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.IOException;
22 import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
23 import org.apache.lucene.util.CharacterUtils;
24 import org.apache.lucene.util.Version;
27 * Normalizes token text to lower case.
29 * <p>You must specify the required {@link Version}
30 * compatibility when creating LowerCaseFilter:
32 * <li> As of 3.1, supplementary characters are properly lowercased.
35 public final class LowerCaseFilter extends TokenFilter {
36 private final CharacterUtils charUtils;
37 private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
40 * Create a new LowerCaseFilter, that normalizes token text to lower case.
42 * @param matchVersion See <a href="#version">above</a>
43 * @param in TokenStream to filter
45 public LowerCaseFilter(Version matchVersion, TokenStream in) {
47 charUtils = CharacterUtils.getInstance(matchVersion);
51 * @deprecated Use {@link #LowerCaseFilter(Version, TokenStream)} instead.
54 public LowerCaseFilter(TokenStream in) {
55 this(Version.LUCENE_30, in);
59 public final boolean incrementToken() throws IOException {
60 if (input.incrementToken()) {
61 final char[] buffer = termAtt.buffer();
62 final int length = termAtt.length();
63 for (int i = 0; i < length;) {
64 i += Character.toChars(
65 Character.toLowerCase(
66 charUtils.codePointAt(buffer, i)), buffer, i);