int main(int argc, char** argv) {
// handle parameters
po::variables_map cfg;
if (!init_params(argc,argv, &cfg)) exit(1); // something is wrong
// set number of jobs
#ifdef _OPENMP
if (cfg.count("jobs")) {
omp_set_num_threads(cfg["jobs"].as<int>());
cerr << "CLIR::Using " << cfg["jobs"].as<int>() << " threads.\n";
}
#else
#endif
const bool no_qtf = cfg.count("no-qtf");
string run_id = cfg["run-id"].as<string>();
const int K = cfg["K"].as<int>();
// load queries
vector<Query> queries;
CLIR::loadQueries(cfg["queries"].as<string>(), queries, cfg.count("psq"), cfg.count("text-input"));
size_t queries_size = queries.size();
size_t done = queries_size / 10.0;
cerr.precision(1);
// setup result vector
vector<vector<Score> > results(queries_size);
if (cfg.count("index")) {
Index::Index idx;
Index::LoadIndex(cfg["index"].as<string>(), idx);
IndexScorer* ranker = CLIR::setupIndexScorer(cfg["model"].as<string>(), &idx);
cerr << "CLIR::Retrieving from in-memory inverted index ...";
# pragma omp parallel for
for ( int i = 0 ; i < queries_size ; ++ i ) {
vector<double> scores(idx.NumberOfDocuments(), .0);
ranker->score(queries[i], scores, no_qtf);
Scores kbest(K);
for (int d=0;d<idx.NumberOfDocuments();++d) {
if (scores[d]>0) {
kbest.update( Score(idx.GetDocID(d), prob_t(scores[d]) ) );
}
}
results[i] = kbest.k_largest();
i%done == 0 ? cerr << done/queries_size << "%.." : cerr ;
}
delete ranker;
cerr << "ok.\n";
} else if (cfg.count("documents")) {
// load DfTable
DfTable dft(cfg["dftable"].as<string>());
cerr << "CLIR::DF table loaded (" << dft.size() << " entries)." << endl;
// load document collection
vector<CLIR::Document> documents;
double avgDocLen = CLIR::loadDocuments(cfg["documents"].as<string>(), documents);
size_t N = documents.size();
if (N < dft.mMaxDf) {
cerr << "CLIR::maxDf=" << dft.mMaxDf << " > N=" << N << ", setting N to maxDf.\n";
N = dft.mMaxDf;
}
Scorer* ranker = CLIR::setupScorer(cfg["model"].as<string>(), N, avgDocLen, &dft);
cerr << "CLIR::Retrieving from in-memory documents ...";
# pragma omp parallel for
for ( int i = 0 ; i < queries_size ; ++ i ) {
const Query& query = queries[i];
Scores scores(K);
for ( int d = 0 ; d < N ; ++d ) {
Document& doc = documents[d];
scores.update( Score(doc.id_, ranker->score(query, doc, no_qtf) ) );
}
results[i] = scores.k_largest();
i%done == 0 ? cerr << done/queries_size << "%.." : cerr ;
}
delete ranker;
cerr << "ok.\n";
} else {
// load DfTable
DfTable dft(cfg["dftable"].as<string>());
cerr << "CLIR::DF table loaded (" << dft.size() << " entries)." << endl;
size_t N = cfg["N"].as<int>();
if (N < dft.mMaxDf) {
cerr << "CLIR::maxDf=" << dft.mMaxDf << " > N=" << N << ", setting N to maxDf.\n";
N = dft.mMaxDf;
}
double avgDocLen = cfg["avg_len"].as<double>();
cerr << "CLIR::Retrieving from STDIN documents ...";
Scorer* ranker = CLIR::setupScorer(cfg["model"].as<string>(), N, avgDocLen, &dft);
vector<Scores> scores (queries_size, Scores(K)); // score vectors for each query
string docid, raw;
int len, c = 0;
cerr << "reporter:status:scanned="<< c << "\n";
TermVector doc;
while (cin >> docid) {
cin.ignore(1,'\t');
cin >> len;
cin.ignore(1,'\t');
getline(cin, raw);
if (docid.size() == 0 || len <= 0 || raw.size() == 0)
continue;
Document doc(vutils::read_vector(raw), docid, len);
// for each query compute score between current document and query
# pragma omp parallel for
for ( size_t i = 0 ; i < queries_size ; ++i ) {
scores[i].update( Score(doc.id_, ranker->score(queries[i], doc, no_qtf) ) );
}
c++;
c%10==0 ? cerr << "reporter:status:scanned="<< c << "\n" : cerr ;
}
delete ranker;
// create kbest lists
for ( size_t i = 0; i < scores.size(); ++i ) {
results[i] = scores[i].k_largest();
}
}
// retrieval done; output results
WriteFile out(cfg["output"].as<string>());
if (cfg.count("qrels")) {
cerr << "CLIR::Evaluating results ...";
CLIR::IRScorer irs(queries_size, cfg["qrels"].as<string>());
# pragma omp parallel for
for ( int i = 0 ; i < queries_size ; ++ i ) {
irs.evaluateIthSegment(i, queries[i].id(), results[i]);
}
*out << "num_q\t" << irs.N() << "\tnum_rel_ret\t" << irs.NUMRELRET() << "\tMAP\t" << irs.MAP() << "\tNDCG\t" << irs.NDCG() << endl;
} else {
cerr << "CLIR::Writing results ...";
for ( int i = 0 ; i < queries_size ; ++ i ) {
CLIR::writeResult(*out, queries[i], results[i], run_id);
}
}
cerr << "ok.\nCLIR::done.\n";
}
