/// <summary>Constructs a {@link StandardTokenizer} filtered by a {@link /// StandardFilter}, a {@link LowerCaseFilter} and a {@link StopFilter}. /// </summary> public override TokenStream TokenStream(System.String fieldName, System.IO.TextReader reader) { StandardTokenizer tokenStream = new StandardTokenizer(reader, replaceInvalidAcronym); tokenStream.SetMaxTokenLength(maxTokenLength); TokenStream result = new StandardFilter(tokenStream); result = new LowerCaseFilter(result); result = new StopFilter(result, stopSet); return(result); }
/// <summary>Constructs a {@link StandardTokenizer} filtered by a {@link /// StandardFilter}, a {@link LowerCaseFilter} and a {@link StopFilter}. /// </summary> public override TokenStream TokenStream(System.String fieldName, System.IO.TextReader reader) { StandardTokenizer tokenStream = new StandardTokenizer(reader, replaceInvalidAcronym); tokenStream.SetMaxTokenLength(maxTokenLength); TokenStream result = new StandardFilter(tokenStream); result = new LowerCaseFilter(result); if (useDefaultStopPositionIncrements) { result = new StopFilter(result, stopSet); } else { result = new StopFilter(enableStopPositionIncrements, result, stopSet); } return(result); }
public override TokenStream TokenStream(string fieldName, TextReader reader) { var tokenizer = new StandardTokenizer(Version.LUCENE_29, reader); tokenizer.SetMaxTokenLength(255); TokenStream filter = new StandardFilter(tokenizer); filter = new LowerCaseFilter(filter); filter = new StopFilter(false,filter, StandardAnalyzer.STOP_WORDS_SET); return new NGramTokenFilter(filter, 2, 6); }
/// <summary>Constructs a {@link StandardTokenizer} filtered by a {@link /// StandardFilter}, a {@link LowerCaseFilter} and a {@link StopFilter}. /// </summary> public override TokenStream TokenStream(System.String fieldName, System.IO.TextReader reader) { StandardTokenizer tokenStream = new StandardTokenizer(reader, replaceInvalidAcronym); tokenStream.SetMaxTokenLength(maxTokenLength); TokenStream result = new StandardFilter(tokenStream); result = new LowerCaseFilter(result); if (useDefaultStopPositionIncrements) { result = new StopFilter(result, stopSet); } else { result = new StopFilter(enableStopPositionIncrements, result, stopSet); } return result; }
/// <summary>Constructs a {@link StandardTokenizer} filtered by a {@link /// StandardFilter}, a {@link LowerCaseFilter} and a {@link StopFilter}. /// </summary> public override TokenStream TokenStream(System.String fieldName, System.IO.TextReader reader) { StandardTokenizer tokenStream = new StandardTokenizer(reader, replaceInvalidAcronym); tokenStream.SetMaxTokenLength(maxTokenLength); TokenStream result = new StandardFilter(tokenStream); result = new LowerCaseFilter(result); result = new StopFilter(result, stopSet); return result; }