题目链接:http://poj.org/problem?id=3261
题目大意:给你一组数,和一个数k,代表了要重复次数,问你最长的重复出现了K次子串的长度是多少 (子串可重叠)
思路: 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)。
AC代码:
#include <cstdio>
#include <iostream>
#include <cstring>
#include <algorithm>
using namespace std;
const int maxn = 20005;
int sa[maxn], t1[maxn], t2[maxn], c[maxn];
int ranks[maxn], height[maxn], s[maxn];
bool cmp(int *r, int a, int b, int l){
return r[a] == r[b] && r[a+l] == r[b+l];
}
void build_sa(int s[], int n, int m)
{
int i, j, p, *x = t1, *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 (j = 1; j <= n; j <<= 1) {
p = 0;
for (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 < 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]] = cmp(y, sa[i-1], sa[i], j) ? p-1 : p++;
if(p >= n) break;
m = p;
}
}
void getHeight(int s[], int n)
{
int i, j, k = 0;
for (i = 0; i <= n; ++i) ranks[sa[i]] = i;
for (i = 0; i < n; ++i) {
if(k) k--;
j = sa[ranks[i]-1];
while (s[i+k] == s[j+k]) k++;
height[ranks[i]] = k;
}
}
bool check(int n, int k, int t)
{
int num = 1;
for (int i = 2; i <= n; ++i) {
if(height[i] >= t){
num++;
if(num >= k) return true;
}
else num = 1;
}
return false;
}
int main()
{
int n, k;
while (~scanf("%d %d", &n, &k)) {
int maxs = 0;
for (int i = 0; i < n; ++i) {
scanf("%d", &s[i]);
maxs = max(maxs, s[i]);
}
s[n] = 0;
build_sa(s, n+1, maxs+1);
getHeight(s, n);
int l = 0, r = n, ans = 0;
while (l <= r) {
int mid = (l+r) / 2;
if(check(n, k, mid)){
ans = mid;
l = mid+1;
}
else r = mid-1;
}
cout << ans << '\n';
}
return 0;
}
写的时候,1和l打错了,一直没看出来,debug了半天.......