Search in sources :

Example 61 with StandardTokenizer

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

the class DanishAnalyzer 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 DanishStemmer());
    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) DanishStemmer(org.tartarus.snowball.ext.DanishStemmer) 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 62 with StandardTokenizer

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

the class GermanAnalyzer 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 LowerCaseFilter}, {@link StopFilter}
   *         , {@link SetKeywordMarkerFilter} if a stem exclusion set is
   *         provided, {@link GermanNormalizationFilter} and {@link GermanLightStemFilter}
   */
@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);
    result = new SetKeywordMarkerFilter(result, exclusionSet);
    result = new GermanNormalizationFilter(result);
    result = new GermanLightStemFilter(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 63 with StandardTokenizer

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

the class CatalanAnalyzer 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 ElisionFilter}, {@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 ElisionFilter(result, DEFAULT_ARTICLES);
    result = new LowerCaseFilter(result);
    result = new StopFilter(result, stopwords);
    if (!stemExclusionSet.isEmpty())
        result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new CatalanStemmer());
    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) LowerCaseFilter(org.apache.lucene.analysis.LowerCaseFilter) CatalanStemmer(org.tartarus.snowball.ext.CatalanStemmer)

Example 64 with StandardTokenizer

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

the class CzechAnalyzer 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 LowerCaseFilter}, {@link StopFilter}
   *         , and {@link CzechStemFilter} (only if version is >= LUCENE_31). If
   *         a stem exclusion set is provided via
   *         {@link #CzechAnalyzer(CharArraySet, CharArraySet)} a
   *         {@link SetKeywordMarkerFilter} is added before
   *         {@link CzechStemFilter}.
   */
@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 (!this.stemExclusionTable.isEmpty())
        result = new SetKeywordMarkerFilter(result, stemExclusionTable);
    result = new CzechStemFilter(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 65 with StandardTokenizer

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

the class BrazilianAnalyzer 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 StandardFilter}, {@link StopFilter}
   *         , and {@link BrazilianStemFilter}.
   */
@Override
protected TokenStreamComponents createComponents(String fieldName) {
    Tokenizer source = new StandardTokenizer();
    TokenStream result = new LowerCaseFilter(source);
    result = new StandardFilter(result);
    result = new StopFilter(result, stopwords);
    if (excltable != null && !excltable.isEmpty())
        result = new SetKeywordMarkerFilter(result, excltable);
    return new TokenStreamComponents(source, new BrazilianStemFilter(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)

Aggregations

StandardTokenizer (org.apache.lucene.analysis.standard.StandardTokenizer)82 Tokenizer (org.apache.lucene.analysis.Tokenizer)68 TokenStream (org.apache.lucene.analysis.TokenStream)57 LowerCaseFilter (org.apache.lucene.analysis.LowerCaseFilter)43 StopFilter (org.apache.lucene.analysis.StopFilter)43 StandardFilter (org.apache.lucene.analysis.standard.StandardFilter)36 SetKeywordMarkerFilter (org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter)35 StringReader (java.io.StringReader)18 SnowballFilter (org.apache.lucene.analysis.snowball.SnowballFilter)16 Analyzer (org.apache.lucene.analysis.Analyzer)10 LowerCaseFilter (org.apache.lucene.analysis.core.LowerCaseFilter)10 ASCIIFoldingFilter (org.apache.lucene.analysis.miscellaneous.ASCIIFoldingFilter)7 EnglishPossessiveFilter (org.apache.lucene.analysis.en.EnglishPossessiveFilter)6 ElisionFilter (org.apache.lucene.analysis.util.ElisionFilter)6 DecimalDigitFilter (org.apache.lucene.analysis.core.DecimalDigitFilter)5 StopFilter (org.apache.lucene.analysis.core.StopFilter)5 ESTestCase (org.elasticsearch.test.ESTestCase)5 HashMap (java.util.HashMap)4 TokenFilter (org.apache.lucene.analysis.TokenFilter)4 PorterStemFilter (org.apache.lucene.analysis.en.PorterStemFilter)4