string string string
TimeLimit: 2000/1000 MS (Java/Others) Memory Limit:32768/32768 K (Java/Others)
Total Submission(s): 714 Accepted Submission(s): 206
Problem Description
UncleMao is a wonderful ACMER. One day he met an easy problem, but Uncle Mao was solazy 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 animportant string, and you need to find out how many substrings which areimportant strings.
Input
The first line contains an integer T (T≤100) implying thenumber of test cases.
For each test case, there are two lines:
the first line contains an integer k (k≥1) which isdescribed 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
【题意】
给出一个字符串,问它的字串中有哪些在字符串中出现了k次。
【思路】
我们先处理出sa数组和height数组,然后由于sa数组相邻的两项是最接近的,也就是说出现了k次的子串它的起始位置在sa数组中是连续的。
那么我们考虑去枚举长度为区间,比如我们现在枚举的区间为[l,l+k-1],那么我们我们利用RMQ求出这一段区间的lcp(最长公共前缀)。
假设lcp为x,那么说明在枚举的区间内有x个子串在字符串中至少出现了k次,但是我们要求的是正好出现k次的。
很容易想到可以用至少出现k次的数目减去至少出现(k+1)次的便是正好出现k次的数目。
对于一个长度为k的区间来说,我们可以在头部或尾部加一个位置使它变成长度为(k+1)的区间(边界情况只有一种情况),那么对于可以在两端增加的,如果减去区间[l-1,l+k-1]和区间[l,l+k]的lcp,显然多减了区间[i-1,i+k]的lcp,再将这一部分加上即可。
#include <cstdio>
#include <cmath>
#include <cstring>
#include <algorithm>
using namespace std;
#define mst(a,b) memset((a),(b),sizeof(a))
#define rush() int T;scanf("%d",&T);while(T--)
typedef long long ll;
const int maxn = 100005;
const ll mod = 998244353;
const int INF = 0x3f3f3f3f;
const double eps = 1e-9;
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 *Rank,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++) Rank[sa[i]]=i;
for(i=0; i<n; i++)
{
if(k) k--;
j=sa[Rank[i]-1];
while(str[i+k]==str[j+k]) k++;
height[Rank[i]]=k;
}
}
int Rank[maxn],height[maxn],sa[maxn];
char str[maxn];
int r[maxn];
int dp[maxn][30];
void initRMQ(int n)
{
for(int i=0;i<n;i++) dp[i][0]=height[i];
for(int j=1;(1<<j)<=n;j++)
for(int i=0;i+(1<<j)-1<n;i++)
{
dp[i][j]=min(dp[i][j-1],dp[i+(1<<(j-1))][j-1]);
}
}
int len;
int lcp(int l,int r)
{
if(l==r) return len-sa[r];
/*l=Rank[l],r=Rank[r];
if(l>r) swap(l,r);*/
l++;
int k=0;
while((1<<(k+1))<=r-l+1) k++;
return min(dp[l][k],dp[r-(1<<k)+1][k]);
}
int main()
{
int k;
rush()
{
scanf("%d%s",&k,str);
int n=strlen(str);
len=n;
for(int i=0; i<n; i++)
{
r[i]=str[i]-'a'+1;
}
r[n]=0;
da(r,sa,Rank,height,n,30); //得到sa,Rank,height数组
initRMQ(n+1); //RMQ预处理区间最长公共前缀
ll ans=0;
for(int i=1; i+k-1<=n; i++) //枚举区间
{
ans+=lcp(i,i+k-1);
if(i>1) ans-=lcp(i-1,i+k-1);
if(i+k<=n) ans-=lcp(i,i+k);
if(i>1&&i+k<=n) ans+=lcp(i-1,i+k);
}
printf("%I64d\n",ans);
}
return 0;
}