protected internal override TokenStreamComponents createComponents(string fieldName, Reader reader) { Tokenizer source = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false); TokenStream sink = new SetKeywordMarkerFilter(source, exclusionSet); return(new TokenStreamComponents(source, new SwedishLightStemFilter(sink))); }
/// <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="EnglishPossessiveFilter"/>, /// <seealso cref="LowerCaseFilter"/>, <seealso cref="StopFilter"/> /// , <seealso cref="SetKeywordMarkerFilter"/> if a stem exclusion set is /// provided and <seealso cref="PorterStemFilter"/>. </returns> protected internal override TokenStreamComponents createComponents(string fieldName, Reader reader) { //JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final': //ORIGINAL LINE: final org.apache.lucene.analysis.Tokenizer source = new org.apache.lucene.analysis.standard.StandardTokenizer(matchVersion, reader); Tokenizer source = new StandardTokenizer(matchVersion, reader); TokenStream result = new StandardFilter(matchVersion, source); // prior to this we get the classic behavior, standardfilter does it for us. if (matchVersion.onOrAfter(Version.LUCENE_31)) { result = new EnglishPossessiveFilter(matchVersion, result); } result = new LowerCaseFilter(matchVersion, result); result = new StopFilter(matchVersion, result, stopwords); if (!stemExclusionSet.Empty) { result = new SetKeywordMarkerFilter(result, stemExclusionSet); } result = new PorterStemFilter(result); return(new TokenStreamComponents(source, result)); }
public override TokenFilter create(TokenStream input) { SnowballProgram program; try { program = stemClass.newInstance(); } catch (Exception e) { throw new Exception("Error instantiating stemmer for language " + language + "from class " + stemClass, e); } if (protectedWords != null) { input = new SetKeywordMarkerFilter(input, protectedWords); } return new SnowballFilter(input, program); }
protected internal override TokenStreamComponents createComponents(string fieldName, Reader reader) { Tokenizer source = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false); TokenStream sink = new SetKeywordMarkerFilter(source, exclusionSet); return new TokenStreamComponents(source, new NorwegianLightStemFilter(sink)); }
/// <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="LowerCaseFilter"/>, <seealso cref="StopFilter"/> /// , <seealso cref="SetKeywordMarkerFilter"/> if a stem exclusion set is /// provided and <seealso cref="SnowballFilter"/>. </returns> protected internal override TokenStreamComponents createComponents(string fieldName, Reader reader) { //JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final': //ORIGINAL LINE: final org.apache.lucene.analysis.Tokenizer source = new org.apache.lucene.analysis.standard.StandardTokenizer(matchVersion, reader); Tokenizer source = new StandardTokenizer(matchVersion, reader); TokenStream result = new StandardFilter(matchVersion, source); result = new LowerCaseFilter(matchVersion, result); result = new StopFilter(matchVersion, result, stopwords); if (!stemExclusionSet.Empty) { result = new SetKeywordMarkerFilter(result, stemExclusionSet); } result = new SnowballFilter(result, new DanishStemmer()); return new TokenStreamComponents(source, result); }
/// <summary> /// Creates /// <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/> /// used to tokenize all the text in the provided <seealso cref="Reader"/>. /// </summary> /// <returns> <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/> /// built from an <seealso cref="StandardTokenizer"/> filtered with /// <seealso cref="LowerCaseFilter"/>, <seealso cref="StopFilter"/>, /// <seealso cref="ArabicNormalizationFilter"/>, <seealso cref="SetKeywordMarkerFilter"/> /// if a stem exclusion set is provided and <seealso cref="ArabicStemFilter"/>. </returns> protected internal override TokenStreamComponents createComponents(string fieldName, Reader reader) { //JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final': //ORIGINAL LINE: final org.apache.lucene.analysis.Tokenizer source = matchVersion.onOrAfter(org.apache.lucene.util.Version.LUCENE_31) ? new org.apache.lucene.analysis.standard.StandardTokenizer(matchVersion, reader) : new