bool HyperTreeLoader::Load(AllOptions const& opts,
                           const std::vector<FactorType> &input,
                           const std::vector<FactorType> &output,
                           const std::string &inFile,
                           const RuleTableFF &ff,
                           HyperTree &trie,
                           boost::unordered_set<std::size_t> &sourceTermSet)
{
  PrintUserTime(std::string("Start loading HyperTree"));

  sourceTermSet.clear();

  std::size_t count = 0;

  std::ostream *progress = NULL;
  IFVERBOSE(1) progress = &std::cerr;
  util::FilePiece in(inFile.c_str(), progress);

  // reused variables
  std::vector<float> scoreVector;
  StringPiece line;

  double_conversion::StringToDoubleConverter converter(double_conversion::StringToDoubleConverter::NO_FLAGS, NAN, NAN, "inf", "nan");

  HyperPathLoader hyperPathLoader;

  Phrase dummySourcePhrase;
  {
    Word *lhs = NULL;
    dummySourcePhrase.CreateFromString(Input, input, "hello", &lhs);
    delete lhs;
  }

  while(true) {
    try {
      line = in.ReadLine();
    } catch (const util::EndOfFileException &e) {
      break;
    }

    util::TokenIter<util::MultiCharacter> pipes(line, "|||");
    StringPiece sourceString(*pipes);
    StringPiece targetString(*++pipes);
    StringPiece scoreString(*++pipes);

    StringPiece alignString;
    if (++pipes) {
      StringPiece temp(*pipes);
      alignString = temp;
    }

    ++pipes;  // counts

    scoreVector.clear();
    for (util::TokenIter<util::AnyCharacter, true> s(scoreString, " \t"); s; ++s) {
      int processed;
      float score = converter.StringToFloat(s->data(), s->length(), &processed);
      UTIL_THROW_IF2(std::isnan(score), "Bad score " << *s << " on line " << count);
      scoreVector.push_back(FloorScore(TransformScore(score)));
    }
    const std::size_t numScoreComponents = ff.GetNumScoreComponents();
    if (scoreVector.size() != numScoreComponents) {
      UTIL_THROW2("Size of scoreVector != number (" << scoreVector.size() << "!="
                  << numScoreComponents << ") of score components on line " << count);
    }

    // Source-side
    HyperPath sourceFragment;
    hyperPathLoader.Load(sourceString, sourceFragment);
    ExtractSourceTerminalSetFromHyperPath(sourceFragment, sourceTermSet);

    // Target-side
    TargetPhrase *targetPhrase = new TargetPhrase(&ff);
    Word *targetLHS = NULL;
    targetPhrase->CreateFromString(Output, output, targetString, &targetLHS);
    targetPhrase->SetTargetLHS(targetLHS);
    targetPhrase->SetAlignmentInfo(alignString);

    if (++pipes) {
      StringPiece sparseString(*pipes);
      targetPhrase->SetSparseScore(&ff, sparseString);
    }

    if (++pipes) {
      StringPiece propertiesString(*pipes);
      targetPhrase->SetProperties(propertiesString);
    }

    targetPhrase->GetScoreBreakdown().Assign(&ff, scoreVector);
    targetPhrase->EvaluateInIsolation(dummySourcePhrase,
                                      ff.GetFeaturesToApply());

    // Add rule to trie.
    TargetPhraseCollection::shared_ptr phraseColl
    = GetOrCreateTargetPhraseCollection(trie, sourceFragment);
    phraseColl->Add(targetPhrase);

    count++;
  }

  // sort and prune each target phrase collection
  if (ff.GetTableLimit()) {
    SortAndPrune(trie, ff.GetTableLimit());
  }

  return true;
}
void PhraseDictionaryFuzzyMatch::InitializeForInput(ttasksptr const& ttask)
{
  InputType const& inputSentence = *ttask->GetSource();
#if defined __MINGW32__
  char dirName[] = "moses.XXXXXX";
#else
  char dirName[] = "/tmp/moses.XXXXXX";
#endif // defined
  char *temp = mkdtemp(dirName);
  UTIL_THROW_IF2(temp == NULL,
                 "Couldn't create temporary directory " << dirName);

  string dirNameStr(dirName);

  string inFileName(dirNameStr + "/in");

  ofstream inFile(inFileName.c_str());

  for (size_t i = 1; i < inputSentence.GetSize() - 1; ++i) {
    inFile << inputSentence.GetWord(i);
  }
  inFile << endl;
  inFile.close();

  long translationId = inputSentence.GetTranslationId();
  string ptFileName = m_FuzzyMatchWrapper->Extract(translationId, dirNameStr);

