01: package org.apache.lucene.analysis;
02:
03: /**
04: * Licensed to the Apache Software Foundation (ASF) under one or more
05: * contributor license agreements. See the NOTICE file distributed with
06: * this work for additional information regarding copyright ownership.
07: * The ASF licenses this file to You under the Apache License, Version 2.0
08: * (the "License"); you may not use this file except in compliance with
09: * 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: /**
23: * LowerCaseTokenizer performs the function of LetterTokenizer
24: * and LowerCaseFilter together. It divides text at non-letters and converts
25: * them to lower case. While it is functionally equivalent to the combination
26: * of LetterTokenizer and LowerCaseFilter, there is a performance advantage
27: * to doing the two tasks at once, hence this (redundant) implementation.
28: * <P>
29: * Note: this does a decent job for most European languages, but does a terrible
30: * job for some Asian languages, where words are not separated by spaces.
31: */
32: public final class LowerCaseTokenizer extends LetterTokenizer {
33: /** Construct a new LowerCaseTokenizer. */
34: public LowerCaseTokenizer(Reader in) {
35: super (in);
36: }
37:
38: /** Collects only characters which satisfy
39: * {@link Character#isLetter(char)}.*/
40: protected char normalize(char c) {
41: return Character.toLowerCase(c);
42: }
43: }
|