Search in sources :

Example 81 with LowerCaseFilter

use of org.apache.lucene.analysis.LowerCaseFilter in project lucene-solr by apache.

the class SpanishAnalyzer method createComponents.

/**
   * Creates a
   * {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
   * which tokenizes all the text in the provided {@link Reader}.
   * 
   * @return A
   *         {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
   *         built from an {@link StandardTokenizer} filtered with
   *         {@link StandardFilter}, {@link LowerCaseFilter}, {@link StopFilter}
   *         , {@link SetKeywordMarkerFilter} if a stem exclusion set is
   *         provided and {@link SpanishLightStemFilter}.
   */
@Override
protected TokenStreamComponents createComponents(String fieldName) {
    final Tokenizer source = new StandardTokenizer();
    TokenStream result = new StandardFilter(source);
    result = new LowerCaseFilter(result);
    result = new StopFilter(result, stopwords);
    if (!stemExclusionSet.isEmpty())
        result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SpanishLightStemFilter(result);
    return new TokenStreamComponents(source, result);
}
Also used : TokenStream(org.apache.lucene.analysis.TokenStream) StandardTokenizer(org.apache.lucene.analysis.standard.StandardTokenizer) StopFilter(org.apache.lucene.analysis.StopFilter) SetKeywordMarkerFilter(org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter) StandardFilter(org.apache.lucene.analysis.standard.StandardFilter) Tokenizer(org.apache.lucene.analysis.Tokenizer) StandardTokenizer(org.apache.lucene.analysis.standard.StandardTokenizer) LowerCaseFilter(org.apache.lucene.analysis.LowerCaseFilter)

Example 82 with LowerCaseFilter

use of org.apache.lucene.analysis.LowerCaseFilter in project lucene-solr by apache.

the class SpanishAnalyzer method normalize.

@Override
protected TokenStream normalize(String fieldName, TokenStream in) {
    TokenStream result = new StandardFilter(in);
    result = new LowerCaseFilter(result);
    return result;
}
Also used : TokenStream(org.apache.lucene.analysis.TokenStream) StandardFilter(org.apache.lucene.analysis.standard.StandardFilter) LowerCaseFilter(org.apache.lucene.analysis.LowerCaseFilter)

Example 83 with LowerCaseFilter

use of org.apache.lucene.analysis.LowerCaseFilter in project lucene-solr by apache.

the class PersianAnalyzer method createComponents.

/**
   * Creates
   * {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
   * used to tokenize all the text in the provided {@link Reader}.
   * 
   * @return {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
   *         built from a {@link StandardTokenizer} filtered with
   *         {@link LowerCaseFilter}, {@link DecimalDigitFilter}, {@link ArabicNormalizationFilter},
   *         {@link PersianNormalizationFilter} and Persian Stop words
   */
@Override
protected TokenStreamComponents createComponents(String fieldName) {
    final Tokenizer source = new StandardTokenizer();
    TokenStream result = new LowerCaseFilter(source);
    result = new DecimalDigitFilter(result);
    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(result, stopwords));
}
Also used : DecimalDigitFilter(org.apache.lucene.analysis.core.DecimalDigitFilter) ArabicNormalizationFilter(org.apache.lucene.analysis.ar.ArabicNormalizationFilter) TokenStream(org.apache.lucene.analysis.TokenStream) StandardTokenizer(org.apache.lucene.analysis.standard.StandardTokenizer) StopFilter(org.apache.lucene.analysis.StopFilter) Tokenizer(org.apache.lucene.analysis.Tokenizer) StandardTokenizer(org.apache.lucene.analysis.standard.StandardTokenizer) LowerCaseFilter(org.apache.lucene.analysis.LowerCaseFilter)

Example 84 with LowerCaseFilter

use of org.apache.lucene.analysis.LowerCaseFilter in project lucene-solr by apache.

the class FinnishAnalyzer method normalize.

@Override
protected TokenStream normalize(String fieldName, TokenStream in) {
    TokenStream result = new StandardFilter(in);
    result = new LowerCaseFilter(result);
    return result;
}
Also used : TokenStream(org.apache.lucene.analysis.TokenStream) StandardFilter(org.apache.lucene.analysis.standard.StandardFilter) LowerCaseFilter(org.apache.lucene.analysis.LowerCaseFilter)

Example 85 with LowerCaseFilter

use of org.apache.lucene.analysis.LowerCaseFilter in project lucene-solr by apache.

the class FinnishAnalyzer method createComponents.

/**
   * Creates a
   * {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
   * which tokenizes all the text in the provided {@link Reader}.
   * 
   * @return A
   *         {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
   *         built from an {@link StandardTokenizer} filtered with
   *         {@link StandardFilter}, {@link LowerCaseFilter}, {@link StopFilter}
   *         , {@link SetKeywordMarkerFilter} if a stem exclusion set is
   *         provided and {@link SnowballFilter}.
   */
@Override
protected TokenStreamComponents createComponents(String fieldName) {
    final Tokenizer source = new StandardTokenizer();
    TokenStream result = new StandardFilter(source);
    result = new LowerCaseFilter(result);
    result = new StopFilter(result, stopwords);
    if (!stemExclusionSet.isEmpty())
        result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new FinnishStemmer());
    return new TokenStreamComponents(source, result);
}
Also used : TokenStream(org.apache.lucene.analysis.TokenStream) StandardTokenizer(org.apache.lucene.analysis.standard.StandardTokenizer) StopFilter(org.apache.lucene.analysis.StopFilter) SetKeywordMarkerFilter(org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter) StandardFilter(org.apache.lucene.analysis.standard.StandardFilter) SnowballFilter(org.apache.lucene.analysis.snowball.SnowballFilter) FinnishStemmer(org.tartarus.snowball.ext.FinnishStemmer) Tokenizer(org.apache.lucene.analysis.Tokenizer) StandardTokenizer(org.apache.lucene.analysis.standard.StandardTokenizer) LowerCaseFilter(org.apache.lucene.analysis.LowerCaseFilter)

Aggregations

LowerCaseFilter (org.apache.lucene.analysis.LowerCaseFilter)95 TokenStream (org.apache.lucene.analysis.TokenStream)88 StandardFilter (org.apache.lucene.analysis.standard.StandardFilter)60 Tokenizer (org.apache.lucene.analysis.Tokenizer)51 StopFilter (org.apache.lucene.analysis.StopFilter)48 StandardTokenizer (org.apache.lucene.analysis.standard.StandardTokenizer)43 SetKeywordMarkerFilter (org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter)31 SnowballFilter (org.apache.lucene.analysis.snowball.SnowballFilter)14 DecimalDigitFilter (org.apache.lucene.analysis.core.DecimalDigitFilter)10 Analyzer (org.apache.lucene.analysis.Analyzer)9 IOException (java.io.IOException)5 ElisionFilter (org.apache.lucene.analysis.util.ElisionFilter)5 StringReader (java.io.StringReader)4 HashMap (java.util.HashMap)4 TokenFilter (org.apache.lucene.analysis.TokenFilter)4 WhitespaceAnalyzer (org.apache.lucene.analysis.core.WhitespaceAnalyzer)4 EnglishPossessiveFilter (org.apache.lucene.analysis.en.EnglishPossessiveFilter)4 PerFieldAnalyzerWrapper (org.apache.lucene.analysis.miscellaneous.PerFieldAnalyzerWrapper)4 Document (org.apache.lucene.document.Document)4 Field (org.apache.lucene.document.Field)4