Package org.languagetool

Examples of org.languagetool.AnalyzedToken

157
158
159
160
161
162
163
    return new AnalyzedTokenReadings(new AnalyzedToken(token, null, null), startPos);
  }

  @Override
  public AnalyzedToken createToken(String token, String posTag) {
    return new AnalyzedToken(token, posTag, null);
  }
View Full Code Here
39
40
41
42
43
44
45
46
47
48
    final List<AnalyzedTokenReadings> tokenReadings = new ArrayList<>();
    for (String word : sentenceTokens) {
      final List<AnalyzedToken> l = new ArrayList<>();
      // a real tagger would need to assign a POS tag
      // in the next line instead of null:
      l.add(new AnalyzedToken(word, null, null));     
      tokenReadings.add(new AnalyzedTokenReadings(l, 0));
    }
    return tokenReadings;
  }
View Full Code Here
47
48
49
50
51
52
53
    return tokenReadings;
  }

  @Override
  public AnalyzedTokenReadings createNullToken(String token, int startPos) {
    return new AnalyzedTokenReadings(new AnalyzedToken(token, null, null), startPos);
  }
View Full Code Here
52
53
54
55
56
57
58
    return new AnalyzedTokenReadings(new AnalyzedToken(token, null, null), startPos);
  }

  @Override
  public AnalyzedToken createToken(String token, String posTag) {
    return new AnalyzedToken(token, posTag, null);
  }
View Full Code Here
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
              if (newTokenReadings[i].getLemma() == null) { //empty lemma
                lemma = token;
              } else {
                lemma = newTokenReadings[i].getLemma();
              }
              final AnalyzedToken newTok = new AnalyzedToken(token, newTokenReadings[i].getPOSTag(), lemma);

              final String prevValue = whTokens[position].toString();
              final String prevAnot = whTokens[position].getHistoricalAnnotations();
              whTokens[position].addReading(newTok);
              annotateChange(whTokens[position], prevValue, prevAnot);
            }
          }
        }
        break;
      case FILTERALL:
        for (int i = 0; i < matchingTokens - startPositionCorrection
                + endPositionCorrection; i++) {
          final int position = text.getOriginalPosition(firstMatchToken
                  + correctedStPos + i);
          final Element myEl = patternElements.get(i+startPositionCorrection);
          final Match tmpMatchToken = new Match(myEl.getPOStag(), null,
                  true, myEl.getPOStag(), //myEl.isPOStagRegularExpression()
                  null, Match.CaseConversion.NONE, false, false,
                  Match.IncludeRange.NONE);
          tmpMatchToken.setToken(whTokens[position]);
          final String prevValue = whTokens[position].toString();
          final String prevAnot = whTokens[position]
                  .getHistoricalAnnotations();
          whTokens[position] = tmpMatchToken.filterReadings();
          annotateChange(whTokens[position], prevValue, prevAnot);
        }
        break;
      case IMMUNIZE:
        for (int i = 0; i < matchingTokens - startPositionCorrection + endPositionCorrection; i++) {
          whTokens[text.getOriginalPosition(firstMatchToken + correctedStPos + i)].immunize();
        }
        break;
      case FILTER:
        if (matchElement == null) { // same as REPLACE if using <match>
          final Match tmpMatchToken = new Match(disambiguatedPOS, null, true,
                  disambiguatedPOS, null, Match.CaseConversion.NONE,
                  false, false, Match.IncludeRange.NONE);
          tmpMatchToken.setToken(whTokens[fromPos]);
          final String prevValue = whTokens[fromPos].toString();
          final String prevAnot = whTokens[fromPos].getHistoricalAnnotations();
          whTokens[fromPos] = tmpMatchToken.filterReadings();
          annotateChange(whTokens[fromPos], prevValue, prevAnot);
          filtered = true;
        }
        // FALLTHROUGH
      case REPLACE:
      default:
        if (!filtered) {
          if (newTokenReadings != null && newTokenReadings.length > 0) {
            if (newTokenReadings.length == matchingTokens - startPositionCorrection + endPositionCorrection) {
              String lemma;
              String token;
              for (int i = 0; i < newTokenReadings.length; i++) {
                final int position = text.getOriginalPosition(firstMatchToken + correctedStPos
                        + i);
                if ("".equals(newTokenReadings[i].getToken())) { //empty token
                  token = whTokens[position].getToken();
                } else {
                  token = newTokenReadings[i].getToken();
                }
                if (newTokenReadings[i].getLemma() == null) { //empty lemma
                  lemma = token;
                } else {
                  lemma = newTokenReadings[i].getLemma();
                }
                final AnalyzedTokenReadings toReplace = new AnalyzedTokenReadings(
                        new AnalyzedToken(token, newTokenReadings[i].getPOSTag(), lemma),
                        whTokens[fromPos].getStartPos());
                whTokens[position] = replaceTokens(whTokens[position], toReplace);
              }
            }
          } else if (matchElement == null) {
            String lemma = "";
            for (int l = 0; l < numRead; l++) {
              if (whTokens[fromPos].getAnalyzedToken(l).getPOSTag() != null
                      && (whTokens[fromPos].getAnalyzedToken(l).getPOSTag().equals(
                      disambiguatedPOS) && (whTokens[fromPos].getAnalyzedToken(l)
                      .getLemma() != null))) {
                lemma = whTokens[fromPos].getAnalyzedToken(l).getLemma();
              }
            }
            if (StringTools.isEmpty(lemma)) {
              lemma = whTokens[fromPos].getAnalyzedToken(0).getLemma();
            }

