protected internal override Analyzer.TokenStreamComponents createComponents(string fieldName, Reader reader) { Tokenizer source = new StandardTokenizer(TEST_VERSION_CURRENT, reader); TokenStream result = new LowerCaseFilter(TEST_VERSION_CURRENT, source); return(new Analyzer.TokenStreamComponents(source, new PortugueseLightStemFilter(result))); }
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET: //ORIGINAL LINE: public void testElision() throws Exception 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]); }
protected internal override TokenStreamComponents CreateComponents(string fieldName) { StandardTokenizer src = new StandardTokenizer(); src.MaxTokenLength = DEFAULT_MAX_TOKEN_LENGTH; TokenStream tok = new StandardFilter(src); tok = new LowerCaseFilter(tok); tok = new StopFilter(tok, stopwords); tok = new ASCIIFoldingFilter(tok); return(new TokenStreamComponents(src, tok)); }
/// <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)); }
/// <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="ArabicNormalizationFilter"/>, /// <seealso cref="PersianNormalizationFilter"/> and Persian 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_31)) { source = new StandardTokenizer(matchVersion, reader); } else { source = new ArabicLetterTokenizer(matchVersion, reader); } TokenStream result = new LowerCaseFilter(matchVersion, source); result = new ArabicNormalizationFilter(result); /* additional persian-specific normalization */ result = new PersianNormalizationFilter(result); /* * the order here is important: the stopword list is normalized with the * above! */ return new TokenStreamComponents(source, new StopFilter(matchVersion, result, stopwords)); }
protected internal override TokenStreamComponents createComponents(string fieldName, Reader reader) { Tokenizer source = new StandardTokenizer(TEST_VERSION_CURRENT, reader); TokenStream result = new LowerCaseFilter(TEST_VERSION_CURRENT, source); return new TokenStreamComponents(source, new PortugueseStemFilter(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="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 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 TokenStreamComponents createComponents(string fieldName, Reader reader) { Tokenizer t = new StandardTokenizer(TEST_VERSION_CURRENT, reader); return new TokenStreamComponents(t, new CJKBigramFilter(t, CJKBigramFilter.HAN, true)); }
public TokenStreamComponentsAnonymousInnerClassHelper(StandardAnalyzer outerInstance, org.apache.lucene.analysis.standard.StandardTokenizer src, TokenStream tok, Reader reader) : base(src, tok) { this.outerInstance = outerInstance; this.reader = reader; this.src = src; }
/// <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); }