Develop Reference

What am I doing wrong when parsing a wav file?

I'm trying to parse a wav file. I'm not sure if there can be multiple data chunks in a wav file, but I originally assumed there was only 1 since the wav file format description I was reading only mentioned there being 1.
But I noticed that the subchunk2size was very small (like 26) when the wav file being parsed was something like 36MB and the sample rate was 44100.
So I tried to parse it assuming there were multiple chunks, but after the 1st chunk, there was no subchunk2id to be found.
To go chunk by chunk, I was using the below code
int chunkSize = System.BitConverter.ToInt32(strm, 40);
int widx = 44; //wav data starts at the 44th byte
//strm is a byte array of the wav file
while(widx < strm.Length)
{
widx += chunkSize;
if(widx < 1000)
{
//log "data" or "100 97 116 97" for the subchunkid
//This is only getting printed the 1st time though. All prints after that are garbage
Debug.Log( strm[widx] + " " + strm[widx+1] + " " + strm[widx+2] + " " + strm[widx+3]);
}
if(widx + 8 < strm.Length)
{
widx += 4;
chunkSize = System.BitConverter.ToInt32(strm, widx);
widx += 4;
}else
{
widx += 8;
}
}

A .wav-File has 3 chunks:
Each chunk has a size of 4 Byte
The first chunk is the "RIFF"-chunk. It includes 8 Byte the filesize(4 Byte) and the name of the format(4byte, usually "WAVE").
The next chunk is the "fmt "-chunk (the space in the chunk-name is important). It includes the audio-format(2 Byte), the number of channels (2 Byte), the sample rate (4 Byte), the byte rate (4 Byte), blockalign (2 Byte) and the bits per sample (2 Byte).
The third and last chunk is the data-chunk. Here are the real data and the amplitudes of the samples. It includes 4 Byte for the datasize, which is the number of bytes for the data.
You can find further explanations of the properties of a .wav-file here.
From this knowledge I have already created the following class:
public sealed class WaveFile
{
//privates
private int fileSize;
private string format;
private int fmtChunkSize;
private int audioFormat;
private int numChannels;
private int sampleRate;
private int byteRate;
private int blockAlign;
private int bitsPerSample;
private int dataSize;
private int[][] data;//One array per channel
//publics
public int FileSize => fileSize;
public string Format => format;
public int FmtChunkSize => fmtChunkSize;
public int AudioFormat => audioFormat;
public int NumChannels => numChannels;
public int SampleRate => sampleRate;
public int ByteRate => byteRate;
public int BitsPerSample => bitsPerSample;
public int DataSize => dataSize;
public int[][] Data => data;
public WaveFile(string path)
{
FileStream fs = File.OpenRead(path);
LoadChunk(fs); //read RIFF Chunk
LoadChunk(fs); //read fmt Chunk
LoadChunk(fs); //read data Chunk
fs.Close();
}
private void LoadChunk(FileStream fs)
{
ASCIIEncoding Encoder = new ASCIIEncoding();
byte[] bChunkID = new byte[4];
fs.Read(bChunkID, 0, 4);
string sChunkID = Encoder.GetString(bChunkID);
byte[] ChunkSize = new byte[4];
fs.Read(ChunkSize, 0, 4);
if (sChunkID.Equals("RIFF"))
{
fileSize = BitConverter.ToInt32(ChunkSize, 0);
byte[] Format = new byte[4];
fs.Read(Format, 0, 4);
this.format = Encoder.GetString(Format);
}
if (sChunkID.Equals("fmt "))
{
fmtChunkSize = BitConverter.ToInt32(ChunkSize, 0);
byte[] audioFormat = new byte[2];
fs.Read(audioFormat, 0, 2);
this.audioFormat = BitConverter.ToInt16(audioFormat, 0);
byte[] numChannels = new byte[2];
fs.Read(numChannels, 0, 2);
this.numChannels = BitConverter.ToInt16(numChannels, 0);
byte[] sampleRate = new byte[4];
fs.Read(sampleRate, 0, 4);
this.sampleRate = BitConverter.ToInt32(sampleRate, 0);
byte[] byteRate = new byte[4];
fs.Read(byteRate, 0, 4);
this.byteRate = BitConverter.ToInt32(byteRate, 0);
byte[] blockAlign = new byte[2];
fs.Read(blockAlign, 0, 2);
this.blockAlign = BitConverter.ToInt16(blockAlign, 0);
byte[] bitsPerSample = new byte[2];
fs.Read(bitsPerSample, 0, 2);
this.bitsPerSample = BitConverter.ToInt16(bitsPerSample, 0);
}
if (sChunkID.Equals("data"))
{
dataSize = BitConverter.ToInt32(ChunkSize, 0);
data = new int[this.numChannels][];
byte[] temp = new byte[dataSize];
for (int i = 0; i < this.numChannels; i++)
{
data[i] = new int[this.dataSize / (numChannels * bitsPerSample / 8)];
}
for (int i = 0; i < data[0].Length; i++)
{
for (int j = 0; j < numChannels; j++)
{
if (fs.Read(temp, 0, blockAlign / numChannels) > 0)
{
if (blockAlign / numChannels == 2)
{ data[j][i] = BitConverter.ToInt32(temp, 0); }
else
{ data[j][i] = BitConverter.ToInt16(temp, 0); }
}
}
}
}
}
}
Needed using-directives:
using System;
using System.IO;
using System.Text;
This class reads all chunks byte per byte and sets the properties. You just have to initialize this class and it will return all properties of your selected wave-file.

