Package org.languagetool

Examples of org.languagetool.AnalyzedToken

60
61
62
63
64
65
66
  private AnalyzedTokenReadings[] getAnalyzedTokenReadings(final String input) throws IOException {
    return languageTool.getAnalyzedSentence(input).getTokensWithoutWhitespace();
  }

  private AnalyzedTokenReadings getAnalyzedTokenReadings(String token, String posTag, String lemma) {
    return new AnalyzedTokenReadings(new AnalyzedToken(token, posTag, lemma), 0);
  }
View Full Code Here
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
    final Element elUpper = new Element("\\p{Lu}\\p{Ll}+", true, true, false);
    final Element elAllUpper = new Element("\\p{Lu}+$", true, true, false);
    uni.setEquivalence("case-sensitivity", "lowercase", elLower);
    uni.setEquivalence("case-sensitivity", "uppercase", elUpper);
    uni.setEquivalence("case-sensitivity", "alluppercase", elAllUpper);
    final AnalyzedToken lower1 = new AnalyzedToken("lower", "JJR", "lower");
    final AnalyzedToken lower2 = new AnalyzedToken("lowercase", "JJ", "lowercase");
    final AnalyzedToken upper1 = new AnalyzedToken("Uppercase", "JJ", "Uppercase");
    final AnalyzedToken upper2 = new AnalyzedToken("John", "NNP", "John");
    final AnalyzedToken upperAll1 = new AnalyzedToken("JOHN", "NNP", "John");
    final AnalyzedToken upperAll2 = new AnalyzedToken("JAMES", "NNP", "James");

    final Map<String, List<String>> equiv = new HashMap<>();
    final List<String> list1 = new ArrayList<>();
    list1.add("lowercase");
    equiv.put("case-sensitivity", list1);
View Full Code Here
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
    uni.setEquivalence("number", "singular", sgElement);
    final Element plElement = new Element("", false, false, false);
    plElement.setPosElement(".*[\\.:]pl:.*", true, false);
    uni.setEquivalence("number", "plural", plElement);

    final AnalyzedToken sing1 = new AnalyzedToken("mały", "adj:sg:blahblah", "mały");
    final AnalyzedToken sing2 = new AnalyzedToken("człowiek", "subst:sg:blahblah", "człowiek");

    final Map<String, List<String>> equiv = new HashMap<>();
    final List<String> list1 = new ArrayList<>();
    list1.add("singular");
    equiv.put("number", list1);

    boolean satisfied = uni.isSatisfied(sing1, equiv);
    uni.startUnify();
    satisfied &= uni.isSatisfied(sing2, equiv);
    assertEquals(true, satisfied);
    uni.reset();

    //for multiple readings - OR for interpretations, AND for tokens
    AnalyzedToken sing1a = new AnalyzedToken("mały", "adj:pl:blahblah", "mały");
    satisfied = uni.isSatisfied(sing1, equiv);
    satisfied |= uni.isSatisfied(sing1a, equiv);
    uni.startUnify();
    satisfied &= uni.isSatisfied(sing2, equiv);
    assertEquals(true, satisfied);
    uni.reset();

    //check if any of the equivalences is there
    list1.add("plural");
    equiv.clear();
    equiv.put("number", list1);
    sing1a = new AnalyzedToken("mały", "adj:pl:blahblah", "mały");
    satisfied = uni.isSatisfied(sing1, equiv);
    satisfied |= uni.isSatisfied(sing1a, equiv);
    uni.startUnify();
    satisfied &= uni.isSatisfied(sing2, equiv);
    assertEquals(true, satisfied);
    uni.reset();

    //now test all possible feature equivalences by leaving type blank
    sing1a = new AnalyzedToken("mały", "adj:pl:blahblah", "mały");
    equiv.clear();
    equiv.put("number", null);
    satisfied = uni.isSatisfied(sing1, equiv);
    satisfied |= uni.isSatisfied(sing1a, equiv);
    uni.startUnify();
View Full Code Here
181
182
183
184
185
186
187
188
189
190
191
192
193
194
    final Element mascElement = new Element("", false, false, false);
    mascElement.setPosElement(".*[\\.:]m", true, false);
    uni.setEquivalence("gender", "masculine", mascElement);

    final AnalyzedToken sing1 = new AnalyzedToken("mały", "adj:sg:blahblah:m", "mały");
    final AnalyzedToken sing1a = new AnalyzedToken("mała", "adj:sg:blahblah:f", "mały");
    final AnalyzedToken sing1b = new AnalyzedToken("małe", "adj:pl:blahblah:m", "mały");
    final AnalyzedToken sing2 = new AnalyzedToken("człowiek", "subst:sg:blahblah:m", "człowiek");

    final Map<String, List<String>> equiv = new HashMap<>();
    equiv.put("number", null);
    equiv.put("gender", null);

