spoj 694 Distinct Substrings（不相同的子串的个数）

Distinct Substrings

Time Limit: 159MS

Memory Limit: Unknown

64bit IO Format: %lld & %llu

Submit Status

Description

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：给定一个字符串，求不相同的子串的个数。
思路：每个子串一定是某个后缀的前缀，那么原问题等价于求所有后缀之间的不相同的前缀的个数。如果所有的后缀按照suffix(sa[1]), suffix(sa[2]),suffix(sa[3]), …… ,suffix(sa[n])的顺序计算，不难发现，对于每一次新加进来的后缀suffix(sa[k]),它将产生n-sa[k]+1 个新的前缀。但是其中有height[k]个是和前面的字符串的前缀是相同的。所以suffix(sa[k])将“贡献”出n-sa[k]+1- height[k]个不同的子串。累加后便是原问题的答案。这个做法的时间复杂度为O(n)。

AC代码：

#include <cstdio>
#include <cstring>
#include <iostream>
#include <cmath>
#include <algorithm>
#include <queue>
#define ll long long
using namespace std;

const int maxn = 1005;
const int maxm = 20000;
const int INF = 1e9;

char s[maxn];
int sa[maxn], t[maxn], t2[maxn], c[maxn], n;
int rank[maxn], height[maxn];
void build_sa(int n, int m){
    int i, *x = t, *y = t2;
    for(i = 0; i < m; i++) c[i] = 0;
    for(i = 0; i < n; i++) c[x[i] = s[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(int k = 1; k <= n; k <<= 1)
    {
        int p = 0;
        for(i = n - k; i < n; i++) y[p++] = i;
        for(i = 0; i < n; i++) if(sa[i] >= k) y[p++] = sa[i] - k;
        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]] = y[sa[i - 1]] == y[sa[i]] && y[sa[i - 1] + k] == y[sa[i] + k] ? p - 1 : p++;
        if(p >= n) break;
        m = p;
    }
}
void getHeight(){
    int i, j, k = 0;
    for(i = 1; i <= n; i++) rank[sa[i]] = i;
    for(i = 0; i < n; i++)
    {
        if(k) k--;
        j = sa[rank[i] - 1];
        while(s[i + k] == s[j + k]) k++;
        height[rank[i]] = k;
    }
}
int main()
{
    int t;
    scanf("%d", &t);
    while(t--)
    {
        scanf("%s", s);
        n = strlen(s);
        build_sa(n + 1, 256);
        getHeight();
        ll ans = 0;
        for(int i = 1; i <= n; i++)
        {
            ans += n - sa[i] - height[i];
        }
        cout<<ans<<endl;
    }
    return 0;
}