You are given two strings A and B. Find the number of distinct strings which appear in both A and B . A string s is said to appear in S iff s is a substring (appears contiguously) of S.
Input
- The first line of the input contains an integer T denoting the number of test cases. The description ofT test cases follows.
- Each test case consists of two lines.
- The first line contains two space separated integers n1 and n2 denoting the lengths of A and B.
- The second line contains two space separated strings A and B.
Output
- For each test case output a single number denoting the number of distinct strings appearing in Aand B .
Constraints
- 1 ≤ T ≤ 104
- 1 ≤ n1, n2 ≤ 105
- Sum of n1 + n2 over all test cases ≤ 105
- A is a string consisting of n1 lowercase characters ('a'-'z').
- B is a string consisting of n2 lowercase characters ('a'-'z').
Example
Input: 2 3 5 aad zaacd 4 4 abcd lmno Output: 3 0
Explanation
Example case 1. The three strings are "a", "d", "aa".
Example case 2. There are no strings that appear in both A and B.
https://www.codechef.com/IOPC2015/problems/IOPC15G/kuangbin大神的代码。。还没看懂先瞻仰一下。。
#include <stdio.h>
#include <string.h>
#include <iostream>
#include <algorithm>
#include <vector>
#include <queue>
#include <set>
#include <map>
#include <string>
#include <math.h>
#include <stdlib.h>
#include <time.h>
using namespace std;
/*
*suffix array
*倍增算法 O(n*logn)
*待排序数组长度为n,放在0~n-1中,在最后面补一个0
*da(str ,n+1,sa,rank,height, , );//注意是n+1;
*例如:
*n = 8;
*num[] = { 1, 1, 2, 1, 1, 1, 1, 2, $ };注意num最后一位为0,其他大于0
*rank[] = { 4, 6, 8, 1, 2, 3, 5, 7, 0 };rank[0~n-1]为有效值,rank[n]必定为0无效值
*sa[] = { 8, 3, 4, 5, 0, 6, 1, 7, 2 };sa[1~n]为有效值,sa[0]必定为n是无效值
*height[]= { 0, 0, 3, 2, 3, 1, 2, 0, 1 };height[2~n]为有效值
*
*/
const int MAXN=200010;
int t1[MAXN],t2[MAXN],c[MAXN];//求SA数组需要的中间变量,不需要赋值
//待排序的字符串放在s数组中,从s[0]到s[n-1],长度为n,且最大值小于m,
//除s[n-1]外的所有s[i]都大于0,r[n-1]=0
//函数结束以后结果放在sa数组中
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;
//第一轮基数排序,如果s的最大值很大,可改为快速排序
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;
//直接利用sa数组排序第二关键字
for(i = n-j; i < n; i++)y[p++] = i;//后面的j个数第二关键字为空的最小
for(i = 0; i < n; i++)if(sa[i] >= j)y[p++] = sa[i] - j;
//这样数组y保存的就是按照第二关键字排序的结果
//基数排序第一关键字
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];
//根据sa和x数组计算新的x数组
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;//下次基数排序的最大值
}
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];
int r[MAXN],sa[MAXN];
char str1[MAXN],str2[MAXN];
bool check(int i,int j,int n,int m){
return (i < n && j > n) || (i > n && j < n);
}
int main()
{
int T;
int n,m;
scanf("%d",&T);
while(T--){
scanf("%d%d",&n,&m);
scanf("%s%s",str1,str2);
for(int i = 0;i < n;i++)
r[i] = str1[i]-'a'+1;
r[n] = 27;
for(int i = 0;i < m;i++)
r[n+1+i] = str2[i]-'a'+1;
r[n+m+1] = 0;
da(r,sa,rank,height,n+m+1,28);
long long ans = 0;
int tmp = 0;
for(int i = 2;i <= n+m+1;i++){
tmp = min(tmp,height[i]);
if(check(sa[i],sa[i-1],n,m)){
ans += height[i]-tmp;
tmp = height[i];
}
}
cout<<ans<<endl;
}
return 0;
}