ArabicLetterTokenizer(matchVersion, reader); Tokenizer source = matchVersion.onOrAfter(Version.LUCENE_31) ? new StandardTokenizer(matchVersion, reader) : new ArabicLetterTokenizer(matchVersion, reader); TokenStream result = new LowerCaseFilter(matchVersion, source); // the order here is important: the stopword list is not normalized! result = new StopFilter(matchVersion, result, stopwords); // TODO maybe we should make ArabicNormalization filter also KeywordAttribute aware?! result = new ArabicNormalizationFilter(result); if (!stemExclusionSet.Empty) { result = new SetKeywordMarkerFilter(result, stemExclusionSet); } return new TokenStreamComponents(source, new ArabicStemFilter(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="EnglishPossessiveFilter"/>, /// <seealso cref="LowerCaseFilter"/>, <seealso cref="StopFilter"/> /// , <seealso cref="SetKeywordMarkerFilter"/> if a stem exclusion set is /// provided and <seealso cref="PorterStemFilter"/>. </returns> protected internal override TokenStreamComponents createComponents(string fieldName, Reader reader) { //JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final': //ORIGINAL LINE: final org.apache.lucene.analysis.Tokenizer source = new org.apache.lucene.analysis.standard.StandardTokenizer(matchVersion, reader); Tokenizer source = new StandardTokenizer(matchVersion, reader); TokenStream result = new StandardFilter(matchVersion, source); // prior to this we get the classic behavior, standardfilter does it for us. if (matchVersion.onOrAfter(Version.LUCENE_31)) { result = new EnglishPossessiveFilter(matchVersion, result); } result = new LowerCaseFilter(matchVersion, result); result = new StopFilter(matchVersion, result, stopwords); if (!stemExclusionSet.Empty) { result = new SetKeywordMarkerFilter(result, stemExclusionSet); } result = new PorterStemFilter(result); return new TokenStreamComponents(source, result); }
protected internal override Analyzer.TokenStreamComponents createComponents(string fieldName, Reader reader) { Tokenizer source = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false); TokenStream sink = new SetKeywordMarkerFilter(source, exclusionSet); return new Analyzer.TokenStreamComponents(source, new PortugueseMinimalStemFilter(sink)); }
/// <summary> /// Creates /// <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/> /// used to tokenize all the text in the provided <seealso cref="Reader"/>. /// </summary> /// <returns> <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/> /// built from a <seealso cref="StandardTokenizer"/> filtered with /// <seealso cref="StandardFilter"/>, <seealso cref="LowerCaseFilter"/>, <seealso cref="StopFilter"/> /// , <seealso cref="SetKeywordMarkerFilter"/> if a stem exclusion set is /// provided, <seealso cref="GermanNormalizationFilter"/> and <seealso cref="GermanLightStemFilter"/> </returns> protected internal override TokenStreamComponents createComponents(string fieldName, Reader reader) { //JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final': //ORIGINAL LINE: final org.apache.lucene.analysis.Tokenizer source = new org.apache.lucene.analysis.standard.StandardTokenizer(matchVersion, reader); Tokenizer source = new StandardTokenizer(matchVersion, reader); TokenStream result = new StandardFilter(matchVersion, source); result = new LowerCaseFilter(matchVersion, result); result = new StopFilter(matchVersion, result, stopwords); result = new SetKeywordMarkerFilter(result, exclusionSet); if (matchVersion.onOrAfter(Version.LUCENE_36)) { result = new GermanNormalizationFilter(result); result = new GermanLightStemFilter(result); } else if (matchVersion.onOrAfter(Version.LUCENE_31)) { result = new SnowballFilter(result, new German2Stemmer()); } else { result = new GermanStemFilter(result); } 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="IrishLowerCaseFilter"/>, <seealso cref="StopFilter"/> /// , <seealso cref="SetKeywordMarkerFilter"/> if a stem exclusion set is /// provided and <seealso cref="SnowballFilter"/>. </returns> protected internal override TokenStreamComponents createComponents(string fieldName, Reader reader) { //JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final': //ORIGINAL LINE: final org.apache.lucene.analysis.Tokenizer