hdu 2222 Keywords Search AC自动机——多串匹配

http://acm.hdu.edu.cn/showproblem.php?pid=2222

题意:

给出n个单词,再给出一段包含m个字符的文章,求有多少个单词在文章里出现过。

思路:
才开开始以为简单的Trie数就可以,结果TLE到无语,字典树枚举每一个查找单词的第一个字母的话是O(N*50)前边还有一个T计算的话会超时,看了一下解题报告原来是AC自动机的基础应用。给出一个不错的链接http://blog.himdd.com/?p=2169 这里讲的很详细。

想不到,回校第一个题目竟然是4个2的题号,无语。。。。

//#pragma comment(linker,"/STACK:327680000,327680000")
#include <iostream>
#include <cstdio>
#include <cmath>
#include <vector>
#include <cstring>
#include <algorithm>
#include <string>
#include <set>
#include <functional>
#include <numeric>
#include <sstream>
#include <stack>
#include <map>
#include <queue>

#define CL(arr, val)    memset(arr, val, sizeof(arr))

#define lc l,m,rt<<1
#define rc m + 1,r,rt<<1|1
#define pi acos(-1.0)
#define ll long long
#define L(x)    (x) << 1
#define R(x)    (x) << 1 | 1
#define MID(l, r)   (l + r) >> 1
#define Min(x, y)   (x) < (y) ? (x) : (y)
#define Max(x, y)   (x) < (y) ? (y) : (x)
#define E(x)        (1 << (x))
#define iabs(x)     (x) < 0 ? -(x) : (x)
#define OUT(x)  printf("%I64d\n", x)
#define lowbit(x)   (x)&(-x)
#define Read()  freopen("din.txt", "r", stdin)
#define Write() freopen("dout.txt", "w", stdout);


#define M 57
#define N 1000007
using namespace std;

struct node
{
    node *fail;
    node *next[26];
    int cnt;
    void newnode()//生成节点
    {
        fail = NULL;
        for (int i = 0; i < 26; ++i)
        {
            next[i] = NULL;
        }
        cnt = 0;
    }
};
class Ac_Automat
{
    node *q[N],H[N],*root;
    int fr,tl,t;
    public:
//    初始化
    void init()
    {
        fr = tl = 0;
        t = 0;
        H[t].newnode();
        root = &H[t++];
    }
//    插入单词
    void insert(char *s)
    {
        int i,k,len;
        len = strlen(s);
        node *p = root;
        for (i = 0; i < len; ++i)
        {
            k = s[i] - 'a';
            if (p->next[k] == NULL)
            {
                H[t].newnode();
                p->next[k] = &H[t++];
            }
            p = p->next[k];
        }
        p->cnt++;
    }
//    建立失败指针
    void build()
    {
        root->fail = NULL;
        q[tl] = root;

        while (fr <= tl)
        {
            node *tmp = q[fr++];
            node *p = NULL;
            for (int i = 0; i < 26; ++i)
            {
                if (tmp->next[i])
                {
                    if (tmp == root) tmp->next[i]->fail = root;
                    else
                    {
                        p = tmp->fail;
                        while (p != NULL)
                        {
                            if (p->next[i])
                            {
                                tmp->next[i]->fail = p->next[i];
                                break;
                            }
                            p = p->fail;
                        }
                        if (p == NULL) tmp->next[i]->fail = root;
                    }
                    q[++tl] = tmp->next[i];
                }
            }

        }
    }
//    查找
    int query(char *s)
    {
        int res = 0;
        node *p = root;
        int len = strlen(s);
        for (int i = 0; i < len; ++i)
        {
            int k = s[i] - 'a';
            while (p->next[k] == NULL && p != root) p = p->fail;

            p = p->next[k];
            if (p == NULL) p = root;
            node *tmp = p;
            while (tmp != root && tmp->cnt != -1)
            {
                res += tmp->cnt;
                tmp->cnt = - 1;
                tmp = tmp->fail;
            }
        }
        return res;
    }
}ac;

char ques[M],ans[N];

int n;

int main()
{
    int i;
    int T;
    scanf("%d",&T);
    while (T--)
    {
        ac.init();
        scanf("%d",&n);
        for (i = 0; i < n; ++i)
        {
            scanf("%s",ques);
            ac.insert(ques);
        }
        ac.build();
//        printf(">>>>\n");
        scanf("%s",ans);
//        printf("%s\n",ans);
        printf("%d\n",ac.query(ans));
    }
    return 0;
}

  

 

posted @ 2013-02-19 15:52  E_star  阅读(296)  评论(0编辑  收藏  举报