Package org.apache.lucene.analysis.snowball

Examples of org.apache.lucene.analysis.snowball.SnowballFilter

242
243
244
245
246
247
248
249
250
251
    TokenStream result = new StandardFilter(matchVersion, source);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter( matchVersion, result, stopwords);
    result = new KeywordMarkerFilter(result, exclusionSet);
    if (matchVersion.onOrAfter(Version.LUCENE_31))
      result = new SnowballFilter(result, new German2Stemmer());
    else
      result = new GermanStemFilter(result);
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
144
145
146
147
148
149
150
151
    }
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new KeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new ItalianStemmer());
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
271
272
273
274
275
276
277
278
279
280
281
      result = new StopFilter(matchVersion, result, stoptable);
      if (!excltable.isEmpty())
        result = new KeywordMarkerFilter(result, excltable);
      if (!stemdict.isEmpty())
        result = new StemmerOverrideFilter(matchVersion, result, stemdict);
      result = new SnowballFilter(result, new org.tartarus.snowball.ext.DutchStemmer());
      return new TokenStreamComponents(source, result);
    } else {
      final Tokenizer source = new StandardTokenizer(matchVersion, aReader);
      TokenStream result = new StandardFilter(matchVersion, source);
      result = new StopFilter(matchVersion, result, stoptable);
View Full Code Here
179
180
181
182
183
184
185
186
187
188
189
        TokenStream result = new StandardFilter(matchVersion, source);
        result = new LowerCaseFilter(matchVersion, result);
        result = new StopFilter(matchVersion, result, stopwords);
        if (!stemExclusionSet.isEmpty()) result = new KeywordMarkerFilter(
            result, stemExclusionSet);
        result = new SnowballFilter(result, new org.tartarus.snowball.ext.RussianStemmer());
        return new TokenStreamComponents(source, result);
      } else {
        final Tokenizer source = new RussianLetterTokenizer(matchVersion, reader);
        TokenStream result = new LowerCaseFilter(matchVersion, source);
        result = new StopFilter(matchVersion, result, stopwords);
View Full Code Here
124
125
126
127
128
129
130
131
    TokenStream result = new StandardFilter(matchVersion, source);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new KeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new SpanishStemmer());
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
44
45
46
47
48
49
50
    }

    @Override
    public TokenStream create(TokenStream tokenStream) {
        tokenStream = new SetKeywordMarkerFilter(tokenStream, exclusions);
        return new SnowballFilter(tokenStream, new FrenchStemmer());
    }
View Full Code Here
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
        final Version indexVersion = Version.indexCreated(indexSettings);

        if ("arabic".equalsIgnoreCase(language)) {
            return new ArabicStemFilter(tokenStream);
        } else if ("armenian".equalsIgnoreCase(language)) {
            return new SnowballFilter(tokenStream, new ArmenianStemmer());
        } else if ("basque".equalsIgnoreCase(language)) {
            return new SnowballFilter(tokenStream, new BasqueStemmer());
        } else if ("brazilian".equalsIgnoreCase(language)) {
            return new BrazilianStemFilter(tokenStream);
        } else if ("bulgarian".equalsIgnoreCase(language)) {
            return new BulgarianStemFilter(tokenStream);
        } else if ("catalan".equalsIgnoreCase(language)) {
            return new SnowballFilter(tokenStream, new CatalanStemmer());
        } else if ("czech".equalsIgnoreCase(language)) {
            return new CzechStemFilter(tokenStream);
        } else if ("danish".equalsIgnoreCase(language)) {
            return new SnowballFilter(tokenStream, new DanishStemmer());

            // Dutch stemmers
        } else if ("dutch".equalsIgnoreCase(language)) {
            return new SnowballFilter(tokenStream, new DutchStemmer());
        } else if ("dutch_kp".equalsIgnoreCase(language) || "dutchKp".equalsIgnoreCase(language) || "kp".equalsIgnoreCase(language)) {
            return new SnowballFilter(tokenStream, new KpStemmer());

