1 package org.apache.lucene.analysis.snowball;
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 org.apache.lucene.analysis.BaseTokenStreamTestCase;
21 import org.apache.lucene.analysis.Analyzer;
22 import org.apache.lucene.index.Payload;
23 import org.apache.lucene.analysis.TokenStream;
24 import org.apache.lucene.analysis.standard.StandardAnalyzer;
25 import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
26 import org.apache.lucene.analysis.tokenattributes.FlagsAttribute;
27 import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
28 import org.apache.lucene.analysis.tokenattributes.PayloadAttribute;
29 import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
30 import org.apache.lucene.analysis.tokenattributes.TypeAttribute;
31 import org.apache.lucene.util.Version;
33 public class TestSnowball extends BaseTokenStreamTestCase {
35 public void testEnglish() throws Exception {
36 Analyzer a = new SnowballAnalyzer(TEST_VERSION_CURRENT, "English");
37 assertAnalyzesTo(a, "he abhorred accents",
38 new String[]{"he", "abhor", "accent"});
41 public void testStopwords() throws Exception {
42 Analyzer a = new SnowballAnalyzer(TEST_VERSION_CURRENT, "English",
43 StandardAnalyzer.STOP_WORDS_SET);
44 assertAnalyzesTo(a, "the quick brown fox jumped",
45 new String[]{"quick", "brown", "fox", "jump"});
49 * Test english lowercasing. Test both cases (pre-3.1 and post-3.1) to ensure
50 * we lowercase I correct for non-Turkish languages in either case.
52 public void testEnglishLowerCase() throws Exception {
53 Analyzer a = new SnowballAnalyzer(TEST_VERSION_CURRENT, "English");
54 assertAnalyzesTo(a, "cryogenic", new String[] { "cryogen" });
55 assertAnalyzesTo(a, "CRYOGENIC", new String[] { "cryogen" });
57 Analyzer b = new SnowballAnalyzer(Version.LUCENE_30, "English");
58 assertAnalyzesTo(b, "cryogenic", new String[] { "cryogen" });
59 assertAnalyzesTo(b, "CRYOGENIC", new String[] { "cryogen" });
63 * Test turkish lowercasing
65 public void testTurkish() throws Exception {
66 Analyzer a = new SnowballAnalyzer(TEST_VERSION_CURRENT, "Turkish");
68 assertAnalyzesTo(a, "ağacı", new String[] { "ağaç" });
69 assertAnalyzesTo(a, "AĞACI", new String[] { "ağaç" });
73 * Test turkish lowercasing (old buggy behavior)
74 * @deprecated Remove this when support for 3.0 indexes is no longer required
77 public void testTurkishBWComp() throws Exception {
78 Analyzer a = new SnowballAnalyzer(Version.LUCENE_30, "Turkish");
79 // AĞACI in turkish lowercases to ağacı, but with lowercase filter ağaci.
80 // this fails due to wrong casing, because the stemmer
81 // will only remove -ı, not -i
82 assertAnalyzesTo(a, "ağacı", new String[] { "ağaç" });
83 assertAnalyzesTo(a, "AĞACI", new String[] { "ağaci" });
87 public void testReusableTokenStream() throws Exception {
88 Analyzer a = new SnowballAnalyzer(TEST_VERSION_CURRENT, "English");
89 assertAnalyzesToReuse(a, "he abhorred accents",
90 new String[]{"he", "abhor", "accent"});
91 assertAnalyzesToReuse(a, "she abhorred him",
92 new String[]{"she", "abhor", "him"});
95 public void testFilterTokens() throws Exception {
96 SnowballFilter filter = new SnowballFilter(new TestTokenStream(), "English");
97 CharTermAttribute termAtt = filter.getAttribute(CharTermAttribute.class);
98 OffsetAttribute offsetAtt = filter.getAttribute(OffsetAttribute.class);
99 TypeAttribute typeAtt = filter.getAttribute(TypeAttribute.class);
100 PayloadAttribute payloadAtt = filter.getAttribute(PayloadAttribute.class);
101 PositionIncrementAttribute posIncAtt = filter.getAttribute(PositionIncrementAttribute.class);
102 FlagsAttribute flagsAtt = filter.getAttribute(FlagsAttribute.class);
104 filter.incrementToken();
106 assertEquals("accent", termAtt.toString());
107 assertEquals(2, offsetAtt.startOffset());
108 assertEquals(7, offsetAtt.endOffset());
109 assertEquals("wrd", typeAtt.type());
110 assertEquals(3, posIncAtt.getPositionIncrement());
111 assertEquals(77, flagsAtt.getFlags());
112 assertEquals(new Payload(new byte[]{0,1,2,3}), payloadAtt.getPayload());
115 private final class TestTokenStream extends TokenStream {
116 private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
117 private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
118 private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class);
119 private final PayloadAttribute payloadAtt = addAttribute(PayloadAttribute.class);
120 private final PositionIncrementAttribute posIncAtt = addAttribute(PositionIncrementAttribute.class);
121 private final FlagsAttribute flagsAtt = addAttribute(FlagsAttribute.class);
128 public boolean incrementToken() {
130 termAtt.setEmpty().append("accents");
131 offsetAtt.setOffset(2, 7);
132 typeAtt.setType("wrd");
133 posIncAtt.setPositionIncrement(3);
134 payloadAtt.setPayload(new Payload(new byte[]{0,1,2,3}));
135 flagsAtt.setFlags(77);