String Similarity


Problem Statement :


For two strings A and B, we define the similarity of the strings to be the length of the longest prefix common to both strings. For example, the similarity of strings "abc" and "abd" is 2, while the similarity of strings "aaa" and "aaab" is 3.

Calculate the sum of similarities of a string S with each of it's suffixes.

Input Format

The first line contains the number of test cases t.
Each of the next t lines contains a string to process, s.

Constraints

1  <=  t  <=  10
1   <=   | s  |  <=   100000
s is composed of characters in the range ascii[a-z]


Output Format

Output t lines, each containing the answer for the corresponding test case.

Sample Input

2
ababaa  
aa


Sample Output

11  
3



Solution :



title-img


                            Solution in C :

In    C++  :








#include <algorithm>
#include <string>
#include <vector>
#include <queue>
#include <iostream>
#include <cmath>
#include <sstream>
#include <map>
#include <set>
#include <numeric>
#include <memory.h>
#include <cstdio>
#include <assert.h>
#include <numeric>

using namespace std;

#define pb push_back
#define INF 1011111111
#define FOR(i,a,b) for (int _n(b), i(a); i < _n; i++)
#define rep(i,n) FOR(i,0,n)
#define ford(i,a,b) for(int i=(a),_b=(b);i>=_b;--i)
#define CL(a,v) memset((a),(v),sizeof(a))
#define mp make_pair
#define X first
#define Y second
#define all(c) (c).begin(), (c).end()
#define SORT(c) sort(all(c))

typedef long long ll;
typedef vector<int> VI;
typedef pair<int,int> pii;

vector<ll> z_func(const string &s)
{
    int n = s.size();
    vector<ll> z(n,0);
    int l = 0,r = 0;

    FOR(i,1,n)
    {
        if(i <= r)
            z[i] = min(z[i-l], (ll)r-i+1);

        while(i+z[i] < n && s[i+z[i]] == s[z[i]]) z[i] ++;

        if(i+z[i]-1 > r)
            r = i+z[i]-1, l = i;
    }

    return z;
}

int main()
{
	#ifndef ONLINE_JUDGE
        //freopen("input.txt","r",stdin);
        //freopen("output.txt","w",stdout);
	#endif

    int T;
    cin >> T;

    while(T--)
    {
        string s;
        cin >> s;

        vector<ll> z = z_func(s);

        cout << 1LL*s.size() + accumulate(all(z), 0LL) << endl;
    }

	return 0;
}









In   Java   :







import java.util.Scanner;


public class Solution {

	private String[] strArray;
	
	public boolean read(){
		
		Scanner sc = new Scanner(System.in);
		int n = Integer.valueOf(sc.nextLine());
		strArray = new String[n];
		int i = 0;
		while(i < n){
			
			strArray[i++] = sc.nextLine();
		}
		
		return true;
	}
	
	public void solve(){
		
    	for(String s : strArray){
	    	int len = s.length();
	    	int sum = len;
	    	for(int i=1; i<len;i++){
	    		int count = 0;
	    		for(int j=0,k=i; j<len && k<len; j++,k++){
	    			  if(s.charAt(k) == s.charAt(j)){
	    				  count++;
	    			  }else{
	    				  break;
	    			  }
	    		}
	    		sum = sum + count;
	    	}
	    	System.out.println(sum);
    	}
    	
	}
	public void solveIt(){
		
    	for(String s : strArray){
	    	int len = s.length();
	    	long sum = len;
	    	char ch = s.charAt(0);
	    	int pos = s.indexOf(ch, 1);	    	
	    	while(pos != -1){
	    		long count = 1;
	    		for(int j=1,k=pos+1; j<len && k<len; j++,k++){
	    			  if(s.charAt(k) == s.charAt(j)){
	    				  count++;
	    			  }else{
	    				  break;
	    			  }
	    		}
	    		sum = sum + count;
	    		pos = s.indexOf(ch, pos+1);
	    	}
	    	System.out.println(sum);
    	}
    	
	}

	public void solveZ(){
		
    	for(String s : strArray){
	    	int len = s.length();
	    	long sum = len;
	    	int[] z = new int[len];
	    	int l=0,r=0;
	    	for(int k=1;k<len;k++){
	    		int j;
	    		if(k < r){
	    			j = ((r-k) < z[k-l] )? (r-k) : z[k-l];
	    		}else{
	    			j = 0;
	    		} 
	    		while(k+j < len){
	    			
	    			if(s.charAt(k+j) == s.charAt(j)){
	    				j++;
	    			}else{
	    				break;
	    			}
	    		}
	    		z[k] = j;
	    		sum = sum + z[k];
	    		if(k+j > r){
	    			l = k;
	    			r= k+j;
	    		}

