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;
31 public class TestHindiStemmer extends BaseTokenStreamTestCase {
33 * Test masc noun inflections
35 public void testMasculineNouns() throws IOException {
38 check("लडकों", "लडक");
41 check("गुरुओं", "गुर");
43 check("दोस्त", "दोस्त");
44 check("दोस्तों", "दोस्त");
48 * Test feminine noun inflections
50 public void testFeminineNouns() throws IOException {
52 check("लडकियों", "लडक");
54 check("किताब", "किताब");
55 check("किताबें", "किताब");
56 check("किताबों", "किताब");
58 check("आध्यापीका", "आध्यापीक");
59 check("आध्यापीकाएं", "आध्यापीक");
60 check("आध्यापीकाओं", "आध्यापीक");
64 * Test some verb forms
66 public void testVerbs() throws IOException {
74 * From the paper: since the suffix list for verbs includes AI, awA and anI,
75 * additional suffixes had to be added to the list for noun/adjectives
76 * ending with these endings.
78 public void testExceptions() throws IOException {
79 check("कठिनाइयां", "कठिन");
80 check("कठिन", "कठिन");
83 private void check(String input, String output) throws IOException {
84 Tokenizer tokenizer = new MockTokenizer(new StringReader(input), MockTokenizer.WHITESPACE, false);
85 TokenFilter tf = new HindiStemFilter(tokenizer);
86 assertTokenStreamContents(tf, new String[] { output });