题意:每次给你一个字符串,问"子串不重叠出现至少两次"这样子串的个数。
解法:先求后缀数组,sa 表示 第几个后缀,height[i]表示 sa[i-1]与sa[i]的最长公共前缀。之后就用for循环来寻找每一个长度的子串的个数:当height[i]>=len时,就更新最大右编号和最小左编号。反之则,判断右编号减去左编号是否大于等于len,如果大于就把ans++,最后给左编号和右编号赋初值。近乎于暴力。。。
#include<iostream>
#include<cstring>
#include<string>
#include<cmath>
#include<cstdio>
#include<algorithm>
using namespace std;
const int maxnode = 1e5+10;
const double eps = 1e-8;
char s[maxnode];
int sa[maxnode], t[maxnode], t2[maxnode], c[maxnode], n;
void buildsa(int m)//字符最大范围 一般是256
{
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 = 0; 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 = 0; 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;
}
}
int rank[maxnode], height[maxnode];
void getheight()
{
int i, j, k = 0;
for(i = 0; i < n; ++i) rank[sa[i]] = i;
for(i = 0; i < n; ++i)
{
if(k) k--;
if(!rank[i]) continue;
int j = sa[rank[i]-1];
while(s[i+k] == s[j+k]) k++;
height[rank[i]] = k;
}
}
int main()
{
//freopen("in.txt","r",stdin);
while(~scanf("%s",s)&&s[0]!='#')
{
memset(height,0,sizeof height);
n = strlen(s); n++;
buildsa(256);
getheight();
int ans = 0;
for(int len = 1 ; len <= n/2+1 ; ++ len)
{
int left = 1e8, right = -1;
for(int i = 2 ; i <= n ; ++ i)
{
if(height[i]>=len)
{
left = min(left, sa[i-1]);
left = min(left, sa[i]);
right = max(right, sa[i-1]);
right = max(right, sa[i]);
}
else
{
if(right!=-1&&left!=1e8&&right-left>=len) ans++;
left = 1e8; right = -1;
}
}
}
printf("%d\n",ans);
}
return 0;
}