Description
Farmer John has noticed that the quality of milk given by his cows varies from day to day. On further investigation, he discovered that although he can’t predict the quality of milk from one day to the next, there are some regular patterns in the daily milk quality.
To perform a rigorous study, he has invented a complex classification scheme by which each milk sample is recorded as an integer between 0 and 1,000,000 inclusive, and has recorded data from a single cow over N (1 ≤ N ≤ 20,000) days. He wishes to find the longest pattern of samples which repeats identically at least K (2 ≤ K ≤ N) times. This may include overlapping patterns – 1 2 3 2 3 2 3 1 repeats 2 3 2 3 twice, for example.
Help Farmer John by finding the longest repeating subsequence in the sequence of samples. It is guaranteed that at least one subsequence is repeated at least K times.
Input
Line 1: Two space-separated integers: N and K
Lines 2..N+1: N integers, one per line, the quality of the milk on day i appears on the *i*th line.
Output
Line 1: One integer, the length of the longest pattern which occurs at least K times
Sample Input
8 2
1
2
3
2
3
2
3
1
Sample Output
4
思路
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。
和POJ1743
思路基本一样,都是求最长重复子串,不同的是这个题加了条件,要求:
- 字符串可以重叠
- 出现次数>=k
我们同样采取二分的方法,首先按照二分的长度mid进行分组,使得每一个组中相邻后缀的最长公共前缀的值都>=mid
(就是height[i]>=mid
),那么只要有一个组中元素的数量>=k
时就满足情况
论文题解:
代码
#include <cstdio>
#include <iostream>
#include <cstring>
#include <algorithm>
using namespace std;
#define mem(a, b) memset(a, b, sizeof(a))
const int N = 1e5 + 10;
int t1[N], t2[N], c[N], r[N], sa[N], rak[N], height[N];
bool cmp(int *r, int a, int b, int l)
{
return r[a] == r[b] && r[a + l] == r[b + l];
}
void da(int str[], int sa[], int rak[], int height[], int n, int m)
{
n++;
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] = str[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;
}
int k = 0;
n--;
for (i = 0; i <= n; i++)
rak[sa[i]] = i;
for (i = 0; i < n; i++)
{
if (k)
k--;
j = sa[rak[i] - 1];
while (str[i + k] == str[j + k])
k++;
height[rak[i]] = k;
}
}
int n, a[N], k;
bool check(int mid)
{
int cnt = 1;
for (int i = 2; i <= n; i++)
{
if (height[i] >= mid)
{
cnt++;
continue;
}
if (cnt >= k)
return true;
cnt = 1;
}
if (cnt >= k)
return true;
return false;
}
int main()
{
// freopen("in.txt", "r", stdin);
while (~scanf("%d%d", &n, &k))
{
int temp = 0;
for (int i = 0; i < n; i++)
{
scanf("%d", &a[i]);
temp = max(temp, a[i]);
}
a[n] = 0;
da(a, sa, rak, height, n, temp + 1);
int l = 0, r = n, ans = 0;
while (l <= r)
{
int mid = (l + r) >> 1;
if (check(mid))
{
ans = mid;
l = mid + 1;
}
else
r = mid - 1;
}
printf("%d\n", ans);
}
return 0;
}
/*
8 2
2 6 8 3 9 1 7 5
8 2
2 7 3 3 8 8 8 8
*/