HDU 2457 (AC自动机 DP)

题目链接:点击这里

题意:给定一个DNA串, 至少改变多少字母才能使得所有的模式串都不出现在这个DNA串里.

先给所有的模式串建立AC自动机,然后DNA串就不能走到自动机上的危险节点, 也就是模式串的结尾节点. 假设$dp[i][j]$表示在字典树上i节点, DNA串长为j的最小改变个数, 转移就是 $$d[i][j] = min \left\{ \begin{array}{rcl} dp[k][j-1] & & {buf[k]=buf[i+1],k是文本串i的后继不是模式串结尾}\\ dp[k][j-1]+1 & & {buf[k]\neq buf[i+1],k不是文本串i的后继且k不是模式串结尾}\\ \end{array} \right.$$

#include <bits/stdc++.h>
using namespace std;
#define maxn 1005
#define INF 1111111

int dp[maxn][maxn];//在字典树上i节点 长度为j 最少改变了多少次
int n;
char str[maxn];

void change (char *s) {
    int len = strlen (s);
    for (int i = 0; i < len; i++) {
        if (s[i] == 'A') s[i] = 'a';
        else if (s[i] == 'C') s[i] = 'b';
        else if (s[i] == 'G') s[i] = 'c';
        else s[i] = 'd';
    }
}

struct trie {
    int next[maxn][4], fail[maxn], end[maxn];
    int root, cnt;
    int new_node () {
        memset (next[cnt], -1, sizeof next[cnt]);
        end[cnt++] = 0;
        return cnt-1;
    }
    void init () {
        cnt = 0;
        root = new_node ();
    }
    void insert (char *buf) {//字典树插入一个单词
        int len = strlen (buf);
        int now = root;
        for (int i = 0; i < len; i++) {
            int id = buf[i]-'a';
            if (next[now][id] == -1) {
                next[now][id] = new_node ();
            }
            now = next[now][id];
        }
        end[now]++;
    }
    void build () {//构建fail指针
        queue <int> q;
        fail[root] = root;
        for (int i = 0; i < 4; i++) {
            if (next[root][i] == -1) {
                next[root][i] = root;
            }
            else {
                fail[next[root][i]] = root;
                q.push (next[root][i]);
            }
        }
        while (!q.empty ()) {
            int now = q.front (); q.pop ();
            end[now] += end[fail[now]];
            for (int i = 0; i < 4; i++) {
                if (next[now][i] == -1) {
                    next[now][i] = next[fail[now]][i];
                }
                else {
                    fail[next[now][i]] = next[fail[now]][i];
                    q.push (next[now][i]);
                }
            }
        }
    }
    int query (char *buf) {
        int len = strlen (buf);
        for (int i = 0; i < cnt; i++) {
            for (int j = 0; j <= len; j++) dp[i][j] = INF;
        }
        dp[0][0] = 0;
        for (int j = 0; j < len; j++) {
            for (int i = 0; i < cnt; i++) {
                if (end[i]) continue;
                int id = buf[j]-'a';
                int nexti = next[i][id];
                if (!end[nexti]) {//可以走到这个点
                    dp[nexti][j+1] = min (dp[nexti][j+1], dp[i][j]);
                }
                for (int x = 0; x < 4; x++) if (x != id) {
                    nexti = next[i][x];
                    if (!end[nexti]) {
                        dp[nexti][j+1] = min (dp[nexti][j+1], dp[i][j]+1);
                    }
                }
            }
        }
        int ans = INF;
        for (int i = 0; i < cnt; i++) ans = min (ans, dp[i][len]);
        if (ans >= INF)
            ans = -1;
        return ans;
    }
}ac;

int main () {
    int kase = 0;
    while (scanf ("%d", &n) == 1 && n) {
        ac.init ();
        for (int i = 1; i <= n; i++) {
            scanf ("%s", str);
            change (str); 
            ac.insert (str);
        }
        ac.build ();
        scanf ("%s", str);
        change (str);
        printf ("Case %d: %d\n", ++kase, ac.query (str));
    }
    return 0;
}