P2178品酒大会（单调栈写法，加o2优化）

很明显这是一道后缀数组可以解出的题，我使用了单调栈来维护一个r相似，因为LCP(i,k)=min(LCP(i,j),LCP(j,k)) 对于任意1<=i<=j<=k<=n所以在这个l[i] 到r[i]中的全部都是r相似，用一个L和R数组来维护每个h[i]的范围，由于r相似也是r-1.....0相似故我们需要用差分维护，然后两颗线段树维护大小相关。（文字表达真的差，开始口胡），最后还是TLE了一部分样例，开了o2优化才全过

#pragma GCC optimize(2)
#include<iostream>
#include<algorithm>
#include<string.h>
#include<string>
#include<vector>
using namespace std;
typedef long long ll;
const int N = 3e5 + 5;
const int M = 30;
const ll INF = 1e18 + 5;
const int inf = 1e9 + 5;
int p[N];
struct SA {
	int sa[N], h[N], x[N], y[N], c[N], rk[N];
	string s;
	void innt(string s1) {
		s = s1;
		int n = s.size();
		for (int i = 0; i <= n; i++) {
			sa[i] = h[i] = x[i] = y[i] = c[i] = rk[i] = 0;
		}
	}

	void get_sa() {
		int n = s.size();
		int m = M;
		for (int i = 1; i <= n; i++) c[x[i] = (s[i - 1] - 'a' + 1)]++;
		for (int i = 1; i <= m; i++) c[i] += c[i - 1];
		for (int i = n; i; i--) sa[c[x[i]]--] = i;
		for (int k = 1; k <= n; k = k << 1) {
			int tot = 0;
			for (int i = n - k + 1; i <= n; i++) y[++tot] = i;
			for (int i = 1; i <= n; i++) if (sa[i] > k) y[++tot] = sa[i] - k;
			for (int i = 0; i <= m; i++) c[i] = 0;
			for (int i = 1; i <= n; i++) c[x[i]]++;
			for (int i = 1; i <= m; i++) c[i] += c[i - 1];
			for (int i = n; i; i--) sa[c[x[y[i]]]--] = y[i];
			swap(x, y);
			tot = 1, x[sa[1]] = 1;
			for (int i = 2; i <= n; i++) x[sa[i]] = (y[sa[i]] == y[sa[i - 1]] && y[sa[i - 1] + k] == y[sa[i] + k]) ? tot : ++tot;
			if (tot == n) break;
			m = tot;
		}
		/*for (int i = 1; i <= n; i++) printf("%d ", sa[i]);
		cout << endl;*/
	}

	void get_h() {
		int n = s.size();
		for (int i = 1; i <= n; i++) rk[sa[i]] = i;
		int k = 0;
		for (int i = 1; i <= n; i++) {
			if (rk[i] == 1) continue;
			if (k) k--;
			int j = sa[rk[i] - 1];
			while (i + k <= n && j + k <= n && s[i + k - 1] == s[j + k - 1]) k++;
			h[rk[i]] = k;
		}
		//for (int i = 1; i <=n; i++) printf("%d ", h[i]);
		//cout << endl;
	}

}q;

struct node {
	int l, r, mi, mx, v1, v2;
}t[N << 2];

struct Data {
	int l, r;
	ll zy;
	ll w;
}tq[N << 2];

void updata1(int x) {
	tq[x].w = max(tq[x << 1].w, tq[x << 1 | 1].w);
}

void down(int x) {
	tq[x << 1].w = max(tq[x].zy, tq[x << 1].w);
	tq[x << 1].zy = max(tq[x].zy, tq[x << 1].zy);
	tq[x << 1 | 1].w = max(tq[x].zy, tq[x << 1 | 1].w);
	tq[x << 1 | 1].zy = max(tq[x].zy, tq[x << 1 | 1].zy);
	tq[x].zy = -INF;

}

void bulit1(int l, int r, int rt) {
	tq[rt].l = l;
	tq[rt].r = r;
	tq[rt].zy = -INF;
	if (tq[rt].l == tq[rt].r) {
		tq[rt].w = -INF;
		//tq[rt].zy = -INF;
		return;
	}
	int mid = (l + r) >> 1;
	bulit1(l, mid, rt << 1);
	bulit1(mid + 1, r, rt << 1 | 1);
	updata1(rt);
}

ll query(int v, int rt) {
	if (tq[rt].l == tq[rt].r) {
		//cout << tq[rt].w << endl;
		return tq[rt].w;
	}
	down(rt);
	int mid = (tq[rt].l + tq[rt].r) >> 1;
	ll ans = -INF;
	if (mid >= v) ans = max(query(v, rt << 1), ans);
	else ans = max(query(v, rt << 1 | 1), ans);
	return ans;
}

void dataup(int l, int r, int rt, ll x) {
	if (l <= tq[rt].l && tq[rt].r <= r) {
		tq[rt].w = max(tq[rt].w, x);
		tq[rt].zy = max(tq[rt].zy, x);
		return;
	}
	down(rt);
	int mid = (tq[rt].l + tq[rt].r) >> 1;
	if (l <= mid) dataup(l, r, rt << 1, x);
	if (mid < r) dataup(l, r, rt << 1 | 1, x);
	updata1(rt);

}

void updata(int x) {
	if (t[x << 1].mx > t[x << 1|1].mx) {
		t[x].mx = t[x << 1].mx;
		t[x].v1 = t[x << 1].v1;
	}
	else {
		t[x].mx = t[x << 1|1].mx;
		t[x].v1 = t[x << 1|1].v1;
	}

	if (t[x << 1].mi < t[x << 1|1].mi) {
		t[x].mi = t[x << 1].mi;
		t[x].v2 = t[x << 1].v2;
	}
	else {
		t[x].mi = t[x << 1 | 1].mi;
		t[x].v2 = t[x << 1 | 1].v2;
	}

