/// <summary>
/// Creates a new HunspellStemFilter that will stem tokens from the given TokenStream using
/// affix rules in the provided HunspellDictionary.
/// </summary>
/// <param name="input">TokenStream whose tokens will be stemmed.</param>
/// <param name="dictionary">HunspellDictionary containing the affix rules and words that will be used to stem the tokens.</param>
/// <param name="dedup">true if only unique terms should be output.</param>
public HunspellStemFilter(TokenStream input, HunspellDictionary dictionary, Boolean dedup = true)
: base(input) {
_posIncAtt = (PositionIncrementAttribute)AddAttribute(typeof(PositionIncrementAttribute));
_termAtt = (TermAttribute)AddAttribute(typeof(TermAttribute));
_dedup = dedup;
_stemmer = new HunspellStemmer(dictionary);
}
/// <summary>
/// Creates a new HunspellStemFilter that will stem tokens from the given TokenStream using
/// affix rules in the provided HunspellDictionary.
/// </summary>
/// <param name="input">TokenStream whose tokens will be stemmed.</param>
/// <param name="dictionary">HunspellDictionary containing the affix rules and words that will be used to stem the tokens.</param>
/// <param name="dedup">true if only unique terms should be output.</param>
public HunspellStemFilter(TokenStream input, HunspellDictionary dictionary, Boolean dedup = true)
: base(input)
{
_posIncAtt = (PositionIncrementAttribute)AddAttribute(typeof(PositionIncrementAttribute));
_termAtt = (TermAttribute)AddAttribute(typeof(TermAttribute));
_dedup = dedup;
_stemmer = new HunspellStemmer(dictionary);
}
public void TestStem_RecursiveSuffix_EnUS() {
var dictionary = HunspellDictionaryLoader.Dictionary("en_US");
var stemmer = new HunspellStemmer(dictionary);
var stems = stemmer.Stem("drinkables").ToList();
Assert.AreEqual(1, stems.Count);
Assert.AreEqual("drink", stems[0].Stem);
}
public void TestStem_SimplePrefix_EnUS() {
var dictionary = HunspellDictionaryLoader.Dictionary("en_US");
var stemmer = new HunspellStemmer(dictionary);
var stems = stemmer.Stem("remove").ToList();
Assert.AreEqual(1, stems.Count);
Assert.AreEqual("move", stems[0].Stem);
}
/// <summary>
/// Creates a new HunspellStemFilter that will stem tokens from the given TokenStream using
/// affix rules in the provided HunspellDictionary.
/// </summary>
/// <param name="input">TokenStream whose tokens will be stemmed.</param>
/// <param name="dictionary">HunspellDictionary containing the affix rules and words that will be used to stem the tokens.</param>
/// <param name="dedup">true if only unique terms should be output.</param>
public HunspellStemFilter(TokenStream input, HunspellDictionary dictionary, Boolean dedup = true)
: base(input)
{
_posIncAtt = AddAttribute <IPositionIncrementAttribute>();
_termAtt = AddAttribute <ITermAttribute>();
_dedup = dedup;
_stemmer = new HunspellStemmer(dictionary);
_slovakStemmer = new SlovakStemmer();
}
public void TestStem_fietsenFiets_NlNL() {
var dictionary = HunspellDictionaryLoader.Dictionary("nl_NL");
var stemmer = new HunspellStemmer(dictionary);
var stems = stemmer.Stem("fietsen").ToList();
Assert.AreEqual(2, stems.Count);
Assert.AreEqual("fietsen", stems[0].Stem);
Assert.AreEqual("fiets", stems[1].Stem);
stems = stemmer.Stem("fiets").ToList();
Assert.AreEqual(1, stems.Count);
Assert.AreEqual("fiets", stems[0].Stem);
}
