Count distinct substrings that contain some characters at most k times

Given a integer k and a sting str, the task is to count the number of distinct sub-strings such that each sub-string does not contain some specific characters more than k times. The specific characters are given as another string.

Examples:

Input: str = “ababab”, anotherStr = “bcd”, k = 1
Output: 5
All valid sub-strings are “a”, “b”, “ab”, “ba” and “aba”

Input: str = “acbacbacaa”, anotherStr = “ycb”, k = 2
Output: 8



Approach:

  • Store characters of anotherStr in a boolean array of size 256 for quick lookip
  • Traverse through all substrings of given string. For every substring, keep the count of illegal characters in anotherStr.
  • If the count of these characters exceeds the value of k then break out of the inner loop.
  • Else, store this sub-string in an hash table to keep distinct substrings.

Below is the implementation of the above approach:

C++

filter_none

edit
close

play_arrow

link
brightness_4
code

// C++ implementation of the approach
#include <bits/stdc++.h>
using namespace std;
  
const int MAX_CHAR = 256;
  
// Function to return the count of valid sub-strings
int countSubStrings(string s, string anotherStr, int k)
{
    // Store all characters of anotherStr in a 
    // direct index table for quick lookup.
    bool illegal[MAX_CHAR] = { false };
    for (int i = 0; i < anotherStr.size(); i++)
        illegal[anotherStr[i]] = true;
  
    // To store distinct output substrings
    unordered_set<string> us;
  
    // Traverse through the given string and
    // one by one generate substrings beginning
    // from s[i].
    for (int i = 0; i < s.size(); ++i) {
  
        // One by one generate substrings ending
        // with s[j]
        string ss = "";
        int count = 0;
        for (int j = i; j < s.size(); ++j) {
  
            // If character is illegal
            if (illegal[s[j]])
                ++count;
            ss = ss + s[j];
  
            // If current substring is valid
            if (count <= k) {
                us.insert(ss);
            }
  
            // If current substring is invalid,
            // adding more characters would not
            // help.
            else
                break;
        }
    }
  
    // Return the count of distinct sub-strings
    return us.size();
}
  
// Driver code
int main()
{
    string str = "acbacbacaa";
    string anotherStr = "abcdefghijklmnopqrstuvwxyz";
    int k = 2;
    cout << countSubStrings(str, anotherStr, k);
    return 0;
}

chevron_right


Java

filter_none

edit
close

play_arrow

link
brightness_4
code

// Java implementation of the approach
import java.util.*;
  
class GFG {
  
    static int MAX_CHAR = 256;
  
    // Function to return the count of valid sub-strings
    static int countSubStrings(String s, String anotherStr, int k) 
    {
        // Store all characters of anotherStr in a 
        // direct index table for quick lookup.
        boolean illegal[] = new boolean[MAX_CHAR];
        for (int i = 0; i < anotherStr.length(); i++) 
        {
            illegal[anotherStr.charAt(i)] = true;
        }
  
        // To store distinct output substrings
        HashSet<String> us = new HashSet<String>();
  
        // Traverse through the given string and
        // one by one generate substrings beginning
        // from s[i].
        for (int i = 0; i < s.length(); ++i) 
        {
  
            // One by one generate substrings ending
            // with s[j]
            String ss = "";
            int count = 0;
            for (int j = i; j < s.length(); ++j) 
            {
  
                // If character is illegal
                if (illegal[s.charAt(j)])
                {
                    ++count;
                }
                ss = ss + s.charAt(j);
  
                // If current substring is valid
                if (count <= k) 
                {
                    us.add(ss);
                
                  
                // If current substring is invalid,
                // adding more characters would not
                // help.
                else 
                {
                    break;
                }
            }
        }
  
        // Return the count of distinct sub-strings
        return us.size();
    }
  
    // Driver code
    public static void main(String[] args) 
    {
        String str = "acbacbacaa";
        String anotherStr = "abcdefghijklmnopqrstuvwxyz";
        int k = 2;
        System.out.println(countSubStrings(str, anotherStr, k));
    }
}
  
// This code is contributed by PrinciRaj1992

chevron_right


Python3

filter_none

edit
close

play_arrow

link
brightness_4
code

# Python3 implementation of the approach 
  
MAX_CHAR = 256
  
# Function to return the count
# of valid sub-strings 
def countSubStrings(s, anotherStr, k) :
      
    # Store all characters of anotherStr in
    # a direct index table for quick lookup. 
    illegal = [False] * MAX_CHAR
      
    for i in range(len(anotherStr)) :
        illegal[ord(anotherStr[i])] = True
          
    # To store distinct output substrings 
    us = set() 
      
    # Traverse through the given string 
    # and one by one generate substrings 
    # beginning from s[i]. 
    for i in range(len(s)) :
          
        # One by one generate substrings 
        # ending with s[j] 
        ss = "" 
          
        count = 0
        for j in range(i, len(s)) :
              
            # If character is illegal
            if (illegal[ord(s[j])]) :
                count += 1
            ss = ss + s[j]
              
            # If current substring is valid
            if (count <= k) :
                us.add(ss)
              
            # If current substring is invalid,
            # adding more characters would not
            # help.
            else :
                break
      
    # Return the count of distinct
    # sub-strings 
    return len(us)
  
# Driver code 
if __name__ == "__main__"
  
    string = "acbacbacaa"
    anotherStr = "abcdefghijklmnopqrstuvwxyz"
    k = 2
    print(countSubStrings(string, 
                          anotherStr, k))
  
# This code is contributed by Ryuga

chevron_right


Output:

8


My Personal Notes arrow_drop_up

Check out this Author's contributed articles.

If you like GeeksforGeeks and would like to contribute, you can also write an article using contribute.geeksforgeeks.org or mail your article to contribute@geeksforgeeks.org. See your article appearing on the GeeksforGeeks main page and help other Geeks.

Please Improve this article if you find anything incorrect by clicking on the "Improve Article" button below.



Improved By : Ryuga, princiraj1992