Package org.apache.lucene.analysis.en

Examples of org.apache.lucene.analysis.en.EnglishPossessiveFilter
32
33
34
35
36
37
38
* &lt;/fieldType&gt;</pre>
* @version $Id$
*/
public class EnglishPossessiveFilterFactory extends BaseTokenFilterFactory {
  public TokenStream create(TokenStream input) {
    return new EnglishPossessiveFilter(input);
  }
View Full Code Here
108
109
110
111
112
113
114
115
116
117
118
        } else if ("turkish".equalsIgnoreCase(language)) {
            return new SnowballFilter(tokenStream, new TurkishStemmer());
        } else if ("minimal_english".equalsIgnoreCase(language) || "minimalEnglish".equalsIgnoreCase(language)) {
            return new EnglishMinimalStemFilter(tokenStream);
        } else if ("possessive_english".equalsIgnoreCase(language) || "possessiveEnglish".equalsIgnoreCase(language)) {
            return new EnglishPossessiveFilter(tokenStream);
        } else if ("light_finish".equalsIgnoreCase(language) || "lightFinish".equalsIgnoreCase(language)) {
            return new FinnishLightStemFilter(tokenStream);
        } else if ("light_french".equalsIgnoreCase(language) || "lightFrench".equalsIgnoreCase(language)) {
            return new FrenchLightStemFilter(tokenStream);
        } else if ("minimal_french".equalsIgnoreCase(language) || "minimalFrench".equalsIgnoreCase(language)) {
View Full Code Here
43
44
45
46
47
48
49
    assureMatchVersion();
  }
 
  @Override
  public TokenStream create(TokenStream input) {
    return new EnglishPossessiveFilter(luceneMatchVersion, input);
  }
View Full Code Here
71
72
73
74
75
76
77
78
79
80
81
    Tokenizer tokenizer = new StandardTokenizer(matchVersion, reader);
    TokenStream result = new StandardFilter(matchVersion, tokenizer);
    // remove the possessive 's for english stemmers
    if (matchVersion.onOrAfter(Version.LUCENE_3_1) &&
        (name.equals("English") || name.equals("Porter") || name.equals("Lovins")))
      result = new EnglishPossessiveFilter(result);
    // Use a special lowercase filter for turkish, the stemmer expects it.
    if (matchVersion.onOrAfter(Version.LUCENE_3_1) && name.equals("Turkish"))
      result = new TurkishLowerCaseFilter(result);
    else
      result = new LowerCaseFilter(matchVersion, result);
View Full Code Here
258
259
260
261
262
263
264
265
266
267
268
      final 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(result);
      result = new LowerCaseFilter(matchVersion, result);
      result = new StopFilter(matchVersion, result, stopwords);
      if (!stemExclusionSet.isEmpty())
        result = new KeywordMarkerFilter(result, stemExclusionSet);
      result = new PorterSpecialStemFilter(result);
View Full Code Here
71
72
73
74
75
76
77
78
79
80
81
    Tokenizer tokenizer = new StandardTokenizer(matchVersion, reader);
    TokenStream result = new StandardFilter(matchVersion, tokenizer);
    // remove the possessive 's for english stemmers
    if (matchVersion.onOrAfter(Version.LUCENE_31) &&
        (name.equals("English") || name.equals("Porter") || name.equals("Lovins")))
      result = new EnglishPossessiveFilter(result);
    // Use a special lowercase filter for turkish, the stemmer expects it.
    if (matchVersion.onOrAfter(Version.LUCENE_31) && name.equals("Turkish"))
      result = new TurkishLowerCaseFilter(result);
    else
      result = new LowerCaseFilter(matchVersion, result);
View Full Code Here
45
46
47
48
49
50
51
    }
  }
 
  @Override
  public TokenStream create(TokenStream input) {
    return new EnglishPossessiveFilter(luceneMatchVersion, input);
  }
View Full Code Here
122
123
124
125
126
127
128
129
130
131
132
        final 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(result);
        }
        result = new LowerCaseFilter(matchVersion, result);
        result = new StopFilter(matchVersion, result, stopwords);
        if (stem) {
            if (!stemExclusionSet.isEmpty())
View Full Code Here
84
85
86
87
88
89
90
91
92
93
94
    @Override
    protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        final Tokenizer source = new StandardTokenizer(matchVersion, reader);
        TokenStream result = new StandardFilter(matchVersion, source);
        if (matchVersion.onOrAfter(Version.LUCENE_31)) {
            result = new EnglishPossessiveFilter(result);
        }
        result = new LowerCaseFilter(matchVersion, result);
        ShingleAllStopFilter sf = new ShingleAllStopFilter(result, minNGram, maxNGram, stopwords);
        sf.setOutputUnigrams(outputUnigrams);
        if (!outputUnigrams) {
View Full Code Here
72
73
74
75
76
77
78
79
80
81
82
    protected TokenStreamComponents createComponents(String fieldName,
        Reader reader) {
      Version matchVersion = Version.LUCENE_45;
      final Tokenizer source = new StandardTokenizer(matchVersion, reader);
      TokenStream result = new StandardFilter(matchVersion, source);
      result = new EnglishPossessiveFilter(matchVersion, result);
      result = new LowerCaseFilter(matchVersion, result);
      result = new StopFilter(matchVersion, result,
          DefaultSetHolder.DEFAULT_STOP_SET);
      result = new ASCIIFoldingFilter(result);
      result = new KStemFilter(result);
View Full Code Here
TOP

Related Classes of org.apache.lucene.analysis.en.EnglishPossessiveFilter

  • com.github.pmerienne.trident.ml.preprocessing.EnglishTokenizer$EnglishSpecialAnalyzer
  • com.livingsocial.hive.udf.Tokenize$MyAnalyzer
  • com.mozilla.grouperfish.lucene.analysis.en.EnglishAnalyzer
  • com.mozilla.grouperfish.lucene.analysis.en.NGramEnglishAnalyzer
  • com.mozilla.grouperfish.transforms.coclustering.lucene.analysis.en.EnglishAnalyzer
  • com.mozilla.grouperfish.transforms.coclustering.lucene.analysis.en.NGramEnglishAnalyzer
  • org.apache.lucene.analysis.en.EnglishPossessiveFilterFactory
  • org.apache.lucene.analysis.snowball.SnowballAnalyzer
  • org.apache.solr.analysis.EnglishPossessiveFilterFactory
  • org.elasticsearch.index.analysis.SnowballAnalyzer
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.