beagled/Lucene.Net/Analysis/RU/RussianLowerCaseFilter.cs

   1 /*
   2  * Copyright 2004 The Apache Software Foundation
   3  *
   4  * Licensed under the Apache License, Version 2.0 (the "License");
   5  * you may not use this file except in compliance with the License.
   6  * You may obtain a copy of the License at
   7  *
   8  * http://www.apache.org/licenses/LICENSE-2.0
   9  *
  10  * Unless required by applicable law or agreed to in writing, software
  11  * distributed under the License is distributed on an "AS IS" BASIS,
  12  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  13  * See the License for the specific language governing permissions and
  14  * limitations under the License.
  15  */
  16 using System;
  17 using Token = Lucene.Net.Analysis.Token;
  18 using TokenFilter = Lucene.Net.Analysis.TokenFilter;
  19 using TokenStream = Lucene.Net.Analysis.TokenStream;
  20 namespace Lucene.Net.Analysis.RU
  21 {
  22
  23         /// <summary> Normalizes token text to lower case, analyzing given ("russian") charset.
  24         ///
  25         /// </summary>
  26         /// <author>   Boris Okner, b.okner@rogers.com
  27         /// </author>
  28         /// <version>  $Id: RussianLowerCaseFilter.cs,v 1.2 2005/01/17 19:54:28 joeshaw Exp $
  29         /// </version>
  30         public sealed class RussianLowerCaseFilter : TokenFilter
  31         {
  32                 internal char[] charset;
  33
  34                 public RussianLowerCaseFilter(TokenStream in_Renamed, char[] charset):base(in_Renamed)
  35                 {
  36                         this.charset = charset;
  37                 }
  38
  39                 public override Token Next()
  40                 {
  41                         Token t = input.Next();
  42
  43                         if (t == null)
  44                                 return null;
  45
  46                         System.String txt = t.TermText();
  47
  48                         char[] chArray = txt.ToCharArray();
  49                         for (int i = 0; i < chArray.Length; i++)
  50                         {
  51                                 chArray[i] = RussianCharsets.ToLowerCase(chArray[i], charset);
  52                         }
  53
  54                         System.String newTxt = new System.String(chArray);
  55                         // create new token
  56                         Token newToken = new Token(newTxt, t.StartOffset(), t.EndOffset());
  57
  58                         return newToken;
  59                 }
  60         }
  61 }