C++ 读取 WAV 文件的数据部分

Question

I plan to create a program that will visualize the audio waveform of a .wav file.

So far, I have started by properly reading the header part of the said wav file. The code I use would be this:

#include <iostream>
#include <string>
#include <fstream>

using namespace std;
using std::string;
using std::fstream;

typedef struct  WAV_HEADER{
    char                RIFF[4];        // RIFF Header      Magic header
    unsigned long       ChunkSize;      // RIFF Chunk Size  
    char                WAVE[4];        // WAVE Header      
    char                fmt[4];         // FMT header       
    unsigned long       Subchunk1Size;  // Size of the fmt chunk                                
    unsigned short      AudioFormat;    // Audio format 1=PCM,6=mulaw,7=alaw, 257=IBM Mu-Law, 258=IBM A-Law, 259=ADPCM 
    unsigned short      NumOfChan;      // Number of channels 1=Mono 2=Sterio                   
    unsigned long       SamplesPerSec;  // Sampling Frequency in Hz                             
    unsigned long       bytesPerSec;    // bytes per second 
    unsigned short      blockAlign;     // 2=16-bit mono, 4=16-bit stereo 
    unsigned short      bitsPerSample;  // Number of bits per sample      
    char                Subchunk2ID[4]; // "data"  string   
    unsigned long       Subchunk2Size;  // Sampled data length    

}wav_hdr; 

// Function prototypes 
int getFileSize(FILE *inFile); 

int main(int argc,char *argv[]){
    wav_hdr wavHeader;
    FILE *wavFile;
    int headerSize = sizeof(wav_hdr),filelength = 0;

    string answer;

    do{
        string input;
        string answer;

        const char* filePath;

        cout << "Pick wav file from the Windows Media File: ";
        cin >> input;
        cin.get();

        cout << endl;

        path = "C:\\Windows\\Media\\" + input + ".wav";
        filePath = path.c_str();

        wavFile = fopen( filePath , "r" );

        if(wavFile == NULL){
            printf("Can not able to open wave file\n");
            //exit(EXIT_FAILURE);
        }

        fread(&wavHeader,headerSize,1,wavFile);
        filelength = getFileSize(wavFile);
        fclose(wavFile);

        cout << "File is                    :" << filelength << " bytes." << endl;

        cout << "RIFF header                :" << wavHeader.RIFF[0] 
                                                << wavHeader.RIFF[1] 
                                                << wavHeader.RIFF[2] 
                                                << wavHeader.RIFF[3] << endl;

        cout << "WAVE header                :" << wavHeader.WAVE[0] 
                                                << wavHeader.WAVE[1] 
                                                << wavHeader.WAVE[2] 
                                                << wavHeader.WAVE[3] 
                                                << endl;

        cout << "FMT                        :" << wavHeader.fmt[0] 
                                                << wavHeader.fmt[1] 
                                                << wavHeader.fmt[2] 
                                                << wavHeader.fmt[3] 
                                                << endl;

        cout << "Data size                  :" << wavHeader.ChunkSize << endl;

        // Display the sampling Rate form the header
        cout << "Sampling Rate              :" << wavHeader.SamplesPerSec << endl;
        cout << "Number of bits used        :" << wavHeader.bitsPerSample << endl;
        cout << "Number of channels         :" << wavHeader.NumOfChan << endl;
        cout << "Number of bytes per second :" << wavHeader.bytesPerSec << endl;
        cout << "Data length                :" << wavHeader.Subchunk2Size << endl;
        cout << "Audio Format               :" << wavHeader.AudioFormat << endl;
        // Audio format 1=PCM,6=mulaw,7=alaw, 257=IBM Mu-Law, 258=IBM A-Law, 259=ADPCM 


        cout << "Block align                :" << wavHeader.blockAlign << endl;

        cout << "Data string                :" << wavHeader.Subchunk2ID[0] 
                                                << wavHeader.Subchunk2ID[1]
                                                << wavHeader.Subchunk2ID[2] 
                                                << wavHeader.Subchunk2ID[3] 
                                                << endl;

        cout << endl << endl << "Try something else? (y/n)";
        cin >> answer;
        //cin.get();
        cout << endl << endl;

    }while( answer == "y" );


    getchar();
    return 0;
} 
// find the file size 
int getFileSize(FILE *inFile){
    int fileSize = 0;
    fseek(inFile,0,SEEK_END);

    fileSize=ftell(inFile);

    fseek(inFile,0,SEEK_SET);
    return fileSize;
}

I've tried it several times and the data it gives seems consistent through different wav files in the Media folder in the Windows folder.

The next step then would be storing the actual data of the wav file in a vector. However, I'm quite clueless on how to do this. Online solutions that I found only went as far as reading the header file.

Any ideas on how to store (and hopefully display) the actual data of the wav file? Thanks!

Answer 1

This image is taken from a Stanford course

So you can see that the audio data occurs immediately after the headers you already read and there will be Subchunk2Size bytes of audio data.

The pseudocode for this would be

ReadRIFF();
ReadFMT();
int32 chunk2Id = Read32(BigEndian);
int32 chunk2Size = Read32(LittleEndian);
for (int i = 0; i < chunk2Size; i++)
{
    audioData[i] = ReadByte();
}

If the audio is stereo you'll have two audio streams in data . If the audio is compressed (mp3, aac, etc) you'll have to decompress it first.

