1
package org.apache.lucene.analysis.in;
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.analysis.CharTokenizer;
23
import org.apache.lucene.util.AttributeSource;
24
import org.apache.lucene.util.Version;
27
* Simple Tokenizer for text in Indian Languages.
29
public final class IndicTokenizer extends CharTokenizer {
31
public IndicTokenizer(Version matchVersion, AttributeFactory factory, Reader input) {
32
super(matchVersion, factory, input);
35
public IndicTokenizer(Version matchVersion, AttributeSource source, Reader input) {
36
super(matchVersion, source, input);
39
public IndicTokenizer(Version matchVersion, Reader input) {
40
super(matchVersion, input);
44
protected boolean isTokenChar(int c) {
45
return Character.isLetter(c)
46
|| Character.getType(c) == Character.NON_SPACING_MARK
47
|| Character.getType(c) == Character.FORMAT
48
|| Character.getType(c) == Character.COMBINING_SPACING_MARK;