public void Setup()
{
var fsm = new FsmMorphologicalAnalyzer();
parse1 = fsm.MorphologicalAnalysis("açılır").GetFsmParse(0);
parse2 = fsm.MorphologicalAnalysis("koparılarak").GetFsmParse(0);
parse3 = fsm.MorphologicalAnalysis("toplama").GetFsmParse(0);
parse4 = fsm.MorphologicalAnalysis("değerlendirmede").GetFsmParse(0);
parse5 = fsm.MorphologicalAnalysis("soruşturmasının").GetFsmParse(0);
parse6 = fsm.MorphologicalAnalysis("karşılaştırmalı").GetFsmParse(0);
parse7 = fsm.MorphologicalAnalysis("esaslarını").GetFsmParse(0);
parse8 = fsm.MorphologicalAnalysis("güçleriyle").GetFsmParse(0);
parse9 = fsm.MorphologicalAnalysis("bulmayacakları").GetFsmParse(0);
parse10 = fsm.MorphologicalAnalysis("mü").GetFsmParse(0);
}
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>The candidateList method takes a {@link Word} as an input and creates new candidates {@link List}. First it
* adds given word to this {@link List} and calls generateCandidateList method with candidates, given word and
* index 0. Then, loops i times where i ranges from 0 to size of candidates {@link List} and calls morphologicalAnalysis
* method with ith item of candidates {@link List}. If it does not return any analysis for given item, it removes
* the item from candidates {@link List}.</summary>
*
* <param name="word">{@link Word} type input.</param>
* <returns>List candidates.</returns>
*/
public List <string> CandidateList(Word word)
{
var candidates = new List <string> {
word.GetName()
};
GenerateCandidateList(candidates, word.GetName(), 0);
for (var i = 0; i < candidates.Count; i++)
{
var fsmParseList = fsm.MorphologicalAnalysis(candidates[i]);
if (fsmParseList.Size() == 0)
{
candidates.RemoveAt(i);
i--;
}
}
return(candidates);
}
/**
* <summary>The candidateList method takes a {@link Word} as an input and creates a candidates {@link List} by calling generateCandidateList
* method with given word. Then, it loop i times where i ranges from 0 to size of candidates {@link List} and creates a
* {@link FsmParseList} by calling morphologicalAnalysis with each item of candidates {@link List}. If the size of
* {@link FsmParseList} is 0, it then removes the ith item.</summary>
*
* <param name="word">Word input.</param>
* <returns>candidates {@link List}.</returns>
*/
protected List <string> CandidateList(Word word)
{
var candidates = generateCandidateList(word.GetName());
for (var i = 0; i < candidates.Count; i++)
{
var fsmParseList = fsm.MorphologicalAnalysis(candidates[i]);
if (fsmParseList.Size() == 0)
{
var newCandidate = fsm.GetDictionary().GetCorrectForm(candidates[i]);
if (newCandidate != null && fsm.MorphologicalAnalysis(newCandidate).Size() > 0)
{
candidates[i] = newCandidate;
}
else
{
candidates.RemoveAt(i);
i--;
}
}
}
return(candidates);
}
public void morphologicalAnalysisDataTimeNumber()
{
Assert.True(fsm.MorphologicalAnalysis("3/4").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("3\\/4").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("4/2/1973").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("14/2/1993").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("14/12/1933").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("6/12/1903").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("%34.5").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("%3").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("%56").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("2:3").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("12:3").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("4:23").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("11:56").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("1:2:3").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("3:12:3").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("5:4:23").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("7:11:56").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("12:2:3").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("10:12:3").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("11:4:23").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("22:11:56").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("45").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("34.23").Size() != 0);
}
public void TestNumberWithAccusative()
{
Assert.True(fsm.MorphologicalAnalysis("2'yi").Size() != 0);
Assert.AreEqual(0, fsm.MorphologicalAnalysis("2'i").Size());
Assert.True(fsm.MorphologicalAnalysis("5'i").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("9'u").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("10'u").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("30'u").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("3'ü").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("4'ü").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("100'ü").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("6'yı").Size() != 0);
Assert.AreEqual(0, fsm.MorphologicalAnalysis("6'ı").Size());
Assert.True(fsm.MorphologicalAnalysis("40'ı").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("60'ı").Size() != 0);
Assert.True(fsm.MorphologicalAnalysis("90'ı").Size() != 0);
}
