File size: 1,576 Bytes
158b61b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 |
#include "moses/TranslationModel/UG/mm/ug_mm_ttrack.h"
#include "moses/TranslationModel/UG/mm/ug_mm_tsa.h"
#include "moses/TranslationModel/UG/mm/tpt_tokenindex.h"
#include "moses/TranslationModel/UG/mm/ug_corpus_token.h"
#include "moses/TranslationModel/UG/mm/ug_typedefs.h"
#include "moses/TranslationModel/UG/mm/tpt_pickler.h"
#include "moses/TranslationModel/UG/mm/ug_bitext.h"
#include "moses/TranslationModel/UG/mm/ug_lexical_phrase_scorer2.h"
#include "moses/TranslationModel/UG/generic/file_io/ug_stream.h"
// using namespace Moses;
using namespace ugdiss;
using namespace sapt;
using namespace std;
typedef L2R_Token<SimpleWordId> Token;
TokenIndex V;
SPTR<vector<vector<Token> > > C(new vector<vector<Token> >());
void
add_file(string fname)
{
boost::iostreams::filtering_istream in;
open_input_stream(fname,in);
string line;
while (getline(in,line))
{
C->push_back(vector<Token>());
fill_token_seq(V,line,C->back());
}
}
int
main(int argc, char* argv[])
{
V.setDynamic(true);
add_file(argv[1]);
SPTR<imTtrack<Token> > T(new imTtrack<Token>(C));
imTSA<Token> I(T,NULL,NULL);
string line;
while (getline(cin,line))
{
vector<Token> seq; fill_token_seq<Token>(V,line,seq);
for (size_t i = 0; i < seq.size(); ++i)
{
TSA<Token>::tree_iterator m(&I);
cout << V[seq[i].id()];
for (size_t k = i; k < seq.size() && m.extend(seq[k]); ++k)
{
cout << " ";
if (k > i) cout << V[seq[k].id()] << " ";
cout << "[" << m.approxOccurrenceCount() << "]";
}
cout << endl;
}
}
}
|