cc.mallet.pipe.CharSequenceArray2TokenSequence Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of jcore-mallet-2.0.9 Show documentation

MALLET is a Java-based package for statistical natural language processing, document classification, clustering, topic modeling, information extraction, and other machine learning applications to text.

The newest version!

/* Copyright (C) 2003 Univiversity of Pennsylvania.
   This file is part of "MALLET" (MAchine Learning for LanguagE Toolkit).
   http://www.cs.umass.edu/~mccallum/mallet
   This software is provided under the terms of the Common Public License,
   version 1.0, as published by http://www.opensource.org.  For further
   information, see the file `LICENSE' included with this distribution. */


package cc.mallet.pipe;

import java.io.*;
import cc.mallet.types.Instance;
import cc.mallet.types.TokenSequence;

/**
 * Transform an array of character Sequences into a token sequence.
   @author Fernando Pereira [email protected]
 */
public class CharSequenceArray2TokenSequence extends Pipe
  implements Serializable
{
	public CharSequenceArray2TokenSequence ()
	{
	}
  
	public Instance pipe (Instance carrier)
	{
    carrier.setData(new TokenSequence((CharSequence[]) carrier.getData()));
		return carrier;
	}

	// Serialization 
	
	private static final long serialVersionUID = 1;
	private static final int CURRENT_SERIAL_VERSION = 0;
	
	private void writeObject (ObjectOutputStream out) throws IOException {
		out.writeInt(CURRENT_SERIAL_VERSION);
	}
	
	private void readObject (ObjectInputStream in) throws IOException, ClassNotFoundException {
		int version = in.readInt ();
	}
}