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 LetterTokenizer is a tokenizer that divides text at non-letters. That's
23: to say, it defines tokens as maximal strings of adjacent letters, as defined
24: by java.lang.Character.isLetter() predicate.
25:
26: Note: this does a decent job for most European languages, but does a terrible
27: job for some Asian languages, where words are not separated by spaces. */
28:
29: public class LetterTokenizer extends CharTokenizer {
30: /** Construct a new LetterTokenizer. */
31: public LetterTokenizer(Reader in) {
32: super (in);
33: }
34:
35: /** Collects only characters which satisfy
36: * {@link Character#isLetter(char)}.*/
37: protected boolean isTokenChar(char c) {
38: return Character.isLetter(c);
39: }
40: }
|