verify/LibraryChecker/string/SuffixArray.test.cpp

• View this file on GitHub
• Last update: 2024-09-26 13:24:19+09:00
• Problem: https://judge.yosupo.jp/problem/suffixarray

Depends on

• Suffix Array (string/SuffixArray.hpp)
• Template (template/template.hpp)

Code

#include "../../../template/template.hpp"
#define PROBLEM "https://judge.yosupo.jp/problem/suffixarray"
#include "../../../string/SuffixArray.hpp"

int main() {
    cin.tie(0)->sync_with_stdio(0);
    string s;
    in(s);
    out(suffixArray(s));
}

#line 2 "template/template.hpp"
#pragma region Macros
#include <bits/stdc++.h>
using namespace std;
using lint = long long;
using ull = unsigned long long;
using ld = long double;
using int128 = __int128_t;
#define all(x) (x).begin(), (x).end()
#define uniqv(v) v.erase(unique(all(v)), v.end())
#define OVERLOAD_REP(_1, _2, _3, name, ...) name
#define REP1(i, n) for (auto i = std::decay_t<decltype(n)>{}; (i) != (n); ++(i))
#define REP2(i, l, r) for (auto i = (l); (i) != (r); ++(i))
#define rep(...) OVERLOAD_REP(__VA_ARGS__, REP2, REP1)(__VA_ARGS__)
#define logfixed(x) cout << fixed << setprecision(10) << x << endl;

ostream &operator<<(ostream &dest, __int128_t value) {
  ostream::sentry s(dest);
  if (s) {
    __uint128_t tmp = value < 0 ? -value : value;
    char buffer[128];
    char *d = end(buffer);
    do {
      --d;
      *d = "0123456789"[tmp % 10];
      tmp /= 10;
    } while (tmp != 0);
    if (value < 0) {
      --d;
      *d = '-';
    }
    int len = end(buffer) - d;
    if (dest.rdbuf()->sputn(d, len) != len) {
      dest.setstate(ios_base::badbit);
    }
  }
  return dest;
}

template <typename T>
ostream &operator<<(ostream &os, const vector<T> &v) {
  for (int i = 0; i < (int)v.size(); i++) {
    os << v[i] << (i + 1 != (int)v.size() ? " " : "");
  }
  return os;
}

template <typename T>
ostream &operator<<(ostream &os, const set<T> &set_var) {
  for (auto itr = set_var.begin(); itr != set_var.end(); itr++) {
    os << *itr;
    ++itr;
    if (itr != set_var.end()) os << " ";
    itr--;
  }
  return os;
}

template <typename T>
ostream &operator<<(ostream &os, const unordered_set<T> &set_var) {
  for (auto itr = set_var.begin(); itr != set_var.end(); itr++) {
    os << *itr;
    ++itr;
    if (itr != set_var.end()) os << " ";
    itr--;
  }
  return os;
}

template <typename T, typename U>
ostream &operator<<(ostream &os, const map<T, U> &map_var) {
  for (auto itr = map_var.begin(); itr != map_var.end(); itr++) {
    os << itr->first << " -> " << itr->second << "\n";
  }
  return os;
}

template <typename T, typename U>
ostream &operator<<(ostream &os, const unordered_map<T, U> &map_var) {
  for (auto itr = map_var.begin(); itr != map_var.end(); itr++) {
    os << itr->first << " -> " << itr->second << "\n";
  }
  return os;
}

template <typename T, typename U>
ostream &operator<<(ostream &os, const pair<T, U> &pair_var) {
  os << pair_var.first << " " << pair_var.second;
  return os;
}

void out() { cout << '\n'; }
template <class T, class... Ts>
void out(const T &a, const Ts &...b) {
  cout << a;
  (cout << ... << (cout << ' ', b));
  cout << '\n';
}

void outf() { cout << '\n'; }
template <class T, class... Ts>
void outf(const T &a, const Ts &...b) {
  cout << fixed << setprecision(14) << a;
  (cout << ... << (cout << ' ', b));
  cout << '\n';
}

template <typename T>
istream &operator>>(istream &is, vector<T> &v) {
  for (T &in : v) is >> in;
  return is;
}

inline void in(void) { return; }
template <typename First, typename... Rest>
void in(First &first, Rest &...rest) {
  cin >> first;
  in(rest...);
  return;
}

template <typename T>
bool chmax(T &a, const T &b) {
  if (a < b) {
    a = b;
    return true;
  }
  return false;
}
template <typename T>
bool chmin(T &a, const T &b) {
  if (a > b) {
    a = b;
    return true;
  }
  return false;
}

vector<lint> dx8 = {1, 1, 0, -1, -1, -1, 0, 1};
vector<lint> dy8 = {0, 1, 1, 1, 0, -1, -1, -1};
vector<lint> dx4 = {1, 0, -1, 0};
vector<lint> dy4 = {0, 1, 0, -1};

#pragma endregion
#line 2 "verify/LibraryChecker/string/SuffixArray.test.cpp"
#define PROBLEM "https://judge.yosupo.jp/problem/suffixarray"
#line 2 "string/SuffixArray.hpp"

#define tget(i) (((t)[(i) >> 3] >> (7 - ((i) & 7))) & 1)

#define tset(i, b)                                    \
    do {                                              \
        if (b)                                        \
            (t)[(i) >> 3] |= (1 << (7 - ((i) & 7)));  \
        else                                          \
            (t)[(i) >> 3] &= ~(1 << (7 - ((i) & 7))); \
    } while (0)

