I have the following C# code to convert my number array into byte array and then save it as a base64 string and vice-versa, however it doesn't work for long because long is 8-byte and my code only works for 4-byte numbers.
private static int _endianDiff1;
private static int _endianDiff2;
private static int _idx;
private static byte[] _byteBlock;
enum ArrayType { Float, Int32, UInt32, Int64, UInt64 }
public static bool SetIntArray(string key, int[] intArray)
{
return SetValue(key, intArray, ArrayType.Int32, 1, ConvertFromInt);
}
public static bool SetLongArray(string key, long[] longArray)
{
return SetValue(key, longArray, ArrayType.Int64, 1, ConvertFromLong);
}
private static bool SetValue<T>(string key, T array, ArrayType arrayType, int vectorNumber, Action<T, byte[], int> convert) where T : IList
{
var bytes = new byte[(4 * array.Count) * vectorNumber + 1];
bytes[0] = Convert.ToByte(arrayType); // Identifier
Initialize();
for (var i = 0; i < array.Count; i++)
{
convert(array, bytes, i);
}
return SaveBytes(key, bytes);
}
private static void ConvertFromInt(int[] array, byte[] bytes, int i)
{
ConvertInt32ToBytes(array[i], bytes);
}
private static void ConvertFromLong(long[] array, byte[] bytes, int i)
{
ConvertInt64ToBytes(array[i], bytes);
}
public static int[] GetIntArray(string key)
{
var intList = new List<int>();
GetValue(key, intList, ArrayType.Int32, 1, ConvertToInt);
return intList.ToArray();
}
public static long[] GetLongArray(string key)
{
var longList = new List<long>();
GetValue(key, longList, ArrayType.Int64, 1, ConvertToLong);
return longList.ToArray();
}
private static void GetValue<T>(string key, T list, ArrayType arrayType, int vectorNumber, Action<T, byte[]> convert) where T : IList
{
if (!PlayerPrefs.HasKey(key))
return;
var bytes = Convert.FromBase64String(PlayerPrefs.GetString(key));
if ((bytes.Length - 1) % (vectorNumber * 4) != 0)
{
Debug.LogError("Corrupt preference file for " + key);
return;
}
if ((ArrayType)bytes[0] != arrayType)
{
Debug.LogError(key + " is not a " + arrayType + " array");
return;
}
Initialize();
var end = (bytes.Length - 1) / (vectorNumber * 4);
for (var i = 0; i < end; i++)
{
convert(list, bytes);
}
}
private static void ConvertToInt(List<int> list, byte[] bytes)
{
list.Add(ConvertBytesToInt32(bytes));
}
private static void ConvertToLong(List<long> list, byte[] bytes)
{
list.Add(ConvertBytesToInt64(bytes));
}
private static void Initialize()
{
if (BitConverter.IsLittleEndian)
{
_endianDiff1 = 0;
_endianDiff2 = 0;
}
else
{
_endianDiff1 = 3;
_endianDiff2 = 1;
}
if (_byteBlock == null)
{
_byteBlock = new byte[4];
}
_idx = 1;
}
private static bool SaveBytes(string key, byte[] bytes)
{
try
{
PlayerPrefs.SetString(key, Convert.ToBase64String(bytes));
}
catch
{
return false;
}
return true;
}
private static void ConvertInt32ToBytes(int i, byte[] bytes)
{
_byteBlock = BitConverter.GetBytes(i);
ConvertTo4Bytes(bytes);
}
private static void ConvertInt64ToBytes(long i, byte[] bytes)
{
_byteBlock = BitConverter.GetBytes(i);
ConvertTo8Bytes(bytes);
}
private static int ConvertBytesToInt32(byte[] bytes)
{
ConvertFrom4Bytes(bytes);
return BitConverter.ToInt32(_byteBlock, 0);
}
private static long ConvertBytesToInt64(byte[] bytes)
{
ConvertFrom8Bytes(bytes);
return BitConverter.ToInt64(_byteBlock, 0);
}
private static void ConvertTo4Bytes(byte[] bytes)
{
bytes[_idx] = _byteBlock[_endianDiff1];
bytes[_idx + 1] = _byteBlock[1 + _endianDiff2];
bytes[_idx + 2] = _byteBlock[2 - _endianDiff2];
bytes[_idx + 3] = _byteBlock[3 - _endianDiff1];
_idx += 4;
}
private static void ConvertFrom4Bytes(byte[] bytes)
{
_byteBlock[_endianDiff1] = bytes[_idx];
_byteBlock[1 + _endianDiff2] = bytes[_idx + 1];
_byteBlock[2 - _endianDiff2] = bytes[_idx + 2];
_byteBlock[3 - _endianDiff1] = bytes[_idx + 3];
_idx += 4;
}
private static void ConvertTo8Bytes(byte[] bytes)
{
}
private static void ConvertFrom8Bytes(byte[] bytes)
{
}
So far I have it working for int, uint and float because they are all 4-byte and my problem is to change my Initialize function so it works based on the passed type size.
I guess there should also be ConvertTo8Bytes and ConvertFrom8Bytes functions which I don't know how to make because I set the _endianDiff and _byteBlock for 4-byte only. I understand that _byteBlock should have dynamic size instead of 4 but I don't know what to do with endianness in this case.
On the side note, I have solved this problem by splitting the long into 2 ints and just storing them as two int arrays, but I'm allocating useless memory like this just because I'm not able to make this algorithm to work.
