macaon_decode.cpp

/// @file macaon_decode.cpp
/// @author Franck Dary
/// @version 1.0
/// @date 2018-08-07

#include <cstdio>
#include <cstdlib>
#include <boost/program_options.hpp>
#include "BD.hpp"
#include "Config.hpp"
#include "TransitionMachine.hpp"
#include "Decoder.hpp"

namespace po = boost::program_options;

/// @brief Get the list of mandatory and optional program arguments.
///
/// @return The lists.
po::options_description getOptionsDescription()
{
  po::options_description desc("Command-Line Arguments ");

  po::options_description req("Required");
  req.add_options()
    ("expName", po::value<std::string>()->required(),
      "Name of this experiment")
    ("tm", po::value<std::string>()->required(),
      "File describing the Tape Machine to use")
    ("bd", po::value<std::string>()->required(),
      "BD file that describes the multi-tapes buffer")
    ("mcd", po::value<std::string>()->required(),
      "MCD file that describes the input")
    ("input,I", po::value<std::string>()->required(),
      "Input file formated according to the mcd");

  po::options_description opt("Optional");
  opt.add_options()
    ("help,h", "Produce this help message")
    ("debug,d", "Print infos on stderr")
    ("dicts", po::value<std::string>()->default_value(""),
      "The .dict file describing all the dictionaries to be used in the experiement. By default the filename specified in the .tm file will be used")
    ("featureModels", po::value<std::string>()->default_value(""),
      "For each classifier, specify what .fm (feature model) file to use. By default the filename specified in the .cla file will be used. Example : --featureModel Parser=parser.fm,Tagger=tagger.fm")

    ("printEntropy", "Print entropy for each sequence")
    ("sequenceDelimiterTape", po::value<std::string>()->default_value("EOS"),
      "The name of the buffer's tape that contains the delimiter token for a sequence")
    ("sequenceDelimiter", po::value<std::string>()->default_value("1"),
      "The value of the token that act as a delimiter for sequences")
    ("tapeSize", po::value<int>()->default_value(100000),
      "Number of lines in the input file.")
    ("showFeatureRepresentation", po::value<int>()->default_value(0),
      "For each state of the Config, show its feature representation")
    ("interactive", po::value<bool>()->default_value(true),
      "Is the shell interactive ? Display advancement informations")
    ("lang", po::value<std::string>()->default_value("fr"),
      "Language you are working with");

  po::options_description analysis("Error analysis related options");
  analysis.add_options()
    ("errorAnalysis", "Print an analysis of errors")
    ("meanEntropy", "Print the mean entropy for error types")
    ("onlyPrefixes", "Only uses the prefixes of error categories")
    ("nbErrorsToShow", po::value<int>()->default_value(10),
      "Display only the X most common errors")
    ("classifier", po::value<std::string>()->default_value(""),
      "Name of the monitored classifier, if not specified monitor everyone");

  po::options_description beam("Beam search related options");
  beam.add_options()