SPOJDISUBSTR-Distinct Substrings

DISUBSTR - Distinct Substrings

#suffix-array-8

Given a string, we need to find the total number of its distinct substrings.

Input

T- number of test cases. T<=20;
Each test case consists of one string, whose length is <= 1000

Output

For each test case output one number saying the number of distinct substrings.

Example

Sample Input:
2
CCCCC
ABABA

Sample Output:
5
9

Explanation for the testcase with string ABABA: 
len=1 : A,B
len=2 : AB,BA
len=3 : ABA,BAB
len=4 : ABAB,BABA
len=5 : ABABA
Thus, total number of distinct substrings is 9.

题意：给你一个字符串， 求有几种子串

解题思路：后缀数组

#include <iostream>
#include <cstdio>
#include <cmath>
#include <cstring>
#include <algorithm>
#include <stack>
#include <queue>
#include <vector>
#include <map>

using namespace std;

#define N 200010

struct Sa
{
    char s[N];
    int rk[2][N],sa[N],h[N],w[N],now,n;
    int rmq[N][20],lg[N];

    bool GetS()
    {
        scanf("%s",s+1);
        return true;
    }

    void getsa(int z,int &m)
    {
        int x=now,y=now^=1;
        for(int i=1;i<=z;i++) rk[y][i]=n-i+1;
        for(int i=1,j=z;i<=n;i++)
            if(sa[i]>z) rk[y][++j]=sa[i]-z;
        for(int i=1;i<=m;i++) w[i]=0;
        for(int i=1;i<=n;i++) w[rk[x][rk[y][i]]]++;
        for(int i=1;i<=m;i++) w[i]+=w[i-1];
        for(int i=n;i>=1;i--) sa[w[rk[x][rk[y][i]]]--]=rk[y][i];
        for(int i=m=1;i<=n;i++)
        {
            int *a=rk[x]+sa[i],*b=rk[x]+sa[i-1];
            rk[y][sa[i]]=*a==*b&&*(a+z)==*(b+z)?m-1:m++;
        }
    }

    void getsa(int m)
    {
        now=rk[1][0]=sa[0]=s[0]=0;
        n=strlen(s+1);
        for(int i=1;i<=m;i++) w[i]=0;
        for(int i=1;i<=n;i++) w[s[i]]++;
        for(int i=1;i<=m;i++) rk[1][i]=rk[1][i-1]+(bool)w[i];
        for(int i=1;i<=m;i++) w[i]+=w[i-1];
        for(int i=1;i<=n;i++) rk[0][i]=rk[1][s[i]];
        for(int i=1;i<=n;i++) sa[w[s[i]]--]=i;
        for(int x=1,y=rk[1][m];x<=n&&y<=n;x<<=1) getsa(x,y);
        for(int i=1,j=0;i<=n;h[rk[now][i++]]=j?j--:j)
        {
            if(rk[now][i]==1) continue;
            int k=n-max(sa[rk[now][i]-1],i);
            while(j<=k&&s[sa[rk[now][i]-1]+j]==s[i+j]) ++j;
        }

    }

    void getrmq()
    {
        h[n+1]=h[1]=lg[1]=0;
        for(int i=2;i<=n;i++)
            rmq[i][0]=h[i],lg[i]=lg[i>>1]+1;
        for(int i=1;(1<<i)<=n;i++)
        {
            for(int j=2;j<=n;j++)
            {
                if(j+(1<<i)>n+1) break;
                rmq[j][i]=min(rmq[j][i-1],rmq[j+(1<<i-1)][i-1]);
            }
        }
    }

    int lcp(int x,int y)
    {
        int l=min(rk[now][x],rk[now][y])+1,r=max(rk[now][x],rk[now][y]);
        return min(rmq[l][lg[r-l+1]],rmq[r-(1<<lg[r-l+1])+1][lg[r-l+1]]);
    }

    void work()
    {
        GetS();getsa(300);
        int ans=n-sa[1]+1;
        for(int i=2;i<=n;i++)
            ans+=n-sa[i]-h[i]+1;
        printf("%d\n",ans);
    }
}sa;

int main()
{
    int t;
    scanf("%d",&t);
    while(t--) sa.work();
    return 0;
}