/*
 * 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.
 */
package org.apache.lucene.analysis.wikipedia;

import java.io.StringReader;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.tests.util.LuceneTestCase;

public class TestWikipediaTokenizerLinkCjk extends LuceneTestCase {

  public void testCjkInsideInternalLink() throws Exception {
    StringBuilder terms = new StringBuilder();
    try (WikipediaTokenizer tokenizer = new WikipediaTokenizer()) {
      tokenizer.setReader(new StringReader("[[日本]]"));
      CharTermAttribute term = tokenizer.addAttribute(CharTermAttribute.class);
      tokenizer.reset();
      while (tokenizer.incrementToken()) {
        terms.append(term);
      }
      tokenizer.end();
    }
    // expected: the link text 日本 is tokenized, as [[Japan]] gives Japan; actual: no token at all
    assertEquals("日本", terms.toString());
  }
}