Package org.apache.lucene.analysis.core

Examples of org.apache.lucene.analysis.core.LowerCaseFilter
141
142
143
144
145
146
147
148
149
150
151
  @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 KeywordMarkerFilter(result, stemExclusionSet);
    result = new StempelFilter(result, new StempelStemmer(stemTable));
    return new TokenStreamComponents(source, result);
View Full Code Here
136
137
138
139
140
141
142
143
144
145
146
  @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 (matchVersion.onOrAfter(Version.LUCENE_3_1)) {
      if(!this.stemExclusionTable.isEmpty())
        result = new SetKeywordMarkerFilter(result, stemExclusionTable);
      result = new CzechStemFilter(result);
View Full Code Here
130
131
132
133
134
135
136
137
138
139
140
    if (matchVersion.onOrAfter(Version.LUCENE_3_6)) {
      source = new StandardTokenizer(matchVersion, reader);
    } else {
      source = new IndicTokenizer(matchVersion, reader);
    }
    TokenStream result = new LowerCaseFilter(matchVersion, source);
    if (!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new IndicNormalizationFilter(result);
    result = new HindiNormalizationFilter(result);
    result = new StopFilter(matchVersion, result, stopwords);
View Full Code Here
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
  @Override
  protected TokenStreamComponents createComponents(String fieldName,
      Reader reader) {
    if (matchVersion.onOrAfter(Version.LUCENE_4_8)) {
      final Tokenizer source = new ThaiTokenizer(reader);
      TokenStream result = new LowerCaseFilter(matchVersion, source);
      result = new StopFilter(matchVersion, result, stopwords);
      return new TokenStreamComponents(source, result);
    } else {
      final Tokenizer source = new StandardTokenizer(matchVersion, reader);
      TokenStream result = new StandardFilter(matchVersion, source);
      if (matchVersion.onOrAfter(Version.LUCENE_3_1))
        result = new LowerCaseFilter(matchVersion, result);
      result = new ThaiWordFilter(matchVersion, result);
      return new TokenStreamComponents(source, new StopFilter(matchVersion,
        result, stopwords));
    }
  }
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 SpanishLightStemFilter(result);
View Full Code Here
68
69
70
71
72
73
74
75
76
77
  private boolean hasIllegalOffsets = false; // only if the length changed before this filter

  /** Creates a new ThaiWordFilter with the specified match version. */
  public ThaiWordFilter(Version matchVersion, TokenStream input) {
    super(matchVersion.onOrAfter(Version.LUCENE_3_1) ?
      input : new LowerCaseFilter(matchVersion, input));
    if (!DBBI_AVAILABLE)
      throw new UnsupportedOperationException("This JRE does not have support for Thai segmentation");
    handlePosIncr = matchVersion.onOrAfter(Version.LUCENE_3_1);
  }
View Full Code Here
76
77
78
79
80
81
82
83
84
85
86
      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);
    if (stopSet != null)
      result = new StopFilter(matchVersion,
                              result, stopSet);
    result = new SnowballFilter(result, name);
    return new TokenStreamComponents(tokenizer, result);
View Full Code Here
136
137
138
139
140
141
142
143
144
145
146
    final Tokenizer source = new StandardTokenizer(matchVersion, reader);
    TokenStream result = new StandardFilter(matchVersion, source);
    if (matchVersion.onOrAfter(Version.LUCENE_3_6)) {
      result = new ElisionFilter(result, DEFAULT_ARTICLES);
    }
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new CatalanStemmer());
    return new TokenStreamComponents(source, result);
View Full Code Here
186
187
188
189
190
191
192
193
194
195
196
  protected TokenStreamComponents createComponents(String fieldName,
      Reader aReader) {
    if (matchVersion.onOrAfter(Version.LUCENE_3_1)) {
      final Tokenizer source = new StandardTokenizer(matchVersion, aReader);
      TokenStream result = new StandardFilter(matchVersion, source);
      result = new LowerCaseFilter(matchVersion, result);
      result = new StopFilter(matchVersion, result, stoptable);
      if (!excltable.isEmpty())
        result = new SetKeywordMarkerFilter(result, excltable);
      if (stemdict != null)
        result = new StemmerOverrideFilter(result, stemdict);
View Full Code Here
137
138
139
140
141
142
143
144
145
146
147
  @Override
  protected TokenStreamComponents createComponents(String fieldName,
      Reader reader) {
    final Tokenizer source = matchVersion.onOrAfter(Version.LUCENE_3_1) ?
        new StandardTokenizer(matchVersion, reader) : new ArabicLetterTokenizer(matchVersion, reader);
    TokenStream result = new LowerCaseFilter(matchVersion, source);
    // the order here is important: the stopword list is not normalized!
    result = new StopFilter( matchVersion, result, stopwords);
    // TODO maybe we should make ArabicNormalization filter also KeywordAttribute aware?!
    result = new ArabicNormalizationFilter(result);
    if(!stemExclusionSet.isEmpty()) {
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.