RussianLowerCaseFilter


1   package org.apache.lucene.analysis.ru;
2   
3   /**
4    * Copyright 2004 The Apache Software Foundation
5    *
6    * Licensed under the Apache License, Version 2.0 (the "License");
7    * you may not use this file except in compliance with the License.
8    * You may obtain a copy of the License at
9    *
10   *     http://www.apache.org/licenses/LICENSE-2.0
11   *
12   * Unless required by applicable law or agreed to in writing, software
13   * distributed under the License is distributed on an "AS IS" BASIS,
14   * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15   * See the License for the specific language governing permissions and
16   * limitations under the License.
17   */
18  
19  import org.apache.lucene.analysis.TokenFilter;
20  import org.apache.lucene.analysis.Token;
21  import org.apache.lucene.analysis.TokenStream;
22  
23  /**
24   * Normalizes token text to lower case, analyzing given ("russian") charset.
25   *
26   * @author  Boris Okner, b.okner@rogers.com
27   * @version $Id: RussianLowerCaseFilter.java 150998 2004-08-16 20:30:46Z dnaber $
28   */
29  public final class RussianLowerCaseFilter extends TokenFilter
30  {
31      char[] charset;
32  
33      public RussianLowerCaseFilter(TokenStream in, char[] charset)
34      {
35          super(in);
36          this.charset = charset;
37      }
38  
39      public final Token next() throws java.io.IOException  
40      {
41          Token t = input.next();
42  
43          if (t == null)
44              return null;
45  
46          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          String   newTxt = new String  (chArray);
55          // create new token
56          Token newToken = new Token(newTxt, t.startOffset(), t.endOffset());
57  
58          return newToken;
59      }
60  }
61
A to Z: JavaDoc & Examples Daily Java News & Articles Open Source Projects Open Source Codes Free Computer Books Remove Frame
Popular Tags