            // English stemmers
        } else if ("english".equalsIgnoreCase(language)) {
            if (indexVersion.onOrAfter(Version.V_1_3_0)) {
                return new PorterStemFilter(tokenStream);
            } else {
                return new SnowballFilter(tokenStream, new EnglishStemmer());
            }
        } else if ("light_english".equalsIgnoreCase(language) || "lightEnglish".equalsIgnoreCase(language)
                || "kstem".equalsIgnoreCase(language)) {
            return new KStemFilter(tokenStream);
        } else if ("lovins".equalsIgnoreCase(language)) {
            return new SnowballFilter(tokenStream, new LovinsStemmer());
        } else if ("porter".equalsIgnoreCase(language)) {
            return new PorterStemFilter(tokenStream);
        } else if ("porter2".equalsIgnoreCase(language)) {
            if (indexVersion.onOrAfter(Version.V_1_3_0)) {
                return new SnowballFilter(tokenStream, new EnglishStemmer());
            } else {
                return new SnowballFilter(tokenStream, new PorterStemmer());
            }
        } 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);

            // Finnish stemmers
        } else if ("finnish".equalsIgnoreCase(language)) {
            return new SnowballFilter(tokenStream, new FinnishStemmer());
        } else if ("light_finish".equalsIgnoreCase(language) || "lightFinish".equalsIgnoreCase(language)) {
            // leaving this for backward compatibility
            return new FinnishLightStemFilter(tokenStream);
        } else if ("light_finnish".equalsIgnoreCase(language) || "lightFinnish".equalsIgnoreCase(language)) {
            return new FinnishLightStemFilter(tokenStream);

            // French stemmers
        } else if ("french".equalsIgnoreCase(language)) {
            return new SnowballFilter(tokenStream, new FrenchStemmer());
        } else if ("light_french".equalsIgnoreCase(language) || "lightFrench".equalsIgnoreCase(language)) {
            return new FrenchLightStemFilter(tokenStream);
        } else if ("minimal_french".equalsIgnoreCase(language) || "minimalFrench".equalsIgnoreCase(language)) {
            return new FrenchMinimalStemFilter(tokenStream);
           
            // Galician stemmers
        } else if ("galician".equalsIgnoreCase(language)) {
            return new GalicianStemFilter(tokenStream);
        } else if ("minimal_galician".equalsIgnoreCase(language)) {
            return new GalicianMinimalStemFilter(tokenStream);

            // German stemmers
        } else if ("german".equalsIgnoreCase(language)) {
            return new SnowballFilter(tokenStream, new GermanStemmer());
        } else if ("german2".equalsIgnoreCase(language)) {
            return new SnowballFilter(tokenStream, new German2Stemmer());
        } else if ("light_german".equalsIgnoreCase(language) || "lightGerman".equalsIgnoreCase(language)) {
            return new GermanLightStemFilter(tokenStream);
        } else if ("minimal_german".equalsIgnoreCase(language) || "minimalGerman".equalsIgnoreCase(language)) {
            return new GermanMinimalStemFilter(tokenStream);

        } else if ("greek".equalsIgnoreCase(language)) {
            return new GreekStemFilter(tokenStream);
        } else if ("hindi".equalsIgnoreCase(language)) {
            return new HindiStemFilter(tokenStream);

            // Hungarian stemmers
        } else if ("hungarian".equalsIgnoreCase(language)) {
            return new SnowballFilter(tokenStream, new HungarianStemmer());
        } else if ("light_hungarian".equalsIgnoreCase(language) || "lightHungarian".equalsIgnoreCase(language)) {
            return new HungarianLightStemFilter(tokenStream);

        } else if ("indonesian".equalsIgnoreCase(language)) {
            return new IndonesianStemFilter(tokenStream);
           
            // Irish stemmer
        } else if ("irish".equalsIgnoreCase(language)) {
            return new SnowballFilter(tokenStream, new IrishStemmer());

            // Italian stemmers
        } else if ("italian".equalsIgnoreCase(language)) {
            return new SnowballFilter(tokenStream, new ItalianStemmer());
        } else if ("light_italian".equalsIgnoreCase(language) || "lightItalian".equalsIgnoreCase(language)) {
            return new ItalianLightStemFilter(tokenStream);

        } else if ("latvian".equalsIgnoreCase(language)) {
            return new LatvianStemFilter(tokenStream);

            // Norwegian (Bokmål) stemmers
        } else if ("norwegian".equalsIgnoreCase(language)) {
            return new SnowballFilter(tokenStream, new NorwegianStemmer());
        } else if ("light_norwegian".equalsIgnoreCase(language) || "lightNorwegian".equalsIgnoreCase(language)) {
            return new NorwegianLightStemFilter(tokenStream);
        } else if ("minimal_norwegian".equalsIgnoreCase(language) || "minimalNorwegian".equals(language)) {
            return new NorwegianMinimalStemFilter(tokenStream);
           
