Package org.languagetool.rules.patterns

Examples of org.languagetool.rules.patterns.Match

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
        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:
View Full Code Here
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
      Match.IncludeRange includeRange = Match.IncludeRange.NONE;
      if (attrs.getValue("include_skipped") != null) {
        includeRange = Match.IncludeRange.toRange(attrs
            .getValue("include_skipped").toUpperCase());
      }
      final Match mWorker = new Match(attrs.getValue(POSTAG), attrs
          .getValue("postag_replace"), YES
          .equals(attrs.getValue(POSTAG_REGEXP)), attrs
          .getValue("regexp_match"), attrs.getValue("regexp_replace"),
          caseConversion, YES.equals(attrs.getValue("setpos")),
          YES.equals(attrs.getValue("suppress_mispelled")),
          includeRange);
      if (inDisambiguation) {
        if (attrs.getValue(NO) != null) {
          final int refNumber = Integer.parseInt(attrs.getValue(NO));
          if (refNumber > elementList.size()) {
            throw new SAXException(
                "Only backward references in match elements are possible, tried to specify token "
                    + refNumber
                    + "\n Line: "
                    + pLocator.getLineNumber()
                    + ", column: " + pLocator.getColumnNumber() + ".");
          }
          mWorker.setTokenRef(refNumber);
          posSelector = mWorker;
        }
      } else if (inToken) {
        if (attrs.getValue(NO) != null) {
          final int refNumber = Integer.parseInt(attrs.getValue(NO));
          if (refNumber > elementList.size()) {
            throw new SAXException(
                "Only backward references in match elements are possible, tried to specify token "
                    + refNumber
                    + "\n Line: "
                    + pLocator.getLineNumber()
                    + ", column: " + pLocator.getColumnNumber() + ".");
          }
          mWorker.setTokenRef(refNumber);
          tokenReference = mWorker;
          elements.append('\\');
          elements.append(refNumber);
        }
      }
View Full Code Here
34
35
36
37
38
39
40
41
  private AnalyzedTokenReadings getAnalyzedTokenReadings(String token, String posTag, String lemma) {
    return new AnalyzedTokenReadings(new AnalyzedToken(token, posTag, lemma), 0);
  }

  private Match getMatch(String posTag, String posTagReplace, boolean spell) throws IOException {
    final Match match = new Match(posTag, posTagReplace, true, null, null, CaseConversion.NONE, false, spell, IncludeRange.NONE);
    return match;
  }
View Full Code Here
39
40
41
42
43
44
45
46
    final Match match = new Match(posTag, posTagReplace, true, null, null, CaseConversion.NONE, false, spell, IncludeRange.NONE);
    return match;
  }

  private Match getTextMatch(String regexMatch, String regexpReplace, boolean spell) throws IOException {
    final Match match = new Match(null, null, false, regexMatch, regexpReplace, CaseConversion.NONE, false, spell, IncludeRange.NONE);
    return match;
  }
View Full Code Here
45
46
47
48
49
50
51
52
53
54
55
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
    return match;
  }

  public void testSpeller() throws Exception {
    //tests with synthesizer
    Match match = getMatch("POS1", "POS2", true);
    final Polish polish = new Polish();
    match.setSynthesizer(polish.getSynthesizer());
    match.setToken(getAnalyzedTokenReadings("inflectedform11", "POS1", "Lemma1"));
    //getting empty strings, which is what we want
    assertEquals("[]", Arrays.toString(match.toFinalString(polish)));

    // contrast with a speller = false!
    match = getMatch("POS1", "POS2", false);
    match.setSynthesizer(polish.getSynthesizer());
    match.setToken(getAnalyzedTokenReadings("inflectedform11", "POS1", "Lemma1"));
    assertEquals("[(inflectedform11)]", Arrays.toString(match.toFinalString(polish)));

    //and now a real word - we should get something
    match = getMatch("subst:sg:acc.nom:m3", "subst:sg:gen:m3", true);
    match.setSynthesizer(polish.getSynthesizer());
    match.setToken(getAnalyzedTokenReadings("AON", "subst:sg:acc.nom:m3", "AON"));
    assertEquals("[AON-u]", Arrays.toString(match.toFinalString(polish)));

