edu.stanford.nlp.ling.BasicDatum 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.ling;

import java.util.ArrayList;
import java.util.Collection;
import java.util.List;

/**
 * Basic implementation of Datum interface that can be constructed with a
 * Collection of features and one more more labels. The features must be
 * specified
 * at construction, but the labels can be set and/or changed later.
 *
 * @author Joseph Smarr ([email protected])
 * @author Sarah Spikes ([email protected]) (Templatization)
 *
 * @param  The type of the labels in the Dataset
 * @param  The type of the features in the Dataset
 */
public class BasicDatum implements Datum {

  /**
   * features for this Datum
   */
  @SuppressWarnings({"NonSerializableFieldInSerializableClass"})
  private final Collection features;

  /**
   * labels for this Datum. Invariant: always non-null
   */
  @SuppressWarnings({"NonSerializableFieldInSerializableClass"})
  private final List labels = new ArrayList<>();

  /**
   * Constructs a new BasicDatum with the given features and labels.
   */
  public BasicDatum(Collection features, Collection labels) {
    this(features);
    setLabels(labels);
  }

  /**
   * Constructs a new BasicDatum with the given features and label.
   */
  public BasicDatum(Collection features, LabelType label) {
    this(features);
    setLabel(label);
  }

  /**
   * Constructs a new BasicDatum with the given features and no labels.
   */
  public BasicDatum(Collection features) {
    this.features = features;
  }

  /**
   * Constructs a new BasicDatum with no features or labels.
   */
  public BasicDatum() {
    this(null);
  }

  /**
   * Returns the collection that this BasicDatum was constructed with.
   */
  public Collection asFeatures() {
    return (features);
  }

  /**
   * Returns the first label for this Datum, or null if none have been set.
   */
  public LabelType label() {
    return ((labels.size() > 0) ?  labels.get(0) : null);
  }

  /**
   * Returns the complete List of labels for this Datum, which may be empty.
   */
  public Collection labels() {
    return labels;
  }

  /**
   * Removes all currently assigned Labels for this Datum then adds the
   * given Label.
   * Calling setLabel(null) effectively clears all labels.
   */
  public void setLabel(LabelType label) {
    labels.clear();
    addLabel(label);
  }

  /**
   * Removes all currently assigned labels for this Datum then adds all
   * of the given Labels.
   */
  public void setLabels(Collection labels) {
    this.labels.clear();
    if (labels != null) {
      this.labels.addAll(labels);
    }
  }

  /**
   * Adds the given Label to the List of labels for this Datum if it is not
   * null.
   */
  public void addLabel(LabelType label) {
    if (label != null) {
      labels.add(label);
    }
  }

  /**
   * Returns a String representation of this BasicDatum (lists features and labels).
   */
  @Override
  public String toString() {
    return ("BasicDatum[features=" + asFeatures() + ",labels=" + labels() + "]");
  }


  /**
   * Returns whether the given Datum contains the same features as this Datum.
   * Doesn't check the labels, should we change this?
   */
  @SuppressWarnings("unchecked")
  @Override
  public boolean equals(Object o) {
    if (!(o instanceof Datum)) {
      return (false);
    }

    Datum d = (Datum) o;
    return features.equals(d.asFeatures());
  }

  public int hashCode() {
    return features.hashCode();
  }

  private static final long serialVersionUID = -4857004070061779966L;

}