1 package org.apache.lucene.analysis.fa;
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.ar.ArabicLetterTokenizer;
27 * Test the Persian Normalization Filter
30 public class TestPersianNormalizationFilter extends BaseTokenStreamTestCase {
32 public void testFarsiYeh() throws IOException {
36 public void testYehBarree() throws IOException {
40 public void testKeheh() throws IOException {
41 check("کشاندن", "كشاندن");
44 public void testHehYeh() throws IOException {
45 check("كتابۀ", "كتابه");
48 public void testHehHamzaAbove() throws IOException {
49 check("كتابهٔ", "كتابه");
52 public void testHehGoal() throws IOException {
53 check("زادہ", "زاده");
56 private void check(final String input, final String expected) throws IOException {
57 ArabicLetterTokenizer tokenStream = new ArabicLetterTokenizer(TEST_VERSION_CURRENT,
58 new StringReader(input));
59 PersianNormalizationFilter filter = new PersianNormalizationFilter(
61 assertTokenStreamContents(filter, new String[]{expected});