// la séquence initiale est lue et découpée en sous-séquences de
// longueur 20 ;
// chaque sous-séquence est terminée par une observation END pour que
// le HMM généré possède un état terminal
Sequences build_initial_sequences(const std::string& name)
{
Sequence sequence = read_initial_sequence(name, false);
Sequences sequences;
unsigned int length = sequence.size() / 20;
Sequence::const_iterator it = sequence.begin();
unsigned int added = 0;
unsigned int index = 0;
sequences.push_back(Sequence());
while (it != sequence.end()) {
if (added == length) {
sequences[index].push_back(Observation(0, END));
++index;
added = 0;
sequences.push_back(Sequence());
}
sequences[index].push_back(*it);
++added;
++it;
}
if (sequence.size() % 20 != 0) {
sequences[index].push_back(Observation(0, END));
}
return sequences;
}
/*private*/
LineSequencer::Sequences*
LineSequencer::findSequences()
{
Sequences *sequences = new Sequences();
planargraph::algorithm::ConnectedSubgraphFinder csFinder(graph);
vector<planargraph::Subgraph*> subgraphs;
csFinder.getConnectedSubgraphs(subgraphs);
for (vector<planargraph::Subgraph*>::const_iterator
it=subgraphs.begin(), endIt=subgraphs.end();
it!=endIt;
++it )
{
planargraph::Subgraph* subgraph = *it;
if (hasSequence(*subgraph)) {
planargraph::DirectedEdge::NonConstList* seq=findSequence(*subgraph);
sequences->push_back(seq);
}
else {
// if any subgraph cannot be sequenced, abort
delete subgraph;
delAll(*sequences);
delete sequences;
return nullptr;
}
delete subgraph;
}
return sequences;
}
void generateAllSubstrings(Sequences& substrings, const Sequences& s, size_t len)
{
for (size_t i = 0; i < s.size(); ++i)
{
for (int j = 0; j <= ((int)s[i].size() - (int)len); ++j)
{
string sub(string(&(s[i][j]), len));
substrings.push_back(sub);
if (sub.size() != len)
cout << "generateAllSubstrings size: " << sub.size() << endl;
}
}
}