mosesdecoder/moses/TranslationModel/UG/util/tokenindex.dump.cc

32 lines
812 B
C++
Raw Normal View History

2014-06-12 21:30:41 +04:00
// (c) 2007,2008 Ulrich Germann
// Licensed to NRC-CNRC under special agreement.
/**
* @author Ulrich Germann
* @file tokenindex.dump.cc
* @brief Dumps a TokenIndex (vocab file for TPPT and TPLM) to stdout.
*/
2014-08-14 17:04:25 +04:00
#include "../mm/tpt_tokenindex.h"
2014-06-12 21:30:41 +04:00
#include <iostream>
#include <iomanip>
using namespace std;
2016-02-18 19:39:34 +03:00
using namespace sapt;
int
2014-06-12 21:30:41 +04:00
main(int argc,char* argv[])
{
if (argc > 1 && !strcmp(argv[1], "-h")) {
printf("Usage: %s <file>\n\n", argv[0]);
cout << "Converts a phrase table in text format to a phrase table in tighly packed format." << endl;
cout << "input file: token index file" << endl;
exit(1);
}
TokenIndex I;
I.open(argv[1]);
vector<char const*> foo = I.reverseIndex();
for (size_t i = 0; i < foo.size(); i++)
cout << setw(10) << i << " " << foo[i] << endl;
}