POJ 2778 DNA Sequence(AC自动机+矩阵快速幂)

Language: Default DNA Sequence Time Limit: 1000MS   Memory Limit: 65536K Total Submissions: 13522   Accepted: 5152 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 Source POJ Monthly--2006.03.26,dodo

题解: 我们可以通过AC自动机来寻找一个状态转移矩阵, ary[i][j]表示从第i个节点到第j个节点有多少种走法. 如何构造这个矩阵就是关键, 我们可以通过fail指针, 分别找出这个节点到A, C, T, G四个节点的走法, 从而构造出这个矩阵, 如代码所示. 另外需要注意的一点是, 如果fail指针指向的节点被感染了, 那么这个节点一定会被感染的.

#include <cstdio>
#include <cstring>
#include <queue>

using namespace std;
const int N = 110;
const int MOD = 100000;
typedef long long LL;

struct Matrix{
	int ary[N][N];
	int row, col;
	void init() {
		memset(ary, 0, sizeof(ary));
	}
	Matrix (int row = N, int col = N) {
		this->row = row, this->col = col;
		init();
	}
	Matrix operator=(const Matrix & A) {
		row = A.row;
		col = A.col;
		for (int i = 0; i < row; ++i)
			for (int j = 0; j < col; ++j)
				ary[i][j] = A.ary[i][j];
	}
};

const Matrix operator*(const Matrix & A, const Matrix & B) {
	Matrix t;
	t.row = A.row;
	t.col = B.col;
	for (int i = 0; i < A.row; ++i)
		for (int j = 0; j < B.col; ++j) {
			for (int k = 0; k < A.col; ++k)
				t.ary[i][j] += (int)(((LL)A.ary[i][k] * (LL)B.ary[k][j]) % MOD);
			t.ary[i][j] %= MOD;
		}
	return t;
}

struct Trie{
	int next[N][4], fail[N];
	bool vis[N];
	int total, root;
	Matrix mt;

	int new_node() {
		for (int i = 0; i < 4; ++i)
			next[total][i] = -1;
		vis[total] = false;
		return total++;
	}

	void init() {
		total = 0;
		mt.init();
		root = new_node();
	}

	int get_index(char ch) {
		if (ch == 'A') return 0;
		if (ch == 'T') return 1;
		if (ch == 'G') return 2;
		return 3;
	}

	void insert(char *str) {
		int cur = root;
		while (*str) {
			int idx = get_index(*str);
			if (next[cur][idx] == -1)
				next[cur][idx] = new_node();
			cur = next[cur][idx];
			++str;
		}
		vis[cur] = true;
	}

	void build() {
		queue<int> q;
		fail[root] = -1;
		q.push(root);

		while (!q.empty()) {
			int cur = q.front();
			q.pop();

			if (fail[cur] != -1 && vis[fail[cur]] == true)
				vis[cur] = true;

			for (int i = 0; i < 4; ++i) {
				if (next[cur][i] == -1) 
					next[cur][i] = fail[cur] == -1 ? root : next[fail[cur]][i];
				else {
					fail[next[cur][i]] = fail[cur] == -1 ? root : next[fail[cur]][i];
					q.push(next[cur][i]);
				}
			}
		}

		mt.row = mt.col = total;

		for (int i = 0; i < total; ++i)
			for (int j = 0; j < 4; ++j)
				if (vis[next[i][j]] == false)
					++mt.ary[i][next[i][j]];
	}
}tree;

int quick_pow(Matrix & mt, int n) {
	Matrix ans, tmp = mt;
	ans.row = mt.row, ans.col = mt.col;
	for (int i = 0; i < mt.row; ++i)
		ans.ary[i][i] = 1;

	while (n) {
		if (n & 1)
			ans = ans * tmp;
		n >>= 1;
		tmp = tmp * tmp;
	}

	int res = 0;
	for (int i = 0; i < mt.row; ++i)
		res += ans.ary[0][i];
	return res % MOD;
}

int main() {
	int n, m;

	while (~scanf("%d%d", &n, &m)) {
		tree.init();
		char str[20];
		for (int i = 0; i < n; ++i) {
			scanf("%s", str);
			tree.insert(str);
		}
		tree.build();
		int ans = quick_pow(tree.mt, m);
		printf("%d\n", ans);
	}

	return 0;
}