            final AnalyzedTokenReadings toReplace = new AnalyzedTokenReadings(
                    new AnalyzedToken(whTokens[fromPos].getToken(), disambiguatedPOS,
                            lemma), whTokens[fromPos].getStartPos());
            whTokens[fromPos] = replaceTokens(whTokens[fromPos], toReplace);
          } else {
            // using the match element
            matchElement.setToken(whTokens[fromPos]);
View Full Code Here
166
167
168
169
170
171
172
173
      if (isLast) {
          sb.append("/");
      }
      sb.append(mFull.get(tokens));
      sb.append(">");
      final AnalyzedToken tokenStart = new AnalyzedToken(tok, sb.toString(), tokens);
      return setAndAnnotate(token, tokenStart);     
  }
View Full Code Here
410
411
412
413
414
415
416
417
418
419
420
    }
  }

  private void addNewWord(final String word, final String lemma,
      final String pos) {
    final AnalyzedToken newWd = new AnalyzedToken(word, pos, lemma);
    if (newWdList == null) {
      newWdList = new ArrayList<>();
    }
    newWdList.add(newWd);
  }
View Full Code Here
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
124
125
126
127
128
129
130
131
132
133
134
135
136
      for (AnalyzedToken taggerToken : taggerTokens ) {
        final String posTag = taggerToken.getPOSTag();
        if (posTag != null) {
          final Matcher m = ADJ_PART_FS.matcher(posTag);
          if (m.matches()) {
            additionalTaggedTokens.add(new AnalyzedToken(word, "RG", lowerWord));
            return additionalTaggedTokens;
          }
        }
      }
    }
    //Any well-formed verb with prefixes is tagged as a verb copying the original tags  
    Matcher matcher=PREFIXES_FOR_VERBS.matcher(word);
    if (matcher.matches()) {
      final String possibleVerb = matcher.group(2).toLowerCase();
      List<AnalyzedToken> taggerTokens;
      taggerTokens = asAnalyzedTokenList(possibleVerb, dictLookup.lookup(possibleVerb));
      for (AnalyzedToken taggerToken : taggerTokens ) {
        final String posTag = taggerToken.getPOSTag();
        if (posTag != null) {
          final Matcher m = VERB.matcher(posTag);
          if (m.matches()) {
            String lemma=matcher.group(1).toLowerCase().concat(taggerToken.getLemma());
            additionalTaggedTokens.add(new AnalyzedToken(word, posTag, lemma));
          }
        }
      }
      return additionalTaggedTokens;
    }
    // Any well-formed noun with prefix ex- is tagged as a noun copying the original tags
    if (word.startsWith("ex")) {
      final String lowerWord = word.toLowerCase(conversionLocale);
      final String possibleNoun = lowerWord.replaceAll("^ex(.+)$", "$1");
      List<AnalyzedToken> taggerTokens;
      taggerTokens = asAnalyzedTokenList(possibleNoun,dictLookup.lookup(possibleNoun));
      for (AnalyzedToken taggerToken : taggerTokens) {
        final String posTag = taggerToken.getPOSTag();
        if (posTag != null) {
          final Matcher m = NOUN.matcher(posTag);
          if (m.matches()) {
            String lemma = "ex".concat(taggerToken.getLemma());
            additionalTaggedTokens.add(new AnalyzedToken(word, posTag, lemma));
          }
        }
      }
      return additionalTaggedTokens;
    }
View Full Code Here
58
59
60
61
62
63
64
  private String synthNonRegex(String word, String pos) throws IOException {
    return Arrays.toString(synth.synthesize(dummyToken(word), pos, false));
  }

  private AnalyzedToken dummyToken(String tokenStr) {
    return new AnalyzedToken(tokenStr, tokenStr, tokenStr);
  }
View Full Code Here
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
      final List<WordData> taggerTokens = morfologik.lookup(lowerCaseWord);
      if (taggerTokens != null) {
        for (WordData wd : taggerTokens) {
          final String[] tagsArr = wd.getStem().toString().split("\\+");
          for (final String currTag : tagsArr) {
            l.add(new AnalyzedToken(word,
                wd.getTag().toString(), currTag));
          }
        }     
      }
      if (manualTagger != null) { // add user tags, if any
        final String[] manualTags = manualTagger.lookup(lowerCaseWord);
        if (manualTags != null) {
          for (int i = 0; i < manualTags.length/2; i=i+2) {
            l.add(new AnalyzedToken(word, manualTags[i+1], manualTags[i]));
      }
        }
      }

      if (l.isEmpty()) {
        l.add(new AnalyzedToken(word, null, null));
      }     
      tokenReadings.add(new AnalyzedTokenReadings(l, pos));
      pos += word.length();
    }
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.