Package org.apache.lucene.analysis.synonym

Examples of org.apache.lucene.analysis.synonym.SynonymMap

69
70
71
72
73
74
75
76
77
78
79
    CharsRef multiWordCharsRef = new CharsRef();
    SynonymMap.Builder.join(new String[] { "and", "indubitably", "single", "only" }, multiWordCharsRef);
    builder.add(new CharsRef("one"), multiWordCharsRef, true);
    SynonymMap.Builder.join(new String[]{"dopple", "ganger"}, multiWordCharsRef);
    builder.add(new CharsRef("two"), multiWordCharsRef, true);
    SynonymMap synonymMap = builder.build();
    TokenStream stream = new SynonymFilter(tokenizer, synonymMap, true);
    stream = new LimitTokenPositionFilter(stream, 3); // consumeAllTokens defaults to false
   
    // "only", the 4th word of multi-word synonym "and indubitably single only" is not emitted, since its position is greater than 3.
    assertTokenStreamContents(stream,
View Full Code Here
149
150
151
152
153
154
155
156
157
158
159
      SynonymMap.Builder b = new SynonymMap.Builder(random().nextBoolean());
      final int numEntries = atLeast(10);
      for (int j = 0; j < numEntries; j++) {
        add(b, randomNonEmptyString(), randomNonEmptyString(), random().nextBoolean());
      }
      final SynonymMap map = b.build();
      final boolean ignoreCase = random().nextBoolean();
     
      final Analyzer analyzer = new Analyzer() {
        @Override
        protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
View Full Code Here
63
64
65
66
67
68
69
70
        }
        if (tokenizerFactoryFactory == null) {
            throw new ElasticSearchIllegalArgumentException("failed to fine tokenizer [" + tokenizerName + "] for synonym token filter");
        }
        TokenizerFactory tokenizerFactory = tokenizerFactoryFactory.create(tokenizerName, settings);
        synonymMap = new SynonymMap(ignoreCase);
        parseRules(rules, synonymMap, "=>", ",", expand, tokenizerFactory);
    }
View Full Code Here
149
150
151
152
153
154
155
156
157
158
159
      SynonymMap.Builder b = new SynonymMap.Builder(random().nextBoolean());
      final int numEntries = atLeast(10);
      for (int j = 0; j < numEntries; j++) {
        add(b, randomNonEmptyString(), randomNonEmptyString(), random().nextBoolean());
      }
      final SynonymMap map = b.build();
      final boolean ignoreCase = random().nextBoolean();
     
      final Analyzer analyzer = new Analyzer() {
        @Override
        protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
View Full Code Here
69
70
71
72
73
74
75
76
77
78
79
    CharsRef multiWordCharsRef = new CharsRef();
    SynonymMap.Builder.join(new String[] { "and", "indubitably", "single", "only" }, multiWordCharsRef);
    builder.add(new CharsRef("one"), multiWordCharsRef, true);
    SynonymMap.Builder.join(new String[]{"dopple", "ganger"}, multiWordCharsRef);
    builder.add(new CharsRef("two"), multiWordCharsRef, true);
    SynonymMap synonymMap = builder.build();
    TokenStream stream = new SynonymFilter(tokenizer, synonymMap, true);
    stream = new LimitTokenPositionFilter(stream, 3); // consumeAllTokens defaults to false
   
    // "only", the 4th word of multi-word synonym "and indubitably single only" is not emitted, since its position is greater than 3.
    assertTokenStreamContents(stream,
View Full Code Here
72
73
74
75
76
77
78
79
80
81
82
      CharsRef multiWordCharsRef = new CharsRef();
      SynonymMap.Builder.join(new String[]{"and", "indubitably", "single", "only"}, multiWordCharsRef);
      builder.add(new CharsRef("one"), multiWordCharsRef, true);
      SynonymMap.Builder.join(new String[]{"dopple", "ganger"}, multiWordCharsRef);
      builder.add(new CharsRef("two"), multiWordCharsRef, true);
      SynonymMap synonymMap = builder.build();
      TokenStream stream = new SynonymFilter(tokenizer, synonymMap, true);
      stream = new LimitTokenPositionFilter(stream, 3, consumeAll);

      // "only", the 4th word of multi-word synonym "and indubitably single only" is not emitted, since its position is greater than 3.
      assertTokenStreamContents(stream,
View Full Code Here
149
150
151
152
153
154
155
156
157
158
159
      SynonymMap.Builder b = new SynonymMap.Builder(random().nextBoolean());
      final int numEntries = atLeast(10);
      for (int j = 0; j < numEntries; j++) {
        add(b, randomNonEmptyString(), randomNonEmptyString(), random().nextBoolean());
      }
      final SynonymMap map = b.build();
      final boolean ignoreCase = random().nextBoolean();
     
      final Analyzer analyzer = new Analyzer() {
        @Override
        protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
View Full Code Here
TOP

Related Classes of org.apache.lucene.analysis.synonym.SynonymMap

  • org.apache.lucene.analysis.miscellaneous.TestLimitTokenPositionFilter
  • org.apache.lucene.analysis.miscellaneous.TestRemoveDuplicatesTokenFilter
  • org.apache.lucene.analysis.Token
  • org.apache.lucene.analysis.tokenattributes.CharTermAttribute
  • org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute
  • org.apache.lucene.analysis.TokenStream
  • org.apache.lucene.store.ByteArrayDataOutput
  • org.apache.lucene.util.BytesRef
  • org.apache.lucene.util.CharsRef
  • org.apache.lucene.util.fst.ByteSequenceOutputs
    • 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.