UVA 11468 Substring AC自动机

Given a set of pattern strings, and a text, you have to find, if any of the pattern is a substring of the text. If any of the pattern string can be found in text, then print “yes”, otherwise “no” (without quotes).

But, unfortunately, that’s not what is asked here. J

The problem described above, requires a input file generator. The generator generates a text of length L, by choosing L characters randomly. Probability of choosing each character is given as priori, and independent of choosing others.

Now, given a set of patterns, calculate the probability of a valid program generating “no”.

 

Input

First line contains an integer T, the number of test cases. Each case starts with an integer K, the number of pattern strings. Next K lines each contain a pattern string, followed by an integer N, number of valid characters.  Next N lines each contain a character and the probability of selecting that character, p_i. Next an integer L, the length of the string generated. The generated text can consist of only the valid characters, given above.

 

There will be a blank line after each test case.

 

Output

For each test case, output the number of test case, and the probability of getting a “no”.

 

Constraints

·         T  ≤ 50

·         K ≤ 20

·        Length of each pattern string is between 1 and 20

·        Each pattern string consists of only alphanumeric characters (‘a’ to ‘z’, ‘A’ to ‘Z’,’0’ to ‘9’)

·        Valid characters are all alphanumeric characters

·        ∑p_i = 1

·        L ≤ 100

Sample Input                             Output for Sample Input

2 1 a 2 a 0.5 b 0.5 2   2 ab ab 2 a 0.2 b 0.8 2

Case #1: 0.250000 Case #2: 0.840000

 

题意：给出一些字符和各自的选择概率，随机选择L次后将得到一个长度为L的随机字符串S，给出K个模板串，计算S不包含任何一个串的概率（即任何一个模板串都不是S的连续子串）

思路：AC自动机+DP。首先将所给病毒串建立trie图。末尾+上标记。然后DP转移为

           dp[i+1] = dp[qq[j] -> next[k] -> cnt] += dp[i][j] * p[k];

           即长度为I，当前状态为J，后面添加一个字符转移到的状态的概率为dp[i][j]的概率乘于该字符的概率。

#include <iostream>
#include <cstdio>
#include <cstring>
using namespace std;
#define maxn 15000
int Cnt = 0;
double dp[108][500];
double p[68];
struct node
{
	node * fail;
	node * next[62];
	int cnt,end;
	node()
	{
		fail = NULL;
		for(int i = 0;i < 62;i++)
			next[i] = NULL;
		cnt = Cnt++;
		end = 0;
	}
}*q[maxn],*qq[maxn];
char str[28];
int first,rear;

int idx(char c)
{
	if(c >= 'a' && c <= 'z')	return c - 'a';
	if(c >= 'A' && c <= 'Z')	return c - 'A' + 26;
	return c - '0' + 52;
}

void Creat_Trie(char * s,node * root)
{
	int i,id,len;
	node * p = root;
	len = strlen(s);
	for(int i = 0;i < len;i++)
	{
		if(p -> end)	break;
		id = idx(s[i]);
		if(p -> next[id] == NULL)
			p -> next[id] = qq[Cnt-1] = new node();
		p = p -> next[id];
	}
	p -> end = 1;
}

void Build_ac_automation(node * root)
{
	q[rear++] = root;
	node * p = NULL;
	while(first < rear)
	{
		p = q[first++];
		for(int i = 0;i < 62;i++)
		{
			if(p -> next[i] != NULL)
			{
				if(p == root)
				{
					p -> next[i] -> fail = root;
				}
				else 
				{
					p -> next[i] -> fail = p -> fail -> next[i];
					if(p -> fail -> next[i] -> end)
						p -> next[i] -> end = 1;
				}
				q[rear++] = p -> next[i];
			}
			else 
			{
				if(p == root)
				{
					p -> next[i] = root;
				}
				else 
				{
					p -> next[i] = p -> fail -> next[i];
				}
			}
		}
	}
}

int main()
{
	//freopen("in.txt","r",stdin);
	int t;
	scanf("%d",&t);
	for(int cas = 1;cas <= t;cas++)
	{
		first = rear = Cnt = 0;
		node * root = new node();
		qq[0] = root;
		int k;	scanf("%d",&k);
		while(k--)
		{
			scanf("%s",str);
			Creat_Trie(str,root);
		}
		Build_ac_automation(root);
		int n;	scanf("%d",&n);
		memset(p,0,sizeof(p));
		for(int j = 1;j <= n;j++)
		{
			char c;	cin >> c;
			double pp;	scanf("%lf",&pp);
			p[idx(c)] = pp;
		}
		int L;	scanf("%d",&L);
		memset(dp,0,sizeof(dp));
		dp[0][0] = 1;
		for(int i = 0;i < L;i++)
		{
			for(int j = 0;j < Cnt;j++)
			{
				if(qq[j] -> end)	continue;
				for(int k = 0;k < 62;k++)
				{
					if(p[k] != 0 && qq[j] -> next[k] -> end == 0)
					{
						dp[i+1][qq[j] -> next[k] -> cnt] += dp[i][j] * p[k];
					}
				}
			}
		}
		double ans = 0;
		for(int i = 0;i < Cnt;i++)
		{
			if(qq[i] -> end == 0)
				ans += dp[L][i];
		}
		printf("Case #%d: %.6lf\n",cas,ans);
	}
	return 0;
}