View Full Code Here
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
    uni.setEquivalence("gender", "masculine", mascElement);
    final Element neutElement = new Element("", false, false, false);
    neutElement.setPosElement(".*[\\.:]n([\\.:].*)?", true, false);
    uni.setEquivalence("gender", "neutral", neutElement);

    final AnalyzedToken sing1 = new AnalyzedToken("mały", "adj:sg:blahblah:m", "mały");
    AnalyzedToken sing1a = new AnalyzedToken("mały", "adj:pl:blahblah:f", "mały");
    AnalyzedToken sing1b = new AnalyzedToken("mały", "adj:pl:blahblah:f", "mały");
    AnalyzedToken sing2 = new AnalyzedToken("zgarbiony", "adj:pl:blahblah:f", "zgarbiony");   
    final AnalyzedToken sing3 = new AnalyzedToken("człowiek", "subst:sg:blahblah:m", "człowiek");
   
    final Map<String, List<String>> equiv = new HashMap<>();
    equiv.put("number", null);
    equiv.put("gender", null);

    boolean satisfied = uni.isSatisfied(sing1, equiv);
    satisfied |= uni.isSatisfied(sing1a, equiv);
    satisfied |= uni.isSatisfied(sing1b, equiv);
    uni.startUnify();
    satisfied &= uni.isSatisfied(sing2, equiv);
    uni.startNextToken();
    satisfied &= uni.isSatisfied(sing3, equiv);
    uni.startNextToken();
    assertEquals(false, satisfied);
    uni.reset();

    //now test the simplified interface   
    uni.isUnified(sing1, equiv, false);
    uni.isUnified(sing1a, equiv, false);
    uni.isUnified(sing1b, equiv, true);
    uni.isUnified(sing2, equiv, true);   
    assertEquals(false, uni.isUnified(sing3, equiv, true));
    uni.reset();

    sing1a = new AnalyzedToken("osobiste", "adj:pl:nom.acc.voc:f.n.m2.m3:pos:aff", "osobisty");
    sing1b = new AnalyzedToken("osobiste", "adj:sg:nom.acc.voc:n:pos:aff", "osobisty");
    sing2 = new AnalyzedToken("godło", "subst:sg:nom.acc.voc:n", "godło");
   
    uni.isUnified(sing1a, equiv, false);
    uni.isUnified(sing1b, equiv, true);   
    assertEquals(true, uni.isUnified(sing2, equiv, true));
    assertEquals("[osobiste[osobisty/adj:sg:nom.acc.voc:n:pos:aff*], godło[godło/subst:sg:nom.acc.voc:n*]]", Arrays.toString(uni.getFinalUnified()));
    uni.reset();

    //now test a case when the last reading doesn't match at all

    sing1a = new AnalyzedToken("osobiste", "adj:pl:nom.acc.voc:f.n.m2.m3:pos:aff", "osobisty");
    sing1b = new AnalyzedToken("osobiste", "adj:sg:nom.acc.voc:n:pos:aff", "osobisty");
    final AnalyzedToken sing2a = new AnalyzedToken("godło", "subst:sg:nom.acc.voc:n", "godło");
    final AnalyzedToken sing2b = new AnalyzedToken("godło", "indecl", "godło");
   
    uni.isUnified(sing1a, equiv, false);
    uni.isUnified(sing1b, equiv, true);
    uni.isUnified(sing2a, equiv, false);
    assertEquals(true, uni.isUnified(sing2b, equiv, true));
    assertEquals("[osobiste[osobisty/adj:sg:nom.acc.voc:n:pos:aff*], godło[godło/subst:sg:nom.acc.voc:n*]]", Arrays.toString(uni.getFinalUnified()));
    uni.reset();
   
