How to find repeating sequence of characters in a given array?

Question

My problem is to find the repeating sequence of characters in the given array. simply, to identify the pattern in which the characters are appearing.

Answer 1

This is a solution I came up with using the queue, it passed all the test cases of a similar problem in codeforces. Problem No is 745A.

#include<bits/stdc++.h>
using namespace std;
typedef long long ll;

int main()
{
    ios_base::sync_with_stdio(false);
    cin.tie(NULL);

    string s, s1, s2; cin >> s; queue<char> qu; qu.push(s[0]); bool flag = true; int ind = -1;
    s1 = s.substr(0, s.size() / 2);
    s2 = s.substr(s.size() / 2);
    if(s1 == s2)
    {
        for(int i=0; i<s1.size(); i++)
        {
            s += s1[i];
        }
    }
    //cout << s1 << " " << s2 << " " << s << "\n";
    for(int i=1; i<s.size(); i++)
    {
        if(qu.front() == s[i]) {qu.pop();}
        qu.push(s[i]);
    }
    int cycle = qu.size();

    /*queue<char> qu2 = qu; string str = "";
    while(!qu2.empty())
    {
        cout << qu2.front() << " ";
        str += qu2.front();
        qu2.pop();
    }*/


    while(!qu.empty())
    {
        if(s[++ind] != qu.front()) {flag = false; break;}
        qu.pop();
    }
    flag == true ? cout << cycle : cout << s.size();
    return 0;
}

Answer 2

In Python, you can leverage regexes thus:

def recurrence(text):
    import re
    for i in range(1, len(text)/2 + 1):
        m = re.match(r'^(.{%d})\1+$'%i, text)
        if m: return m.group(1)

recurrence('abcabc') # Returns 'abc'

I'm not sure how this would translate to Java or C. (That's one of the reasons I like Python, I guess. :-)

Answer 3

Just figured this out myself and wrote some code for this (written in C#) with a lot of comments. Hope this helps someone:

// Check whether the string contains a repeating sequence.
public static bool ContainsRepeatingSequence(string str)
{
    if (string.IsNullOrEmpty(str)) return false;

    for (int i=0; i<str.Length; i++)
    {
        // Every iteration, cut down the string from i to the end.
        string toCheck = str.Substring(i);

        // Set N equal to half the length of the substring. At most, we have to compare half the string to half the string. If the string length is odd, the last character will not be checked against, but it will be checked in the next iteration.
        int N = toCheck.Length / 2;

        // Check strings of all lengths from 1 to N against the subsequent string of length 1 to N.
        for (int j=1; j<=N; j++)
        {
            // Check from beginning to j-1, compare against j to j+j.
            if (toCheck.Substring(0, j) == toCheck.Substring(j, j)) return true;
        }
    }

    return false;
}

Feel free to ask any questions if it's unclear why it works.

Answer 4

I'd convert the array to a String object and use regex

Answer 5

and here is a concrete working example:

/* find greatest repeated substring */
char *fgrs(const char *s,size_t *l)
{
  char *r=0,*a=s;
  *l=0;
  while( *a )
  {
    char *e=strrchr(a+1,*a);
    if( !e )
      break;
    do {
      size_t t=1;
      for(;&a[t]!=e && a[t]==e[t];++t);
      if( t>*l )
        *l=t,r=a;
      while( --e!=a && *e!=*a );
    } while( e!=a && *e==*a );
    ++a;
  }
  return r;
}

  size_t t;
  const char *p;
  p=fgrs("BARBARABARBARABARBARA",&t);
  while( t-- ) putchar(*p++);
  p=fgrs("0123456789",&t);
  while( t-- ) putchar(*p++);
  p=fgrs("1111",&t);
  while( t-- ) putchar(*p++);
  p=fgrs("11111",&t);
  while( t-- ) putchar(*p++);

Answer 6

First write a method that find repeating substring sub in the container string as below.

boolean findSubRepeating(String sub, String container);

Now keep calling this method with increasing substring in the container, first try 1 character substring, then 2 characters, etc going upto container.length/2.