#define chr(i) (cs == sizeof(int) ? ((int *)s)[i] : ((unsigned char *)s)[i])
#define isLMS(i) (i > 0 and tget(i) and !tget(i - 1))

void getBuckets(unsigned char *s, int *bkt, int n, int K, int cs, bool end) {
    int sum = 0;
    for (int i = 0; i <= K; i++) {
        bkt[i] = 0;
    }
    for (int i = 0; i < n; i++) {
        bkt[chr(i)]++;
    }
    for (int i = 0; i <= K; i++) {
        sum += bkt[i];
        bkt[i] = end ? sum : sum - bkt[i];
    }
}

void induceSAl(unsigned char *t, int *SA, unsigned char *s, int *bkt, int n, int K, int cs, bool end) {
    getBuckets(s, bkt, n, K, cs, end);
    for (int i = 0; i < n; i++) {
        int j = SA[i] - 1;
        if (j >= 0 and !tget(j)) {
            SA[bkt[chr(j)]++] = j;
        }
    }
}

void induceSAs(unsigned char *t, int *SA, unsigned char *s, int *bkt, int n, int K, int cs, bool end) {
    getBuckets(s, bkt, n, K, cs, end);
    for (int i = n - 1; i >= 0; i--) {
        int j = SA[i] - 1;
        if (j >= 0 and tget(j)) {
            SA[--bkt[chr(j)]] = j;
        }
    }
}

void SA_IS(unsigned char *s, int *SA, int n, int K, int cs) {
    unsigned char *t = (unsigned char *)malloc(n / 8 + 1);
    tset(n - 2, 0);
    tset(n - 1, 1);
    for (int i = n - 3; i >= 0; i--) {
        tset(i, (chr(i) < chr(i + 1) or (chr(i) == chr(i + 1) and tget(i + 1) == 1)) ? 1 : 0);
    }

    int *bkt = (int *)malloc(sizeof(int) * (K + 1));
    getBuckets(s, bkt, n, K, cs, true);
    for (int i = 0; i < n; i++) {
        SA[i] = -1;
    }
    for (int i = 1; i < n; i++) {
        if (isLMS(i)) {
            SA[--bkt[chr(i)]] = i;
        }
    }
    induceSAl(t, SA, s, bkt, n, K, cs, false);
    induceSAs(t, SA, s, bkt, n, K, cs, true);
    free(bkt);

    int n1 = 0;
    for (int i = 0; i < n; i++) {
        if (isLMS(SA[i])) {
            SA[n1++] = SA[i];
        }
    }

    for (int i = n1; i < n; i++) {
        SA[i] = -1;
    }
    int name = 0;
    int prev = -1;
    for (int i = 0; i < n1; i++) {
        int pos = SA[i];
        bool diff = false;
        for (int d = 0; d < n; d++) {
            if (prev == -1 or chr(pos + d) != chr(prev + d) or tget(pos + d) != tget(prev + d)) {
                diff = true;
                break;
            } else if (d > 0 and (isLMS(pos + d) or isLMS(prev + d))) {
                break;
            }
        }
        if (diff) {
            name++;
            prev = pos;
        }
        pos = (pos % 2 == 0) ? pos / 2 : (pos - 1) / 2;
        SA[n1 + pos] = name - 1;
    }
    for (int i = n - 1, j = n - 1; i >= n1; i--) {
        if (SA[i] >= 0) {
            SA[j--] = SA[i];
        }
    }

    int *SA1 = SA;
    int *s1 = SA + n - n1;
    if (name < n1) {
        SA_IS((unsigned char *)s1, SA1, n1, name - 1, sizeof(int));
    } else {
        for (int i = 0; i < n1; i++) {
            SA1[s1[i]] = i;
        }
    }
    bkt = (int *)malloc(sizeof(int) * (K + 1));
    getBuckets(s, bkt, n, K, cs, true);
    for (int i = 1, j = 0; i < n; i++) {
        if (isLMS(i)) {
            s1[j++] = i;
        }
    }
    for (int i = 0; i < n1; i++) {
        SA1[i] = s1[SA1[i]];
    }
    for (int i = n1; i < n; i++) {
        SA[i] = -1;
    }
    for (int i = n1 - 1; i >= 0; i--) {
        int j = SA[i];
        SA[i] = -1;
        SA[--bkt[chr(j)]] = j;
    }
    induceSAl(t, SA, s, bkt, n, K, cs, false);
    induceSAs(t, SA, s, bkt, n, K, cs, true);
    free(bkt);
    free(t);
}

vector<int> suffixArray(string &str) {
    int n = str.size() + 1;
    int *sa = (int *)malloc(sizeof(int) * n);
    unsigned char *s = (unsigned char *)malloc(sizeof(unsigned char) * (n + 2));
    int k = 256;
    int cs = sizeof(unsigned char);
    for (int i = 0; i < str.size(); i++) {
        s[i] = str[i];
    }
    s[int(str.size())] = 0;
    SA_IS((unsigned char *)(s), sa, n, k, cs);
    vector<int> res(n - 1);
    for (int i = 0; i < n - 1; i++) {
        res[i] = sa[i + 1];
    }
    free(sa);
    free(s);
    return res;
}
#line 4 "verify/LibraryChecker/string/SuffixArray.test.cpp"

int main() {
    cin.tie(0)->sync_with_stdio(0);
    string s;
    in(s);
    out(suffixArray(s));
}

Back to top page