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   /** A LetterTokenizer is a tokenizer that divides text at non-letters.  That's
   25     to say, it defines tokens as maximal strings of adjacent letters, as defined
   26     by java.lang.Character.isLetter() predicate.
   27   
   28     Note: this does a decent job for most European languages, but does a terrible
   29     job for some Asian languages, where words are not separated by spaces. */
   30   
   31   public class LetterTokenizer extends CharTokenizer {
   32     /** Construct a new LetterTokenizer. */
   33     public LetterTokenizer(Reader in) {
   34       super(in);
   35     }
   36     
   37     /** Construct a new LetterTokenizer using a given {@link AttributeSource}. */
   38     public LetterTokenizer(AttributeSource source, Reader in) {
   39       super(source, in);
   40     }
   41     
   42     /** Construct a new LetterTokenizer using a given {@link org.apache.lucene.util.AttributeSource.AttributeFactory}. */
   43     public LetterTokenizer(AttributeFactory factory, Reader in) {
   44       super(factory, in);
   45     }
   46   
   47     /** Collects only characters which satisfy
   48      * {@link Character#isLetter(char)}.*/
   49     @Override
   50     protected boolean isTokenChar(char c) {
   51       return Character.isLetter(c);
   52     }
   53   }

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