SPOJ - DISUBSTR （后缀数组）

题意：

求一个字符串的不同子串的个数？

思路：

后缀数组算法：

每一个子串都是某一个后缀的前缀，那么问题转换为 求 所有后缀的不同前缀个数。

如果按照后缀数组 sa[0],sa[1],sa[2],,,sa[k]访问的话，

那么访问sa[k] 便会新加入n - sa[k] + 1个 前缀。

这些前缀中 有height[k] 是与前面重复的，减去即可。

#include <cstdio>
#include <cstring>
#include <algorithm>
using namespace std;

const int maxn = 1000 + 10;

int n, k;
int Rank[maxn];
char s[maxn];
int tmp[maxn ], sa[maxn], lcp[maxn];
bool cmp(int i,int j){

    if (Rank[i] != Rank[j]) return Rank[i] < Rank[j];
    else {
        int ri = i + k <= n ?  Rank[i+k] : -1;
        int rj = j + k <= n ?  Rank[j + k]: -1;
        return ri < rj;
    }
}

void build_sa(char* s,int * sa){
    for (int i = 0; i <= n; ++i){
        sa[i] = i;
        Rank[i] = i < n ? s[i] : -1;

    }

    for (k = 1; k <= n; k *= 2){

        sort(sa, sa+n+1, cmp);

        tmp[sa[0] ] = 0;
        for (int i = 1; i <= n; ++i){
            tmp[sa[i] ] = tmp[sa[i-1] ] + (cmp(sa[i-1], sa[i]) ? 1:0);



        }
        for (int i = 0; i <= n; ++i) {
            Rank[i] = tmp[i];
        }


    }


}

void get_height(char* s, int* sa, int* lcp){
    for (int i = 0; i <= n; ++i) Rank[sa[i] ] = i;
    int h = 0;
    lcp[0] = 0;
    for (int i = 0; i < n; ++i){
        int j = sa[Rank[i] -1 ];
        if (h > 0) h--;
        for (; j + h < n && i + h < n; ++h){

            if (s[j+h] != s[i+h])break;

        }
        lcp[Rank[i]-1 ] = h;

    }


}


int main(){
    int T;
    scanf("%d",&T);
    while(T--){
        memset(tmp,0,sizeof tmp);
        memset(sa,0,sizeof sa);
        memset(lcp,0,sizeof lcp);
        memset(Rank,0,sizeof Rank);
//        memset(tmp,0,sizeof tmp);
        scanf("%s",s);
        n = strlen(s);
        build_sa(s, sa);
        get_height(s,sa,lcp);
        int ans = 0;
//        for (int i = 1; i <= n; ++i) printf("%d %d\n", sa[i],lcp[i]);
        for (int i = 1; i <= n; ++i){
            ans += n-sa[i];
            ans -= lcp[i];
        }
        printf("%d\n",ans);
    }
    return 0;
}

DISUBSTR - Distinct Substrings

no tags 

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.