Package org.languagetool

Examples of org.languagetool.AnalyzedToken

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
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
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
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
    unifierConfig.setEquivalence("gender", "neutral",
        preparePOSElement(".*[\\.:]n([\\.:].*)?"));

    final Unifier uni = unifierConfig.createUnifier();

    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();
    satisfied &= uni.getFinalUnificationValue(equiv);
    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));
    assertEquals("[zgarbieni[zgarbiony/adj:pl:foobar:m*,zgarbiony/adj:pl:blabla:m*], " +
        "ludzie[człowiek/subst:pl:blabla:m*,człowiek/subst:pl:pampam:m*]]", Arrays.toString(uni.getFinalUnified()));

    //check with a sequence of many tokens

    uni.reset();

    AnalyzedToken case1a = new AnalyzedToken("xx", "abc:sg:f", "xx");
    AnalyzedToken case1b = new AnalyzedToken("xx", "cde:pl:f", "xx");

    AnalyzedToken case2a = new AnalyzedToken("yy", "abc:pl:f", "yy");
    AnalyzedToken case2b = new AnalyzedToken("yy", "cde:as:f", "yy");
    AnalyzedToken case2c = new AnalyzedToken("yy", "cde:pl:c", "yy");
    AnalyzedToken case2d = new AnalyzedToken("yy", "abc:sg:f", "yy");
    AnalyzedToken case2e = new AnalyzedToken("yy", "efg:aa:e", "yy");

    uni.isUnified(case1a, equiv, false);
    uni.isUnified(case1b, equiv, true);

    uni.isUnified(case2a, equiv, false);
    uni.isUnified(case2b, equiv, false);
    uni.isUnified(case2c, equiv, false);
    uni.isUnified(case2d, equiv, false);
    assertTrue(uni.isUnified(case2e, equiv, true));
    assertEquals("[xx[xx/abc:sg:f*,xx/cde:pl:f*], yy[yy/abc:pl:f*,yy/abc:sg:f*]]",
        Arrays.toString(uni.getFinalUnified()));

    uni.reset();

    AnalyzedToken tokenComplex1_1 = new AnalyzedToken("xx", "abc:sg:f", "xx1");
    AnalyzedToken tokenComplex1_2 = new AnalyzedToken("xx", "cde:pl:f", "xx2");

    AnalyzedToken tokenComplex2_1 = new AnalyzedToken("yy", "abc:sg:f", "yy1");
    AnalyzedToken tokenComplex2_2 = new AnalyzedToken("yy", "cde:pl:f", "yy2");

    AnalyzedToken tokenComplex3 = new AnalyzedToken("zz", "cde:sg:f", "zz");

    uni.isUnified(tokenComplex1_1, equiv, false);
    uni.isUnified(tokenComplex1_2, equiv, true);

    uni.isUnified(tokenComplex2_1, equiv, false);
View Full Code Here
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
    unifierConfig.setEquivalence("case", "vocativus",
        preparePOSElement(".*[\\.:]voc[\\.:]?.*"));

    final Unifier uni = unifierConfig.createUnifier();

    final AnalyzedToken sing1 = new AnalyzedToken("niezgorsze", "adj:sg:acc:n1.n2:pos", "niezgorszy");
    final AnalyzedToken sing1a = new AnalyzedToken("niezgorsze", "adj:pl:acc:m2.m3.f.n1.n2.p2.p3:pos", "niezgorszy");
    final AnalyzedToken sing1b = new AnalyzedToken("niezgorsze", "adj:pl:nom.voc:m2.m3.f.n1.n2.p2.p3:pos", "niezgorszy");
    final AnalyzedToken sing1c = new AnalyzedToken("niezgorsze", "adj:sg:nom.voc:n1.n2:pos", "niezgorszy");
    final AnalyzedToken sing2 = new AnalyzedToken("lekarstwo", "subst:sg:acc:n2", "lekarstwo");
    final AnalyzedToken sing2b = new AnalyzedToken("lekarstwo", "subst:sg:nom:n2", "lekarstwo");
    final AnalyzedToken sing2c = new AnalyzedToken("lekarstwo", "subst:sg:voc:n2", "lekarstwo");

    final Map<String, List<String>> equiv = new HashMap<>();
    equiv.put("number", null);
    equiv.put("gender", null);
    equiv.put("case", null);
View Full Code Here
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
        preparePOSElement(".*:m"));

    final Unifier uni = unifierConfig.createUnifier();

