advance C# string comparison - c#

Is there any class (function) in .Net that can do this:
if
s1 = " I have a black car" and s2 = "I have a car that is small";
int matchingProcentage = matchingFunction(s1,s2);
matchingProcentage == 70% <-- just as an example value :)

Here's a good way of going about it!
Levenshtein Distance

A function like the following should work, it was hastily written so feel free to change things up:
Usage:
GetStringPercentage("I have a black car", "I have a car that is small");
Method:
public static decimal GetStringPercentage(string s1, string s2)
{
decimal matches = 0.0m;
List<string> s1Split = s1.Split(' ').ToList();
List<string> s2Split = s2.Split(' ').ToList();
if (s1Split.Count() > s2Split.Count())
{
foreach (string s in s1Split)
if (s2Split.Any(st => st == s))
matches++;
return (matches / s1Split.Count());
}
else
{
foreach (string s in s2Split)
if (s1Split.Any(st => st == s))
matches++;
return (matches / s2Split.Count());
}
}

you can use Levenshtein Distance algorithm

Using the code found at http://www.dotnetperls.com/levenshtein as a base, I modified it to return a % instead of a number:
public static int Compute(string word1, string word2)
{
int n = word1.Length;
int m = word2.Length;
int[,] d = new int[n + 1, m + 1];
// Step 1
if (n == 0)
{
return m;
}
if (m == 0)
{
return n;
}
// Step 2
for (int i = 0; i <= n; d[i, 0] = i++)
{
}
for (int j = 0; j <= m; d[0, j] = j++)
{
}
// Step 3
for (int i = 1; i <= n; i++)
{
//Step 4
for (int j = 1; j <= m; j++)
{
// Step 5
int cost = (word2[j - 1] == word1[i - 1]) ? 0 : 1;
// Step 6
d[i, j] = Math.Min(
Math.Min(d[i - 1, j] + 1, d[i, j - 1] + 1),
d[i - 1, j - 1] + cost);
}
}
// Step 7
decimal changesRequired = d[n, m];
//Find the longest word and calculate the percentage equality
if (word1.Length > word2.Length)
return Convert.ToInt32(100 - (changesRequired / word1.Length) * 100);
else
return Convert.ToInt32(100 - (changesRequired / word2.Length) * 100);
}
Hope this helps.

No, there's not. You'd have to implement your own.

Just a suggestion, but would you be able to take both strings and compare character to character and define a percentage based on the number of matching characters?

try this:
public static int MatchingFunction(string s1, string s2, bool duplicate, bool keySensitive)
{
if (!keySensitive)
{
s1 = s1.ToLower();
s2 = s2.ToLower();
}
List<string> ls1 = null;
s2 = s2.Trim();
if (duplicate)
{
ls1 = s1.Trim().Split(' ').ToList();
}
else
{
ls1 = new List<string>();
string[] as1 = s1.Trim().Split(' ');
foreach (string s in as1)
if (!ls1.Contains(s))
ls1.Add(s);
string[] as2 = s2.Trim().Split(' ');
s2 = string.Empty;
foreach (string s in as2)
if (!s2.Contains(s))
s2 = string.Format("{0} {1}", s2, s);
}
int has = 0;
s2 = string.Format("#{0}#", s2.Replace(' ', '#');
foreach (string s in ls1)
has += s2.Contains(string.Format("#{0}#", s)) ? 1 : 0;
return (has * 100 / ls1.Count());
}
string s1 = " I have a black car";
string s2 = "I have a car that is small";
int p = MatchingFunction(s1, s2, false, false);

