1 package org.apache.lucene.analysis.in;
4 * Licensed to the Apache Software Foundation (ASF) under one or more
5 * contributor license agreements. See the NOTICE file distributed with
6 * this work for additional information regarding copyright ownership.
7 * The ASF licenses this file to You under the Apache License, Version 2.0
8 * (the "License"); you may not use this file except in compliance with
9 * the License. You may obtain a copy of the License at
11 * http://www.apache.org/licenses/LICENSE-2.0
13 * Unless required by applicable law or agreed to in writing, software
14 * distributed under the License is distributed on an "AS IS" BASIS,
15 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
16 * See the License for the specific language governing permissions and
17 * limitations under the License.
20 import java.io.IOException;
21 import java.io.StringReader;
23 import org.apache.lucene.analysis.BaseTokenStreamTestCase;
24 import org.apache.lucene.analysis.MockTokenizer;
25 import org.apache.lucene.analysis.TokenFilter;
26 import org.apache.lucene.analysis.Tokenizer;
29 * Test IndicNormalizer
31 public class TestIndicNormalizer extends BaseTokenStreamTestCase {
33 * Test some basic normalization
35 public void testBasics() throws IOException {
36 check("अाॅअाॅ", "ऑऑ");
37 check("अाॆअाॆ", "ऒऒ");
38 check("अाेअाे", "ओओ");
39 check("अाैअाै", "औऔ");
46 private void check(String input, String output) throws IOException {
47 Tokenizer tokenizer = new MockTokenizer(new StringReader(input), MockTokenizer.WHITESPACE, false);;
48 TokenFilter tf = new IndicNormalizationFilter(tokenizer);
49 assertTokenStreamContents(tf, new String[] { output });