private void GetPossibleWords(Word word, string restOfWord, IList <Word> words, bool checkTransition)
{
if (restOfWord.Length == 0)
{
var newPossibleWord = Word.CopyOf(word);
words.Add(newPossibleWord);
return;
}
IList <KeyValuePair <string, Suffix> > possibleFirstSuffixes = GetPossibleFirstSuffixes(restOfWord);
if (possibleFirstSuffixes.Count == 0)
{
return;
}
foreach (var pair in possibleFirstSuffixes)
{
//Burada değişiklik yaptık, şimdilik sorun yok
if (!_lang.Morphotactics.HasTransition(word.Last.Morpheme.Id, pair.Value.Id) && checkTransition)
{
continue;
}
word.AddSuffix(pair.Value);
GetPossibleWords(word, restOfWord.Remove(0, pair.Key.Length), words, checkTransition);
word.RemoveLastSuffix();
}
}
/// <summary>
/// Creates and returns a word with the specified "morpheme id" sequence
/// </summary>
public Word Generate(params string[] morphemes)
{
StringExtensions.ThrowIfNullAny(morphemes);
var index = StringExtensions.ContainsWhitespaceAny(morphemes);
//var index = StringExtensions.ContainsWhitespaceAny(morphemes);
//if (index >= 0)
//{
// throw new ArgumentException($"Morpheme identifier can not contain whitespace: \"{morphemes[index]}\"");
//}
var root = GetRoot(morphemes[0]);
if (root == null)
{
return(null);
}
var word = new Word(root);
for (var i = 1; i < morphemes.Length; i++)
{
var suffix = GetSuffix(morphemes[i]);
if (suffix == null)
{
return(null);
}
word.AddSuffix(suffix);
}
return(word);
}
public bool TestStrictGeneration(string rootWord, string suffixId)
{
var root = Tr.GetRootsHavingSurface(rootWord).First();
var word = new Word(root);
var suffix = Tr.GetSuffix(suffixId);
return word.AddSuffix(suffix, Tr);
}
public bool TestStrictGeneration(string rootWord, string suffixId)
{
var root = Tr.GetRootsHavingSurface(rootWord).First();
var word = new Word(root);
var suffix = Tr.GetSuffix(suffixId);
return(word.AddSuffix(suffix, Tr));
}
public void TestStrictGeneration2()
{
var root = Tr.GetRootsHavingSurface("gel").First();
var word = new Word(root);
var copy = Word.CopyOf(word);
word.AddSuffix(Tr.GetSuffix("IC_COGUL_lAr"), Tr);
Assert.True(copy.Equals(word));
Assert.True(word.Equals(copy));
}
public void TestStrictGeneration2()
{
var root = Tr.GetRootsHavingSurface("gel").First();
var word = new Word(root);
var copy = Word.CopyOf(word);
word.AddSuffix(Tr.GetSuffix("IC_COGUL_lAr"), Tr);
Assert.True(copy.Equals(word));
Assert.True(word.Equals(copy));
}
private void GetPossibleWords(Word word, string restOfWord, IList <Word> words)
{
var suffixes = FindPossibleSuffixes(word.Last.Morpheme, restOfWord);
foreach (var suffix in suffixes)
{
word.AddSuffix(suffix.Morpheme);
GetPossibleWords(word, restOfWord.Remove(0, suffix.Surface.Length), words);
word.RemoveLastSuffix();
}
if (restOfWord.Length == 0 && _lang.Morphotactics.IsTerminal(word.Last.Morpheme))
{
var newPossibleWord = Word.CopyOf(word);
words.Add(newPossibleWord);
}
}
public string LerimdekilerdenTest(string rootWord)
{
Root root = tr.GetRootsHavingSurface(rootWord).First();
word = new Word(root);
word.AddSuffix(tr.GetSuffix("IC_COGUL_lAr"));
word.AddSuffix(tr.GetSuffix("IC_SAHIPLIK_BEN_(U)m"));
word.AddSuffix(tr.GetSuffix("IC_HAL_BULUNMA_DA"));
word.AddSuffix(tr.GetSuffix("IC_AITLIK_ki"));
word.AddSuffix(tr.GetSuffix("IC_COGUL_lAr"));
word.AddSuffix(tr.GetSuffix("IC_HAL_AYRILMA_DAn"));
return word.GetSurface();
}
public string TestGeneration(string rootWord)
{
var root = Tr.GetRootsHavingSurface(rootWord).First();
var word = new Word(root);
word.AddSuffix(Tr.GetSuffix("IC_COGUL_lAr"));
word.AddSuffix(Tr.GetSuffix("IC_SAHIPLIK_BEN_(U)m"));
word.AddSuffix(Tr.GetSuffix("IC_HAL_BULUNMA_DA"));
word.AddSuffix(Tr.GetSuffix("IC_AITLIK_ki"));