Related

C# implementation of Ascii Minimum Delete Distance

How do you implement the ASCII Minimum Delete Distance in C#?
See description here with a Python solution.
Deletion distance between 2 strings
I derived the C# solution from this Java solution.
https://leetcode.com/articles/minimum-ascii-delete-sum-for-two-strings/#
static void TestAscMinDelDist()
{
List<string[]> l = new List<string[]> {
new string[]{"cat", "at", "99"},
new string[]{"aunt","ant", "117"},
new string[]{"sea", "eat", "231"},
new string[]{"boat", "got", "298"},,
new string[]{"toradol", "tramadol", "317"},
new string[]{"tattoo","platoon", "562"},
new string[]{"delete", "leet", "403"},
new string[]{"flomax", "volmax", "436"},
new string[]{"clozapine", "olanzapine", "522"},
new string[]{"Sam", "Samantha", "524"},
new string[]{"kitten", "sitting", "531" },
new string[]{"sloughs", "thought", "674"}, };
foreach (string[] a in l) {
CalcPrint(a[0], a[1], a[2]);
CalcPrint(a[1], a[0], a[2]);
}
}
static int AsciiMinimumDeleteDistance(String s1, String s2) {
int s1Len = s1.Length, s2Len = s2.Length;
int[,] dp = new int[s1Len + 1, s2Len + 1];
for (int i = s1Len - 1; i >= 0; i--) {
dp[i, s2Len] = dp[i + 1, s2Len] + (int)s1[i]; }
for (int j = s2Len - 1; j >= 0; j--) {
dp[s1Len, j] = dp[s1Len, j+1] + (int)s2[j]; }
for (int i = s1Len - 1; i >= 0; i--) {
for (int j = s2Len - 1; j >= 0; j--) {
if (s1[i] == s2[j]) {
dp[i, j] = dp[i+1, j+1];
} else {
dp[i, j] = Math.Min(dp[i+1, j] + (int)s1[i],
dp[i, j+1] + (int)s2[j]);
}
}
}
return dp[0,0];
}
static void CalcPrint(string s1, string s2, string s3)
{
int cost = AsciiMinimumDeleteDistance(s1, s2);
string result = cost == int.Parse(s3) ? "Passed" : "Failed: Expected: " + s3;
Console.WriteLine($"{s1} -> {s2} {cost} \t {result}");
}

how can i find lcs length between two large strings

I've written the following code in C# for obtaining the length of longest common subsequence of two texts given by use, but it doesn't work with large strings. Could you please help me. I'm really confused.
public Form1()
{
InitializeComponent();
}
public int lcs(char[] s1, char[] s2, int s1size, int s2size)
{
if (s1size == 0 || s2size == 0)
{
return 0;
}
else
{
if (s1[s1size - 1] == s2[s2size - 1])
{
return (lcs(s1, s2, s1size - 1, s2size - 1) + 1);
}
else
{
int x = lcs(s1, s2, s1size, s2size - 1);
int y = lcs(s1, s2, s1size - 1, s2size);
if (x > y)
{
return x;
}
else
return y;
}
}
}
private void button1_Click(object sender, EventArgs e)
{
string st1 = textBox2.Text.Trim(' ');
string st2 = textBox3.Text.Trim(' ');
char[] a = st1.ToCharArray();
char[] b = st2.ToCharArray();
int s1 = a.Length;
int s2 = b.Length;
textBox1.Text = lcs(a, b, s1, s2).ToString();
}
Here you are using the Recursion method. So it leads the program to occur performance problems as you mentioned.
Instead of recursion, use the dynamic programming approach.
Here is the C# Code.
public static void LCS(char[] str1, char[] str2)
{
int[,] l = new int[str1.Length, str2.Length];
int lcs = -1;
string substr = string.Empty;
int end = -1;
for (int i = 0; i < str1.Length; i++)
{
for (int j = 0; j < str2.Length; j++)
{
if (str1[i] == str2[j])
{
if (i == 0 || j == 0)
{
l[i, j] = 1;
}
else
l[i, j] = l[i - 1, j - 1] + 1;
if (l[i, j] > lcs)
{
lcs = l[i, j];
end = i;
}
}
else
l[i, j] = 0;
}
}
for (int i = end - lcs + 1; i <= end; i++)
{
substr += str1[i];
}
Console.WriteLine("Longest Common SubString Length = {0}, Longest Common Substring = {1}", lcs, substr);
}
Here is a solution how to find the longest common substring in C#:
public static string GetLongestCommonSubstring(params string[] strings)
{
var commonSubstrings = new HashSet<string>(strings[0].GetSubstrings());
foreach (string str in strings.Skip(1))
{
commonSubstrings.IntersectWith(str.GetSubstrings());
if (commonSubstrings.Count == 0)
return string.Empty;
}
return commonSubstrings.OrderByDescending(s => s.Length).DefaultIfEmpty(string.Empty).First();
}
private static IEnumerable<string> GetSubstrings(this string str)
{
for (int c = 0; c < str.Length - 1; c++)
{
for (int cc = 1; c + cc <= str.Length; cc++)
{
yield return str.Substring(c, cc);
}
}
}
I found it here: http://www.snippetsource.net/Snippet/75/longest-common-substring
Just for fun, here is one example using Queue<T>:
string LongestCommonSubstring(params string[] strings)
{
return LongestCommonSubstring(strings[0], new Queue<string>(strings.Skip(1)));
}
string LongestCommonSubstring(string x, Queue<string> strings)
{
if (!strings.TryDequeue(out var y))
{
return x;
}
var output = string.Empty;
for (int i = 0; i < x.Length; i++)
{
for (int j = x.Length - i; j > -1; j--)
{
string common = x.Substring(i, j);
if (y.IndexOf(common) > -1 && common.Length > output.Length) output = common;
}
}
return LongestCommonSubstring(output, strings);
}
It's still using recursion though, but it's a nice example of Queue<T>.
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;
}
}

