001/** 002 * Copyright (c) 2007-2008, Regents of the University of Colorado 003 * All rights reserved. 004 * 005 * Redistribution and use in source and binary forms, with or without 006 * modification, are permitted provided that the following conditions are met: 007 * 008 * Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer. 009 * 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. 010 * 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. 011 * 012 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" 013 * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 014 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 015 * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE 016 * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR 017 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF 018 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS 019 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN 020 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) 021 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE 022 * POSSIBILITY OF SUCH DAMAGE. 023 */ 024package org.cleartk.token.tokenizer; 025 026import java.util.ArrayList; 027import java.util.List; 028 029/** 030 * <br> 031 * Copyright (c) 2007-2008, Regents of the University of Colorado <br> 032 * All rights reserved. 033 * 034 * <p> 035 */ 036public abstract class Tokenizer_ImplBase implements Tokenizer { 037 038 public abstract String[] getTokenTexts(String text); 039 040 /** 041 * performs tokenization on the input text and returns the character offsets corresponding to the 042 * begining and end of each token w.r.t. the input text. 043 * 044 * @param text 045 * the text that you want tokenized. 046 * @return offsets corresponding to the begining and end of each token. The dimensions of the 047 * returned array will be number of tokens returned by getTokens by 2 (one for token begin 048 * and one for token end). 049 * 050 * <pre> 051 * 052 * <code> int[][] offsets = getTokenOffsets("example text"); int 053 * beginFirstToken = offsets[0][0]; int endFirstToken = 054 * offsets[0][1]; int begin4thToken = offsets[3][0]; int end4thToken 055 * = offsets[3][1]; 056 * 057 * </pre> 058 * 059 * </code> 060 * 061 */ 062 public List<Token> getTokens(String text) { 063 List<Token> returnValues = new ArrayList<Token>(); 064 String[] tokenTexts = getTokenTexts(text); 065 if (text.length() > 0) { 066 int offset = 0; 067 for (String tokenText : tokenTexts) { 068 while (text.charAt(offset) != tokenText.charAt(0)) 069 offset++; 070 071 Token token = new Token(offset, offset + tokenText.length(), tokenText); 072 returnValues.add(token); 073 offset += tokenText.length(); 074 } 075 } 076 077 return returnValues; 078 } 079 080}