Package org.apache.lucene.analysis.core

Examples of org.apache.lucene.analysis.core.LowerCaseFilter
91
92
93
94
95
96
97
98
99
100
101
      Reader reader) {
    if (matchVersion.onOrAfter(Version.LUCENE_3_6)) {
      final Tokenizer source = new StandardTokenizer(matchVersion, reader);
      // run the widthfilter first before bigramming, it sometimes combines characters.
      TokenStream result = new CJKWidthFilter(source);
      result = new LowerCaseFilter(matchVersion, result);
      result = new CJKBigramFilter(result);
      return new TokenStreamComponents(source, new StopFilter(matchVersion, result, stopwords));
    } else {
      final Tokenizer source = new CJKTokenizer(reader);
      return new TokenStreamComponents(source, new StopFilter(matchVersion, source, stopwords));
View Full Code Here
122
123
124
125
126
127
128
129
130
131
132
  @Override
  protected TokenStreamComponents createComponents(String fieldName,
      Reader reader) {
    final Tokenizer source = new StandardTokenizer(matchVersion, reader);
    TokenStream result = new StandardFilter(matchVersion, source);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new RomanianStemmer());
    return new TokenStreamComponents(source, result);
View Full Code Here
105
106
107
108
109
110
111
112
113
114
115
    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_3_1))
      result = new EnglishPossessiveFilter(matchVersion, result);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new PorterStemFilter(result);
    return new TokenStreamComponents(source, result);
View Full Code Here
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
      Reader reader) {
    if (matchVersion.onOrAfter(Version.LUCENE_3_1)) {
      final Tokenizer source = new StandardTokenizer(matchVersion, reader);
      TokenStream result = new StandardFilter(matchVersion, source);
      result = new ElisionFilter(result, DEFAULT_ARTICLES);
      result = new LowerCaseFilter(matchVersion, result);
      result = new StopFilter(matchVersion, result, stopwords);
      if(!excltable.isEmpty())
        result = new SetKeywordMarkerFilter(result, excltable);
      if (matchVersion.onOrAfter(Version.LUCENE_3_6)) {
        result = new FrenchLightStemFilter(result);
      } else {
        result = new SnowballFilter(result, new org.tartarus.snowball.ext.FrenchStemmer());
      }
      return new TokenStreamComponents(source, result);
    } else {
      final Tokenizer source = new StandardTokenizer(matchVersion, reader);
      TokenStream result = new StandardFilter(matchVersion, source);
      result = new StopFilter(matchVersion, result, stopwords);
      if(!excltable.isEmpty())
        result = new SetKeywordMarkerFilter(result, excltable);
      result = new FrenchStemFilter(result);
      // Convert to lowercase after stemming!
      return new TokenStreamComponents(source, new LowerCaseFilter(matchVersion, result));
    }
  }
View Full Code Here
161
162
163
164
165
166
167
168
169
170
171
    assertTokenStreamContents(theDetector, new String[]{"The", "the", "The", "the"});
    assertTokenStreamContents(dogDetector, new String[]{"Dogs", "Dogs"});
   
    source1.reset();
    TokenStream lowerCasing = new LowerCaseFilter(TEST_VERSION_CURRENT, source1);
    String[] lowerCaseTokens = new String[tokens1.length];
    for (int i = 0; i < tokens1.length; i++)
      lowerCaseTokens[i] = tokens1[i].toLowerCase(Locale.ROOT);
    assertTokenStreamContents(lowerCasing, lowerCaseTokens);
  }
View Full Code Here
121
122
123
124
125
126
127
128
129
130
131
    if (matchVersion.onOrAfter(Version.LUCENE_3_1)) {
      source = new StandardTokenizer(matchVersion, reader);
    } else {
      source = new ArabicLetterTokenizer(matchVersion, reader);
    }
    TokenStream result = new LowerCaseFilter(matchVersion, source);
    result = new ArabicNormalizationFilter(result);
    /* additional persian-specific normalization */
    result = new PersianNormalizationFilter(result);
    /*
     * the order here is important: the stopword list is normalized with the
View Full Code Here
127
128
129
130
131
132
133
134
135
136
137
  @Override
  protected TokenStreamComponents createComponents(String fieldName,
      Reader reader) {
    final Tokenizer source = new StandardTokenizer(matchVersion, reader);
    TokenStream result = new StandardFilter(matchVersion, source);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    if (matchVersion.onOrAfter(Version.LUCENE_3_6)) {
      result = new PortugueseLightStemFilter(result);
View Full Code Here
172
173
174
175
176
177
178
179
180
181
182
  @Override
  protected TokenStreamComponents createComponents(String fieldName,
      Reader reader) {
    final Tokenizer source = new StandardTokenizer(matchVersion, reader);
    TokenStream result = new StandardFilter(matchVersion, source);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter( matchVersion, result, stopwords);
    result = new SetKeywordMarkerFilter(result, exclusionSet);
    if (matchVersion.onOrAfter(Version.LUCENE_3_6)) {
      result = new GermanNormalizationFilter(result);
      result = new GermanLightStemFilter(result);
View Full Code Here
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
    protected TokenStreamComponents createComponents(String fieldName,
        Reader reader) {
      if (matchVersion.onOrAfter(Version.LUCENE_3_1)) {
        final Tokenizer source = new StandardTokenizer(matchVersion, reader);
        TokenStream result = new StandardFilter(matchVersion, source);
        result = new LowerCaseFilter(matchVersion, result);
        result = new StopFilter(matchVersion, result, stopwords);
        if (!stemExclusionSet.isEmpty()) result = new SetKeywordMarkerFilter(
            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);
        if (!stemExclusionSet.isEmpty()) result = new SetKeywordMarkerFilter(
          result, stemExclusionSet);
        result = new SnowballFilter(result, new org.tartarus.snowball.ext.RussianStemmer());
        return new TokenStreamComponents(source, result);
View Full Code Here
117
118
119
120
121
122
123
124
125
126
127
  @Override
  protected TokenStreamComponents createComponents(String fieldName,
      Reader reader) {
    final Tokenizer source = new StandardTokenizer(matchVersion, reader);
    TokenStream result = new StandardFilter(matchVersion, source);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new ArmenianStemmer());
    return new TokenStreamComponents(source, result);
View Full Code Here
TOP

Related Classes of org.apache.lucene.analysis.core.LowerCaseFilter

  • com.code972.elasticsearch.analysis.HebrewExactAnalyzer
  • com.foundationdb.server.service.text.SelectiveCaseAnalyzer
  • com.googlecode.lucene.PorterAnalyzer
  • com.livingsocial.hive.udf.Tokenize$MyAnalyzer
  • de.arago.lucene.util.LowCaseAnalyzer
  • gov.nysenate.openleg.lucene.OpenLegislationAnalyzer
  • org.apache.blur.analysis.NoStopWordStandardAnalyzer
  • org.apache.jackrabbit.oak.plugins.index.lucene.OakAnalyzer
  • org.apache.lucene.analysis.ar.ArabicAnalyzer
  • org.apache.lucene.analysis.bg.BulgarianAnalyzer
    • 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.