Seems like a lot of code if all you are doing is trying to get a Base64 representation of a numeric array. Am I missing the goal?
If all you want to do is get int or long arrays to and from base64 strings, try this:
private static string ConvertArrayToBase64<T>(IList<T> array) where T : struct
{
if (typeof(T).IsPrimitive)
{
int size = System.Runtime.InteropServices.Marshal.SizeOf<T>();
var byteArray = new byte[array.Count * size];
Buffer.BlockCopy(array.ToArray(), 0, byteArray, 0, byteArray.Length);
return Convert.ToBase64String(byteArray);
}
throw new InvalidOperationException("Only primitive types are supported.");
}
private static T[] ConvertBase64ToArray<T>(string base64String) where T : struct
{
if (typeof(T).IsPrimitive)
{
var byteArray = Convert.FromBase64String(base64String);
var array = new T[byteArray.Length / System.Runtime.InteropServices.Marshal.SizeOf<T>()];
Buffer.BlockCopy(byteArray, 0, array, 0, byteArray.Length);
return array;
}
throw new InvalidOperationException("Only primitive types are supported.");
}
There are a couple things to consider with this code though...
It does make a complete copy of the array, so if you are dealing with a large array or a performance sensitive operation, it may not be the best way.
This should work with any "primitive value type" arrays, which should include all the numeric types like int, long, uint, float, etc.
To demonstrate usage, see this example:
var longArray = new long[] { 11111, 22222, 33333, 44444 };
var intArray = new int[] { 55555, 66666, 77777, 88888};
string base64longs = ConvertArrayToBase64(longArray);
Console.WriteLine(base64longs);
Console.WriteLine(string.Join(", ", ConvertBase64ToArray<long>(base64longs)));
string base64ints = ConvertArrayToBase64(intArray);
Console.WriteLine(base64ints);
Console.WriteLine(string.Join(", ", ConvertBase64ToArray<int>(base64ints)));
What it does:
Verifies that the array only has primitive types.
Determines the size of the elements in the array to
calculate the length of the byte array to allocate.
It copies the array to the byte array.
Returns the base64 representation.
The complementary function does the reverse.
Update: Here are the .NET 2.0 compatible versions...
private static string ConvertArrayToBase64<T>(IList<T> array) where T : struct
{
if (typeof(T).IsPrimitive)
{
int size = System.Runtime.InteropServices.Marshal.SizeOf(typeof(T));
var byteArray = new byte[array.Count * size];
Buffer.BlockCopy((Array)array, 0, byteArray, 0, byteArray.Length);
return Convert.ToBase64String(byteArray);
}
throw new InvalidOperationException("Only primitive types are supported.");
}
private static T[] ConvertBase64ToArray<T>(string base64String) where T : struct
{
if (typeof(T).IsPrimitive)
{
var byteArray = Convert.FromBase64String(base64String);
var array = new T[byteArray.Length / System.Runtime.InteropServices.Marshal.SizeOf(typeof(T))];
Buffer.BlockCopy(byteArray, 0, array, 0, byteArray.Length);
return array;
}
throw new InvalidOperationException("Only primitive types are supported.");
}
Related
I created small not finishd Packet Builder class.
AddString() working without problems, but if i use AddInt() the console output looks very weird. Any can tell me why the integer not display correctly?
Main
Packet packet = new Packet();
packet.builder.AddString(Constants.Requests.GET_RESOURCES);
packet.builder.AddString("Another_String");
packet.builder.AddInt(500);
byte[] byteArray = packet.builder.GetByteBuffer();
Console.WriteLine(ByteArrayToString(byteArray));
ByteArray Output: Get_Resources:Another_String:?☺:
47-65-74-5F-52-65-73-6F-75-72-63-65-73-00-3A-41-6E-6F-74-68-65-72-5F-53-74-72-69-6E-67-00-3A-F4-01-00-00-00-3A
As you can see: ?☺ is definitly wrong. The functions are almost the same.
Class
class Packet
{
public Builder builder;
public Packet()
{
builder = new Builder();
}
private static string ByteArrayToString(byte[] arr)
{
System.Text.ASCIIEncoding enc = new System.Text.ASCIIEncoding();
return enc.GetString(arr);
}
public static string[] Read(byte[] _recievedData)
{
string data = ByteArrayToString(_recievedData).Trim();
string[] result = data.Split(':');
return result;
}
public class Builder
{
private byte[] buffer;
private int offset;
//Makes very easy on client to filter packets...
private byte[] seperator;
public Builder()
{
offset = 0;
buffer = new byte[4096];
seperator = BitConverter.GetBytes(':');
}
public void AddInt(int intValue)
{
byte[] byteArray = BitConverter.GetBytes(intValue);
for (int x = 0; x < byteArray.Length; x++)
{
buffer[x + offset] = byteArray[x];
}
for (int y = 0; y < seperator.Length; y++)
{
buffer[byteArray.Length + (y + 1) + offset] = seperator[y];
}
offset += (byteArray.Length + seperator.Length);
}
public void AddString(string str)
{
byte[] byteArray = Encoding.ASCII.GetBytes(str);
for (int x = 0; x < byteArray.Length; x++)
{
buffer[x + offset] = byteArray[x];
}
for (int y = 0; y < seperator.Length; y++)
{
buffer[byteArray.Length + (y + 1) + offset] = seperator[y];
}
offset += (byteArray.Length + seperator.Length);
}
public byte[] GetByteBuffer()
{
return buffer;
}
public void Reset()
{
buffer = null;
offset = 0;
}
}
}
Your code is working perfectly fine. Possibly it is not what you want but following code converts an int in 4 bytes because it is a 32-bit integer.
byte[] byteArray = BitConverter.GetBytes(intValue);
at the end of your output, you see those 4 bytes as expected in little endian format F4-01-00-00 because 500 in hexadecimal is 0x01F4. This explains why you are getting, what you are getting.
