tokensequencelowercase.java

来自「mallet是自然语言处理、机器学习领域的一个开源项目。」· Java 代码 · 共 50 行

/* Copyright (C) 2002 Univ. of Massachusetts Amherst, Computer Science Dept.
   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 edu.umass.cs.mallet.base.pipe;

import edu.umass.cs.mallet.base.types.TokenSequence;
import edu.umass.cs.mallet.base.types.Token;
import edu.umass.cs.mallet.base.types.Instance;
import java.io.*;
/**
 * Convert the text in each token in the token sequence in the data field to lower case.
   @author Andrew McCallum <a href="mailto:[e-mail]">[e-mail]</a>
 */

public class TokenSequenceLowercase extends Pipe implements Serializable
{
	
	public Instance pipe (Instance carrier)
	{
		TokenSequence ts = (TokenSequence) carrier.getData();
		for (int i = 0; i < ts.size(); i++) {
			Token t = ts.getToken(i);
			t.setText(t.getText().toLowerCase());
		}
		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 ();
	}

}