| Classes in this File | Line Coverage | Branch Coverage | Complexity | ||||
| CzechLuceneAnalyzer |
|
| 2.6666666666666665;2.667 |
| 1 | /** | |
| 2 | * Distribution License: | |
| 3 | * JSword is free software; you can redistribute it and/or modify it under | |
| 4 | * the terms of the GNU Lesser General Public License, version 2.1 or later | |
| 5 | * as published by the Free Software Foundation. This program is distributed | |
| 6 | * in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even | |
| 7 | * the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. | |
| 8 | * See the GNU Lesser General Public License for more details. | |
| 9 | * | |
| 10 | * The License is available on the internet at: | |
| 11 | * http://www.gnu.org/copyleft/lgpl.html | |
| 12 | * or by writing to: | |
| 13 | * Free Software Foundation, Inc. | |
| 14 | * 59 Temple Place - Suite 330 | |
| 15 | * Boston, MA 02111-1307, USA | |
| 16 | * | |
| 17 | * © CrossWire Bible Society, 2007 - 2016 | |
| 18 | * | |
| 19 | */ | |
| 20 | package org.crosswire.jsword.index.lucene.analysis; | |
| 21 | ||
| 22 | import java.io.IOException; | |
| 23 | import java.io.Reader; | |
| 24 | ||
| 25 | import org.apache.lucene.analysis.LowerCaseTokenizer; | |
| 26 | import org.apache.lucene.analysis.StopFilter; | |
| 27 | import org.apache.lucene.analysis.TokenStream; | |
| 28 | import org.apache.lucene.analysis.cz.CzechAnalyzer; | |
| 29 | import org.apache.lucene.util.Version; | |
| 30 | ||
| 31 | /** | |
| 32 | * An Analyzer whose {@link TokenStream} is built from a | |
| 33 | * {@link LowerCaseTokenizer} filtered with {@link StopFilter} (optional). | |
| 34 | * Stemming not implemented yet | |
| 35 | * | |
| 36 | * @see gnu.lgpl.License The GNU Lesser General Public License for details. | |
| 37 | * @author Sijo Cherian | |
| 38 | * @author DM SMITH | |
| 39 | */ | |
| 40 | public class CzechLuceneAnalyzer extends AbstractBookAnalyzer { | |
| 41 | 0 | public CzechLuceneAnalyzer() { |
| 42 | 0 | stopSet = CzechAnalyzer.getDefaultStopSet(); |
| 43 | 0 | } |
| 44 | ||
| 45 | /* (non-Javadoc) | |
| 46 | * @see org.apache.lucene.analysis.Analyzer#tokenStream(java.lang.String, java.io.Reader) | |
| 47 | */ | |
| 48 | @Override | |
| 49 | public final TokenStream tokenStream(String fieldName, Reader reader) { | |
| 50 | 0 | TokenStream result = new LowerCaseTokenizer(reader); |
| 51 | ||
| 52 | 0 | if (doStopWords && stopSet != null) { |
| 53 | 0 | result = new StopFilter(false, result, stopSet); |
| 54 | } | |
| 55 | ||
| 56 | 0 | return result; |
| 57 | } | |
| 58 | ||
| 59 | /* (non-Javadoc) | |
| 60 | * @see org.apache.lucene.analysis.Analyzer#reusableTokenStream(java.lang.String, java.io.Reader) | |
| 61 | */ | |
| 62 | @Override | |
| 63 | public TokenStream reusableTokenStream(String fieldName, Reader reader) throws IOException { | |
| 64 | 0 | SavedStreams streams = (SavedStreams) getPreviousTokenStream(); |
| 65 | 0 | if (streams == null) { |
| 66 | 0 | streams = new SavedStreams(new LowerCaseTokenizer(reader)); |
| 67 | 0 | if (doStopWords && stopSet != null) { |
| 68 | 0 | streams.setResult(new StopFilter(StopFilter.getEnablePositionIncrementsVersionDefault(matchVersion), streams.getResult(), stopSet)); |
| 69 | } | |
| 70 | ||
| 71 | 0 | setPreviousTokenStream(streams); |
| 72 | } else { | |
| 73 | 0 | streams.getSource().reset(reader); |
| 74 | } | |
| 75 | 0 | return streams.getResult(); |
| 76 | } | |
| 77 | ||
| 78 | 0 | private final Version matchVersion = Version.LUCENE_29; |
| 79 | } |