  // populate with rules for this sentence
  PhraseDictionaryNodeMemory &rootNode = m_collection[translationId];
  FormatType format = MosesFormat;

  // data from file
  InputFileStream inStream(ptFileName);

  // copied from class LoaderStandard
  PrintUserTime("Start loading fuzzy-match phrase model");

  const StaticData &staticData = StaticData::Instance();


  string lineOrig;
  size_t count = 0;

  while(getline(inStream, lineOrig)) {
    const string *line;
    if (format == HieroFormat) { // reformat line
      UTIL_THROW(util::Exception, "Cannot be Hiero format");
      //line = ReformatHieroRule(lineOrig);
    } else {
      // do nothing to format of line
      line = &lineOrig;
    }

    vector<string> tokens;
    vector<float> scoreVector;

    TokenizeMultiCharSeparator(tokens, *line , "|||" );

    if (tokens.size() != 4 && tokens.size() != 5) {
      UTIL_THROW2("Syntax error at " << ptFileName << ":" << count);
    }

    const string &sourcePhraseString = tokens[0]
                                       , &targetPhraseString = tokens[1]
                                           , &scoreString        = tokens[2]
                                               , &alignString        = tokens[3];

    bool isLHSEmpty = (sourcePhraseString.find_first_not_of(" \t", 0) == string::npos);
    if (isLHSEmpty && !staticData.IsWordDeletionEnabled()) {
      TRACE_ERR( ptFileName << ":" << count << ": pt entry contains empty target, skipping\n");
      continue;
    }

    Tokenize<float>(scoreVector, scoreString);
    const size_t numScoreComponents = GetNumScoreComponents();
    if (scoreVector.size() != numScoreComponents) {
      UTIL_THROW2("Size of scoreVector != number (" << scoreVector.size() << "!="
                  << numScoreComponents << ") of score components on line " << count);
    }

    UTIL_THROW_IF2(scoreVector.size() != numScoreComponents,
                   "Number of scores incorrectly specified");

    // parse source & find pt node

    // constituent labels
    Word *sourceLHS;
    Word *targetLHS;

    // source
    Phrase sourcePhrase( 0);
    sourcePhrase.CreateFromString(Input, m_input, sourcePhraseString, &sourceLHS);

    // create target phrase obj
    TargetPhrase *targetPhrase = new TargetPhrase(this);
    targetPhrase->CreateFromString(Output, m_output, targetPhraseString, &targetLHS);

    // rest of target phrase
    targetPhrase->SetAlignmentInfo(alignString);
    targetPhrase->SetTargetLHS(targetLHS);
    //targetPhrase->SetDebugOutput(string("New Format pt ") + line);

    // component score, for n-best output
    std::transform(scoreVector.begin(),scoreVector.end(),scoreVector.begin(),TransformScore);
    std::transform(scoreVector.begin(),scoreVector.end(),scoreVector.begin(),FloorScore);

    targetPhrase->GetScoreBreakdown().Assign(this, scoreVector);
    targetPhrase->EvaluateInIsolation(sourcePhrase, GetFeaturesToApply());

    TargetPhraseCollection::shared_ptr phraseColl
    = GetOrCreateTargetPhraseCollection(rootNode, sourcePhrase,
                                        *targetPhrase, sourceLHS);
    phraseColl->Add(targetPhrase);

    count++;

    if (format == HieroFormat) { // reformat line
      delete line;
    } else {
      // do nothing
    }

  }

  // sort and prune each target phrase collection
  SortAndPrune(rootNode);

  //removedirectoryrecursively(dirName);
}