HDU2222_Keywords Search _AC自动机模板题

题意

给出若干单词和一串字符，问这串字符中出现了给出单词中的几个。

思路

AC自动机模板题
AC自动机学习资料：
kuangbin大神的blog：http://www.cppblog.com/mythit/archive/2009/04/21/80633.html
包括AC代码中的第二种，也是直接从这里抄过来的

题目链接

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

AC代码

这里代码有两版，第二个是照抄的kuangbin大神的，第二版稍微进行了一些改动，只是更靠近自己的风格，几乎可以说完全一样。

版本一

#include<iostream>
#include<cstdio>
#include<cstring>
using namespace std;

const int kind = 26;
struct node
{
    node *fail;                                                     //fail指针
    node *next[kind];                                               //子节点指针
    int count;                                                      //当前节点代表的单词个数
    node()
    {
        fail = NULL;
        count = 0;
        memset(next, NULL, sizeof next);
    }
};
node *q[500001];                                                    //队列
int head, tail;                                                     //队列的首尾指针
char keyword[51];                                                   //单词表
char str[1000001];                                                  //模式串

void insert(char *str, node *root)                                  //将单词插入字典树中
{
    node *p = root;
    int i = 0;
    while(str[i])
    {
        int index = str[i] - 'a';
        if(p->next[index] == NULL) p->next[index] = new node();
        p = p->next[index];
        i ++;
    }
    p->count ++;
}

void build_ac_automation(node *root)
{
    head = tail = 0;
    q[head ++] = root;
    while(head != tail)
    {
        node *temp = q[tail ++];
        node *p = NULL;

        for(int i= 0; i< 26; i++)                                   //线序遍历子树
        {
            if(temp->next[i] != NULL)
            {
                p = temp->fail;
                while(p != NULL)                                    //沿着fail链找到一个与当前位置对应的位置，构造fail链
                {
                    if(p->next[i] != NULL)
                    {
                        temp->next[i]->fail = p->next[i];
                        break;
                    }
                    p = p->fail;
                }
                if(p == NULL) temp->next[i]->fail = root;           //加边失败，fail指针指向root
                q[head ++] = temp->next[i];                         //子节点入队
            }
        }
    }
}

int query(node *root)
{
    int i = 0, cnt = 0, len = strlen(str);
    node *p = root;
    while(str[i])                                                   //遍历模式串
    {
        int index = str[i] - 'a';

        while(p->next[index] == NULL && p != root) p = p->fail;     //沿着fail链找一个能继续匹配的树枝，找到root也要停止
        p = p->next[index];
        if(p == NULL) p = root;                                     //查找失败，p置为root

        node *temp = p;                                             //沿着fail链检查是否有单词被构成
        while(temp != root && temp->count != -1)                    //-1表示该单词已经被找过一次了
        {
            cnt += temp->count;
            temp->count = -1;
            temp = temp->fail;
        }

        i ++;
    }

    return cnt;
}

int main()
{
    int n, t;
    scanf("%d", &t);
    while(t --)
    {
        node *root = new node();
        scanf("%d", &n);
        getchar();

        while(n --)
        {
            gets(keyword);
            insert(keyword, root);
        }
        build_ac_automation(root);

        scanf("%s", str);
        printf("%d\n", query(root));
    }

    return 0;
}

版本二

#include<iostream>
#include<cstdio>
#include<cstring>
using namespace std;

const int kind = 26;
struct node
{
    node *fail;
    node *next[kind];
    int count;
    node()
    {
        fail = NULL;
        count = 0;
        memset(next, NULL, sizeof next);
    }
} *q[500001];
char keyword[51];
char str[1000001];
int head, tail;

void insert(char *str, node *root)
{
    node *p = root;
    int i = 0, index;
    while(str[i])
    {
        index = str[i] - 'a';
        if(p->next[index] == NULL) p->next[index] = new node();
        p = p->next[index];
        i ++;
    }
    p->count ++;
}

void build_ac_automation(node *root)
{
    int i;
    root->fail = NULL;
    q[head ++] = root;
    while(head != tail)
    {
        node *temp = q[tail ++];
        node *p = NULL;

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

int query(node *root)
{
    int i = 0, cnt = 0, index, len = strlen(str);
    node *p = root;
    while(str[i])
    {
        index = str[i] - 'a';
        while(p->next[index] == NULL && p != root) p = p->fail;
        p = p->next[index];
        p = (p == NULL) ? root : p;
        node *temp = p;
        while(temp != root && temp->count != -1)
        {
            cnt += temp->count;
            temp->count = -1;
            temp = temp->fail;
        }

        i ++;
    }
    return cnt;
}

int main()
{
    int n, t;
    scanf("%d", &t);
    while(t --)
    {
        head = tail = 0;
        node *root = new node();
        scanf("%d", &n);
        getchar();
        while(n --)
        {
            gets(keyword);
            insert(keyword, root);
        }

        build_ac_automation(root);
        scanf("%s", str);
        printf("%d\n", query(root));
    }

    return 0;
}