    //check if two features are left out correctly (both match)
    AnalyzedToken plur1 = new AnalyzedToken("zgarbieni", "adj:pl:foobar:m", "zgarbiony");
    AnalyzedToken plur2 = new AnalyzedToken("zgarbieni", "adj:pl:blabla:m", "zgarbiony");
   
    AnalyzedToken plur3 = new AnalyzedToken("ludzie", "subst:pl:blabla:m", "człowiek");
    AnalyzedToken plur4 = new AnalyzedToken("ludzie", "subst:pl:pampam:m", "człowiek");

    uni.isUnified(plur1, equiv, false);
    uni.isUnified(plur2, equiv, true);
    uni.isUnified(plur3, equiv, false);
    assertTrue(uni.isUnified(plur4, equiv, true));
View Full Code Here
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
      final Element mascElement = new Element("", false, false, false);
      mascElement.setPosElement(".*:m", true, false);
      uni.setEquivalence("gender", "masculine", mascElement);

      //Latin adjectives
      final AnalyzedToken sing_masc = new AnalyzedToken("parvus", "adj:sg:blahblah:m", "parvus");
      final AnalyzedToken plur_masc = new AnalyzedToken("parvi", "adj:sg:blahblah:m", "parvus");
      final AnalyzedToken plur_fem = new AnalyzedToken("parvae", "adj:pl:blahblah:f", "parvus");
      final AnalyzedToken sing_fem = new AnalyzedToken("parva", "adj:sg:blahblah:f", "parvus");
     
      //Let's pretend Latin has determiners
      final AnalyzedToken det_sing_fem = new AnalyzedToken("una", "det:sg:blahblah:f", "unus");
      final AnalyzedToken det_plur_fem = new AnalyzedToken("unae", "det:pl:blahblah:f", "unus");
      final AnalyzedToken det_sing_masc = new AnalyzedToken("unus", "det:sg:blahblah:m", "unus");
      final AnalyzedToken det_plur_masc = new AnalyzedToken("uni", "det:sg:blahblah:m", "unus");
     
      //and nouns
      final AnalyzedToken subst_sing_fem = new AnalyzedToken("discrepatio", "subst:sg:blahblah:f", "discrepatio");
      final AnalyzedToken subst_plur_fem = new AnalyzedToken("discrepationes", "subst:sg:blahblah:f", "discrepatio");
      final AnalyzedToken subst_sing_masc = new AnalyzedToken("homo", "sg:sg:blahblah:m", "homo");
      final AnalyzedToken subst_plur_masc = new AnalyzedToken("homines", "sg:sg:blahblah:m", "homo");
     
      //now we should have 4x4x4 combinations...
     
      final Map<String, List<String>> equiv = new HashMap<>();
      equiv.put("number", null);
View Full Code Here
326
327
328
329
330
331
332
333
334
335
336
        final String[] parts = line.split(";");
        if (parts.length != 3) {
          throw new IOException("Format error in file " + fileName + ", line: " + line + ", " +
                  "expected 3 semicolon-separated parts, got " + parts.length);
        }
        final AnalyzedToken analyzedToken = new AnalyzedToken(parts[1], parts[2], null);
        map.put(parts[0], new AnalyzedTokenReadings(analyzedToken, 0));
      }
    } finally {
      scanner.close();
    }
View Full Code Here
48
49
50
51
52
53
54
55
56
57
 
  @Override
  public List<AnalyzedToken> additionalTags(String word) {
    if ( NUMBER.matcher(word).matches() ){
      List<AnalyzedToken> additionalTaggedTokens  = new ArrayList<>();
      additionalTaggedTokens.add(new AnalyzedToken(word, IPOSTag.numr.toString(), word));
        return additionalTaggedTokens;
    }
    return null;
  }
View Full Code Here
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
    element4.setPosElement(Element.UNKNOWN_TAG+"|VBG", true, true);
   
    final Element element5 = new Element("\\p{Ll}+", false, true, false);
    element5.setPosElement(Element.UNKNOWN_TAG, false, false);       
   
    final AnalyzedToken an = new AnalyzedToken("schword", null, null);
    assertTrue(element.isMatched(an));
    assertFalse(element2.isMatched(an));
    assertTrue(element3.isMatched(an));
    assertFalse(element4.isMatched(an));
    assertTrue(element5.isMatched(an));
   
