Examples of CapitalizationFilter

org.apache.lucene.analysis.miscellaneous.CapitalizationFilter
A filter to apply normal capitalization rules to Tokens. It will make the first letter capital and the rest lower case.
This filter is particularly useful to build nice looking facet parameters. This filter is not appropriate if you intend to use a prefix query.

Examples of org.apache.lucene.analysis.miscellaneous.CapitalizationFilter

  
  static void assertCapitalizesTo(Tokenizer tokenizer, String expected[],
      boolean onlyFirstWord, CharArraySet keep, boolean forceFirstLetter,
      Collection<char[]> okPrefix, int minWordLength, int maxWordCount,
      int maxTokenLength) throws IOException {
    CapitalizationFilter filter = new CapitalizationFilter(tokenizer, onlyFirstWord, keep, 
        forceFirstLetter, okPrefix, minWordLength, maxWordCount, maxTokenLength);
    assertTokenStreamContents(filter, expected);    
  }

View Full Code Here

Examples of org.apache.lucene.analysis.miscellaneous.CapitalizationFilter

    Analyzer a = new Analyzer() {


      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
        return new TokenStreamComponents(tokenizer, new CapitalizationFilter(tokenizer));
      }
    };
    
    checkRandomData(random(), a, 1000*RANDOM_MULTIPLIER);
  }

View Full Code Here

Examples of org.apache.lucene.analysis.miscellaneous.CapitalizationFilter

  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 CapitalizationFilter(tokenizer));
      }
    };
    checkOneTerm(a, "", "");
  }

View Full Code Here

Examples of org.apache.lucene.analysis.miscellaneous.CapitalizationFilter

    }
  }


  @Override
  public CapitalizationFilter create(TokenStream input) {
    return new CapitalizationFilter(input, onlyFirstWord, keep, 
      forceFirstLetter, okPrefix, minWordLength, maxWordCount, maxTokenLength);
  }

View Full Code Here

Examples of org.apache.lucene.analysis.miscellaneous.CapitalizationFilter

  
  static void assertCapitalizesTo(Tokenizer tokenizer, String expected[],
      boolean onlyFirstWord, CharArraySet keep, boolean forceFirstLetter,
      Collection<char[]> okPrefix, int minWordLength, int maxWordCount,
      int maxTokenLength) throws IOException {
    CapitalizationFilter filter = new CapitalizationFilter(tokenizer, onlyFirstWord, keep, 
        forceFirstLetter, okPrefix, minWordLength, maxWordCount, maxTokenLength);
    assertTokenStreamContents(filter, expected);    
  }

View Full Code Here

Examples of org.apache.lucene.analysis.miscellaneous.CapitalizationFilter

    Analyzer a = new Analyzer() {


      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
        return new TokenStreamComponents(tokenizer, new CapitalizationFilter(tokenizer));
      }
    };
    
    checkRandomData(random(), a, 1000*RANDOM_MULTIPLIER);
  }

View Full Code Here

Examples of org.apache.lucene.analysis.miscellaneous.CapitalizationFilter

  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 CapitalizationFilter(tokenizer));
      }
    };
    checkOneTerm(a, "", "");
  }

View Full Code Here

Examples of org.apache.lucene.analysis.miscellaneous.CapitalizationFilter

  /**
   * checking the validity of constructor arguments
   */
  @Test(expected = IllegalArgumentException.class)
  public void testIllegalArguments() throws Exception {
    new CapitalizationFilter(new MockTokenizer(new StringReader("accept only valid arguments"), MockTokenizer.WHITESPACE, false),true, null, true, null, -1 , DEFAULT_MAX_WORD_COUNT, DEFAULT_MAX_TOKEN_LENGTH);
  }

View Full Code Here

Examples of org.apache.lucene.analysis.miscellaneous.CapitalizationFilter

  public void testIllegalArguments() throws Exception {
    new CapitalizationFilter(new MockTokenizer(new StringReader("accept only valid arguments"), MockTokenizer.WHITESPACE, false),true, null, true, null, -1 , DEFAULT_MAX_WORD_COUNT, DEFAULT_MAX_TOKEN_LENGTH);
  }
  @Test(expected = IllegalArgumentException.class)
  public void testIllegalArguments1() throws Exception {
    new CapitalizationFilter(new MockTokenizer(new StringReader("accept only valid arguments"), MockTokenizer.WHITESPACE, false),true, null, true, null, 0 , -10, DEFAULT_MAX_TOKEN_LENGTH);
  }

View Full Code Here

Examples of org.apache.lucene.analysis.miscellaneous.CapitalizationFilter

  public void testIllegalArguments1() throws Exception {
    new CapitalizationFilter(new MockTokenizer(new StringReader("accept only valid arguments"), MockTokenizer.WHITESPACE, false),true, null, true, null, 0 , -10, DEFAULT_MAX_TOKEN_LENGTH);
  }
  @Test(expected = IllegalArgumentException.class)
  public void testIllegalArguments2() throws Exception {
    new CapitalizationFilter(new MockTokenizer(new StringReader("accept only valid arguments"), MockTokenizer.WHITESPACE, false),true, null, true, null, 0 , DEFAULT_MAX_WORD_COUNT, -50);
  }

View Full Code Here

0 1

TOP

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.