Lucene.Net/Analysis/RU/RussianStemFilter.cs

   1 using System;
   2 using Lucene.Net.Analysis;
   3
   4 namespace Lucene.Net.Analysis.Ru
   5 {
   6         /* ====================================================================
   7          * The Apache Software License, Version 1.1
   8          *
   9          * Copyright (c) 2001 The Apache Software Foundation.  All rights
  10          * reserved.
  11          *
  12          * Redistribution and use in source and binary forms, with or without
  13          * modification, are permitted provided that the following conditions
  14          * are met:
  15          *
  16          * 1. Redistributions of source code must retain the above copyright
  17          *    notice, this list of conditions and the following disclaimer.
  18          *
  19          * 2. Redistributions in binary form must reproduce the above copyright
  20          *    notice, this list of conditions and the following disclaimer in
  21          *    the documentation and/or other materials provided with the
  22          *    distribution.
  23          *
  24          * 3. The end-user documentation included with the redistribution,
  25          *    if any, must include the following acknowledgment:
  26          *       "This product includes software developed by the
  27          *        Apache Software Foundation (http://www.apache.org/)."
  28          *    Alternately, this acknowledgment may appear in the software itself,
  29          *    if and wherever such third-party acknowledgments normally appear.
  30          *
  31          * 4. The names "Apache" and "Apache Software Foundation" and
  32          *    "Apache Lucene" must not be used to endorse or promote products
  33          *    derived from this software without prior written permission. For
  34          *    written permission, please contact apache@apache.org.
  35          *
  36          * 5. Products derived from this software may not be called "Apache",
  37          *    "Apache Lucene", nor may "Apache" appear in their name, without
  38          *    prior written permission of the Apache Software Foundation.
  39          *
  40          * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
  41          * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
  42          * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
  43          * DISCLAIMED.  IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
  44          * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
  45          * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
  46          * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
  47          * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
  48          * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
  49          * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
  50          * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  51          * SUCH DAMAGE.
  52          * ====================================================================
  53          *
  54          * This software consists of voluntary contributions made by many
  55          * individuals on behalf of the Apache Software Foundation.  For more
  56          * information on the Apache Software Foundation, please see
  57          * <http://www.apache.org/>.
  58          */
  59
  60         /// <summary>
  61         /// A filter that stems Russian words. The implementation was inspired by GermanStemFilter.
  62         /// The input should be filtered by RussianLowerCaseFilter before passing it to RussianStemFilter,
  63         /// because RussianStemFilter only works  with lowercase part of any "russian" charset.
  64         /// <author>Boris Okner, b.okner@rogers.com</author>
  65         /// <version>$Id: RussianStemFilter.cs,v 1.1.1.1 2004/04/29 22:53:51 trow Exp $</version>
  66         /// </summary>
  67         public sealed class RussianStemFilter : TokenFilter
  68         {
  69                 /// <summary>
  70                 /// The actual token in the input stream.
  71                 /// </summary>
  72                 private Token token = null;
  73                 private RussianStemmer stemmer = null;
  74
  75                 public RussianStemFilter(TokenStream _in, char[] charset) : base(_in)
  76                 {
  77                         stemmer = new RussianStemmer(charset);
  78                 }
  79
  80                 /// <summary>
  81                 ///
  82                 /// </summary>
  83                 /// <returns>Returns the next token in the stream, or null at EOS</returns>
  84                 public override Token Next()
  85                 {
  86                         if ((token = input.Next()) == null)
  87                         {
  88                                 return null;
  89                         }
  90                         else
  91                         {
  92                                 String s = stemmer.Stem(token.TermText());
  93                                 if (!s.Equals(token.TermText()))
  94                                 {
  95                                         return new Token(s, token.StartOffset(), token.EndOffset(),
  96                                                 token.Type());
  97                                 }
  98                                 return token;
  99                         }
 100                 }
 101
 102                 /// <summary>
 103                 /// Set a alternative/custom RussianStemmer for this filter.
 104                 /// </summary>
 105                 /// <param name="stemmer"></param>
 106                 public void SetStemmer(RussianStemmer stemmer)
 107                 {
 108                         if (stemmer != null)
 109                         {
 110                                 this.stemmer = stemmer;
 111                         }
 112                 }
 113         }
 114 }