In the reference you added I dont see any mention of the chunk size being repeated for each data chunk...
Try something like this:
int chunkSize = System.BitConverter.ToInt32(strm, 40);
int widx = 44; //wav data starts at the 44th byte
//strm is a byte array of the wav file
while(widx < strm.Length)
{
if(widx < 1000)
{
//log "data" or "100 97 116 97" for the subchunkid
//This is only getting printed the 1st time though. All prints after that are garbage
Debug.Log( strm[widx] + " " + strm[widx+1] + " " + strm[widx+2] + " " + strm[widx+3]);
}
widx += chunkSize;
}

How have a generic conversion from 32/24bit From Bytes To 16bit To bytes

Have been searching the solution for two days.
I want to convert my wave 32 or 24 bits to a 16bit.
This my code after reading few stackoverflow topics):
byte[] data = Convert.FromBase64String("-- Wav String encoded --") (32 or 24 bits)
int conv = Convert.ToInt16(data);
byte[] intBytes = BitConverter.GetBytes(conv);
if (BitConverter.IsLittleEndian)
Array.Reverse(intBytes);
byte[] result = intBytes;
but when i writeAllbyte my result, nothing to hear...

Here is a method that cuts the least significant bits:
byte[] data = ...
var skipBytes = 0;
byte[] data16bit;
int samples;
if( /* data was 32 bit */ ) {
skipBytes = 2;
samples = data.Length / 4;
} else if( /* data was 24 bit */ ) {
skipBytes = 1;
samples = data.Length / 3;
}
data16bit = new byte[samples * 2];
int writeIndex = 0;
int readIndex = 0;
for(var i = 0; i < samples; ++i) {
readIndex += skipBytes; //skip the least significant bytes
//read the two most significant bytes
data16bit[writeIndex++] = data[readIndex++];
data16bit[writeIndex++] = data[readIndex++];
}
This assumes a little endian byte order (least significant byte is the first byte, usual for WAV RIFF). If you have big endian, you have to put the readIndex += ... after the two read lines.
You could implement your own conversion iterator for this task like so:
IEnumerable<byte> ConvertTo16Bit(byte[] data, int skipBytes)
{
int bytesToRead = 0;
int bytesToSkip = skipBytes;
int readIndex = 0;
while (readIndex < data.Length)
{
if (bytesToSkip > 0)
{
readIndex += bytesToSkip;
bytesToSkip = 0;
bytesToRead = 2;
continue;
}
if (bytesToRead == 0)
{
bytesToSkip = skipBytes;
continue;
}
yield return data[readIndex++];
bytesToRead--;
}
}
This way you don't have to create a new array if there is no need for it. And you could simply convert the data array to a new 16 bit array with the IEnumerable<T> extension methods:
var data16bit = ConvertTo16Bit(data, 1).ToArray();
Or if you don't need the array, you can iterate the data skipping the least significant bytes:
foreach (var b in ConvertTo16Bit(data, 1))
{
Console.WriteLine(b);
}

Fastest way to extract variable width signed integer from byte[]

The title speaks for itself. I have a file containing a base64 encoded byte[] of variable width integer, min 8 bit, max 32bit
I have a large file (48MB) and I am trying to find the fastest way of grabbing integers from the stream.
This is the fastest code from a perf app:
static int[] Base64ToIntArray3(string base64, int size)
{
List<int> res = new List<int>();
byte[] buffer = new byte[4];
using (var ms = new System.IO.MemoryStream(Convert.FromBase64String(base64)))
{
while(ms.Position < ms.Length)
{
ms.Read(buffer, 0, size);
res.Add(BitConverter.ToInt32(buffer, 0));
}
}
return res.ToArray();
}
I can't see a faster way of padding the bytes to 32bit. Any ideas, chaps and chapettes? Solutions should be in c#. I could fall down to C/++ if i must but i don't want to.

