题目链接:http://poj.org/problem?id=3261
题意:在序列中求连续可重复至少出现了K次的最长的子串
我们将height数组更加二分的答案分组,一个分组里面的后缀个数就是有某个子串出现的次数
代码:
#include <cstdio>
#include <cstring>
#include <algorithm>
#include <vector>
#define sf scanf
#define pf printf
using namespace std;
const int maxn = 20000 + 5;
int wa[maxn],wb[maxn],wv[maxn],ws[maxn];
int cmp(int *r,int a,int b,int l)
{return r[a]==r[b]&&r[a+l]==r[b+l];}
void da(int *r,int *sa,int n,int m)
{
int i,j,p,*x=wa,*y=wb,*t;
for(i=0;i<m;i++) ws[i]=0;
for(i=0;i<n;i++) ws[x[i]=r[i]]++;
for(i=1;i<m;i++) ws[i]+=ws[i-1];
for(i=n-1;i>=0;i--) sa[--ws[x[i]]]=i;
for(j=1,p=1;p<n;j*=2,m=p)
{
for(p=0,i=n-j;i<n;i++) y[p++]=i;
for(i=0;i<n;i++) if(sa[i]>=j) y[p++]=sa[i]-j;
for(i=0;i<n;i++) wv[i]=x[y[i]];
for(i=0;i<m;i++) ws[i]=0;
for(i=0;i<n;i++) ws[wv[i]]++;
for(i=1;i<m;i++) ws[i]+=ws[i-1];
for(i=n-1;i>=0;i--) sa[--ws[wv[i]]]=y[i];
for(t=x,x=y,y=t,p=1,x[sa[0]]=0,i=1;i<n;i++)
x[sa[i]]=cmp(y,sa[i-1],sa[i],j)?p-1:p++;
}
return;
}
int rank[maxn],height[maxn];
void calheight(int *r,int *sa,int n)
{
int i,j,k=0;
for(i=1;i<=n;i++) rank[sa[i]]=i;
for(i=0;i<n;height[rank[i++]]=k)
for(k?k--:0,j=sa[rank[i]-1];r[i+k]==r[j+k];k++);
return;
}
int num[maxn],sa[maxn];
int sub_num[maxn];
vector<int> S[maxn];
bool check(int k,int n,int CNT){
int cur = 0;
S[0].clear();
for(int i = 1;i <= n + 1;++i){
if(height[i] < k) S[++cur].clear();
S[cur].push_back(sa[i]);
}
for(int i = 0;i <= cur;++i){
if(S[i].size() >= CNT) return true;
}
return false;
}
int main(){
int n,k;
while( ~sf("%d %d",&n,&k) ){
for(int i = 0;i < n;++i) {sf("%d",&num[i]);num[i]++;sub_num[i] = num[i];}
sort(sub_num,sub_num + n);
int size = unique(sub_num,sub_num + n) - sub_num;
for(int i = 0;i < n;++i) num[i] = lower_bound(sub_num,sub_num + size,num[i]) - sub_num + 1;
num[n] = 0;
da(num,sa,n + 1,maxn);
calheight(num,sa,n);
int l = 1,r = n,m;
while(l <= r){
m = l + r >> 1;
if(check(m,n,k)){
l = m + 1;
}else r = m - 1;
}
pf("%d\n",r);
}
return 0;
}