Regex or string compare with allowance of error

I'm trying to do a string compare in C# with some allowance for error. For example, if my search term is "Welcome", but if my comparison string (generated through OCR) is "We1come" and my error allowance is 20%, that should match. That part isn't so difficult using something like the Levenshtein algorithm. The hard part is making it work within a larger block of text, like a regular expression. For example, maybe my OCR result is "Hello. My name is Ben. We1come to my StackOverflow question.", I would like to pick out that We1come as a good result compared to my search term.
Took quite a while, but this works well. Fun problem :)
string PossibleString = PossibleString.ToString().ToLower();
string StaticText = StaticText.ToLower();
decimal PossibleStringLength = (PossibleString.Length);
decimal StaticTextLength = (StaticText.Length);
decimal NumberOfErrorsAllowed = Math.Round((StaticTextLength * (ErrorAllowance / 100)), MidpointRounding.AwayFromZero);
int LevenshteinDistance = LevenshteinAlgorithm(StaticText, PossibleString);
string PossibleResult = string.Empty;
if (LevenshteinDistance == PossibleStringLength - StaticTextLength)
{
// Perfect match. no need to calculate.
PossibleResult = StaticText;
}
else
{
int TextLengthBuffer = (int)StaticTextLength - 1;
int LowestLevenshteinNumber = 999999;
for (int i = 0; i < 3; i++) // Check for best results with same amount of characters as expected, as well as +/- 1
{
for (int e = TextLengthBuffer; e <= (int)PossibleStringLength; e++)
{
string possibleResult = (PossibleString.Substring((e - TextLengthBuffer), TextLengthBuffer));
int lAllowance = (int)(Math.Round((possibleResult.Length - StaticTextLength) + (NumberOfErrorsAllowed), MidpointRounding.AwayFromZero));
int lNumber = LevenshteinAlgorithm(StaticText, possibleResult);
if (lNumber <= lAllowance && ((lNumber < LowestLevenshteinNumber) || (TextLengthBuffer == StaticText.Length && lNumber <= LowestLevenshteinNumber)))
{
PossibleResult = possibleResult;
LowestLevenshteinNumber = lNumber;
}
}
TextLengthBuffer++;
}
}
public static int LevenshteinAlgorithm(string s, string t)
{
int n = s.Length;
int m = t.Length;
int[,] d = new int[n + 1, m + 1];
if (n == 0)
{
return m;
}
if (m == 0)
{
return n;
}
for (int i = 0; i <= n; d[i, 0] = i++)
{
}
for (int j = 0; j <= m; d[0, j] = j++)
{
}
for (int i = 1; i <= n; i++)
{
for (int j = 1; j <= m; j++)
{
int cost = (t[j - 1] == s[i - 1]) ? 0 : 1;
d[i, j] = Math.Min(
Math.Min(d[i - 1, j] + 1, d[i, j - 1] + 1),
d[i - 1, j - 1] + cost);
}
}
return d[n, m];
}
If it is somehow predictable how the OCR can miss letters, I would replace the letters in the search with misses.
If the search is Welcome, the regex would be (?i)We[l1]come.

How to add or subtract very large numbers without bigint in C#?

