1
package org.apache.lucene.analysis;
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
11
* http://www.apache.org/licenses/LICENSE-2.0
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.
20
import java.io.Reader;
22
import org.apache.lucene.util.AttributeSource;
23
import org.apache.lucene.util.Version;
26
* LowerCaseTokenizer performs the function of LetterTokenizer
27
* and LowerCaseFilter together. It divides text at non-letters and converts
28
* them to lower case. While it is functionally equivalent to the combination
29
* of LetterTokenizer and LowerCaseFilter, there is a performance advantage
30
* to doing the two tasks at once, hence this (redundant) implementation.
32
* Note: this does a decent job for most European languages, but does a terrible
33
* job for some Asian languages, where words are not separated by spaces.
37
* You must specify the required {@link Version} compatibility when creating
38
* {@link LowerCaseTokenizer}:
40
* <li>As of 3.1, {@link CharTokenizer} uses an int based API to normalize and
41
* detect token characters. See {@link CharTokenizer#isTokenChar(int)} and
42
* {@link CharTokenizer#normalize(int)} for details.</li>
46
public final class LowerCaseTokenizer extends LetterTokenizer {
49
* Construct a new LowerCaseTokenizer.
52
* Lucene version to match See {@link <a href="#version">above</a>}
55
* the input to split up into tokens
57
public LowerCaseTokenizer(Version matchVersion, Reader in) {
58
super(matchVersion, in);
62
* Construct a new LowerCaseTokenizer using a given {@link AttributeSource}.
65
* Lucene version to match See {@link <a href="#version">above</a>}
67
* the attribute source to use for this {@link Tokenizer}
69
* the input to split up into tokens
71
public LowerCaseTokenizer(Version matchVersion, AttributeSource source, Reader in) {
72
super(matchVersion, source, in);
76
* Construct a new LowerCaseTokenizer using a given
77
* {@link org.apache.lucene.util.AttributeSource.AttributeFactory}.
80
* Lucene version to match See {@link <a href="#version">above</a>}
82
* the attribute factory to use for this {@link Tokenizer}
84
* the input to split up into tokens
86
public LowerCaseTokenizer(Version matchVersion, AttributeFactory factory, Reader in) {
87
super(matchVersion, factory, in);
91
* Construct a new LowerCaseTokenizer.
93
* @deprecated use {@link #LowerCaseTokenizer(Version, Reader)} instead. This will be
94
* removed in Lucene 4.0.
97
public LowerCaseTokenizer(Reader in) {
98
super(Version.LUCENE_30, in);
102
* Construct a new LowerCaseTokenizer using a given {@link AttributeSource}.
104
* @deprecated use {@link #LowerCaseTokenizer(Version, AttributeSource, Reader)}
105
* instead. This will be removed in Lucene 4.0.
108
public LowerCaseTokenizer(AttributeSource source, Reader in) {
109
super(Version.LUCENE_30, source, in);
113
* Construct a new LowerCaseTokenizer using a given
114
* {@link org.apache.lucene.util.AttributeSource.AttributeFactory}.
116
* @deprecated use {@link #LowerCaseTokenizer(Version, AttributeSource.AttributeFactory, Reader)}
117
* instead. This will be removed in Lucene 4.0.
120
public LowerCaseTokenizer(AttributeFactory factory, Reader in) {
121
super(Version.LUCENE_30, factory, in);
124
/** Converts char to lower case
125
* {@link Character#toLowerCase(int)}.*/
127
protected int normalize(int c) {
128
return Character.toLowerCase(c);