public void TestDeasciify()
{
var fsm = new FsmMorphologicalAnalyzer();
var simpleDeasciifier = new SimpleDeasciifier(fsm);
var simpleAsciifier = new SimpleAsciifier();
for (var i = 0; i < fsm.GetDictionary().Size(); i++)
{
var word = (TxtWord)fsm.GetDictionary().GetWord(i);
var count = 0;
for (var j = 0; j < word.GetName().Length; j++)
{
switch (word.GetName()[j])
{
case 'ç':
case 'ö':
case 'ğ':
case 'ü':
case 'ş':
case 'ı':
count++;
break;
}
}
if (count > 0 && !word.GetName().EndsWith("fulü") && (word.IsNominal() || word.IsAdjective() || word.IsAdverb() || word.IsVerb()))
{
var asciified = simpleAsciifier.Asciify(word);
if (simpleDeasciifier.CandidateList(new Word(asciified)).Count == 1)
{
var deasciified = simpleDeasciifier.Deasciify(new Sentence(asciified)).ToString();
Assert.AreEqual(word.GetName(), deasciified);
}
}
}
}
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());
}
}
}
}
}
public void Setup()
{
simpleAsciifier = new SimpleAsciifier();
}
