tokensequenceparsefeaturestring.java

这是一个matlab的java实现。里面有许多内容。请大家慢慢捉摸。

/* 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. */




/**
   @author Aron Culotta <a href="mailto:[e-mail]">[e-mail]</a>

	 Convert the string in each field <code>Token.text</code> to a list
	 of Strings (space delimited). Add each string as a feature to the
	 token. If <code>realValued</code> is true, then treat the position
	 in the list as the feature name and the value as a
	 double. Otherwise, the feature name is the string itself and the
	 value is 1.0.
*/

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 edu.umass.cs.mallet.base.util.MalletLogger;
import java.util.regex.Pattern;
import java.util.regex.Matcher;
import java.util.logging.*;
import java.io.*;

public class TokenSequenceParseFeatureString extends Pipe implements Serializable
{
	boolean realValued;
	
	public TokenSequenceParseFeatureString (boolean _realValued) {
		this.realValued = _realValued;		
	}

	public Instance pipe (Instance carrier) {
		TokenSequence ts = (TokenSequence) carrier.getData ();
		for (int i=0; i < ts.size(); i++) {
			Token t = ts.getToken (i);
			String[] values = t.getText().split("\\s+");
			for (int j=0; j < values.length; j++) {
				if (realValued) 
					t.setFeatureValue ("Feature#" + j, Double.parseDouble (values[j]));
				else
					t.setFeatureValue (values[j], 1.0);					
			}
		}
		carrier.setData (ts);
		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);
		out.writeBoolean (realValued);
	}
	
	private void readObject (ObjectInputStream in) throws IOException, ClassNotFoundException {
		int version = in.readInt ();
		realValued = in.readBoolean ();
	}
}