Develop Reference

C# Function to translate Binary-Code

Right now I try to write a C# Program to translate 8 Base Binary into Text.
But I guess I am not experienced enough with C# to truly make it Work.
I think the code I come up with, should, from a logical Point-of-View somewhat do what I want, but the Syntax isn't properly doing it, since don´t know it better.
This is what I have so far:
using System;
using System.Linq;
using System.Text;
class binaryTranslate
{
public int convertBin(string CodeInput)
{
int [] code = CodeInput.ToArray();
int CodeCount = code.ToString().Length;
int EightBaseSegAmount = CodeCount / 8;
int ByteCapacity = 8;
StringBuilder translated = new StringBuilder();
for (var i = 1; i < EightBaseSegAmount + 1; i++)
{
StringBuilder Byte = new StringBuilder(ByteCapacity);
int ByteStart = (i * 8) - 8;
int ByteEnd = (i * 8) - 1;
int ByteIncrement = 1;
for (var j = ByteStart ; j < ByteEnd + 1; j++)
{
Byte.Append(code[j]);
}
for (var k = 0; k > 7; k++)
{
int BitValue = 128;
if (Byte[k] == 1)
{
if (k > 0)
{
int Squared = Math.Pow(2, k);
ByteIncrement += BitValue / Squared;
}
else
{
ByteIncrement += BitValue;
}
}
}
char toSymbol = Convert.ToChar(ByteIncrement);
translated.Append(toSymbol);
}
return translated;
}
public static int Main()
{
convertBin("010010000110000101101100011011000110111100100001");
}
}

First of all, your code won't compile. Here are the errors/mistakes.
The first one is, at the first line of your function, you are converting the input string to an array using String.ToArray(), which returns a char[] but your try to assign it to a variable (code) typed int[]. You can solve this by replacing the int[] with either char[] or var.
The second one is, inside the second for loop (k = 0; k > 7), you use Math.Pow() and assign it's return value to an int variable (Squared). But Math.Pow returns double. You can solve this by casting the return value of Math.Pow to int. Like; int Squared = (int)Math.Pow(2, k);
The last thing is not easily solvable like the first two because, your code is not exactly correct. You are trying to return something called translated, which is a variable of type StringBuilder. But your function is defined to return an int.
Now these were compile errors. There are a bunch of logical and decision errors/mistakes. Your algorithm also isn't very correct.
Here is a sample code you can use/examine. I'd like to help you further, why your code was incorrect, what was your design mistakes etc. if you want to.
class binaryTranslate
{
public enum IncompleteSegmentBehavior
{
Skip = 0,
ZerosToStart = 1,
ZerosToEnd = 2
}
private byte ConvertBinstrToByte(string sequence)
{
if (string.IsNullOrEmpty(sequence))
return 0; // Throw?
if (sequence.Length != sizeof(byte) * 8)
return 0; // Throw?
const char zero = '0';
const char one = '1';
byte value = 0;
for (int i = 0; i < sequence.Length; i++)
{
if (sequence[i] != zero && sequence[i] != one)
return 0; // Throw
value |= (byte)((sequence[i] - zero) << (7 - i));
}
return value;
}
private string HandleIncompleteSegment(string segment, int segmentSize, IncompleteSegmentBehavior behavior)
{
string result = null;
var zeroAppender = new StringBuilder();
for (int i = 0; i < segmentSize - segment.Length; i++)
zeroAppender.Append('0');
var zeros = zeroAppender.ToString();
switch (behavior)
{
case IncompleteSegmentBehavior.Skip:
break;
case IncompleteSegmentBehavior.ZerosToStart:
result = zeros + result;
break;
case IncompleteSegmentBehavior.ZerosToEnd:
result = result + zeros;
break;
default:
break;
}
return result;
}
public byte[] ConvertBinstrToBytes(string binarySequence, IncompleteSegmentBehavior behavior = IncompleteSegmentBehavior.Skip)
{
var segmentSize = sizeof(byte) * 8;
var sequenceLength = binarySequence.Length;
var numberOfBytes = (int)Math.Ceiling((double)sequenceLength / segmentSize);
var bytes = new byte[numberOfBytes];
for (int i = 0; i < numberOfBytes; i++)
{
var charactersLeft = sequenceLength - i * segmentSize;
var segmentLength = (charactersLeft < segmentSize ? charactersLeft : segmentSize);
var segment = binarySequence.Substring(i * segmentSize, segmentLength);
if (charactersLeft < segmentSize)
{
segment = HandleIncompleteSegment(segment, segmentSize, behavior);
if (segment == null)
continue;
}
bytes[i] = ConvertBinstrToByte(segment);
}
return bytes;
}
}
This code passes these assertions.
var bytes = new binaryTranslate()
.ConvertBinstrToBytes("00000000");
Assert.Equal(bytes.Length, 1);
Assert.Equal(bytes[0], 0b00000000);
bytes = new binaryTranslate()
.ConvertBinstrToBytes("10000000");
Assert.Equal(bytes.Length, 1);
Assert.Equal(bytes[0], 0b10000000);
bytes = new binaryTranslate()
.ConvertBinstrToBytes("11111111");
Assert.Equal(bytes.Length, 1);
Assert.Equal(bytes[0], 0b11111111);
bytes = new binaryTranslate()
.ConvertBinstrToBytes("00000001");
Assert.Equal(bytes.Length, 1);
Assert.Equal(bytes[0], 0b00000001);
bytes = new binaryTranslate()
.ConvertBinstrToBytes("1100110000110011");
Assert.Equal(bytes.Length, 2);
Assert.Equal(bytes[0], 0b11001100);
Assert.Equal(bytes[1], 0b00110011);

