1
package org.apache.solr.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.Reader;
21
import java.io.StringReader;
23
import org.apache.lucene.analysis.TokenStream;
26
* Simple tests to ensure the CJK tokenizer factory is working.
28
public class TestCJKTokenizerFactory extends BaseTokenTestCase {
30
* Ensure the tokenizer actually tokenizes CJK text correctly
32
public void testTokenizer() throws Exception {
33
Reader reader = new StringReader("我是中国人");
34
CJKTokenizerFactory factory = new CJKTokenizerFactory();
35
TokenStream stream = factory.create(reader);
36
assertTokenStreamContents(stream, new String[] {"我是", "是中", "中国", "国人"});