There is no reason to use a memory stream to move bytes from an array to another array, just read from the array directly. Also, the size of the array is known, so there is need to add the items to a list that is then converted to an array, you can use an array from the start:
static int[] Base64ToIntArray3(string base64, int size) {
byte[] data = Convert.FromBase64String(base64);
int cnt = data.Length / size;
int[] res = new int[cnt];
for (int i = 0; i < cnt; i++) {
switch (size) {
case 1: res[i] = data[i]; break;
case 2: res[i] = BitConverter.ToInt16(data, i * 2); break;
case 3: res[i] = data[i * 3] + data[i * 3 + 1] * 256 + data[i * 3 + 2] * 65536; break;
case 4: res[i] = BitConverter.ToInt32(data, i * 4); break;
}
}
return res;
}
Note: Untested code! You have to verify that it actually does what it is supposed to do, but at least it shows the principle.

This is probably how I would do it. Not using a stream should increase performance. This seems like the sort of thing that should be easy to do using Linq but I couldn't figure it out.
static int[] Base64ToIntArray3(string base64, int size)
{
if (size < 1 || size > 4) throw new ArgumentOutOfRangeException("size");
byte[] data = Convert.FromBase64String(base64);
List<int> res = new List<int>();
byte[] buffer = new byte[4];
for (int i = 0; i < data.Length; i += size )
{
Buffer.BlockCopy(data, i, buffer, 0, size);
res.Add(BitConverter.ToInt32(buffer, 0));
}
return res.ToArray();
}

Ok so I believe this is the Linq way to do this:
static int[] Base64ToIntArray3(string base64, int size)
{
byte[] data = Convert.FromBase64String(base64);
return data.Select((Value, Index) => new { Value, Index })
.GroupBy(p => p.Index / size)
.Select(g => BitConverter.ToInt32(g.Select(p => p.Value).Union(new byte[4 - size]).ToArray(), 0))
.ToArray();
}

What is the correct way to get a byte array from a FileStream?

The Microsoft website has the code snippet:
using (FileStream fsSource = new FileStream(pathSource,
FileMode.Open, FileAccess.Read))
{
// Read the source file into a byte array.
byte[] bytes = new byte[fsSource.Length];
int numBytesToRead = (int)fsSource.Length;
int numBytesRead = 0;
while (numBytesToRead > 0)
{
// Read may return anything from 0 to numBytesToRead.
int n = fsSource.Read(bytes, numBytesRead, numBytesToRead);
// Break when the end of the file is reached.
if (n == 0)
break;
numBytesRead += n;
numBytesToRead -= n;
}
}
What concerns me is that fsSource.Length is a long, whereas numBytesRead is an int so at most only 2 * int.MaxValue can be read into bytes (the head and the tail of the stream). So my questions are:
Is there some reason that this is OK?
If not, how should you read a FileStream into a byte[].

In this situation I wouldn't even bother processing the FileStream manually; use File.ReadAllBytes instead:
byte[] bytes = File.ReadAllBytes(pathSource);

To answer your question:
The sample code is good for most of applications where we are not reaching extremes.
If you have really long stream like say a video, use BufferedStream. Sample code is available at MSDN site

Example using ReadAllBytes:
private byte[] m_cfgBuffer;
m_cfgBuffer = File.ReadAllBytes(m_FileName);
StringBuilder PartNbr = new StringBuilder();
StringBuilder Version = new StringBuilder();
int i, j;
byte b;
i = 356; // We know that the cfg file header ends at position 356 (1st hex(80))
b = m_cfgBuffer[i];
while (b != 0x80) // Scan for 2nd hex(80)
{
i++;
b = m_cfgBuffer[i];
}
// Now extract the part number - 6 bytes after hex(80)
m_PartNbrPos = i + 5;
for (j = m_PartNbrPos; j < m_PartNbrPos + 6; j++)
{
char cP = (char)m_cfgBuffer[j];
PartNbr.Append(cP);
}
m_PartNbr = PartNbr.ToString();
// Now, extract version number - 6 bytes after part number
m_VersionPos = (m_PartNbrPos + 6) + 6;
for (j = m_VersionPos; j < m_VersionPos + 2; j++)
{
char cP = (char)m_cfgBuffer[j];
Version.Append(cP);
}
m_Version = Version.ToString();

Write bytes to file

I have a hexadecimal string (e.g 0CFE9E69271557822FE715A8B3E564BE) and I want to write it to a file as bytes. For example,
Offset 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
00000000 0C FE 9E 69 27 15 57 82 2F E7 15 A8 B3 E5 64 BE .þži'.W‚/ç.¨³åd¾
How can I accomplish this using .NET and C#?