If you are really converting to a string the code should look like this
namespace binaryTranslate
{
class Program
{
static void Main(string[] args)
{
//convertBin("01001000 01100001 01101100 01101100 01101111 00100001");
string results = BinaryTranslate.convertBin(new byte[] { 0x44, 0x61, 0x6c, 0x6c, 0x6f, 0x21 });
}
}
public class BinaryTranslate
{
public static string convertBin(byte[] CodeInput)
{
return string.Join("", CodeInput.Select(x => x.ToString("X2")));
}
}
}

this should do the trick.
public static string FromBinary(string binary)
{
int WordLength = 8;
binary = binary.Replace(' ', '');
while(binary.Length % WordLength != 0)
binary += "0";
string output = String.Empty;
string word = String.Empty;
int offset = 0;
while(offset < binary.Length)
{
int tmp = 0;
word = binary.Substring(offset, 8);
for(int i=0; i<(WordLength - 1); i++)
if(word[i] == '1')
tmp += (int) Math.Pow(2, i);
output += Convert.ToChar(tmp);
offset += WordLength;
}
return output;
}

Find byte sequence within a byte array

I have a byte array and wish to find the "occurrences" of some bytes.
For example 00 69 73 6F 6D in a very large byte array (> 50/100 Megabytes)
OR
even better a reverse operation: Searching the most common pattern without knowing it the code should be able to read and find it from the file.

You can use the Boyer-Moore algorithm to efficiently search for a sequence of bytes in an array of bytes.
Here's a C# version I converted from the Java version from the Wikipedia entry on Boyer-Moore.
public sealed class BoyerMoore
{
readonly byte[] needle;
readonly int[] charTable;
readonly int[] offsetTable;
public BoyerMoore(byte[] needle)
{
this.needle = needle;
this.charTable = makeByteTable(needle);
this.offsetTable = makeOffsetTable(needle);
}
public IEnumerable<int> Search(byte[] haystack)
{
if (needle.Length == 0)
yield break;
for (int i = needle.Length - 1; i < haystack.Length;)
{
int j;
for (j = needle.Length - 1; needle[j] == haystack[i]; --i, --j)
{
if (j != 0)
continue;
yield return i;
i += needle.Length - 1;
break;
}
i += Math.Max(offsetTable[needle.Length - 1 - j], charTable[haystack[i]]);
}
}
static int[] makeByteTable(byte[] needle)
{
const int ALPHABET_SIZE = 256;
int[] table = new int[ALPHABET_SIZE];
for (int i = 0; i < table.Length; ++i)
table[i] = needle.Length;
for (int i = 0; i < needle.Length - 1; ++i)
table[needle[i]] = needle.Length - 1 - i;
return table;
}
static int[] makeOffsetTable(byte[] needle)
{
int[] table = new int[needle.Length];
int lastPrefixPosition = needle.Length;
for (int i = needle.Length - 1; i >= 0; --i)
{
if (isPrefix(needle, i + 1))
lastPrefixPosition = i + 1;
table[needle.Length - 1 - i] = lastPrefixPosition - i + needle.Length - 1;
}
for (int i = 0; i < needle.Length - 1; ++i)
{
int slen = suffixLength(needle, i);
table[slen] = needle.Length - 1 - i + slen;
}
return table;
}
static bool isPrefix(byte[] needle, int p)
{
for (int i = p, j = 0; i < needle.Length; ++i, ++j)
if (needle[i] != needle[j])
return false;
return true;
}
static int suffixLength(byte[] needle, int p)
{
int len = 0;
for (int i = p, j = needle.Length - 1; i >= 0 && needle[i] == needle[j]; --i, --j)
++len;
return len;
}
}
Here's some console app test code for it:
public static void Main()
{
byte[] haystack = new byte[10000];
byte[] needle = { 0x00, 0x69, 0x73, 0x6F, 0x6D };
// Put a few copies of the needle into the haystack.
for (int i = 1000; i <= 9000; i += 1000)
Array.Copy(needle, 0, haystack, i, needle.Length);
var searcher = new BoyerMoore(needle);
foreach (int index in searcher.Search(haystack))
Console.WriteLine(index);
}
Note how the Search() method returns the indices of all the locations of the start of needle inside haystack.
If you just wanted the count, you could just do:
int count = new BoyerMoore(needle).Search(haystack).Count();
For your second question: I assume you are asking about finding the longest repeated sequence of bytes?
That's a much more complicated - and very different - question. If you want an answer for that, you should ask a separate question for it, but you should read the Wikipedia entry on the "longest repeated substring problem".

