HDU-6194 string string string 后缀数组

pxlsdz

于 2019-08-27 18:27:57 发布

阅读量250

点赞数

CC 4.0 BY-SA版权

分类专栏： # 字符串——后缀数组 # ACM算法模板题

本文链接：https://blog.csdn.net/sdz20172133/article/details/100103407

ACM算法模板题同时被 2 个专栏收录

229 篇文章

订阅专栏

字符串——后缀数组

6 篇文章

订阅专栏

本文介绍了一种使用后缀数组和后缀自动机解决子串计数问题的方法，旨在找出在一个给定字符串中恰好出现k次的所有子串数量。通过构建后缀数组，计算最长公共前缀（LCP），并利用高度数组来确定满足条件的子串。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

string string string

Time Limit: 2000/1000 MS (Java/Others) Memory Limit: 32768/32768 K (Java/Others)
Total Submission(s): 3500 Accepted Submission(s): 1181

Problem Description

Uncle Mao is a wonderful ACMER. One day he met an easy problem, but Uncle Mao was so lazy that he left the problem to you. I hope you can give him a solution.
Given a string s, we define a substring that happens exactly k times as an important string, and you need to find out how many substrings which are important strings.

Input

The first line contains an integer T (T≤100) implying the number of test cases.
For each test case, there are two lines:
the first line contains an integer k (k≥1) which is described above;
the second line contain a string s (length(s)≤105).
It's guaranteed that ∑length(s)≤2∗106.

Output

For each test case, print the number of the important substrings in a line.

Sample Input

2 2 abcabc 3 abcabcabcabc

Sample Output

6 9

Source

2017 ACM/ICPC Asia Regional Shenyang Online

Recommend

liuyiding | We have carefully selected several similar problems for you: 6724 6723 6722 6721 6720

题意：

给你一个字符串s，让你求出恰好出现了k次的子串的数量。

分析：

建立后缀数组，对每对sa[i]和sa[i+k-1]求lcp，再减去height[i]和height[i+k]中较大的那个，即len=lcp(sa[i],sa[i+k-1])-max(height[i],height[i+k])，如果还有剩余则说明由s[sa[i]]的前[1,len]个字母组成的子串均恰好出现了k次。

后缀自动机待补

#include <bits/stdc++.h>
using namespace std;
const int maxn=200000+1000;
int len1,len2;
struct SuffixArray
{
    char s[maxn];
    ///_rank[i] 第i个后缀的排名; SA[i] 排名为i的后缀位置; Height[i] 排名为i的后缀与排名为(i-1)的后缀的LCP
    int sa[maxn],_rank[maxn],height[maxn];
    ///c[i] 基数排序辅助数组
    int t1[maxn],t2[maxn],c[maxn],n;
    int dmin[maxn][21];
    
    void init()
    {
    	memset(height,0,sizeof(height));
        memset(_rank,0,sizeof(_rank));
        memset(sa,0,sizeof(sa));
        memset(c,0,sizeof(c));
        memset(t1,0,sizeof(t1));
        memset(t2,0,sizeof(t2));
        memset(dmin,0,sizeof(dmin));
    }

    void build_sa(int m)  ///m大于s[]数组出现的任意字符的int值
    {
        /// x[i]是第i个元素的第一关键字  y[i]表示第二关键字排名为i的数，第一关键字的位置
        int i,p,*x=t1,*y=t2;
        x[n]=y[n]=-1;
        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)
        {
            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[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++)
            {
                if(y[sa[i]]==y[sa[i-1]]&&y[sa[i]+k]==y[sa[i-1]+k])
                    x[sa[i]]=p-1;
                else
                    x[sa[i]]=p++;
            }
            if(p>=n)
                break;
            m=p;
        }
    }

    void build_height()//单个字符也行
    {
        int i,j,k=0,r;
        for(i=0; i<n; i++)
            _rank[sa[i]]=i;
        height[0]=0;
        for(i=0; i<n; i++)
        {
            if(k)
                k--;
            r=_rank[i];
            if(r==0)
                continue;
            j=sa[r-1];
            while(s[i+k]==s[j+k])
                k++;
            height[_rank[i]]=k;
        }
    }
    int LongestMessage() //最长公共子串
    {
        int ans=0;
        for(int i=2; i<n; i++)
        {
            int a1=sa[i-1],a2=sa[i];
            if(a1>a2)
                swap(a1,a2);
            if(a1>=0&&a1<=len1-1&&a2>=len1+1&&a2<=len1+len2)
                ans = max(ans,height[i]);
        }
        return ans;
    }


    void initMin()
    {

        for(int i=0; i<n; i++)
            dmin[i][0]=height[i];
        for(int j=1; (1<<j)<=n; j++)
            for(int i=0; i+(1<<j)-1<n; i++)
                dmin[i][j]=min(dmin[i][j-1],dmin[i+(1<<(j-1))][j-1]);
    }
    int RMQ(int L,int R)//取得范围最小值
    {
        int k=0;
        while((1<<(k+1))<=R-L+1)
            k++;
        return min(dmin[L][k], dmin[R-(1<<k)+1][k]);
    }
    int LCP(int i,int j)//求后缀i和j的LCP最长公共前缀
    {
         //if(i==j) return n-i;
        //int L=_rank[i],R=_rank[j];//求后缀i与后缀j的LCP
        
		if(i==j)
            return n-sa[i];
        int L=i,R=j;//直接求排名i与j后缀的LCP
        if(L>R)
            swap(L,R);
        L++;//注意这里
        return RMQ(L,R);
    }
    //主函数里添加  sa.n=strlen(sa.s)+1;sa.s[sa.n-1]=0;
    int num()//子串的个数
    {
        int ans=0;
        for(int i=1; i<n; i++)
            ans += n-1-sa[i]-height[i];
        return ans;
    }

    int get_LR(int be,int len,int &L,int &R)
    {
        int pos=_rank[be];
        int l=0,r=pos;
        while(l<r)
        {
            int mid=(l+r)>>1;
            if(RMQ(mid+1,pos)>=len)
                r=mid;
            else
                l=mid+1;
        }
        L=l;

        l=pos;
        r=n-1;
        while(l<r)
        {
            int mid=(l+r+1)>>1;
            if(RMQ(pos+1,mid)>=len)
                l=mid;
            else
                r=mid-1;

        }
        R=l;
        R++;
        L++;

    }
    //恰好出现w次子串的个数
    int num_w(int w)
    {
    	int ans=0;
    	for(int i=0; i+w-1<n; i++)
            ans+=max(0,LCP(i,i+w-1)-max(height[i],height[i+w]));
		return ans;
    }
    void out()
    {
        for(int i=0; i<n; i++)
        {
            cout<<sa[i]<<" ";
        }
        cout<<endl;
        for(int i=0; i<n; i++)
        {
            cout<<_rank[i]<<" ";
        }
        cout<<endl;
        for(int i=0; i<n; i++)
        {
            cout<<height[i]<<" ";
        }
        cout<<endl;
    }
} sa;
int main()
{
    int t;
    scanf("%d",&t);
    while(t--)
    {
        int w;
        scanf("%d",&w);
        sa.init();
        scanf("%s",sa.s);
        sa.n=strlen(sa.s);
        sa.build_sa(256);
        sa.build_height();
        sa.initMin();
        int ans=sa.num_w(w);
        
        printf("%d\n",ans);
    }
    return 0;
}