Package org.apache.lucene.analysis.compound.hyphenation

Examples of org.apache.lucene.analysis.compound.hyphenation.HyphenationTree

54
55
56
57
58
59
60
61
62
63
64
  public void testHyphenationCompoundWordsDELongestMatch() throws Exception {
    String[] dict = { "basketball", "basket", "ball", "kurv" };

    InputSource is = new InputSource(getClass().getResource("da_UTF8.xml").toExternalForm());
    HyphenationTree hyphenator = HyphenationCompoundWordTokenFilter
        .getHyphenationTree(is);

    // the word basket will not be added due to the longest match option
    HyphenationCompoundWordTokenFilter tf = new HyphenationCompoundWordTokenFilter(TEST_VERSION_CURRENT,
        new MockTokenizer(new StringReader("basketballkurv"), MockTokenizer.WHITESPACE, false),
View Full Code Here
76
77
78
79
80
81
82
83
84
85
86
   * With hyphenation-only, you can get a lot of nonsense tokens.
   * This can be controlled with the min/max subword size.
   */
  public void testHyphenationOnly() throws Exception {
    InputSource is = new InputSource(getClass().getResource("da_UTF8.xml").toExternalForm());
    HyphenationTree hyphenator = HyphenationCompoundWordTokenFilter
        .getHyphenationTree(is);
   
    HyphenationCompoundWordTokenFilter tf = new HyphenationCompoundWordTokenFilter(
        TEST_VERSION_CURRENT,
        new MockTokenizer(new StringReader("basketballkurv"), MockTokenizer.WHITESPACE, false),
View Full Code Here
29
30
31
32
33
34
35
36
37
38
39
public class TestCompoundWordTokenFilter extends BaseTokenStreamTestCase {
  public void testHyphenationCompoundWordsDA() throws Exception {
    String[] dict = { "læse", "hest" };

    InputSource is = new InputSource(getClass().getResource("da_UTF8.xml").toExternalForm());
    HyphenationTree hyphenator = HyphenationCompoundWordTokenFilter
        .getHyphenationTree(is);

    HyphenationCompoundWordTokenFilter tf = new HyphenationCompoundWordTokenFilter(TEST_VERSION_CURRENT,
        new WhitespaceTokenizer(TEST_VERSION_CURRENT, new StringReader(
            "min veninde som er lidt af en læsehest")), hyphenator,
View Full Code Here
48
49
50
51
52
53
54
55
56
57
58
  public void testHyphenationCompoundWordsDELongestMatch() throws Exception {
    String[] dict = { "basketball", "basket", "ball", "kurv" };

    InputSource is = new InputSource(getClass().getResource("da_UTF8.xml").toExternalForm());
    HyphenationTree hyphenator = HyphenationCompoundWordTokenFilter
        .getHyphenationTree(is);

    // the word basket will not be added due to the longest match option
    HyphenationCompoundWordTokenFilter tf = new HyphenationCompoundWordTokenFilter(TEST_VERSION_CURRENT,
        new WhitespaceTokenizer(TEST_VERSION_CURRENT, new StringReader(
View Full Code Here
70
71
72
73
74
75
76
77
78
79
80
   * With hyphenation-only, you can get a lot of nonsense tokens.
   * This can be controlled with the min/max subword size.
   */
  public void testHyphenationOnly() throws Exception {
    InputSource is = new InputSource(getClass().getResource("da_UTF8.xml").toExternalForm());
    HyphenationTree hyphenator = HyphenationCompoundWordTokenFilter
        .getHyphenationTree(is);
   
    HyphenationCompoundWordTokenFilter tf = new HyphenationCompoundWordTokenFilter(
        TEST_VERSION_CURRENT,
        new WhitespaceTokenizer(TEST_VERSION_CURRENT, new StringReader("basketballkurv")),
View Full Code Here
308
309
310
311
312
313
314
315
316
   * @return An object representing the hyphenation patterns
   * @throws Exception
   */
  public static HyphenationTree getHyphenationTree(InputSource hyphenationSource)
      throws Exception {
    HyphenationTree tree = new HyphenationTree();
    tree.loadPatterns(hyphenationSource);
    return tree;
  }
View Full Code Here
42
43
44
45
46
47
48
49
50
51
52
public class TestCompoundWordTokenFilter extends BaseTokenStreamTestCase {
  public void testHyphenationCompoundWordsDA() throws Exception {
    String[] dict = { "læse", "hest" };

    InputSource is = new InputSource(getClass().getResource("da_UTF8.xml").toExternalForm());
    HyphenationTree hyphenator = HyphenationCompoundWordTokenFilter
        .getHyphenationTree(is);

    HyphenationCompoundWordTokenFilter tf = new HyphenationCompoundWordTokenFilter(TEST_VERSION_CURRENT,
        new MockTokenizer(new StringReader("min veninde som er lidt af en læsehest"), MockTokenizer.WHITESPACE, false),
        hyphenator,
View Full Code Here
61
62
63
64
65
66
67
68
69
70
71
  public void testHyphenationCompoundWordsDELongestMatch() throws Exception {
    String[] dict = { "basketball", "basket", "ball", "kurv" };

    InputSource is = new InputSource(getClass().getResource("da_UTF8.xml").toExternalForm());
    HyphenationTree hyphenator = HyphenationCompoundWordTokenFilter
        .getHyphenationTree(is);

    // the word basket will not be added due to the longest match option
    HyphenationCompoundWordTokenFilter tf = new HyphenationCompoundWordTokenFilter(TEST_VERSION_CURRENT,
        new MockTokenizer(new StringReader("basketballkurv"), MockTokenizer.WHITESPACE, false),
View Full Code Here
83
84
85
86
87
88
89
90
91
92
93
   * With hyphenation-only, you can get a lot of nonsense tokens.
   * This can be controlled with the min/max subword size.
   */
  public void testHyphenationOnly() throws Exception {
    InputSource is = new InputSource(getClass().getResource("da_UTF8.xml").toExternalForm());
    HyphenationTree hyphenator = HyphenationCompoundWordTokenFilter
        .getHyphenationTree(is);
   
    HyphenationCompoundWordTokenFilter tf = new HyphenationCompoundWordTokenFilter(
        TEST_VERSION_CURRENT,
        new MockTokenizer(new StringReader("basketballkurv"), MockTokenizer.WHITESPACE, false),
View Full Code Here
342
343
344
345
346
347
348
349
350
351
352
      }
    };
    checkRandomData(random, a, 10000*RANDOM_MULTIPLIER);
   
    InputSource is = new InputSource(getClass().getResource("da_UTF8.xml").toExternalForm());
    final HyphenationTree hyphenator = HyphenationCompoundWordTokenFilter.getHyphenationTree(is);
    Analyzer b = new ReusableAnalyzerBase() {

      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
View Full Code Here
TOP

Related Classes of org.apache.lucene.analysis.compound.hyphenation.HyphenationTree

  • org.apache.lucene.analysis.compound.HyphenationCompoundWordTokenFilter
  • org.apache.lucene.analysis.compound.TestCompoundWordTokenFilter
  • org.xml.sax.InputSource
  • java.util.HashMap
  • java.util.ArrayList
    • 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.