Now I am assuming that you are expecting 500 instead of ?☺. Following code should fetch you desired result:
byte[] byteArray = BitConverter.GetBytes(intValue.ToString());
This will add a string representation of the number instead of binary representation. Based on the return type of Read function, the need seems to be a string representation.
I'm making a demo about sound in WindowsForm, I created 3 classes for taking data of wave file. Code is below:
RiffBlock
public class RiffBlock
{
private byte[] riffID;
private uint riffSize;
private byte[] riffFormat;
public byte[] RiffID
{
get { return riffID; }
}
public uint RiffSize
{
get { return (riffSize); }
}
public byte[] RiffFormat
{
get { return riffFormat; }
}
public RiffBlock()
{
riffID = new byte[4];
riffFormat = new byte[4];
}
public void ReadRiff(FileStream inFS)
{
inFS.Read(riffID, 0, 4);
BinaryReader binRead = new BinaryReader(inFS);
riffSize = binRead.ReadUInt32();
inFS.Read(riffFormat, 0, 4);
}
}
FormatBlock
public class FormatBlock
{
private byte[] fmtID;
private uint fmtSize;
private ushort fmtTag;
private ushort fmtChannels;
private uint fmtSamplesPerSec;
private uint fmtAverageBytesPerSec;
private ushort fmtBlockAlign;
private ushort fmtBitsPerSample;
public byte[] FmtID
{
get { return fmtID; }
}
public uint FmtSize
{
get { return fmtSize; }
}
public ushort FmtTag
{
get { return fmtTag; }
}
public ushort Channels
{
get { return fmtChannels; }
}
public uint SamplesPerSec
{
get { return fmtSamplesPerSec; }
}
public uint AverageBytesPerSec
{
get { return fmtAverageBytesPerSec; }
}
public ushort BlockAlign
{
get { return fmtBlockAlign; }
}
public ushort BitsPerSample
{
get { return fmtBitsPerSample; }
}
public FormatBlock()
{
fmtID = new byte[4];
}
public void ReadFmt(FileStream inFS)
{
inFS.Read(fmtID, 0, 4);
BinaryReader binRead = new BinaryReader(inFS);
fmtSize = binRead.ReadUInt32();
fmtTag = binRead.ReadUInt16();
fmtChannels = binRead.ReadUInt16();
fmtSamplesPerSec = binRead.ReadUInt32();
fmtAverageBytesPerSec = binRead.ReadUInt32();
fmtBlockAlign = binRead.ReadUInt16();
fmtBitsPerSample = binRead.ReadUInt16();
// This accounts for the variable format header size
// 12 bytes of Riff Header, 4 bytes for FormatId, 4 bytes for FormatSize & the Actual size of the Format Header
inFS.Seek(fmtSize + 20, System.IO.SeekOrigin.Begin);
}
}
DataBlock
public class DataBlock
{
private byte[] dataID;
private uint dataSize;
private Int16[] data;
private int dataNumSamples;
public byte[] DataID
{
get { return dataID; }
}
public uint DataSize
{
get { return dataSize; }
}
public Int16 this[int pos]
{
get { return data[pos]; }
}
public int NumSamples
{
get { return dataNumSamples; }
}
public DataBlock()
{
dataID = new byte[4];
}
public void ReadData(FileStream inFS)
{
inFS.Read(dataID, 0, 4);
BinaryReader binRead = new BinaryReader(inFS);
dataSize = binRead.ReadUInt32();
data = new Int16[dataSize];
inFS.Seek(40, SeekOrigin.Begin);
dataNumSamples = (int)(dataSize / 2);
for (int i = 0; i < dataNumSamples; i++)
{
data[i] = binRead.ReadInt16();
}
}
}
It works ok with only 16bit wave file, but when I choose a 8 bit wav file or another, the result of this command dataSize = binRead.ReadUInt32();is only 4 although the file size is big.
How I can get the data of 8bit, 24bit... wav file?
Some solutions is appreciated, thank you very much.
Your reading methodology is flawed. The length is correct but for an 8 bits per sample file you should be reading bytes not words; as it stands the data will be incorrect and the value returned by the NumSamples property will be wrong.
In my case, the sub chunk size is 1160, the number of channels is 1 (mono) and the bits per sample is 8 (byte). You will need to decode the bits per sample and adjust your reading accordingly. For the WAV file I used, your program allocated a data array the correct length but 16 bit, divided the data length by 2 and called this the number of samples (wrong, it should be 1160) and then proceeded to read 580 word values from the stream.
Edit: My ancient code will not cut it in the modern age (I seem to recall having to modify it some years ago to cope with at least one additional chunk type but the details escape me).
