Longest Common Substring in an Array of Strings

Last Updated : 28 Nov, 2024

We are given a list of words sharing a common stem i.e the words originate from same word for ex: the words sadness, sadly and sad all originate from the stem ‘sad’.
Our task is to find and return the Longest Common Substring also known as stem of those words. In case there are ties, we choose the smallest one in alphabetical order.

Examples:

Input : grace graceful disgraceful gracefully
Output : grace
Input : sadness sad sadly
Output : sad

The idea is to take any word from the list as reference and form all its substrings and iterate over the entire list checking if the generated substring occurs in all of them.

Below is the implementation of the above idea:

C++

// C++ program to find the stem of given list of // words #include <bits/stdc++.h> using namespace std;  // function to find the stem (longest common // substring) from the string array string findstem(vector<string> arr) {     // Determine size of the array     int n = arr.size();      // Take first word from array as reference     string s = arr[0];     int len = s.length();      string res = "";      for (int i = 0; i < len; i++) {         for (int j = i + 1; j <= len; j++) {             // generating all possible substrings             // of our reference string arr[0] i.e s             string stem = s.substr(i, j);             int k = 1;             for (k = 1; k < n; k++) {                 // Check if the generated stem is                 // common to all words                 if (arr[k].find(stem) == std::string::npos)                     break;             }              // If current substring is present in             // all strings and its length is greater             // than current result             if (k == n && res.length() < stem.length())                 res = stem;         }     }      return res; }  // Driver code int main() {     vector<string> arr{ "grace", "graceful", "disgraceful",                         "gracefully" };      // Function call     string stems = findstem(arr);     cout << stems << endl; }  // This code is contributed by // sanjeev2552

Java

// Java program to find the stem of given list of // words import java.io.*; import java.util.*;  class stem {      // function to find the stem (longest common     // substring) from the string  array     public static String findstem(String arr[])     {         // Determine size of the array         int n = arr.length;          // Take first word from array as reference         String s = arr[0];         int len = s.length();          String res = "";          for (int i = 0; i < len; i++) {             for (int j = i + 1; j <= len; j++) {                  // generating all possible substrings                 // of our reference string arr[0] i.e s                 String stem = s.substring(i, j);                 int k = 1;                 for (k = 1; k < n; k++)                      // Check if the generated stem is                     // common to all words                     if (!arr[k].contains(stem))                         break;                  // If current substring is present in                 // all strings and its length is greater                 // than current result                 if (k == n && res.length() < stem.length())                     res = stem;             }         }          return res;     }      // Driver Code     public static void main(String args[])     {         String arr[] = { "grace", "graceful",                          "disgraceful","gracefully" };                // Function call         String stems = findstem(arr);         System.out.println(stems);     } }

Python

# Python 3 program to find the stem # of given list of words  # function to find the stem (longest # common substring) from the string array   def findstem(arr):      # Determine size of the array     n = len(arr)      # Take first word from array     # as reference     s = arr[0]     l = len(s)      res = ""      for i in range(l):         for j in range(i + 1, l + 1):              # generating all possible substrings             # of our reference string arr[0] i.e s             stem = s[i:j]             k = 1             for k in range(1, n):                  # Check if the generated stem is                 # common to all words                 if stem not in arr[k]:                     break              # If current substring is present in             # all strings and its length is greater             # than current result             if (k + 1 == n and len(res) < len(stem)):                 res = stem      return res   # Driver Code if __name__ == "__main__":      arr = ["grace", "graceful",            "disgraceful", "gracefully"]          # Function call     stems = findstem(arr)     print(stems)  # This code is contributed by ita_c

// C# program to find the stem of given list of  // words  using System; using System.Collections.Generic;  class stem {      // function to find the stem (longest common      // substring) from the string array      public static String findstem(String []arr)      {          // Determine size of the array          int n = arr.Length;           // Take first word from array as reference          String s = arr[0];          int len = s.Length;           String res = "";           for (int i = 0; i < len; i++)          {              for (int j = i + 1; j <= len; j++)             {                   // generating all possible substrings                  // of our reference string arr[0] i.e s                  String stem = s.Substring(i, j-i);                  int k = 1;                  for (k = 1; k < n; k++)                       // Check if the generated stem is                      // common to all words                      if (!arr[k].Contains(stem))                          break;                                   // If current substring is present in                  // all strings and its length is greater                  // than current result                  if (k == n && res.Length < stem.Length)                      res = stem;              }          }           return res;      }       // Driver Code      public static void Main(String []args)      {          String []arr = { "grace", "graceful", "disgraceful",                                              "gracefully" };          // Function call         String stems = findstem(arr);          Console.WriteLine(stems);      }  }   // This code contributed by Rajput-Ji

JavaScript

// JavaScript program to find the stem of given list of // words function findstem(arr) {  // Determine size of the array let n = arr.length;  // Take first word from array as reference let s = arr[0]; let len = s.length;  let res = "";  for (let i = 0; i < len; i++) {     for (let j = i + 1; j <= len; j++) {          // generating all possible substrings         // of our reference string arr[0] i.e s         let stem = s.substring(i, j);         let k = 1;         for (k = 1; k < n; k++) {              // Check if the generated stem is             // common to all words             if (!arr[k].includes(stem))                 break;         }          // If current substring is present in         // all strings and its length is greater         // than current result         if (k === n && res.length < stem.length)             res = stem;     } }  return res; }  // Driver Code let arr = ["grace", "graceful", "disgraceful", "gracefully"];  // Function call let stems = findstem(arr); console.log(stems);

PHP

<?php // PHP program to find the stem of given list of  // words      // function to find the stem (longest common      // substring) from the string array     function findstem($arr)     {         // Determine size of the array         $n = count($arr);          // Take first word from array as reference         $s = $arr[0];         $len = strlen($s);                  $res = "";          for ($i = 0; $i < $len; $i++)         {             for ($j = $i+1; $j <=$len; $j++)              {                  // generating all possible substrings                 // of our reference string arr[0] i.e s                 $stem = substr($s,$i, $j-$i);                                  $k = 1;                 for ($k = 1; $k < $n; $k++)                       // Check if the generated stem is                     // common to all words                     if (!strpos($arr[$k],$stem))                         break;                                  // If current substring is present in                 // all strings and its length is greater                  // than current result                 if ($k <= $n && strlen($res) < strlen($stem))                     $res = $stem;                              }         }          return $res;     }      // Driver Code     $arr = array( "grace", "graceful",                   "disgraceful", "gracefully" );      // Function call     $stems = findstem($arr);     print($stems);      // This code is contributed by mits ?>

Output

grace

Time Complexity: O(L² * n * m)
Auxiliary Space: O(L).

Longest common anagram subsequence from N strings

GeeksforGeeks

Improve

Article Tags :

Practice Tags :

Longest Common Substring in an Array of Strings

Similar Reads