Package edu.stanford.nlp.ling

Examples of edu.stanford.nlp.ling.CoreLabel.endPosition()

109
110
111
112
113
114
115
116
117
118
119
          continue;
        }

        // trailing -
        if(crt.endPosition() == nxt.beginPosition() &&
          (i + 2 >= tokens.size() || nxt.endPosition() != tokens.get(i + 2).beginPosition()) &&
          ! isParen(crt.word()) &&
          nxt.word().equals("-")){
          String word = crt.word() + nxt.word();
          output.add(tokenFactory.makeToken(word, crt.beginPosition(), word.length()));
          i ++;
View Full Code Here
183
184
185
186
187
188
189
190
191
192
193
          output.add(tokenFactory.makeToken(sep, token.beginPosition() + sepPos, 1));
        }
        String s3 = token.word().substring(sepPos + 1);
        if(! DISCARD_STANDALONE_DASHES || ! s3.equals("-")){
          output.add(tokenFactory.makeToken(s3, token.beginPosition() + sepPos + 1,
            token.endPosition() - token.beginPosition() - sepPos - 1));
        }

      } else {
        output.add(token);
      }
View Full Code Here
124
125
126
127
128
129
130
131
132
133
134
    List<CoreLabel> output = new ArrayList<CoreLabel>(tokens.size());
    int i = 0;
    CoreLabel token = tokens.get(i);
    for (IntPair offsets:chunkCharOffsets) {
      assert(token.beginPosition() >= 0);
      assert(token.endPosition() >= 0);
      int offsetBegin = offsets.getSource();
      int offsetEnd = offsets.getTarget();
      // Find tokens where token begins after chunk starts
      // and token ends after chunk starts
      while (offsetBegin < token.get(CoreAnnotations.CharacterOffsetBeginAnnotation.class)
View Full Code Here
147
148
149
150
151
152
153
154
155
156
157
          if (offsetEnd < token.get(CoreAnnotations.CharacterOffsetEndAnnotation.class)) {
            output.add(tokenFactory.makeToken(text.substring(token.beginPosition(), offsetBegin),
                    token.beginPosition(), offsetBegin-token.beginPosition()));
            output.add(tokenFactory.makeToken(text.substring(offsetBegin,offsetEnd),
                    offsetBegin, offsetEnd-offsetBegin));
            output.add(tokenFactory.makeToken(text.substring(offsetEnd,token.endPosition()),
                    offsetEnd, token.endPosition()-offsetEnd));
          } else {
            output.add(tokenFactory.makeToken(text.substring(token.beginPosition(), offsetBegin),
                    token.beginPosition(), offsetBegin-token.beginPosition()));
            output.add(tokenFactory.makeToken(text.substring(offsetBegin,token.endPosition()),
View Full Code Here
148
149
150
151
152
153
154
155
156
157
158
            output.add(tokenFactory.makeToken(text.substring(token.beginPosition(), offsetBegin),
                    token.beginPosition(), offsetBegin-token.beginPosition()));
            output.add(tokenFactory.makeToken(text.substring(offsetBegin,offsetEnd),
                    offsetBegin, offsetEnd-offsetBegin));
            output.add(tokenFactory.makeToken(text.substring(offsetEnd,token.endPosition()),
                    offsetEnd, token.endPosition()-offsetEnd));
          } else {
            output.add(tokenFactory.makeToken(text.substring(token.beginPosition(), offsetBegin),
                    token.beginPosition(), offsetBegin-token.beginPosition()));
            output.add(tokenFactory.makeToken(text.substring(offsetBegin,token.endPosition()),
                    offsetBegin, token.endPosition()-offsetBegin));
View Full Code Here
152
153
154
155
156
157
158
159
160
161
162
            output.add(tokenFactory.makeToken(text.substring(offsetEnd,token.endPosition()),
                    offsetEnd, token.endPosition()-offsetEnd));
          } else {
            output.add(tokenFactory.makeToken(text.substring(token.beginPosition(), offsetBegin),
                    token.beginPosition(), offsetBegin-token.beginPosition()));
            output.add(tokenFactory.makeToken(text.substring(offsetBegin,token.endPosition()),
                    offsetBegin, token.endPosition()-offsetBegin));
          }
        } else if (offsetEnd < token.get(CoreAnnotations.CharacterOffsetEndAnnotation.class)) {
          output.add(tokenFactory.makeToken(text.substring(token.beginPosition(),offsetEnd),
                  token.beginPosition(), offsetEnd-token.beginPosition()));
View Full Code Here
153
154
155
156
157
158
159
160
161
162
163
                    offsetEnd, token.endPosition()-offsetEnd));
          } else {
            output.add(tokenFactory.makeToken(text.substring(token.beginPosition(), offsetBegin),
                    token.beginPosition(), offsetBegin-token.beginPosition()));
            output.add(tokenFactory.makeToken(text.substring(offsetBegin,token.endPosition()),
                    offsetBegin, token.endPosition()-offsetBegin));
          }
        } else if (offsetEnd < token.get(CoreAnnotations.CharacterOffsetEndAnnotation.class)) {
          output.add(tokenFactory.makeToken(text.substring(token.beginPosition(),offsetEnd),
                  token.beginPosition(), offsetEnd-token.beginPosition()));
          output.add(tokenFactory.makeToken(text.substring(offsetEnd,token.endPosition()), offsetEnd,
View Full Code Here
158
159
160
161
162
163
164
165
166
167
168
                    offsetBegin, token.endPosition()-offsetBegin));
          }
        } else if (offsetEnd < token.get(CoreAnnotations.CharacterOffsetEndAnnotation.class)) {
          output.add(tokenFactory.makeToken(text.substring(token.beginPosition(),offsetEnd),
                  token.beginPosition(), offsetEnd-token.beginPosition()));
          output.add(tokenFactory.makeToken(text.substring(offsetEnd,token.endPosition()), offsetEnd,
                  token.endPosition()-offsetEnd));
        } else {
          // success!  chunk contains token
          output.add(token);
        }
View Full Code Here
159
160
161
162
163
164
165
166
167
168
169
          }
        } else if (offsetEnd < token.get(CoreAnnotations.CharacterOffsetEndAnnotation.class)) {
          output.add(tokenFactory.makeToken(text.substring(token.beginPosition(),offsetEnd),
                  token.beginPosition(), offsetEnd-token.beginPosition()));
          output.add(tokenFactory.makeToken(text.substring(offsetEnd,token.endPosition()), offsetEnd,
                  token.endPosition()-offsetEnd));
        } else {
          // success!  chunk contains token
          output.add(token);
        }
        i++;
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.