Compare string using bitwise shift operation

So i am new to csharp and i cant seem to find a logical error here in this program.i am learning the bitwise shift operators as i am new to these operators. I need help tracing a fault in my code. the program encodes an input String and decodes the encoded String after.After that i compare the string to see if they are equal.They seem to be equal to me but i keep getting a false when i compare them. Here is my code:
class Program
{
static char[] transcode = new char[64];
private static void prep()
{
for (int i = 0; i < transcode.Length; i++)
{
transcode[i] = (char)((int)'A' + i);
if (i > 25 && i <= 51)
{
transcode[i] = (char)((int)transcode[i] + 6);
}
else if (i > 51)
{
transcode[i] = (char)((int)transcode[i] - 0x4b);
}
}
transcode[transcode.Length - 3] = '+';
transcode[transcode.Length - 2] = '/';
transcode[transcode.Length - 1] = '=';
}
static void Main(string[] args)
{
prep();
string test_string = "a";
if (Convert.ToBoolean(String.Compare(test_string, decode(encode(test_string)))))
{
Console.WriteLine("Test succeeded");
}
else
{
Console.WriteLine("Test failed");
}
}
private static string encode(string input)
{
int l = input.Length;
int cb = (l / 3 + (Convert.ToBoolean(l % 3) ? 1 : 0)) * 4;// (0 +(1))*4 =4
char[] output = new char[cb];
for (int i = 0; i < cb; i++)
{
output[i] = '=';
}
int c = 0;
int reflex = 0;
const int s = 0x3f;
for (int j = 0; j < l; j++)
{
reflex <<= 8;
reflex &= 0x00ffff00;
reflex += input[j];
int x = ((j % 3) + 1) * 2;
int mask = s << x;
while (mask >= s)
{
int pivot = (reflex & mask) >> x;
output[c++] = transcode[pivot];
char alpha = transcode[pivot];
int invert = ~mask;
reflex &= invert;
mask >>= 6;
x -= 6; //-4
}
}
switch (l % 3)
{
case 1:
reflex <<= 4; //16
output[c++] = transcode[reflex];
char at16 = transcode[16];
// Console.WriteLine("Character at 16 is: " + at16);
break;
case 2:
reflex <<= 2;
output[c++] = transcode[reflex];
break;
}
return new string(output);//final value is: YQ== (Encoded String.)
}
private static string decode(string input)//input is YQ== which has a length of 4
{
int l = input.Length;
int cb = (l / 4 + ((Convert.ToBoolean(l % 4)) ? 1 : 0)) * 3 + 1; // (1 + (0))*4
char[] output = new char[cb]; //4 in length
int c = 0;
int bits = 0;
int reflex = 0;
for (int j = 0; j < l; j++)
{
reflex <<= 6;
bits += 6;
bool fTerminate = ('=' == input[j]);
if (!fTerminate)
{
reflex += indexOf(input[j]);
while (bits >= 8)
{
int mask = 0x000000ff << (bits % 8);
output[c++] = (char)((reflex & mask) >> (bits % 8)); //convert issue cannot implicitly convert to proper data type.so will have to explicitly convert.
int invert = ~mask;
reflex &= invert;
bits -= 8;
}
}
else
{
break;
}
}
return new string(output);
}
private static int indexOf(char ch)
{
int index;
for (index = 0; index < transcode.Length; index++)
if (ch == transcode[index])
break;
return index;
}
}

