HDU5769 Substring 后缀数组

题目链接：HDU5769

Substring

Time Limit: 2000/1000 MS (Java/Others)    Memory Limit: 65536/65536 K (Java/Others)
Total Submission(s): 1205    Accepted Submission(s): 469

Problem Description

?? is practicing his program skill, and now he is given a string, he has to calculate the total number of its distinct substrings. 
But ?? thinks that is too easy, he wants to make this problem more interesting. 
?? likes a character X very much, so he wants to know the number of distinct substrings which contains at least one X. 
However, ?? is unable to solve it, please help him.

 

Input

The first line of the input gives the number of test cases T;T test cases follow. 
Each test case is consist of 2 lines: 
First line is a character X, and second line is a string S. 
X is a lowercase letter, and S contains lowercase letters(‘a’-‘z’) only.

T<=30 
1<=|S|<=10^5 
The sum of |S| in all the test cases is no more than 700,000.

 

Output

For each test case, output one line containing “Case #x: y”(without quotes), where x is the test case number(starting from 1) and y is the answer you get for that case.

 

Sample Input

  
  

   
   2 
a 
abc 
b 
bbb
  
  

 

Sample Output

  
  

   
   Case #1: 3 
Case #2: 3


   
   

    
    

     
     Hint
    
    
In first case, all distinct substrings containing at least one a: a, ab, abc. 
In second case, all distinct substrings containing at least one b: b, bb, bbb.
   
   
   
    
  
  

 

题意：求母串中包含特定字符的不同子串的个数。

题目分析：显然是后缀数组的题，由于需要在子串中包含特定字符，所以我们可以先记录哪些后缀有这些字符以及最远出现的位置。之后统计每个后缀能够贡献的子串数，正常情况下子串数为len-sa[i]-height[i]，但是考虑字符的位置pos，所以子串数为len-max((sa[i]+height[i]),pos)。

//
//  main.cpp
//  HDU5769
//
//  Created by teddywang on 2016/9/22.
//  Copyright © 2016年 teddywang. All rights reserved.
//

#include <iostream>
#include<cstdio>
#include<cstring>
#include<algorithm>
using namespace std;
const int maxn=100010;
int t1[maxn],t2[maxn],c[maxn];
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 ranks[],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++)ranks[sa[i]]=i;
    for(i=0;i<n;i++)
    {
        if(k)k--;
        j=sa[ranks[i]-1];
        while(str[i+k]==str[j+k])k++;
        height[ranks[i]]=k;
    }
}
int ranks[maxn],height[maxn];
char str[maxn],s1[maxn];
int r[maxn],sa[maxn];
int pre[maxn],vis[maxn];
int main()
{
    int T;
    scanf("%d",&T);
    for(int cas=1;cas<=T;cas++)
    {
        int flag=0,fpre=0;
        scanf("%s%s",s1,str);
        int len=strlen(str);
        int n=len;
        for(int i=0;i<=len;i++) r[i]=str[i];
        r[len]=0;
        memset(vis,0,sizeof(vis));
        memset(pre,0,sizeof(pre));
        for(int i=len-1;i>=0;i--)
        {
            if(str[i]==s1[0])
            {
                flag=1;fpre=i;
            }
            if(flag==1)
            {
                vis[i]=1;
                pre[i]=fpre;
            }
        }
        long long int ans=0;
        da(r,sa,ranks,height,n,128);
        for(int i=0;i<=n;i++)
        {
            if(vis[sa[i]]) ans=ans+len-max((sa[i]+height[i]),pre[sa[i]]);
        }
        printf("Case #%d: %lld\n",cas,ans);
    }
}