Milk Patterns（poj 3261,后缀数组）

http://poj.org/problem?id=3261

Milk Patterns

Time Limit: 5000MS		Memory Limit: 65536K
Total Submissions: 8066		Accepted: 3673
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

8 2
1
2
3
2
3
2
3
1

Sample Output

4

Source

USACO 2006 December Gold

解析：

题意：

找出至少出现k此的最长子串

思路：

构造后缀数组，利用二分法找答案,扫一遍height数组，如果比设定答案小则开辟新段

0 MS 676 KB GNU C++

*/

#include<stdio.h>
#include<string.h>
#include<algorithm>
#include <iostream>
using namespace std;
const int maxn=20010;
int s[maxn];
int sa[maxn],t[maxn],t2[maxn],c[maxn],height[maxn],rank[maxn];
int vis[maxn];
void build_sa(int n,int m)
{
int i,*x=t,*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(int k=1;k<=n;k<<=1)
{
int p=0;
for(i=n-k;i<n;i++)y[p++]=i;
for(i=0;i<n;i++)if(sa[i]>=k)y[p++]=sa[i]-k;
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]]=y[sa[i-1]]==y[sa[i]]&&y[sa[i-1]+k]==y[sa[i]+k] ?p-1:p++;
if(p>=n)break;
m=p;
}
}
void getheight(int n)
{
int i,j,k=0;
for(i=0;i<n;i++)rank[sa[i]]=i;
for(i=0;i<n;i++)
{
if(k)k--;
j=sa[rank[i]-1];
while(s[i+k]==s[j+k])k++;
//printf("k==%d\n",k);
height[rank[i]]=k;
}
}
int check(int n,int len,int k)
{
int a=1;
for(int i=2;i<=n;i++)
{
if(height[i]<len)//当出现比当前的长度小时开劈一个新的段
{
a=1;
if(a>=k)
return i;//每一步都要判断是否满足条件 
}
else
{
a++;
if(a>=k)
return i;
}
}
return -1;
}
int main()
{
    int n,k,i,ans;
    while(scanf("%d%d",&n,&k)!=EOF)
    {    int m=0;
    	for(i=0;i<n;i++)
    	 {
    	 	scanf("%d",&s[i]);
    	 	if(s[i]>m)
    	 	 m=s[i];
 }
build_sa(n+1,m+1);
getheight(n);
int l=1,r=n;
int mid;
ans=0;
while(l<=r)//利用二分法找答案
{mid=(l+r)/2;
 int x=check(n,mid,k);
 if(x==-1)
   r=mid-1;
  else
  {
  	ans=mid;//因为是找最长子串，所以答案是尽量往大的一边取
  	l=mid+1;
  }
 // printf("ans=%d\n",ans);
}
     printf("%d\n",ans);
    }
    return 0;
}