Examples of IndicNormalizationFilterFactory

Examples of org.apache.lucene.analysis.in.IndicNormalizationFilterFactory

37
38
39
40
41
42
43
44
45
46
47
48
49
50
   */
  public void testIndicNormalizer() throws Exception {
    Reader reader = new StringReader("ত্‍ अाैर");
    StandardTokenizerFactory factory = new StandardTokenizerFactory();
    factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
    IndicNormalizationFilterFactory filterFactory = new IndicNormalizationFilterFactory();
    filterFactory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
    Map<String, String> args = Collections.emptyMap();
    factory.init(args);
    filterFactory.init(args);
    Tokenizer tokenizer = factory.create(reader);
    TokenStream stream = filterFactory.create(tokenizer);
    assertTokenStreamContents(stream, new String[] { "ৎ", "और" });
  }
View Full Code Here

Examples of org.apache.lucene.analysis.in.IndicNormalizationFilterFactory

54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
   */
  public void testHindiNormalizer() throws Exception {
    Reader reader = new StringReader("क़िताब");
    StandardTokenizerFactory factory = new StandardTokenizerFactory();
    factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
    IndicNormalizationFilterFactory indicFilterFactory = new IndicNormalizationFilterFactory();
    HindiNormalizationFilterFactory hindiFilterFactory = new HindiNormalizationFilterFactory();
    hindiFilterFactory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
    Map<String, String> args = Collections.emptyMap();
    factory.init(args);
    hindiFilterFactory.init(args);
    Tokenizer tokenizer = factory.create(reader);
    TokenStream stream = indicFilterFactory.create(tokenizer);
    stream = hindiFilterFactory.create(stream);
    assertTokenStreamContents(stream, new String[] {"किताब"});
  }
View Full Code Here

Examples of org.apache.lucene.analysis.in.IndicNormalizationFilterFactory

73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
   */
  public void testStemmer() throws Exception {
    Reader reader = new StringReader("किताबें");
    StandardTokenizerFactory factory = new StandardTokenizerFactory();
    factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
    IndicNormalizationFilterFactory indicFilterFactory = new IndicNormalizationFilterFactory();
    HindiNormalizationFilterFactory hindiFilterFactory = new HindiNormalizationFilterFactory();
    HindiStemFilterFactory stemFactory = new HindiStemFilterFactory();
    stemFactory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
    Map<String, String> args = Collections.emptyMap();
    factory.init(args);
    stemFactory.init(args);
    Tokenizer tokenizer = factory.create(reader);
    TokenStream stream = indicFilterFactory.create(tokenizer);
    stream = hindiFilterFactory.create(stream);
    stream = stemFactory.create(stream);
    assertTokenStreamContents(stream, new String[] {"किताब"});
  }
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.