poj 3294 不小于 k 个字符串中的最长子串（后缀数组+二分）

题目：http://poj.org/problem?id=3294
题意：

给定 n 个字符串，求出现在大于一半个字符串中的最长子串。

分析:

将 n 个字符串连起来，中间用不相同的且没有出现在字符串中的字符隔开，求后缀数组。然后二分答案，将后缀分成若干组，判断每组的后缀是否出现在不小于 k 个的原串中。这个做法的时间复杂度为 O(nlogn)。

#include<cstdio>
#include<cstring>
#include<algorithm>
#include<iostream>
using namespace std;
typedef long long ll;
const int INF = 1e9 + 9;
const int N = 2e5 + 9;

/********************倍增算法*后缀数组模板*******************************/

int sa[N], t1[N], t2[N], c[N], rk[N], height[N];
void build_sa (int s[], int n, int m) {
    int i, k, p, *x = t1, *y = t2;
    for (i = 0; i < m; i++) c[i] = 0;
    for (i = 0; i < n; i++) c[x[i] = s[i]]++;
    for (i = 1; i < m; i++) c[i] += c[i - 1];
    for (i = n - 1; i >= 0; i--) sa[--c[x[i]]] = i;
    for (k = 1; k <= n; k <<= 1) {
        p = 0;
        for (i = n - k; i < n; i++) y[p++] = i;
        for (i = 0; i < n; i++) if (sa[i] >= k) y[p++] = sa[i] - k;
        for (i = 0; i < m; i++) c[i] = 0;
        for (i = 0; i < n; i++) c[x[y[i]]]++;
        for (i = 1; i < m; i++) c[i] += c[i - 1];
        for (i = n - 1; i >= 0; i--) sa[--c[x[y[i]]]] = y[i];
        swap (x, y);
        p = 1;
        x[sa[0]] = 0;
        for (i = 1; i < n; i++)
            x[sa[i]] = y[sa[i - 1]] == y[sa[i]] && y[sa[i - 1] + k] == y[sa[i] + k] ? p - 1 : p ++;
        if (p >= n) break;
        m = p;
    }
}
void getHeight (int s[], int n) {
    int i, j, k = 0;
    for (i = 0; i <= n; i++) rk[sa[i]] = i;
    for (i = 0; i < n; i++) {
        if (k) k--;
        j = sa[rk[i] - 1];
        while (s[i + k] == s[j + k]) k++;
        height[rk[i]] = k;
    }
}
/********************************************************************************/


int s[N], n, m, length[N], tot, ans[N];
bool flag[111];
char str[N];
int check (int x) { //判断在哪个字符串中
    for (int i = 0; i < m; i++)
        if (x < length[i]) return i;
}
bool ok (int k) {
    tot = 0;
    int cnt = 0;
    for (int i = 1; i <= n; i++) {
        if (height[i] < k) {
            if (cnt > (m ) / 2) ans[tot++] = i - 1; //ans保存出现次数大于一半的字符串的一个后缀，然后再根据长度计算出字符串
            cnt = 0;
            memset (flag, 0, sizeof (flag) );
            continue;
        }
        if (cnt == 0) {
            flag[check (sa[i - 1])] = 1;
            cnt++;
        }
        int id = check (sa[i]);
        if (!flag[id]) flag[id] = 1, cnt++;
    }
    return tot > 0;
}
int main() {
    //freopen ("f.txt", "r", stdin);
    int cas = 0;
    while (~scanf ("%d", &m) && m ) {
        if (cas++) printf ("\n");
        int XX = 30;
        n = 0;
        for (int i = 0; i < m; i++) {
            scanf ("%s", str);
            int len = strlen (str);
            for (int j = 0; j < len; j++) s[n++] = str[j] - 'a' + 1;
            s[n++] = XX++; //每个字符串后面插入一个不同的符号
            length[i] = n;
        }
        if (m == 1) { //测试数据中没有m=1
            puts ("?");
            continue;
        }
        s[n] = 0;
        build_sa (s, n + 1, 150);
        getHeight (s, n);

        int l = 0, r = n;
        while (l < r) { //二分长度
            int mid = l + (r - l + 1) / 2;
            if (ok (mid) ) l = mid;
            else r = mid - 1;
        }
        ok (l);
        if (tot == 0) puts ("?");
        else
            for (int i = 0; i < tot; i++) {
                for (int j = sa[ans[i]]; j < sa[ans[i]] + l; j++)
                    printf ("%c", (char) (s[j] + 'a' - 1) );
                printf ("\n");
            }
    }
    return 0;
}
/*
Sample Input

3
abcdefg
bcdefgh
cdefghi
3
xxx
yyy
zzz
0

Sample Output

bcdefg
cdefgh

?


*/