/*
 * 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.icu.segmentation;

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

public class TestMyanmarSyllableModifierLetter extends LuceneTestCase {

  public void testShanReduplicationMarkIsKept() throws Exception {
    Tokenizer t = new ICUTokenizer(new DefaultICUTokenizerConfig(true, false));
    CharTermAttribute term = t.addAttribute(CharTermAttribute.class);
    t.setReader(new StringReader("\u1000\uA9E6"));
    StringBuilder tokens = new StringBuilder();
    t.reset();
    while (t.incrementToken()) {
      tokens.append(term);
    }
    t.end();
    t.close();
    // expected: the tokens keep U+A9E6, as word mode does ([\u1000\uA9E6]); actual: only [\u1000]
    assertEquals("\u1000\uA9E6", tokens.toString());
  }
}