Description
Given a string, we need to find the total number of its distinct substrings.
Input
T- number of test cases. T<=20;
Each test case consists of one string, whose length is <= 1000
Output
For each test case output one number saying the number of distinct substrings.
Example
Sample Input:
2
CCCCC
ABABA
Sample Output:
5
9
Explanation for the testcase with string ABABA:
len=1 : A,B
len=2 : AB,BA
len=3 : ABA,BAB
len=4 : ABAB,BABA
len=5 : ABABA
Thus, total number of distinct substrings is 9.
每一个后缀,其会产生 n-sa[i] 个前缀,并且会有height[i]个与前一个相同。加入当前后缀增加的不同前缀数量为: n-sa[i]+1 - height[i]. 然后整个串的不同子串数量即为,所有前缀产生的总和。
#include<iostream>
#include<cstring>
#include<cstdio>
#include<cmath>
#define inf 0x3f3f3f3f
#include<algorithm>
using namespace std;
const int MAX=1020;
int n,k;
int wa[MAX],wb[MAX],wsf[MAX],wv[MAX],sa[MAX];
int rank[MAX],height[MAX],r[MAX];
int cmp(int *r,int a,int b,int k){
return (r[a]==r[b])&&(r[a+k]==r[b+k]);
}
void da(int *r,int *sa,int n,int m)//??N????N??1????????????????cmp???
{
int i,j,p,*x=wa,*y=wb,*t;
for(i=0;i<m;i++) wsf[i]=0;
for(i=0;i<n;i++) wsf[x[i]=r[i]]++;
for(i=1;i<m;i++) wsf[i]+=wsf[i-1];
for(i=n-1;i>=0;i--) sa[--wsf[x[i]]]=i;
for(j=1,p=1;p<n;j*=2,m=p)
{
for(p=0,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<n;i++) wv[i]=x[y[i]];
for(i=0;i<m;i++) wsf[i]=0;
for(i=0;i<n;i++) wsf[wv[i]]++;
for(i=1;i<m;i++) wsf[i]+=wsf[i-1];
for(i=n-1;i>=0;i--) sa[--wsf[wv[i]]]=y[i];
for(t=x,x=y,y=t,p=1,x[sa[0]]=0,i=1;i<n;i++)
x[sa[i]]=cmp(y,sa[i-1],sa[i],j)?p-1:p++;
}
}
void calheight(int *r,int *sa,int n)//??height??,
{
int i,j,k=0;
for(i=1;i<=n;i++)
rank[sa[i]]=i; //????1~n?sa[]=(0~n-1)??
for(i=0;i<n;i++)
{
if(k) k--;
else k=0;
j=sa[rank[i]-1];
while(r[i+k]==r[j+k])
k++;
height[rank[i]]=k;
}
}
int main()
{
int T;
cin>>T;
while(T--)
{
string str;
cin>>str;
int len=str.length();
for(int i=0;i<=len-1;i++)
r[i]=str[i];
n=len;
r[n]=0;
da(r,sa,n+1,128);
calheight(r,sa,n);
int ans=0;
for(int i=1;i<=n;i++)
ans+=n-sa[i]-height[i];
cout<<ans<<endl;
}
}