string/aho_corasick_for_general_trie.hpp

• View this file on GitHub
• Last update: 2024-11-01 21:56:32+09:00
• Include: #include "string/aho_corasick_for_general_trie.hpp"
• Link: https://qoj.ac/contest/1435/problem/7742

Depends on

• ds/dynamic_array.hpp
• ds/hashmap.hpp
• ds/to_small_key.hpp
• graph/base.hpp

Code

#include "ds/dynamic_array.hpp"
#include "ds/to_small_key.hpp"
#include "graph/base.hpp"

// 入力: 0 を根とする木で辺には int ラベルがついている
// return: suffix link
// https://qoj.ac/contest/1435/problem/7742
vc<int> aho_corasick_for_general_trie(Graph<int, 1> G) {
  const int N = G.N;
  To_Small_Key MP(N);
  assert(N < (1 << 20));
  Dynamic_Array<int, true> X(6 * N, 0);
  vc<int> BFS(N), link(N, -1);
  using np = decltype(X)::np;
  vc<np> S(N);
  int p = 0, q = 0;
  BFS[q++] = 0;
  S[0] = X.new_root();
  while (p < q) {
    int v = BFS[p++];
    if (v) S[v] = S[link[v]];
    for (auto& e: G[v]) {
      int s = MP.query(e.cost, 1), w = e.to;
      link[w] = X.get(S[v], s);
      S[v] = X.set(S[v], s, w);
      BFS[q++] = w;
    }
  }
  return link;
}

#line 2 "ds/dynamic_array.hpp"

template <typename T, bool PERSISTENT>
struct Dynamic_Array {
  static constexpr int LOG = 4;
  static constexpr int MASK = (1 << LOG) - 1;
  struct Node {
    T x;
    Node* ch[1 << LOG] = {};
  };
  const int NODES;
  Node* pool;
  int pid;
  using np = Node*;
  const T x0;

  Dynamic_Array(int NODES, T default_value) : NODES(NODES), pid(0), x0(default_value) { pool = new Node[NODES]; }
  ~Dynamic_Array() { delete[] pool; }
  np new_root() {
    pool[pid].x = x0;
    fill(pool[pid].ch, pool[pid].ch + (1 << LOG), nullptr);
    return &(pool[pid++]);
  }

  np new_node(vc<T> dat) {
    np root = new_root();
    FOR(i, len(dat)) root = set(root, i, dat[i], false);
    return root;
  }

  T get(np c, int idx) {
    if (!c) return x0;
    if (idx == 0) return c->x;
    return get(c->ch[idx & MASK], (idx - 1) >> LOG);
  }

  np set(np c, int idx, T x, bool make_copy = true) {
    c = (c ? copy_node(c, make_copy) : new_root());
    if (idx == 0) {
      c->x = x;
      return c;
    }
    c->ch[idx & MASK] = set(c->ch[idx & MASK], (idx - 1) >> LOG, x);
    return c;
  }

private:
  np copy_node(np c, bool make_copy) {
    if (!make_copy || !PERSISTENT) return c;
    pool[pid].x = c->x;
    FOR(k, (1 << LOG)) pool[pid].ch[k] = c->ch[k];
    return &(pool[pid++]);
  }
};
#line 2 "ds/hashmap.hpp"

// u64 -> Val

template <typename Val>
struct HashMap {
  // n は入れたいものの個数で ok

  HashMap(u32 n = 0) { build(n); }
  void build(u32 n) {
    u32 k = 8;
    while (k < n * 2) k *= 2;
    cap = k / 2, mask = k - 1;
    key.resize(k), val.resize(k), used.assign(k, 0);
  }

  // size を保ったまま. size=0 にするときは build すること.

  void clear() {
    used.assign(len(used), 0);
    cap = (mask + 1) / 2;
  }
  int size() { return len(used) / 2 - cap; }

  int index(const u64& k) {
    int i = 0;
    for (i = hash(k); used[i] && key[i] != k; i = (i + 1) & mask) {}
    return i;
  }

  Val& operator[](const u64& k) {
    if (cap == 0) extend();
    int i = index(k);
    if (!used[i]) { used[i] = 1, key[i] = k, val[i] = Val{}, --cap; }
    return val[i];
  }

  Val get(const u64& k, Val default_value) {
    int i = index(k);
    return (used[i] ? val[i] : default_value);
  }

  bool count(const u64& k) {
    int i = index(k);
    return used[i] && key[i] == k;
  }