This is what you get; anything more and your question should read "Could someone write me a program to load WAV files", as it is, we are way beyond the original question and it is time for you to knuckle down and make it work how you need it to :-)
References:
http://www.neurophys.wisc.edu/auditory/riff-format.txt
http://www-mmsp.ece.mcgill.ca/Documents/AudioFormats/WAVE/WAVE.html
http://www.shikadi.net/moddingwikiResource_Interchange_File_Format_(RIFF)
http://soundfile.sapp.org/doc/WaveFormat/
All are very useful.
///<summary>
///Reads up to 16 bit WAV files
///</summary>
///<remarks> Things have really changed in the last 15 years</remarks>
public class RiffLoader
{
public enum RiffStatus { Unknown = 0, OK, FileError, FormatError, UnsupportedFormat };
LinkedList<Chunk> chunks = new LinkedList<Chunk>();
RiffStatus status = RiffStatus.Unknown;
List<String> errorMessages = new List<string>();
String source;
public String SourceName { get { return source; } }
public RiffStatus Status { get { return status; } }
public String[] Messages { get { return errorMessages.ToArray(); } }
enum chunkType { Unknown = 0, NoMore, Riff, Fmt, Fact, Data, Error = -1 };
static Int32 scan32bits(byte[] source, int offset = 0)
{
return source[offset] | source[offset + 1] << 8 | source[offset + 2] << 16 | source[offset + 3] << 24;
}
static Int32 scan16bits(byte[] source, int offset = 0)
{
return source[offset] | source[offset + 1] << 8;
}
static Int32 scan8bits(byte[] source, int offset = 0)
{
return source[offset];
}
abstract class Chunk
{
public chunkType Ident = chunkType.Unknown;
public int ByteCount = 0;
}
class RiffChunk : Chunk
{
public RiffChunk(int count)
{
this.Ident = chunkType.Riff;
this.ByteCount = count;
}
}
class FmtChunk : Chunk
{
int formatCode = 0;
int channels = 0;
int samplesPerSec = 0;
int avgBytesPerSec = 0;
int blockAlign = 0;
int bitsPerSample = 0;
int significantBits = 0;
public int Format { get { return formatCode; } }
public int Channels { get { return channels; } }
public int BlockAlign { get { return blockAlign; } }
public int BytesPerSample { get { return bitsPerSample / 8 + ((bitsPerSample % 8) > 0 ? 1 : 0); } }
public int BitsPerSample
{
get
{
if (significantBits > 0)
return significantBits;
return bitsPerSample;
}
}
public FmtChunk(byte[] buffer) : base()
{
int size = buffer.Length;
// if the length is 18 then buffer 16,17 should be 00 00 (I don't bother checking)
if (size != 16 && size != 18 && size != 40)
return;
formatCode = scan16bits(buffer, 0);
channels = scan16bits(buffer, 2);
samplesPerSec = scan32bits(buffer, 4);
avgBytesPerSec = scan32bits(buffer, 8);
blockAlign = scan16bits(buffer, 12);
bitsPerSample = scan16bits(buffer, 14);
if (formatCode == 0xfffe) // EXTENSIBLE
{
if (size != 40)
return;
significantBits = scan16bits(buffer, 18);
// skiping speaker map
formatCode = scan16bits(buffer, 24); // first two bytes of the GUID
// the rest of the GUID is fixed, decode it and check it if you wish
}
this.Ident = chunkType.Fmt;
this.ByteCount = size;
}
}
class DataChunk : Chunk
{
byte[] samples = null;
///<summary>
///Create a data chunk
///<para>
///The supplied buffer must be correctly sized with zero offset and must be purely for this class
///</para>
///<summary>
///<param name="buffer">source array</param>
public DataChunk(byte[] buffer)
{
this.Ident = chunkType.Data;
this.ByteCount = buffer.Length;
samples = buffer;
}
public enum SampleStatus { OK, Duff }
public class Samples
{
public SampleStatus Status = SampleStatus.Duff;
public List<int[]> Channels = new List<int[]>();
#if false // debugger helper method
/*
** Change #if false to #if true to include this
** Break at end of GetSamples on "return retval"
** open immediate window and type retval.DumpLast(16)
** look in output window for dump of last 16 entries
*/
public int DumpLast(int count)
{
for (int i = Channels[0].Length - count; i < Channels[0].Length; i++)
Console.WriteLine(String.Format("{0:X4} {1:X4},{2:X4}", i, Channels[0][i], Channels[1][i]));
return 0;
}
#endif
}
/*
** Return the decoded samples
*/
public Samples GetSamples(FmtChunk format)
{
Samples retval = new Samples();
int samplesPerChannel = this.ByteCount / (format.BytesPerSample * format.Channels);
int mask = 0, sign=0;
int [][] samples = new int [format.Channels][];
for (int c = 0; c < format.Channels; c++)
samples[c] = new int[samplesPerChannel];
if (format.BitsPerSample >= 8 && format.BitsPerSample <= 16) // 24+ is left as an excercise
{
sign = (int)Math.Floor(Math.Pow(2, format.BitsPerSample - 1));
mask = (int)Math.Floor(Math.Pow(2, format.BitsPerSample)) - 1;
int offset = 0, index = 0;
int s = 0;
while (index < samplesPerChannel)
{
for (int c = 0; c < format.Channels; c++)
{
switch (format.BytesPerSample)
{
case 1:
s = scan8bits(this.samples, offset) & mask;
break;
case 2:
s = scan16bits(this.samples, offset) & mask;
break;
}
