From d03991acec06b10bdd6fe213aac64012978ae90b Mon Sep 17 00:00:00 2001 From: Hieu Hoang Date: Thu, 6 Oct 2016 13:31:18 +0100 Subject: delete CreateProbingPT2 --- Jamroot | 2 + contrib/moses2/CreateProbingPT2.cpp | 113 ------------------------------------ contrib/moses2/Jamfile | 3 +- 3 files changed, 3 insertions(+), 115 deletions(-) delete mode 100644 contrib/moses2/CreateProbingPT2.cpp diff --git a/Jamroot b/Jamroot index efafa0122..7a7be5c93 100644 --- a/Jamroot +++ b/Jamroot @@ -341,3 +341,5 @@ if [ path.exists $(TOP)/dist ] && $(prefix) != dist { local temp = [ _shell "mkdir -p $(TOP)/bin" ] ; local temp = [ _shell "rm -f $(TOP)/bin/moses_chart" ] ; local temp = [ _shell "cd $(TOP)/bin && ln -s moses moses_chart" ] ; +local temp = [ _shell "cd $(TOP)/bin && ln -s CreateProbingPT CreateProbingPT2" ] ; + diff --git a/contrib/moses2/CreateProbingPT2.cpp b/contrib/moses2/CreateProbingPT2.cpp deleted file mode 100644 index 24b0e2fd1..000000000 --- a/contrib/moses2/CreateProbingPT2.cpp +++ /dev/null @@ -1,113 +0,0 @@ -#include -#include -#include "util/usage.hh" -#include "TranslationModel/ProbingPT/storing.hh" -#include "legacy/InputFileStream.h" -#include "legacy/OutputFileStream.h" -#include "legacy/Util2.h" - -using namespace std; - -std::string ReformatSCFGFile(const std::string &path); - -int main(int argc, char* argv[]) -{ - string inPath, outPath; - int num_scores = 4; - int num_lex_scores = 0; - bool log_prob = false; - bool scfg = false; - int max_cache_size = 50000; - - namespace po = boost::program_options; - po::options_description desc("Options"); - desc.add_options() - ("help", "Print help messages") - ("input-pt", po::value()->required(), "Text pt") - ("output-dir", po::value()->required(), "Directory when binary files will be written") - ("num-scores", po::value()->default_value(num_scores), "Number of pt scores") - ("num-lex-scores", po::value()->default_value(num_lex_scores), "Number of lexicalized reordering scores") - ("log-prob", "log (and floor) probabilities before storing") - ("max-cache-size", po::value()->default_value(max_cache_size), "Maximum number of high-count source lines to write to cache file. 0=no cache, negative=no limit") - ("scfg", "Rules are SCFG in Moses format (ie. with non-terms and LHS") - - ; - - po::variables_map vm; - try { - po::store(po::parse_command_line(argc, argv, desc), - vm); // can throw - - /** --help option - */ - if ( vm.count("help")) { - std::cout << desc << std::endl; - return EXIT_SUCCESS; - } - - po::notify(vm); // throws on error, so do after help in case - // there are any problems - } catch(po::error& e) { - std::cerr << "ERROR: " << e.what() << std::endl << std::endl; - std::cerr << desc << std::endl; - return EXIT_FAILURE; - } - - if (vm.count("input-pt")) inPath = vm["input-pt"].as(); - if (vm.count("output-dir")) outPath = vm["output-dir"].as(); - if (vm.count("num-scores")) num_scores = vm["num-scores"].as(); - if (vm.count("num-lex-scores")) num_lex_scores = vm["num-lex-scores"].as(); - if (vm.count("max-cache-size")) max_cache_size = vm["max-cache-size"].as(); - if (vm.count("log-prob")) log_prob = true; - if (vm.count("scfg")) scfg = true; - - - if (scfg) { - inPath = ReformatSCFGFile(inPath); - } - - Moses2::createProbingPT(inPath, outPath, num_scores, num_lex_scores, log_prob, max_cache_size, scfg); - - //util::PrintUsage(std::cout); - return 0; -} - -std::string ReformatSCFGFile(const std::string &path) -{ - Moses2::InputFileStream inFile(path); - string reformattedPath = path + ".reformat.gz"; - Moses2::OutputFileStream outFile(reformattedPath); - - string line; - while (getline(inFile, line)) { - vector toks = Moses2::TokenizeMultiCharSeparator(line, "|||"); - assert(toks.size() >= 3); - - // source - vector sourceToks = Moses2::Tokenize(toks[0], " "); - for (size_t i = 0; i < sourceToks.size() - 1; ++i) { - outFile << sourceToks[i] << " "; - } - - // other columns - for (size_t i = 1; i < toks.size(); ++i) { - outFile << "|||" << toks[i]; - } - outFile << endl; - } - - inFile.Close(); - outFile.Close(); - - string sortedPath = path + ".reformat.sorted.gz"; - string tmpPath = path + ".tmp "; - string cmd = "mkdir " + tmpPath - + " && gzip -dc " + reformattedPath + " | LC_ALL=C sort -T " + tmpPath + " | gzip -c > " + sortedPath; - system(cmd.c_str()); - - cmd = "rm -rf " + tmpPath + " " + reformattedPath; - system(cmd.c_str()); - - return sortedPath; -} - diff --git a/contrib/moses2/Jamfile b/contrib/moses2/Jamfile index 193ac8db5..8791e3cf9 100644 --- a/contrib/moses2/Jamfile +++ b/contrib/moses2/Jamfile @@ -173,11 +173,10 @@ alias deps : ../..//z ../..//boost_iostreams ../..//boost_filesystem ../../mose deps ; exe moses2 : Main.cpp moses2_lib ; -exe CreateProbingPT2 : CreateProbingPT2.cpp moses2_lib ; if [ xmlrpc ] { echo "Building Moses2" ; - alias programs : moses2 CreateProbingPT2 ; + alias programs : moses2 ; } else { echo "Not building Moses2" ; -- cgit v1.2.3