            // Norwegian (Nynorsk) stemmers
        } else if ("light_nynorsk".equalsIgnoreCase(language) || "lightNynorsk".equalsIgnoreCase(language)) {
            return new NorwegianLightStemFilter(tokenStream, NorwegianLightStemmer.NYNORSK);
        } else if ("minimal_nynorsk".equalsIgnoreCase(language) || "minimalNynorsk".equalsIgnoreCase(language)) {
            return new NorwegianMinimalStemFilter(tokenStream, NorwegianLightStemmer.NYNORSK);

            // Portuguese stemmers
        } else if ("portuguese".equalsIgnoreCase(language)) {
            return new SnowballFilter(tokenStream, new PortugueseStemmer());
        } else if ("light_portuguese".equalsIgnoreCase(language) || "lightPortuguese".equalsIgnoreCase(language)) {
            return new PortugueseLightStemFilter(tokenStream);
        } else if ("minimal_portuguese".equalsIgnoreCase(language) || "minimalPortuguese".equalsIgnoreCase(language)) {
            return new PortugueseMinimalStemFilter(tokenStream);
        } else if ("portuguese_rslp".equalsIgnoreCase(language)) {
            return new PortugueseStemFilter(tokenStream);

        } else if ("romanian".equalsIgnoreCase(language)) {
            return new SnowballFilter(tokenStream, new RomanianStemmer());

            // Russian stemmers
        } else if ("russian".equalsIgnoreCase(language)) {
            return new SnowballFilter(tokenStream, new RussianStemmer());
        } else if ("light_russian".equalsIgnoreCase(language) || "lightRussian".equalsIgnoreCase(language)) {
            return new RussianLightStemFilter(tokenStream);

            // Spanish stemmers
        } else if ("spanish".equalsIgnoreCase(language)) {
            return new SnowballFilter(tokenStream, new SpanishStemmer());
        } else if ("light_spanish".equalsIgnoreCase(language) || "lightSpanish".equalsIgnoreCase(language)) {
            return new SpanishLightStemFilter(tokenStream);
           
            // Sorani Kurdish stemmer
        } else if ("sorani".equalsIgnoreCase(language)) {
            return new SoraniStemFilter(tokenStream);

            // Swedish stemmers
        } else if ("swedish".equalsIgnoreCase(language)) {
            return new SnowballFilter(tokenStream, new SwedishStemmer());
        } else if ("light_swedish".equalsIgnoreCase(language) || "lightSwedish".equalsIgnoreCase(language)) {
            return new SwedishLightStemFilter(tokenStream);

        } else if ("turkish".equalsIgnoreCase(language)) {
            return new SnowballFilter(tokenStream, new TurkishStemmer());
        }

        return new SnowballFilter(tokenStream, language);
    }
View Full Code Here
44
45
46
47
48
49
50
    }

    @Override
    public TokenStream create(TokenStream tokenStream) {
        tokenStream = new SetKeywordMarkerFilter(tokenStream, exclusions);
        return new SnowballFilter(tokenStream, new DutchStemmer());
    }
View Full Code Here
78
79
80
81
82
83
84
85
      result = new TurkishLowerCaseFilter(result);
    else
      result = new LowerCaseFilter(result);
    if (stopSet != null)
      result = new StopFilter(result, stopSet);
    result = new SnowballFilter(result, name);
    return new TokenStreamComponents(tokenizer, result);
  }
View Full Code Here
41
42
43
44
45
46
47
        this.language = Strings.capitalize(settings.get("language", settings.get("name", "English")));
    }

    @Override
    public TokenStream create(TokenStream tokenStream) {
        return new SnowballFilter(tokenStream, language);
    }
View Full Code Here
TOP

Related Classes of org.apache.lucene.analysis.snowball.SnowballFilter

  • com.enigmastation.extractors.impl.LuceneStemmingWordLister
  • com.flaptor.indextank.query.analyzers.StemmerFilter
  • de.jetwick.es.JetwickQuery
  • org.apache.lucene.analysis.ca.CatalanAnalyzer
  • org.apache.lucene.analysis.da.DanishAnalyzer
  • org.apache.lucene.analysis.de.GermanAnalyzer
  • org.apache.lucene.analysis.es.SpanishAnalyzer
  • org.apache.lucene.analysis.eu.BasqueAnalyzer
  • org.apache.lucene.analysis.fi.FinnishAnalyzer
  • org.apache.lucene.analysis.fr.FrenchAnalyzer
    • 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.