How can you remove duplicate characters in a string?

Question

I have to implements a function that takes a string as an input and finds the non-duplicate character from this string.

So an an example is if I pass string str = "DHCD" it will return "DHC" or str2 = "KLKLHHMO" it will return "KLHMO"

Answer 1

A Linq approach:

public static string RemoveDuplicates(string input)
{
    return new string(input.ToCharArray().Distinct().ToArray());
}

Answer 2

It will do the job

string removedupes(string s)
{
    string newString = string.Empty;
    List<char> found = new List<char>();
    foreach(char c in s)
    {
       if(found.Contains(c))
          continue;

       newString+=c.ToString();
       found.Add(c);
    }
    return newString;
}

I should note this is criminally inefficient.

I think I was delirious on first revision.

Answer 3

For arbitrary length strings of byte-sized characters (not for wide characters or other encodings), I would use a lookup table, one bit per character (32 bytes for a 256-bit table). Loop through your string, only output characters that don't have their bits turned on, then turn the bit on for that character.

string removedupes(string s)
{
    string t;
    byte[] found = new byte[256];
    foreach(char c in s)
    {
        if(!found[c]) {
            t.Append(c);
            found[c]=1;
        }
    }
    return t;
}

I am not good with C#, so I don't know the right way to use a bitfield instead of a byte array.

If you know that your strings are going to be very short, then other approaches would offer better memory usage and/or speed.

Answer 4

    void removeDuplicate()
    {
      string value1 = RemoveDuplicateChars("Devarajan");
    }

     static string RemoveDuplicateChars(string key)
    {
        string result = "";          
        foreach (char value in key)
            if (result.IndexOf(value) == -1)                   
                result += value;
        return result;
    }

Answer 5

It sounds like homework to me, so I'm just going to describe at a high level.

• Loop over the string, examining each character
• Check if you've seen the character before
  • if you have, remove it from the string
  • if you haven't, note that you've now seen that character

Answer 6

this is in C#. validation left out for brevity. primitive solution for removing duplicate chars from a given string

    public static char[] RemoveDup(string s)
    {
        char[] chars = new char[s.Length];
        int unique = 0;
        chars[unique] = s[0];  // Assume: First char is unique
        for (int i = 1; i < s.Length; i++)
        {
            // add char in i index to unique array 
            // if char in i-1 != i index
            // i.e s = "ab" -> a != b
            if (s[i-1] != s[i]
            chars[++unique] = s[i];
        }
        return chars;
    }

Answer 7

you may use HashSet:

 static void Main()
    {
        string textWithDuplicates = "aaabbcccggg";

        Console.WriteLine(textWithDuplicates.Count());  
        var letters = new HashSet<char>(textWithDuplicates);
        Console.WriteLine(letters.Count());

        foreach (char c in letters) Console.Write(c);   
    }

Answer 8

 class Program
    {
        static void Main(string[] args)
        {
            bool[] doesExists = new bool[256];
            String st = Console.ReadLine();
            StringBuilder sb = new StringBuilder();
            foreach (char ch in st)
            {
                if (!doesExists[ch])
                {
                    sb.Append(ch);
                    doesExists[ch] = true;
                }
            }
            Console.WriteLine(sb.ToString());
        }
    }

Answer 9

My answer in java language.
Posting here so that you might get a idea even it is in Java language.Algorithm would remain same.

public String removeDup(String s)
  {
    if(s==null) return null;
    int l = s.length();
    //if length is less than 2 return string
    if(l<2)return s;
    char arr[] = s.toCharArray();

    for(int i=0;i<l;i++)
    {
      int j =i+1; //index to check with ith index
      int t = i+1; //index of first repetative char.

      while(j<l)
      {
        if(arr[j]==arr[i])
        {
          j++;

        }
        else
        {
          arr[t]=arr[j];
          t++;
          j++;
        }

      }
      l=t;
    }

    return new String(arr,0,l);
  }

Answer 10

Revised version of the first answer i.e: You don't need ToCharArray() function for this to work.

public static string RemoveDuplicates(string input)
{
    return new string(input.Distinct().ToArray());
}

Answer 11

// Remove both upper-lower duplicates

public static string RemoveDuplicates(string key)
    {
        string Result = string.Empty;
        foreach (char a in key)
        {
            if (Result.Contains(a.ToString().ToUpper()) || Result.Contains(a.ToString().ToLower()))
                continue;
            Result += a.ToString();
        }
        return Result;
    }

Answer 12

char *remove_duplicates(char *str) { char *str1, *str2;

if(!str)
    return str;

str1 = str2 = str;

while(*str2)            
{   
    if(strchr(str, *str2)<str2)
    {
        str2++;
        continue;
    }

    *str1++ = *str2++;      
}
*str1 = '\0';

return  str;

}

Answer 13

char* removeDups(const char* str)
{
 char* new_str = (char*)malloc(256*sizeof(char));
 int i,j,current_pos = 0,len_of_new_str;
 new_str[0]='\0';

 for(i=0;i<strlen(str);i++)
{
 len_of_new_str = strlen(new_str);
for(j=0;j<len_of_new_str && new_str[j]!=str[i];j++)
   ;
  if(j==len_of_new_str)
   {
     new_str[len_of_new_str] = str[i];
     new_str[len_of_new_str+1] = '\0';
   }
}
  return new_str;
}

Hope this helps

Answer 14

var input1 = Console.ReadLine().ToLower().ToCharArray();
var input2 = input1;
var WithoutDuplicate = input1.Union(input2);

Answer 15

Console.WriteLine("Enter String");

string str = Console.ReadLine();

string result = "";
result += str[0]; // first character of string

for (int i = 1; i < str.Length; i++)
{
    if (str[i - 1] != str[i])
        result += str[i];
}

Console.WriteLine(result);

Answer 16

I like Quintin Robinson answer, only there should be some improvements like removing List, because it is not necessarry in this case. Also, in my opinion Uppercase char ("K") and lowercase char ("k") is the same thing, so they should be counted as one.

So here is how I would do it:

private static string RemoveDuplicates(string textEntered)
    {

        string newString = string.Empty;

        foreach (var c in textEntered)
        {
            if (newString.Contains(char.ToLower(c)) || newString.Contains(char.ToUpper(c)))
            {
                continue;
            }
            newString += c.ToString();
        }
        return newString;
    }

Answer 17

Not sure how optimal it is:

public static string RemoveDuplicates(string input)
{
    var output = string.Join("", input.ToHashSet());
    return output;
}

Answer 18

Below is the code to remove duplicate chars from a string

        var input = "SaaSingeshe";
        var filteredString = new StringBuilder();
        foreach(char c in input)
        {
            if(filteredString.ToString().IndexOf(c)==-1)
            {
                filteredString.Append(c);
            }
        }
        Console.WriteLine(filteredString);
        Console.ReadKey();

Answer 19

namespace Demo { class Program {

  static void Main(string[] args) {
     string myStr = "kkllmmnnouo";
     Console.WriteLine("Initial String: "+myStr);
    // var unique = new HashSet<char>(myStr);
     HashSet<char> unique = new HashSet<char>(myStr);
     Console.Write("New String after removing duplicates: ");

     foreach (char c in unique) 
        Console.Write(c);   
  }    } }

Answer 20

this works for me

private string removeDuplicateChars(String value)
{
    return new string(value.Distinct().ToArray());
}

Answer 21

String str="AABBCANCDE";  
String newStr=""; 
for( int i=0; i<str.length(); i++)
{
 if(!newStr.contains(str.charAt(i)+""))
 newStr= newStr+str.charAt(i);
 }
 System.out.println(newStr);