So let me start by saying that I'm a newbie with little to moderate knowledge about C#.
Coming to the topic: I need to make a program that is able to add/subtract very large integers. Initially, used BigInt only to find out it's not allowed. There should be a logical workaround for this? I have an idea which is using "elementary school method" where you add each digit starting from right to left.
I made a string which I split into char array and added each digit from right to left(GetUpperBound-i). But it doesn't seem to work.
My Code:
string s, s2;
char[] c_arr, c_arr2;
int i, erg;
s = "1234";
s2 = "5678";
c_arr = s.ToCharArray();
c_arr2 = s2.ToCharArray();
for (i = 0; i <= c_arr.GetUpperBound(0); i++)
{
erg = c_arr[c_arr.GetUpperBound(0)-i]+c_arr2[c_arr2.GetUpperBound(0)-i];
Console.Write(erg);
}
Console.ReadKey();
There are a few things wrong with your code for the 'elementary school method'. You don't account for carry, you're adding up ascii values rather than actual values between 0-9, and you're outputting the results in the wrong order.
The code below, whilst not very elegant, does produce the correct results:
var s1 = "12345";
var s2 = "5678";
var carry = false;
var result = String.Empty;
if(s1.Length != s2.Length)
{
var diff = Math.Abs(s1.Length - s2.Length);
if(s1.Length < s2.Length)
{
s1 = String.Join("", Enumerable.Repeat("0", diff)) + s1;
}
else
{
s2 = String.Join("", Enumerable.Repeat("0", diff)) + s2;
}
}
for(int i = s1.Length-1;i >= 0; i--)
{
var augend = Convert.ToInt32(s1.Substring(i,1));
var addend = Convert.ToInt32(s2.Substring(i,1));
var sum = augend + addend;
sum += (carry ? 1 : 0);
carry = false;
if(sum > 9)
{
carry = true;
sum -= 10;
}
result = sum.ToString() + result;
}
if(carry)
{
result = "1" + result;
}
Console.WriteLine(result);
The following program can be used to add two large numbers, I have used string builder to store the result. You can add numbers containing digits upto '2,147,483,647'.
Using System;
using System.Text;
using System.Linq;
public class Test
{
public static void Main()
{
string term1="15245142151235123512352362362352351236";
string term2="1522135123612646436143613461344";
StringBuilder sum=new StringBuilder();
int n1=term1.Length;
int n2=term2.Length;
int carry=0;
int n=(n1>n2)?n1:n2;
if(n1>n2)
term2=term2.PadLeft(n1,'0');
else
term1=term1.PadLeft(n2,'0');
for(int i=n-1;i>=0;i--)
{
int value=(carry+term1[i]-48+term2[i]-48)%10;
sum.Append(value);
carry=(carry+term1[i]-48+term2[i]-48)/10;
}
char[] c=sum.ToString().ToCharArray();
Array.Reverse(c);
Console.WriteLine(c);
}
}
string Add(string s1, string s2)
{
bool carry = false;
string result = string.Empty;
if(s1[0] != '-' && s2[0] != '-')
{
if (s1.Length < s2.Length)
s1 = s1.PadLeft(s2.Length, '0');
if(s2.Length < s1.Length)
s2 = s2.PadLeft(s1.Length, '0');
for(int i = s1.Length-1; i >= 0; i--)
{
var augend = Convert.ToInt64(s1.Substring(i,1));
var addend = Convert.ToInt64(s2.Substring(i,1));
var sum = augend + addend;
sum += (carry ? 1 : 0);
carry = false;
if(sum > 9)
{
carry = true;
sum -= 10;
}
result = sum.ToString() + result;
}
if(carry)
{
result = "1" + result;
}
}
else if(s1[0] == '-' || s2[0] == '-')
{
long sum = 0;
if(s2[0] == '-')
{
//Removing negative sign
char[] MyChar = {'-'};
string NewString = s2.TrimStart(MyChar);
s2 = NewString;
if(s2.Length < s1.Length)
s2 = s2.PadLeft(s1.Length, '0');
for (int i = s1.Length - 1; i >= 0; i--)
{
var augend = Convert.ToInt64(s1.Substring(i,1));
var addend = Convert.ToInt64(s2.Substring(i,1));
if(augend >= addend)
{
sum = augend - addend;
}
else
{
int temp = i - 1;
long numberNext = Convert.ToInt64(s1.Substring(temp,1));
//if number before is 0
while(numberNext == 0)
{
temp--;
numberNext = Convert.ToInt64(s1.Substring(temp,1));
}
//taking one from the neighbor number
int a = int.Parse(s1[temp].ToString());
a--;
StringBuilder tempString = new StringBuilder(s1);
string aString = a.ToString();
tempString[temp] = Convert.ToChar(aString);