}
int a, ai, b, bi;
void bulit(int l, int r, int rt) {
	t[rt].l = l;
	t[rt].r = r;
	if (l == r) {
		t[rt].v1 = l;
		t[rt].v2 = l;
		t[rt].mi = t[rt].mx = p[q.sa[l]];
		return;
	}
	int mid = (l + r) >> 1;
	bulit(l, mid, rt << 1);
	bulit(mid + 1, r, rt << 1 | 1);
	updata(rt);
}

void get_max(int l, int r, int rt) {
	if (t[rt].l >= l && t[rt].r <= r) {
		if (t[rt].mx > a) {
			a = t[rt].mx;
			ai = t[rt].v1;
		}
		return;
	}
	int mid = (t[rt].l + t[rt].r) >> 1;
	if (l <= mid) get_max(l, r, rt << 1);
	if (r > mid) get_max(l, r, rt << 1 | 1);
}

void get_min(int l,int r,int rt) {
	if (t[rt].l >= l && t[rt].r <= r) {
		if (t[rt].mi < b) {
			b = t[rt].mi;
			bi = t[rt].v2;
		}
		return;
	}
	int mid = (t[rt].l + t[rt].r) >> 1;
	if (l <= mid) get_min(l, r, rt << 1);
	if (r > mid) get_min(l, r, rt << 1 | 1);
}
template <class T>//适用于正负整数 
inline bool read(T &ret) {
	char c;
	int sgn;
	if (c = getchar(), c == EOF) return false; //EOF
	while (c != '-' && (c<'0' || c>'9')) c = getchar();
	sgn = (c == '-') ? -1 : 1;
	ret = (c == '-') ? 0 : (c - '0');
	while (c = getchar(), c >= '0'&&c <= '9') ret = ret * 10 + (c - '0');
	ret *= sgn;
	return true;
}

void add(int v, int x, int rt) {
	if (t[rt].l == t[rt].r) {
		t[rt].mi = x;
		t[rt].mx = x;
		return;
	}
	int mid = (t[rt].l + t[rt].r) >> 1;
	if (v <= mid) add(v, x, rt << 1);
	else add(v, x, rt << 1 | 1);
	updata(rt);
}

ll per[N], val[N];
ll inv[N];

int l[N], r[N];
int L[N], R[N];

void solve(int n) {
	bulit1(0, n, 1);
	bulit(1, n, 1);
	for (int i = 0; i <= n; i++) l[i] = r[i] = i, L[i] = R[i] = inv[i] = 0;
	q.h[0] = q.h[n + 1] = -1;
	for (int i = 1; i <= n; i++) {
		while (q.h[l[i] - 1] >= q.h[i]) l[i] = l[l[i] - 1];
	}
	for (int i = n; i; i--) {
		while (q.h[r[i] + 1] >= q.h[i]) r[i] = r[r[i] + 1];
	}

	for (int i = 0; i <= n; i++) {
		per[i] = 0;
		val[i] = -INF;
	}
	for (int i = 1; i <= n; i++) {
		if (i >= L[q.h[i]] && i <= R[q.h[i]]) continue;

		L[q.h[i]] = l[i];
		R[q.h[i]] = r[i];
		l[i] = max(2, l[i]);

		a = -inf;
		get_max(l[i] - 1, r[i], 1);
		int x1 = a;
		add(ai, -inf, 1);
		int v = ai;
		a = -inf;
		get_max(l[i] - 1, r[i], 1);
		int x2 = a;
		add(v, x1, 1);

		b = inf;
		get_min(l[i] - 1, r[i], 1);
		int x3 = b;
		add(bi, inf, 1);
		v = bi;
		b = inf;
		get_min(l[i] - 1, r[i], 1);
		int x4 = b;
		add(v, x3, 1);

		ll tmp1 = max(1ll * x1 *x2, 1ll * x3*x4);
		ll tmp2 = 1ll * (r[i] - l[i] + 2) * (r[i] - l[i] + 1) / 2;

		val[q.h[i]] = max(val[q.h[i]], tmp1);
		per[q.h[i]] += tmp2;
		//cout << per[0] << endl;
		//printf("%lld %lld\n", tmp1, tmp2);
		int x = max(q.h[l[i] - 1], q.h[r[i] + 1]);
		if (x + 1 <= q.h[i]) {
			inv[x + 1] += tmp2;
			inv[q.h[i]] -= tmp2;
			dataup(x + 1, q.h[i], 1, tmp1);
		}
		//for (int j = x + 1; j < q.h[i]; j++) {
		//	per[j] += tmp2;
		//	val[j] = max(val[j],tmp1);
		//}

	}
	//cout << per[0] << endl;
	for (int i = 1; i < n; i++) inv[i] += inv[i - 1];
	for (int i = 0; i < n; i++) {
		//printf("%lld %lld\n", per[i], inv[i]);
		per[i] += inv[i];
	//	printf("%lld\n", val[i]);
		val[i] = max(val[i], query(i, 1));
	}
	for (int i = n - 1; i >= 0; i--) {
		if (!per[i]) val[i] = 0;
	}
	for (int i = 0; i <= n - 1; i++) {
		printf("%lld %lld\n", per[i], val[i]);
	}
}

int main() {
	int n;
	scanf("%d", &n);
	char s[N];
	scanf("%s", s);
	for (int i = 1; i <= n; i++) {
		read(p[i]);
	}
	//cout << "sad" << endl;
	q.innt(s);q.get_sa();q.get_h();
	solve(n);
	return 0;
}