int _tmain(int argc, _TCHAR* argv[])
{
//int i;
//printf("argc: %d\n", argc);
//for(i = 0; i < argc; i++)
// printf("arg %d: %S\n", i, argv[i]);
if(argc != 4)
usage();
printf("reading %S to buffer...", argv[1]);
deffile = loadFileToBuf(argv[1], &deflen);
if((deffile != NULL)&&(deflen != 0))
{
printf("read 0x%x bytes OK\n", deflen);
printf("reading %S to buffer...", argv[2]);
listfile = loadFileToBuf(argv[2], &listlen);
if((listfile != NULL)&&(listlen != 0))
{
printf("read 0x%x bytes OK\n", listlen);
processFiles(argv[3]);
}
}
if(deffile)
free(deffile);
if(listfile)
free(listfile);
printf("\n\n");
return 0;
}
int main(int argc, char* argv[])
{
if (argc == 1)
{
processFiles("");
}
else if (argc == 2)
{
processFiles(argv[1]);
}
else
{
printf("Usage: LGEOTables [LGEO Path]\n");
return 1;
}
return 0;
}
void processHist(std::vector<std::string> event_timing_vec, int max_size)
{
std::cerr << event_timing_vec.size() << std::endl;
//If all the vectors are full (6 entries)
if(event_timing_vec.size()==max_size)
{
for(int i=0;i<max_size;i++)
{
std::cerr << event_timing_vec[i] << std::endl;
processFiles(event_timing_vec[i]);
}
}
};
int main(int argc, char* argv[])
{
std::cerr << "Consolidate v2.0 written by Philipp Koehn" << std::endl
<< "consolidating direct and indirect rule tables" << std::endl;
if (argc < 4) {
std::cerr << "syntax: consolidate phrase-table.direct phrase-table.indirect phrase-table.consolidated [--Hierarchical] [--OnlyDirect] [--PhraseCount] [--GoodTuring counts-of-counts-file] [--KneserNey counts-of-counts-file] [--LowCountFeature] [--SourceLabels source-labels-file] [--PartsOfSpeech parts-of-speech-file] [--MinScore id:threshold[,id:threshold]*]" << std::endl;
exit(1);
}
const std::string fileNameDirect = argv[1];
const std::string fileNameIndirect = argv[2];
const std::string fileNameConsolidated = argv[3];
std::string fileNameCountOfCounts;
std::string fileNameSourceLabelSet;
std::string fileNamePartsOfSpeechVocabulary;
for(int i=4; i<argc; i++) {
if (strcmp(argv[i],"--Hierarchical") == 0) {
hierarchicalFlag = true;
std::cerr << "processing hierarchical rules" << std::endl;
} else if (strcmp(argv[i],"--OnlyDirect") == 0) {
onlyDirectFlag = true;
std::cerr << "only including direct translation scores p(e|f)" << std::endl;
} else if (strcmp(argv[i],"--PhraseCount") == 0) {
phraseCountFlag = true;
std::cerr << "including the phrase count feature" << std::endl;
} else if (strcmp(argv[i],"--GoodTuring") == 0) {
goodTuringFlag = true;
UTIL_THROW_IF2(i+1==argc, "specify count of count files for Good Turing discounting!");
fileNameCountOfCounts = argv[++i];
std::cerr << "adjusting phrase translation probabilities with Good Turing discounting" << std::endl;
} else if (strcmp(argv[i],"--KneserNey") == 0) {
kneserNeyFlag = true;
UTIL_THROW_IF2(i+1==argc, "specify count of count files for Kneser Ney discounting!");
fileNameCountOfCounts = argv[++i];
std::cerr << "adjusting phrase translation probabilities with Kneser Ney discounting" << std::endl;
} else if (strcmp(argv[i],"--LowCountFeature") == 0) {
lowCountFlag = true;
std::cerr << "including the low count feature" << std::endl;
} else if (strcmp(argv[i],"--CountBinFeature") == 0 ||
strcmp(argv[i],"--SparseCountBinFeature") == 0) {
if (strcmp(argv[i],"--SparseCountBinFeature") == 0)
sparseCountBinFeatureFlag = true;
std::cerr << "include "<< (sparseCountBinFeatureFlag ? "sparse " : "") << "count bin feature:";
int prev = 0;
while(i+1<argc && argv[i+1][0]>='0' && argv[i+1][0]<='9') {
int binCount = Moses::Scan<int>(argv[++i]);
countBin.push_back( binCount );
if (prev+1 == binCount) {
std::cerr << " " << binCount;
} else {
std::cerr << " " << (prev+1) << "-" << binCount;
}
prev = binCount;
}
std::cerr << " " << (prev+1) << "+" << std::endl;
} else if (strcmp(argv[i],"--LogProb") == 0) {
logProbFlag = true;
std::cerr << "using log-probabilities" << std::endl;
} else if (strcmp(argv[i],"--Counts") == 0) {
countsProperty = true;
std::cerr << "output counts as a property" << std::endl;;
} else if (strcmp(argv[i],"--SourceLabels") == 0) {
sourceLabelsFlag = true;
UTIL_THROW_IF2(i+1==argc, "specify source label set file!");
fileNameSourceLabelSet = argv[++i];
std::cerr << "processing source labels property" << std::endl;
} else if (strcmp(argv[i],"--PartsOfSpeech") == 0) {
partsOfSpeechFlag = true;
UTIL_THROW_IF2(i+1==argc, "specify parts-of-speech file!");
fileNamePartsOfSpeechVocabulary = argv[++i];
std::cerr << "processing parts-of-speech property" << std::endl;
} else if (strcmp(argv[i],"--MinScore") == 0) {
std::string setting = argv[++i];
bool done = false;
while (!done) {
std::string single_setting;
size_t pos;
if ((pos = setting.find(",")) != std::string::npos) {
single_setting = setting.substr(0, pos);
setting.erase(0, pos + 1);
} else {
single_setting = setting;
done = true;
}
pos = single_setting.find(":");
UTIL_THROW_IF2(pos == std::string::npos, "faulty MinScore setting '" << single_setting << "' in '" << argv[i] << "'");
unsigned int field = Moses::Scan<unsigned int>( single_setting.substr(0,pos) );
float threshold = Moses::Scan<float>( single_setting.substr(pos+1) );
if (field == 0) {
minScore0 = threshold;
std::cerr << "setting minScore0 to " << threshold << std::endl;
} else if (field == 2) {
minScore2 = threshold;
std::cerr << "setting minScore2 to " << threshold << std::endl;
} else {
UTIL_THROW2("MinScore currently only supported for indirect (0) and direct (2) phrase translation probabilities");
}
}
} else {
UTIL_THROW2("unknown option " << argv[i]);
}
}
processFiles( fileNameDirect, fileNameIndirect, fileNameConsolidated, fileNameCountOfCounts, fileNameSourceLabelSet, fileNamePartsOfSpeechVocabulary );
}
