To prevent terms from being stemmed use an instance of SetKeywordMarkerFilter or a custom TokenFilter that sets the KeywordAttribute before this TokenStream.
private void Check(string input, string expected) { ArabicLetterTokenizer tokenStream = new ArabicLetterTokenizer(TEST_VERSION_CURRENT, new StringReader(input)); ArabicStemFilter filter = new ArabicStemFilter(tokenStream); AssertTokenStreamContents(filter, new string[] { expected }); }
private void Check(string input, string expected) { #pragma warning disable 612, 618 ArabicLetterTokenizer tokenStream = new ArabicLetterTokenizer(TEST_VERSION_CURRENT, new StringReader(input)); #pragma warning restore 612, 618 ArabicStemFilter filter = new ArabicStemFilter(tokenStream); AssertTokenStreamContents(filter, new string[] { expected }); }
public virtual void TestWithKeywordAttribute() { CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true); set.add("ساهدهات"); ArabicLetterTokenizer tokenStream = new ArabicLetterTokenizer(TEST_VERSION_CURRENT, new StringReader("ساهدهات")); ArabicStemFilter filter = new ArabicStemFilter(new SetKeywordMarkerFilter(tokenStream, set)); AssertTokenStreamContents(filter, new string[] { "ساهدهات" }); }
public virtual void TestWithKeywordAttribute() { CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true); set.add("ساهدهات"); #pragma warning disable 612, 618 ArabicLetterTokenizer tokenStream = new ArabicLetterTokenizer(TEST_VERSION_CURRENT, new StringReader("ساهدهات")); #pragma warning restore 612, 618 ArabicStemFilter filter = new ArabicStemFilter(new SetKeywordMarkerFilter(tokenStream, set)); AssertTokenStreamContents(filter, new string[] { "ساهدهات" }); }