代码

#include <cstdio>
#include <cstring>
#include <vector>
#include <algorithm>
using namespace std;

static const int THRESHOLD_NAIVE = 10;
static const int THRESHOLD_DOUBLING = 40;

static vector<int> sa_naive(const vector<int>& s) {
    int n = s.size();
    vector<int> sa(n);
    for (int i = 0; i < n; i++) sa[i] = i;
    sort(sa.begin(), sa.end(), [&](int l, int r) {
        if (l == r) return false;
        while (l < n && r < n) {
            if (s[l] != s[r]) return s[l] < s[r];
            l++; r++;
        }
        return l == n;
    });
    return sa;
}

static vector<int> sa_doubling(const vector<int>& s) {
    int n = s.size();
    vector<int> sa(n), rnk(n), tmp(n);
    for (int i = 0; i < n; i++) sa[i] = i;
    for (int i = 0; i < n; i++) rnk[i] = s[i];
    for (int k = 1; k < n; k *= 2) {
        auto cmp = [&](int x, int y) {
            if (rnk[x] != rnk[y]) return rnk[x] < rnk[y];
            int rx = x + k < n ? rnk[x + k] : -1;
            int ry = y + k < n ? rnk[y + k] : -1;
            return rx < ry;
        };
        sort(sa.begin(), sa.end(), cmp);
        tmp[sa[0]] = 0;
        for (int i = 1; i < n; i++) tmp[sa[i]] = tmp[sa[i - 1]] + (cmp(sa[i - 1], sa[i]) ? 1 : 0);
        swap(tmp, rnk);
    }
    return sa;
}

static vector<int> sa_is(vector<int>& s, int upper) {
    int n = s.size();
    if (n == 0) return {};
    if (n == 1) return {0};
    if (n == 2) {
        if (s[0] < s[1]) return {0, 1};
        else return {1, 0};
    }
    if (n < THRESHOLD_NAIVE) return sa_naive(s);
    if (n < THRESHOLD_DOUBLING) return sa_doubling(s);

    vector<int> sa(n);
    vector<bool> ls(n);
    for (int i = n - 2; i >= 0; i--) {
        ls[i] = (s[i] == s[i + 1]) ? ls[i + 1] : (s[i] < s[i + 1]);
    }
    vector<int> sum_l(upper + 1), sum_s(upper + 1);
    for (int i = 0; i < n; i++) {
        if (!ls[i]) sum_s[s[i]]++;
        else sum_l[s[i] + 1]++;
    }
    for (int i = 0; i <= upper; i++) {
        sum_s[i] += sum_l[i];
        if (i < upper) sum_l[i + 1] += sum_s[i];
    }

    auto induce = [&](const vector<int>& lms) {
        fill(sa.begin(), sa.end(), -1);
        vector<int> buf(upper + 1);
        copy(sum_s.begin(), sum_s.end(), buf.begin());
        for (int d : lms) {
            if (d == n) continue;
            sa[buf[s[d]]++] = d;
        }
        copy(sum_l.begin(), sum_l.end(), buf.begin());
        sa[buf[s[n - 1]]++] = n - 1;
        for (int i = 0; i < n; i++) {
            int v = sa[i];
            if (v >= 1 && !ls[v - 1]) sa[buf[s[v - 1]]++] = v - 1;
        }
        copy(sum_l.begin(), sum_l.end(), buf.begin());
        for (int i = n - 1; i >= 0; i--) {
            int v = sa[i];
            if (v >= 1 && ls[v - 1]) sa[--buf[s[v - 1] + 1]] = v - 1;
        }
    };

    vector<int> lms_map(n + 1, -1);
    int m = 0;
    for (int i = 1; i < n; i++) {
        if (!ls[i - 1] && ls[i]) lms_map[i] = m++;
    }
    vector<int> lms;
    lms.reserve(m);
    for (int i = 1; i < n; i++) {
        if (!ls[i - 1] && ls[i]) lms.push_back(i);
    }

    induce(lms);

    if (m) {
        vector<int> sorted_lms;
        sorted_lms.reserve(m);
        for (int v : sa) {
            if (lms_map[v] != -1) sorted_lms.push_back(v);
        }
        vector<int> rec_s(m);
        int rec_upper = 0;
        rec_s[lms_map[sorted_lms[0]]] = 0;
        for (int i = 1; i < m; i++) {
            int l = sorted_lms[i - 1], r = sorted_lms[i];
            int end_l = (lms_map[l] + 1 < m) ? lms[lms_map[l] + 1] : n;
            int end_r = (lms_map[r] + 1 < m) ? lms[lms_map[r] + 1] : n;
            bool same = true;
            if (end_l - l != end_r - r) {
                same = false;
            } else {
                while (l < end_l) {
                    if (s[l] != s[r]) break;
                    l++; r++;
                }
                if (l == n || s[l] != s[r]) same = false;
            }
            if (!same) rec_upper++;
            rec_s[lms_map[sorted_lms[i]]] = rec_upper;
        }

        vector<int> rec_sa = sa_is(rec_s, rec_upper + 1);

        for (int i = 0; i < m; i++) sorted_lms[i] = lms[rec_sa[i]];
        induce(sorted_lms);
    }
    return sa;
}

static char inbuf[1 << 20];
static char outbuf[1 << 22];

int main() {
    // read all stdin
    size_t nread = fread(inbuf, 1, sizeof(inbuf), stdin);
    // find string: lowercase letters until newline or end
    int n = 0;
    while (n < (int)nread && inbuf[n] >= 'a' && inbuf[n] <= 'z') n++;

    vector<int> s(n);
    for (int i = 0; i < n; i++) s[i] = inbuf[i] - 'a';

    vector<int> sa = sa_is(s, 26);

    // rank
    vector<int> rnk(n);
    for (int i = 0; i < n; i++) rnk[sa[i]] = i;

    // height (Kasai)
    vector<int> h(n);
    int k = 0;
    for (int i = 0; i < n; i++) {
        if (rnk[i] == 0) { k = 0; continue; }
        if (k) k--;
        int j = sa[rnk[i] - 1];
        while (i + k < n && j + k < n && s[i + k] == s[j + k]) k++;
        h[rnk[i]] = k;
    }

    // output
    char *p = outbuf;
    for (int i = 0; i < n; i++) {
        int v = sa[i] + 1;
        // fast itoa
        char tmp[8];
        int c = 0;
        do { tmp[c++] = '0' + v % 10; v /= 10; } while (v);
        while (c) *p++ = tmp[--c];
        *p++ = (i == n - 1) ? '\n' : ' ';
    }
    for (int i = 1; i < n; i++) {
        int v = h[i];
        char tmp[8];
        int c = 0;
        do { tmp[c++] = '0' + v % 10; v /= 10; } while (v);
        while (c) *p++ = tmp[--c];
        *p++ = (i == n - 1) ? '\n' : ' ';
    }
    if (n == 1) *p++ = '\n';
    fwrite(outbuf, 1, p - outbuf, stdout);
    return 0;
}

评测结果