Package org.apache.lucene.analysis

Examples of org.apache.lucene.analysis.ReusableAnalyzerBase

32
33
34
35
36
37
38
39
40
41
42
* @deprecated Remove this test class (and its datafiles!) in Lucene 4.0
*/
@Deprecated
public class TestRussianStem extends LuceneTestCase {
  public void testStem() throws IOException {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName,
          Reader reader) {
        Tokenizer t = new KeywordTokenizer(reader);
        return new TokenStreamComponents(t, new RussianStemFilter(t));
View Full Code Here
36
37
38
39
40
41
42
43
44
45
46
*
*/
public class TestGermanStemFilter extends BaseTokenStreamTestCase {

  public void testStemming() throws Exception {
    Analyzer analyzer = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName,
          Reader reader) {
        Tokenizer t = new KeywordTokenizer(reader);
        return new TokenStreamComponents(t,
View Full Code Here
67
68
69
70
71
72
73
74
75
76
77
   */
  private void assertCorrectOutput(final String snowballLanguage, String dataDirectory)
      throws IOException {
    if (VERBOSE) System.out.println("checking snowball language: " + snowballLanguage);
   
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName,
          Reader reader) {
        Tokenizer t = new KeywordTokenizer(reader);
        return new TokenStreamComponents(t, new SnowballFilter(t, snowballLanguage));
View Full Code Here
49
50
51
52
53
54
55
56
57
58
59
  public void testRandomStrings() throws IOException {
    checkRandomData(random, analyzer, atLeast(10000));
  }
 
  public void testEmptyTerm() throws IOException {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        return new TokenStreamComponents(tokenizer, new JapaneseBaseFormFilter(tokenizer));
      }
View Full Code Here
64
65
66
67
68
69
70
71
72
73
74
    assertTokenStreamContents(filter, new String[]{"lucene", "is", "awesome"}, new int[] {1, 1, 1});
  }
 
  /** blast some random strings through the analyzer */
  public void testRandomStrings() throws Exception {
    Analyzer analyzer = new ReusableAnalyzerBase() {

      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
        return new TokenStreamComponents(tokenizer, new HunspellStemFilter(tokenizer, DICTIONARY));
View Full Code Here
76
77
78
79
80
81
82
83
84
85
86
    };
    checkRandomData(random, analyzer, 10000*RANDOM_MULTIPLIER);
  }
 
  public void testEmptyTerm() throws IOException {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        return new TokenStreamComponents(tokenizer, new HunspellStemFilter(tokenizer, DICTIONARY));
      }
View Full Code Here
63
64
65
66
67
68
69
70
71
72
73
  /** restrict the output to a set of possible origin languages */
  public void testLanguageSet() throws Exception {
    final LanguageSet languages = LanguageSet.from(new HashSet<String>() {{
      add("italian"); add("greek"); add("spanish");
    }});
    Analyzer analyzer = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
        return new TokenStreamComponents(tokenizer,
            new BeiderMorseFilter(tokenizer,
View Full Code Here
94
95
96
97
98
99
100
101
102
103
104
  public void testRandom() throws Exception {
    checkRandomData(random, analyzer, 1000 * RANDOM_MULTIPLIER);
  }
 
  public void testEmptyTerm() throws IOException {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        return new TokenStreamComponents(tokenizer, new BeiderMorseFilter(tokenizer, new PhoneticEngine(NameType.GENERIC, RuleType.EXACT, true)));
      }
View Full Code Here
67
68
69
70
71
72
73
74
75
76
77
  public void testRandomStrings() throws Exception {
    checkRandomData(random, analyzer, 10000*RANDOM_MULTIPLIER);
  }
 
  public void testEmptyTerm() throws IOException {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        return new TokenStreamComponents(tokenizer, new GermanNormalizationFilter(tokenizer));
      }
View Full Code Here
190
191
192
193
194
195
196
197
198
199
200
    ts.addAttribute(FlagsAttribute.class);
    assertTokenStreamContents(ts, new String[] { "ภาษา", "ไทย" });
  }
 
  public void testEmptyTerm() throws IOException {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        return new TokenStreamComponents(tokenizer, new ThaiWordFilter(TEST_VERSION_CURRENT, tokenizer));
      }
View Full Code Here
TOP

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

  • com.tigertext.lucene.LuceneServer
  • org.apache.lucene.analysis.ar.TestArabicNormalizationFilter
  • org.apache.lucene.analysis.ar.TestArabicStemFilter
  • org.apache.lucene.analysis.bg.TestBulgarianStemmer
  • org.apache.lucene.analysis.br.TestBrazilianStemmer
  • org.apache.lucene.analysis.charfilter.HTMLStripCharFilterTest
  • org.apache.lucene.analysis.cjk.TestCJKAnalyzer
  • org.apache.lucene.analysis.cjk.TestCJKWidthFilter
  • org.apache.lucene.analysis.cn.smart.TestSmartChineseAnalyzer
  • org.apache.lucene.analysis.compound.TestCompoundWordTokenFilter
    • 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.