resources.sentenceSplitter.grammar.cleanup.jape Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of annie

ANNIE is a general purpose information extraction system that provides the building blocks of many other GATE applications.

There is a newer version: 9.1

Show newest version

/*
*  cleanup.jape
*
* Copyright (c) 1998-2007, The University of Sheffield.
*
*  This file is part of GATE (see http://gate.ac.uk/), and is free
*  software, licenced under the GNU Library General Public License,
*  Version 2, June 1991 (in the distribution as file licence.html,
*  and also available at http://gate.ac.uk/gate/licence.html).
*
*  Valentin Tablan, March 7th, 2007 
* 
*  $Id$
*/

Phase:	cleanup
Input: Token
Options: control = once

//Removes temporary data created by the sentence splitter
Rule: cleanUp
{Token}
-->
{
  //if there were any sentences created, then we need to remove the document
  //feature -> useful for future runs
  doc.getFeatures().remove("temp-last-sentence-end");
  //remove all lookups used for abbreviations
  FeatureMap constraints = Factory.newFeatureMap();
  constraints.put("majorType", "splitter_abbreviation");
  AnnotationSet toRemove = inputAS.get("Lookup", constraints);
  if(toRemove != null) inputAS.removeAll(toRemove);
}