  // f(key, val)

  template <typename F>
  void enumerate_all(F f) {
    FOR(i, len(used)) if (used[i]) f(key[i], val[i]);
  }

private:
  u32 cap, mask;
  vc<u64> key;
  vc<Val> val;
  vc<bool> used;

  u64 hash(u64 x) {
    static const u64 FIXED_RANDOM = std::chrono::steady_clock::now().time_since_epoch().count();
    x += FIXED_RANDOM;
    x = (x ^ (x >> 30)) * 0xbf58476d1ce4e5b9;
    x = (x ^ (x >> 27)) * 0x94d049bb133111eb;
    return (x ^ (x >> 31)) & mask;
  }

  void extend() {
    vc<pair<u64, Val>> dat;
    dat.reserve(len(used) / 2 - cap);
    FOR(i, len(used)) {
      if (used[i]) dat.eb(key[i], val[i]);
    }
    build(2 * len(dat));
    for (auto& [a, b]: dat) (*this)[a] = b;
  }
};
#line 2 "ds/to_small_key.hpp"

// [30,10,20,30] -> [0,1,2,0] etc.
struct To_Small_Key {
  int kind = 0;
  HashMap<int> MP;
  To_Small_Key(u32 n = 0) : MP(n) {}
  void reserve(u32 n) { MP.build(n); }
  int size() { return MP.size(); }
  int query(u64 x, bool set_if_not_exist) {
    int ans = MP.get(x, -1);
    if (ans == -1 && set_if_not_exist) MP[x] = ans = kind++;
    return ans;
  }
};
#line 2 "graph/base.hpp"

template <typename T>
struct Edge {
  int frm, to;
  T cost;
  int id;
};

template <typename T = int, bool directed = false>
struct Graph {
  static constexpr bool is_directed = directed;
  int N, M;
  using cost_type = T;
  using edge_type = Edge<T>;
  vector<edge_type> edges;
  vector<int> indptr;
  vector<edge_type> csr_edges;
  vc<int> vc_deg, vc_indeg, vc_outdeg;
  bool prepared;

  class OutgoingEdges {
  public:
    OutgoingEdges(const Graph* G, int l, int r) : G(G), l(l), r(r) {}

    const edge_type* begin() const {
      if (l == r) { return 0; }
      return &G->csr_edges[l];
    }

    const edge_type* end() const {
      if (l == r) { return 0; }
      return &G->csr_edges[r];
    }

  private:
    const Graph* G;
    int l, r;
  };

  bool is_prepared() { return prepared; }

  Graph() : N(0), M(0), prepared(0) {}
  Graph(int N) : N(N), M(0), prepared(0) {}

  void build(int n) {
    N = n, M = 0;
    prepared = 0;
    edges.clear();
    indptr.clear();
    csr_edges.clear();
    vc_deg.clear();
    vc_indeg.clear();
    vc_outdeg.clear();
  }

  void add(int frm, int to, T cost = 1, int i = -1) {
    assert(!prepared);
    assert(0 <= frm && 0 <= to && to < N);
    if (i == -1) i = M;
    auto e = edge_type({frm, to, cost, i});
    edges.eb(e);
    ++M;
  }

#ifdef FASTIO
  // wt, off
  void read_tree(bool wt = false, int off = 1) { read_graph(N - 1, wt, off); }

  void read_graph(int M, bool wt = false, int off = 1) {
    for (int m = 0; m < M; ++m) {
      INT(a, b);
      a -= off, b -= off;
      if (!wt) {
        add(a, b);
      } else {
        T c;
        read(c);
        add(a, b, c);
      }
    }
    build();
  }
#endif

  void build() {
    assert(!prepared);
    prepared = true;
    indptr.assign(N + 1, 0);
    for (auto&& e: edges) {
      indptr[e.frm + 1]++;
      if (!directed) indptr[e.to + 1]++;
    }
    for (int v = 0; v < N; ++v) { indptr[v + 1] += indptr[v]; }
    auto counter = indptr;
    csr_edges.resize(indptr.back() + 1);
    for (auto&& e: edges) {
      csr_edges[counter[e.frm]++] = e;
      if (!directed)
        csr_edges[counter[e.to]++] = edge_type({e.to, e.frm, e.cost, e.id});
    }
  }

