Examples of org.apache.lucene.analysis.core.WhitespaceTokenizer

org.apache.lucene.analysis.core.WhitespaceTokenizer
A WhitespaceTokenizer is a tokenizer that divides text at whitespace. Adjacent sequences of non-Whitespace characters form tokens.
You must specify the required {@link Version} compatibility when creating{@link WhitespaceTokenizer}:
- As of 3.1, {@link CharTokenizer} uses an int based API to normalize anddetect token characters. See {@link CharTokenizer#isTokenChar(int)} and{@link CharTokenizer#normalize(int)} for details.

    TokenStream filter = new DoubleMetaphoneFilter(stream, 8, true);
    assertTokenStreamContents(filter, new String[] { "12345", "#$%@#^%&" });
  }


  public void testNonConvertableStringsWithoutInject() throws Exception {
    TokenStream stream = new WhitespaceTokenizer(TEST_VERSION_CURRENT, new StringReader("12345 #$%@#^%&"));
    TokenStream filter = new DoubleMetaphoneFilter(stream, 8, false);
    assertTokenStreamContents(filter, new String[] { "12345", "#$%@#^%&" });
    
    // should have something after the stream
    stream = new WhitespaceTokenizer(TEST_VERSION_CURRENT, new StringReader("12345 #$%@#^%& hello"));
    filter = new DoubleMetaphoneFilter(stream, 8, false);
    assertTokenStreamContents(filter, new String[] { "12345", "#$%@#^%&", "HL" });
  }

View Full Code Here

     * convenience to show the behavior of the filter.
     */
    private class JustChineseFilterAnalyzer extends Analyzer {
      @Override
      public TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new WhitespaceTokenizer(Version.LUCENE_CURRENT, reader);
        return new TokenStreamComponents(tokenizer, new ChineseFilter(tokenizer));
      }

View Full Code Here


  public void testTokenEndingWithWordComponentOfMinimumLength() throws Exception {
    CharArraySet dict = makeDictionary("ab", "cd", "ef");


    DictionaryCompoundWordTokenFilter tf = new DictionaryCompoundWordTokenFilter(TEST_VERSION_CURRENT,
      new WhitespaceTokenizer(TEST_VERSION_CURRENT,
        new StringReader(
          "abcdef")
        ),
      dict,
      CompoundWordTokenFilterBase.DEFAULT_MIN_WORD_SIZE,

View Full Code Here


  public void testWordComponentWithLessThanMinimumLength() throws Exception {
    CharArraySet dict = makeDictionary("abc", "d", "efg");


    DictionaryCompoundWordTokenFilter tf = new DictionaryCompoundWordTokenFilter(TEST_VERSION_CURRENT,
      new WhitespaceTokenizer(TEST_VERSION_CURRENT,
        new StringReader(
          "abcdefg")
        ),
      dict,
      CompoundWordTokenFilterBase.DEFAULT_MIN_WORD_SIZE,

View Full Code Here


  public void testReset() throws Exception {
    CharArraySet dict = makeDictionary("Rind", "Fleisch", "Draht", "Schere", "Gesetz",
        "Aufgabe", "Überwachung");


    Tokenizer wsTokenizer = new WhitespaceTokenizer(TEST_VERSION_CURRENT, new StringReader(
        "Rindfleischüberwachungsgesetz"));
    DictionaryCompoundWordTokenFilter tf = new DictionaryCompoundWordTokenFilter(TEST_VERSION_CURRENT, 
        wsTokenizer, dict,
        CompoundWordTokenFilterBase.DEFAULT_MIN_WORD_SIZE,
        CompoundWordTokenFilterBase.DEFAULT_MIN_SUBWORD_SIZE,
        CompoundWordTokenFilterBase.DEFAULT_MAX_SUBWORD_SIZE, false);
    
    CharTermAttribute termAtt = tf.getAttribute(CharTermAttribute.class);
    tf.reset();
    assertTrue(tf.incrementToken());
    assertEquals("Rindfleischüberwachungsgesetz", termAtt.toString());
    assertTrue(tf.incrementToken());
    assertEquals("Rind", termAtt.toString());
    wsTokenizer.setReader(new StringReader("Rindfleischüberwachungsgesetz"));
    tf.reset();
    assertTrue(tf.incrementToken());
    assertEquals("Rindfleischüberwachungsgesetz", termAtt.toString());
  }

