public virtual void TestElision_() { string test = "Plop, juste pour voir l'embrouille avec O'brian. M'enfin."; Tokenizer tokenizer = new StandardTokenizer(TEST_VERSION_CURRENT, new StringReader(test)); CharArraySet articles = new CharArraySet(TEST_VERSION_CURRENT, AsSet("l", "M"), false); TokenFilter filter = new ElisionFilter(tokenizer, articles); IList <string> tas = Filter(filter); assertEquals("embrouille", tas[4]); assertEquals("O'brian", tas[6]); assertEquals("enfin", tas[7]); }
/// <summary> /// Creates a /// <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/> /// which tokenizes all the text in the provided <seealso cref="Reader"/>. /// </summary> /// <returns> A /// <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/> /// built from an <seealso cref="StandardTokenizer"/> filtered with /// <seealso cref="StandardFilter"/>, <seealso cref="IrishLowerCaseFilter"/>, <seealso cref="StopFilter"/> /// , <seealso cref="SetKeywordMarkerFilter"/> if a stem exclusion set is /// provided and <seealso cref="SnowballFilter"/>. </returns> public override TokenStreamComponents CreateComponents(string fieldName, TextReader reader) { Tokenizer source = new StandardTokenizer(matchVersion, reader); TokenStream result = new StandardFilter(matchVersion, source); StopFilter s = new StopFilter(matchVersion, result, HYPHENATIONS); #pragma warning disable 612, 618 if (!matchVersion.OnOrAfter(LuceneVersion.LUCENE_44)) #pragma warning restore 612, 618 { s.EnablePositionIncrements = false; } result = s; result = new ElisionFilter(result, DEFAULT_ARTICLES); result = new IrishLowerCaseFilter(result); result = new StopFilter(matchVersion, result, stopwords); if (stemExclusionSet.Count > 0) { result = new SetKeywordMarkerFilter(result, stemExclusionSet); } result = new SnowballFilter(result, new IrishStemmer()); return new TokenStreamComponents(source, result); }
/// <summary> /// Creates a /// <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/> /// which tokenizes all the text in the provided <seealso cref="Reader"/>. /// </summary> /// <returns> A /// <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/> /// built from an <seealso cref="StandardTokenizer"/> filtered with /// <seealso cref="StandardFilter"/>, <seealso cref="ElisionFilter"/>, <seealso cref="LowerCaseFilter"/>, <seealso cref="StopFilter"/> /// , <seealso cref="SetKeywordMarkerFilter"/> if a stem exclusion set is /// provided and <seealso cref="ItalianLightStemFilter"/>. </returns> public override TokenStreamComponents CreateComponents(string fieldName, TextReader reader) { Tokenizer source = new StandardTokenizer(matchVersion, reader); TokenStream result = new StandardFilter(matchVersion, source); #pragma warning disable 612, 618 if (matchVersion.OnOrAfter(LuceneVersion.LUCENE_32)) #pragma warning restore 612, 618 { result = new ElisionFilter(result, DEFAULT_ARTICLES); } result = new LowerCaseFilter(matchVersion, result); result = new StopFilter(matchVersion, result, stopwords); if (stemExclusionSet.Count > 0) { result = new SetKeywordMarkerFilter(result, stemExclusionSet); } #pragma warning disable 612, 618 if (matchVersion.OnOrAfter(LuceneVersion.LUCENE_36)) #pragma warning restore 612, 618 { result = new ItalianLightStemFilter(result); } else { result = new SnowballFilter(result, new ItalianStemmer()); } return new TokenStreamComponents(source, result); }