  OutgoingEdges operator[](int v) const {
    assert(prepared);
    return {this, indptr[v], indptr[v + 1]};
  }

  vc<int> deg_array() {
    if (vc_deg.empty()) calc_deg();
    return vc_deg;
  }

  pair<vc<int>, vc<int>> deg_array_inout() {
    if (vc_indeg.empty()) calc_deg_inout();
    return {vc_indeg, vc_outdeg};
  }

  int deg(int v) {
    if (vc_deg.empty()) calc_deg();
    return vc_deg[v];
  }

  int in_deg(int v) {
    if (vc_indeg.empty()) calc_deg_inout();
    return vc_indeg[v];
  }

  int out_deg(int v) {
    if (vc_outdeg.empty()) calc_deg_inout();
    return vc_outdeg[v];
  }

#ifdef FASTIO
  void debug() {
    print("Graph");
    if (!prepared) {
      print("frm to cost id");
      for (auto&& e: edges) print(e.frm, e.to, e.cost, e.id);
    } else {
      print("indptr", indptr);
      print("frm to cost id");
      FOR(v, N) for (auto&& e: (*this)[v]) print(e.frm, e.to, e.cost, e.id);
    }
  }
#endif

  vc<int> new_idx;
  vc<bool> used_e;

  // G における頂点 V[i] が、新しいグラフで i になるようにする
  // {G, es}
  // sum(deg(v)) の計算量になっていて、
  // 新しいグラフの n+m より大きい可能性があるので注意
  Graph<T, directed> rearrange(vc<int> V, bool keep_eid = 0) {
    if (len(new_idx) != N) new_idx.assign(N, -1);
    int n = len(V);
    FOR(i, n) new_idx[V[i]] = i;
    Graph<T, directed> G(n);
    vc<int> history;
    FOR(i, n) {
      for (auto&& e: (*this)[V[i]]) {
        if (len(used_e) <= e.id) used_e.resize(e.id + 1);
        if (used_e[e.id]) continue;
        int a = e.frm, b = e.to;
        if (new_idx[a] != -1 && new_idx[b] != -1) {
          history.eb(e.id);
          used_e[e.id] = 1;
          int eid = (keep_eid ? e.id : -1);
          G.add(new_idx[a], new_idx[b], e.cost, eid);
        }
      }
    }
    FOR(i, n) new_idx[V[i]] = -1;
    for (auto&& eid: history) used_e[eid] = 0;
    G.build();
    return G;
  }

  Graph<T, true> to_directed_tree(int root = -1) {
    if (root == -1) root = 0;
    assert(!is_directed && prepared && M == N - 1);
    Graph<T, true> G1(N);
    vc<int> par(N, -1);
    auto dfs = [&](auto& dfs, int v) -> void {
      for (auto& e: (*this)[v]) {
        if (e.to == par[v]) continue;
        par[e.to] = v, dfs(dfs, e.to);
      }
    };
    dfs(dfs, root);
    for (auto& e: edges) {
      int a = e.frm, b = e.to;
      if (par[a] == b) swap(a, b);
      assert(par[b] == a);
      G1.add(a, b, e.cost);
    }
    G1.build();
    return G1;
  }

private:
  void calc_deg() {
    assert(vc_deg.empty());
    vc_deg.resize(N);
    for (auto&& e: edges) vc_deg[e.frm]++, vc_deg[e.to]++;
  }

  void calc_deg_inout() {
    assert(vc_indeg.empty());
    vc_indeg.resize(N);
    vc_outdeg.resize(N);
    for (auto&& e: edges) { vc_indeg[e.to]++, vc_outdeg[e.frm]++; }
  }
};
#line 4 "string/aho_corasick_for_general_trie.hpp"

// 入力: 0 を根とする木で辺には int ラベルがついている
// return: suffix link
// https://qoj.ac/contest/1435/problem/7742
vc<int> aho_corasick_for_general_trie(Graph<int, 1> G) {
  const int N = G.N;
  To_Small_Key MP(N);
  assert(N < (1 << 20));
  Dynamic_Array<int, true> X(6 * N, 0);
  vc<int> BFS(N), link(N, -1);
  using np = decltype(X)::np;
  vc<np> S(N);
  int p = 0, q = 0;
  BFS[q++] = 0;
  S[0] = X.new_root();
  while (p < q) {
    int v = BFS[p++];
    if (v) S[v] = S[link[v]];
    for (auto& e: G[v]) {
      int s = MP.query(e.cost, 1), w = e.to;
      link[w] = X.get(S[v], s);
      S[v] = X.set(S[v], s, w);
      BFS[q++] = w;
    }
  }
  return link;
}

Back to top page