// sign extend the data to Int32
samples[c][index] = s | ((s & sign) != 0 ? ~mask : 0);
offset += format.BytesPerSample;
}
++index;
}
retval.Channels = new List<int[]>(samples);
retval.Status = SampleStatus.OK;
}
return retval;
}
}
class FactChunk : Chunk
{
int samplesPerChannel;
public int SamplesPerChannel { get { return samplesPerChannel; } }
public FactChunk(byte[] buffer)
{
this.Ident = chunkType.Fact;
this.ByteCount = buffer.Length;
if (buffer.Length >= 4)
samplesPerChannel = scan32bits(buffer);
}
}
class DummyChunk : Chunk
{
public DummyChunk(int size, chunkType type = chunkType.Unknown)
{
this.Ident = type;
this.ByteCount = size;
}
}
public RiffLoader(String fileName)
{
source = fileName;
try
{
using (FileStream fs = new FileStream(fileName, FileMode.Open, FileAccess.Read))
using (BinaryReader reader = new BinaryReader(fs))
{
Chunk c = getChunk(fs, reader);
if (c.Ident != chunkType.Riff)
{
status = RiffStatus.FileError;
errorMessages.Add(String.Format("Error loading \"{0}\": No valid header"));
}
chunks.AddLast(c);
c = getChunk(fs, reader);
if (c.Ident != chunkType.Fmt)
{
status = RiffStatus.FileError;
errorMessages.Add(String.Format("Error loading \"{0}\": No format chunk"));
}
chunks.AddLast(c);
/*
** From now on we just keep scanning to the end of the file
*/
while (fs.Position < fs.Length)
{
c = getChunk(fs, reader);
switch (c.Ident)
{
case chunkType.Fact:
case chunkType.Data:
chunks.AddLast(c);
break;
case chunkType.Unknown:
break; // skip it - don't care what it is
}
}
FmtChunk format = null;
foreach (var chunk in chunks)
{
switch(chunk.Ident)
{
case chunkType.Fmt:
format = chunk as FmtChunk;
break;
case chunkType.Data:
if (format != null)
{
DataChunk dc = chunk as DataChunk;
var x = dc.GetSamples(format);
}
break;
}
}
}
}
catch (Exception e)
{
status = RiffStatus.FileError;
errorMessages.Add(String.Format("Error loading \"{0}\": {1}", e.Message));
}
}
/*
** Get a chunk of data from the file - knows nothing of the internal format of the chunk.
*/
Chunk getChunk(FileStream stream, BinaryReader reader)
{
byte[] buffer;
int size;
buffer = reader.ReadBytes(8);
if (buffer.Length == 8)
{
String prefix = new String(Encoding.ASCII.GetChars(buffer, 0, 4));
size = scan32bits(buffer, 4);
if (size + stream.Position <= stream.Length) // skip if there isn't enough data
{
if (String.Compare(prefix, "RIFF") == 0)
{
/*
** only "WAVE" type is acceptable
**
** Don't read size bytes or the entire file will end up in the RIFF chunk
*/
if (size >= 4)
{
buffer = reader.ReadBytes(4);
String ident = new String(Encoding.ASCII.GetChars(buffer, 0, 4));
if (String.CompareOrdinal(ident, "WAVE") == 0)
return new RiffChunk(size - 4);
}
}
else if (String.Compare(prefix, "fmt ") == 0)
{
if (size >= 16)
{
buffer = reader.ReadBytes(size);
if (buffer.Length == size)
return new FmtChunk(buffer);
}
}
else if (String.Compare(prefix, "fact") == 0)
{
if (size >= 4)
{
buffer = reader.ReadBytes(4);
if (buffer.Length == size)
return new FactChunk(buffer);
}
}
else if (String.Compare(prefix, "data") == 0)
{
// assume that there has to be data
if (size > 0)
{
buffer = reader.ReadBytes(size);
if ((size & 1) != 0) // odd length?
{
if (stream.Position < stream.Length)
reader.ReadByte();
else
size = -1; // force an error - there should be a pad byte
}
if (buffer.Length == size)
return new DataChunk(buffer);
}
}
else
{
/*
** there are a number of weird and wonderful block types - assume there has to be data
*/
if (size > 0)
{
buffer = reader.ReadBytes(size);
if ((size & 1) != 0) // odd length?
{
if (stream.Position < stream.Length)
reader.ReadByte();
else
size = -1; // force an error - there should be a pad byte
}
if (buffer.Length == size)
{
DummyChunk skip = new DummyChunk(size);
return skip;
}
}
}
}
}
return new DummyChunk(0, chunkType.Error);
}
}
You will need to add properties as required and code to navigate the returned linked list. Particular properties you may need are the sample rates in the format block, assuming you are going to process the data in some way.
Adding 24 to 32 bits is simple, if you need to go beyond 32 bits you will have to switch to int64's.
I have tested it with some good samples from http://www-mmsp.ece.mcgill.ca/Documents/AudioFormats/WAVE/Samples.html, as well as your 8 bit file, and it decodes OK and seems to have the correct data.
You should be more than capable of making it work now, good luck.
Edit (again, like the proverbial dog...):
Of course, I should have sign extended the value, so DataChunk.GetSamples() now does that. Looking at the Codeproject files (it isn't the greatest code by the way, but the guy does say that he is only just learning C#, so fair play for tackling a graphical user control) it is obvious that the data is signed. It's a shame that he didn't standardise his source to be an array of Int32's, then it wouldn't matter how many bits the WAV was encoded in.
