【POJ2778】DNA Sequence

Description

It's well known that DNA Sequence is a sequence only contains A, C, T and G, and it's very useful to analyze a segment of DNA Sequence,For example, if a animal's DNA sequence contains segment ATC then it may mean that the animal may have a genetic disease. Until now scientists have found several those segments, the problem is how many kinds of DNA sequences of a species don't contain those segments.

Suppose that DNA sequences of a species is a sequence that consist of A, C, T and G,and the length of sequences is a given integer n.

Input

First line contains two integer m (0 <= m <= 10), n (1 <= n <=2000000000). Here, m is the number of genetic disease segment, and n is the length of sequences.

Next m lines each line contain a DNA genetic disease segment, and length of these segments is not larger than 10.

Output

An integer, the number of DNA sequences, mod 100000.

Sample Input

4 3

AT

AC

AG

AA

Sample Output

36


题意简单来说,就是【POJ1625】检查Censored!加了矩阵乘法优化


思路:

AC自动机+DP,处理失败指针(fail)时继承失败指针的标记(flag)

trie[v].flag|=trie[trie[trie[u].fail].ch[i]].flag;

o(n)太大,用矩阵乘法优化

注意:

结构体初始化清零,运算过程要mod,不然要开long long

代码:

#include <iostream>
#include <cstdio>
#include <queue>
#include <cstring>
#define mod 100000
using namespace std;
int m,n,cnt;
struct node{
	long long e[105][105];
	void clear(){memset(e,0,sizeof(e));}
}sequ,ans;
int rflag(char a)
{
	if(a=='A') return 0;
	if(a=='C') return 1;
	if(a=='T') return 2;
	if(a=='G') return 3;
}
struct fdfdfd{
	int flag,fail,ch[5];
	void clear(){flag=0; fail=0; memset(ch,0,sizeof(ch));}
}trie[105];
void insert(char a[],int len)
{
	int root=0;
	for(int i=0;i<len;++i)
	{
		int j=rflag(a[i]);
		if(!trie[root].ch[j]) trie[cnt+1].clear(),trie[root].ch[j]=++cnt;
		root=trie[root].ch[j];
	}
	trie[root].flag=1;
}
void getfail()
{
	queue<int> q;
	for(int i=0;i<4;++i)
		if(trie[0].ch[i]) q.push(trie[0].ch[i]);
	while(!q.empty())
	{
		int u=q.front(); q.pop();
		for(int i=0;i<4;++i)
		{
			int v=trie[u].ch[i];
			if(!v) trie[u].ch[i]=trie[trie[u].fail].ch[i];
			else
			{
				trie[v].flag|=trie[trie[trie[u].fail].ch[i]].flag;
				trie[v].fail=trie[trie[u].fail].ch[i];
				q.push(v);
			}
		}
	}
}
node Mul(node &a,node &b)
{
	node temp; temp.clear();
	for(int i=0;i<=cnt;++i)
		for(int j=0;j<=cnt;++j)
		{
			temp.e[i][j]=0;
			for(int k=0;k<=cnt;++k)	temp.e[i][j]+=a.e[i][k]*b.e[k][j]%mod,temp.e[i][j]%=mod;
		}
	return temp;
}
int main()
{
	scanf("%d%d",&m,&n);
	trie[0].clear();
	for(int i=1;i<=m;++i)
	{
		char temp[12]; scanf("%s",&temp);
		insert(temp,strlen(temp));
	}
	getfail();
	ans.clear(); sequ.clear();
	for(int i=0;i<=cnt;++i)
		for(int j=0;j<4;++j)
			if(!trie[i].flag&&!trie[trie[i].ch[j]].flag) ++sequ.e[i][trie[i].ch[j]];
	for(int i=0;i<=cnt;++i) ans.e[i][i]=1;
	for(;n;n>>=1)
	{
		if(n&1) ans=Mul(ans,sequ);
		sequ=Mul(sequ,sequ);
	}
	long long sum=0;
	for(int i=0;i<=cnt;++i) sum=(sum+ans.e[0][i])%mod;
	printf("%lld
",sum);
	return 0;
}
原文地址:https://www.cnblogs.com/wuwendongxi/p/13215944.html