可重叠的 k 次最长重复子串
给定一个字符串,求至少出现 k 次的最长重复子串,这 k 个子串可以重叠。
算法分析:
这题的做法和上一题差不多,也是先二分答案,然后将后缀分成若干组。不
同的是,这里要判断的是有没有一个组的后缀个数不小于 k。如果有,那么存在 k 个相同的子串满足条件,否则不存在。这个做法的时间复杂度为 O(nlogn)。
#include <cstdio>
#include <cstring>
#include<iostream>
#include <algorithm>
#define F(x) ((x) / 3 + ((x) % 3 == 1 ? 0 : tb))
#define G(x) ((x) < tb ? (x) * 3 + 1 : ((x) - tb) * 3 + 2)
#define ll long long
using namespace std;
const int N = 3*(1e6+5);
int wa[N], wb[N], wss[N], wv[N], sa[N];
int rak[N], height[N], cal[N],n;
char s[N],ans[N],s1[N];
int cnt[N];
int c0(int *r, int a, int b) {
return r[a] == r[b] && r[a + 1] == r[b + 1] && r[a + 2] == r[b + 2];
}
int c12(int k, int *r, int a, int b) {
if (k == 2)
return r[a] < r[b] || r[a] == r[b] && c12(1, r, a + 1, b + 1);
return r[a] < r[b] || r[a] == r[b] && wv[a + 1] < wv[b + 1];
}
void Rsort(int *r, int *a, int *b, int n, int m) {
for (int i = 0; i < n; i++) wv[i] = r[a[i]];
for (int i = 0; i < m; i++) wss[i] = 0;
for (int i = 0; i < n; i++) wss[wv[i]]++;
for (int i = 1; i < m; i++) wss[i] += wss[i - 1];
for (int i = n - 1; i >= 0; i--) b[--wss[wv[i]]] = a[i];
}
void dc3(int *r, int *sa, int n, int m) {
int i, j, *rn = r + n, *san = sa + n, ta = 0, tb = (n + 1) / 3, tbc = 0, p;
r[n] = r[n + 1] = 0;
for (i = 0; i < n; i++) if (i % 3 != 0) wa[tbc++] = i;
Rsort(r + 2, wa, wb, tbc, m);
Rsort(r + 1, wb, wa, tbc, m);
Rsort(r, wa, wb, tbc, m);
for (p = 1, rn[F(wb[0])] = 0, i = 1; i < tbc; i++)
rn[F(wb[i])] = c0(r, wb[i - 1], wb[i]) ? p - 1 : p++;
if (p < tbc) dc3(rn, san, tbc, p);
else for (i = 0; i < tbc; i++) san[rn[i]] = i;
for (i = 0; i < tbc; i++) if (san[i] < tb) wb[ta++] = san[i] * 3;
if (n % 3 == 1) wb[ta++] = n - 1;
Rsort(r, wb, wa, ta, m);
for (i = 0; i < tbc; i++) wv[wb[i] = G(san[i])] = i;
for (i = 0, j = 0, p = 0; i < ta && j < tbc; p++)
sa[p] = c12(wb[j] % 3, r, wa[i], wb[j]) ? wa[i++] : wb[j++];
for (; i < ta; p++) sa[p] = wa[i++];
for (; j < tbc; p++) sa[p] = wb[j++];
}
void calheight(int *r, int *sa, int n) {
int i, j, k = 0;
for (i = 1; i <= n; i++) rak[sa[i]] = i;
for (i = 0; i < n; height[rak[i++]] = k)
for (k ? k-- : 0, j = sa[rak[i] - 1]; r[i + k] == r[j + k]; k++);
for(int i=n;i;i--) rak[i]=rak[i-1];
for(int i=n;i;i--) sa[i]++;
}
bool check(int k,int x)
{
int ans=1;
for(int i=2;i<=n;i++)
{
if(height[i]<k)
{
if(ans>=x) return 1;
ans=1;
}
else
{
ans++;
}
}
if(ans>=x) return 1;
return 0;
}
int main(){
int k;
scanf("%d%d",&n,&k);
for(int i=1;i<=n;i++) scanf("%d",&cal[i]);
cal[n+1]=0;
dc3(cal+1,sa,n+1,1000010);
calheight(cal+1,sa,n);
int l=0,r=n;
while(l<r)
{
int mid=(l+r+1)/2;
if(check(mid,k)) l=mid;
else r=mid-1;
}
printf("%d\n",l);
}