You could use the Naudio library:
https://naudio.codeplex.com/ (take a look at their website, there are quite a lot of tutorials).
Hope this helps :).
I`m looking for solution for hashing large file content (files may be over 2gb in 32bit os). It there any easy solution for that? Or just reading by part and loading to buffer?
Driis's solution sounds more flexible, but HashAlgorithm.ComputeHash will also accept Streams as parameters.
Use TransformBlock and TransformFinalBlock to calculate the hash block by block, so you won't need to read the entire file into memory. (There is a nice example in the first link - and another one in this previous question).
If you choose to use TransformBlock, then you can safely ignore the last parameter and set the outputBuffer to null. TransformBlock will copy from the input to the output array - but why would you want to simply copy bits for no good reason?
Furthermore, all mscorlib HashAlgorithms work as you might expect, i.e. the block size doesn't seem to affect the hash output; and whether you pass the data in one array and then hash in chunks by changing the inputOffset or you hash by passing smaller, separate arrays doesn't matter. I verified this using the following code:
(this is slightly long, just here so people can verify for themselves that HashAlgorithm implementations are sane).
public static void Main() {
RandomNumberGenerator rnd = RandomNumberGenerator.Create();
byte[] input = new byte[20];
rnd.GetBytes(input);
Console.WriteLine("Input Data: " + BytesToStr(input));
var hashAlgoTypes = Assembly.GetAssembly(typeof(HashAlgorithm)).GetTypes()
.Where(t => typeof(HashAlgorithm).IsAssignableFrom(t) && !t.IsAbstract);
foreach (var hashType in hashAlgoTypes)
new AlgoTester(hashType).AssertOkFor(input.ToArray());
}
public static string BytesToStr(byte[] bytes) {
StringBuilder str = new StringBuilder();
for (int i = 0; i < bytes.Length; i++)
str.AppendFormat("{0:X2}", bytes[i]);
return str.ToString();
}
public class AlgoTester {
readonly byte[] key;
readonly Type type;
public AlgoTester(Type type) {
this.type=type;
if (typeof(KeyedHashAlgorithm).IsAssignableFrom(type))
using(var algo = (KeyedHashAlgorithm)Activator.CreateInstance(type))
key = algo.Key.ToArray();
}
public HashAlgorithm MakeAlgo() {
HashAlgorithm algo = (HashAlgorithm)Activator.CreateInstance(type);
if (key != null)
((KeyedHashAlgorithm)algo).Key = key;
return algo;
}
public byte[] GetHash(byte[] input) {
using(HashAlgorithm sha = MakeAlgo())
return sha.ComputeHash(input);
}
public byte[] GetHashOneBlock(byte[] input) {
using(HashAlgorithm sha = MakeAlgo()) {
sha.TransformFinalBlock(input, 0, input.Length);
return sha.Hash;
}
}
public byte[] GetHashMultiBlock(byte[] input, int size) {
using(HashAlgorithm sha = MakeAlgo()) {
int offset = 0;
while (input.Length - offset >= size)
offset += sha.TransformBlock(input, offset, size, input, offset);
sha.TransformFinalBlock(input, offset, input.Length - offset);
return sha.Hash;
}
}
public byte[] GetHashMultiBlockInChunks(byte[] input, int size) {
using(HashAlgorithm sha = MakeAlgo()) {
int offset = 0;
while (input.Length - offset >= size)
offset += sha.TransformBlock(input.Skip(offset).Take(size).ToArray()
, 0, size, null, -24124512);
sha.TransformFinalBlock(input.Skip(offset).ToArray(), 0
, input.Length - offset);
return sha.Hash;
}
}
public void AssertOkFor(byte[] data) {
var direct = GetHash(data);
var indirect = GetHashOneBlock(data);
var outcomes =
new[] { 1, 2, 3, 5, 10, 11, 19, 20, 21 }.SelectMany(i =>
new[]{
new{ Hash=GetHashMultiBlock(data,i), Name="ByMSDN"+i},
new{ Hash=GetHashMultiBlockInChunks(data,i), Name="InChunks"+i}
}).Concat(new[] { new { Hash = indirect, Name = "OneBlock" } })
.Where(result => !result.Hash.SequenceEqual(direct)).ToArray();
Console.Write("Testing: " + type);
if (outcomes.Any()) {
Console.WriteLine("not OK.");
Console.WriteLine(type.Name + " direct was: " + BytesToStr(direct));
} else Console.WriteLine(" OK.");
foreach (var outcome in outcomes)
Console.WriteLine(type.Name + " differs with: " + outcome.Name + " "
+ BytesToStr(outcome.Hash));
}
}
Please show me optimized solutions for castings:
1)
public static byte[] ToBytes(List<Int64> list)
{
byte[] bytes = null;
//todo
return bytes;
}
2)
public static List<Int64> ToList(byte[] bytes)
{
List<Int64> list = null;
//todo
return list;
}
It will be very helpful to see versions with minimized copying and/or with unsafe code (if it can be implemented). Ideally, copying of data are do not need at all.
Update:
My question is about casting like C++ manner:
__int64* ptrInt64 = (__int64*)ptrInt8;
and
__int8* ptrInt8 = (__int8*)ptrInt64
Thank you for help!!!
