zoukankan      html  css  js  c++  java
  • Keywords Search AC自动机

    In the modern time, Search engine came into the life of everybody like Google, Baidu, etc. 
    Wiskey also wants to bring this feature to his image retrieval system. 
    Every image have a long description, when users type some keywords to find the image, the system will match the keywords with description of image and show the image which the most keywords be matched. 
    To simplify the problem, giving you a description of image, and some keywords, you should tell me how many keywords will be match. 

    InputFirst line will contain one integer means how many cases will follow by. 
    Each case will contain two integers N means the number of keywords and N keywords follow. (N <= 10000) 
    Each keyword will only contains characters 'a'-'z', and the length will be not longer than 50. 
    The last line is the description, and the length will be not longer than 1000000. 
    OutputPrint how many keywords are contained in the description.Sample Input

    1
    5
    she
    he
    say
    shr
    her
    yasherhs

    Sample Output

    3
    AC自动机:利用ttie树节省空间,利用kmp相似的原理构建fail指针进行匹配
    #include<iostream>
    #include<cstdio>
    #include<cmath>
    #include<cstring>
    #include<sstream>
    #include<algorithm>
    #include<queue>
    #include<deque>
    #include<iomanip>
    #include<vector>
    #include<cmath>
    #include<map>
    #include<stack>
    #include<set>
    #include<fstream>
    #include<memory>
    #include<list>
    #include<string>
    using namespace std;
    typedef long long LL;
    typedef unsigned long long ULL;
    #define MAXN 26
    #define L 31
    #define INF 1000000009
    #define eps 0.00000001
    struct node
    {
        node()
        {
            cnt = 0;
            fail = NULL;
            for (int i = 0; i < MAXN; i++)
                next[i] = NULL;
        }
        int cnt;
        struct node* next[MAXN];
        struct node* fail;
    };
    typedef struct node* Tree;
    void insert(Tree T, const char* str)
    {
        int p = 0;
        Tree tmp = T;
        while (str[p] != '')
        {
            int k = str[p] - 'a';
            if (tmp->next[k] == NULL)
            {
                tmp->next[k] = new node();
            }
            tmp = tmp->next[k];
            p++;
        }
        tmp->cnt++;
    }
    void build_ac(Tree root)
    {
        root->fail = NULL;
        queue<Tree> q;
        q.push(root);
        while (!q.empty())
        {
            Tree tmp = q.front();
            q.pop();
            Tree p = NULL;
            for (int i = 0; i < MAXN; i++)
            {
                if (tmp->next[i] != NULL)
                {
                    if (tmp == root)
                        tmp->next[i]->fail = root;
                    else
                    {
                        p = tmp->fail;
                        while (p != NULL)
                        {
                            if (p->next[i] != NULL)
                            {
                                tmp->next[i]->fail = p->next[i];
                                break;
                            }
                            p = p->fail;
                        }
                        if (p == NULL) tmp->next[i]->fail = root;
                    }
                    q.push(tmp->next[i]);
                }
            }
        }
    }
    int query(Tree root,const char* str)
    {
        int i = 0;
        int count = 0;
        int l = strlen(str);
        Tree tmp = root;
        int index;
        while (str[i])
        {
            index = str[i] - 'a';
            while (tmp->next[index] == NULL && tmp != root)
                tmp = tmp->fail;
            tmp = tmp->next[index];
            if (tmp == NULL) tmp = root;
            Tree p = tmp;
            while (p != root)
            {
                count += p->cnt;
                p->cnt = 0;
                p = p->fail;
            }
            i++;
        }
        return count;
    }
    
    void del(Tree root)
    {
        for (int i = 0; i < MAXN; i++)
            if (root->next[i] != NULL)
                del(root->next[i]);
        delete root;
    }
    char key[60], s[1000010];
    int main()
    {
        int T, n;
        scanf("%d", &T);
        while (T--)
        {
            scanf("%d", &n);
            Tree root = new node();
            root->cnt = 0;
            root->fail = NULL;
            for (int i = 0; i < MAXN; i++)
                root->next[i] = NULL;
            for (int i = 0; i < n; i++)
            {
                scanf("%s", key);
                insert(root, key);
            }
            build_ac(root);
            scanf("%s", s);
            printf("%d
    ", query(root, s));
            del(root);
        }
    }
  • 相关阅读:
    《代码之道》试读:规范书变更请求
    解读ASP.NET MVC 4 规划路线图
    淘宝数据魔方技术架构解析
    《程序员实用算法》试读:1.2.2主要的优化:函数调用
    《软件框架设计的艺术》试读:2.2 模块化应用程序
    磁盘分割原理
    无锡云计算中心3年内到底做了什么
    模式识别的一些资料
    边缘检测算法
    用递归方法来搜索连通区域
  • 原文地址:https://www.cnblogs.com/joeylee97/p/7349061.html
Copyright © 2011-2022 走看看