SPOJ - REPEATS Repeats （后缀数组 + RMQ 重复次数最多的连续重复子串的重复次数）

Repeats

 

A string s is called an (k,l)-repeat if s is obtained by concatenating k>=1 times some seed string t with length l>=1. For example, the string

s = abaabaabaaba

is a (4,3)-repeat with t = aba as its seed string. That is, the seed string t is 3 characters long, and the whole string s is obtained by repeating t 4 times.

Write a program for the following task: Your program is given a long string u consisting of characters ‘a’ and/or ‘b’ as input. Your program must find some (k,l)-repeat that occurs as substring within u with k as large as possible. For example, the input string

u = babbabaabaabaabab

contains the underlined (4,3)-repeat s starting at position 5. Since u contains no other contiguous substring with more than 4 repeats, your program must output the maximum k.

 

Input

In the first line of the input contains H- the number of test cases (H <= 20). H test cases follow. First line of each test cases is n - length of the input string (n <= 50000), The next n lines contain the input string, one character (either ‘a’ or ‘b’) per line, in order.

Output

For each test cases, you should write exactly one interger k in a line - the repeat count that is maximized.

Example

Input:
1
17
b
a
b
b
a
b
a
a
b
a
a
b
a
a
b
a
b

Output:
4

since a (4, 3)-repeat is found starting at the 5th character of the input string.

题目链接：https://vjudge.net/problem/SPOJ-REPEATS

题目大意：给一个长度为n的字符串，求这个字符串重复次数最多的连续重复子串的重复次数

思路：罗穗骞的论文《后缀数组——处理字符串的有力工具》中写的很详细，就不再赘述。

代码：

#include<stdio.h>
#include<string.h>
#include<algorithm>
using namespace std;
#define ll long long
const int N=500005;
int a[N],id[N],sa[N],rak[N],h[N],c[N],t1[N],t2[N];
bool cmp(int *f,int x,int y,int w){return f[x]==f[y]&&f[x+w]==f[y+w];}
void da(int a[], int sa[], int rak[], int h[], int n, int m)
{
    n++;
    int i,j,p,*x = t1,*y = t2;
    for (i=0; i<m; i++) c[i]=0;
    for (i=0; i<n; i++) c[x[i]=a[i]]++;
    for (i=1; i<m; i++) c[i]+=c[i-1];
    for (i=n-1; i>=0; i--) sa[--c[x[i]]]=i;
    for (j=1; j<=n; j<<=1)
    {
        p=0;
        for (i=n-j; i<n; i++) y[p++]=i;
        for (i=0; i<n; i++) if(sa[i]>=j) y[p++]=sa[i]-j;
        for (i=0; i<m; i++) c[i]=0;
        for (i=0; i<n; i++) c[x[y[i]]]++;
        for (i=1; i<m; i++) c[i]+=c[i-1];
        for (i=n-1; i>=0; i--) sa[--c[x[y[i]]]]=y[i];
        swap(x, y); p=1; x[sa[0]]=0;
        for (i=1; i<n; i++) x[sa[i]]=cmp(y, sa[i-1], sa[i], j)?p-1:p++;
        if(p>=n) break;
        m=p;
    }
    n--;
    for(i=0;i<=n;i++) rak[sa[i]]=i;
    int k=0;
    for(int i=0;i<n;h[rak[i++]]=k)
        for(k=k?k-1:k,j=sa[rak[i]-1];a[i+k]==a[j+k];k++);
}

int mm[N],dp[N][30];
void init_RMQ(int n)
{
    mm[0]=-1;
    for(int i=1; i<=n; i++)
    {
        dp[i][0]=h[i];
        mm[i]=((i&(i-1))==0)? mm[i-1]+1:mm[i-1];
    }
    for(int j=1; j<=mm[n]; j++)
        for(int i=1; i+(1<<j)-1<=n; i++)
            dp[i][j]=min(dp[i][j-1], dp[i+(1<<(j-1))][j-1]);
}
int RMQ(int L, int R)
{
    int k = mm[R-L+1];
    return min(dp[L][k], dp[R-(1<<k)+1][k]);
}
int LCP(int i, int j)
{
    i=rak[i],j=rak[j];
    if(i>j) swap(i,j);
    return RMQ(i+1,j);
}
int main()
{
    int T,n;
    scanf("%d", &T);
    while(T--)
    {
        scanf("%d", &n);
        char s;
        for(int i=0;i<n;i++)
        {scanf(" %c",&s);a[i]=s;}
        a[n]=0;
        da(a,sa,rak,h,n,128);
        init_RMQ(n);
        int ans=1;
        for(int i=1;i<n;i++)
            for(int j=0;j+i<n;j+=i)
            {
                int len=LCP(j,j+i);
                int tp=len/i+1;
                int pos=j-(i-len%i);
                if(pos>=0)
                {   len=LCP(pos,pos+i);
                    tp=max(tp,len/i+1);
                }
                ans=max(ans, tp);
            }
        printf("%d\n", ans);
    }
    return 0;
}