source = new org.apache.lucene.analysis.standard.StandardTokenizer(matchVersion, reader); Tokenizer source = new StandardTokenizer(matchVersion, reader); TokenStream result = new StandardFilter(matchVersion, source); StopFilter s = new StopFilter(matchVersion, result, HYPHENATIONS); if (!matchVersion.onOrAfter(Version.LUCENE_44)) { s.EnablePositionIncrements = false; } result = s; result = new ElisionFilter(result, DEFAULT_ARTICLES); result = new IrishLowerCaseFilter(result); result = new StopFilter(matchVersion, result, stopwords); if (!stemExclusionSet.Empty) { result = new SetKeywordMarkerFilter(result, stemExclusionSet); } result = new SnowballFilter(result, new IrishStemmer()); return new TokenStreamComponents(source, result); }
/// <summary> /// Returns a (possibly reused) <seealso cref="TokenStream"/> which tokenizes all the /// text in the provided <seealso cref="Reader"/>. /// </summary> /// <returns> A <seealso cref="TokenStream"/> built from a <seealso cref="StandardTokenizer"/> /// filtered with <seealso cref="StandardFilter"/>, <seealso cref="LowerCaseFilter"/>, /// <seealso cref="StopFilter"/>, <seealso cref="SetKeywordMarkerFilter"/> if a stem exclusion set is provided, /// <seealso cref="StemmerOverrideFilter"/>, and <seealso cref="SnowballFilter"/> </returns> protected internal override TokenStreamComponents createComponents(string fieldName, Reader aReader) { if (matchVersion.onOrAfter(Version.LUCENE_31)) { //JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final': //ORIGINAL LINE: final org.apache.lucene.analysis.Tokenizer source = new org.apache.lucene.analysis.standard.StandardTokenizer(matchVersion, aReader); Tokenizer source = new StandardTokenizer(matchVersion, aReader); TokenStream result = new StandardFilter(matchVersion, source); result = new LowerCaseFilter(matchVersion, result); result = new StopFilter(matchVersion, result, stoptable); if (!excltable.Empty) { result = new SetKeywordMarkerFilter(result, excltable); } if (stemdict != null) { result = new StemmerOverrideFilter(result, stemdict); } result = new SnowballFilter(result, new org.tartarus.snowball.ext.DutchStemmer()); return new TokenStreamComponents(source, result); } else { //JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final': //ORIGINAL LINE: final org.apache.lucene.analysis.Tokenizer source = new org.apache.lucene.analysis.standard.StandardTokenizer(matchVersion, aReader); Tokenizer source = new StandardTokenizer(matchVersion, aReader); TokenStream result = new StandardFilter(matchVersion, source); result = new StopFilter(matchVersion, result, stoptable); if (!excltable.Empty) { result = new SetKeywordMarkerFilter(result, excltable); } result = new DutchStemFilter(result, origStemdict); return new TokenStreamComponents(source, result); } }
/// <summary> /// Creates /// <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/> /// used to tokenize all the text in the provided <seealso cref="Reader"/>. /// </summary> /// <returns> <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/> /// built from a <seealso cref="StandardTokenizer"/> filtered with /// <seealso cref="LowerCaseFilter"/>, <seealso cref="IndicNormalizationFilter"/>, /// <seealso cref="HindiNormalizationFilter"/>, <seealso cref="SetKeywordMarkerFilter"/> /// if a stem exclusion set is provided, <seealso cref="HindiStemFilter"/>, and /// Hindi Stop words </returns> protected internal override TokenStreamComponents createComponents(string fieldName, Reader reader) { //JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final': //ORIGINAL LINE: final org.apache.lucene.analysis.Tokenizer source; Tokenizer source; if (matchVersion.onOrAfter(Version.LUCENE_36)) { source = new StandardTokenizer(matchVersion, reader); } else { source = new IndicTokenizer(matchVersion, reader); } TokenStream result = new LowerCaseFilter(matchVersion, source); if (!stemExclusionSet.Empty) { result = new SetKeywordMarkerFilter(result, stemExclusionSet); } result = new IndicNormalizationFilter(result); result = new HindiNormalizationFilter(result); result = new StopFilter(matchVersion, result, stopwords); result = new HindiStemFilter(result); return new TokenStreamComponents(source, result); }