d3e25bcee4c597dffec7798b5cfad9 100644
--- a/mainwindow.cpp
+++ b/mainwindow.cpp
@@ -2,26 +2,15 @@
#include <iostream>
#include <string.h>
#include <stdio.h>
+#include <CImg.h>
-typedef struct WAV_HEADER {
- uint8_t RIFF[4]; // RIFF Header Magic header
- uint32_t chunkSize; // RIFF Chunk Size
- uint8_t FORMAT[4]; // WAVE Header
-} wav_header;
-
-typedef struct FTM_CHUNK_DATA {
- uint16_t audioFormat; // Audio format
- uint16_t numOfChan; // Number of channels
- uint32_t sampleRate; // Sampling Frequency in Hz
- uint32_t byteRate; // bytes per second
- uint16_t blockAlign; // 2=16-bit mono, 4=16-bit stereo
- uint16_t bitsPerSample; // Number of bits per sample
-} wav_fmt_chunk_data;
-
-typedef struct DATA_CHUNK_PARAM {
- uint32_t chunkID; // "data" string
- uint32_t chunkSize; // Sampled data length
-} data_chunk_param;
+extern "C" {
+#include <libavutil/opt.h>
+#include <libavcodec/avcodec.h>
+#include <libavformat/avformat.h>
+#include <libswresample/swresample.h>
+#include <libavcodec/avfft.h>
+}
MainWindow::MainWindow(QWidget *parent)
: QMainWindow(parent)
@@ -45,31 +34,171 @@ MainWindow::~MainWindow()
{
}
+int decode_audio_file(const char* path, const int sample_rate, double** data, int* size) {
+
+ // initialize all muxers, demuxers and protocols for libavformat
+ // (does nothing if called twice during the course of one program execution)
+ av_register_all();
+
+ // get format from audio file
+ AVFormatContext* format = avformat_alloc_context();
+ if (avformat_open_input(&format, path, NULL, NULL) != 0) {
+ fprintf(stderr, "Could not open file '%s'\n", path);
+ return -1;
+ }
+ if (avformat_find_stream_info(format, NULL) < 0) {
+ fprintf(stderr, "Could not retrieve stream info from file '%s'\n", path);
+ return -1;
+ }
+
+ // Find the index of the first audio stream
+ int stream_index =- 1;
+ for (int i=0; i<format->nb_streams; i++) {
+ if (format->streams[i]->codec->codec_type == AVMEDIA_TYPE_AUDIO) {
+ stream_index = i;
+ break;
+ }
+ }
+ if (stream_index == -1) {
+ fprintf(stderr, "Could not retrieve audio stream from file '%s'\n", path);
+ return -1;
+ }
+ AVStream* stream = format->streams[stream_index];
+
+ // find & open codec
+ AVCodecContext* codec = stream->codec;
+ if (avcodec_open2(codec, avcodec_find_decoder(codec->codec_id), NULL) < 0) {
+ fprintf(stderr, "Failed to open decoder for stream #%u in file '%s'\n", stream_index, path);
+ return -1;
+ }
+
+ // prepare resampler
+ struct SwrContext* swr = swr_alloc();
+ av_opt_set_int(swr, "in_channel_count", codec->channels, 0);
+ av_opt_set_int(swr, "out_channel_count", 1, 0);
+ av_opt_set_int(swr, "in_channel_layout", codec->channel_layout, 0);
+ av_opt_set_int(swr, "out_channel_layout", AV_CH_LAYOUT_MONO, 0);
+ av_opt_set_int(swr, "in_sample_rate", codec->sample_rate, 0);
+ av_opt_set_int(swr, "out_sample_rate", sample_rate, 0);
+ av_opt_set_sample_fmt(swr, "in_sample_fmt", codec->sample_fmt, 0);
+ av_opt_set_sample_fmt(swr, "out_sample_fmt", AV_SAMPLE_FMT_DBL, 0);
+ swr_init(swr);
+ if (!swr_is_initialized(swr)) {
+ fprintf(stderr, "Resampler has not been properly initialized\n");
+ return -1;
+ }
+
+ // prepare to read data
+ AVPacket packet;
+ av_init_packet(&packet);
+ AVFrame* frame = av_frame_alloc();
+ if (!frame) {
+ fprintf(stderr, "Error allocating the frame\n");
+ return -1;
+ }
+
+ // iterate through frames
+ *data = NULL;
+ *size = 0;
+ while (av_read_frame(format, &packet) >= 0) {
+ // decode one frame
+ int gotFrame;
+ if (avcodec_decode_audio4(codec, frame, &gotFrame, &packet) < 0) {
+ break;
+ }
+ if (!gotFrame) {
+ continue;
+ }
+ // resample frames
+ double* buffer;