    //and now pure text changes       
    match = getTextMatch("^(.*)$", "$0-u", true);
    match.setSynthesizer(polish.getSynthesizer());
    match.setLemmaString("AON");
    assertEquals("[AON-u]", Arrays.toString(match.toFinalString(polish)));
    match.setLemmaString("batalion");
    //should be empty
    assertEquals("[]", Arrays.toString(match.toFinalString(polish)));
    match.setLemmaString("ASEAN");
    //and this one not
    assertEquals("[ASEAN-u]", Arrays.toString(match.toFinalString(polish)));
  }
View Full Code Here
35
36
37
38
39
40
41
42
  private AnalyzedTokenReadings getAnalyzedTokenReadings(String token, String posTag, String lemma) {
    return new AnalyzedTokenReadings(new AnalyzedToken(token, posTag, lemma), 0);
  }

  private Match getMatch(String posTag, String posTagReplace, boolean spell) {
    final Match match = new Match(posTag, posTagReplace, true, null, null, CaseConversion.NONE, false, spell, IncludeRange.NONE);
    return match;
  }
View Full Code Here
40
41
42
43
44
45
46
47
    final Match match = new Match(posTag, posTagReplace, true, null, null, CaseConversion.NONE, false, spell, IncludeRange.NONE);
    return match;
  }

  private Match getTextMatch(String regexMatch, String regexpReplace, boolean spell) {
    final Match match = new Match(null, null, false, regexMatch, regexpReplace, CaseConversion.NONE, false, spell, IncludeRange.NONE);
    return match;
  }
View Full Code Here
46
47
48
49
50
51
52
53
54
55
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
    return match;
  }

  public void testSpeller() throws Exception {
    //tests with synthesizer
    Match match = getMatch("POS1", "POS2", true);
    final Polish polish = new Polish();
    MatchState matchState = new MatchState(match, polish.getSynthesizer());
    matchState.setToken(getAnalyzedTokenReadings("inflectedform11", "POS1", "Lemma1"));
    //getting empty strings, which is what we want
    assertEquals("[]", Arrays.toString(matchState.toFinalString(polish)));

    // contrast with a speller = false!
    match = getMatch("POS1", "POS2", false);
    matchState = new MatchState(match, polish.getSynthesizer());
    matchState.setToken(getAnalyzedTokenReadings("inflectedform11", "POS1", "Lemma1"));
    assertEquals("[(inflectedform11)]", Arrays.toString(matchState.toFinalString(polish)));

    //and now a real word - we should get something
    match = getMatch("subst:sg:acc.nom:m3", "subst:sg:gen:m3", true);
    matchState = new MatchState(match, polish.getSynthesizer());
    matchState.setToken(getAnalyzedTokenReadings("AON", "subst:sg:acc.nom:m3", "AON"));
    assertEquals("[AON-u]", Arrays.toString(matchState.toFinalString(polish)));

    //and now pure text changes       
    match = getTextMatch("^(.*)$", "$0-u", true);
    match.setSynthesizer(polish.getSynthesizer());
    match.setLemmaString("AON");
    matchState = new MatchState(match, polish.getSynthesizer());
    assertEquals("[AON-u]", Arrays.toString(matchState.toFinalString(polish)));
    match.setLemmaString("batalion");
    //should be empty
    matchState = new MatchState(match, polish.getSynthesizer());
    assertEquals("[]", Arrays.toString(matchState.toFinalString(polish)));
    match.setLemmaString("ASEAN");
    //and this one not
    matchState = new MatchState(match, polish.getSynthesizer());
    assertEquals("[ASEAN-u]", Arrays.toString(matchState.toFinalString(polish)));
  }
View Full Code Here
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
          Match.IncludeRange includeRange = Match.IncludeRange.NONE;
          if (attrs.getValue("include_skipped") != null) {
            includeRange = Match.IncludeRange.valueOf(attrs
                    .getValue("include_skipped").toUpperCase(Locale.ENGLISH));
          }
          final Match mWorker = new Match(attrs.getValue(POSTAG), attrs
                  .getValue("postag_replace"), YES
                  .equals(attrs.getValue(POSTAG_REGEXP)), attrs
                  .getValue("regexp_match"), attrs.getValue("regexp_replace"),
                  caseConversion, YES.equals(attrs.getValue("setpos")),
                  YES.equals(attrs.getValue("suppress_mispelled")),
                  includeRange);
          if (inDisambiguation) {
            if (attrs.getValue(NO) != null) {
              final int refNumber = Integer.parseInt(attrs.getValue(NO));
              refNumberSanityCheck(refNumber);
              mWorker.setTokenRef(refNumber);
              posSelector = mWorker;
            }
          } else if (inToken) {
            if (attrs.getValue(NO) != null) {
              final int refNumber = Integer.parseInt(attrs.getValue(NO));
              refNumberSanityCheck(refNumber);
              mWorker.setTokenRef(refNumber);
              tokenReference = mWorker;
              elements.append('\\');
              elements.append(refNumber);
            }
          }
View Full Code Here
TOP

Related Classes of org.languagetool.rules.patterns.Match

  • org.languagetool.AnalyzedToken
  • org.languagetool.AnalyzedTokenReadings
  • org.languagetool.rules.pl.MatchTest
  • org.languagetool.tagging.disambiguation.rules.DisambiguationPatternRule
  • org.languagetool.tagging.disambiguation.rules.DisambiguationRuleHandler
    • 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.