/*
 * 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.IOException;
import java.io.StringReader;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.ko.KoreanTokenizer.DecompoundMode;
import org.apache.lucene.analysis.ko.dict.UserDictionary;
import org.apache.lucene.tests.analysis.BaseTokenStreamTestCase;

public class TestCompoundPartOffsets extends BaseTokenStreamTestCase {

  /** The compound 세종시 is segmented into one part, 세종, its first two characters. */
  public void testSegmentationShorterThanWord() throws IOException {
    UserDictionary dict = UserDictionary.open(new StringReader("세종시 세종"));
    Tokenizer tokenizer =
        new KoreanTokenizer(newAttributeFactory(), dict, DecompoundMode.DISCARD, false);
    tokenizer.setReader(new StringReader("세종시"));
    // the part 세종 is characters [0,2) of the input
    assertTokenStreamContents(tokenizer, new String[] {"세종"}, new int[] {0}, new int[] {2});
  }
}