Package org.languagetool

Examples of org.languagetool.AnalyzedSentence

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
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
          // enable indentation use
          goodSentence = goodSentence.replaceAll("[\\n\\t]+", "");
          goodSentence = cleanXML(goodSentence);

          assertTrue(goodSentence.trim().length() > 0);
          final AnalyzedSentence sent = disambiguateUntil(rules, id,
              languageTool.getRawAnalyzedSentence(goodSentence));
          final AnalyzedSentence sentToReplace = disambiguateUntil(rules, id,
              languageTool.getRawAnalyzedSentence(goodSentence));
          //note: we're testing only if string representations are equal
          //it's because getRawAnalyzedSentence does not set all properties
          //in AnalyzedSentence, and during equal test they are set for the
          //left-hand side
          assertEquals("The untouched example (" + goodSentence + ") for " + lang.getName() +
              " rule " + id +"["+ rule.getSubId() +"] was touched!",
              sent.toString(), rule.replace(sentToReplace).toString());
        }
      }
      final List<DisambiguatedExample> examples = rule.getExamples();
      if (examples != null) {
        for (final DisambiguatedExample example : examples) {

          final String outputForms = example.getDisambiguated();
          assertTrue("No input form found for: " + id, outputForms != null);
          assertTrue(outputForms.trim().length() > 0);
          final int expectedMatchStart = example.getExample().indexOf("<marker>");
          final int expectedMatchEnd = example.getExample().indexOf("</marker>") - "<marker>".length();
          if (expectedMatchStart == -1 || expectedMatchEnd == -1) {
            fail(lang
                + ": No position markup ('<marker>...</marker>') in disambiguated example in rule " + rule);
          }
          final String inputForms = example.getAmbiguous();
          assertTrue("No input form found for: " + id, inputForms != null);
          assertTrue(inputForms.trim().length() > 0);
          assertTrue("Input and output forms for rule " + id + "are the same!",
              !outputForms.equals(inputForms));
          final AnalyzedSentence cleanInput = languageTool
              .getRawAnalyzedSentence(cleanXML(example.getExample()));
          final AnalyzedSentence sent = disambiguateUntil(rules, id,
              languageTool
              .getRawAnalyzedSentence(cleanXML(example.getExample())));
          final AnalyzedSentence disambiguatedSent = rule
              .replace(disambiguateUntil(rules, id, languageTool
                  .getRawAnalyzedSentence(cleanXML(example.getExample()))));
          assertTrue(
              "Disambiguated sentence is equal to the non-disambiguated sentence for rule: "
                  + id, !cleanInput.equals(disambiguatedSent));
          assertTrue(
              "Disambiguated sentence is equal to the input sentence for rule: "
                  + id + ". The sentence was: " + sent, !sent.equals(disambiguatedSent));
          String reading = "";
          String annotations = "";
          for (final AnalyzedTokenReadings readings : sent.getTokens()) {
            if (readings.isSentenceStart() && !inputForms.contains("<S>")) {
              continue;
            }
            if (readings.getStartPos() == expectedMatchStart) {
              final AnalyzedTokenReadings[] r = { readings };
              reading = new AnalyzedSentence(r).toShortString(",");
              annotations = readings.getHistoricalAnnotations();
              assertTrue(
                  "Wrong marker position in the example for the rule " + id,
                  readings.getStartPos() == expectedMatchStart
                  && readings.getStartPos() + readings.getToken().length() == expectedMatchEnd);
              break;
            }
          }
          assertEquals("The input form for the rule " + id + " in the example: "
              + example.toString() + " is different than expected (expected "
              + inputForms + " but got " + sortForms(reading) + "). The token has been changed by the disambiguator: " + annotations,
              inputForms, sortForms(reading));
          for (final AnalyzedTokenReadings readings : disambiguatedSent.getTokens()) {
            if (readings.isSentenceStart() && !outputForms.contains("<S>")) {
              continue;
            }
            if (readings.getStartPos() == expectedMatchStart) {
              final AnalyzedTokenReadings[] r = { readings };
              reading = new AnalyzedSentence(r).toShortString(",");
              assertTrue(readings.getStartPos() == expectedMatchStart
                  && readings.getStartPos() + readings.getToken().length() == expectedMatchEnd);
              break;
            }
          }
View Full Code Here
200
201
202
203
204
205
206
207
208
209
210
  // useful for testing the rule cascade
  private static AnalyzedSentence disambiguateUntil(
      final List<DisambiguationPatternRule> rules, final String ruleID,
      final AnalyzedSentence sentence) throws IOException {
    AnalyzedSentence disambiguated = sentence;
    for (final DisambiguationPatternRule rule : rules) {
      if (ruleID.equals(rule.getId())) {
        break;
      }
      disambiguated = rule.replace(disambiguated);
View Full Code Here
770
771
772
773
774
775
776
777
778
779
780
781
    // tag text
    final List<String> sentences = langTool.sentenceTokenize(textArea.getText());
    final StringBuilder sb = new StringBuilder();
    try {
      for (String sent : sentences) {
        final AnalyzedSentence analyzedText = langTool.getAnalyzedSentence(sent);
        final String analyzedTextString = StringTools.escapeHTML(analyzedText.toString(",")).
                replace("&lt;S&gt;", "&lt;S&gt;<br>").
                replace("[", "<font color='" + TAG_COLOR + "'>[").
                replace("]", "]</font><br>");
        sb.append(analyzedTextString).append('\n');
      }
View Full Code Here
29
30
31
32
33
34
35
36
37
38
39
class TestFrenchDisambiguator implements Disambiguator {