s1 = tempString.ToString();
while(temp < i)
{
temp++;
StringBuilder copyS1 = new StringBuilder(s1);
string nine = "9";
tempString[temp] = Convert.ToChar(nine);
s1 = tempString.ToString();
}
augend += 10;
sum = augend - addend;
}
result = sum.ToString() + result;
}
//Removing the zero infront of the answer
char[] zeroChar = {'0'};
string tempResult = result.TrimStart(zeroChar);
result = tempResult;
}
}
return result;
}
string Multiply(string s1, string s2)
{
string result = string.Empty;
//For multipication
bool Negative = false;
if(s1[0] == '-' && s2[0] == '-')
Negative = false;
else if(s1[0] == '-' || s2[0] == '-')
Negative = true;
char[] minusChar = {'-'};
string NewString;
NewString = s2.TrimStart(minusChar);
s2 = NewString;
NewString = s1.TrimStart(minusChar);
s1 = NewString;
List<string> resultList = new List<string>();
for(int i = s2.Length - 1; i >= 0; i--)
{
string multiplycation = string.Empty;
for (int j = s1.Length - 1; j >= 0; j--)
{
var augend = Convert.ToInt64(s1.Substring(j,1));
var addend = Convert.ToInt64(s2.Substring(i,1));
long multiply = augend * addend;
// print(multiply);
multiplycation = multiply.ToString() + multiplycation;
}
//Adding zero at the end of the multiplication
for (int k = s2.Length - 1 - i; k > 0; k--)
{
multiplycation += "0";
}
resultList.Add(multiplycation);
}
for (int i = 1; i < resultList.Count; i++)
{
resultList[0] = Add(resultList[0],resultList[i]);
}
//Finally assigning if negative negative sign in front of the number
if(Negative)
result = resultList[0].Insert(0,"-");
else
result = resultList[0];
return result;
}
string Divide(string dividend, string divisor)
{
string result = string.Empty;
int remainder = 0;
int intNumberstoGet = divisor.Length;
int currentInt = 0;
int dividing = int.Parse(dividend.Substring(currentInt,intNumberstoGet));
int intDivisor = int.Parse(divisor);
while(currentInt < dividend.Length)
{
if(dividing == 0)
{
currentInt++;
result += "0";
}
else
{
while(dividing < intDivisor)
{
intNumberstoGet++;
dividing = int.Parse(dividend.Substring(currentInt,intNumberstoGet));
}
if (dividing > 0)
{
remainder = dividing % intDivisor;
result += ((dividing - remainder) / intDivisor).ToString();
intNumberstoGet = 1;
if(currentInt < dividend.Length - 2)
currentInt += 2;
else
currentInt++;
if(currentInt != dividend.Length)
{
dividing = int.Parse(dividend.Substring(currentInt,intNumberstoGet));
remainder *= 10;
dividing += remainder;
}
}
}
}
return result;
}
Here you go. Another example. It's 10 to 30 times faster than the accepted answer.
static string AddNumStr(string v1, string v2)
{
var v1Len = v1.Length;
var v2Len = v2.Length;
var count = Math.Max(v1Len, v2Len);
var answ = new char[count + 1];
while (count >= 0) answ[count--] = (char)((v1Len > 0 ? v1[--v1Len] & 0xF:0) + (v2Len>0 ? v2[--v2Len]&0xF : 0));
for (var i = answ.Length - 1; i >= 0; i--)
{
if (answ[i] > 9)
{
answ[i - 1]++;
answ[i] -= (char)10;
}
answ[i] = (char)(answ[i] | 48);
}
return new string(answ).TrimStart('0');
}
Below SO question has some interesting approaches. Though the answer is in Java, but you will surely get to know what needs to be done.
How to handle very large numbers in Java without using java.math.BigInteger
public static int[] addTwoNumbers(string s1, string s2)
{
char[] num1 = s1.ToCharArray();
char[] num2 = s2.ToCharArray();
int sum = 0;
int carry = 0;
int size = (s1.Length > s2.Length) ? s1.Length + 1 : s2.Length + 1;
int[] result = new int[size];
int index = size - 1;
int num1index = num1.Length - 1;
int num2index = num2.Length - 1;
while (true)
{
if (num1index >= 0 && num2index >= 0)
{
sum = (num1[num1index]-'0') + (num2[num2index]-'0') + carry;
}
else if(num1index< 0 && num2index >= 0)
{
sum = (num2[num2index]-'0') + carry;
}
else if (num1index >= 0 && num2index < 0)
{
sum = (num1[num1index]-'0') + carry;
}
else { break; }
carry = sum /10;
result[index] = sum % 10;
index--;
num1index--;
num2index--;
}
if(carry>0)
{
result[index] = carry;
}
return result;
}

