Examples of edu.stanford.nlp.util.ArrayCoreMap

edu.stanford.nlp.util.ArrayCoreMap

Base implementation of {@link CoreMap} backed by two Java arrays.

Reasonable care has been put into ensuring that this class is both fast and has a light memory footprint.

Note that like the base classes in the Collections API, this implementation is not thread-safe. For speed reasons, these methods are not synchronized. A synchronized wrapper could be developed by anyone so inclined.

Equality is defined over the complete set of keys and values currently stored in the map. Because this class is mutable, it should not be used as a key in a Map.
@author dramage @author rafferty


              sent.add(c);
            }
          }
        }
        CoreMap sentcm = new ArrayCoreMap();
        sentcm.set(CoreAnnotations.TextAnnotation.class, sentStr.trim());
        sentcm.set(CoreAnnotations.TokensAnnotation.class, sent);
        sentcm.set(CoreAnnotations.DocIDAnnotation.class, id + "-" + sentNum);
        sentences.add(sentcm);
      }
    }
    return sentences;
  }

View Full Code Here

          Timex timex = new Timex(child);
          if (child.getChildNodes().getLength() != 1) {
            throw new RuntimeException("TIMEX3 should only contain text " + child);
          }
          String timexText = child.getTextContent();
          CoreMap timexMap = new ArrayCoreMap();
          //(timex)
          timexMap.set(TimeAnnotations.TimexAnnotation.class, timex);
          //(text)
          timexMap.set(CoreAnnotations.TextAnnotation.class, timexText);
          //(characters)
          int charBegin = offset;
          timexMap.set(CoreAnnotations.CharacterOffsetBeginAnnotation.class, charBegin);
          offset += timexText.length();
          int charEnd = offset;
          timexMap.set(CoreAnnotations.CharacterOffsetEndAnnotation.class, charEnd);
          //(tokens)
          if(haveTokenOffsets){
            Integer tokBegin = beginMap.get(charBegin);
            int searchStep = 1;          //if no exact match, search around the character offset
            while(tokBegin == null){
              tokBegin = beginMap.get(charBegin - searchStep);
              if(tokBegin == null){
                tokBegin = beginMap.get(charBegin + searchStep);
              }
              searchStep += 1;
            }
            searchStep = 1;
            Integer tokEnd = endMap.get(charEnd);
            while(tokEnd == null){
              tokEnd = endMap.get(charEnd - searchStep);
              if(tokEnd == null){
                tokEnd = endMap.get(charEnd + searchStep);
              }
              searchStep += 1;
            }
            timexMap.set(CoreAnnotations.TokenBeginAnnotation.class, tokBegin);
            timexMap.set(CoreAnnotations.TokenEndAnnotation.class, tokEnd);
          }
          //(add)
          timexMaps.add(timexMap);
        } else {
          throw new RuntimeException("unexpected element " + child);

View Full Code Here

    tokens.get(1).set(CoreAnnotations.NamedEntityTagAnnotation.class, "PERSON");
    tokens.get(2).set(CoreAnnotations.NamedEntityTagAnnotation.class, "PERSON");
    tokens.get(5).set(CoreAnnotations.NamedEntityTagAnnotation.class, "LOCATION");
    tokens.get(7).set(CoreAnnotations.NamedEntityTagAnnotation.class, "LOCATION");


    CoreMap sentence = new ArrayCoreMap();
    sentence.set(CoreAnnotations.TokensAnnotation.class, tokens);


    List<CoreMap> sentences = new ArrayList<CoreMap>();
    sentences.add(sentence);


    Annotation corpus = new Annotation("President Barack Obama lives in Chicago, Illinois," +

View Full Code Here

    tokens.get(3).set(CoreAnnotations.NamedEntityTagAnnotation.class, "LOCATION");
    tokens.get(9).set(CoreAnnotations.NamedEntityTagAnnotation.class, "ORGANIZATION");
    tokens.get(10).set(CoreAnnotations.NamedEntityTagAnnotation.class, "ORGANIZATION");
    tokens.get(11).set(CoreAnnotations.NamedEntityTagAnnotation.class, "ORGANIZATION");


    CoreMap sentence = new ArrayCoreMap();
    sentence.set(CoreAnnotations.TokensAnnotation.class, tokens);


    List<CoreMap> sentences = new ArrayList<CoreMap>();
    sentences.add(sentence);


    Annotation corpus = new Annotation("I like Ontario Place, and I like the Native" +

View Full Code Here

    String str = "Christianity is of higher regex priority than Early Christianity . ";
    String[] split = str.split(" ");


