Search in sources :

Example 31 with SetKeywordMarkerFilter

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

the class FrenchAnalyzer 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 StandardFilter}, {@link ElisionFilter},
   *         {@link LowerCaseFilter}, {@link StopFilter},
   *         {@link SetKeywordMarkerFilter} if a stem exclusion set is
   *         provided, and {@link FrenchLightStemFilter}
   */
@Override
protected TokenStreamComponents createComponents(String fieldName) {
    final Tokenizer source = new StandardTokenizer();
    TokenStream result = new StandardFilter(source);
    result = new ElisionFilter(result, DEFAULT_ARTICLES);
    result = new LowerCaseFilter(result);
    result = new StopFilter(result, stopwords);
    if (!excltable.isEmpty())
        result = new SetKeywordMarkerFilter(result, excltable);
    result = new FrenchLightStemFilter(result);
    return new TokenStreamComponents(source, result);
}
Also used : TokenStream(org.apache.lucene.analysis.TokenStream) ElisionFilter(org.apache.lucene.analysis.util.ElisionFilter) 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 32 with SetKeywordMarkerFilter

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

the class IrishAnalyzer 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 IrishLowerCaseFilter}, {@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 StopFilter(result, HYPHENATIONS);
    result = new ElisionFilter(result, DEFAULT_ARTICLES);
    result = new IrishLowerCaseFilter(result);
    result = new StopFilter(result, stopwords);
    if (!stemExclusionSet.isEmpty())
        result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new IrishStemmer());
    return new TokenStreamComponents(source, result);
}
Also used : TokenStream(org.apache.lucene.analysis.TokenStream) ElisionFilter(org.apache.lucene.analysis.util.ElisionFilter) 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) Tokenizer(org.apache.lucene.analysis.Tokenizer) StandardTokenizer(org.apache.lucene.analysis.standard.StandardTokenizer) IrishStemmer(org.tartarus.snowball.ext.IrishStemmer)

Example 33 with SetKeywordMarkerFilter

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

the class HungarianAnalyzer 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 HungarianStemmer());
    return new TokenStreamComponents(source, result);
}
Also used : HungarianStemmer(org.tartarus.snowball.ext.HungarianStemmer) 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) Tokenizer(org.apache.lucene.analysis.Tokenizer) StandardTokenizer(org.apache.lucene.analysis.standard.StandardTokenizer) LowerCaseFilter(org.apache.lucene.analysis.LowerCaseFilter)

Example 34 with SetKeywordMarkerFilter

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

the class ArmenianAnalyzer 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 ArmenianStemmer());
    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) ArmenianStemmer(org.tartarus.snowball.ext.ArmenianStemmer) StandardFilter(org.apache.lucene.analysis.standard.StandardFilter) SnowballFilter(org.apache.lucene.analysis.snowball.SnowballFilter) Tokenizer(org.apache.lucene.analysis.Tokenizer) StandardTokenizer(org.apache.lucene.analysis.standard.StandardTokenizer) LowerCaseFilter(org.apache.lucene.analysis.LowerCaseFilter)

Example 35 with SetKeywordMarkerFilter

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

the class LithuanianAnalyzer 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 LithuanianStemmer());
    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) LithuanianStemmer(org.tartarus.snowball.ext.LithuanianStemmer) Tokenizer(org.apache.lucene.analysis.Tokenizer) StandardTokenizer(org.apache.lucene.analysis.standard.StandardTokenizer) LowerCaseFilter(org.apache.lucene.analysis.LowerCaseFilter)

Aggregations

SetKeywordMarkerFilter (org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter)57 Tokenizer (org.apache.lucene.analysis.Tokenizer)52 TokenStream (org.apache.lucene.analysis.TokenStream)50 StandardTokenizer (org.apache.lucene.analysis.standard.StandardTokenizer)32 StopFilter (org.apache.lucene.analysis.StopFilter)31 StandardFilter (org.apache.lucene.analysis.standard.StandardFilter)30 LowerCaseFilter (org.apache.lucene.analysis.LowerCaseFilter)29 CharArraySet (org.apache.lucene.analysis.CharArraySet)26 MockTokenizer (org.apache.lucene.analysis.MockTokenizer)21 Analyzer (org.apache.lucene.analysis.Analyzer)19 KeywordTokenizer (org.apache.lucene.analysis.core.KeywordTokenizer)19 SnowballFilter (org.apache.lucene.analysis.snowball.SnowballFilter)14 StringReader (java.io.StringReader)5 ElisionFilter (org.apache.lucene.analysis.util.ElisionFilter)4 DecimalDigitFilter (org.apache.lucene.analysis.core.DecimalDigitFilter)3 LowerCaseTokenizer (org.apache.lucene.analysis.core.LowerCaseTokenizer)2 IndicNormalizationFilter (org.apache.lucene.analysis.in.IndicNormalizationFilter)1 StemmerOverrideFilter (org.apache.lucene.analysis.miscellaneous.StemmerOverrideFilter)1 MorfologikFilter (org.apache.lucene.analysis.morfologik.MorfologikFilter)1 StempelFilter (org.apache.lucene.analysis.stempel.StempelFilter)1