Compare string similarity

What is the best way to compare two strings to see how similar they are?
Examples:
My String
My String With Extra Words
Or
My String
My Slightly Different String
What I am looking for is to determine how similar the first and second string in each pair is. I would like to score the comparison and if the strings are similar enough, I would consider them a matching pair.
Is there a good way to do this in C#?
static class LevenshteinDistance
{
public static int Compute(string s, string t)
{
if (string.IsNullOrEmpty(s))
{
if (string.IsNullOrEmpty(t))
return 0;
return t.Length;
}
if (string.IsNullOrEmpty(t))
{
return s.Length;
}
int n = s.Length;
int m = t.Length;
int[,] d = new int[n + 1, m + 1];
// initialize the top and right of the table to 0, 1, 2, ...
for (int i = 0; i <= n; d[i, 0] = i++);
for (int j = 1; j <= m; d[0, j] = j++);
for (int i = 1; i <= n; i++)
{
for (int j = 1; j <= m; j++)
{
int cost = (t[j - 1] == s[i - 1]) ? 0 : 1;
int min1 = d[i - 1, j] + 1;
int min2 = d[i, j - 1] + 1;
int min3 = d[i - 1, j - 1] + cost;
d[i, j] = Math.Min(Math.Min(min1, min2), min3);
}
}
return d[n, m];
}
}
If anyone was wondering what the C# equivalent of what #FrankSchwieterman posted is:
public static int GetDamerauLevenshteinDistance(string s, string t)
{
if (string.IsNullOrEmpty(s))
{
throw new ArgumentNullException(s, "String Cannot Be Null Or Empty");
}
if (string.IsNullOrEmpty(t))
{
throw new ArgumentNullException(t, "String Cannot Be Null Or Empty");
}
int n = s.Length; // length of s
int m = t.Length; // length of t
if (n == 0)
{
return m;
}
if (m == 0)
{
return n;
}
int[] p = new int[n + 1]; //'previous' cost array, horizontally
int[] d = new int[n + 1]; // cost array, horizontally
// indexes into strings s and t
int i; // iterates through s
int j; // iterates through t
for (i = 0; i <= n; i++)
{
p[i] = i;
}
for (j = 1; j <= m; j++)
{
char tJ = t[j - 1]; // jth character of t
d[0] = j;
for (i = 1; i <= n; i++)
{
int cost = s[i - 1] == tJ ? 0 : 1; // cost
// minimum of cell to the left+1, to the top+1, diagonally left and up +cost
d[i] = Math.Min(Math.Min(d[i - 1] + 1, p[i] + 1), p[i - 1] + cost);
}
// copy current distance counts to 'previous row' distance counts
int[] dPlaceholder = p; //placeholder to assist in swapping p and d
p = d;
d = dPlaceholder;
}
// our last action in the above loop was to switch d and p, so p now
// actually has the most recent cost counts
return p[n];
}
I am comparing two sentences like this
string[] vs = string1.Split(new char[] { ' ', '-', '/', '(', ')' },StringSplitOptions.RemoveEmptyEntries);
string[] vs1 = string2.Split(new char[] { ' ', '-', '/', '(', ')' }, StringSplitOptions.RemoveEmptyEntries);
vs.Intersect(vs1, StringComparer.OrdinalIgnoreCase).Count();
Intersect gives you a set of identical word lists , I continue by looking at the count and saying if it is more than 1, these two sentences contain similar words.

Categories