/*
 * 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.ko;

import java.io.StringReader;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.ko.dict.UserDictionary;
import org.apache.lucene.tests.analysis.BaseTokenStreamTestCase;

public class TestNoriUserDictionaryUtf8Bom extends BaseTokenStreamTestCase {

  public void testLeadingBomKeepsFirstEntry() throws Exception {
    UserDictionary dict = UserDictionary.open(new StringReader("\uFEFF세종시 세종 시\n"));
    Tokenizer tokenizer =
        new KoreanTokenizer(
            newAttributeFactory(), dict, KoreanTokenizer.DecompoundMode.DISCARD, false);
    tokenizer.setReader(new StringReader("세종시"));
    // expected: the user entry segments 세종시 as [세종, 시], as without the BOM; actual: [세, 종시]
    assertTokenStreamContents(tokenizer, new String[] {"세종", "시"});
  }
}