edu.stanford.nlp.process.CoreLabelTokenFactory Maven / Gradle / Ivy

Show more of this group Show more artifacts with this name
Show all versions of stanford-corenlp Show documentation

Stanford CoreNLP provides a set of natural language analysis tools which can take raw English language text input and give the base forms of words, their parts of speech, whether they are names of companies, people, etc., normalize dates, times, and numeric quantities, mark up the structure of sentences in terms of phrases and word dependencies, and indicate which noun phrases refer to the same entities. It provides the foundational building blocks for higher level text understanding applications.

There is a newer version: 4.5.7

Show newest version

package edu.stanford.nlp.process;

import java.io.Serializable;

import edu.stanford.nlp.ling.CoreAnnotations;
import edu.stanford.nlp.ling.CoreLabel;

/**
 * Constructs {@link CoreLabel}s from Strings optionally with
 * beginning and ending (character after the end) offset positions in
 * an original text.  The makeToken method will put the token in the
 * OriginalTextAnnotation AND TextAnnotation keys (2 places!),
 * and optionally records
 * begin and position after offsets in BeginPositionAnnotation and
 * EndPositionAnnotation.  If the tokens are built in PTBTokenizer with
 * an "invertible" tokenizer, you will also get a BeforeAnnotation and for
 * the last token an AfterAnnotation.You can also get an empty CoreLabel token
 *
 * @author Anna Rafferty
 * @author Sonal Gupta (now implements CoreTokenFactory, you can make tokens using many options)
 */
public class CoreLabelTokenFactory implements CoreTokenFactory, LexedTokenFactory, Serializable {

  private final boolean addIndices;

  /**
   * Constructor for a new token factory which will add in the word, the
   * "current" annotation, and the begin/end position annotations.
   */
  public CoreLabelTokenFactory() {
    this(true);
  }

  /**
   * Constructor that allows one to choose if index annotation
   * indicating begin/end position will be included in the label.
   *
   * @param addIndices if true, begin and end position annotations will be included (this is the default)
   */
  public CoreLabelTokenFactory(boolean addIndices) {
    super();
    this.addIndices = addIndices;
  }

  /**
   * Constructs a CoreLabel as a String with a corresponding BEGIN and END position.
   * (Does not take substring).
   */
  @Override
  public CoreLabel makeToken(String tokenText, int begin, int length) {
    return makeToken(tokenText, tokenText, begin, length);
  }

  /**
   * Constructs a CoreLabel as a String with a corresponding BEGIN and END position,
   * when the original OriginalTextAnnotation is different from TextAnnotation
   * (Does not take substring).
   */
  public CoreLabel makeToken(String tokenText, String originalText, int begin, int length) {
    CoreLabel cl = addIndices ? new CoreLabel(5) : new CoreLabel();
    cl.setValue(tokenText);
    cl.setWord(tokenText);
    cl.setOriginalText(originalText);
    if(addIndices) {
      cl.set(CoreAnnotations.CharacterOffsetBeginAnnotation.class, begin);
      cl.set(CoreAnnotations.CharacterOffsetEndAnnotation.class, begin+length);
    }
    return cl;
  }

  @Override
  public CoreLabel makeToken() {
    CoreLabel l = new CoreLabel();
    return l;
  }

  @Override
  public CoreLabel makeToken(String[] keys, String[] values) {
    CoreLabel l = new CoreLabel(keys, values);
    return l;
  }

  @Override
  public CoreLabel makeToken(CoreLabel labelToBeCopied) {
    CoreLabel l = new CoreLabel(labelToBeCopied);
    return l;
  }

  private static final long serialVersionUID = 4L;
}