poj3261Milk Patterns 二分+后缀数组

Language: Default Milk Patterns Time Limit: 5000MS   Memory Limit: 65536K Total Submissions: 9665   Accepted: 4333 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

Language: Default

题意：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。

思路：二分答案，利用height数组，将后缀分成若干组，判断是否存在一个组的后缀个数不小于k，如果存在那么存在k个相同的子串满足条件。时间复杂度为O（nlogn），详见代码：

#include<cstdio>
#include<cstring>
#include<algorithm>
using namespace std;
const int MAXN=20000+100;
const int M=1000010;
int n,K;
int a[MAXN],sa[MAXN],height[MAXN],c[M],rank[MAXN],t1[MAXN],t2[MAXN];
int cmp(int *r,int a,int b,int l)
{
    return r[a]==r[b] && r[a+l]==r[b+l];
}
void build_sa(int m)
{
    int i,k,p=0;
    int *x=t1,*y=t2;
    for(i=0;i<m;i++) c[i]=0;
    for(i=0;i<n;i++) c[x[i]=a[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(k=1;p<n;k<<=1,m=p)
    {
        for(p=0,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);
        for(p=1,x[sa[0]]=0,i=1;i<n;i++)
            x[sa[i]]=cmp(y,sa[i-1],sa[i],k)? p-1:p++;
    }
}
bool ok(int n,int m)
{
    int cnt=1;
    for(int i=1;i<=n;i++)
    {
        if(height[i]>=m)
        {
            cnt++;
            if(cnt>=K)
                return 1;
        }
        else
            cnt=1;
    }
    return 0;
}
void calheight(int n)
{
    int k=0;
    for(int i=1;i<=n;i++) rank[sa[i]]=i;
    for(int i=0;i<n;i++)
    {
        if(k) k--;
        int j=sa[rank[i]-1];
        while(a[i+k]==a[j+k]) k++;
        height[rank[i]]=k;
    }
}
int main()
{
    //freopen("text.txt","r",stdin);
    while(~scanf("%d%d",&n,&K))
    {
        for(int i=0;i<n;i++)
            scanf("%d",&a[i]),a[i]++;
        a[n++]=0;
        build_sa(1000010);
        calheight(n-1);
        int l=1,r=n-1,ans=0;
        while(l<=r)
        {
            int mid=(l+r)>>1;
            if(ok(n-1,mid))
                ans=mid,l=mid+1;
            else
                r=mid-1;
        }
        printf("%d\n",ans);
    }
    return 0;
}