runtime/nepomuk/services/storage/cluceneanalyzer.h

   1 /*
   2  * Modified version of StandardAnalyzer.h for Nepomuk mostly to optimize for filename indexing
   3  * Copyright (C) 2008 Sebastian Trueg <trueg@kde.org>
   4  *
   5  * Based on StandardAnalyzer.h from the CLucene package.
   6  * Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
   7  *
   8  * This library is free software; you can redistribute it and/or
   9  * modify it under the terms of the GNU Library General Public
  10  * License as published by the Free Software Foundation; either
  11  * version 2 of the License, or (at your option) any later version.
  12  *
  13  * This library is distributed in the hope that it will be useful,
  14  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  15  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  16  * Library General Public License for more details.
  17  *
  18  * You should have received a copy of the GNU Library General Public License
  19  * along with this library; see the file COPYING.LIB.  If not, write to
  20  * the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
  21  * Boston, MA 02110-1301, USA.
  22  */
  23
  24 #ifndef _NEPOMUK_CLUCENE_ANALYZER_H_
  25 #define _NEPOMUK_CLUCENE_ANALYZER_H_
  26
  27 #include <CLucene.h>
  28 #include <CLucene/clucene-config.h>
  29 #include <CLucene/StdHeader.h>
  30 #include <CLucene/util/VoidMap.h>
  31 #include <CLucene/util/Reader.h>
  32 #include <CLucene/analysis/AnalysisHeader.h>
  33 #include <CLucene/analysis/Analyzers.h>
  34
  35
  36 namespace Nepomuk {
  37
  38         /** Represents a standard analyzer. */
  39         class CLuceneAnalyzer : public CL_NS(analysis)::Analyzer
  40         {
  41         public:
  42                 /** Builds an analyzer.*/
  43                 CLuceneAnalyzer();
  44
  45                 /** Builds an analyzer with the given stop words. */
  46                 CLuceneAnalyzer( const TCHAR** stopWords);
  47
  48                 ~CLuceneAnalyzer();
  49
  50                 /**
  51          * Constructs a StandardTokenizer filtered by a
  52          * StandardFilter, a LowerCaseFilter and a StopFilter.
  53          */
  54                 CL_NS(analysis)::TokenStream* tokenStream(const TCHAR* fieldName, CL_NS(util)::Reader* reader);
  55
  56         private:
  57                 CL_NS(util)::CLSetList<const TCHAR*> stopSet;
  58         };
  59 }
  60
  61 #endif