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

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

140
141
142
143
144
145
146
147
148
149
150
   * @return An object representing the hyphenation patterns
   * @throws Exception
   */
  public static HyphenationTree getHyphenationTree(Reader hyphenationReader)
      throws Exception {
    HyphenationTree tree = new HyphenationTree();

    tree.loadPatterns(new InputSource(hyphenationReader));

    return tree;
  }
View Full Code Here
154
155
156
157
158
159
160
161
162
   * @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
65
66
67
68
69
70
71
72
73
74
75
    if (reader == null) {
      // we gracefully die if we have no reader
      return;
    }

    HyphenationTree hyphenator = HyphenationCompoundWordTokenFilter
        .getHyphenationTree(reader);

    HyphenationCompoundWordTokenFilter tf = new HyphenationCompoundWordTokenFilter(
        new WhitespaceTokenizer(new StringReader(
            "Rindfleischüberwachungsgesetz Drahtschere abba")), hyphenator,
View Full Code Here
91
92
93
94
95
96
97
98
99
100
101
    if (reader == null) {
      // we gracefully die if we have no reader
      return;
    }

    HyphenationTree hyphenator = HyphenationCompoundWordTokenFilter
        .getHyphenationTree(reader);

    HyphenationCompoundWordTokenFilter tf = new HyphenationCompoundWordTokenFilter(
        new WhitespaceTokenizer(new StringReader(
            "Rindfleischüberwachungsgesetz")), hyphenator, dict,
View Full Code Here
161
162
163
164
165
166
167
168
169
170
171
    if (reader == null) {
      // we gracefully die if we have no reader
      return;
    }

    HyphenationTree hyphenator = HyphenationCompoundWordTokenFilter
        .getHyphenationTree(reader);

    Tokenizer wsTokenizer = new WhitespaceTokenizer(new StringReader(
        "Rindfleischüberwachungsgesetz"));
    HyphenationCompoundWordTokenFilter tf = new HyphenationCompoundWordTokenFilter(
View Full Code Here
154
155
156
157
158
159
160
161
162
   * @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
30
31
32
33
34
35
36
37
38
39
40
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
49
50
51
52
53
54
55
56
57
58
59
  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
71
72
73
74
75
76
77
78
79
80
81
   * 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
47
48
49
50
51
52
53
54
55
56
57
  public void testHyphenationCompoundWordsDA() throws Exception {
    CharArraySet dict = makeDictionary("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
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.