01: package org.apache.lucene.analysis.cn;
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.IOException;
21: import java.io.StringReader;
22:
23: import junit.framework.TestCase;
24:
25: import org.apache.lucene.analysis.Token;
26:
27: /**
28: * @author rayt
29: */
30: public class TestChineseTokenizer extends TestCase {
31: public void testOtherLetterOffset() throws IOException {
32: String s = "a天b";
33: ChineseTokenizer tokenizer = new ChineseTokenizer(
34: new StringReader(s));
35: Token token;
36:
37: int correctStartOffset = 0;
38: int correctEndOffset = 1;
39: while ((token = tokenizer.next()) != null) {
40: assertEquals(correctStartOffset, token.startOffset());
41: assertEquals(correctEndOffset, token.endOffset());
42: correctStartOffset++;
43: correctEndOffset++;
44: }
45: }
46: }
|