    List<CoreLabel> tokens = Sentence.toCoreLabelList(split);


    CoreMap sentence = new ArrayCoreMap();
    sentence.set(CoreAnnotations.TokensAnnotation.class, tokens);


    List<CoreMap> sentences = new ArrayList<CoreMap>();
    sentences.add(sentence);


    Annotation corpus = new Annotation("Christianity is of higher regex priority than Early " +

View Full Code Here

    return os.toString();
  }
  
  public CoreMap attributeMap() {
    if(attributeMap == null){
      attributeMap = new ArrayCoreMap();
    }
    return attributeMap;
  }

View Full Code Here

  }


  public void testSentencesAnnotation() throws Exception {
    List<CoreLabel> words = getTestWords();


    CoreMap sentence = new ArrayCoreMap();
    sentence.set(CoreAnnotations.TokensAnnotation.class, words);
    List<CoreMap> sentences = new ArrayList<CoreMap>();
    sentences.add(sentence);
    Annotation document = new Annotation(text);
    document.set(CoreAnnotations.SentencesAnnotation.class, sentences);

View Full Code Here

          Timex timex = new Timex(child);
          if (child.getChildNodes().getLength() != 1) {
            throw new RuntimeException("TIMEX3 should only contain text " + child);
          }
          String timexText = child.getTextContent();
          CoreMap timexMap = new ArrayCoreMap();
          timexMap.set(TimeAnnotations.TimexAnnotation.class, timex);
          timexMap.set(CoreAnnotations.TextAnnotation.class, timexText);
          int charBegin = offset;
          timexMap.set(CoreAnnotations.CharacterOffsetBeginAnnotation.class, offset);
          offset += timexText.length();
          timexMap.set(CoreAnnotations.CharacterOffsetEndAnnotation.class, offset);
          int charEnd = offset;
          //(tokens)
          if(haveTokenOffsets){
            Integer tokBegin = beginMap.get(charBegin);
            int searchStep = 1;          //if no exact match, search around the character offset
            while(tokBegin == null){
              tokBegin = beginMap.get(charBegin - searchStep);
              if(tokBegin == null){
                tokBegin = beginMap.get(charBegin + searchStep);
              }
              searchStep += 1;
            }
            searchStep = 1;
            Integer tokEnd = endMap.get(charEnd);
            while(tokEnd == null){
              tokEnd = endMap.get(charEnd - searchStep);
              if(tokEnd == null){
                tokEnd = endMap.get(charEnd + searchStep);
              }
              searchStep += 1;
            }
            timexMap.set(CoreAnnotations.TokenBeginAnnotation.class, tokBegin);
            timexMap.set(CoreAnnotations.TokenEndAnnotation.class, tokEnd);
          }
          timexMaps.add(timexMap);
        } else {
          throw new RuntimeException("unexpected element " + child);
        }

View Full Code Here

    return labels;
  }


  static public CoreMap makeSentenceCoreMap(String sentence){
    List<CoreLabel> tokens = makeSentence(sentence);
    CoreMap map = new ArrayCoreMap(1);
    map.set(CoreAnnotations.TokensAnnotation.class, tokens);
    return map;
  }

View Full Code Here

   * Test that a single sentence works for the SentenceAnnotation
   */
  public void testSentencesAnnotation() {
    List<CoreLabel> labels = makeSentence(testSentences[0]);


    CoreMap sentence = new ArrayCoreMap();
    sentence.set(CoreAnnotations.TokensAnnotation.class, labels);
    List<CoreMap> sentences = new ArrayList<CoreMap>();
    sentences.add(sentence);
    
    Annotation annotation = new Annotation(shortText);
    annotation.set(CoreAnnotations.SentencesAnnotation.class, sentences);

View Full Code Here

0 1

TOP

Related Classes of edu.stanford.nlp.util.ArrayCoreMap

edu.stanford.nlp.ie.machinereading.structure.ExtractionObject

edu.stanford.nlp.patterns.surface.AnnotatedTextReader

edu.stanford.nlp.pipeline.AnnotationTest

edu.stanford.nlp.pipeline.MorphaAnnotatorITest

edu.stanford.nlp.pipeline.POSTaggerAnnotatorITest

edu.stanford.nlp.pipeline.RegexNERAnnotatorITest

edu.stanford.nlp.time.GUTimeAnnotator

edu.stanford.nlp.time.HeidelTimeAnnotator

edu.stanford.nlp.time.ParsedGigawordReader

java.util.NoSuchElementException

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.