1
package org.apache.lucene.analysis;
4
* Copyright 2005 The Apache Software Foundation
6
* Licensed under the Apache License, Version 2.0 (the "License");
7
* you may not use this file except in compliance with the License.
8
* You may obtain a copy of the License at
10
* http://www.apache.org/licenses/LICENSE-2.0
12
* Unless required by applicable law or agreed to in writing, software
13
* distributed under the License is distributed on an "AS IS" BASIS,
14
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15
* See the License for the specific language governing permissions and
16
* limitations under the License.
19
import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
20
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
21
import org.apache.lucene.util.English;
22
import org.apache.lucene.util.Version;
24
import java.io.IOException;
25
import java.io.StringReader;
26
import java.util.ArrayList;
27
import java.util.Arrays;
29
import java.util.HashSet;
31
import org.apache.lucene.analysis.BaseTokenStreamTestCase;
32
import org.apache.lucene.analysis.MockTokenizer;
33
import org.apache.lucene.analysis.TokenStream;
35
public class TestStopFilter extends BaseTokenStreamTestCase {
37
// other StopFilter functionality is already tested by TestStopAnalyzer
39
public void testExactCase() throws IOException {
40
StringReader reader = new StringReader("Now is The Time");
41
Set<String> stopWords = new HashSet<String>(Arrays.asList("is", "the", "Time"));
42
TokenStream stream = new StopFilter(TEST_VERSION_CURRENT, new MockTokenizer(reader, MockTokenizer.WHITESPACE, false), stopWords, false);
43
assertTokenStreamContents(stream, new String[] { "Now", "The" });
46
public void testIgnoreCase() throws IOException {
47
StringReader reader = new StringReader("Now is The Time");
48
Set<Object> stopWords = new HashSet<Object>(Arrays.asList( "is", "the", "Time" ));
49
TokenStream stream = new StopFilter(TEST_VERSION_CURRENT, new MockTokenizer(reader, MockTokenizer.WHITESPACE, false), stopWords, true);
50
assertTokenStreamContents(stream, new String[] { "Now" });
53
public void testStopFilt() throws IOException {
54
StringReader reader = new StringReader("Now is The Time");
55
String[] stopWords = new String[] { "is", "the", "Time" };
56
Set<Object> stopSet = StopFilter.makeStopSet(TEST_VERSION_CURRENT, stopWords);
57
TokenStream stream = new StopFilter(TEST_VERSION_CURRENT, new MockTokenizer(reader, MockTokenizer.WHITESPACE, false), stopSet);
58
assertTokenStreamContents(stream, new String[] { "Now", "The" });
62
* Test Position increments applied by StopFilter with and without enabling this option.
64
public void testStopPositons() throws IOException {
65
StringBuilder sb = new StringBuilder();
66
ArrayList<String> a = new ArrayList<String>();
67
for (int i=0; i<20; i++) {
68
String w = English.intToEnglish(i).trim();
69
sb.append(w).append(" ");
70
if (i%3 != 0) a.add(w);
73
String stopWords[] = a.toArray(new String[0]);
74
for (int i=0; i<a.size(); i++) log("Stop: "+stopWords[i]);
75
Set<Object> stopSet = StopFilter.makeStopSet(TEST_VERSION_CURRENT, stopWords);
77
StringReader reader = new StringReader(sb.toString());
78
StopFilter stpf = new StopFilter(Version.LUCENE_24, new MockTokenizer(reader, MockTokenizer.WHITESPACE, false), stopSet);
79
doTestStopPositons(stpf,true);
81
reader = new StringReader(sb.toString());
82
stpf = new StopFilter(TEST_VERSION_CURRENT, new MockTokenizer(reader, MockTokenizer.WHITESPACE, false), stopSet);
83
doTestStopPositons(stpf,false);
84
// with increments, concatenating two stop filters
85
ArrayList<String> a0 = new ArrayList<String>();
86
ArrayList<String> a1 = new ArrayList<String>();
87
for (int i=0; i<a.size(); i++) {
94
String stopWords0[] = a0.toArray(new String[0]);
95
for (int i=0; i<a0.size(); i++) log("Stop0: "+stopWords0[i]);
96
String stopWords1[] = a1.toArray(new String[0]);
97
for (int i=0; i<a1.size(); i++) log("Stop1: "+stopWords1[i]);
98
Set<Object> stopSet0 = StopFilter.makeStopSet(TEST_VERSION_CURRENT, stopWords0);
99
Set<Object> stopSet1 = StopFilter.makeStopSet(TEST_VERSION_CURRENT, stopWords1);
100
reader = new StringReader(sb.toString());
101
StopFilter stpf0 = new StopFilter(TEST_VERSION_CURRENT, new MockTokenizer(reader, MockTokenizer.WHITESPACE, false), stopSet0); // first part of the set
102
stpf0.setEnablePositionIncrements(true);
103
StopFilter stpf01 = new StopFilter(TEST_VERSION_CURRENT, stpf0, stopSet1); // two stop filters concatenated!
104
doTestStopPositons(stpf01,true);
107
private void doTestStopPositons(StopFilter stpf, boolean enableIcrements) throws IOException {
108
log("---> test with enable-increments-"+(enableIcrements?"enabled":"disabled"));
109
stpf.setEnablePositionIncrements(enableIcrements);
110
CharTermAttribute termAtt = stpf.getAttribute(CharTermAttribute.class);
111
PositionIncrementAttribute posIncrAtt = stpf.getAttribute(PositionIncrementAttribute.class);
113
for (int i=0; i<20; i+=3) {
114
assertTrue(stpf.incrementToken());
115
log("Token "+i+": "+stpf);
116
String w = English.intToEnglish(i).trim();
117
assertEquals("expecting token "+i+" to be "+w,w,termAtt.toString());
118
assertEquals("all but first token must have position increment of 3",enableIcrements?(i==0?1:3):1,posIncrAtt.getPositionIncrement());
120
assertFalse(stpf.incrementToken());
125
// print debug info depending on VERBOSE
126
private static void log(String s) {
128
System.out.println(s);