Read the docs for String.Compare then read the docs for Convert.ToBoolean. Pay particular attention to the value returned by String.Compare when two strings are equal. Then compare with how that value gets converted to a boolean by ToBoolean
String.Compare is designed for sorting strings. It returns 0 when two strings are equal. ToBoolean will convert that 0 to false. So when you strings are equal, your if evaluates to false and not true.
A simple change would be:
if (String.Compare(test_string, decode(encode(test_string)))==0)
{
Console.WriteLine("Test succeeded");
}
else
{
Console.WriteLine("Test failed");
}
#Tom's comment about the trailing nulls also applies, but it seems that String.Compare just ignores them.

Get longest substring between two strings

I have two words,
britanicaeng and
britanicahin
I need to find out the longest common word between these i.e, britanica.
How can I do this in C# ?

Try this method:
public static string FindLongestCommonSubstring(string s1, string s2)
{
int[,] a = new int[s1.Length + 1, s2.Length + 1];
int row = 0; // s1 index
int col = 0; // s2 index
for (var i = 0; i < s1.Length; i++)
for (var j = 0; j < s2.Length; j++)
if (s1[i] == s2[j])
{
int len = a[i + 1, j + 1] = a[i, j] + 1;
if (len > a[row, col])
{
row = i + 1;
col = j + 1;
}
}
return s1.Substring(row - a[row, col], a[row, col]);
}
Usage example:
Console.WriteLine(FindLongestCommonSubstring("britanicaeng", "britanicahin"));