Answer 2

I know this is an old post, but your fread parameters are switched, here is a more correct version (requires g++-4.7 or higher with -std=c++11 flag like this "g++ -std=c++11 WaveReader.cpp -o WaveReader").

#include <iostream>
#include <string>
#include <fstream>
#include <cstdint>

using std::cin;
using std::cout;
using std::endl;
using std::fstream;
using std::string;

typedef struct  WAV_HEADER
{
    /* RIFF Chunk Descriptor */
    uint8_t         RIFF[4];        // RIFF Header Magic header
    uint32_t        ChunkSize;      // RIFF Chunk Size
    uint8_t         WAVE[4];        // WAVE Header
    /* "fmt" sub-chunk */
    uint8_t         fmt[4];         // FMT header
    uint32_t        Subchunk1Size;  // Size of the fmt chunk
    uint16_t        AudioFormat;    // Audio format 1=PCM,6=mulaw,7=alaw,     257=IBM Mu-Law, 258=IBM A-Law, 259=ADPCM
    uint16_t        NumOfChan;      // Number of channels 1=Mono 2=Sterio
    uint32_t        SamplesPerSec;  // Sampling Frequency in Hz
    uint32_t        bytesPerSec;    // bytes per second
    uint16_t        blockAlign;     // 2=16-bit mono, 4=16-bit stereo
    uint16_t        bitsPerSample;  // Number of bits per sample
    /* "data" sub-chunk */
    uint8_t         Subchunk2ID[4]; // "data"  string
    uint32_t        Subchunk2Size;  // Sampled data length
} wav_hdr;

// Function prototypes
int getFileSize(FILE* inFile);

int main(int argc, char* argv[])
{
    wav_hdr wavHeader;
    int headerSize = sizeof(wav_hdr), filelength = 0;

    const char* filePath;
    string input;
    if (argc <= 1)
    {
        cout << "Input wave file name: ";
        cin >> input;
        cin.get();
        filePath = input.c_str();
    }
    else
    {
        filePath = argv[1];
        cout << "Input wave file name: " << filePath << endl;
    }

    FILE* wavFile = fopen(filePath, "r");
    if (wavFile == nullptr)
    {
        fprintf(stderr, "Unable to open wave file: %s\n", filePath);
        return 1;
    }

    //Read the header
    size_t bytesRead = fread(&wavHeader, 1, headerSize, wavFile);
    cout << "Header Read " << bytesRead << " bytes." << endl;
    if (bytesRead > 0)
    {
        //Read the data
        uint16_t bytesPerSample = wavHeader.bitsPerSample / 8;      //Number     of bytes per sample
        uint64_t numSamples = wavHeader.ChunkSize / bytesPerSample; //How many samples are in the wav file?
        static const uint16_t BUFFER_SIZE = 4096;
        int8_t* buffer = new int8_t[BUFFER_SIZE];
        while ((bytesRead = fread(buffer, sizeof buffer[0], BUFFER_SIZE / (sizeof buffer[0]), wavFile)) > 0)
        {
            /** DO SOMETHING WITH THE WAVE DATA HERE **/
            cout << "Read " << bytesRead << " bytes." << endl;
        }
        delete [] buffer;
        buffer = nullptr;
        filelength = getFileSize(wavFile);

        cout << "File is                    :" << filelength << " bytes." << endl;
        cout << "RIFF header                :" << wavHeader.RIFF[0] << wavHeader.RIFF[1] << wavHeader.RIFF[2] << wavHeader.RIFF[3] << endl;
        cout << "WAVE header                :" << wavHeader.WAVE[0] << wavHeader.WAVE[1] << wavHeader.WAVE[2] << wavHeader.WAVE[3] << endl;
        cout << "FMT                        :" << wavHeader.fmt[0] << wavHeader.fmt[1] << wavHeader.fmt[2] << wavHeader.fmt[3] << endl;
        cout << "Data size                  :" << wavHeader.ChunkSize << endl;

        // Display the sampling Rate from the header
        cout << "Sampling Rate              :" << wavHeader.SamplesPerSec << endl;
        cout << "Number of bits used        :" << wavHeader.bitsPerSample << endl;
        cout << "Number of channels         :" << wavHeader.NumOfChan << endl;
        cout << "Number of bytes per second :" << wavHeader.bytesPerSec << endl;
        cout << "Data length                :" << wavHeader.Subchunk2Size << endl;
        cout << "Audio Format               :" << wavHeader.AudioFormat << endl;
        // Audio format 1=PCM,6=mulaw,7=alaw, 257=IBM Mu-Law, 258=IBM A-Law, 259=ADPCM

        cout << "Block align                :" << wavHeader.blockAlign << endl;
        cout << "Data string                :" << wavHeader.Subchunk2ID[0] << wavHeader.Subchunk2ID[1] << wavHeader.Subchunk2ID[2] << wavHeader.Subchunk2ID[3] << endl;
    }
    fclose(wavFile);
    return 0;
}

// find the file size
int getFileSize(FILE* inFile)
{
    int fileSize = 0;
    fseek(inFile, 0, SEEK_END);

    fileSize = ftell(inFile);

    fseek(inFile, 0, SEEK_SET);
    return fileSize;
}