M2MFstAligner::M2MFstAligner(string _model_file)
{
VectorFst<LogArc> *model = VectorFst<LogArc>::Read(_model_file);
for (StateIterator<VectorFst<LogArc> > siter(*model);
!siter.Done(); siter.Next()) {
LogArc::StateId q = siter.Value();
for (ArcIterator<VectorFst<LogArc> > aiter(*model, q);
!aiter.Done(); aiter.Next()) {
const LogArc & arc = aiter.Value();
alignment_model.insert(pair<LogArc::Label,LogWeight> (arc.ilabel, arc.weight));
}
}
isyms = (SymbolTable *) model->InputSymbols();
int i = 0;
eps = isyms->Find(i); //Can't write '0' here for some reason...
skip = isyms->Find(1);
vector<string> seps = split(isyms->Find(2), "_");
seq1_sep = seps[0];
seq2_sep = seps[1];
s1s2_sep = isyms->Find(3);
vector<string> params = split(isyms->Find(4), "_");
seq1_del = params[0].compare("true") ? false : true;
seq2_del = params[1].compare("true") ? false : true;
seq1_max = atoi(params[2].c_str());
seq2_max = atoi(params[3].c_str());
}
M2MFstAligner::M2MFstAligner( string _model_file, bool _penalize, bool _penalize_em, bool _restrict ){
/*
Initialize the aligner with a previously trained model.
The model requires that the first several symbols in the
symbols table contain the separator and other bookkeeping info.
*/
restrict = _restrict;
penalize = _penalize;
penalize_em = _penalize_em;
penalties.set_empty_key(0);
VectorFst<LogArc>* model = VectorFst<LogArc>::Read( _model_file );
for( StateIterator<VectorFst<LogArc> > siter(*model); !siter.Done(); siter.Next() ){
LogArc::StateId q = siter.Value();
for( ArcIterator<VectorFst<LogArc> > aiter(*model, q); !aiter.Done(); aiter.Next() ){
const LogArc& arc = aiter.Value();
alignment_model.insert( pair<LogArc::Label,LogWeight>(arc.ilabel,arc.weight) );
}
}
isyms = (SymbolTable*)model->InputSymbols();
int i = 0;
eps = isyms->Find(i);//Can't write '0' here for some reason...
skip = isyms->Find(1);
string tie = "_"; //tie to pack parameters
string sseps = isyms->Find(2);
vector<string> seps = tokenize_utf8_string( &sseps, &tie );
seq1_sep = seps[0];
seq2_sep = seps[1];
s1s2_sep = isyms->Find(3);
string sparams = isyms->Find(4);
vector<string> params = tokenize_utf8_string( &sparams, &tie );
seq1_del = params[0].compare("true") ? false : true;
seq2_del = params[1].compare("true") ? false : true;
seq1_max = atoi(params[2].c_str());
seq2_max = atoi(params[3].c_str());
}
