Package org.apache.lucene.analysis

Examples of org.apache.lucene.analysis.TokenStream$TokenWrapperAttributeFactory

188
189
190
191
192
193
194
195
196
197
198
    // Ideally the Analyzer superclass should have a method with the same signature,
    // with a default impl that simply delegates to the StringReader flavour.
    if (text == null)
      throw new IllegalArgumentException("text must not be null");
   
    TokenStream stream;
    if (pattern == NON_WORD_PATTERN) { // fast path
      stream = new FastStringTokenizer(text, true, toLowerCase, stopWords);
    }
    else if (pattern == WHITESPACE_PATTERN) { // fast path
      stream = new FastStringTokenizer(text, false, toLowerCase, stopWords);
View Full Code Here
196
197
198
199
200
201
202
203
204
205
206
   *       {@link LowerCaseFilter}, {@link StandardFilter}, {@link StopFilter}, and
   *          {@link BrazilianStemFilter}.
   */
  @Override
  public final TokenStream tokenStream(String fieldName, Reader reader) {
                TokenStream result = new StandardTokenizer( matchVersion, reader );
    result = new LowerCaseFilter( result );
    result = new StandardFilter( result );
    result = new StopFilter( StopFilter.getEnablePositionIncrementsVersionDefault(matchVersion),
                                         result, stoptable );
    result = new BrazilianStemFilter( result, excltable );
View Full Code Here
82
83
84
85
86
87
88
89
90
    this.collator = collator;
  }

  @Override
  public TokenStream tokenStream(String fieldName, Reader reader) {
    TokenStream result = new KeywordTokenizer(reader);
    result = new CollationKeyFilter(result, collator);
    return result;
  }
View Full Code Here
64
65
66
67
68
69
70
71
72
  private class PayloadAnalyzer extends Analyzer {


    @Override
    public TokenStream tokenStream(String fieldName, Reader reader) {
      TokenStream result = new LowerCaseTokenizer(reader);
      result = new PayloadFilter(result, fieldName);
      return result;
    }
View Full Code Here
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
  }

  public QueryTermVector(String queryString, Analyzer analyzer) {   
    if (analyzer != null)
    {
      TokenStream stream = analyzer.tokenStream("", new StringReader(queryString));
      if (stream != null)
      {
        List<String> terms = new ArrayList<String>();
        try {
          boolean hasMoreTokens = false;
         
          stream.reset();
          TermAttribute termAtt = stream.addAttribute(TermAttribute.class);

          hasMoreTokens = stream.incrementToken();
          while (hasMoreTokens) {
            terms.add(termAtt.term());
            hasMoreTokens = stream.incrementToken();
          }
          processTerms(terms.toArray(new String[terms.size()]));
        } catch (IOException e) {
        }
      }
View Full Code Here
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
      FieldQueryNode fieldNode = ((FieldQueryNode) node);
      String text = fieldNode.getTextAsString();
      String field = fieldNode.getFieldAsString();

      TokenStream source = this.analyzer.tokenStream(field, new StringReader(
          text));
      CachingTokenFilter buffer = new CachingTokenFilter(source);

      PositionIncrementAttribute posIncrAtt = null;
      int numTokens = 0;
      int positionCount = 0;
      boolean severalTokensAtSamePosition = false;

      if (buffer.hasAttribute(PositionIncrementAttribute.class)) {
        posIncrAtt = buffer.getAttribute(PositionIncrementAttribute.class);
      }

      try {

        while (buffer.incrementToken()) {
          numTokens++;
          int positionIncrement = (posIncrAtt != null) ? posIncrAtt
              .getPositionIncrement() : 1;
          if (positionIncrement != 0) {
            positionCount += positionIncrement;

          } else {
            severalTokensAtSamePosition = true;
          }

        }

      } catch (IOException e) {
        // ignore
      }

      try {
        // rewind the buffer stream
        buffer.reset();

        // close original stream - all tokens buffered
        source.close();
      } catch (IOException e) {
        // ignore
      }

      if (!buffer.hasAttribute(TermAttribute.class)) {
View Full Code Here
248
249
250
251
252
253
254
255
256
257
    if (text == null)
      throw new IllegalArgumentException("text must not be null");
    if (analyzer == null)
      throw new IllegalArgumentException("analyzer must not be null");
   
    TokenStream stream = analyzer.tokenStream(fieldName,
        new StringReader(text));

    addField(fieldName, stream);
  }
View Full Code Here
270
271
272
273
274
275
276
277
278
279
280
  public <T> TokenStream keywordTokenStream(final Collection<T> keywords) {
    // TODO: deprecate & move this method into AnalyzerUtil?
    if (keywords == null)
      throw new IllegalArgumentException("keywords must not be null");
   
    return new TokenStream() {
      private Iterator<T> iter = keywords.iterator();
      private int start = 0;
      private TermAttribute termAtt = addAttribute(TermAttribute.class);
      private OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
     
View Full Code Here
165
166
167
168
169
170
171
172
173
174
175
   *       {@link LowerCaseFilter}, {@link StopFilter}, {@link ArabicNormalizationFilter}
   *            and {@link ArabicStemFilter}.
   */
  @Override
  public final TokenStream tokenStream(String fieldName, Reader reader) {
    TokenStream result = new ArabicLetterTokenizer( reader );
    result = new LowerCaseFilter(result);
    // the order here is important: the stopword list is not normalized!
    result = new StopFilter( StopFilter.getEnablePositionIncrementsVersionDefault(matchVersion),
                             result, stoptable );
    result = new ArabicNormalizationFilter( result );
View Full Code Here
55
56
57
58
59
60
61
62
63
  }

  private class PayloadAnalyzer extends Analyzer {
    @Override
    public TokenStream tokenStream(String fieldName, Reader reader) {
      TokenStream result = new LowerCaseTokenizer(reader);
      result = new PayloadFilter(result, fieldName);
      return result;
    }
View Full Code Here
TOP

Related Classes of org.apache.lucene.analysis.TokenStream$TokenWrapperAttributeFactory

  • com.code972.elasticsearch.rest.action.RestHebrewAnalyzerCheckWordAction
  • com.gentics.cr.lucene.analysis.CustomPatternAnalyzerTest
  • com.github.pmerienne.trident.ml.preprocessing.EnglishTokenizer
  • com.o19s.RegexPathHierarchyTokenizerTest
  • com.stimulus.archiva.search.FileNameAnalyzer
  • com.stimulus.archiva.search.FileNameAnalyzer$LowercaseDelimiterAnalyzer
  • ivory.core.tokenize.LuceneAnalyzer
  • ivory.core.tokenize.LuceneArabicAnalyzer
  • ivory.core.tokenize.LuceneTokenizer
  • org.apache.jackrabbit.core.query.lucene.SearchIndex
    • 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.