If I understand you correctly, this should do the trick. You'll need add using System.IO at the top of your file if you don't already have it.
public bool ByteArrayToFile(string fileName, byte[] byteArray)
{
try
{
using (var fs = new FileStream(fileName, FileMode.Create, FileAccess.Write))
{
fs.Write(byteArray, 0, byteArray.Length);
return true;
}
}
catch (Exception ex)
{
Console.WriteLine("Exception caught in process: {0}", ex);
return false;
}
}

The simplest way would be to convert your hexadecimal string to a byte array and use the File.WriteAllBytes method.
Using the StringToByteArray() method from this question, you'd do something like this:
string hexString = "0CFE9E69271557822FE715A8B3E564BE";
File.WriteAllBytes("output.dat", StringToByteArray(hexString));
The StringToByteArray method is included below:
public static byte[] StringToByteArray(string hex) {
return Enumerable.Range(0, hex.Length)
.Where(x => x % 2 == 0)
.Select(x => Convert.ToByte(hex.Substring(x, 2), 16))
.ToArray();
}

Try this:
private byte[] Hex2Bin(string hex)
{
if ((hex == null) || (hex.Length < 1)) {
return new byte[0];
}
int num = hex.Length / 2;
byte[] buffer = new byte[num];
num *= 2;
for (int i = 0; i < num; i++) {
int num3 = int.Parse(hex.Substring(i, 2), NumberStyles.HexNumber);
buffer[i / 2] = (byte) num3;
i++;
}
return buffer;
}
private string Bin2Hex(byte[] binary)
{
StringBuilder builder = new StringBuilder();
foreach(byte num in binary) {
if (num > 15) {
builder.AppendFormat("{0:X}", num);
} else {
builder.AppendFormat("0{0:X}", num); /////// 大于 15 就多加个 0
}
}
return builder.ToString();
}

You convert the hex string to a byte array.
public static byte[] StringToByteArray(string hex) {
return Enumerable.Range(0, hex.Length)
.Where(x => x % 2 == 0)
.Select(x => Convert.ToByte(hex.Substring(x, 2), 16))
.ToArray();
}
Credit: Jared Par
And then use WriteAllBytes to write to the file system.

This example reads 6 bytes into a byte array and writes it to another byte array. It does an XOR operation with the bytes so that the result written to the file is the same as the original starting values. The file is always 6 bytes in size, since it writes at position 0.
using System;
using System.IO;
namespace ConsoleApplication1
{
class Program
{
static void Main()
{
byte[] b1 = { 1, 2, 4, 8, 16, 32 };
byte[] b2 = new byte[6];
byte[] b3 = new byte[6];
byte[] b4 = new byte[6];
FileStream f1;
f1 = new FileStream("test.txt", FileMode.Create, FileAccess.Write);
// write the byte array into a new file
f1.Write(b1, 0, 6);
f1.Close();
// read the byte array
f1 = new FileStream("test.txt", FileMode.Open, FileAccess.Read);
f1.Read(b2, 0, 6);
f1.Close();
// make changes to the byte array
for (int i = 1; i < b2.Length; i++)
{
b2[i] = (byte)(b2[i] ^ (byte)10); //xor 10
}
f1 = new FileStream("test.txt", FileMode.Open, FileAccess.Write);
// write the new byte array into the file
f1.Write(b2, 0, 6);
f1.Close();
f1 = new FileStream("test.txt", FileMode.Open, FileAccess.Read);
// read the byte array
f1.Read(b3, 0, 6);
f1.Close();
// make changes to the byte array
for (int i = 1; i < b3.Length; i++)
{
b4[i] = (byte)(b3[i] ^ (byte)10); //xor 10
}
f1 = new FileStream("test.txt", FileMode.Open, FileAccess.Write);
// b4 will have the same values as b1
f1.Write(b4, 0, 6);
f1.Close();
}
}
}