1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
|
/*
* Licensed to Elasticsearch under one or more contributor
* license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright
* ownership. Elasticsearch licenses this file to you under
* the Apache License, Version 2.0 (the "License"); you may
* not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing,
* software distributed under the License is distributed on an
* "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
* KIND, either express or implied. See the License for the
* specific language governing permissions and limitations
* under the License.
*/
package org.elasticsearch.index.analysis;
import com.ibm.icu.text.Collator;
import com.ibm.icu.text.RuleBasedCollator;
import com.ibm.icu.util.ULocale;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.KeywordTokenizer;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.test.ESTestCase;
import java.io.IOException;
import java.io.StringReader;
import static org.elasticsearch.index.analysis.AnalysisTestUtils.createAnalysisService;
import static org.hamcrest.Matchers.equalTo;
// Tests borrowed from Solr's Icu collation key filter factory test.
public class SimpleIcuCollationTokenFilterTests extends ESTestCase {
/*
* Turkish has some funny casing.
* This test shows how you can solve this kind of thing easily with collation.
* Instead of using LowerCaseFilter, use a turkish collator with primary strength.
* Then things will sort and match correctly.
*/
public void testBasicUsage() throws Exception {
Settings settings = Settings.settingsBuilder()
.put("path.home", createTempDir())
.put("index.analysis.filter.myCollator.type", "icu_collation")
.put("index.analysis.filter.myCollator.language", "tr")
.put("index.analysis.filter.myCollator.strength", "primary")
.build();
AnalysisService analysisService = createAnalysisService(settings);
TokenFilterFactory filterFactory = analysisService.tokenFilter("myCollator");
assertCollatesToSame(filterFactory, "I WİLL USE TURKİSH CASING", "ı will use turkish casıng");
}
/*
* Test usage of the decomposition option for unicode normalization.
*/
public void testNormalization() throws IOException {
Settings settings = Settings.settingsBuilder()
.put("path.home", createTempDir())
.put("index.analysis.filter.myCollator.type", "icu_collation")
.put("index.analysis.filter.myCollator.language", "tr")
.put("index.analysis.filter.myCollator.strength", "primary")
.put("index.analysis.filter.myCollator.decomposition", "canonical")
.build();
AnalysisService analysisService = createAnalysisService(settings);
TokenFilterFactory filterFactory = analysisService.tokenFilter("myCollator");
assertCollatesToSame(filterFactory, "I W\u0049\u0307LL USE TURKİSH CASING", "ı will use turkish casıng");
}
/*
* Test secondary strength, for english case is not significant.
*/
public void testSecondaryStrength() throws IOException {
Settings settings = Settings.settingsBuilder()
.put("path.home", createTempDir())
.put("index.analysis.filter.myCollator.type", "icu_collation")
.put("index.analysis.filter.myCollator.language", "en")
.put("index.analysis.filter.myCollator.strength", "secondary")
.put("index.analysis.filter.myCollator.decomposition", "no")
.build();
AnalysisService analysisService = createAnalysisService(settings);
TokenFilterFactory filterFactory = analysisService.tokenFilter("myCollator");
assertCollatesToSame(filterFactory, "TESTING", "testing");
}
/*
* Setting alternate=shifted to shift whitespace, punctuation and symbols
* to quaternary level
*/
public void testIgnorePunctuation() throws IOException {
Settings settings = Settings.settingsBuilder()
.put("path.home", createTempDir())
.put("index.analysis.filter.myCollator.type", "icu_collation")
.put("index.analysis.filter.myCollator.language", "en")
.put("index.analysis.filter.myCollator.strength", "primary")
.put("index.analysis.filter.myCollator.alternate", "shifted")
.build();
AnalysisService analysisService = createAnalysisService(settings);
TokenFilterFactory filterFactory = analysisService.tokenFilter("myCollator");
assertCollatesToSame(filterFactory, "foo-bar", "foo bar");
}
/*
* Setting alternate=shifted and variableTop to shift whitespace, but not
* punctuation or symbols, to quaternary level
*/
public void testIgnoreWhitespace() throws IOException {
Settings settings = Settings.settingsBuilder()
.put("path.home", createTempDir())
.put("index.analysis.filter.myCollator.type", "icu_collation")
.put("index.analysis.filter.myCollator.language", "en")
.put("index.analysis.filter.myCollator.strength", "primary")
.put("index.analysis.filter.myCollator.alternate", "shifted")
.put("index.analysis.filter.myCollator.variableTop", " ")
.build();
AnalysisService analysisService = createAnalysisService(settings);
TokenFilterFactory filterFactory = analysisService.tokenFilter("myCollator");
