1 package org.apache.lucene.analysis.hi;
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 HindiNormalizer
31 public class TestHindiNormalizer extends BaseTokenStreamTestCase {
33 * Test some basic normalization, with an example from the paper.
35 public void testBasics() throws IOException {
36 check("अँगरेज़ी", "अंगरेजि");
37 check("अँगरेजी", "अंगरेजि");
38 check("अँग्रेज़ी", "अंगरेजि");
39 check("अँग्रेजी", "अंगरेजि");
40 check("अंगरेज़ी", "अंगरेजि");
41 check("अंगरेजी", "अंगरेजि");
42 check("अंग्रेज़ी", "अंगरेजि");
43 check("अंग्रेजी", "अंगरेजि");
46 public void testDecompositions() throws IOException {
48 check("क़िताब", "किताब");
51 // some other composed nukta forms
52 check("ऱऴख़ग़ड़ढ़य़", "रळखगडढय");
53 // removal of format (ZWJ/ZWNJ)
54 check("शार्मा", "शारमा");
55 check("शार्मा", "शारमा");
57 check("ॅॆॉॊऍऎऑऒ\u0972", "ेेोोएएओओअ");
59 check("आईऊॠॡऐऔीूॄॣैौ", "अइउऋऌएओिुृॢेो");
61 private void check(String input, String output) throws IOException {
62 Tokenizer tokenizer = new MockTokenizer(new StringReader(input), MockTokenizer.WHITESPACE, false);
63 TokenFilter tf = new HindiNormalizationFilter(tokenizer);
64 assertTokenStreamContents(tf, new String[] { output });