| package org.apache.lucene.analysis.standard; |
| |
| /* ==================================================================== |
| * The Apache Software License, Version 1.1 |
| * |
| * Copyright (c) 2001 The Apache Software Foundation. All rights |
| * reserved. |
| * |
| * Redistribution and use in source and binary forms, with or without |
| * modification, are permitted provided that the following conditions |
| * are met: |
| * |
| * 1. Redistributions of source code must retain the above copyright |
| * notice, this list of conditions and the following disclaimer. |
| * |
| * 2. 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. |
| * |
| * 3. The end-user documentation included with the redistribution, |
| * if any, must include the following acknowledgment: |
| * "This product includes software developed by the |
| * Apache Software Foundation (http://www.apache.org/)." |
| * Alternately, this acknowledgment may appear in the software itself, |
| * if and wherever such third-party acknowledgments normally appear. |
| * |
| * 4. The names "Apache" and "Apache Software Foundation" and |
| * "Apache Lucene" must not be used to endorse or promote products |
| * derived from this software without prior written permission. For |
| * written permission, please contact apache@apache.org. |
| * |
| * 5. Products derived from this software may not be called "Apache", |
| * "Apache Lucene", nor may "Apache" appear in their name, without |
| * prior written permission of the Apache Software Foundation. |
| * |
| * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED 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 APACHE SOFTWARE FOUNDATION OR |
| * ITS 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. |
| * ==================================================================== |
| * |
| * This software consists of voluntary contributions made by many |
| * individuals on behalf of the Apache Software Foundation. For more |
| * information on the Apache Software Foundation, please see |
| * <http://www.apache.org/>. |
| */ |
| |
| import org.apache.lucene.analysis.*; |
| |
| /** Normalizes tokens extracted with {@link StandardTokenizer}. */ |
| |
| public final class StandardFilter extends TokenFilter |
| implements StandardTokenizerConstants { |
| |
| |
| /** Construct filtering <i>in</i>. */ |
| public StandardFilter(TokenStream in) { |
| input = in; |
| } |
| |
| private static final String APOSTROPHE_TYPE = tokenImage[APOSTROPHE]; |
| private static final String ACRONYM_TYPE = tokenImage[ACRONYM]; |
| |
| /** Returns the next token in the stream, or null at EOS. |
| * <p>Removes <tt>'s</tt> from the end of words. |
| * <p>Removes dots from acronyms. |
| */ |
| public final org.apache.lucene.analysis.Token next() throws java.io.IOException { |
| org.apache.lucene.analysis.Token t = input.next(); |
| |
| if (t == null) |
| return null; |
| |
| String text = t.termText(); |
| String type = t.type(); |
| |
| if (type == APOSTROPHE_TYPE && // remove 's |
| (text.endsWith("'s") || text.endsWith("'S"))) { |
| return new org.apache.lucene.analysis.Token |
| (text.substring(0,text.length()-2), |
| t.startOffset(), t.endOffset(), type); |
| |
| } else if (type == ACRONYM_TYPE) { // remove dots |
| StringBuffer trimmed = new StringBuffer(); |
| for (int i = 0; i < text.length(); i++) { |
| char c = text.charAt(i); |
| if (c != '.') |
| trimmed.append(c); |
| } |
| return new org.apache.lucene.analysis.Token |
| (trimmed.toString(), t.startOffset(), t.endOffset(), type); |
| |
| } else { |
| return t; |
| } |
| } |
| } |