Package opennlp.tools.util

Examples of opennlp.tools.util.Span

39
40
41
42
43
44
45
46
47
48
49
  public TokenSample read() throws IOException {
    String inputString = input.read();
   
    if (inputString != null) {
      Span tokens[] = tokenizer.tokenizePos(inputString);
     
      return new TokenSample(inputString, tokens);
    }
   
    return null;
View Full Code Here
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
          tag = "O";
       
        if (tag.startsWith("B-")) {
         
          if (beginIndex != -1) {
            names.add(new Span(beginIndex, endIndex, tags.get(beginIndex).substring(2)));
            beginIndex = -1;
            endIndex = -1;
          }
         
          beginIndex = i;
          endIndex = i +1;
        }
        else if (tag.startsWith("I-")) {
          endIndex++;
        }
        else if (tag.equals("O")) {
          if (beginIndex != -1) {
            names.add(new Span(beginIndex, endIndex, tags.get(beginIndex).substring(2)));
            beginIndex = -1;
            endIndex = -1;
          }
        }
        else {
          throw new IOException("Invalid tag: " + tag);
        }
      }
     
      // if one span remains, create it here
      if (beginIndex != -1)
        names.add(new Span(beginIndex, endIndex, tags.get(beginIndex).substring(2)));
     
      return new NameSample(sentence.toArray(new String[sentence.size()]), names.toArray(new Span[names.size()]), isClearAdaptiveData);
    }
    else if (line != null) {
      // Just filter out empty events, if two lines in a row are empty
View Full Code Here
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
338
339
340
341
342
343
344
   * method assumes that the specified constituent can be inserted into this parse.
   *
   * @param constituent The constituent to be inserted.
   */
  public void insert(final Parse constituent) {
    Span ic = constituent.span;
    if (span.contains(ic)) {
      //double oprob=c.prob;
      int pi=0;
      int pn = parts.size();
      for (; pi < pn; pi++) {
        Parse subPart = parts.get(pi);
        //System.err.println("Parse.insert:con="+constituent+" sp["+pi+"] "+subPart+" "+subPart.getType());
        Span sp = subPart.span;
        if (sp.getStart() >= ic.getEnd()) {
          break;
        }
        // constituent contains subPart
        else if (ic.contains(sp)) {
          //System.err.println("Parse.insert:con contains subPart");
          parts.remove(pi);
          pi--;
          constituent.parts.add(subPart);
          subPart.setParent(constituent);
          //System.err.println("Parse.insert: "+subPart.hashCode()+" -> "+subPart.getParent().hashCode());
          pn = parts.size();
        }
        else if (sp.contains(ic)) {
          //System.err.println("Parse.insert:subPart contains con");
          subPart.insert(constituent);
          return;
        }
      }
View Full Code Here
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
      //System.out.print(head+" ");
      //System.out.print(df.format(prob)+" ");
    }
    for (Iterator<Parse> i = parts.iterator(); i.hasNext();) {
      Parse c = i.next();
      Span s = c.span;
      if (start < s.getStart()) {
        //System.out.println("pre "+start+" "+s.getStart());
        sb.append(encodeToken(text.substring(start, s.getStart())));
      }
      c.show(sb);
      start = s.getEnd();
    }
    if (start < span.getEnd()) {
      sb.append(encodeToken(text.substring(start, span.getEnd())));
    }
    if (!type.equals(AbstractBottomUpParser.TOK_NODE)) {
View Full Code Here
493
494
495
496
497
498
499
500
501
502
503
  public void add(Parse daughter, HeadRules rules) {
    if (daughter.prevPunctSet != null) {
      parts.addAll(daughter.prevPunctSet);
    }
    parts.add(daughter);
    this.span = new Span(span.getStart(),daughter.getSpan().getEnd());
    this.head = rules.getHead(getChildren(),type);
    if (head == null) {
      System.err.println(parts);
    }
    this.headIndex = head.headIndex;
View Full Code Here
504
505
506
507
508
509
510
511
  }

  public void remove(int index) {
    parts.remove(index);
    if (index == 0 || index == parts.size()) { //size is orig last element
      span = new Span((parts.get(0)).span.getStart(),(parts.get(parts.size()-1)).span.getEnd());
    }
  }
View Full Code Here
510
511
512
513
514
515
516
517
518
519
520
    }
  }

  public Parse adjoinRoot(Parse node, HeadRules rules, int parseIndex) {
    Parse lastChild = parts.get(parseIndex);
    Parse adjNode = new Parse(this.text,new Span(lastChild.getSpan().getStart(),node.getSpan().getEnd()),lastChild.getType(),1,rules.getHead(new Parse[]{lastChild,node},lastChild.getType()));
    adjNode.parts.add(lastChild);
    if (node.prevPunctSet != null) {
      adjNode.parts.addAll(node.prevPunctSet);
    }
    adjNode.parts.add(node);
View Full Code Here
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
   * @param rules The head rules for the parser.
   * @return The new parent node of this node and the specified sister node.
   */
  public Parse adjoin(Parse sister, HeadRules rules) {
    Parse lastChild = parts.get(parts.size()-1);
    Parse adjNode = new Parse(this.text,new Span(lastChild.getSpan().getStart(),sister.getSpan().getEnd()),lastChild.getType(),1,rules.getHead(new Parse[]{lastChild,sister},lastChild.getType()));
    adjNode.parts.add(lastChild);
    if (sister.prevPunctSet != null) {
      adjNode.parts.addAll(sister.prevPunctSet);
    }
    adjNode.parts.add(sister);
    parts.set(parts.size()-1,adjNode);
    this.span = new Span(span.getStart(),sister.getSpan().getEnd());
    this.head = rules.getHead(getChildren(),type);
    this.headIndex = head.headIndex;
    return adjNode;
  }
View Full Code Here
105
106
107
108
109
110
111
    }
    else {
      throw new InvalidFormatException("Unkonw type: " + type);
    }
   
    return new Span(begin, end, type);
  }
View Full Code Here
733
734
735
736
737
738
739
      this.head = this;
    }
  }

  public void updateSpan() {
    span = new Span((parts.get(0)).span.getStart(),(parts.get(parts.size()-1)).span.getEnd());
  }
View Full Code Here
TOP

Related Classes of opennlp.tools.util.Span

  • com.bericotech.clavin.extractor.ApacheExtractor
  • com.tamingtext.opennlp.NameFinderTest
  • net.sf.nlpshell.CorefParse
  • net.sf.nlpshell.Main
  • opennlp.tools.chunker.ChunkerMETest
  • opennlp.tools.chunker.ChunkSample
  • opennlp.tools.chunker.ChunkSampleTest
  • opennlp.tools.cmdline.EvaluationErrorPrinter
  • opennlp.tools.cmdline.namefind.TokenNameFinderTool
  • opennlp.tools.cmdline.parser.ParserTool
    • 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.