题目:
http://poj.org/problem?id=3261
题意:
给一个数组,求数组中至少出现k次的最长可重叠子串
思路:
后缀数组可以解决的经典问题之一
先建立后缀数组,然后二分枚举长度,把问题转化为是否存在一个至少出现k次的长度为mid的可重叠子串,这个判定问题可以在O(n)的时间内解决,遍历一次后缀数组即可,乘上二分的时间复杂度O(lgn),O(nlgn)的规模可解决本题。
这里讲一下怎么一次遍历height数组就能判定,将sa序列视为若干组,每组内的任意两个后缀必须满足lcp值大于等于mid,即在height数组中某个区间的值均大于等于mid,注意,这里height数组中的[l,r]区间对应的是,后缀排名[l-1,r]的后缀。因为这分组在height中是一段段连续的区间,所以遍历一次就能实现。如果存在一组满足组内后缀数大于等于k则判定为真,否则为假。
代码:
#include <stdio.h>
#include <iostream>
#include <string.h>
#include <algorithm>
using namespace std;
#define rep(i,n) for(int i = 0; i < n; i++)
const int MAXSIZE = 2*1e5 + 100;
int rk[MAXSIZE], sa[MAXSIZE], height[MAXSIZE], wa[MAXSIZE], res[MAXSIZE];
char w[MAXSIZE];
int len;
void getSa(int up) {
int *k = rk, *id = height, *r = res, *cnt = wa;
rep(i, up) cnt[i] = 0;
rep(i, len) cnt[k[i] = w[i]]++;
rep(i, up) cnt[i + 1] += cnt[i];
for (int i = len - 1; i >= 0; i--) {
sa[--cnt[k[i]]] = i;
}
int d = 1, p = 0;
while (p < len){
for (int i = len - d; i < len; i++) id[p++] = i;
rep(i, len) if (sa[i] >= d) id[p++] = sa[i] - d;
rep(i, len) r[i] = k[id[i]];
rep(i, up) cnt[i] = 0;
rep(i, len) cnt[r[i]]++;
rep(i, up) cnt[i + 1] += cnt[i];
for (int i = len - 1; i >= 0; i--) {
sa[--cnt[r[i]]] = id[i];
}
swap(k, r);
p = 0;
k[sa[0]] = p++;
rep(i, len - 1) {
if (sa[i] + d < len && sa[i + 1] + d < len && r[sa[i]] == r[sa[i + 1]] && r[sa[i] + d] == r[sa[i + 1] + d])
k[sa[i + 1]] = p - 1;
else k[sa[i + 1]] = p++;
}
if (p >= len) return;
d <<= 1, up = p, p = 0;
}
}
void getHeight() {
int i, k, h = 0;
rep(i, len) rk[sa[i]] = i;
rep(i, len) {
if (rk[i] == 0)
h = 0;
else {
k = sa[rk[i] - 1];
if (h) h--;
while (w[i + h] == w[k + h]) h++;
}
height[rk[i]] = h;
}
}
void getSuffix() {
int up = 0;
rep(i, len) {
up = up > w[i] ? up : w[i];
}
w[len] = 0;
getSa(up + 1);
getHeight();
}
int solve(int k){
getSuffix();
int l = 0, r = len;
while (l<=r){
int mid = (l+r)>>1;
bool flag = false;
int sum = 1;
for (int i=1;i<len;++i){
if (height[i]>=mid){
sum++;
}
else {
if (sum >= k){
flag = true;
break;
}
sum = 1;
}
}
if (sum >= k){
flag = true;
}
if (flag)
l = mid + 1;
else
r = mid - 1;
//cout<<"mid res: "<<mid<<" "<<flag<<endl;
}
return r;
}
int main(){
int n,k;
cin>>n>>k;
for (int i=0;i<n;++i){
scanf("%d",w+i);
}
len = n;
int ans = solve(k);
cout<<ans<<endl;
return 0;
}