Package org.languagetool.language

Examples of org.languagetool.language.Polish

37
38
39
40
41
42
43
44
     
    @Override
    public void setUp() {
      tagger = new PolishTagger();
      tokenizer = new WordTokenizer();
      sentenceTokenizer = new SRXSentenceTokenizer(new Polish());
      disambiguator = new MultiWordChunker("/pl/multiwords.txt");
    }
View Full Code Here
29
30
31
32
33
34
35
36
37
38
39
import java.util.List;

public class ToolsTest extends TestCase {

  public void testCheck() throws IOException, ParserConfigurationException, SAXException {
    final JLanguageTool tool = new JLanguageTool(new Polish());
    tool.activateDefaultPatternRules();
    tool.activateDefaultFalseFriendRules();

    List<RuleMatch> matches = tool.check("To jest całkowicie prawidłowe zdanie.");
    assertEquals(0, matches.size());
View Full Code Here
42
43
44
45
46
47
48
49
50
51
52
    assertEquals(1, matches2.size());
    assertEquals("WORD_REPEAT_RULE", matches2.get(0).getRule().getId());
  }

  public void testCorrect() throws IOException, ParserConfigurationException, SAXException {
    JLanguageTool tool = new JLanguageTool(new Polish());
    tool.activateDefaultPatternRules();
    tool.activateDefaultFalseFriendRules();

    String correct = Tools.correctText("To jest całkowicie prawidłowe zdanie.", tool);
    assertEquals("To jest całkowicie prawidłowe zdanie.", correct);
View Full Code Here
59
60
61
62
63
64
65
66
67
68
69
70
    final String compoundSentence = "To jest kobieta-wojownik w polsko-czeskim ubraniu, która wysłała dwa SMS-y.";
    List<String> compoundTokens = wordTokenizer.tokenize(compoundSentence);
    assertEquals(21, compoundTokens.size());
    assertEquals("[To,  , jest,  , kobieta-wojownik,  , w,  , polsko-czeskim,  , ubraniu, ,,  , która,  , wysłała,  , dwa,  , SMS-y, .]", compoundTokens.toString());
    //now setup the tagger...
    Language pl = new Polish();
    wordTokenizer.setTagger(pl.getTagger());
    compoundTokens = wordTokenizer.tokenize(compoundSentence);
    //we should get 4 more tokens: two hyphen tokens and two for the split words
    assertEquals(25, compoundTokens.size());
    assertEquals("[To,  , jest,  , kobieta, -, wojownik,  , " +
        "w,  , polsko, -, czeskim,  , ubraniu, ,,  " +
View Full Code Here
TOP

Related Classes of org.languagetool.language.Polish

  • org.languagetool.JLanguageToolTest
  • org.languagetool.PolishConcurrencyTest
  • org.languagetool.rules.bitext.FalseFriendsAsBitextLoaderTest
  • org.languagetool.rules.pl.CompoundRule
  • org.languagetool.rules.pl.CompoundRuleTest
  • org.languagetool.rules.pl.MatchTest
  • org.languagetool.rules.pl.MorfologikPolishSpellerRule
  • org.languagetool.rules.pl.MorfologikPolishSpellerRuleTest
  • org.languagetool.rules.pl.MultipleWhitespaceRuleTest
  • org.languagetool.rules.pl.PolishUnpairedBracketsRule
    • 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.