Examples of org.apache.commons.codec.language.bm.PhoneticEngine$RulesApplication

Package org.apache.commons.codec.language.bm

Examples of org.apache.commons.codec.language.bm.PhoneticEngine$RulesApplication

org.apache.commons.codec.language.bm.PhoneticEngine
A function closure capturing the application of a list of rules to an input sequence at a particular offset. After invocation, the values i and found are updated. i points to the index of the next char in input that must be processed next (the input up to that index having been processed already), and found indicates if a matching rule was found or not. In the case where a matching rule was found, phonemeBuilder is replaced with a new builder containing the phonemes updated by the matching rule. Although this class is not thread-safe (it has mutable unprotected fields), it is not shared between threads as it is constructed as needed by the calling methods. @since 1.6

      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
        return new TokenStreamComponents(tokenizer, 
            new BeiderMorseFilter(tokenizer, 
                new PhoneticEngine(NameType.GENERIC, RuleType.EXACT, true), languages));
      }
    };
    assertAnalyzesTo(analyzer, "Angelo",
        new String[] { "andZelo", "angelo", "anxelo" },
        new int[] { 0, 0, 0, },

View Full Code Here

  public void testEmptyTerm() throws IOException {
    Analyzer a = new Analyzer() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        return new TokenStreamComponents(tokenizer, new BeiderMorseFilter(tokenizer, new PhoneticEngine(NameType.GENERIC, RuleType.EXACT, true)));
      }
    };
    checkOneTerm(a, "", "");
  }

View Full Code Here

  }
  
  public void testCustomAttribute() throws IOException {
    TokenStream stream = new KeywordTokenizer(new StringReader("D'Angelo"));
    stream = new PatternKeywordMarkerFilter(stream, Pattern.compile(".*"));
    stream = new BeiderMorseFilter(stream, new PhoneticEngine(NameType.GENERIC, RuleType.EXACT, true));
    KeywordAttribute keyAtt = stream.addAttribute(KeywordAttribute.class);
    stream.reset();
    int i = 0;
    while(stream.incrementToken()) {
      assertTrue(keyAtt.isKeyword());

View Full Code Here

    public TokenStream create(TokenStream tokenStream) {
        if (encoder == null) {
            if (ruletype != null && nametype != null) {
                if (languageset != null) {
                    final LanguageSet languages = LanguageSet.from(new HashSet(Arrays.asList(languageset)));
                    return new BeiderMorseFilter(tokenStream, new PhoneticEngine(nametype, ruletype, true), languages);
                }
                return new BeiderMorseFilter(tokenStream, new PhoneticEngine(nametype, ruletype, true));
            }
            if (maxcodelength > 0) {
                return new DoubleMetaphoneFilter(tokenStream, maxcodelength, !replace);
            }
        } else {

View Full Code Here

      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
        return new TokenStreamComponents(tokenizer, 
            new BeiderMorseFilter(tokenizer, 
                new PhoneticEngine(NameType.GENERIC, RuleType.EXACT, true), languages));
      }
    };
    assertAnalyzesTo(analyzer, "Angelo",
        new String[] { "andZelo", "angelo", "anxelo" },
        new int[] { 0, 0, 0, },

View Full Code Here

  public void testEmptyTerm() throws IOException {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        return new TokenStreamComponents(tokenizer, new BeiderMorseFilter(tokenizer, new PhoneticEngine(NameType.GENERIC, RuleType.EXACT, true)));
      }
    };
    checkOneTermReuse(a, "", "");
  }

View Full Code Here

0 1

TOP

Related Classes of org.apache.commons.codec.language.bm.PhoneticEngine$RulesApplication

org.apache.commons.codec.language.bm.Languages.LanguageSet

org.apache.commons.codec.language.bm.Rule.Phoneme

org.apache.lucene.analysis.phonetic.BeiderMorseFilterFactory

org.apache.lucene.analysis.phonetic.TestBeiderMorseFilter

org.elasticsearch.index.analysis.PhoneticTokenFilterFactory

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.