org.cleartk.token.tokenizer.PennTreebankTokenizer Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of cleartk-token Show documentation
Show all versions of cleartk-token Show documentation
ClearTK annotators for sentence segmentation and tokenization
The newest version!
/**
* Copyright (c) 2007-2008, Regents of the University of Colorado
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following disclaimer in the documentation and/or other materials provided with the distribution.
* Neither the name of the University of Colorado at Boulder nor the names of its contributors may be used to endorse or promote products derived from this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
* LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
* SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
* INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
* CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
* POSSIBILITY OF SUCH DAMAGE.
*/
package org.cleartk.token.tokenizer;
import java.util.regex.Pattern;
/**
*
* Copyright (c) 2007-2008, Regents of the University of Colorado
* All rights reserved.
*
*
* @author Philip Ogren
*
* This code was derived directly (i.e. translated) from a python script that Steven Bethard
* gave me called tokenizer.py. This copyright of this script is owned by the Regents of the
* University of Colorado and therefore there is no restriction on our use and distribution
* of this derivitive work here. The python script was derived from a sed script available
* here:
*
* http://www.cis.upenn.edu/~treebank/tokenization.html
*
* Steve's script fixes several misc. errors.
*
* @author Philip Ogren
*
*/
public class PennTreebankTokenizer extends Tokenizer_ImplBase {
// different brace type regexes
public static String openBracesRegex = "\\[\\(\\{\\<";
public static String closedBracesRegex = "\\]\\)\\}\\>";
public static String bracesRegex = "([" + openBracesRegex + closedBracesRegex + "])";
public static Pattern bracesPattern = Pattern.compile(bracesRegex);
// ellipsis regex
public static String ellipsisRegex = "(" + Pattern.quote("...") + ")";
public static Pattern ellipsisPattern = Pattern.compile(ellipsisRegex);
// comma regex - any comma that is not between two digits
public static String commaRegex = "((?