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: /** A WhitespaceTokenizer is a tokenizer that divides text at whitespace.
23: * Adjacent sequences of non-Whitespace characters form tokens. */
24:
25: public class WhitespaceTokenizer extends CharTokenizer {
26: /** Construct a new WhitespaceTokenizer. */
27: public WhitespaceTokenizer(Reader in) {
28: super (in);
29: }
30:
31: /** Collects only characters which do not satisfy
32: * {@link Character#isWhitespace(char)}.*/
33: protected boolean isTokenChar(char c) {
34: return !Character.isWhitespace(c);
35: }
36: }
|