    //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
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
    final Map<String, List<String>> equiv = new HashMap<>();
    equiv.put("number", null);
    equiv.put("gender", null);

    AnalyzedToken sing1a = new AnalyzedToken("osobiste", "adj:pl:nom.acc.voc:f.n.m2.m3:pos:aff", "osobisty");
    AnalyzedToken sing1b = new AnalyzedToken("osobiste", "adj:sg:nom.acc.voc:n:pos:aff", "osobisty");
    AnalyzedToken sing2 = new AnalyzedToken("godło", "subst:sg:nom.acc.voc:n", "godło");

    AnalyzedToken comma = new AnalyzedToken(",", "comma", ",");

    uni.isUnified(sing1a, equiv, false);
    uni.isUnified(sing1b, equiv, true);
    uni.addNeutralElement(new AnalyzedTokenReadings(comma, 0));
    assertEquals(true, uni.isUnified(sing2, equiv, true));
View Full Code Here
37
38
39
40
41
42
43
    //with regular expressions
    assertEquals("[časopisy, časopisov, časopisom, časopisy, časopisy, časopisoch, časopismi, časopis, časopisu, časopisu, časopis, časopis, časopise, časopisom]", Arrays.toString(synth.synthesize(dummyToken("časopis"), "SS.*", true)));   
  }
 
  private AnalyzedToken dummyToken(String tokenStr) {
    return new AnalyzedToken(tokenStr, tokenStr, tokenStr);
  }
View Full Code Here
56
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
    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
58
59
60
61
62
63
64
65
66
67
68
    assertTrue(p.testAllReadings(tokenReadings("bar", "myChunk"), elemMatcher, null, 0, 0, 0));
    assertFalse(p.testAllReadings(tokenReadings("bar", "otherChunk"), elemMatcher, null, 0, 0, 0));
  }

  private AnalyzedTokenReadings[] tokenReadings(String token, String chunkTag) {
    AnalyzedTokenReadings tokenReadings1 = new AnalyzedTokenReadings(new AnalyzedToken(token, "pos", "lemma"), 0);
    if (chunkTag != null) {
      tokenReadings1.setChunkTags(Collections.singletonList(new ChunkTag(chunkTag)));
    }
    return new AnalyzedTokenReadings[] { tokenReadings1 };
  }
View Full Code Here
35
36
37
38
39
40
41
42
43
44
45
46
  private final RuleFilterEvaluator eval = new RuleFilterEvaluator(null);

  @Test
  public void testGetResolvedArguments() throws Exception {
    AnalyzedTokenReadings[] readingsList = {
            new AnalyzedTokenReadings(new AnalyzedToken("fake1", "pos", null), 0),
            new AnalyzedTokenReadings(new AnalyzedToken("fake2", "pos", null), 0)
    };
    Map<String,String> map = eval.getResolvedArguments("year:\\1 month:\\2", readingsList, Arrays.asList(1, 1));
    assertThat(map.get("year"), is("fake1"));
    assertThat(map.get("month"), is("fake2"));
    assertThat(map.size(), is(2));
View Full Code Here
47
48
49
50
51
52
53
54
55
56
57
  }

  @Test(expected = RuntimeException.class)
  public void testDuplicateKey() throws Exception {
    AnalyzedTokenReadings[] readingsList = {
            new AnalyzedTokenReadings(new AnalyzedToken("fake1", "SENT_START", null), 0),
            new AnalyzedTokenReadings(new AnalyzedToken("fake1", "pos", null), 0),
            new AnalyzedTokenReadings(new AnalyzedToken("fake2", "pos", null), 0)
    };
    eval.getResolvedArguments("year:\\1 year:\\2", readingsList, Arrays.asList(1, 2));
  }
View Full Code Here
26
27
28
29
30
31
32
import org.languagetool.AnalyzedToken;

public class RussianSynthesizerTest extends TestCase {
  private AnalyzedToken dummyToken(String tokenStr) {
    return new AnalyzedToken(tokenStr, tokenStr, tokenStr);
  }
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.