Package org.apache.lucene.analysis.util

Examples of org.apache.lucene.analysis.util.ClasspathResourceLoader

116
117
118
119
120
121
122
123
124
   */
  public void testFactoryReflectionCaverphone2() throws IOException {
    Map<String,String> args = new HashMap<>();
    args.put(PhoneticFilterFactory.ENCODER, "Caverphone2");
    PhoneticFilterFactory factory = new PhoneticFilterFactory(args);
    factory.inform(new ClasspathResourceLoader(factory.getClass()));
    assertTrue(factory.getEncoder() instanceof Caverphone2);
    assertTrue(factory.inject); // default
  }
View Full Code Here
125
126
127
128
129
130
131
132
133
 
  public void testFactoryReflectionCaverphone() throws IOException {
    Map<String,String> args = new HashMap<>();
    args.put(PhoneticFilterFactory.ENCODER, "Caverphone");
    PhoneticFilterFactory factory = new PhoneticFilterFactory(args);
    factory.inform(new ClasspathResourceLoader(factory.getClass()));
    assertTrue(factory.getEncoder() instanceof Caverphone2);
    assertTrue(factory.inject); // default
  }
View Full Code Here
184
185
186
187
188
189
190
191
192
    Tokenizer tokenizer = new MockTokenizer(new StringReader(input), MockTokenizer.WHITESPACE, false);
    Map<String,String> args = new HashMap<>();
    args.put("encoder", algName);
    args.put("inject", inject);
    PhoneticFilterFactory factory = new PhoneticFilterFactory(args);
    factory.inform(new ClasspathResourceLoader(factory.getClass()));
    TokenStream stream = factory.create(tokenizer);
    assertTokenStreamContents(stream, expected);
  }
View Full Code Here
164
165
166
167
168
169
170
171
172
    TokenStream stream = tokenizerFactory("UAX29URLEmail").create(reader);
    assertTokenStreamContents(stream,
        new String[] {"ざ"});
   
    reader = new StringReader("ざ");
    stream = tokenizerFactory("UAX29URLEmail", Version.LUCENE_31, new ClasspathResourceLoader(getClass())).create(reader);
    assertTokenStreamContents(stream,
        new String[] {"さ"}); // old broken behavior
  }
View Full Code Here
310
311
312
313
314
315
316
317
318
      } else {
        throw e;
      }
    }
    if (factory instanceof ResourceLoaderAware) {
      ((ResourceLoaderAware) factory).inform(new ClasspathResourceLoader(getClass()));
    }
    return factory;
  }
View Full Code Here
23
24
25
26
27
28
29
30
31
32
33
import org.apache.lucene.analysis.util.ResourceLoader;

public class TestKeepFilterFactory extends BaseTokenStreamFactoryTestCase {

  public void testInform() throws Exception {
    ResourceLoader loader = new ClasspathResourceLoader(getClass());
    assertTrue("loader is null and it shouldn't be", loader != null);
    KeepWordFilterFactory factory = (KeepWordFilterFactory) tokenFilterFactory("KeepWord",
        "words", "keep-1.txt",
        "ignoreCase", "true");
    CharArraySet words = factory.getWords();
View Full Code Here
34
35
36
37
38
39
40
41
42
43
44
* so this won't break if stop filter test files change
**/
public class TestCommonGramsFilterFactory extends BaseTokenStreamFactoryTestCase {

  public void testInform() throws Exception {
    ResourceLoader loader = new ClasspathResourceLoader(TestStopFilter.class);
    assertTrue("loader is null and it shouldn't be", loader != null);
    CommonGramsFilterFactory factory = (CommonGramsFilterFactory) tokenFilterFactory("CommonGrams", TEST_VERSION_CURRENT, loader,
        "words", "stop-1.txt",
        "ignoreCase", "true");
    CharArraySet words = factory.getCommonWords();
View Full Code Here
29
30
31
32
33
34
35
36
37
38
39
/** basic tests for {@link ICUTokenizerFactory} **/
public class TestICUTokenizerFactory extends BaseTokenStreamTestCase {
  public void testMixedText() throws Exception {
    Reader reader = new StringReader("การที่ได้ต้องแสดงว่างานดี  This is a test ກວ່າດອກ");
    ICUTokenizerFactory factory = new ICUTokenizerFactory(new HashMap<String,String>());
    factory.inform(new ClasspathResourceLoader(getClass()));
    TokenStream stream = factory.create(reader);
    assertTokenStreamContents(stream,
        new String[] { "การ", "ที่", "ได้", "ต้อง", "แสดง", "ว่า", "งาน", "ดี",
        "This", "is", "a", "test", "ກວ່າ", "ດອກ"});
  }
View Full Code Here
43
44
45
46
47
48
49
50
51
52
53
    Reader reader = new StringReader
        ("  Don't,break.at?/(punct)!  \u201Cnice\u201D\r\n\r\n85_At:all; `really\" +2=3$5,&813 !@#%$^)(*@#$   ");
    final Map<String,String> args = new HashMap<>();
    args.put(ICUTokenizerFactory.RULEFILES, "Latn:Latin-break-only-on-whitespace.rbbi");
    ICUTokenizerFactory factory = new ICUTokenizerFactory(args);
    factory.inform(new ClasspathResourceLoader(this.getClass()));
    TokenStream stream = factory.create(reader);
    assertTokenStreamContents(stream,
        new String[] { "Don't,break.at?/(punct)!", "\u201Cnice\u201D", "85_At:all;", "`really\"",  "+2=3$5,&813", "!@#%$^)(*@#$" },
        new String[] { "<ALPHANUM>",               "<ALPHANUM>",       "<ALPHANUM>", "<ALPHANUM>", "<NUM>",       "<OTHER>" });
  }
View Full Code Here
56
57
58
59
60
61
62
63
64
65
66
    Reader reader = new StringReader
        ("One-two punch.  Brang-, not brung-it.  This one--not that one--is the right one, -ish.");
    final Map<String,String> args = new HashMap<>();
    args.put(ICUTokenizerFactory.RULEFILES, "Latn:Latin-dont-break-on-hyphens.rbbi");
    ICUTokenizerFactory factory = new ICUTokenizerFactory(args);
    factory.inform(new ClasspathResourceLoader(getClass()));
    TokenStream stream = factory.create(reader);
    assertTokenStreamContents(stream,
        new String[] { "One-two", "punch",
            "Brang", "not", "brung-it",
            "This", "one", "not", "that", "one", "is", "the", "right", "one", "ish" });
View Full Code Here
TOP

Related Classes of org.apache.lucene.analysis.util.ClasspathResourceLoader

  • org.apache.lucene.analysis.commongrams.TestCommonGramsFilterFactory
  • org.apache.lucene.analysis.commongrams.TestCommonGramsQueryFilterFactory
  • org.apache.lucene.analysis.compound.TestDictionaryCompoundWordTokenFilterFactory
  • org.apache.lucene.analysis.compound.TestHyphenationCompoundWordTokenFilterFactory
  • org.apache.lucene.analysis.core.TestFactories
  • org.apache.lucene.analysis.core.TestStopFilterFactory
  • org.apache.lucene.analysis.core.TestTypeTokenFilterFactory
  • org.apache.lucene.analysis.hunspell.TestHunspellStemFilterFactory
  • org.apache.lucene.analysis.icu.segmentation.TestICUTokenizerFactory
  • org.apache.lucene.analysis.miscellaneous.TestKeepFilterFactory
    • 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.