Save This Page
Home » lucene-3.0.1-src » org.apache » lucene » analysis » [javadoc | source]
    1   package org.apache.lucene.analysis;
    2   
    3   /**
    4    * Licensed to the Apache Software Foundation (ASF) under one or more
    5    * contributor license agreements.  See the NOTICE file distributed with
    6    * this work for additional information regarding copyright ownership.
    7    * The ASF licenses this file to You under the Apache License, Version 2.0
    8    * (the "License"); you may not use this file except in compliance with
    9    * the License.  You may obtain a copy of the License at
   10    *
   11    *     http://www.apache.org/licenses/LICENSE-2.0
   12    *
   13    * Unless required by applicable law or agreed to in writing, software
   14    * distributed under the License is distributed on an "AS IS" BASIS,
   15    * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
   16    * See the License for the specific language governing permissions and
   17    * limitations under the License.
   18    */
   19   
   20   import java.io.Reader;
   21   
   22   import org.apache.lucene.util.AttributeSource;
   23   
   24   /**
   25    * LowerCaseTokenizer performs the function of LetterTokenizer
   26    * and LowerCaseFilter together.  It divides text at non-letters and converts
   27    * them to lower case.  While it is functionally equivalent to the combination
   28    * of LetterTokenizer and LowerCaseFilter, there is a performance advantage
   29    * to doing the two tasks at once, hence this (redundant) implementation.
   30    * <P>
   31    * Note: this does a decent job for most European languages, but does a terrible
   32    * job for some Asian languages, where words are not separated by spaces.
   33    */
   34   public final class LowerCaseTokenizer extends LetterTokenizer {
   35     /** Construct a new LowerCaseTokenizer. */
   36     public LowerCaseTokenizer(Reader in) {
   37       super(in);
   38     }
   39   
   40     /** Construct a new LowerCaseTokenizer using a given {@link AttributeSource}. */
   41     public LowerCaseTokenizer(AttributeSource source, Reader in) {
   42       super(source, in);
   43     }
   44   
   45     /** Construct a new LowerCaseTokenizer using a given {@link org.apache.lucene.util.AttributeSource.AttributeFactory}. */
   46     public LowerCaseTokenizer(AttributeFactory factory, Reader in) {
   47       super(factory, in);
   48     }
   49     
   50     /** Converts char to lower case
   51      * {@link Character#toLowerCase(char)}.*/
   52     @Override
   53     protected char normalize(char c) {
   54       return Character.toLowerCase(c);
   55     }
   56   }

Save This Page
Home » lucene-3.0.1-src » org.apache » lucene » analysis » [javadoc | source]