Package org.apache.lucene.analysis

Examples of org.apache.lucene.analysis.WhitespaceTokenizer

31
32
33
34
35
36
37
38
39
40
  /**
   * Ensure the filter actually stems text.
   */
  public void testStemming() throws Exception {
    Reader reader = new StringReader("angličtí");
    Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
    CzechStemFilterFactory factory = new CzechStemFilterFactory();
    TokenStream stream = factory.create(tokenizer);
    assertTokenStreamContents(stream, new String[] { "anglick" });
  }
View Full Code Here
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
  private static final String[] commonWords = { "s", "a", "b", "c", "d", "the",
      "of" };
 
  public void testReset() throws Exception {
    final String input = "How the s a brown s cow d like A B thing?";
    WhitespaceTokenizer wt = new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader(input));
    CommonGramsFilter cgf = new CommonGramsFilter(wt, commonWords);
   
    CharTermAttribute term = cgf.addAttribute(CharTermAttribute.class);
    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.reset(new StringReader(input));
    cgf.reset();
    assertTrue(cgf.incrementToken());
    assertEquals("How", term.toString());
  }
View Full Code Here
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
    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(DEFAULT_VERSION, new StringReader(input));
    CommonGramsFilter cgf = new CommonGramsFilter(wt, commonWords);
    CommonGramsQueryFilter nsf = new CommonGramsQueryFilter(cgf);
   
    CharTermAttribute term = wt.addAttribute(CharTermAttribute.class);
    assertTrue(nsf.incrementToken());
    assertEquals("How_the", term.toString());
    assertTrue(nsf.incrementToken());
    assertEquals("the_s", term.toString());
   
    wt.reset(new StringReader(input));
    nsf.reset();
    assertTrue(nsf.incrementToken());
    assertEquals("How_the", term.toString());
  }
View Full Code Here
28
29
30
31
32
33
34
35
*/
public class TestPortugueseMinimalStemFilterFactory extends BaseTokenTestCase {
  public void testStemming() throws Exception {
    Reader reader = new StringReader("questões");
    PortugueseMinimalStemFilterFactory factory = new PortugueseMinimalStemFilterFactory();
    TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
    assertTokenStreamContents(stream, new String[] { "questão" });
  }
View Full Code Here
75
76
77
78
79
80
81
82
83
84
    factory.init(args);
    factory.inform(loader);
    Set<?> words = factory.getCommonWords();
    assertTrue("words is null and it shouldn't be", words != null);
    assertTrue(words.contains("the"));
    Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader("testing the factory"));
    TokenStream stream = factory.create(tokenizer);
    assertTokenStreamContents(stream,
        new String[] { "testing", "testing_the", "the", "the_factory", "factory" });
  }
View Full Code Here
38
39
40
41
42
43
44
45
46
47
48
    DelimitedPayloadTokenFilterFactory factory = new DelimitedPayloadTokenFilterFactory();
    factory.init(args);
    ResourceLoader loader = new SolrResourceLoader(null, null);
    factory.inform(loader);

    TokenStream input = new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader("the|0.1 quick|0.1 red|0.1"));
    DelimitedPayloadTokenFilter tf = factory.create(input);
    while (tf.incrementToken()){
      PayloadAttribute payAttr = tf.getAttribute(PayloadAttribute.class);
      assertTrue("payAttr is null and it shouldn't be", payAttr != null);
      byte[] payData = payAttr.getPayload().getData();
View Full Code Here
60
61
62
63
64
65
66
67
68
69
70
    DelimitedPayloadTokenFilterFactory factory = new DelimitedPayloadTokenFilterFactory();
    factory.init(args);
    ResourceLoader loader = new SolrResourceLoader(null, null);
    factory.inform(loader);

    TokenStream input = new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader("the*0.1 quick*0.1 red*0.1"));
    DelimitedPayloadTokenFilter tf = factory.create(input);
    while (tf.incrementToken()){
      PayloadAttribute payAttr = tf.getAttribute(PayloadAttribute.class);
      assertTrue("payAttr is null and it shouldn't be", payAttr != null);
      byte[] payData = payAttr.getPayload().getData();
View Full Code Here
28
29
30
31
32
33
34
35
*/
public class TestKStemFilterFactory extends BaseTokenTestCase {
  public void testStemming() throws Exception {
    Reader reader = new StringReader("bricks");
    KStemFilterFactory factory = new KStemFilterFactory();
    TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
    assertTokenStreamContents(stream, new String[] { "brick" });
  }
View Full Code Here
31
32
33
34
35
36
37
38
39
40
  /**
   * Ensure the filter actually stems text.
   */
  public void testStemming() throws Exception {
    Reader reader = new StringReader("lichamelijkheden");
    Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
    DutchStemFilterFactory factory = new DutchStemFilterFactory();
    TokenStream stream = factory.create(tokenizer);
    assertTokenStreamContents(stream, new String[] { "licham" });
  }
View Full Code Here
28
29
30
31
32
33
34
35
*/
public class TestGermanMinimalStemFilterFactory extends BaseTokenTestCase {
  public void testStemming() throws Exception {
    Reader reader = new StringReader("bilder");
    GermanMinimalStemFilterFactory factory = new GermanMinimalStemFilterFactory();
    TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
    assertTokenStreamContents(stream, new String[] { "bild" });
  }
View Full Code Here
TOP

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

  • org.apache.james.mailbox.store.lucene.ImapSearchAnalyzer
  • org.apache.lucene.analysis.cn.TestChineseTokenizer$JustChineseFilterAnalyzer
  • org.apache.lucene.analysis.compound.TestCompoundWordTokenFilter
  • org.apache.lucene.analysis.de.TestGermanStemFilter$GermanSubclassAnalyzer
  • org.apache.lucene.analysis.icu.TestICUNormalizer2Filter
  • org.apache.lucene.analysis.icu.TestICUTransformFilter
  • org.apache.lucene.analysis.miscellaneous.TestPrefixAndSuffixAwareTokenFilter
  • org.apache.lucene.analysis.miscellaneous.TestPrefixAwareTokenFilter
  • org.apache.lucene.analysis.ngram.EdgeNGramTokenFilterTest
  • org.apache.lucene.analysis.ngram.NGramTokenFilterTest
    • 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.