    // if the AnalyzedToken is in the set of readings that have
    //non-null tags...
    an.setNoPOSTag(false);
    assertFalse(element.isMatched(an));
    assertTrue(element2.isMatched(an));
    assertFalse(element3.isMatched(an));
    assertTrue(element4.isMatched(an));
    assertFalse(element5.isMatched(an));
   
    final AnalyzedToken anSentEnd = new AnalyzedToken("schword", JLanguageTool.SENTENCE_END_TAGNAME, null);
    assertTrue(element.isMatched(anSentEnd));
    assertFalse(element2.isMatched(anSentEnd));
    assertTrue(element3.isMatched(anSentEnd));
    assertFalse(element4.isMatched(anSentEnd));
    assertTrue(element5.isMatched(anSentEnd));
   
    final Element element6 = new Element("\\p{Ll}+", false, true, false);
    element6.setPosElement(JLanguageTool.SENTENCE_END_TAGNAME, false, false);
    assertTrue(element6.isMatched(anSentEnd));
   
    final Element element7 = new Element("\\p{Ll}+", false, true, false);
    element7.setPosElement(JLanguageTool.SENTENCE_END_TAGNAME+"|BLABLA", true, false);
    assertTrue(element7.isMatched(anSentEnd));
   
    // if the AnalyzedToken is in the set of readings that have
    //non-null tags...
    anSentEnd.setNoPOSTag(false);
    assertFalse(element.isMatched(anSentEnd));
    assertTrue(element2.isMatched(anSentEnd));
    assertFalse(element3.isMatched(anSentEnd));
    assertTrue(element4.isMatched(anSentEnd));
    assertFalse(element5.isMatched(anSentEnd));
   
    final AnalyzedToken anParaEnd = new AnalyzedToken("schword", JLanguageTool.PARAGRAPH_END_TAGNAME, null);
    assertTrue(element.isMatched(anParaEnd));
    assertFalse(element2.isMatched(anParaEnd));
    assertTrue(element3.isMatched(anParaEnd));
    assertFalse(element4.isMatched(anParaEnd));
    assertTrue(element5.isMatched(anParaEnd));
   
    // if the AnalyzedToken is in the set of readings that have
    //non-null tags...
    anParaEnd.setNoPOSTag(false);
    assertFalse(element.isMatched(anParaEnd));
    assertTrue(element2.isMatched(anParaEnd));
    assertFalse(element3.isMatched(anParaEnd));
    assertTrue(element4.isMatched(anParaEnd));
    assertFalse(element5.isMatched(anParaEnd));
   
    final AnalyzedToken anWithPOS = new AnalyzedToken("schword", "POS", null);
    assertFalse(element.isMatched(anWithPOS));
    assertTrue(element2.isMatched(anWithPOS));
    assertFalse(element3.isMatched(anWithPOS));
    assertTrue(element4.isMatched(anWithPOS));
    assertFalse(element5.isMatched(anWithPOS));
View Full Code Here
30
31
32
33
34
35
36
import java.util.Arrays;

public class MatchTest extends TestCase {

  private AnalyzedTokenReadings getAnalyzedTokenReadings(String token, String posTag, String lemma) {
    return new AnalyzedTokenReadings(new AnalyzedToken(token, posTag, lemma), 0);
  }
View Full Code Here
TOP

Related Classes of org.languagetool.AnalyzedToken

  • org.apache.commons.lang.builder.EqualsBuilder
  • org.apache.commons.lang.builder.HashCodeBuilder
  • org.languagetool.chunking.EnglishChunkerTest
  • org.languagetool.chunking.EnglishChunkFilterTest
  • org.languagetool.dev.index.LanguageToolFilter
  • org.languagetool.dev.index.PatternRuleQueryBuilder
  • org.languagetool.rules.AbstractCompoundRule
  • org.languagetool.rules.ca.AccentuationCheckRule
  • org.languagetool.rules.ca.SimpleReplaceVerbsRule
  • org.languagetool.rules.ConfusionProbabilityRuleTest
    • 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.