Edit, fixed for correct 8 byte conversion, also not terribly efficient when converting back to byte array.
public static List<Int64> ToList(byte[] bytes)
{
var list = new List<Int64>();
for (int i = 0; i < bytes.Length; i += sizeof(Int64))
list.Add(BitConverter.ToInt64(bytes, i));
return list;
}
public static byte[] ToBytes(List<Int64> list)
{
var byteList = list.ConvertAll(new Converter<Int64, byte[]>(Int64Converter));
List<byte> resultList = new List<byte>();
byteList.ForEach(x => { resultList.AddRange(x); });
return resultList.ToArray();
}
public static byte[] Int64Converter(Int64 x)
{
return BitConverter.GetBytes(x);
}
Use Mono.DataConvert. This library has converters to/from most primitive types, for big-endian, little-endian, and host-order byte ordering.
CLR arrays know their types and sizes so you can't just cast an array of one type to another. However, it is possible to do unsafe casting of value types. For example, here's the source to BitConverter.GetBytes(long):
public static unsafe byte[] GetBytes(long value)
{
byte[] buffer = new byte[8];
fixed (byte* numRef = buffer)
{
*((long*) numRef) = value;
}
return buffer;
}
You could write this for a list of longs, like this:
public static unsafe byte[] GetBytes(IList<long> value)
{
byte[] buffer = new byte[8 * value.Count];
fixed (byte* numRef = buffer)
{
for (int i = 0; i < value.Count; i++)
*((long*) (numRef + i * 8)) = value[i];
}
return buffer;
}
And of course it would be easy to go in the opposite direction if this was how you wanted to go.
I use an extension method to convert float arrays into byte arrays:
public static unsafe byte[] ToByteArray(this float[] floatArray, int count)
{
int arrayLength = floatArray.Length > count ? count : floatArray.Length;
byte[] byteArray = new byte[4 * arrayLength];
fixed (float* floatPointer = floatArray)
{
fixed (byte* bytePointer = byteArray)
{
float* read = floatPointer;
float* write = (float*)bytePointer;
for (int i = 0; i < arrayLength; i++)
{
*write++ = *read++;
}
}
}
return byteArray;
}
I understand that an array is a pointer to memory associated with information on the type and number of elements. Also, it seems to me that there is no way of doing a conversion from and to a byte array without copying the data as above.
Have I understood this? Would it even be impossible to write IL to create an array from a pointer, type and length without copying data?
EDIT: Thanks for the answers, I learned some fundamentals and got to try out new tricks!
After initially accepting Davy Landman's answer I found out that while his brilliant StructLayout hack does convert byte arrays into float arrays, it does not work the other way around. To demonstrate:
[StructLayout(LayoutKind.Explicit)]
struct UnionArray
{
[FieldOffset(0)]
public Byte[] Bytes;
[FieldOffset(0)]
public float[] Floats;
}
static void Main(string[] args)
{
// From bytes to floats - works
byte[] bytes = { 0, 1, 2, 4, 8, 16, 32, 64 };
UnionArray arry = new UnionArray { Bytes = bytes };
for (int i = 0; i < arry.Bytes.Length / 4; i++)
Console.WriteLine(arry.Floats[i]);
// From floats to bytes - index out of range
float[] floats = { 0.1f, 0.2f, 0.3f };
arry = new UnionArray { Floats = floats };
for (int i = 0; i < arry.Floats.Length * 4; i++)
Console.WriteLine(arry.Bytes[i]);
}
It seems that the CLR sees both arrays as having the same length. If the struct is created from float data, the byte array's length is just too short.
You can use a really ugly hack to temporary change your array to byte[] using memory manipulation.
This is really fast and efficient as it doesn't require cloning the data and iterating on it.
I tested this hack in both 32 & 64 bit OS, so it should be portable.
The source + sample usage is maintained at https://gist.github.com/1050703 , but for your convenience I'll paste it here as well:
public static unsafe class FastArraySerializer
{
[StructLayout(LayoutKind.Explicit)]
private struct Union
{
[FieldOffset(0)] public byte[] bytes;
[FieldOffset(0)] public float[] floats;
}
[StructLayout(LayoutKind.Sequential, Pack = 1)]
private struct ArrayHeader
{
public UIntPtr type;
public UIntPtr length;
}
private static readonly UIntPtr BYTE_ARRAY_TYPE;
private static readonly UIntPtr FLOAT_ARRAY_TYPE;
static FastArraySerializer()
{
fixed (void* pBytes = new byte[1])
fixed (void* pFloats = new float[1])
{
BYTE_ARRAY_TYPE = getHeader(pBytes)->type;
FLOAT_ARRAY_TYPE = getHeader(pFloats)->type;
}
}
public static void AsByteArray(this float[] floats, Action<byte[]> action)
{
if (floats.handleNullOrEmptyArray(action))
return;
var union = new Union {floats = floats};
union.floats.toByteArray();
try
{
action(union.bytes);
}
finally
{
union.bytes.toFloatArray();
}
}
public static void AsFloatArray(this byte[] bytes, Action<float[]> action)
{
if (bytes.handleNullOrEmptyArray(action))
return;
var union = new Union {bytes = bytes};
union.bytes.toFloatArray();
try
{
action(union.floats);
}
finally
{
union.floats.toByteArray();
}
}
public static bool handleNullOrEmptyArray<TSrc,TDst>(this TSrc[] array, Action<TDst[]> action)
{
if (array == null)
{
action(null);
return true;
}
if (array.Length == 0)
{
action(new TDst[0]);
return true;
}
return false;
}
private static ArrayHeader* getHeader(void* pBytes)
{
return (ArrayHeader*)pBytes - 1;
}
private static void toFloatArray(this byte[] bytes)
{
fixed (void* pArray = bytes)
{
var pHeader = getHeader(pArray);
pHeader->type = FLOAT_ARRAY_TYPE;
pHeader->length = (UIntPtr)(bytes.Length / sizeof(float));
}
}
private static void toByteArray(this float[] floats)
{
fixed(void* pArray = floats)
{
var pHeader = getHeader(pArray);
pHeader->type = BYTE_ARRAY_TYPE;
pHeader->length = (UIntPtr)(floats.Length * sizeof(float));
}
}
}
And the usage is:
var floats = new float[] {0, 1, 0, 1};
floats.AsByteArray(bytes =>
{
foreach (var b in bytes)
{
Console.WriteLine(b);
}
});
Yes, the type information and data is in the same memory block, so that is impossible unless you overwrite the type information in a float array to fool the system that it's byte array. That would be a really ugly hack, and could easily blow up...