I refactored the C++ code from Ashutosh Singh at https://iq.opengenus.org/longest-common-substring-using-rolling-hash/ to create a rolling hash approach in C# - this will find the substring in O(N * log(N)^2) time and O(N) space
using System;
using System.Collections.Generic;
public class RollingHash
{
private class RollingHashPowers
{
// _mod = prime modulus of polynomial hashing
// any prime number over a billion should suffice
internal const int _mod = (int)1e9 + 123;
// _hashBase = base (point of hashing)
// this should be a prime number larger than the number of characters used
// in my use case I am only interested in ASCII (256) characters
// for strings in languages using non-latin characters, this should be much larger
internal const long _hashBase = 257;
// _pow1 = powers of base modulo mod
internal readonly List<int> _pow1 = new List<int> { 1 };
// _pow2 = powers of base modulo 2^64
internal readonly List<long> _pow2 = new List<long> { 1L };
internal void EnsureLength(int length)
{
if (_pow1.Capacity < length)
{
_pow1.Capacity = _pow2.Capacity = length;
}
for (int currentIndx = _pow1.Count - 1; currentIndx < length; ++currentIndx)
{
_pow1.Add((int)(_pow1[currentIndx] * _hashBase % _mod));
_pow2.Add(_pow2[currentIndx] * _hashBase);
}
}
}
private class RollingHashedString
{
readonly RollingHashPowers _pows;
readonly int[] _pref1; // Hash on prefix modulo mod
readonly long[] _pref2; // Hash on prefix modulo 2^64
// Constructor from string:
internal RollingHashedString(RollingHashPowers pows, string s, bool caseInsensitive = false)
{
_pows = pows;
_pref1 = new int[s.Length + 1];
_pref2 = new long[s.Length + 1];
const long capAVal = 'A';
const long capZVal = 'Z';
const long aADif = 'a' - 'A';
unsafe
{
fixed (char* c = s)
{
// Fill arrays with polynomial hashes on prefix
for (int i = 0; i < s.Length; ++i)
{
long v = c[i];
if (caseInsensitive && capAVal <= v && v <= capZVal)
{
v += aADif;
}
_pref1[i + 1] = (int)((_pref1[i] + v * _pows._pow1[i]) % RollingHashPowers._mod);
_pref2[i + 1] = _pref2[i] + v * _pows._pow2[i];
}
}
}
}
// Rollingnomial hash of subsequence [pos, pos+len)
// If mxPow != 0, value automatically multiply on base in needed power.
// Finally base ^ mxPow
internal Tuple<int, long> Apply(int pos, int len, int mxPow = 0)
{
int hash1 = _pref1[pos + len] - _pref1[pos];
long hash2 = _pref2[pos + len] - _pref2[pos];
if (hash1 < 0)
{
hash1 += RollingHashPowers._mod;
}
if (mxPow != 0)
{
hash1 = (int)((long)hash1 * _pows._pow1[mxPow - (pos + len - 1)] % RollingHashPowers._mod);
hash2 *= _pows._pow2[mxPow - (pos + len - 1)];
}
return Tuple.Create(hash1, hash2);
}
}
private readonly RollingHashPowers _rhp;
public RollingHash(int longestLength = 0)
{
_rhp = new RollingHashPowers();
if (longestLength > 0)
{
_rhp.EnsureLength(longestLength);
}
}
public string FindCommonSubstring(string a, string b, bool caseInsensitive = false)
{
// Calculate max neede power of base:
int mxPow = Math.Max(a.Length, b.Length);
_rhp.EnsureLength(mxPow);
// Create hashing objects from strings:
RollingHashedString hash_a = new RollingHashedString(_rhp, a, caseInsensitive);
RollingHashedString hash_b = new RollingHashedString(_rhp, b, caseInsensitive);
// Binary search by length of same subsequence:
int pos = -1;
int low = 0;
int minLen = Math.Min(a.Length, b.Length);
int high = minLen + 1;
var tupleCompare = Comparer<Tuple<int, long>>.Default;
while (high - low > 1)
{
int mid = (low + high) / 2;
List<Tuple<int, long>> hashes = new List<Tuple<int, long>>(a.Length - mid + 1);
for (int i = 0; i + mid <= a.Length; ++i)
{
hashes.Add(hash_a.Apply(i, mid, mxPow));
}
hashes.Sort(tupleCompare);
int p = -1;
for (int i = 0; i + mid <= b.Length; ++i)
{
if (hashes.BinarySearch(hash_b.Apply(i, mid, mxPow), tupleCompare) >= 0)
{
p = i;
break;
}
}
if (p >= 0)
{
low = mid;
pos = p;
}
else
{
high = mid;
}
}
// Output answer:
return pos >= 0
? b.Substring(pos, low)
: string.Empty;
}
}

Java Integer.ValueOf method equivalence in C# With Radix Parameter

My task is to migrate this Java code to a C# version, but I'm having trouble with the ValueOf method, since I can't seem to find a equivalent version for C# (because of the Radix parameter used on Java, 16 in this case).
public String decrypt_string(String s)
{
String s1 = "";
int i = s.length() / 2;
int[] ai = new int[i];
for (int j = 0; j < i; j++)
{
// This is the "problematic" line \/
ai[j] = Integer.valueOf(s.substring(j * 2, j * 2 + 2), 16).intValue();
}
int[] ai1 = decrypt_block(ai, i);
for (int k = 0; k < i; k++)
{
if (ai1[k] != 0)
s1 = s1 + (char)ai1[k];
}
return s1;
}
Here is my try, but it failed:
public String decrypt_string(String s)
{
String s1 = "";
int i = s.Length / 2;
int[] ai = new int[i];
for (int j = 0; j < i; j++)
{
int startIndex = j * 2;
string tmp = s.Substring(startIndex, 2);
ai[j] = Int32.Parse (tmp);
}
int[] ai1 = decrypt_block(ai, i);
for (int k = 0; k < i; k++)
{
if (ai1[k] != 0)
s1 = s1 + (char)ai1[k];
}
return s1;
}
Thanks in advance

If you are trying to parse a hexadecimal (base-16) number, use this:
int.Parse (tmp, NumberStyles.HexNumber);

You need to convert a string to an integer, given that the string is in a specific base.
int i = Convert.ToInt32(str, 16);
int j = Convert.ToInt32("A", 16); // 10
So:
for (int j = 0; j < i; j++)
{
int startIndex = j * 2;
ai[j] = Convert.ToInt32(s.Substring(startIndex, 2));
}

The radix is on Integer.valueOf(), not s.substring() in the java code you show there, so this would become:
ai[j] = Int32.Parse(s.Substring(j * 2, j * 2 + 2), 16);