POJ 3261 Milk Patterns 求可重叠的 k 次最长重复子串（后缀数组）

最新推荐文章于 2026-06-02 12:03:54 发布

原创最新推荐文章于 2026-06-02 12:03:54 发布 · 1.3k 阅读

1 ·

本内容遵循CC 4.0 BY-SA版权协议

收录于

数据结构

本文介绍了一种利用二分查找算法高效求解给定序列中最长重复子串的方法，特别适用于那些重复出现至少k次且可能重叠的子串。通过具体实现细节展示了如何运用SA-IS算法快速获取字符串的Suffix Array，并进一步计算高度数组，最终实现二分查找确定最长重复子串长度。

点击打开链接

Milk Patterns

Time Limit: 5000MS		Memory Limit: 65536K
Total Submissions: 9361		Accepted: 4218
Case Time Limit: 2000MS

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 ith line.

Output

Line 1: One integer, the length of the longest pattern which occurs at least K times

Sample Input

Sample Output

Source

USACO 2006 December Gold

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。

跟POJ1743差不多，都用二分求解，只不过这道题二分求解的是最长长度，每判断mid长度时，需要遍历一下所有的height数组，看看有没有最长公共前缀长度是mid而且数量大于k的，如果存在，则此mid满足条件，继续二分。

//4876K	172MS
#include<stdio.h>
#include<string.h>
#include<algorithm>
#define M 20007
#define MAX 1000010
using namespace std;
int sa[MAX],rank[MAX],height[MAX];
int wa[MAX],wb[MAX],wv[MAX],ws[MAX];
int num[MAX],s[MAX];
int cmp(int *r,int a,int b,int l)
{
    return r[a]==r[b]&&r[a+l]==r[b+l];
}
void get_sa(int *r,int n,int m)//求get函数
{
    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++;
    }
}
void get_height(int *r,int n)//求height函数
{
    int i,j,k=0;
    for(i=1; i<=n; i++)rank[sa[i]]=i; //求rank函数
    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++);
}
int solve(int n,int k)//二分求解最长长度
{
    int maxx=n,minn=1;
    while(minn<=maxx)
    {
        int mid=(minn+maxx)/2,count=1,flag=0;
        for(int i=2; i<=n; i++)
            if(height[i]<mid){count=1;}//如果最长公共前缀小于mid，那么count就得重新开始计数
            else
            {
                count++;
                if(count==k)//如果找到k个，说明此长度满足
                {
                    flag=1;break;
                }
            }
        if(flag){minn=mid+1;}
        else maxx=mid-1;
    }
    return maxx;
}
int main()
{
    //freopen("in.txt","r",stdin);
    int n,k;
    while(scanf("%d%d",&n,&k)!=EOF)
    {
        for(int i=0; i<n; i++)
            scanf("%d",&num[i]);
        get_sa(num,n+1,MAX);
        get_height(num,n);
        printf("%d\n",solve(n,k));
    }
    return 0;
}