Here's how you can convert the floats without unsafe code if you like:
public static byte[] ToByteArray(this float[] floatArray) {
int len = floatArray.Length * 4;
byte[] byteArray = new byte[len];
int pos = 0;
foreach (float f in floatArray) {
byte[] data = BitConverter.GetBytes(f);
Array.Copy(data, 0, byteArray, pos, 4);
pos += 4;
}
return byteArray;
}
This question is the reverse of What is the fastest way to convert a float[] to a byte[]?.
I've answered with a union kind of hack to skip the whole copying of the data. You could easily reverse this (length = length *sizeof(Double).
I've written something similar for quick conversion between arrays. It's basically an ugly proof-of-concept more than a handsome solution. ;)
public static TDest[] ConvertArray<TSource, TDest>(TSource[] source)
where TSource : struct
where TDest : struct {
if (source == null)
throw new ArgumentNullException("source");
var sourceType = typeof(TSource);
var destType = typeof(TDest);
if (sourceType == typeof(char) || destType == typeof(char))
throw new NotSupportedException(
"Can not convert from/to a char array. Char is special " +
"in a somewhat unknown way (like enums can't be based on " +
"char either), and Marshal.SizeOf returns 1 even when the " +
"values held by a char can be above 255."
);
var sourceByteSize = Buffer.ByteLength(source);
var destTypeSize = Marshal.SizeOf(destType);
if (sourceByteSize % destTypeSize != 0)
throw new Exception(
"The source array is " + sourceByteSize + " bytes, which can " +
"not be transfered to chunks of " + destTypeSize + ", the size " +
"of type " + typeof(TDest).Name + ". Change destination type or " +
"pad the source array with additional values."
);
var destCount = sourceByteSize / destTypeSize;
var destArray = new TDest[destCount];
Buffer.BlockCopy(source, 0, destArray, 0, sourceByteSize);
return destArray;
}
}
public byte[] ToByteArray(object o)
{
int size = Marshal.SizeOf(o);
byte[] buffer = new byte[size];
IntPtr p = Marshal.AllocHGlobal(size);
try
{
Marshal.StructureToPtr(o, p, false);
Marshal.Copy(p, buffer, 0, size);
}
finally
{
Marshal.FreeHGlobal(p);
}
return buffer;
}
this may help you to convert an object to a byte array.
You should check my answer to a similar question: What is the fastest way to convert a float[] to a byte[]?.
In it you'll find portable code (32/64 bit compatible) to let you view a float array as a byte array or vice-versa, without copying the data. It's the fastest way that I know of to do such thing.
If you're just interested in the code, it's maintained at https://gist.github.com/1050703 .
Well - if you still interested in that hack - check out this modified code - it works like a charm and costs ~0 time, but it may not work in future since it's a hack allowing to gain full access to the whole process address space without trust requirements and unsafe marks.
[StructLayout(LayoutKind.Explicit)]
struct ArrayConvert
{
public static byte[] GetBytes(float[] floats)
{
ArrayConvert ar = new ArrayConvert();
ar.floats = floats;
ar.length.val = floats.Length * 4;
return ar.bytes;
}
public static float[] GetFloats(byte[] bytes)
{
ArrayConvert ar = new ArrayConvert();
ar.bytes = bytes;
ar.length.val = bytes.Length / 4;
return ar.floats;
}
public static byte[] GetTop4BytesFrom(object obj)
{
ArrayConvert ar = new ArrayConvert();
ar.obj = obj;
return new byte[]
{
ar.top4bytes.b0,
ar.top4bytes.b1,
ar.top4bytes.b2,
ar.top4bytes.b3
};
}
public static byte[] GetBytesFrom(object obj, int size)
{
ArrayConvert ar = new ArrayConvert();
ar.obj = obj;
ar.length.val = size;
return ar.bytes;
}
class ArrayLength
{
public int val;
}
class Top4Bytes
{
public byte b0;
public byte b1;
public byte b2;
public byte b3;
}
[FieldOffset(0)]
private Byte[] bytes;
[FieldOffset(0)]
private object obj;
[FieldOffset(0)]
private float[] floats;
[FieldOffset(0)]
private ArrayLength length;
[FieldOffset(0)]
private Top4Bytes top4bytes;
}