word.AddSuffix(Tr.GetSuffix("IC_COGUL_lAr"));
word.AddSuffix(Tr.GetSuffix("IC_HAL_AYRILMA_DAn"));
return word.GetSurface();
}
public string TestGeneration(string rootWord)
{
var root = Tr.GetRootsHavingSurface(rootWord).First();
var word = new Word(root);
word.AddSuffix(Tr.GetSuffix("IC_COGUL_lAr"));
word.AddSuffix(Tr.GetSuffix("IC_SAHIPLIK_BEN_(U)m"));
word.AddSuffix(Tr.GetSuffix("IC_HAL_BULUNMA_DA"));
word.AddSuffix(Tr.GetSuffix("IC_AITLIK_ki"));
word.AddSuffix(Tr.GetSuffix("IC_COGUL_lAr"));
word.AddSuffix(Tr.GetSuffix("IC_HAL_AYRILMA_DAn"));
return(word.GetSurface());
}
public void TestCopyOf()
{
var root = Tr.GetRootsHavingSurface("kitap").First();
var word = new Word(root);
word.AddSuffix(Tr.GetSuffix("IC_COGUL_lAr"));
word.AddSuffix(Tr.GetSuffix("IC_SAHIPLIK_BEN_(U)m"));
word.AddSuffix(Tr.GetSuffix("IC_HAL_BULUNMA_DA"));
word.AddSuffix(Tr.GetSuffix("IC_AITLIK_ki"));
word.AddSuffix(Tr.GetSuffix("IC_COGUL_lAr"));
word.AddSuffix(Tr.GetSuffix("IC_HAL_AYRILMA_DAn"));
var copy = Word.CopyOf(word);
Assert.True(word.Equals(word));
Assert.False(word.Equals(null));
Assert.AreNotSame(word, copy);
Assert.AreEqual(word.GetSurface(), copy.GetSurface());
Assert.True(word.Equals(copy));
}
public void TestCopyOf()
{
var root = Tr.GetRootsHavingSurface("kitap").First();
var word = new Word(root);
word.AddSuffix(Tr.GetSuffix("IC_COGUL_lAr"));
word.AddSuffix(Tr.GetSuffix("IC_SAHIPLIK_BEN_(U)m"));
word.AddSuffix(Tr.GetSuffix("IC_HAL_BULUNMA_DA"));
word.AddSuffix(Tr.GetSuffix("IC_AITLIK_ki"));
word.AddSuffix(Tr.GetSuffix("IC_COGUL_lAr"));
word.AddSuffix(Tr.GetSuffix("IC_HAL_AYRILMA_DAn"));
var copy = Word.CopyOf(word);
Assert.True(word.Equals(word));
Assert.False(word.Equals(null));
Assert.AreNotSame(word, copy);
Assert.AreEqual(word.GetSurface(), copy.GetSurface());
Assert.True(word.Equals(copy));
}
private void GetPossibleWords(Word word, string restOfWord, IList<Word> words, bool checkTransition)
{
if (restOfWord.Length == 0)
{
var newPossibleWord = new Word(word);
words.Add(newPossibleWord);
return;
}
IList<KeyValuePair<string, Suffix>> possibleFirstSuffixes = GetPossibleFirstSuffixes(restOfWord);
if (possibleFirstSuffixes.Count == 0)
{
return;
}
foreach (var pair in possibleFirstSuffixes)
{
//Burada değişiklik yaptık, şimdilik sorun yok
if (!_lang.Morphotactics.HasTransition(word.Last.Morpheme.Id, pair.Value.Id) && checkTransition)
{
continue;
}
word.AddSuffix(pair.Value);
GetPossibleWords(word, restOfWord.Remove(0, pair.Key.Length), words, checkTransition);
word.RemoveLastSuffix();
}
}
private static void Main()
{
//var lines = File.ReadAllLines(@"C:\Users\harun_000\Desktop\workspace\corpus\unigrams.txt",
// Encoding.UTF8);
//List<string> resolved = new List<string>();
//List<string> unresolved = new List<string>();
//foreach (var line in lines)
//{
// var token = line.Split(null)[0];
// var solutions = Analyzer.Analyze(token);
// if (solutions.Count == 0)
// {
// unresolved.Add(line);
// }
// else
// {
// resolved.Add(line);
// }
//}
//File.WriteAllLines(@"C:\Users\harun_000\Desktop\workspace\nuve_resolved", resolved, Encoding.UTF8);
//File.WriteAllLines(@"C:\Users\harun_000\Desktop\workspace\nuve_unresolved", unresolved, Encoding.UTF8);
//var nuve_resolved = File.ReadAllLines(@"C:\Users\harun_000\Desktop\workspace\nuve_resolved", Encoding.UTF8);
//var zemberek_resolved = File.ReadAllLines(@"C:\Users\harun_000\Desktop\workspace\zemberek_resolved",
// Encoding.UTF8);
//var onlyZemberek = zemberek_resolved.Except(nuve_resolved);
//var onlyNuve = nuve_resolved.Except(zemberek_resolved);
//File.WriteAllLines(@"C:\Users\harun_000\Desktop\workspace\onlyZemberek", onlyZemberek, Encoding.UTF8);
//File.WriteAllLines(@"C:\Users\harun_000\Desktop\workspace\onlyNuve", onlyNuve, Encoding.UTF8);
