rmfinalepsilon.h revision 3da1eb108d36da35333b2d655202791af854996b 
1// rmfinalepsilon.h
2
3// Licensed under the Apache License, Version 2.0 (the "License");
4// you may not use this file except in compliance with the License.
5// You may obtain a copy of the License at
6//
7//     http://www.apache.org/licenses/LICENSE-2.0
8//
9// Unless required by applicable law or agreed to in writing, software
10// distributed under the License is distributed on an "AS IS" BASIS,
11// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12// See the License for the specific language governing permissions and
13// limitations under the License.
14//
15// Copyright 2005-2010 Google, Inc.
16// Author: johans@google.com (Johan Schalkwyk)
17//
18// \file
19// Function to remove of final states that have epsilon only input arcs.
20
21#ifndef FST_LIB_RMFINALEPSILON_H__
22#define FST_LIB_RMFINALEPSILON_H__
23
24#include <tr1/unordered_set>
25using std::tr1::unordered_set;
26using std::tr1::unordered_multiset;
27#include <vector>
28using std::vector;
29
30#include <fst/connect.h>
31#include <fst/mutable-fst.h>
32
33
34namespace fst {
35
36template<class A>
37void RmFinalEpsilon(MutableFst<A>* fst) {
38  typedef typename A::StateId StateId;
39  typedef typename A::Weight Weight;
40
41  // Determine the coaccesibility of states.
42  vector<bool> access;
43  vector<bool> coaccess;
44  uint64 props = 0;
45  SccVisitor<A> scc_visitor(0, &access, &coaccess, &props);
46  DfsVisit(*fst, &scc_visitor);
47
48  // Find potential list of removable final states. These are final states
49  // that have no outgoing transitions or final states that have a
50  // non-coaccessible future. Complexity O(S)
51  unordered_set<StateId> finals;
52  for (StateIterator<Fst<A> > siter(*fst); !siter.Done(); siter.Next()) {
53    StateId s = siter.Value();
54    if (fst->Final(s) != Weight::Zero()) {
55      bool future_coaccess = false;
56      for (ArcIterator<Fst<A> > aiter(*fst, s); !aiter.Done(); aiter.Next()) {
57        const A& arc = aiter.Value();
58        if (coaccess[arc.nextstate]) {
59          future_coaccess = true;
60          break;
61        }
62      }
63      if (!future_coaccess) {
64        finals.insert(s);
65      }
66    }
67  }
68
69  // Move the final weight. Complexity O(E)
70  vector<A> arcs;
71  for (StateIterator<Fst<A> > siter(*fst); !siter.Done(); siter.Next()) {
72    StateId s = siter.Value();
73    Weight w(fst->Final(s));
74
75    arcs.clear();
76    for (ArcIterator<Fst<A> > aiter(*fst, s); !aiter.Done(); aiter.Next()) {
77      const A& arc = aiter.Value();
78      // is next state in the list of finals
79      if (finals.find(arc.nextstate) != finals.end()) {
80        // sum up all epsilon arcs
81        if (arc.ilabel == 0 && arc.olabel == 0) {
82          w = Plus(Times(fst->Final(arc.nextstate), arc.weight), w);
83        } else {
84          arcs.push_back(arc);
85        }
86      } else {
87        arcs.push_back(arc);
88      }
89    }
90
91    // If some arcs (epsilon arcs) were deleted, delete all
92    // arcs and add back only the non epsilon arcs
93    if (arcs.size() < fst->NumArcs(s)) {
94      fst->DeleteArcs(s);
95      fst->SetFinal(s, w);
96      for (size_t i = 0; i < arcs.size(); ++i) {
97        fst->AddArc(s, arcs[i]);
98      }
99    }
100  }
101
102  Connect(fst);
103}
104
105}  // namespace fst
106
107#endif  // FST_LIB_RMFINALEPSILON_H__
108