  @Override
  public AnalyzedSentence disambiguate(AnalyzedSentence input) throws IOException {
    AnalyzedSentence sentence = input;
    String filePath = "/disambiguator.xml";
    try (InputStream inputStream = getClass().getResourceAsStream(filePath)) {
      final DisambiguationRuleLoader ruleLoader = new DisambiguationRuleLoader();
      List<DisambiguationPatternRule> disambiguationRules = ruleLoader.getRules(inputStream);
      for (final DisambiguationPatternRule patternRule : disambiguationRules) {
View Full Code Here
54
55
56
57
58
59
60
61
62
63
64
65
   *
   * @param contents Text to tag.
   * @param lt LanguageTool instance
   */
  public static void tagText(final String contents, final JLanguageTool lt) throws IOException {
    AnalyzedSentence analyzedText;
    final List<String> sentences = lt.sentenceTokenize(contents);
    for (final String sentence : sentences) {
      analyzedText = lt.getAnalyzedSentence(sentence);
      System.out.println(analyzedText.toString());
    }
  }
View Full Code Here
82
83
84
85
86
87
88
89
90
91
92
93
94
    if (tokenIter == null || !tokenIter.hasNext()) {
      // there are no remaining tokens from the current sentence... are there more sentences?
      if (input.incrementToken()) {
        // a new sentence is available: process it.
        final AnalyzedSentence sentence = languageTool.getAnalyzedSentence(termAtt.toString());

        final List<AnalyzedTokenReadings> tokenBuffer = Arrays.asList(sentence.getTokens());
        tokenIter = tokenBuffer.iterator();
        /*
         * it should not be possible to have a sentence with 0 words, check just in case. returning
         * EOS isn't the best either, but it's the behavior of the original code.
         */
 
View Full Code Here
102
103
104
105
106
107
108
109
110
111
112
    assertEquals(Arrays.asList("нервах", "нерви"), matches[0].getSuggestedReplacements());
   
    assertEquals(1, rule.match(langTool.getAnalyzedSentence("в п'ятьом людям")).length);
    assertEquals(1, rule.match(langTool.getAnalyzedSentence("в понад п'ятьом людям")).length);

    AnalyzedSentence analyzedSentence = langTool.getAnalyzedSentence("завдяки їх вдалим трюкам");
    RuleMatch[] match = rule.match(analyzedSentence);
    assertEquals(1, match.length);
    List<String> suggestedReplacements = match[0].getSuggestedReplacements();
    assertTrue("Did not find «їхній»: " + suggestedReplacements, suggestedReplacements.contains("їхнім"));
  }
View Full Code Here
161
162
163
164
165
166
167
            }
          }
        }
      }
    }
    return new AnalyzedSentence(output);
  }
View Full Code Here
251
252
253
254
255
256
257
258
259
260
261
      final String sentence = doc.get(FIELD_NAME);
      final List<RuleMatch> ruleMatches = languageTool.check(sentence);
      if (ruleMatches.size() > 0) {
        final String source = doc.get(SOURCE_FIELD_NAME);
        final String title = doc.get(Indexer.TITLE_FIELD_NAME);
        final AnalyzedSentence analyzedSentence = languageTool.getAnalyzedSentence(sentence);
        final MatchingSentence matchingSentence = new MatchingSentence(sentence, source, title, analyzedSentence, ruleMatches);
        matchingSentences.add(matchingSentence);
      }
    }
    return matchingSentences;
View Full Code Here
55
56
57
58
59
60
61
62
63
64
65
66
   * @since 1.0.1
   */
  public static List<RuleMatch> checkBitext(final String src, final String trg,
                                            final JLanguageTool srcLt, final JLanguageTool trgLt,
                                            final List<BitextRule> bRules) throws IOException {
    final AnalyzedSentence srcText = srcLt.getAnalyzedSentence(src);
    final AnalyzedSentence trgText = trgLt.getAnalyzedSentence(trg);
    final List<RuleMatch> ruleMatches = trgLt.checkAnalyzedSentence(JLanguageTool.ParagraphHandling.NORMAL,
            trgLt.getAllRules(), 0, 0, 1, trg, trgText, null);
    for (BitextRule bRule : bRules) {
      final RuleMatch[] curMatch = bRule.match(srcText, trgText);
      if (curMatch != null) {
View Full Code Here
TOP

Related Classes of org.languagetool.AnalyzedSentence

  • org.languagetool.chunking.EnglishChunkerTest
  • org.languagetool.commandline.CommandLineTools
  • org.languagetool.dev.index.LanguageToolFilter
  • org.languagetool.dev.index.Searcher
  • org.languagetool.dev.POSTagLanguageModel
  • org.languagetool.dev.SuggestionExtractorTool
  • org.languagetool.gui.Main
  • org.languagetool.rules.bitext.BitextPatternRuleTest
  • org.languagetool.rules.bitext.FalseFriendsAsBitextLoaderTest
  • org.languagetool.rules.de.CaseRuleTest
    • 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.