Package org.apache.lucene.analysis

Examples of org.apache.lucene.analysis.WhitespaceTokenizer

27
28
29
30
31
32
33
34
35
36
37
public class DoubleMetaphoneFilterFactoryTest extends BaseTokenTestCase {

  public void testDefaults() throws Exception {
    DoubleMetaphoneFilterFactory factory = new DoubleMetaphoneFilterFactory();
    factory.init(new HashMap<String, String>());
    TokenStream inputStream = new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader("international"));

    TokenStream filteredStream = factory.create(inputStream);
    assertEquals(DoubleMetaphoneFilter.class, filteredStream.getClass());
    assertTokenStreamContents(filteredStream, new String[] { "international", "ANTR" });
  }
View Full Code Here
41
42
43
44
45
46
47
48
49
50
51
    Map<String, String> parameters = new HashMap<String, String>();
    parameters.put("inject", "false");
    parameters.put("maxCodeLength", "8");
    factory.init(parameters);

    TokenStream inputStream = new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader("international"));

    TokenStream filteredStream = factory.create(inputStream);
    assertEquals(DoubleMetaphoneFilter.class, filteredStream.getClass());
    assertTokenStreamContents(filteredStream, new String[] { "ANTRNXNL" });
  }
View Full Code Here
54
55
56
57
58
59
60
61
62
63
64
   * Ensure that reset() removes any state (buffered tokens)
   */
  public void testReset() throws Exception {
    DoubleMetaphoneFilterFactory factory = new DoubleMetaphoneFilterFactory();
    factory.init(new HashMap<String, String>());
    TokenStream inputStream = new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader("international"));

    TokenStream filteredStream = factory.create(inputStream);
    CharTermAttribute termAtt = filteredStream.addAttribute(CharTermAttribute.class);
    assertEquals(DoubleMetaphoneFilter.class, filteredStream.getClass());
   
View Full Code Here
31
32
33
34
35
36
37
38
39
40
41
  /**
   * Ensure the filter actually lowercases (and a bit more) greek text.
   */
  public void testNormalization() throws Exception {
    Reader reader = new StringReader("Μάϊος ΜΆΪΟΣ");
    Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
    GreekLowerCaseFilterFactory factory = new GreekLowerCaseFilterFactory();
    factory.init(DEFAULT_VERSION_PARAM);
    TokenStream stream = factory.create(tokenizer);
    assertTokenStreamContents(stream, new String[] { "μαιοσ", "μαιοσ" });
  }
View Full Code Here
28
29
30
31
32
33
34
35
*/
public class TestPortugueseLightStemFilterFactory extends BaseTokenTestCase {
  public void testStemming() throws Exception {
    Reader reader = new StringReader("evidentemente");
    PortugueseLightStemFilterFactory factory = new PortugueseLightStemFilterFactory();
    TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
    assertTokenStreamContents(stream, new String[] { "evident" });
  }
View Full Code Here
35
36
37
38
39
40
41
42
43
44
45
*/
public class TestStemmerOverrideFilterFactory extends BaseTokenTestCase {
  public void testKeywords() throws IOException {
    // our stemdict stems dogs to 'cat'
    Reader reader = new StringReader("testing dogs");
    Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
    StemmerOverrideFilterFactory factory = new StemmerOverrideFilterFactory();
    Map<String,String> args = new HashMap<String,String>(DEFAULT_VERSION_PARAM);
    ResourceLoader loader = new SolrResourceLoader(null, null);
    args.put("dictionary", "stemdict.txt");
    factory.init(args);
View Full Code Here
49
50
51
52
53
54
55
56
57
58
59
    assertTokenStreamContents(ts, new String[] { "test", "cat" });
  }
 
  public void testKeywordsCaseInsensitive() throws IOException {
    Reader reader = new StringReader("testing DoGs");
    Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
    StemmerOverrideFilterFactory factory = new StemmerOverrideFilterFactory();
    Map<String,String> args = new HashMap<String,String>(DEFAULT_VERSION_PARAM);
    ResourceLoader loader = new SolrResourceLoader(null, null);
    args.put("dictionary", "stemdict.txt");
    args.put("ignoreCase", "true");
View Full Code Here
35
36
37
38
39
40
41
42
43
44
45
  /**
   * Ensure the filter actually decompounds text.
   */
  public void testDecompounding() throws Exception {
    Reader reader = new StringReader("I like to play softball");
    Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
    DictionaryCompoundWordTokenFilterFactory factory = new DictionaryCompoundWordTokenFilterFactory();
    ResourceLoader loader = new SolrResourceLoader(null, null);
    Map<String,String> args = new HashMap<String,String>(DEFAULT_VERSION_PARAM);
    args.put("dictionary", "compoundDictionary.txt");
    factory.init(args);
View Full Code Here
28
29
30
31
32
33
34
35
*/
public class TestRussianLightStemFilterFactory extends BaseTokenTestCase {
  public void testStemming() throws Exception {
    Reader reader = new StringReader("журналы");
    RussianLightStemFilterFactory factory = new RussianLightStemFilterFactory();
    TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
    assertTokenStreamContents(stream, new String[] { "журнал" });
  }
View Full Code Here
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
    /* default behavior */
    factoryDefault.init(args);
    factoryDefault.inform(loader);
   
    TokenStream ts = factoryDefault.create(
        new WhitespaceTokenizer(BaseTokenTestCase.DEFAULT_VERSION, new StringReader(testText)));
    BaseTokenTestCase.assertTokenStreamContents(ts,
        new String[] { "I", "borrowed", "5", "400", "00", "540000", "at", "25", "interest", "rate", "interestrate" });

    ts = factoryDefault.create(
        new WhitespaceTokenizer(BaseTokenTestCase.DEFAULT_VERSION, new StringReader("foo\u200Dbar")));
    BaseTokenTestCase.assertTokenStreamContents(ts,
        new String[] { "foo", "bar", "foobar" });

   
    /* custom behavior */
    WordDelimiterFilterFactory factoryCustom = new WordDelimiterFilterFactory();
    // use a custom type mapping
    args.put("types", "wdftypes.txt");
    factoryCustom.init(args);
    factoryCustom.inform(loader);
   
    ts = factoryCustom.create(
        new WhitespaceTokenizer(BaseTokenTestCase.DEFAULT_VERSION, new StringReader(testText)));
    BaseTokenTestCase.assertTokenStreamContents(ts,
        new String[] { "I", "borrowed", "$5,400.00", "at", "25%", "interest", "rate", "interestrate" });
   
    /* test custom behavior with a char > 0x7F, because we had to make a larger byte[] */
    ts = factoryCustom.create(
        new WhitespaceTokenizer(BaseTokenTestCase.DEFAULT_VERSION, new StringReader("foo\u200Dbar")));
    BaseTokenTestCase.assertTokenStreamContents(ts,
        new String[] { "foo\u200Dbar" });
  }
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.