int main(int argc, char** argv) {
// handle parameters
po::variables_map cfg;
if (!init_params(argc,argv, &cfg)) exit(1); // something is wrong
DfTable dft (cfg["dftable"].as<string>());
cerr << "DF table loaded (" << dft.size() << " entries)." << endl;
std::string metric;
bool normalize = false;
Scorer* scorer = setup_metric(cfg, metric, normalize);
if (cfg.count("N"))
scorer->setDocCount(cfg["N"].as<double>());
else
scorer->setDocCount(dft.mMaxDf);
cerr << "Term weighting metric: " << metric << " " << scorer->print() << " [normalization=" << normalize << "]" << endl;
bool verbose = false;
if (cfg.count("verbose"))
verbose = true;
string docid;
int len = -1;
string v_str;
TermVector v;
int c = 0;
int skipped = 0;
int empty_input = 0;
int empty_output = 0;
while (cin >> docid) {
cin.ignore(1, '\t');
cin >> len;
cin.ignore(1, '\t');
getline(cin, v_str);
if (docid.size() == 0 || len <= 0)
continue;
if (v_str.size() == 0) {
cerr << "WARNING: input vector (id=" << docid << ",len=" << len << ") empty!" << endl;
cout << docid << "\t" << len << "\t" << endl;
empty_input++;
continue;
}
v = vutils::read_vector(v_str);
Document d(v, scorer, docid, len);
skipped += d.calc_wvec(dft, normalize, verbose);
if (d.wvec_.size() == 0) {
if (verbose)
cerr << "WARNING! " << d.docid_ << " output vector is empty!" << endl;
empty_output++;
}
// write to output
cout << d.docid_ << "\t" << d.len_ << "\t";
vutils::write_vector(d.wvec_, cout);
cout << endl;
c++;
c%1000==0 ? cerr << "." << c << "." : cerr ;
}
delete scorer;
cerr << "done." << endl << endl
<< c << "\tlines read/written." << endl
<< empty_input << "\tempty input vectors." << endl
<< empty_output << "\tempty output vectors." << endl
<< skipped << "\tterms skipped due missing df value." << endl;
}
