Home | History | Annotate | Download | only in pdt
      1 // pdtexpand.cc
      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: riley (at) google.com (Michael Riley)
     17 // Modified: jpr (at) google.com (Jake Ratkiewicz) to use FstClass
     18 //
     19 // \file
     20 // Expands a (bounded-stack) PDT as an FST.
     21 //
     22 
     23 #include <fst/extensions/pdt/pdtscript.h>
     24 #include <fst/util.h>
     25 
     26 DEFINE_string(pdt_parentheses, "", "PDT parenthesis label pairs.");
     27 DEFINE_bool(connect, true, "Trim output");
     28 DEFINE_bool(keep_parentheses, false, "Keep PDT parentheses in result.");
     29 DEFINE_string(weight, "", "Weight threshold");
     30 
     31 
     32 int main(int argc, char **argv) {
     33   namespace s = fst::script;
     34 
     35   string usage = "Expand a (bounded-stack) PDT as an FST.\n\n  Usage: ";
     36   usage += argv[0];
     37   usage += " in.pdt [out.fst]\n";
     38 
     39   std::set_new_handler(FailedNewHandler);
     40   SET_FLAGS(usage.c_str(), &argc, &argv, true);
     41   if (argc > 3) {
     42     ShowUsage();
     43     return 1;
     44   }
     45 
     46   string in_name = (argc > 1 && (strcmp(argv[1], "-") != 0)) ? argv[1] : "";
     47   string out_name = argc > 2 ? argv[2] : "";
     48 
     49   s::FstClass *ifst = s::FstClass::Read(in_name);
     50   if (!ifst) return 1;
     51 
     52   if (FLAGS_pdt_parentheses.empty()) {
     53     LOG(ERROR) << argv[0] << ": No PDT parenthesis label pairs provided";
     54     return 1;
     55   }
     56 
     57   vector<pair<int64, int64> > parens;
     58   fst::ReadLabelPairs(FLAGS_pdt_parentheses, &parens, false);
     59 
     60   s::WeightClass weight_threshold = FLAGS_weight.empty() ?
     61       s::WeightClass::Zero() :
     62       s::WeightClass(ifst->WeightType(), FLAGS_weight);
     63 
     64   s::VectorFstClass ofst(ifst->ArcType());
     65   s::PdtExpand(*ifst, parens, &ofst, s::PdtExpandOptions(
     66       FLAGS_connect, FLAGS_keep_parentheses, weight_threshold));
     67 
     68   ofst.Write(out_name);
     69 
     70   return 0;
     71 }
     72