	    	}
	    	System.out.println(sum);
    	}
    	
	}
	

	public static void main(String[] args) {
		// TODO Auto-generated method stub

		Solution s = new Solution();
		if(s.read()){
			s.solveZ();
		}
		
	}

}








In    C  :







#include <stdio.h>
#include <string.h>

#define N 200000
char str[N];
int pre[N];
int len[N];

int main() {
	int tc;
	scanf("%d", &tc);
	while (tc --) {
		memset(pre, -1 , sizeof(pre));
		memset(len, 0, sizeof(len));
		scanf("%s", str);
		int n = strlen(str);
		long long sum = 0;
		int k = -1;
		int pos = 0;
		while (pos + 1 < n) {
			if (str[k + 1] == str[pos + 1]) {
				k++; pos++;
				pre[pos] = k;
				len[pos - k] = k + 1;
			} else if (k == -1) {
				pos++;
			} else {
				k = pre[k];
				len[pos - k] = k + 1;
			}
		}
		while (k > 0) {
			k = pre[k];
			len[pos - k] = k + 1;
		}
		len[0] = n;
		for (int i = 0; i < n; i++) {
			sum += len[i];
		}

		for (int i = 0; i < n; i++) {
			if (len[i] == 0) {
				for (int j = 0; i + j < n; j++) {
					if (str[j] == str[i+j]) {
						sum++;
					} else {
						break;
					}
				}
			}
		}
		printf("%lld\n", sum);
	}
}









In    Python3  :






def z(w, T):
    T.append(len(w))
    l = r = 0
    for i in range(1, len(w)):
        k = 0
        if i < r:
            k = min(r-i, T[i-l])
        while i+k<len(w) and w[i+k] == w[k]:
            k += 1
        T.append(k)
        if i+k > r:
            l = i
            r = i+k

N = int(input())
for i in range(N):
    curr = input()
    count = 0
    T = []
    z(curr, T)
    for j in range(len(T)):
        count += T[j]
    print(count)
                        








View More Similar Problems

Cube Summation

You are given a 3-D Matrix in which each block contains 0 initially. The first block is defined by the coordinate (1,1,1) and the last block is defined by the coordinate (N,N,N). There are two types of queries. UPDATE x y z W updates the value of block (x,y,z) to W. QUERY x1 y1 z1 x2 y2 z2 calculates the sum of the value of blocks whose x coordinate is between x1 and x2 (inclusive), y coor

View Solution →

Direct Connections

Enter-View ( EV ) is a linear, street-like country. By linear, we mean all the cities of the country are placed on a single straight line - the x -axis. Thus every city's position can be defined by a single coordinate, xi, the distance from the left borderline of the country. You can treat all cities as single points. Unfortunately, the dictator of telecommunication of EV (Mr. S. Treat Jr.) do

View Solution →

Subsequence Weighting

A subsequence of a sequence is a sequence which is obtained by deleting zero or more elements from the sequence. You are given a sequence A in which every element is a pair of integers i.e A = [(a1, w1), (a2, w2),..., (aN, wN)]. For a subseqence B = [(b1, v1), (b2, v2), ...., (bM, vM)] of the given sequence : We call it increasing if for every i (1 <= i < M ) , bi < bi+1. Weight(B) =

View Solution →

Kindergarten Adventures

Meera teaches a class of n students, and every day in her classroom is an adventure. Today is drawing day! The students are sitting around a round table, and they are numbered from 1 to n in the clockwise direction. This means that the students are numbered 1, 2, 3, . . . , n-1, n, and students 1 and n are sitting next to each other. After letting the students draw for a certain period of ti

View Solution →

Mr. X and His Shots

A cricket match is going to be held. The field is represented by a 1D plane. A cricketer, Mr. X has N favorite shots. Each shot has a particular range. The range of the ith shot is from Ai to Bi. That means his favorite shot can be anywhere in this range. Each player on the opposite team can field only in a particular range. Player i can field from Ci to Di. You are given the N favorite shots of M

View Solution →

Jim and the Skyscrapers

Jim has invented a new flying object called HZ42. HZ42 is like a broom and can only fly horizontally, independent of the environment. One day, Jim started his flight from Dubai's highest skyscraper, traveled some distance and landed on another skyscraper of same height! So much fun! But unfortunately, new skyscrapers have been built recently. Let us describe the problem in one dimensional space

View Solution →