package org.apache.lucene.analysis.icu.segmentation;
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.TokenStream;
/** basic tests for {@link ICUTokenizerFactory} **/
public class TestICUTokenizerFactory extends BaseTokenStreamTestCase {
public void testMixedText() throws Exception {
Reader reader = new StringReader("การที่ได้ต้องแสดงว่างานดี This is a test ກວ່າດອກ");
ICUTokenizerFactory factory = new ICUTokenizerFactory();
TokenStream stream = factory.create(reader);
assertTokenStreamContents(stream,
new String[] { "การ", "ที่", "ได้", "ต้อง", "แสดง", "ว่า", "งาน", "ดี",
"This", "is", "a", "test", "ກວ່າ", "ດອກ"});
}
}