assertCollatesToSame(filterFactory, "foo bar", "foobar");
// now assert that punctuation still matters: foo-bar < foo bar
assertCollation(filterFactory, "foo-bar", "foo bar", -1);
}
/*
* Setting numeric to encode digits with numeric value, so that
* foobar-9 sorts before foobar-10
*/
public void testNumerics() throws IOException {
Settings settings = Settings.settingsBuilder()
.put("path.home", createTempDir())
.put("index.analysis.filter.myCollator.type", "icu_collation")
.put("index.analysis.filter.myCollator.language", "en")
.put("index.analysis.filter.myCollator.numeric", "true")
.build();
AnalysisService analysisService = createAnalysisService(settings);
TokenFilterFactory filterFactory = analysisService.tokenFilter("myCollator");
assertCollation(filterFactory, "foobar-9", "foobar-10", -1);
}
/*
* Setting caseLevel=true to create an additional case level between
* secondary and tertiary
*/
public void testIgnoreAccentsButNotCase() throws IOException {
Settings settings = Settings.settingsBuilder()
.put("path.home", createTempDir())
.put("index.analysis.filter.myCollator.type", "icu_collation")
.put("index.analysis.filter.myCollator.language", "en")
.put("index.analysis.filter.myCollator.strength", "primary")
.put("index.analysis.filter.myCollator.caseLevel", "true")
.build();
AnalysisService analysisService = createAnalysisService(settings);
TokenFilterFactory filterFactory = analysisService.tokenFilter("myCollator");
assertCollatesToSame(filterFactory, "résumé", "resume");
assertCollatesToSame(filterFactory, "Résumé", "Resume");
// now assert that case still matters: resume < Resume
assertCollation(filterFactory, "resume", "Resume", -1);
}
/*
* Setting caseFirst=upper to cause uppercase strings to sort
* before lowercase ones.
*/
public void testUpperCaseFirst() throws IOException {
Settings settings = Settings.settingsBuilder()
.put("path.home", createTempDir())
.put("index.analysis.filter.myCollator.type", "icu_collation")
.put("index.analysis.filter.myCollator.language", "en")
.put("index.analysis.filter.myCollator.strength", "tertiary")
.put("index.analysis.filter.myCollator.caseFirst", "upper")
.build();
AnalysisService analysisService = createAnalysisService(settings);
TokenFilterFactory filterFactory = analysisService.tokenFilter("myCollator");
assertCollation(filterFactory, "Resume", "resume", -1);
}
/*
* For german, you might want oe to sort and match with o umlaut.
* This is not the default, but you can make a customized ruleset to do this.
*
* The default is DIN 5007-1, this shows how to tailor a collator to get DIN 5007-2 behavior.
* http://bugs.sun.com/bugdatabase/view_bug.do?bug_id=4423383
*/
public void testCustomRules() throws Exception {
RuleBasedCollator baseCollator = (RuleBasedCollator) Collator.getInstance(new ULocale("de_DE"));
String DIN5007_2_tailorings =
"& ae , a\u0308 & AE , A\u0308"+
"& oe , o\u0308 & OE , O\u0308"+
"& ue , u\u0308 & UE , u\u0308";
RuleBasedCollator tailoredCollator = new RuleBasedCollator(baseCollator.getRules() + DIN5007_2_tailorings);
String tailoredRules = tailoredCollator.getRules();
Settings settings = Settings.settingsBuilder()
.put("path.home", createTempDir())
.put("index.analysis.filter.myCollator.type", "icu_collation")
.put("index.analysis.filter.myCollator.rules", tailoredRules)
.put("index.analysis.filter.myCollator.strength", "primary")
.build();
AnalysisService analysisService = createAnalysisService(settings);
TokenFilterFactory filterFactory = analysisService.tokenFilter("myCollator");
assertCollatesToSame(filterFactory, "Töne", "Toene");
}
private void assertCollatesToSame(TokenFilterFactory factory, String string1, String string2) throws IOException {
assertCollation(factory, string1, string2, 0);
}
private void assertCollation(TokenFilterFactory factory, String string1, String string2, int comparison) throws IOException {
Tokenizer tokenizer = new KeywordTokenizer();
tokenizer.setReader(new StringReader(string1));
TokenStream stream1 = factory.create(tokenizer);
tokenizer = new KeywordTokenizer();
tokenizer.setReader(new StringReader(string2));
TokenStream stream2 = factory.create(tokenizer);
assertCollation(stream1, stream2, comparison);
}
private void assertCollation(TokenStream stream1, TokenStream stream2, int comparison) throws IOException {
CharTermAttribute term1 = stream1.addAttribute(CharTermAttribute.class);
CharTermAttribute term2 = stream2.addAttribute(CharTermAttribute.class);
stream1.reset();
stream2.reset();
assertThat(stream1.incrementToken(), equalTo(true));
assertThat(stream2.incrementToken(), equalTo(true));
assertThat(Integer.signum(term1.toString().compareTo(term2.toString())), equalTo(Integer.signum(comparison)));
assertThat(stream1.incrementToken(), equalTo(false));
assertThat(stream2.incrementToken(), equalTo(false));
stream1.end();
stream2.end();
stream1.close();
stream2.close();
}
}
|