View Full Code Here

    assertEquals("Rindfleischüberwachungsgesetz", termAtt.toString());
  }


  public void testRetainMockAttribute() throws Exception {
    CharArraySet dict = makeDictionary("abc", "d", "efg");
    Tokenizer tokenizer = new WhitespaceTokenizer(TEST_VERSION_CURRENT,
        new StringReader("abcdefg"));
    TokenStream stream = new MockRetainAttributeFilter(tokenizer);
    stream = new DictionaryCompoundWordTokenFilter(
        TEST_VERSION_CURRENT, stream, dict,
        CompoundWordTokenFilterBase.DEFAULT_MIN_WORD_SIZE,

View Full Code Here

    final TokenizerFactory factory = tokenizerFactory == null ? null : loadTokenizerFactory(loader, tokenizerFactory);
    
    Analyzer analyzer = new Analyzer() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = factory == null ? new WhitespaceTokenizer(Version.LUCENE_43, reader) : factory.create(reader);
        TokenStream stream = ignoreCase ? new LowerCaseFilter(Version.LUCENE_43, tokenizer) : tokenizer;
        return new TokenStreamComponents(tokenizer, stream);
      }
    };

View Full Code Here

      "s", "a", "b", "c", "d", "the", "of"
  ), false);
  
  public void testReset() throws Exception {
    final String input = "How the s a brown s cow d like A B thing?";
    WhitespaceTokenizer wt = new WhitespaceTokenizer(TEST_VERSION_CURRENT, new StringReader(input));
    CommonGramsFilter cgf = new CommonGramsFilter(TEST_VERSION_CURRENT, wt, commonWords);
    
    CharTermAttribute term = cgf.addAttribute(CharTermAttribute.class);
    cgf.reset();
    assertTrue(cgf.incrementToken());
    assertEquals("How", term.toString());
    assertTrue(cgf.incrementToken());
    assertEquals("How_the", term.toString());
    assertTrue(cgf.incrementToken());
    assertEquals("the", term.toString());
    assertTrue(cgf.incrementToken());
    assertEquals("the_s", term.toString());
    
    wt.setReader(new StringReader(input));
    cgf.reset();
    assertTrue(cgf.incrementToken());
    assertEquals("How", term.toString());
  }

View Full Code Here

    assertEquals("How", term.toString());
  }
  
  public void testQueryReset() throws Exception {
    final String input = "How the s a brown s cow d like A B thing?";
    WhitespaceTokenizer wt = new WhitespaceTokenizer(TEST_VERSION_CURRENT, new StringReader(input));
    CommonGramsFilter cgf = new CommonGramsFilter(TEST_VERSION_CURRENT, wt, commonWords);
    CommonGramsQueryFilter nsf = new CommonGramsQueryFilter(cgf);
    
    CharTermAttribute term = wt.addAttribute(CharTermAttribute.class);
    nsf.reset();
    assertTrue(nsf.incrementToken());
    assertEquals("How_the", term.toString());
    assertTrue(nsf.incrementToken());
    assertEquals("the_s", term.toString());
    
    wt.setReader(new StringReader(input));
    nsf.reset();
    assertTrue(nsf.incrementToken());
    assertEquals("How_the", term.toString());
  }

View Full Code Here

    EdgeNGramTokenFilter tokenizer = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, input, EdgeNGramTokenFilter.Side.FRONT, 3, 3);
    assertTokenStreamContents(tokenizer, new String[]{"abc","fgh"}, new int[]{0,7}, new int[]{3,10});
  }
  
  public void testReset() throws Exception {
    WhitespaceTokenizer tokenizer = new WhitespaceTokenizer(TEST_VERSION_CURRENT, new StringReader("abcde"));
    EdgeNGramTokenFilter filter = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, tokenizer, EdgeNGramTokenFilter.Side.FRONT, 1, 3);
    assertTokenStreamContents(filter, new String[]{"a","ab","abc"}, new int[]{0,0,0}, new int[]{5,5,5});
    tokenizer.setReader(new StringReader("abcde"));
    assertTokenStreamContents(filter, new String[]{"a","ab","abc"}, new int[]{0,0,0}, new int[]{5,5,5});
  }

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.lucene.analysis.core.WhitespaceTokenizer

cc.twittertools.index.TweetAnalyzer

cc.twittertools.search.indexing.TweetAnalyzer

cc.twittertools.udf.LuceneTokenizer

de.arago.lucene.util.LowCaseAnalyzer

org.apache.jackrabbit.oak.plugins.index.lucene.OakAnalyzer

org.apache.lucene.analysis.cn.smart.TestSmartChineseFactories

org.apache.lucene.analysis.cn.TestChineseTokenizer$JustChineseFilterAnalyzer

org.apache.lucene.analysis.commongrams.CommonGramsFilterTest

org.apache.lucene.analysis.compound.TestCompoundWordTokenFilter

org.apache.lucene.analysis.core.WhitespaceTokenizerFactory

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.