//File.WriteAllText(@"C:\Users\harun_000\Desktop\vboxshare\tokenized-paragraphs-with-punctuation.txt", Split(text), Encoding.UTF8);
//File.WriteAllLines(@"C:\Users\harun_000\Desktop\vboxshare\sentences-no-punctuation-remove-empty-lines.txt", paragraphs.Select(p => Regex.Replace(p, "[^\\p{L}\\p{Nd}' ]", "")), Encoding.UTF8);
//Benchmarker.TestWithAMillionWords(Analyzer);
//Benchmarker.TestWithAMillionTokens(Analyzer);
//Language tr = Language.Turkish;
////Analysis
//var analyzer = new WordAnalyzer(tr);
////Morphologic Analysis and stemming
//IList<Word> solutions = analyzer.Analyze("deneme");
//foreach (var solution in solutions)
//{
// Console.WriteLine("\t{0}", solution);
// Console.WriteLine("\toriginal:{0} stem:{1}\n",
// solution.GetSurface(),
// solution.GetStem().GetSurface()); //Stemming
//}
var tr = Language.Turkish;
var root = tr.GetRootsHavingSurface("gel").First();
Word word = new Word(root);
if(!word.AddSuffix(tr.GetSuffix("IC_COGUL_lAr"), tr))
{
Console.WriteLine("Adding the suffix IC_COGUL_lAr after a verb is not valid!");
Console.WriteLine(word.GetSurface()); //prints just gel "gel"
}
Console.WriteLine(root);
Console.WriteLine(word);
Console.WriteLine(word.GetSurface());
Test();
}
private static void Main()
{
//var lines = File.ReadAllLines(@"C:\Users\harun_000\Desktop\workspace\corpus\unigrams.txt",
// Encoding.UTF8);
//List<string> resolved = new List<string>();
//List<string> unresolved = new List<string>();
//foreach (var line in lines)
//{
// var token = line.Split(null)[0];
// var solutions = Analyzer.Analyze(token);
// if (solutions.Count == 0)
// {
// unresolved.Add(line);
// }
// else
// {
// resolved.Add(line);
// }
//}
//File.WriteAllLines(@"C:\Users\harun_000\Desktop\workspace\nuve_resolved", resolved, Encoding.UTF8);
//File.WriteAllLines(@"C:\Users\harun_000\Desktop\workspace\nuve_unresolved", unresolved, Encoding.UTF8);
//var nuve_resolved = File.ReadAllLines(@"C:\Users\harun_000\Desktop\workspace\nuve_resolved", Encoding.UTF8);
//var zemberek_resolved = File.ReadAllLines(@"C:\Users\harun_000\Desktop\workspace\zemberek_resolved",
// Encoding.UTF8);
//var onlyZemberek = zemberek_resolved.Except(nuve_resolved);
//var onlyNuve = nuve_resolved.Except(zemberek_resolved);
//File.WriteAllLines(@"C:\Users\harun_000\Desktop\workspace\onlyZemberek", onlyZemberek, Encoding.UTF8);
//File.WriteAllLines(@"C:\Users\harun_000\Desktop\workspace\onlyNuve", onlyNuve, Encoding.UTF8);
//File.WriteAllText(@"C:\Users\harun_000\Desktop\vboxshare\tokenized-paragraphs-with-punctuation.txt", Split(text), Encoding.UTF8);
//File.WriteAllLines(@"C:\Users\harun_000\Desktop\vboxshare\sentences-no-punctuation-remove-empty-lines.txt", paragraphs.Select(p => Regex.Replace(p, "[^\\p{L}\\p{Nd}' ]", "")), Encoding.UTF8);
//Benchmarker.TestWithAMillionWords(Analyzer);
//Benchmarker.TestWithAMillionTokens(Analyzer);
//Language tr = Language.Turkish;
////Analysis
//var analyzer = new WordAnalyzer(tr);
////Morphologic Analysis and stemming
//IList<Word> solutions = analyzer.Analyze("deneme");
//foreach (var solution in solutions)
//{
// Console.WriteLine("\t{0}", solution);
// Console.WriteLine("\toriginal:{0} stem:{1}\n",
// solution.GetSurface(),
// solution.GetStem().GetSurface()); //Stemming
//}
var tr = Language.Turkish;
var root = tr.GetRootsHavingSurface("gel").First();
Word word = new Word(root);
if (!word.AddSuffix(tr.GetSuffix("IC_COGUL_lAr"), tr))
{
Console.WriteLine("Adding the suffix IC_COGUL_lAr after a verb is not valid!");
Console.WriteLine(word.GetSurface()); //prints just gel "gel"
}
Console.WriteLine(root);
Console.WriteLine(word);
Console.WriteLine(word.GetSurface());
Test();
}
