public void TestDeasciify()
{
var fsm = new FsmMorphologicalAnalyzer();
var nGram = new NGram <string>("../../../ngram.txt");
nGram.CalculateNGramProbabilities(new NoSmoothing <string>());
var nGramDeasciifier = new NGramDeasciifier(fsm, nGram, true);
var simpleAsciifier = new SimpleAsciifier();
var corpus = new Corpus.Corpus("../../../corpus.txt");
for (var i = 0; i < corpus.SentenceCount(); i++)
{
var sentence = corpus.GetSentence(i);
for (var j = 1; j < sentence.WordCount(); j++)
{
if (fsm.MorphologicalAnalysis(sentence.GetWord(j).GetName()).Size() > 0)
{
var asciified = simpleAsciifier.Asciify(sentence.GetWord(j));
if (!asciified.Equals(sentence.GetWord(j).GetName()))
{
var deasciified = nGramDeasciifier.Deasciify(
new Sentence(sentence.GetWord(j - 1).GetName() + " " + sentence.GetWord(j).GetName()));
Assert.AreEqual(sentence.GetWord(j).GetName(), deasciified.GetWord(1).GetName());
}
}
}
}
}
/**
* <summary>Updates sentencePosition, sentenceIndex (if needed) and returns the current sentence processed. If one sentence
* is finished, the position shows the beginning of the next sentence and sentenceIndex is incremented. If the
* current sentence is the last sentence, the system shuffles the sentences and returns the first sentence.</summary>
* <param name="currentSentence">Current sentence processed.</param>
* <returns>If current sentence is not changed, currentSentence; if changed the next sentence; if next sentence is
* the last sentence; shuffles the corpus and returns the first sentence.</returns>
*/
public Sentence SentenceUpdate(Sentence currentSentence)
{
_sentencePosition++;
if (_sentencePosition >= currentSentence.WordCount())
{
_wordCount += currentSentence.WordCount();
_sentenceIndex++;
_sentencePosition = 0;
if (_sentenceIndex == corpus.SentenceCount())
{
_iterationCount++;
_wordCount = 0;
_lastWordCount = 0;
_sentenceIndex = 0;
corpus.ShuffleSentences(1);
}
return(corpus.GetSentence(_sentenceIndex));
}
return(currentSentence);
}