+ av_samples_alloc((uint8_t**) &buffer, NULL, 1, frame->nb_samples, AV_SAMPLE_FMT_DBL, 0);
+ int frame_count = swr_convert(swr, (uint8_t**) &buffer, frame->nb_samples, (const uint8_t**) frame->data, frame->nb_samples);
+ // append resampled frames to data
+ *data = (double*) realloc(*data, (*size + frame->nb_samples) * sizeof(double));
+ memcpy(*data + *size, buffer, frame_count * sizeof(double));
+ *size += frame_count;
+ }
+
+ // clean up
+ av_frame_free(&frame);
+ swr_free(&swr);
+ avcodec_close(codec);
+ avformat_free_context(format);
+
+ // success
+ return 0;
+}
+
+#define MAXPIXVALUE 12000
void MainWindow::openAudioFile(){
- QString filename = QFileDialog::getOpenFileName(this, "Select a file");
- wav_header wavHeader;
- QMessageBox msg;
- data_chunk_param dataChunkParam;
- wav_fmt_chunk_data wavFmtChunkData;
- FILE *wavFile = fopen(filename.toStdString().c_str(), "r");
-
- fread(&wavHeader, 1, sizeof(wav_header), wavFile);
- while (1) {
- fread(&dataChunkParam, 1, sizeof(dataChunkParam), wavFile);
- if (dataChunkParam.chunkID == 0x20746d66)
- break;
- fseek(wavFile, dataChunkParam.chunkSize, SEEK_CUR);
- }
- fread(&wavFmtChunkData, 1, dataChunkParam.chunkSize, wavFile);
- while (1) {
- fread(&dataChunkParam, 1, sizeof(dataChunkParam), wavFile);
- if (dataChunkParam.chunkID == 0x61746164)
- break;
- fseek(wavFile, dataChunkParam.chunkSize, SEEK_CUR);
- }
-
- uint16_t* data = (uint16_t*)malloc(dataChunkParam.chunkSize);
- fread(data, 1, dataChunkParam.chunkSize, wavFile);
-
- fclose(wavFile);
+ QString filename = QFileDialog::getOpenFileName(this, "Select a file");
+ QMessageBox msg;
+ FILE *audioFile = fopen(filename.toStdString().c_str(), "r");
+ fclose(audioFile);
+
+ int sample_rate = 44100;
+ double* data;
+ int size;
+ if (decode_audio_file(filename.toStdString().c_str(), sample_rate, &data, &size) != 0){
+ printf("ERROR\n");
+ return;
+ }
+
+ /*
+ for (int j = size/2; j < size/2 + 20; j++){
+ if (data[j] != 0)
+ fprintf(stderr, "data %d: %f\n", j, data[j]);
+ }
+ */
+
+ int i; // just some iterator indices
+ int chunk_size = 512;
+ int overlap = 128;
+ int decal = chunk_size - overlap;
+ fprintf(stderr, "size,chunk_size,overlap,decal: %d,%d,%d,%d\n", size, chunk_size, overlap, decal);
+
+ FFTSample* chunk_data = (FFTSample*)av_malloc_array(2*chunk_size, sizeof(FFTSample));
+ RDFTContext* ctx = av_rdft_init((int) log2(chunk_size), DFT_R2C);
+ int x = 0;
+
+ int width = (size - chunk_size) / decal;
+ int height = chunk_size;
+ int16_t* pixs = (int16_t*)malloc(sizeof(int16_t) * width * height / 2);
+
+ for (i = 0; i < size - chunk_size; i+= decal) {
+ for (int j = 0; j < chunk_size; j++){
+ float curr_dat = data[i+j];
+ double window_modifier = (0.5 * (1 - cos(2 * M_PI * j / (chunk_size - 1)))); // Hann (Hanning) window function
+ //float value = (float) (window_modifier * ((curr_dat) / 32768.0f)); // Convert to float and apply
+ float value = (float) (window_modifier * curr_dat); // Convert to float and apply
+
+ // cap values above 1 and below -1
+ if (value > 1.0) {
+ value = 1;
+ } else if (value < -1.0) {
+ value = -1;
+ }
+ chunk_data[j] = value;
+ }
+
+ av_rdft_calc(ctx, chunk_data);
+
+ for (int j = 0; j < chunk_size / 2; j++){
+ float im = chunk_data[j*2];
+ float re = chunk_data[j*2 + 1];
+ double mag = sqrt(im * im + re * re);
+ /*
+ if ( i == 100*decal && j < 10 )
+ fprintf(stderr, "im,re,mag: %f,%f,%f\n", im, re, mag);
+ */
+ pixs[j*width+x] = (int16_t) (mag) * MAXPIXVALUE;
+ }
+ x++;
+ }
+
+ cimg_library::CImg<int16_t> img(pixs, width, height / 2);
+ img.mirror("y").save_png("out.png");
+
+ av_rdft_end(ctx);
+ av_free(data);
}