Package org.languagetool

Examples of org.languagetool.AnalyzedToken

27
28
29
30
31
32
33
import org.languagetool.AnalyzedToken;

public class EnglishSynthesizerTest extends TestCase {

  private AnalyzedToken dummyToken(String tokenStr) {
    return new AnalyzedToken(tokenStr, tokenStr, tokenStr);
  }
View Full Code Here
35
36
37
38
39
40
41
42
43
44
45
46
47
    for (String word : sentenceTokens) {

      final List<AnalyzedToken> l = new ArrayList<>();

      AnalyzedToken at = asAnalyzedToken(word);
      l.add(at);
      tokenReadings.add(new AnalyzedTokenReadings(l, pos));
      pos += at.getToken().length();
    }

    return tokenReadings;
  }
View Full Code Here
46
47
48
49
50
51
52
    return tokenReadings;
  }

  @Override
  public final AnalyzedTokenReadings createNullToken(final String token, final int startPos) {
    return new AnalyzedTokenReadings(new AnalyzedToken(token, null, null), startPos);
  }
View Full Code Here
51
52
53
54
55
56
57
    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
56
57
58
59
60
61
62
63
64
65
    return new AnalyzedToken(token, posTag, null);
  }

  private AnalyzedToken asAnalyzedToken(final String word) {
    if (word.indexOf("/") < 0) {
      return new AnalyzedToken(" ", null, null);
    }
    String[] parts = word.split("/");
    return new AnalyzedToken(parts[0], parts[1], null);
  }
View Full Code Here
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
137
138
139
    }

    // It must clear attributes, as it is creating new tokens.
    clearAttributes();
    final AnalyzedTokenReadings tr = tokenIter.next();
    AnalyzedToken at = tr.getAnalyzedToken(0);

    // add POS tag for sentence start.
    if (tr.isSentStart()) {
      // TODO: would be needed so negated tokens can match on something (see testNegatedMatchAtSentenceStart())
      // but breaks other cases:
      //termAtt.append("SENT_START");
      typeAtt.setType("pos");
      if (toLowerCase) {
        termAtt.append(POS_PREFIX.toLowerCase() + tr.getAnalyzedToken(0).getPOSTag().toLowerCase());
      } else {
        termAtt.append(POS_PREFIX + tr.getAnalyzedToken(0).getPOSTag());
      }
      return true;
    }

    // by pass the white spaces.
    if (tr.isWhitespace()) {
      return this.incrementToken();
    }

    offsetAtt.setOffset(tr.getStartPos(), tr.getStartPos() + at.getToken().length());

    for (int i = 0; i < tr.getReadingsLength(); i++) {
      at = tr.getAnalyzedToken(i);
      if (at.getPOSTag() != null) {
        if (toLowerCase) {
          posStack.push(POS_PREFIX.toLowerCase() + at.getPOSTag().toLowerCase());
        } else {
          posStack.push(POS_PREFIX + at.getPOSTag());
        }
      }
    }

    current = captureState();
View Full Code Here
103
104
105
106
107
108
109
110
111
112
113
    final Queue<AnalyzedTokenReadings> prevTokens = new ArrayBlockingQueue<>(MAX_TERMS);
    for (int i = 0; i < tokens.length + MAX_TERMS-1; i++) {
      final AnalyzedTokenReadings token;
      // we need to extend the token list so we find matches at the end of the original list:
      if (i >= tokens.length) {
        token = new AnalyzedTokenReadings(new AnalyzedToken("", "", null), prevTokens.peek().getStartPos());
      } else {
        token = tokens[i];
      }
      if (i == 0) {
        addToQueue(token, prevTokens);
View Full Code Here
102
103
104
105
106
107
108
109
110
111
112
        List<AnalyzedToken> additionalTaggedTokens = additionalTags(word);
        addTokens(additionalTaggedTokens, l);      
      }
     
      if (l.isEmpty()) {
        l.add(new AnalyzedToken(word, null, null));
      }
     
      tokenReadings.add(new AnalyzedTokenReadings(l, pos));
      pos += word.length();
    }
View Full Code Here
122
123
124
125
126
127
128
129
130
131
    }
    return aTokenList;
  }

  protected AnalyzedToken asAnalyzedToken(final String word, final WordData wd) {
    return new AnalyzedToken(
        word,
        StringTools.asString(wd.getTag()),
        StringTools.asString(wd.getStem()));
  }
View Full Code Here
152
153
154
155
156
157
158
   * org.languagetool.tagging.Tagger#createNullToken(java.lang.String
   * , int)
   */ 
  @Override
  public final AnalyzedTokenReadings createNullToken(final String token, final int startPos) {
    return new AnalyzedTokenReadings(new AnalyzedToken(token, null, null), startPos);
  }
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.