Package edu.stanford.nlp.ling.tokensregex

Examples of edu.stanford.nlp.ling.tokensregex.TokenSequenceMatcher.start()

450
451
452
453
454
455
456
457
458
459
460
    TokenSequenceMatcher matcher = numberPattern.getMatcher(tokens);
    List<CoreMap> numbers = new ArrayList<CoreMap>();
    while (matcher.find()) {
      @SuppressWarnings("unused")
      List<CoreMap> matchedTokens = matcher.groupNodes();
      int numStart = matcher.start();
      int possibleNumEnd = -1;
      int lastUnitPos = -1;
      int possibleNumStart = -1;
      Number possibleNumEndUnit = null;
      Number lastUnit = null;
View Full Code Here
457
458
459
460
461
462
463
464
465
466
467
      int lastUnitPos = -1;
      int possibleNumStart = -1;
      Number possibleNumEndUnit = null;
      Number lastUnit = null;
      // Check if we need to split matched chunk up more
      for (int i = matcher.start(); i < matcher.end(); i++) {
        CoreLabel token = tokens.get(i);
        CoreLabel prev = (i > matcher.start())? tokens.get(i - 1): null;
        Number num = token.get(CoreAnnotations.NumericValueAnnotation.class);
        Number prevNum = (prev != null)? prev.get(CoreAnnotations.NumericValueAnnotation.class):null;
        String w = token.word();
View Full Code Here
459
460
461
462
463
464
465
466
467
468
469
      Number possibleNumEndUnit = null;
      Number lastUnit = null;
      // Check if we need to split matched chunk up more
      for (int i = matcher.start(); i < matcher.end(); i++) {
        CoreLabel token = tokens.get(i);
        CoreLabel prev = (i > matcher.start())? tokens.get(i - 1): null;
        Number num = token.get(CoreAnnotations.NumericValueAnnotation.class);
        Number prevNum = (prev != null)? prev.get(CoreAnnotations.NumericValueAnnotation.class):null;
        String w = token.word();
        w = w.trim().toLowerCase();
        switch (w) {
View Full Code Here
690
691
692
693
694
695
696
697
698
699
700
        numberRanges.add(matched.get(0));
      } else {
        Number v1 = matched.get(0).get(CoreAnnotations.NumericCompositeValueAnnotation.class);
        Number v2 = matched.get(matched.size()-1).get(CoreAnnotations.NumericCompositeValueAnnotation.class);
        if (v2.doubleValue() > v1.doubleValue()) {
          CoreMap newChunk = ChunkAnnotationUtils.getMergedChunk(numerizedTokens,  matcher.start(), matcher.end(),
                  CoreMapAttributeAggregator.getDefaultAggregators());
          newChunk.set(CoreAnnotations.NumericCompositeTypeAnnotation.class, "NUMBER_RANGE");
          Pair<Number,Number> range = new Pair<Number,Number>(v1,v2);
          newChunk.set(CoreAnnotations.NumericCompositeObjectAnnotation.class, range);
          numberRanges.add(newChunk);
View Full Code Here
55
56
57
58
59
60
61
62
63
64
65
        //Higher branch values makes the faster but uses more memory
        m.setBranchLimit(5);

        while (m.find()) {

          int s = m.start("$term");
          int e = m.end("$term");

          String phrase = "";
          String phraseLemma = "";
          boolean useWordNotLabeled = false;
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.